{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "global_step": 1608, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 3.0769230769230774e-07, "loss": 0.7856, "step": 1 }, { "epoch": 0.0, "learning_rate": 6.153846153846155e-07, "loss": 0.786, "step": 2 }, { "epoch": 0.01, "learning_rate": 9.230769230769232e-07, "loss": 0.679, "step": 3 }, { "epoch": 0.01, "learning_rate": 1.230769230769231e-06, "loss": 0.692, "step": 4 }, { "epoch": 0.01, "learning_rate": 1.5384615384615387e-06, "loss": 0.6971, "step": 5 }, { "epoch": 0.01, "learning_rate": 1.8461538461538465e-06, "loss": 0.6911, "step": 6 }, { "epoch": 0.01, "learning_rate": 2.153846153846154e-06, "loss": 0.663, "step": 7 }, { "epoch": 0.01, "learning_rate": 2.461538461538462e-06, "loss": 0.6721, "step": 8 }, { "epoch": 0.02, "learning_rate": 2.7692307692307697e-06, "loss": 0.6357, "step": 9 }, { "epoch": 0.02, "learning_rate": 3.0769230769230774e-06, "loss": 0.6395, "step": 10 }, { "epoch": 0.02, "learning_rate": 3.384615384615385e-06, "loss": 0.6251, "step": 11 }, { "epoch": 0.02, "learning_rate": 3.692307692307693e-06, "loss": 0.6247, "step": 12 }, { "epoch": 0.02, "learning_rate": 4.000000000000001e-06, "loss": 0.6278, "step": 13 }, { "epoch": 0.03, "learning_rate": 4.307692307692308e-06, "loss": 0.6028, "step": 14 }, { "epoch": 0.03, "learning_rate": 4.615384615384616e-06, "loss": 0.6283, "step": 15 }, { "epoch": 0.03, "learning_rate": 4.923076923076924e-06, "loss": 0.5906, "step": 16 }, { "epoch": 0.03, "learning_rate": 5.230769230769232e-06, "loss": 0.5916, "step": 17 }, { "epoch": 0.03, "learning_rate": 5.538461538461539e-06, "loss": 0.5868, "step": 18 }, { "epoch": 0.04, "learning_rate": 5.846153846153847e-06, "loss": 0.6087, "step": 19 }, { "epoch": 0.04, "learning_rate": 6.153846153846155e-06, "loss": 0.6172, "step": 20 }, { "epoch": 0.04, "learning_rate": 6.461538461538463e-06, "loss": 0.6048, "step": 21 }, { "epoch": 0.04, "learning_rate": 6.76923076923077e-06, "loss": 0.6075, "step": 22 }, { "epoch": 0.04, "learning_rate": 7.076923076923078e-06, "loss": 0.6053, "step": 23 }, { "epoch": 0.04, "learning_rate": 7.384615384615386e-06, "loss": 0.5914, "step": 24 }, { "epoch": 0.05, "learning_rate": 7.692307692307694e-06, "loss": 0.5933, "step": 25 }, { "epoch": 0.05, "learning_rate": 8.000000000000001e-06, "loss": 0.564, "step": 26 }, { "epoch": 0.05, "learning_rate": 8.307692307692309e-06, "loss": 0.5566, "step": 27 }, { "epoch": 0.05, "learning_rate": 8.615384615384617e-06, "loss": 0.5935, "step": 28 }, { "epoch": 0.05, "learning_rate": 8.923076923076925e-06, "loss": 0.5778, "step": 29 }, { "epoch": 0.06, "learning_rate": 9.230769230769232e-06, "loss": 0.5658, "step": 30 }, { "epoch": 0.06, "learning_rate": 9.53846153846154e-06, "loss": 0.5945, "step": 31 }, { "epoch": 0.06, "learning_rate": 9.846153846153848e-06, "loss": 0.5691, "step": 32 }, { "epoch": 0.06, "learning_rate": 1.0153846153846154e-05, "loss": 0.5716, "step": 33 }, { "epoch": 0.06, "learning_rate": 1.0461538461538463e-05, "loss": 0.5659, "step": 34 }, { "epoch": 0.07, "learning_rate": 1.076923076923077e-05, "loss": 0.5747, "step": 35 }, { "epoch": 0.07, "learning_rate": 1.1076923076923079e-05, "loss": 0.5812, "step": 36 }, { "epoch": 0.07, "learning_rate": 1.1384615384615385e-05, "loss": 0.5545, "step": 37 }, { "epoch": 0.07, "learning_rate": 1.1692307692307694e-05, "loss": 0.5445, "step": 38 }, { "epoch": 0.07, "learning_rate": 1.2e-05, "loss": 0.5513, "step": 39 }, { "epoch": 0.07, "learning_rate": 1.230769230769231e-05, "loss": 0.5447, "step": 40 }, { "epoch": 0.08, "learning_rate": 1.2615384615384616e-05, "loss": 0.5714, "step": 41 }, { "epoch": 0.08, "learning_rate": 1.2923076923076925e-05, "loss": 0.5444, "step": 42 }, { "epoch": 0.08, "learning_rate": 1.3230769230769231e-05, "loss": 0.5682, "step": 43 }, { "epoch": 0.08, "learning_rate": 1.353846153846154e-05, "loss": 0.55, "step": 44 }, { "epoch": 0.08, "learning_rate": 1.3846153846153847e-05, "loss": 0.5543, "step": 45 }, { "epoch": 0.09, "learning_rate": 1.4153846153846156e-05, "loss": 0.5692, "step": 46 }, { "epoch": 0.09, "learning_rate": 1.4461538461538462e-05, "loss": 0.5613, "step": 47 }, { "epoch": 0.09, "learning_rate": 1.4769230769230772e-05, "loss": 0.5727, "step": 48 }, { "epoch": 0.09, "learning_rate": 1.5076923076923078e-05, "loss": 0.5557, "step": 49 }, { "epoch": 0.09, "learning_rate": 1.5384615384615387e-05, "loss": 0.5252, "step": 50 }, { "epoch": 0.1, "learning_rate": 1.5692307692307693e-05, "loss": 0.5369, "step": 51 }, { "epoch": 0.1, "learning_rate": 1.6000000000000003e-05, "loss": 0.5389, "step": 52 }, { "epoch": 0.1, "learning_rate": 1.630769230769231e-05, "loss": 0.5374, "step": 53 }, { "epoch": 0.1, "learning_rate": 1.6615384615384618e-05, "loss": 0.5702, "step": 54 }, { "epoch": 0.1, "learning_rate": 1.6923076923076924e-05, "loss": 0.5602, "step": 55 }, { "epoch": 0.1, "learning_rate": 1.7230769230769234e-05, "loss": 0.549, "step": 56 }, { "epoch": 0.11, "learning_rate": 1.753846153846154e-05, "loss": 0.5496, "step": 57 }, { "epoch": 0.11, "learning_rate": 1.784615384615385e-05, "loss": 0.5779, "step": 58 }, { "epoch": 0.11, "learning_rate": 1.8153846153846155e-05, "loss": 0.5565, "step": 59 }, { "epoch": 0.11, "learning_rate": 1.8461538461538465e-05, "loss": 0.5402, "step": 60 }, { "epoch": 0.11, "learning_rate": 1.876923076923077e-05, "loss": 0.537, "step": 61 }, { "epoch": 0.12, "learning_rate": 1.907692307692308e-05, "loss": 0.55, "step": 62 }, { "epoch": 0.12, "learning_rate": 1.9384615384615386e-05, "loss": 0.5635, "step": 63 }, { "epoch": 0.12, "learning_rate": 1.9692307692307696e-05, "loss": 0.5228, "step": 64 }, { "epoch": 0.12, "learning_rate": 2e-05, "loss": 0.5343, "step": 65 }, { "epoch": 0.12, "learning_rate": 1.999997927293795e-05, "loss": 0.5395, "step": 66 }, { "epoch": 0.12, "learning_rate": 1.999991709183772e-05, "loss": 0.5505, "step": 67 }, { "epoch": 0.13, "learning_rate": 1.999981345695707e-05, "loss": 0.5367, "step": 68 }, { "epoch": 0.13, "learning_rate": 1.999966836872562e-05, "loss": 0.5375, "step": 69 }, { "epoch": 0.13, "learning_rate": 1.9999481827744813e-05, "loss": 0.5273, "step": 70 }, { "epoch": 0.13, "learning_rate": 1.9999253834787942e-05, "loss": 0.5691, "step": 71 }, { "epoch": 0.13, "learning_rate": 1.999898439080013e-05, "loss": 0.5214, "step": 72 }, { "epoch": 0.14, "learning_rate": 1.9998673496898334e-05, "loss": 0.5654, "step": 73 }, { "epoch": 0.14, "learning_rate": 1.999832115437134e-05, "loss": 0.5297, "step": 74 }, { "epoch": 0.14, "learning_rate": 1.999792736467975e-05, "loss": 0.5371, "step": 75 }, { "epoch": 0.14, "learning_rate": 1.9997492129455983e-05, "loss": 0.5529, "step": 76 }, { "epoch": 0.14, "learning_rate": 1.999701545050427e-05, "loss": 0.5166, "step": 77 }, { "epoch": 0.15, "learning_rate": 1.9996497329800646e-05, "loss": 0.5416, "step": 78 }, { "epoch": 0.15, "learning_rate": 1.999593776949293e-05, "loss": 0.5221, "step": 79 }, { "epoch": 0.15, "learning_rate": 1.9995336771900732e-05, "loss": 0.5494, "step": 80 }, { "epoch": 0.15, "learning_rate": 1.9994694339515434e-05, "loss": 0.5366, "step": 81 }, { "epoch": 0.15, "learning_rate": 1.9994010475000186e-05, "loss": 0.5453, "step": 82 }, { "epoch": 0.15, "learning_rate": 1.9993285181189884e-05, "loss": 0.5338, "step": 83 }, { "epoch": 0.16, "learning_rate": 1.999251846109117e-05, "loss": 0.5406, "step": 84 }, { "epoch": 0.16, "learning_rate": 1.9991710317882423e-05, "loss": 0.5535, "step": 85 }, { "epoch": 0.16, "learning_rate": 1.9990860754913722e-05, "loss": 0.5346, "step": 86 }, { "epoch": 0.16, "learning_rate": 1.998996977570686e-05, "loss": 0.5402, "step": 87 }, { "epoch": 0.16, "learning_rate": 1.9989037383955308e-05, "loss": 0.5407, "step": 88 }, { "epoch": 0.17, "learning_rate": 1.9988063583524218e-05, "loss": 0.5423, "step": 89 }, { "epoch": 0.17, "learning_rate": 1.99870483784504e-05, "loss": 0.532, "step": 90 }, { "epoch": 0.17, "learning_rate": 1.9985991772942284e-05, "loss": 0.5059, "step": 91 }, { "epoch": 0.17, "learning_rate": 1.9984893771379945e-05, "loss": 0.546, "step": 92 }, { "epoch": 0.17, "learning_rate": 1.9983754378315053e-05, "loss": 0.5629, "step": 93 }, { "epoch": 0.18, "learning_rate": 1.9982573598470858e-05, "loss": 0.536, "step": 94 }, { "epoch": 0.18, "learning_rate": 1.9981351436742186e-05, "loss": 0.5165, "step": 95 }, { "epoch": 0.18, "learning_rate": 1.998008789819539e-05, "loss": 0.5376, "step": 96 }, { "epoch": 0.18, "learning_rate": 1.9978782988068368e-05, "loss": 0.5358, "step": 97 }, { "epoch": 0.18, "learning_rate": 1.9977436711770508e-05, "loss": 0.5231, "step": 98 }, { "epoch": 0.18, "learning_rate": 1.997604907488268e-05, "loss": 0.5137, "step": 99 }, { "epoch": 0.19, "learning_rate": 1.9974620083157214e-05, "loss": 0.5319, "step": 100 }, { "epoch": 0.19, "learning_rate": 1.997314974251786e-05, "loss": 0.5102, "step": 101 }, { "epoch": 0.19, "learning_rate": 1.99716380590598e-05, "loss": 0.5276, "step": 102 }, { "epoch": 0.19, "learning_rate": 1.9970085039049577e-05, "loss": 0.5393, "step": 103 }, { "epoch": 0.19, "learning_rate": 1.9968490688925103e-05, "loss": 0.5105, "step": 104 }, { "epoch": 0.2, "learning_rate": 1.9966855015295613e-05, "loss": 0.5053, "step": 105 }, { "epoch": 0.2, "learning_rate": 1.996517802494165e-05, "loss": 0.5018, "step": 106 }, { "epoch": 0.2, "learning_rate": 1.9963459724815035e-05, "loss": 0.5077, "step": 107 }, { "epoch": 0.2, "learning_rate": 1.996170012203883e-05, "loss": 0.5324, "step": 108 }, { "epoch": 0.2, "learning_rate": 1.9959899223907304e-05, "loss": 0.538, "step": 109 }, { "epoch": 0.21, "learning_rate": 1.9958057037885934e-05, "loss": 0.5143, "step": 110 }, { "epoch": 0.21, "learning_rate": 1.9956173571611335e-05, "loss": 0.5203, "step": 111 }, { "epoch": 0.21, "learning_rate": 1.9954248832891255e-05, "loss": 0.5161, "step": 112 }, { "epoch": 0.21, "learning_rate": 1.995228282970453e-05, "loss": 0.5093, "step": 113 }, { "epoch": 0.21, "learning_rate": 1.9950275570201048e-05, "loss": 0.5431, "step": 114 }, { "epoch": 0.21, "learning_rate": 1.9948227062701733e-05, "loss": 0.504, "step": 115 }, { "epoch": 0.22, "learning_rate": 1.9946137315698493e-05, "loss": 0.503, "step": 116 }, { "epoch": 0.22, "learning_rate": 1.994400633785419e-05, "loss": 0.5419, "step": 117 }, { "epoch": 0.22, "learning_rate": 1.9941834138002605e-05, "loss": 0.5158, "step": 118 }, { "epoch": 0.22, "learning_rate": 1.9939620725148402e-05, "loss": 0.5286, "step": 119 }, { "epoch": 0.22, "learning_rate": 1.9937366108467092e-05, "loss": 0.5019, "step": 120 }, { "epoch": 0.23, "learning_rate": 1.9935070297304993e-05, "loss": 0.5188, "step": 121 }, { "epoch": 0.23, "learning_rate": 1.9932733301179183e-05, "loss": 0.5411, "step": 122 }, { "epoch": 0.23, "learning_rate": 1.993035512977748e-05, "loss": 0.5054, "step": 123 }, { "epoch": 0.23, "learning_rate": 1.9927935792958383e-05, "loss": 0.4931, "step": 124 }, { "epoch": 0.23, "learning_rate": 1.9925475300751044e-05, "loss": 0.5024, "step": 125 }, { "epoch": 0.24, "learning_rate": 1.9922973663355213e-05, "loss": 0.5323, "step": 126 }, { "epoch": 0.24, "learning_rate": 1.992043089114121e-05, "loss": 0.5114, "step": 127 }, { "epoch": 0.24, "learning_rate": 1.991784699464988e-05, "loss": 0.5169, "step": 128 }, { "epoch": 0.24, "learning_rate": 1.991522198459253e-05, "loss": 0.5203, "step": 129 }, { "epoch": 0.24, "learning_rate": 1.9912555871850914e-05, "loss": 0.5135, "step": 130 }, { "epoch": 0.24, "learning_rate": 1.9909848667477173e-05, "loss": 0.5033, "step": 131 }, { "epoch": 0.25, "learning_rate": 1.990710038269378e-05, "loss": 0.5226, "step": 132 }, { "epoch": 0.25, "learning_rate": 1.990431102889351e-05, "loss": 0.5276, "step": 133 }, { "epoch": 0.25, "learning_rate": 1.9901480617639384e-05, "loss": 0.5178, "step": 134 }, { "epoch": 0.25, "learning_rate": 1.9898609160664628e-05, "loss": 0.4969, "step": 135 }, { "epoch": 0.25, "learning_rate": 1.989569666987261e-05, "loss": 0.4847, "step": 136 }, { "epoch": 0.26, "learning_rate": 1.989274315733681e-05, "loss": 0.504, "step": 137 }, { "epoch": 0.26, "learning_rate": 1.9889748635300753e-05, "loss": 0.4992, "step": 138 }, { "epoch": 0.26, "learning_rate": 1.988671311617797e-05, "loss": 0.5221, "step": 139 }, { "epoch": 0.26, "learning_rate": 1.988363661255194e-05, "loss": 0.529, "step": 140 }, { "epoch": 0.26, "learning_rate": 1.9880519137176036e-05, "loss": 0.515, "step": 141 }, { "epoch": 0.26, "learning_rate": 1.987736070297348e-05, "loss": 0.5163, "step": 142 }, { "epoch": 0.27, "learning_rate": 1.9874161323037285e-05, "loss": 0.5019, "step": 143 }, { "epoch": 0.27, "learning_rate": 1.98709210106302e-05, "loss": 0.5047, "step": 144 }, { "epoch": 0.27, "learning_rate": 1.986763977918466e-05, "loss": 0.5227, "step": 145 }, { "epoch": 0.27, "learning_rate": 1.9864317642302714e-05, "loss": 0.5133, "step": 146 }, { "epoch": 0.27, "learning_rate": 1.9860954613755994e-05, "loss": 0.5273, "step": 147 }, { "epoch": 0.28, "learning_rate": 1.9857550707485642e-05, "loss": 0.5193, "step": 148 }, { "epoch": 0.28, "learning_rate": 1.9854105937602254e-05, "loss": 0.5203, "step": 149 }, { "epoch": 0.28, "learning_rate": 1.985062031838582e-05, "loss": 0.4959, "step": 150 }, { "epoch": 0.28, "learning_rate": 1.984709386428567e-05, "loss": 0.5069, "step": 151 }, { "epoch": 0.28, "learning_rate": 1.9843526589920408e-05, "loss": 0.5144, "step": 152 }, { "epoch": 0.29, "learning_rate": 1.983991851007786e-05, "loss": 0.5213, "step": 153 }, { "epoch": 0.29, "learning_rate": 1.9836269639715003e-05, "loss": 0.5243, "step": 154 }, { "epoch": 0.29, "learning_rate": 1.983257999395791e-05, "loss": 0.5027, "step": 155 }, { "epoch": 0.29, "learning_rate": 1.9828849588101687e-05, "loss": 0.5063, "step": 156 }, { "epoch": 0.29, "learning_rate": 1.98250784376104e-05, "loss": 0.5195, "step": 157 }, { "epoch": 0.29, "learning_rate": 1.982126655811703e-05, "loss": 0.5047, "step": 158 }, { "epoch": 0.3, "learning_rate": 1.9817413965423383e-05, "loss": 0.5035, "step": 159 }, { "epoch": 0.3, "learning_rate": 1.9813520675500045e-05, "loss": 0.5076, "step": 160 }, { "epoch": 0.3, "learning_rate": 1.980958670448631e-05, "loss": 0.4913, "step": 161 }, { "epoch": 0.3, "learning_rate": 1.980561206869011e-05, "loss": 0.5036, "step": 162 }, { "epoch": 0.3, "learning_rate": 1.9801596784587957e-05, "loss": 0.5053, "step": 163 }, { "epoch": 0.31, "learning_rate": 1.9797540868824846e-05, "loss": 0.4991, "step": 164 }, { "epoch": 0.31, "learning_rate": 1.9793444338214228e-05, "loss": 0.4917, "step": 165 }, { "epoch": 0.31, "learning_rate": 1.978930720973791e-05, "loss": 0.495, "step": 166 }, { "epoch": 0.31, "learning_rate": 1.9785129500546e-05, "loss": 0.4924, "step": 167 }, { "epoch": 0.31, "learning_rate": 1.978091122795682e-05, "loss": 0.4932, "step": 168 }, { "epoch": 0.32, "learning_rate": 1.977665240945685e-05, "loss": 0.4923, "step": 169 }, { "epoch": 0.32, "learning_rate": 1.9772353062700654e-05, "loss": 0.5103, "step": 170 }, { "epoch": 0.32, "learning_rate": 1.9768013205510793e-05, "loss": 0.4927, "step": 171 }, { "epoch": 0.32, "learning_rate": 1.9763632855877763e-05, "loss": 0.4841, "step": 172 }, { "epoch": 0.32, "learning_rate": 1.9759212031959927e-05, "loss": 0.5175, "step": 173 }, { "epoch": 0.32, "learning_rate": 1.975475075208342e-05, "loss": 0.4898, "step": 174 }, { "epoch": 0.33, "learning_rate": 1.975024903474208e-05, "loss": 0.4919, "step": 175 }, { "epoch": 0.33, "learning_rate": 1.9745706898597392e-05, "loss": 0.4939, "step": 176 }, { "epoch": 0.33, "learning_rate": 1.974112436247838e-05, "loss": 0.5026, "step": 177 }, { "epoch": 0.33, "learning_rate": 1.9736501445381544e-05, "loss": 0.5022, "step": 178 }, { "epoch": 0.33, "learning_rate": 1.9731838166470784e-05, "loss": 0.5133, "step": 179 }, { "epoch": 0.34, "learning_rate": 1.9727134545077312e-05, "loss": 0.5203, "step": 180 }, { "epoch": 0.34, "learning_rate": 1.9722390600699583e-05, "loss": 0.4838, "step": 181 }, { "epoch": 0.34, "learning_rate": 1.97176063530032e-05, "loss": 0.4806, "step": 182 }, { "epoch": 0.34, "learning_rate": 1.9712781821820842e-05, "loss": 0.5017, "step": 183 }, { "epoch": 0.34, "learning_rate": 1.9707917027152185e-05, "loss": 0.4986, "step": 184 }, { "epoch": 0.35, "learning_rate": 1.97030119891638e-05, "loss": 0.4843, "step": 185 }, { "epoch": 0.35, "learning_rate": 1.96980667281891e-05, "loss": 0.5108, "step": 186 }, { "epoch": 0.35, "learning_rate": 1.969308126472823e-05, "loss": 0.5002, "step": 187 }, { "epoch": 0.35, "learning_rate": 1.968805561944799e-05, "loss": 0.4919, "step": 188 }, { "epoch": 0.35, "learning_rate": 1.9682989813181758e-05, "loss": 0.5061, "step": 189 }, { "epoch": 0.35, "learning_rate": 1.967788386692938e-05, "loss": 0.4704, "step": 190 }, { "epoch": 0.36, "learning_rate": 1.9672737801857116e-05, "loss": 0.4918, "step": 191 }, { "epoch": 0.36, "learning_rate": 1.9667551639297528e-05, "loss": 0.4809, "step": 192 }, { "epoch": 0.36, "learning_rate": 1.9662325400749395e-05, "loss": 0.4915, "step": 193 }, { "epoch": 0.36, "learning_rate": 1.9657059107877635e-05, "loss": 0.5174, "step": 194 }, { "epoch": 0.36, "learning_rate": 1.9651752782513203e-05, "loss": 0.5082, "step": 195 }, { "epoch": 0.37, "learning_rate": 1.9646406446653004e-05, "loss": 0.4841, "step": 196 }, { "epoch": 0.37, "learning_rate": 1.9641020122459807e-05, "loss": 0.5164, "step": 197 }, { "epoch": 0.37, "learning_rate": 1.963559383226215e-05, "loss": 0.502, "step": 198 }, { "epoch": 0.37, "learning_rate": 1.9630127598554237e-05, "loss": 0.4843, "step": 199 }, { "epoch": 0.37, "learning_rate": 1.9624621443995863e-05, "loss": 0.511, "step": 200 }, { "epoch": 0.38, "learning_rate": 1.9619075391412314e-05, "loss": 0.4635, "step": 201 }, { "epoch": 0.38, "learning_rate": 1.9613489463794257e-05, "loss": 0.4948, "step": 202 }, { "epoch": 0.38, "learning_rate": 1.9607863684297675e-05, "loss": 0.477, "step": 203 }, { "epoch": 0.38, "learning_rate": 1.9602198076243737e-05, "loss": 0.521, "step": 204 }, { "epoch": 0.38, "learning_rate": 1.959649266311873e-05, "loss": 0.4887, "step": 205 }, { "epoch": 0.38, "learning_rate": 1.959074746857394e-05, "loss": 0.483, "step": 206 }, { "epoch": 0.39, "learning_rate": 1.9584962516425575e-05, "loss": 0.5028, "step": 207 }, { "epoch": 0.39, "learning_rate": 1.9579137830654635e-05, "loss": 0.4765, "step": 208 }, { "epoch": 0.39, "learning_rate": 1.9573273435406855e-05, "loss": 0.4796, "step": 209 }, { "epoch": 0.39, "learning_rate": 1.956736935499257e-05, "loss": 0.4621, "step": 210 }, { "epoch": 0.39, "learning_rate": 1.9561425613886628e-05, "loss": 0.5032, "step": 211 }, { "epoch": 0.4, "learning_rate": 1.955544223672828e-05, "loss": 0.4903, "step": 212 }, { "epoch": 0.4, "learning_rate": 1.9549419248321103e-05, "loss": 0.4805, "step": 213 }, { "epoch": 0.4, "learning_rate": 1.954335667363286e-05, "loss": 0.4543, "step": 214 }, { "epoch": 0.4, "learning_rate": 1.9537254537795432e-05, "loss": 0.4808, "step": 215 }, { "epoch": 0.4, "learning_rate": 1.9531112866104676e-05, "loss": 0.4871, "step": 216 }, { "epoch": 0.4, "learning_rate": 1.9524931684020367e-05, "loss": 0.4656, "step": 217 }, { "epoch": 0.41, "learning_rate": 1.9518711017166044e-05, "loss": 0.4848, "step": 218 }, { "epoch": 0.41, "learning_rate": 1.951245089132894e-05, "loss": 0.492, "step": 219 }, { "epoch": 0.41, "learning_rate": 1.9506151332459865e-05, "loss": 0.4766, "step": 220 }, { "epoch": 0.41, "learning_rate": 1.9499812366673077e-05, "loss": 0.475, "step": 221 }, { "epoch": 0.41, "learning_rate": 1.949343402024621e-05, "loss": 0.4957, "step": 222 }, { "epoch": 0.42, "learning_rate": 1.948701631962014e-05, "loss": 0.4834, "step": 223 }, { "epoch": 0.42, "learning_rate": 1.948055929139888e-05, "loss": 0.494, "step": 224 }, { "epoch": 0.42, "learning_rate": 1.9474062962349476e-05, "loss": 0.4707, "step": 225 }, { "epoch": 0.42, "learning_rate": 1.9467527359401894e-05, "loss": 0.4802, "step": 226 }, { "epoch": 0.42, "learning_rate": 1.94609525096489e-05, "loss": 0.4841, "step": 227 }, { "epoch": 0.43, "learning_rate": 1.945433844034596e-05, "loss": 0.4678, "step": 228 }, { "epoch": 0.43, "learning_rate": 1.944768517891112e-05, "loss": 0.4929, "step": 229 }, { "epoch": 0.43, "learning_rate": 1.9440992752924894e-05, "loss": 0.4665, "step": 230 }, { "epoch": 0.43, "learning_rate": 1.943426119013014e-05, "loss": 0.4709, "step": 231 }, { "epoch": 0.43, "learning_rate": 1.9427490518431966e-05, "loss": 0.486, "step": 232 }, { "epoch": 0.43, "learning_rate": 1.94206807658976e-05, "loss": 0.4893, "step": 233 }, { "epoch": 0.44, "learning_rate": 1.9413831960756274e-05, "loss": 0.4961, "step": 234 }, { "epoch": 0.44, "learning_rate": 1.940694413139911e-05, "loss": 0.4713, "step": 235 }, { "epoch": 0.44, "learning_rate": 1.9400017306378997e-05, "loss": 0.4727, "step": 236 }, { "epoch": 0.44, "learning_rate": 1.939305151441049e-05, "loss": 0.4777, "step": 237 }, { "epoch": 0.44, "learning_rate": 1.9386046784369663e-05, "loss": 0.4779, "step": 238 }, { "epoch": 0.45, "learning_rate": 1.9379003145294015e-05, "loss": 0.4748, "step": 239 }, { "epoch": 0.45, "learning_rate": 1.9371920626382326e-05, "loss": 0.4741, "step": 240 }, { "epoch": 0.45, "learning_rate": 1.936479925699457e-05, "loss": 0.4898, "step": 241 }, { "epoch": 0.45, "learning_rate": 1.935763906665175e-05, "loss": 0.5035, "step": 242 }, { "epoch": 0.45, "learning_rate": 1.9350440085035816e-05, "loss": 0.4869, "step": 243 }, { "epoch": 0.46, "learning_rate": 1.9343202341989512e-05, "loss": 0.4788, "step": 244 }, { "epoch": 0.46, "learning_rate": 1.9335925867516265e-05, "loss": 0.4636, "step": 245 }, { "epoch": 0.46, "learning_rate": 1.9328610691780065e-05, "loss": 0.4711, "step": 246 }, { "epoch": 0.46, "learning_rate": 1.9321256845105335e-05, "loss": 0.4729, "step": 247 }, { "epoch": 0.46, "learning_rate": 1.9313864357976798e-05, "loss": 0.4796, "step": 248 }, { "epoch": 0.46, "learning_rate": 1.9306433261039365e-05, "loss": 0.4763, "step": 249 }, { "epoch": 0.47, "learning_rate": 1.929896358509799e-05, "loss": 0.4777, "step": 250 }, { "epoch": 0.47, "learning_rate": 1.9291455361117576e-05, "loss": 0.4904, "step": 251 }, { "epoch": 0.47, "learning_rate": 1.9283908620222795e-05, "loss": 0.4591, "step": 252 }, { "epoch": 0.47, "learning_rate": 1.9276323393698e-05, "loss": 0.4841, "step": 253 }, { "epoch": 0.47, "learning_rate": 1.926869971298709e-05, "loss": 0.487, "step": 254 }, { "epoch": 0.48, "learning_rate": 1.9261037609693362e-05, "loss": 0.4998, "step": 255 }, { "epoch": 0.48, "learning_rate": 1.9253337115579396e-05, "loss": 0.4685, "step": 256 }, { "epoch": 0.48, "learning_rate": 1.9245598262566914e-05, "loss": 0.4678, "step": 257 }, { "epoch": 0.48, "learning_rate": 1.9237821082736655e-05, "loss": 0.4698, "step": 258 }, { "epoch": 0.48, "learning_rate": 1.9230005608328232e-05, "loss": 0.4686, "step": 259 }, { "epoch": 0.49, "learning_rate": 1.9222151871740014e-05, "loss": 0.4783, "step": 260 }, { "epoch": 0.49, "learning_rate": 1.921425990552898e-05, "loss": 0.4605, "step": 261 }, { "epoch": 0.49, "learning_rate": 1.920632974241058e-05, "loss": 0.4731, "step": 262 }, { "epoch": 0.49, "learning_rate": 1.9198361415258613e-05, "loss": 0.4801, "step": 263 }, { "epoch": 0.49, "learning_rate": 1.9190354957105078e-05, "loss": 0.4842, "step": 264 }, { "epoch": 0.49, "learning_rate": 1.9182310401140054e-05, "loss": 0.4866, "step": 265 }, { "epoch": 0.5, "learning_rate": 1.9174227780711535e-05, "loss": 0.4603, "step": 266 }, { "epoch": 0.5, "learning_rate": 1.916610712932532e-05, "loss": 0.4835, "step": 267 }, { "epoch": 0.5, "learning_rate": 1.9157948480644858e-05, "loss": 0.4906, "step": 268 }, { "epoch": 0.5, "learning_rate": 1.914975186849111e-05, "loss": 0.4582, "step": 269 }, { "epoch": 0.5, "learning_rate": 1.9141517326842414e-05, "loss": 0.4861, "step": 270 }, { "epoch": 0.51, "learning_rate": 1.9133244889834347e-05, "loss": 0.4801, "step": 271 }, { "epoch": 0.51, "learning_rate": 1.9124934591759562e-05, "loss": 0.4739, "step": 272 }, { "epoch": 0.51, "learning_rate": 1.911658646706768e-05, "loss": 0.4932, "step": 273 }, { "epoch": 0.51, "learning_rate": 1.910820055036512e-05, "loss": 0.4951, "step": 274 }, { "epoch": 0.51, "learning_rate": 1.909977687641496e-05, "loss": 0.4843, "step": 275 }, { "epoch": 0.51, "learning_rate": 1.9091315480136807e-05, "loss": 0.4642, "step": 276 }, { "epoch": 0.52, "learning_rate": 1.9082816396606637e-05, "loss": 0.4634, "step": 277 }, { "epoch": 0.52, "learning_rate": 1.9074279661056652e-05, "loss": 0.4774, "step": 278 }, { "epoch": 0.52, "learning_rate": 1.906570530887515e-05, "loss": 0.4616, "step": 279 }, { "epoch": 0.52, "learning_rate": 1.9057093375606354e-05, "loss": 0.4655, "step": 280 }, { "epoch": 0.52, "learning_rate": 1.9048443896950272e-05, "loss": 0.465, "step": 281 }, { "epoch": 0.53, "learning_rate": 1.9039756908762574e-05, "loss": 0.4759, "step": 282 }, { "epoch": 0.53, "learning_rate": 1.9031032447054393e-05, "loss": 0.4519, "step": 283 }, { "epoch": 0.53, "learning_rate": 1.902227054799223e-05, "loss": 0.4805, "step": 284 }, { "epoch": 0.53, "learning_rate": 1.901347124789777e-05, "loss": 0.4874, "step": 285 }, { "epoch": 0.53, "learning_rate": 1.9004634583247735e-05, "loss": 0.4763, "step": 286 }, { "epoch": 0.54, "learning_rate": 1.8995760590673753e-05, "loss": 0.4896, "step": 287 }, { "epoch": 0.54, "learning_rate": 1.898684930696218e-05, "loss": 0.4561, "step": 288 }, { "epoch": 0.54, "learning_rate": 1.8977900769053956e-05, "loss": 0.4569, "step": 289 }, { "epoch": 0.54, "learning_rate": 1.8968915014044465e-05, "loss": 0.4568, "step": 290 }, { "epoch": 0.54, "learning_rate": 1.8959892079183373e-05, "loss": 0.4495, "step": 291 }, { "epoch": 0.54, "learning_rate": 1.8950832001874456e-05, "loss": 0.4719, "step": 292 }, { "epoch": 0.55, "learning_rate": 1.8941734819675482e-05, "loss": 0.4521, "step": 293 }, { "epoch": 0.55, "learning_rate": 1.8932600570298012e-05, "loss": 0.4559, "step": 294 }, { "epoch": 0.55, "learning_rate": 1.8923429291607282e-05, "loss": 0.444, "step": 295 }, { "epoch": 0.55, "learning_rate": 1.8914221021622027e-05, "loss": 0.4619, "step": 296 }, { "epoch": 0.55, "learning_rate": 1.890497579851432e-05, "loss": 0.4591, "step": 297 }, { "epoch": 0.56, "learning_rate": 1.8895693660609425e-05, "loss": 0.4632, "step": 298 }, { "epoch": 0.56, "learning_rate": 1.888637464638563e-05, "loss": 0.4604, "step": 299 }, { "epoch": 0.56, "learning_rate": 1.887701879447409e-05, "loss": 0.4711, "step": 300 }, { "epoch": 0.56, "learning_rate": 1.8867626143658678e-05, "loss": 0.4704, "step": 301 }, { "epoch": 0.56, "learning_rate": 1.8858196732875797e-05, "loss": 0.4787, "step": 302 }, { "epoch": 0.57, "learning_rate": 1.884873060121425e-05, "loss": 0.4635, "step": 303 }, { "epoch": 0.57, "learning_rate": 1.883922778791505e-05, "loss": 0.4721, "step": 304 }, { "epoch": 0.57, "learning_rate": 1.8829688332371284e-05, "loss": 0.4492, "step": 305 }, { "epoch": 0.57, "learning_rate": 1.8820112274127925e-05, "loss": 0.4629, "step": 306 }, { "epoch": 0.57, "learning_rate": 1.8810499652881686e-05, "loss": 0.4512, "step": 307 }, { "epoch": 0.57, "learning_rate": 1.8800850508480842e-05, "loss": 0.454, "step": 308 }, { "epoch": 0.58, "learning_rate": 1.879116488092508e-05, "loss": 0.4553, "step": 309 }, { "epoch": 0.58, "learning_rate": 1.878144281036532e-05, "loss": 0.4422, "step": 310 }, { "epoch": 0.58, "learning_rate": 1.8771684337103553e-05, "loss": 0.4479, "step": 311 }, { "epoch": 0.58, "learning_rate": 1.8761889501592678e-05, "loss": 0.4755, "step": 312 }, { "epoch": 0.58, "learning_rate": 1.8752058344436324e-05, "loss": 0.4458, "step": 313 }, { "epoch": 0.59, "learning_rate": 1.874219090638869e-05, "loss": 0.4503, "step": 314 }, { "epoch": 0.59, "learning_rate": 1.8732287228354385e-05, "loss": 0.4578, "step": 315 }, { "epoch": 0.59, "learning_rate": 1.872234735138823e-05, "loss": 0.4607, "step": 316 }, { "epoch": 0.59, "learning_rate": 1.871237131669512e-05, "loss": 0.4418, "step": 317 }, { "epoch": 0.59, "learning_rate": 1.8702359165629832e-05, "loss": 0.4707, "step": 318 }, { "epoch": 0.6, "learning_rate": 1.8692310939696855e-05, "loss": 0.4477, "step": 319 }, { "epoch": 0.6, "learning_rate": 1.868222668055024e-05, "loss": 0.4603, "step": 320 }, { "epoch": 0.6, "learning_rate": 1.867210642999339e-05, "loss": 0.4658, "step": 321 }, { "epoch": 0.6, "learning_rate": 1.8661950229978924e-05, "loss": 0.4611, "step": 322 }, { "epoch": 0.6, "learning_rate": 1.8651758122608478e-05, "loss": 0.4615, "step": 323 }, { "epoch": 0.6, "learning_rate": 1.8641530150132537e-05, "loss": 0.4758, "step": 324 }, { "epoch": 0.61, "learning_rate": 1.8631266354950267e-05, "loss": 0.4424, "step": 325 }, { "epoch": 0.61, "learning_rate": 1.862096677960934e-05, "loss": 0.4491, "step": 326 }, { "epoch": 0.61, "learning_rate": 1.8610631466805728e-05, "loss": 0.4419, "step": 327 }, { "epoch": 0.61, "learning_rate": 1.8600260459383578e-05, "loss": 0.4852, "step": 328 }, { "epoch": 0.61, "learning_rate": 1.858985380033499e-05, "loss": 0.4698, "step": 329 }, { "epoch": 0.62, "learning_rate": 1.857941153279985e-05, "loss": 0.4428, "step": 330 }, { "epoch": 0.62, "learning_rate": 1.8568933700065668e-05, "loss": 0.45, "step": 331 }, { "epoch": 0.62, "learning_rate": 1.8558420345567386e-05, "loss": 0.4376, "step": 332 }, { "epoch": 0.62, "learning_rate": 1.854787151288719e-05, "loss": 0.4479, "step": 333 }, { "epoch": 0.62, "learning_rate": 1.8537287245754342e-05, "loss": 0.4742, "step": 334 }, { "epoch": 0.62, "learning_rate": 1.8526667588045e-05, "loss": 0.4485, "step": 335 }, { "epoch": 0.63, "learning_rate": 1.8516012583782015e-05, "loss": 0.4484, "step": 336 }, { "epoch": 0.63, "learning_rate": 1.850532227713478e-05, "loss": 0.4738, "step": 337 }, { "epoch": 0.63, "learning_rate": 1.8494596712419025e-05, "loss": 0.4683, "step": 338 }, { "epoch": 0.63, "learning_rate": 1.8483835934096638e-05, "loss": 0.4523, "step": 339 }, { "epoch": 0.63, "learning_rate": 1.8473039986775485e-05, "loss": 0.4592, "step": 340 }, { "epoch": 0.64, "learning_rate": 1.8462208915209216e-05, "loss": 0.4593, "step": 341 }, { "epoch": 0.64, "learning_rate": 1.845134276429709e-05, "loss": 0.4307, "step": 342 }, { "epoch": 0.64, "learning_rate": 1.8440441579083784e-05, "loss": 0.4695, "step": 343 }, { "epoch": 0.64, "learning_rate": 1.842950540475921e-05, "loss": 0.4506, "step": 344 }, { "epoch": 0.64, "learning_rate": 1.841853428665832e-05, "loss": 0.4393, "step": 345 }, { "epoch": 0.65, "learning_rate": 1.8407528270260918e-05, "loss": 0.4562, "step": 346 }, { "epoch": 0.65, "learning_rate": 1.839648740119149e-05, "loss": 0.4516, "step": 347 }, { "epoch": 0.65, "learning_rate": 1.8385411725218983e-05, "loss": 0.4727, "step": 348 }, { "epoch": 0.65, "learning_rate": 1.8374301288256643e-05, "loss": 0.4469, "step": 349 }, { "epoch": 0.65, "learning_rate": 1.836315613636182e-05, "loss": 0.4475, "step": 350 }, { "epoch": 0.65, "learning_rate": 1.8351976315735757e-05, "loss": 0.478, "step": 351 }, { "epoch": 0.66, "learning_rate": 1.834076187272342e-05, "loss": 0.4722, "step": 352 }, { "epoch": 0.66, "learning_rate": 1.832951285381331e-05, "loss": 0.4409, "step": 353 }, { "epoch": 0.66, "learning_rate": 1.8318229305637246e-05, "loss": 0.4523, "step": 354 }, { "epoch": 0.66, "learning_rate": 1.8306911274970184e-05, "loss": 0.4263, "step": 355 }, { "epoch": 0.66, "learning_rate": 1.8295558808730033e-05, "loss": 0.4761, "step": 356 }, { "epoch": 0.67, "learning_rate": 1.8284171953977444e-05, "loss": 0.4158, "step": 357 }, { "epoch": 0.67, "learning_rate": 1.8272750757915627e-05, "loss": 0.4484, "step": 358 }, { "epoch": 0.67, "learning_rate": 1.8261295267890152e-05, "loss": 0.4074, "step": 359 }, { "epoch": 0.67, "learning_rate": 1.824980553138875e-05, "loss": 0.4406, "step": 360 }, { "epoch": 0.67, "learning_rate": 1.8238281596041113e-05, "loss": 0.4561, "step": 361 }, { "epoch": 0.68, "learning_rate": 1.822672350961871e-05, "loss": 0.4348, "step": 362 }, { "epoch": 0.68, "learning_rate": 1.8215131320034576e-05, "loss": 0.4401, "step": 363 }, { "epoch": 0.68, "learning_rate": 1.8203505075343113e-05, "loss": 0.4503, "step": 364 }, { "epoch": 0.68, "learning_rate": 1.8191844823739905e-05, "loss": 0.4595, "step": 365 }, { "epoch": 0.68, "learning_rate": 1.81801506135615e-05, "loss": 0.4426, "step": 366 }, { "epoch": 0.68, "learning_rate": 1.8168422493285223e-05, "loss": 0.4518, "step": 367 }, { "epoch": 0.69, "learning_rate": 1.815666051152897e-05, "loss": 0.4313, "step": 368 }, { "epoch": 0.69, "learning_rate": 1.814486471705101e-05, "loss": 0.4481, "step": 369 }, { "epoch": 0.69, "learning_rate": 1.8133035158749766e-05, "loss": 0.4251, "step": 370 }, { "epoch": 0.69, "learning_rate": 1.8121171885663646e-05, "loss": 0.4397, "step": 371 }, { "epoch": 0.69, "learning_rate": 1.8109274946970802e-05, "loss": 0.4355, "step": 372 }, { "epoch": 0.7, "learning_rate": 1.8097344391988956e-05, "loss": 0.4186, "step": 373 }, { "epoch": 0.7, "learning_rate": 1.8085380270175175e-05, "loss": 0.4474, "step": 374 }, { "epoch": 0.7, "learning_rate": 1.8073382631125682e-05, "loss": 0.4484, "step": 375 }, { "epoch": 0.7, "learning_rate": 1.8061351524575638e-05, "loss": 0.4589, "step": 376 }, { "epoch": 0.7, "learning_rate": 1.8049287000398937e-05, "loss": 0.4107, "step": 377 }, { "epoch": 0.71, "learning_rate": 1.8037189108608012e-05, "loss": 0.4376, "step": 378 }, { "epoch": 0.71, "learning_rate": 1.8025057899353614e-05, "loss": 0.4566, "step": 379 }, { "epoch": 0.71, "learning_rate": 1.8012893422924603e-05, "loss": 0.4332, "step": 380 }, { "epoch": 0.71, "learning_rate": 1.800069572974776e-05, "loss": 0.4227, "step": 381 }, { "epoch": 0.71, "learning_rate": 1.7988464870387547e-05, "loss": 0.4352, "step": 382 }, { "epoch": 0.71, "learning_rate": 1.7976200895545918e-05, "loss": 0.4146, "step": 383 }, { "epoch": 0.72, "learning_rate": 1.796390385606211e-05, "loss": 0.4238, "step": 384 }, { "epoch": 0.72, "learning_rate": 1.7951573802912423e-05, "loss": 0.4387, "step": 385 }, { "epoch": 0.72, "learning_rate": 1.7939210787210012e-05, "loss": 0.4346, "step": 386 }, { "epoch": 0.72, "learning_rate": 1.7926814860204676e-05, "loss": 0.4278, "step": 387 }, { "epoch": 0.72, "learning_rate": 1.7914386073282645e-05, "loss": 0.423, "step": 388 }, { "epoch": 0.73, "learning_rate": 1.7901924477966365e-05, "loss": 0.418, "step": 389 }, { "epoch": 0.73, "learning_rate": 1.788943012591429e-05, "loss": 0.4265, "step": 390 }, { "epoch": 0.73, "learning_rate": 1.7876903068920662e-05, "loss": 0.4569, "step": 391 }, { "epoch": 0.73, "learning_rate": 1.7864343358915295e-05, "loss": 0.4608, "step": 392 }, { "epoch": 0.73, "learning_rate": 1.785175104796337e-05, "loss": 0.4239, "step": 393 }, { "epoch": 0.74, "learning_rate": 1.7839126188265207e-05, "loss": 0.4342, "step": 394 }, { "epoch": 0.74, "learning_rate": 1.782646883215606e-05, "loss": 0.43, "step": 395 }, { "epoch": 0.74, "learning_rate": 1.7813779032105887e-05, "loss": 0.4343, "step": 396 }, { "epoch": 0.74, "learning_rate": 1.780105684071914e-05, "loss": 0.4366, "step": 397 }, { "epoch": 0.74, "learning_rate": 1.7788302310734558e-05, "loss": 0.4423, "step": 398 }, { "epoch": 0.74, "learning_rate": 1.7775515495024917e-05, "loss": 0.4537, "step": 399 }, { "epoch": 0.75, "learning_rate": 1.776269644659685e-05, "loss": 0.4118, "step": 400 }, { "epoch": 0.75, "learning_rate": 1.774984521859059e-05, "loss": 0.42, "step": 401 }, { "epoch": 0.75, "learning_rate": 1.7736961864279788e-05, "loss": 0.4383, "step": 402 }, { "epoch": 0.75, "learning_rate": 1.7724046437071255e-05, "loss": 0.4246, "step": 403 }, { "epoch": 0.75, "learning_rate": 1.7711098990504765e-05, "loss": 0.4294, "step": 404 }, { "epoch": 0.76, "learning_rate": 1.7698119578252823e-05, "loss": 0.414, "step": 405 }, { "epoch": 0.76, "learning_rate": 1.768510825412044e-05, "loss": 0.431, "step": 406 }, { "epoch": 0.76, "learning_rate": 1.7672065072044934e-05, "loss": 0.4246, "step": 407 }, { "epoch": 0.76, "learning_rate": 1.765899008609566e-05, "loss": 0.4393, "step": 408 }, { "epoch": 0.76, "learning_rate": 1.7645883350473834e-05, "loss": 0.4354, "step": 409 }, { "epoch": 0.76, "learning_rate": 1.7632744919512278e-05, "loss": 0.4393, "step": 410 }, { "epoch": 0.77, "learning_rate": 1.761957484767521e-05, "loss": 0.4399, "step": 411 }, { "epoch": 0.77, "learning_rate": 1.760637318955801e-05, "loss": 0.4202, "step": 412 }, { "epoch": 0.77, "learning_rate": 1.759313999988699e-05, "loss": 0.403, "step": 413 }, { "epoch": 0.77, "learning_rate": 1.757987533351918e-05, "loss": 0.4052, "step": 414 }, { "epoch": 0.77, "learning_rate": 1.7566579245442096e-05, "loss": 0.4397, "step": 415 }, { "epoch": 0.78, "learning_rate": 1.7553251790773503e-05, "loss": 0.4416, "step": 416 }, { "epoch": 0.78, "learning_rate": 1.75398930247612e-05, "loss": 0.4168, "step": 417 }, { "epoch": 0.78, "learning_rate": 1.752650300278278e-05, "loss": 0.427, "step": 418 }, { "epoch": 0.78, "learning_rate": 1.7513081780345408e-05, "loss": 0.427, "step": 419 }, { "epoch": 0.78, "learning_rate": 1.7499629413085578e-05, "loss": 0.4323, "step": 420 }, { "epoch": 0.79, "learning_rate": 1.7486145956768913e-05, "loss": 0.4302, "step": 421 }, { "epoch": 0.79, "learning_rate": 1.747263146728989e-05, "loss": 0.4269, "step": 422 }, { "epoch": 0.79, "learning_rate": 1.7459086000671648e-05, "loss": 0.4109, "step": 423 }, { "epoch": 0.79, "learning_rate": 1.7445509613065726e-05, "loss": 0.4203, "step": 424 }, { "epoch": 0.79, "learning_rate": 1.7431902360751854e-05, "loss": 0.4386, "step": 425 }, { "epoch": 0.79, "learning_rate": 1.7418264300137706e-05, "loss": 0.4465, "step": 426 }, { "epoch": 0.8, "learning_rate": 1.7404595487758663e-05, "loss": 0.4394, "step": 427 }, { "epoch": 0.8, "learning_rate": 1.7390895980277592e-05, "loss": 0.4229, "step": 428 }, { "epoch": 0.8, "learning_rate": 1.7377165834484603e-05, "loss": 0.4291, "step": 429 }, { "epoch": 0.8, "learning_rate": 1.736340510729681e-05, "loss": 0.4498, "step": 430 }, { "epoch": 0.8, "learning_rate": 1.73496138557581e-05, "loss": 0.4179, "step": 431 }, { "epoch": 0.81, "learning_rate": 1.7335792137038905e-05, "loss": 0.4119, "step": 432 }, { "epoch": 0.81, "learning_rate": 1.7321940008435944e-05, "loss": 0.4076, "step": 433 }, { "epoch": 0.81, "learning_rate": 1.730805752737201e-05, "loss": 0.4181, "step": 434 }, { "epoch": 0.81, "learning_rate": 1.72941447513957e-05, "loss": 0.4248, "step": 435 }, { "epoch": 0.81, "learning_rate": 1.7280201738181218e-05, "loss": 0.4295, "step": 436 }, { "epoch": 0.82, "learning_rate": 1.7266228545528098e-05, "loss": 0.4489, "step": 437 }, { "epoch": 0.82, "learning_rate": 1.7252225231360994e-05, "loss": 0.4418, "step": 438 }, { "epoch": 0.82, "learning_rate": 1.7238191853729413e-05, "loss": 0.435, "step": 439 }, { "epoch": 0.82, "learning_rate": 1.7224128470807492e-05, "loss": 0.4333, "step": 440 }, { "epoch": 0.82, "learning_rate": 1.721003514089375e-05, "loss": 0.417, "step": 441 }, { "epoch": 0.82, "learning_rate": 1.7195911922410866e-05, "loss": 0.3932, "step": 442 }, { "epoch": 0.83, "learning_rate": 1.7181758873905393e-05, "loss": 0.4145, "step": 443 }, { "epoch": 0.83, "learning_rate": 1.7167576054047552e-05, "loss": 0.4482, "step": 444 }, { "epoch": 0.83, "learning_rate": 1.7153363521630986e-05, "loss": 0.4064, "step": 445 }, { "epoch": 0.83, "learning_rate": 1.7139121335572503e-05, "loss": 0.4221, "step": 446 }, { "epoch": 0.83, "learning_rate": 1.712484955491184e-05, "loss": 0.4386, "step": 447 }, { "epoch": 0.84, "learning_rate": 1.7110548238811405e-05, "loss": 0.3976, "step": 448 }, { "epoch": 0.84, "learning_rate": 1.7096217446556062e-05, "loss": 0.422, "step": 449 }, { "epoch": 0.84, "learning_rate": 1.7081857237552845e-05, "loss": 0.4411, "step": 450 }, { "epoch": 0.84, "learning_rate": 1.7067467671330753e-05, "loss": 0.4334, "step": 451 }, { "epoch": 0.84, "learning_rate": 1.7053048807540465e-05, "loss": 0.4224, "step": 452 }, { "epoch": 0.85, "learning_rate": 1.7038600705954118e-05, "loss": 0.4286, "step": 453 }, { "epoch": 0.85, "learning_rate": 1.7024123426465054e-05, "loss": 0.4216, "step": 454 }, { "epoch": 0.85, "learning_rate": 1.7009617029087566e-05, "loss": 0.4155, "step": 455 }, { "epoch": 0.85, "learning_rate": 1.6995081573956658e-05, "loss": 0.4287, "step": 456 }, { "epoch": 0.85, "learning_rate": 1.6980517121327777e-05, "loss": 0.4043, "step": 457 }, { "epoch": 0.85, "learning_rate": 1.6965923731576596e-05, "loss": 0.4179, "step": 458 }, { "epoch": 0.86, "learning_rate": 1.6951301465198725e-05, "loss": 0.3891, "step": 459 }, { "epoch": 0.86, "learning_rate": 1.6936650382809493e-05, "loss": 0.4433, "step": 460 }, { "epoch": 0.86, "learning_rate": 1.692197054514368e-05, "loss": 0.4005, "step": 461 }, { "epoch": 0.86, "learning_rate": 1.6907262013055267e-05, "loss": 0.4236, "step": 462 }, { "epoch": 0.86, "learning_rate": 1.6892524847517183e-05, "loss": 0.4048, "step": 463 }, { "epoch": 0.87, "learning_rate": 1.6877759109621053e-05, "loss": 0.4172, "step": 464 }, { "epoch": 0.87, "learning_rate": 1.686296486057696e-05, "loss": 0.4225, "step": 465 }, { "epoch": 0.87, "learning_rate": 1.6848142161713162e-05, "loss": 0.4061, "step": 466 }, { "epoch": 0.87, "learning_rate": 1.683329107447586e-05, "loss": 0.4236, "step": 467 }, { "epoch": 0.87, "learning_rate": 1.6818411660428934e-05, "loss": 0.4016, "step": 468 }, { "epoch": 0.88, "learning_rate": 1.680350398125369e-05, "loss": 0.4229, "step": 469 }, { "epoch": 0.88, "learning_rate": 1.6788568098748612e-05, "loss": 0.4146, "step": 470 }, { "epoch": 0.88, "learning_rate": 1.6773604074829085e-05, "loss": 0.4049, "step": 471 }, { "epoch": 0.88, "learning_rate": 1.675861197152717e-05, "loss": 0.412, "step": 472 }, { "epoch": 0.88, "learning_rate": 1.6743591850991307e-05, "loss": 0.4089, "step": 473 }, { "epoch": 0.88, "learning_rate": 1.6728543775486095e-05, "loss": 0.4122, "step": 474 }, { "epoch": 0.89, "learning_rate": 1.6713467807392017e-05, "loss": 0.4068, "step": 475 }, { "epoch": 0.89, "learning_rate": 1.669836400920517e-05, "loss": 0.4406, "step": 476 }, { "epoch": 0.89, "learning_rate": 1.6683232443537033e-05, "loss": 0.3894, "step": 477 }, { "epoch": 0.89, "learning_rate": 1.6668073173114185e-05, "loss": 0.4147, "step": 478 }, { "epoch": 0.89, "learning_rate": 1.665288626077805e-05, "loss": 0.4219, "step": 479 }, { "epoch": 0.9, "learning_rate": 1.6637671769484644e-05, "loss": 0.4116, "step": 480 }, { "epoch": 0.9, "learning_rate": 1.6622429762304314e-05, "loss": 0.3744, "step": 481 }, { "epoch": 0.9, "learning_rate": 1.660716030242146e-05, "loss": 0.415, "step": 482 }, { "epoch": 0.9, "learning_rate": 1.6591863453134287e-05, "loss": 0.4005, "step": 483 }, { "epoch": 0.9, "learning_rate": 1.6576539277854552e-05, "loss": 0.4105, "step": 484 }, { "epoch": 0.9, "learning_rate": 1.6561187840107275e-05, "loss": 0.4119, "step": 485 }, { "epoch": 0.91, "learning_rate": 1.6545809203530502e-05, "loss": 0.4005, "step": 486 }, { "epoch": 0.91, "learning_rate": 1.653040343187502e-05, "loss": 0.4278, "step": 487 }, { "epoch": 0.91, "learning_rate": 1.6514970589004107e-05, "loss": 0.41, "step": 488 }, { "epoch": 0.91, "learning_rate": 1.6499510738893265e-05, "loss": 0.3896, "step": 489 }, { "epoch": 0.91, "learning_rate": 1.6484023945629943e-05, "loss": 0.4281, "step": 490 }, { "epoch": 0.92, "learning_rate": 1.6468510273413288e-05, "loss": 0.3854, "step": 491 }, { "epoch": 0.92, "learning_rate": 1.645296978655387e-05, "loss": 0.4198, "step": 492 }, { "epoch": 0.92, "learning_rate": 1.6437402549473412e-05, "loss": 0.4112, "step": 493 }, { "epoch": 0.92, "learning_rate": 1.642180862670454e-05, "loss": 0.4005, "step": 494 }, { "epoch": 0.92, "learning_rate": 1.640618808289049e-05, "loss": 0.4171, "step": 495 }, { "epoch": 0.93, "learning_rate": 1.639054098278486e-05, "loss": 0.4422, "step": 496 }, { "epoch": 0.93, "learning_rate": 1.6374867391251326e-05, "loss": 0.4074, "step": 497 }, { "epoch": 0.93, "learning_rate": 1.6359167373263402e-05, "loss": 0.4158, "step": 498 }, { "epoch": 0.93, "learning_rate": 1.634344099390412e-05, "loss": 0.3938, "step": 499 }, { "epoch": 0.93, "learning_rate": 1.6327688318365824e-05, "loss": 0.4149, "step": 500 }, { "epoch": 0.93, "learning_rate": 1.6311909411949846e-05, "loss": 0.4145, "step": 501 }, { "epoch": 0.94, "learning_rate": 1.6296104340066255e-05, "loss": 0.4222, "step": 502 }, { "epoch": 0.94, "learning_rate": 1.62802731682336e-05, "loss": 0.4238, "step": 503 }, { "epoch": 0.94, "learning_rate": 1.626441596207861e-05, "loss": 0.4181, "step": 504 }, { "epoch": 0.94, "learning_rate": 1.624853278733595e-05, "loss": 0.4374, "step": 505 }, { "epoch": 0.94, "learning_rate": 1.6232623709847925e-05, "loss": 0.4108, "step": 506 }, { "epoch": 0.95, "learning_rate": 1.6216688795564227e-05, "loss": 0.396, "step": 507 }, { "epoch": 0.95, "learning_rate": 1.6200728110541644e-05, "loss": 0.3856, "step": 508 }, { "epoch": 0.95, "learning_rate": 1.61847417209438e-05, "loss": 0.385, "step": 509 }, { "epoch": 0.95, "learning_rate": 1.616872969304087e-05, "loss": 0.3933, "step": 510 }, { "epoch": 0.95, "learning_rate": 1.615269209320931e-05, "loss": 0.4012, "step": 511 }, { "epoch": 0.96, "learning_rate": 1.6136628987931597e-05, "loss": 0.4055, "step": 512 }, { "epoch": 0.96, "learning_rate": 1.6120540443795918e-05, "loss": 0.4078, "step": 513 }, { "epoch": 0.96, "learning_rate": 1.6104426527495926e-05, "loss": 0.3772, "step": 514 }, { "epoch": 0.96, "learning_rate": 1.608828730583045e-05, "loss": 0.4079, "step": 515 }, { "epoch": 0.96, "learning_rate": 1.607212284570322e-05, "loss": 0.4317, "step": 516 }, { "epoch": 0.96, "learning_rate": 1.6055933214122584e-05, "loss": 0.4239, "step": 517 }, { "epoch": 0.97, "learning_rate": 1.603971847820125e-05, "loss": 0.416, "step": 518 }, { "epoch": 0.97, "learning_rate": 1.602347870515598e-05, "loss": 0.4202, "step": 519 }, { "epoch": 0.97, "learning_rate": 1.6007213962307332e-05, "loss": 0.4055, "step": 520 }, { "epoch": 0.97, "learning_rate": 1.5990924317079376e-05, "loss": 0.4228, "step": 521 }, { "epoch": 0.97, "learning_rate": 1.5974609836999407e-05, "loss": 0.4017, "step": 522 }, { "epoch": 0.98, "learning_rate": 1.5958270589697667e-05, "loss": 0.38, "step": 523 }, { "epoch": 0.98, "learning_rate": 1.5941906642907088e-05, "loss": 0.4023, "step": 524 }, { "epoch": 0.98, "learning_rate": 1.592551806446297e-05, "loss": 0.4104, "step": 525 }, { "epoch": 0.98, "learning_rate": 1.5909104922302725e-05, "loss": 0.3881, "step": 526 }, { "epoch": 0.98, "learning_rate": 1.5892667284465604e-05, "loss": 0.4281, "step": 527 }, { "epoch": 0.99, "learning_rate": 1.5876205219092393e-05, "loss": 0.4094, "step": 528 }, { "epoch": 0.99, "learning_rate": 1.5859718794425143e-05, "loss": 0.4177, "step": 529 }, { "epoch": 0.99, "learning_rate": 1.5843208078806878e-05, "loss": 0.3901, "step": 530 }, { "epoch": 0.99, "learning_rate": 1.582667314068133e-05, "loss": 0.3901, "step": 531 }, { "epoch": 0.99, "learning_rate": 1.581011404859263e-05, "loss": 0.3924, "step": 532 }, { "epoch": 0.99, "learning_rate": 1.5793530871185054e-05, "loss": 0.4043, "step": 533 }, { "epoch": 1.0, "learning_rate": 1.5776923677202703e-05, "loss": 0.4115, "step": 534 }, { "epoch": 1.0, "learning_rate": 1.5760292535489242e-05, "loss": 0.3936, "step": 535 }, { "epoch": 1.0, "learning_rate": 1.5743637514987623e-05, "loss": 0.4158, "step": 536 }, { "epoch": 1.0, "learning_rate": 1.572695868473977e-05, "loss": 0.4071, "step": 537 }, { "epoch": 1.0, "learning_rate": 1.571025611388631e-05, "loss": 0.4039, "step": 538 }, { "epoch": 1.01, "learning_rate": 1.569352987166629e-05, "loss": 0.383, "step": 539 }, { "epoch": 1.01, "learning_rate": 1.5676780027416882e-05, "loss": 0.5733, "step": 540 }, { "epoch": 1.01, "learning_rate": 1.5660006650573097e-05, "loss": 0.3945, "step": 541 }, { "epoch": 1.01, "learning_rate": 1.56432098106675e-05, "loss": 0.4085, "step": 542 }, { "epoch": 1.01, "learning_rate": 1.5626389577329918e-05, "loss": 0.3884, "step": 543 }, { "epoch": 1.01, "learning_rate": 1.560954602028716e-05, "loss": 0.3729, "step": 544 }, { "epoch": 1.02, "learning_rate": 1.5592679209362716e-05, "loss": 0.3971, "step": 545 }, { "epoch": 1.02, "learning_rate": 1.5575789214476465e-05, "loss": 0.3905, "step": 546 }, { "epoch": 1.02, "learning_rate": 1.555887610564441e-05, "loss": 0.3765, "step": 547 }, { "epoch": 1.02, "learning_rate": 1.554193995297836e-05, "loss": 0.4006, "step": 548 }, { "epoch": 1.02, "learning_rate": 1.552498082668565e-05, "loss": 0.4057, "step": 549 }, { "epoch": 1.03, "learning_rate": 1.5507998797068855e-05, "loss": 0.3941, "step": 550 }, { "epoch": 1.03, "learning_rate": 1.5490993934525493e-05, "loss": 0.3759, "step": 551 }, { "epoch": 1.03, "learning_rate": 1.5473966309547725e-05, "loss": 0.3983, "step": 552 }, { "epoch": 1.03, "learning_rate": 1.545691599272209e-05, "loss": 0.399, "step": 553 }, { "epoch": 1.03, "learning_rate": 1.5439843054729172e-05, "loss": 0.3634, "step": 554 }, { "epoch": 1.04, "learning_rate": 1.5422747566343348e-05, "loss": 0.3959, "step": 555 }, { "epoch": 1.04, "learning_rate": 1.5405629598432463e-05, "loss": 0.3962, "step": 556 }, { "epoch": 1.04, "learning_rate": 1.5388489221957557e-05, "loss": 0.4069, "step": 557 }, { "epoch": 1.04, "learning_rate": 1.5371326507972554e-05, "loss": 0.403, "step": 558 }, { "epoch": 1.04, "learning_rate": 1.535414152762399e-05, "loss": 0.3865, "step": 559 }, { "epoch": 1.04, "learning_rate": 1.5336934352150687e-05, "loss": 0.3823, "step": 560 }, { "epoch": 1.05, "learning_rate": 1.5319705052883488e-05, "loss": 0.379, "step": 561 }, { "epoch": 1.05, "learning_rate": 1.5302453701244946e-05, "loss": 0.3811, "step": 562 }, { "epoch": 1.05, "learning_rate": 1.5285180368749023e-05, "loss": 0.3532, "step": 563 }, { "epoch": 1.05, "learning_rate": 1.5267885127000812e-05, "loss": 0.3419, "step": 564 }, { "epoch": 1.05, "learning_rate": 1.5250568047696217e-05, "loss": 0.3836, "step": 565 }, { "epoch": 1.06, "learning_rate": 1.5233229202621678e-05, "loss": 0.3922, "step": 566 }, { "epoch": 1.06, "learning_rate": 1.5215868663653857e-05, "loss": 0.3562, "step": 567 }, { "epoch": 1.06, "learning_rate": 1.5198486502759344e-05, "loss": 0.3954, "step": 568 }, { "epoch": 1.06, "learning_rate": 1.5181082791994371e-05, "loss": 0.3544, "step": 569 }, { "epoch": 1.06, "learning_rate": 1.5163657603504491e-05, "loss": 0.341, "step": 570 }, { "epoch": 1.07, "learning_rate": 1.51462110095243e-05, "loss": 0.3826, "step": 571 }, { "epoch": 1.07, "learning_rate": 1.5128743082377124e-05, "loss": 0.3377, "step": 572 }, { "epoch": 1.07, "learning_rate": 1.5111253894474726e-05, "loss": 0.3907, "step": 573 }, { "epoch": 1.07, "learning_rate": 1.5093743518317001e-05, "loss": 0.3774, "step": 574 }, { "epoch": 1.07, "learning_rate": 1.5076212026491681e-05, "loss": 0.4162, "step": 575 }, { "epoch": 1.07, "learning_rate": 1.5058659491674028e-05, "loss": 0.3537, "step": 576 }, { "epoch": 1.08, "learning_rate": 1.5041085986626538e-05, "loss": 0.3547, "step": 577 }, { "epoch": 1.08, "learning_rate": 1.5023491584198639e-05, "loss": 0.3712, "step": 578 }, { "epoch": 1.08, "learning_rate": 1.5005876357326382e-05, "loss": 0.36, "step": 579 }, { "epoch": 1.08, "learning_rate": 1.4988240379032152e-05, "loss": 0.3936, "step": 580 }, { "epoch": 1.08, "learning_rate": 1.4970583722424349e-05, "loss": 0.3755, "step": 581 }, { "epoch": 1.09, "learning_rate": 1.4952906460697093e-05, "loss": 0.3702, "step": 582 }, { "epoch": 1.09, "learning_rate": 1.4935208667129933e-05, "loss": 0.3796, "step": 583 }, { "epoch": 1.09, "learning_rate": 1.4917490415087512e-05, "loss": 0.346, "step": 584 }, { "epoch": 1.09, "learning_rate": 1.48997517780193e-05, "loss": 0.3973, "step": 585 }, { "epoch": 1.09, "learning_rate": 1.488199282945926e-05, "loss": 0.3712, "step": 586 }, { "epoch": 1.1, "learning_rate": 1.4864213643025558e-05, "loss": 0.3508, "step": 587 }, { "epoch": 1.1, "learning_rate": 1.4846414292420253e-05, "loss": 0.3622, "step": 588 }, { "epoch": 1.1, "learning_rate": 1.4828594851428992e-05, "loss": 0.3939, "step": 589 }, { "epoch": 1.1, "learning_rate": 1.4810755393920715e-05, "loss": 0.3861, "step": 590 }, { "epoch": 1.1, "learning_rate": 1.4792895993847323e-05, "loss": 0.3759, "step": 591 }, { "epoch": 1.1, "learning_rate": 1.4775016725243396e-05, "loss": 0.3963, "step": 592 }, { "epoch": 1.11, "learning_rate": 1.4757117662225877e-05, "loss": 0.3715, "step": 593 }, { "epoch": 1.11, "learning_rate": 1.4739198878993764e-05, "loss": 0.3926, "step": 594 }, { "epoch": 1.11, "learning_rate": 1.4721260449827804e-05, "loss": 0.3706, "step": 595 }, { "epoch": 1.11, "learning_rate": 1.470330244909018e-05, "loss": 0.3617, "step": 596 }, { "epoch": 1.11, "learning_rate": 1.4685324951224217e-05, "loss": 0.4048, "step": 597 }, { "epoch": 1.12, "learning_rate": 1.4667328030754056e-05, "loss": 0.357, "step": 598 }, { "epoch": 1.12, "learning_rate": 1.464931176228435e-05, "loss": 0.3479, "step": 599 }, { "epoch": 1.12, "learning_rate": 1.463127622049997e-05, "loss": 0.371, "step": 600 }, { "epoch": 1.12, "learning_rate": 1.4613221480165665e-05, "loss": 0.3633, "step": 601 }, { "epoch": 1.12, "learning_rate": 1.4595147616125788e-05, "loss": 0.3645, "step": 602 }, { "epoch": 1.12, "learning_rate": 1.4577054703303954e-05, "loss": 0.3575, "step": 603 }, { "epoch": 1.13, "learning_rate": 1.4558942816702753e-05, "loss": 0.3594, "step": 604 }, { "epoch": 1.13, "learning_rate": 1.4540812031403419e-05, "loss": 0.3716, "step": 605 }, { "epoch": 1.13, "learning_rate": 1.4522662422565539e-05, "loss": 0.3654, "step": 606 }, { "epoch": 1.13, "learning_rate": 1.4504494065426724e-05, "loss": 0.3647, "step": 607 }, { "epoch": 1.13, "learning_rate": 1.448630703530231e-05, "loss": 0.3463, "step": 608 }, { "epoch": 1.14, "learning_rate": 1.4468101407585036e-05, "loss": 0.3829, "step": 609 }, { "epoch": 1.14, "learning_rate": 1.4449877257744734e-05, "loss": 0.358, "step": 610 }, { "epoch": 1.14, "learning_rate": 1.4431634661328025e-05, "loss": 0.3941, "step": 611 }, { "epoch": 1.14, "learning_rate": 1.4413373693957988e-05, "loss": 0.3868, "step": 612 }, { "epoch": 1.14, "learning_rate": 1.4395094431333875e-05, "loss": 0.3692, "step": 613 }, { "epoch": 1.15, "learning_rate": 1.4376796949230757e-05, "loss": 0.403, "step": 614 }, { "epoch": 1.15, "learning_rate": 1.4358481323499253e-05, "loss": 0.4218, "step": 615 }, { "epoch": 1.15, "learning_rate": 1.434014763006518e-05, "loss": 0.3833, "step": 616 }, { "epoch": 1.15, "learning_rate": 1.4321795944929258e-05, "loss": 0.3895, "step": 617 }, { "epoch": 1.15, "learning_rate": 1.4303426344166788e-05, "loss": 0.3817, "step": 618 }, { "epoch": 1.15, "learning_rate": 1.428503890392735e-05, "loss": 0.3755, "step": 619 }, { "epoch": 1.16, "learning_rate": 1.4266633700434458e-05, "loss": 0.4125, "step": 620 }, { "epoch": 1.16, "learning_rate": 1.4248210809985272e-05, "loss": 0.3652, "step": 621 }, { "epoch": 1.16, "learning_rate": 1.4229770308950275e-05, "loss": 0.4089, "step": 622 }, { "epoch": 1.16, "learning_rate": 1.4211312273772948e-05, "loss": 0.3614, "step": 623 }, { "epoch": 1.16, "learning_rate": 1.4192836780969454e-05, "loss": 0.4163, "step": 624 }, { "epoch": 1.17, "learning_rate": 1.4174343907128339e-05, "loss": 0.406, "step": 625 }, { "epoch": 1.17, "learning_rate": 1.4155833728910184e-05, "loss": 0.3963, "step": 626 }, { "epoch": 1.17, "learning_rate": 1.4137306323047311e-05, "loss": 0.3761, "step": 627 }, { "epoch": 1.17, "learning_rate": 1.4118761766343465e-05, "loss": 0.3995, "step": 628 }, { "epoch": 1.17, "learning_rate": 1.4100200135673478e-05, "loss": 0.3645, "step": 629 }, { "epoch": 1.18, "learning_rate": 1.4081621507982962e-05, "loss": 0.3608, "step": 630 }, { "epoch": 1.18, "learning_rate": 1.4063025960287995e-05, "loss": 0.3818, "step": 631 }, { "epoch": 1.18, "learning_rate": 1.4044413569674785e-05, "loss": 0.4102, "step": 632 }, { "epoch": 1.18, "learning_rate": 1.4025784413299372e-05, "loss": 0.3607, "step": 633 }, { "epoch": 1.18, "learning_rate": 1.4007138568387293e-05, "loss": 0.401, "step": 634 }, { "epoch": 1.18, "learning_rate": 1.3988476112233262e-05, "loss": 0.4044, "step": 635 }, { "epoch": 1.19, "learning_rate": 1.3969797122200857e-05, "loss": 0.3851, "step": 636 }, { "epoch": 1.19, "learning_rate": 1.3951101675722196e-05, "loss": 0.4053, "step": 637 }, { "epoch": 1.19, "learning_rate": 1.3932389850297611e-05, "loss": 0.381, "step": 638 }, { "epoch": 1.19, "learning_rate": 1.3913661723495344e-05, "loss": 0.3977, "step": 639 }, { "epoch": 1.19, "learning_rate": 1.3894917372951195e-05, "loss": 0.3884, "step": 640 }, { "epoch": 1.2, "learning_rate": 1.3876156876368232e-05, "loss": 0.354, "step": 641 }, { "epoch": 1.2, "learning_rate": 1.385738031151645e-05, "loss": 0.4014, "step": 642 }, { "epoch": 1.2, "learning_rate": 1.3838587756232453e-05, "loss": 0.3715, "step": 643 }, { "epoch": 1.2, "learning_rate": 1.3819779288419135e-05, "loss": 0.4122, "step": 644 }, { "epoch": 1.2, "learning_rate": 1.3800954986045348e-05, "loss": 0.3904, "step": 645 }, { "epoch": 1.21, "learning_rate": 1.378211492714559e-05, "loss": 0.4118, "step": 646 }, { "epoch": 1.21, "learning_rate": 1.3763259189819677e-05, "loss": 0.4016, "step": 647 }, { "epoch": 1.21, "learning_rate": 1.3744387852232418e-05, "loss": 0.4109, "step": 648 }, { "epoch": 1.21, "learning_rate": 1.3725500992613284e-05, "loss": 0.3762, "step": 649 }, { "epoch": 1.21, "learning_rate": 1.3706598689256101e-05, "loss": 0.377, "step": 650 }, { "epoch": 1.21, "learning_rate": 1.3687681020518713e-05, "loss": 0.382, "step": 651 }, { "epoch": 1.22, "learning_rate": 1.3668748064822657e-05, "loss": 0.3669, "step": 652 }, { "epoch": 1.22, "learning_rate": 1.3649799900652843e-05, "loss": 0.3864, "step": 653 }, { "epoch": 1.22, "learning_rate": 1.3630836606557222e-05, "loss": 0.3423, "step": 654 }, { "epoch": 1.22, "learning_rate": 1.3611858261146478e-05, "loss": 0.3926, "step": 655 }, { "epoch": 1.22, "learning_rate": 1.3592864943093671e-05, "loss": 0.3852, "step": 656 }, { "epoch": 1.23, "learning_rate": 1.3573856731133941e-05, "loss": 0.3835, "step": 657 }, { "epoch": 1.23, "learning_rate": 1.3554833704064168e-05, "loss": 0.3948, "step": 658 }, { "epoch": 1.23, "learning_rate": 1.3535795940742635e-05, "loss": 0.401, "step": 659 }, { "epoch": 1.23, "learning_rate": 1.3516743520088736e-05, "loss": 0.3847, "step": 660 }, { "epoch": 1.23, "learning_rate": 1.3497676521082603e-05, "loss": 0.3751, "step": 661 }, { "epoch": 1.24, "learning_rate": 1.3478595022764811e-05, "loss": 0.3891, "step": 662 }, { "epoch": 1.24, "learning_rate": 1.3459499104236042e-05, "loss": 0.3658, "step": 663 }, { "epoch": 1.24, "learning_rate": 1.3440388844656754e-05, "loss": 0.3992, "step": 664 }, { "epoch": 1.24, "learning_rate": 1.3421264323246849e-05, "loss": 0.3788, "step": 665 }, { "epoch": 1.24, "learning_rate": 1.3402125619285364e-05, "loss": 0.3797, "step": 666 }, { "epoch": 1.24, "learning_rate": 1.3382972812110111e-05, "loss": 0.3683, "step": 667 }, { "epoch": 1.25, "learning_rate": 1.3363805981117383e-05, "loss": 0.3783, "step": 668 }, { "epoch": 1.25, "learning_rate": 1.3344625205761592e-05, "loss": 0.3937, "step": 669 }, { "epoch": 1.25, "learning_rate": 1.332543056555497e-05, "loss": 0.3972, "step": 670 }, { "epoch": 1.25, "learning_rate": 1.3306222140067206e-05, "loss": 0.3854, "step": 671 }, { "epoch": 1.25, "learning_rate": 1.3287000008925156e-05, "loss": 0.382, "step": 672 }, { "epoch": 1.26, "learning_rate": 1.3267764251812473e-05, "loss": 0.3957, "step": 673 }, { "epoch": 1.26, "learning_rate": 1.3248514948469309e-05, "loss": 0.3648, "step": 674 }, { "epoch": 1.26, "learning_rate": 1.3229252178691962e-05, "loss": 0.3754, "step": 675 }, { "epoch": 1.26, "learning_rate": 1.3209976022332557e-05, "loss": 0.3834, "step": 676 }, { "epoch": 1.26, "learning_rate": 1.3190686559298715e-05, "loss": 0.3695, "step": 677 }, { "epoch": 1.26, "learning_rate": 1.3171383869553211e-05, "loss": 0.3573, "step": 678 }, { "epoch": 1.27, "learning_rate": 1.3152068033113657e-05, "loss": 0.3741, "step": 679 }, { "epoch": 1.27, "learning_rate": 1.3132739130052157e-05, "loss": 0.3921, "step": 680 }, { "epoch": 1.27, "learning_rate": 1.3113397240494994e-05, "loss": 0.3843, "step": 681 }, { "epoch": 1.27, "learning_rate": 1.3094042444622268e-05, "loss": 0.3763, "step": 682 }, { "epoch": 1.27, "learning_rate": 1.3074674822667595e-05, "loss": 0.3667, "step": 683 }, { "epoch": 1.28, "learning_rate": 1.3055294454917757e-05, "loss": 0.3574, "step": 684 }, { "epoch": 1.28, "learning_rate": 1.3035901421712364e-05, "loss": 0.3757, "step": 685 }, { "epoch": 1.28, "learning_rate": 1.3016495803443545e-05, "loss": 0.4049, "step": 686 }, { "epoch": 1.28, "learning_rate": 1.2997077680555586e-05, "loss": 0.3794, "step": 687 }, { "epoch": 1.28, "learning_rate": 1.2977647133544615e-05, "loss": 0.3702, "step": 688 }, { "epoch": 1.29, "learning_rate": 1.2958204242958262e-05, "loss": 0.3777, "step": 689 }, { "epoch": 1.29, "learning_rate": 1.293874908939533e-05, "loss": 0.3633, "step": 690 }, { "epoch": 1.29, "learning_rate": 1.2919281753505451e-05, "loss": 0.3777, "step": 691 }, { "epoch": 1.29, "learning_rate": 1.2899802315988762e-05, "loss": 0.3591, "step": 692 }, { "epoch": 1.29, "learning_rate": 1.2880310857595567e-05, "loss": 0.3358, "step": 693 }, { "epoch": 1.29, "learning_rate": 1.2860807459125993e-05, "loss": 0.3695, "step": 694 }, { "epoch": 1.3, "learning_rate": 1.2841292201429678e-05, "loss": 0.3681, "step": 695 }, { "epoch": 1.3, "learning_rate": 1.2821765165405408e-05, "loss": 0.3678, "step": 696 }, { "epoch": 1.3, "learning_rate": 1.2802226432000807e-05, "loss": 0.3644, "step": 697 }, { "epoch": 1.3, "learning_rate": 1.278267608221197e-05, "loss": 0.4113, "step": 698 }, { "epoch": 1.3, "learning_rate": 1.2763114197083176e-05, "loss": 0.3482, "step": 699 }, { "epoch": 1.31, "learning_rate": 1.2743540857706493e-05, "loss": 0.3748, "step": 700 }, { "epoch": 1.31, "learning_rate": 1.2723956145221495e-05, "loss": 0.3642, "step": 701 }, { "epoch": 1.31, "learning_rate": 1.2704360140814883e-05, "loss": 0.3577, "step": 702 }, { "epoch": 1.31, "learning_rate": 1.2684752925720183e-05, "loss": 0.3767, "step": 703 }, { "epoch": 1.31, "learning_rate": 1.266513458121739e-05, "loss": 0.3669, "step": 704 }, { "epoch": 1.32, "learning_rate": 1.2645505188632621e-05, "loss": 0.3396, "step": 705 }, { "epoch": 1.32, "learning_rate": 1.2625864829337818e-05, "loss": 0.3628, "step": 706 }, { "epoch": 1.32, "learning_rate": 1.260621358475036e-05, "loss": 0.3734, "step": 707 }, { "epoch": 1.32, "learning_rate": 1.2586551536332766e-05, "loss": 0.3571, "step": 708 }, { "epoch": 1.32, "learning_rate": 1.2566878765592332e-05, "loss": 0.3921, "step": 709 }, { "epoch": 1.32, "learning_rate": 1.254719535408081e-05, "loss": 0.3503, "step": 710 }, { "epoch": 1.33, "learning_rate": 1.2527501383394052e-05, "loss": 0.3705, "step": 711 }, { "epoch": 1.33, "learning_rate": 1.2507796935171697e-05, "loss": 0.3682, "step": 712 }, { "epoch": 1.33, "learning_rate": 1.2488082091096802e-05, "loss": 0.3681, "step": 713 }, { "epoch": 1.33, "learning_rate": 1.2468356932895529e-05, "loss": 0.3603, "step": 714 }, { "epoch": 1.33, "learning_rate": 1.2448621542336794e-05, "loss": 0.3438, "step": 715 }, { "epoch": 1.34, "learning_rate": 1.2428876001231926e-05, "loss": 0.3718, "step": 716 }, { "epoch": 1.34, "learning_rate": 1.2409120391434344e-05, "loss": 0.3664, "step": 717 }, { "epoch": 1.34, "learning_rate": 1.238935479483919e-05, "loss": 0.3501, "step": 718 }, { "epoch": 1.34, "learning_rate": 1.2369579293383018e-05, "loss": 0.386, "step": 719 }, { "epoch": 1.34, "learning_rate": 1.2349793969043436e-05, "loss": 0.3729, "step": 720 }, { "epoch": 1.35, "learning_rate": 1.2329998903838773e-05, "loss": 0.3455, "step": 721 }, { "epoch": 1.35, "learning_rate": 1.2310194179827737e-05, "loss": 0.371, "step": 722 }, { "epoch": 1.35, "learning_rate": 1.229037987910908e-05, "loss": 0.3442, "step": 723 }, { "epoch": 1.35, "learning_rate": 1.2270556083821246e-05, "loss": 0.3827, "step": 724 }, { "epoch": 1.35, "learning_rate": 1.2250722876142046e-05, "loss": 0.3495, "step": 725 }, { "epoch": 1.35, "learning_rate": 1.2230880338288302e-05, "loss": 0.3437, "step": 726 }, { "epoch": 1.36, "learning_rate": 1.2211028552515516e-05, "loss": 0.3413, "step": 727 }, { "epoch": 1.36, "learning_rate": 1.2191167601117533e-05, "loss": 0.3272, "step": 728 }, { "epoch": 1.36, "learning_rate": 1.2171297566426178e-05, "loss": 0.3683, "step": 729 }, { "epoch": 1.36, "learning_rate": 1.215141853081095e-05, "loss": 0.3595, "step": 730 }, { "epoch": 1.36, "learning_rate": 1.2131530576678643e-05, "loss": 0.3334, "step": 731 }, { "epoch": 1.37, "learning_rate": 1.2111633786473029e-05, "loss": 0.3891, "step": 732 }, { "epoch": 1.37, "learning_rate": 1.2091728242674512e-05, "loss": 0.3524, "step": 733 }, { "epoch": 1.37, "learning_rate": 1.2071814027799777e-05, "loss": 0.3538, "step": 734 }, { "epoch": 1.37, "learning_rate": 1.205189122440146e-05, "loss": 0.3533, "step": 735 }, { "epoch": 1.37, "learning_rate": 1.20319599150678e-05, "loss": 0.3478, "step": 736 }, { "epoch": 1.38, "learning_rate": 1.2012020182422288e-05, "loss": 0.3661, "step": 737 }, { "epoch": 1.38, "learning_rate": 1.1992072109123341e-05, "loss": 0.3599, "step": 738 }, { "epoch": 1.38, "learning_rate": 1.1972115777863953e-05, "loss": 0.368, "step": 739 }, { "epoch": 1.38, "learning_rate": 1.1952151271371341e-05, "loss": 0.3809, "step": 740 }, { "epoch": 1.38, "learning_rate": 1.1932178672406626e-05, "loss": 0.3681, "step": 741 }, { "epoch": 1.38, "learning_rate": 1.1912198063764461e-05, "loss": 0.3481, "step": 742 }, { "epoch": 1.39, "learning_rate": 1.1892209528272713e-05, "loss": 0.358, "step": 743 }, { "epoch": 1.39, "learning_rate": 1.1872213148792105e-05, "loss": 0.324, "step": 744 }, { "epoch": 1.39, "learning_rate": 1.1852209008215873e-05, "loss": 0.3165, "step": 745 }, { "epoch": 1.39, "learning_rate": 1.1832197189469434e-05, "loss": 0.3708, "step": 746 }, { "epoch": 1.39, "learning_rate": 1.1812177775510024e-05, "loss": 0.3711, "step": 747 }, { "epoch": 1.4, "learning_rate": 1.1792150849326377e-05, "loss": 0.3518, "step": 748 }, { "epoch": 1.4, "learning_rate": 1.177211649393836e-05, "loss": 0.358, "step": 749 }, { "epoch": 1.4, "learning_rate": 1.1752074792396633e-05, "loss": 0.3619, "step": 750 }, { "epoch": 1.4, "learning_rate": 1.1732025827782318e-05, "loss": 0.3799, "step": 751 }, { "epoch": 1.4, "learning_rate": 1.1711969683206644e-05, "loss": 0.3274, "step": 752 }, { "epoch": 1.4, "learning_rate": 1.1691906441810595e-05, "loss": 0.3339, "step": 753 }, { "epoch": 1.41, "learning_rate": 1.1671836186764587e-05, "loss": 0.3332, "step": 754 }, { "epoch": 1.41, "learning_rate": 1.1651759001268102e-05, "loss": 0.357, "step": 755 }, { "epoch": 1.41, "learning_rate": 1.1631674968549356e-05, "loss": 0.3491, "step": 756 }, { "epoch": 1.41, "learning_rate": 1.1611584171864947e-05, "loss": 0.3435, "step": 757 }, { "epoch": 1.41, "learning_rate": 1.1591486694499507e-05, "loss": 0.3503, "step": 758 }, { "epoch": 1.42, "learning_rate": 1.1571382619765376e-05, "loss": 0.3277, "step": 759 }, { "epoch": 1.42, "learning_rate": 1.155127203100223e-05, "loss": 0.3349, "step": 760 }, { "epoch": 1.42, "learning_rate": 1.1531155011576758e-05, "loss": 0.3291, "step": 761 }, { "epoch": 1.42, "learning_rate": 1.1511031644882295e-05, "loss": 0.3253, "step": 762 }, { "epoch": 1.42, "learning_rate": 1.1490902014338503e-05, "loss": 0.3405, "step": 763 }, { "epoch": 1.43, "learning_rate": 1.1470766203390995e-05, "loss": 0.3368, "step": 764 }, { "epoch": 1.43, "learning_rate": 1.1450624295511017e-05, "loss": 0.367, "step": 765 }, { "epoch": 1.43, "learning_rate": 1.1430476374195081e-05, "loss": 0.3646, "step": 766 }, { "epoch": 1.43, "learning_rate": 1.1410322522964632e-05, "loss": 0.3149, "step": 767 }, { "epoch": 1.43, "learning_rate": 1.1390162825365691e-05, "loss": 0.3448, "step": 768 }, { "epoch": 1.43, "learning_rate": 1.1369997364968524e-05, "loss": 0.3352, "step": 769 }, { "epoch": 1.44, "learning_rate": 1.1349826225367277e-05, "loss": 0.3544, "step": 770 }, { "epoch": 1.44, "learning_rate": 1.1329649490179642e-05, "loss": 0.3528, "step": 771 }, { "epoch": 1.44, "learning_rate": 1.1309467243046513e-05, "loss": 0.3369, "step": 772 }, { "epoch": 1.44, "learning_rate": 1.128927956763162e-05, "loss": 0.3289, "step": 773 }, { "epoch": 1.44, "learning_rate": 1.1269086547621209e-05, "loss": 0.3416, "step": 774 }, { "epoch": 1.45, "learning_rate": 1.1248888266723672e-05, "loss": 0.339, "step": 775 }, { "epoch": 1.45, "learning_rate": 1.1228684808669217e-05, "loss": 0.3573, "step": 776 }, { "epoch": 1.45, "learning_rate": 1.1208476257209507e-05, "loss": 0.3474, "step": 777 }, { "epoch": 1.45, "learning_rate": 1.1188262696117323e-05, "loss": 0.3662, "step": 778 }, { "epoch": 1.45, "learning_rate": 1.1168044209186214e-05, "loss": 0.333, "step": 779 }, { "epoch": 1.46, "learning_rate": 1.114782088023014e-05, "loss": 0.3379, "step": 780 }, { "epoch": 1.46, "learning_rate": 1.1127592793083147e-05, "loss": 0.3634, "step": 781 }, { "epoch": 1.46, "learning_rate": 1.1107360031598993e-05, "loss": 0.3347, "step": 782 }, { "epoch": 1.46, "learning_rate": 1.1087122679650825e-05, "loss": 0.326, "step": 783 }, { "epoch": 1.46, "learning_rate": 1.106688082113081e-05, "loss": 0.309, "step": 784 }, { "epoch": 1.46, "learning_rate": 1.1046634539949797e-05, "loss": 0.3536, "step": 785 }, { "epoch": 1.47, "learning_rate": 1.1026383920036972e-05, "loss": 0.3721, "step": 786 }, { "epoch": 1.47, "learning_rate": 1.100612904533951e-05, "loss": 0.3393, "step": 787 }, { "epoch": 1.47, "learning_rate": 1.0985869999822212e-05, "loss": 0.3555, "step": 788 }, { "epoch": 1.47, "learning_rate": 1.0965606867467187e-05, "loss": 0.3223, "step": 789 }, { "epoch": 1.47, "learning_rate": 1.0945339732273468e-05, "loss": 0.3207, "step": 790 }, { "epoch": 1.48, "learning_rate": 1.092506867825669e-05, "loss": 0.3574, "step": 791 }, { "epoch": 1.48, "learning_rate": 1.0904793789448736e-05, "loss": 0.3276, "step": 792 }, { "epoch": 1.48, "learning_rate": 1.0884515149897372e-05, "loss": 0.319, "step": 793 }, { "epoch": 1.48, "learning_rate": 1.0864232843665935e-05, "loss": 0.3429, "step": 794 }, { "epoch": 1.48, "learning_rate": 1.0843946954832939e-05, "loss": 0.3168, "step": 795 }, { "epoch": 1.49, "learning_rate": 1.0823657567491765e-05, "loss": 0.3329, "step": 796 }, { "epoch": 1.49, "learning_rate": 1.0803364765750285e-05, "loss": 0.3505, "step": 797 }, { "epoch": 1.49, "learning_rate": 1.078306863373054e-05, "loss": 0.3174, "step": 798 }, { "epoch": 1.49, "learning_rate": 1.076276925556836e-05, "loss": 0.3367, "step": 799 }, { "epoch": 1.49, "learning_rate": 1.0742466715413043e-05, "loss": 0.3193, "step": 800 }, { "epoch": 1.49, "learning_rate": 1.072216109742699e-05, "loss": 0.3195, "step": 801 }, { "epoch": 1.5, "learning_rate": 1.070185248578536e-05, "loss": 0.3146, "step": 802 }, { "epoch": 1.5, "learning_rate": 1.0681540964675727e-05, "loss": 0.3305, "step": 803 }, { "epoch": 1.5, "learning_rate": 1.066122661829772e-05, "loss": 0.3639, "step": 804 }, { "epoch": 1.5, "learning_rate": 1.0640909530862685e-05, "loss": 0.3153, "step": 805 }, { "epoch": 1.5, "learning_rate": 1.0620589786593322e-05, "loss": 0.3234, "step": 806 }, { "epoch": 1.51, "learning_rate": 1.060026746972336e-05, "loss": 0.3509, "step": 807 }, { "epoch": 1.51, "learning_rate": 1.0579942664497178e-05, "loss": 0.3351, "step": 808 }, { "epoch": 1.51, "learning_rate": 1.0559615455169479e-05, "loss": 0.3396, "step": 809 }, { "epoch": 1.51, "learning_rate": 1.0539285926004927e-05, "loss": 0.343, "step": 810 }, { "epoch": 1.51, "learning_rate": 1.0518954161277802e-05, "loss": 0.3223, "step": 811 }, { "epoch": 1.51, "learning_rate": 1.0498620245271657e-05, "loss": 0.3258, "step": 812 }, { "epoch": 1.52, "learning_rate": 1.0478284262278962e-05, "loss": 0.324, "step": 813 }, { "epoch": 1.52, "learning_rate": 1.045794629660075e-05, "loss": 0.3113, "step": 814 }, { "epoch": 1.52, "learning_rate": 1.0437606432546273e-05, "loss": 0.3582, "step": 815 }, { "epoch": 1.52, "learning_rate": 1.0417264754432664e-05, "loss": 0.3345, "step": 816 }, { "epoch": 1.52, "learning_rate": 1.0396921346584562e-05, "loss": 0.3112, "step": 817 }, { "epoch": 1.53, "learning_rate": 1.0376576293333784e-05, "loss": 0.3535, "step": 818 }, { "epoch": 1.53, "learning_rate": 1.0356229679018965e-05, "loss": 0.2943, "step": 819 }, { "epoch": 1.53, "learning_rate": 1.0335881587985217e-05, "loss": 0.333, "step": 820 }, { "epoch": 1.53, "learning_rate": 1.0315532104583765e-05, "loss": 0.2963, "step": 821 }, { "epoch": 1.53, "learning_rate": 1.0295181313171607e-05, "loss": 0.3607, "step": 822 }, { "epoch": 1.54, "learning_rate": 1.0274829298111175e-05, "loss": 0.3519, "step": 823 }, { "epoch": 1.54, "learning_rate": 1.0254476143769956e-05, "loss": 0.3162, "step": 824 }, { "epoch": 1.54, "learning_rate": 1.0234121934520173e-05, "loss": 0.3274, "step": 825 }, { "epoch": 1.54, "learning_rate": 1.0213766754738419e-05, "loss": 0.3266, "step": 826 }, { "epoch": 1.54, "learning_rate": 1.0193410688805306e-05, "loss": 0.339, "step": 827 }, { "epoch": 1.54, "learning_rate": 1.0173053821105124e-05, "loss": 0.3542, "step": 828 }, { "epoch": 1.55, "learning_rate": 1.0152696236025483e-05, "loss": 0.3336, "step": 829 }, { "epoch": 1.55, "learning_rate": 1.0132338017956968e-05, "loss": 0.3414, "step": 830 }, { "epoch": 1.55, "learning_rate": 1.0111979251292797e-05, "loss": 0.3164, "step": 831 }, { "epoch": 1.55, "learning_rate": 1.0091620020428446e-05, "loss": 0.3098, "step": 832 }, { "epoch": 1.55, "learning_rate": 1.0071260409761323e-05, "loss": 0.3303, "step": 833 }, { "epoch": 1.56, "learning_rate": 1.0050900503690414e-05, "loss": 0.316, "step": 834 }, { "epoch": 1.56, "learning_rate": 1.0030540386615926e-05, "loss": 0.3319, "step": 835 }, { "epoch": 1.56, "learning_rate": 1.0010180142938939e-05, "loss": 0.3699, "step": 836 }, { "epoch": 1.56, "learning_rate": 9.989819857061064e-06, "loss": 0.3425, "step": 837 }, { "epoch": 1.56, "learning_rate": 9.969459613384075e-06, "loss": 0.317, "step": 838 }, { "epoch": 1.57, "learning_rate": 9.94909949630959e-06, "loss": 0.3118, "step": 839 }, { "epoch": 1.57, "learning_rate": 9.92873959023868e-06, "loss": 0.3263, "step": 840 }, { "epoch": 1.57, "learning_rate": 9.908379979571558e-06, "loss": 0.3189, "step": 841 }, { "epoch": 1.57, "learning_rate": 9.888020748707208e-06, "loss": 0.358, "step": 842 }, { "epoch": 1.57, "learning_rate": 9.867661982043033e-06, "loss": 0.3257, "step": 843 }, { "epoch": 1.57, "learning_rate": 9.847303763974519e-06, "loss": 0.3345, "step": 844 }, { "epoch": 1.58, "learning_rate": 9.826946178894878e-06, "loss": 0.3115, "step": 845 }, { "epoch": 1.58, "learning_rate": 9.806589311194699e-06, "loss": 0.3689, "step": 846 }, { "epoch": 1.58, "learning_rate": 9.786233245261585e-06, "loss": 0.318, "step": 847 }, { "epoch": 1.58, "learning_rate": 9.765878065479828e-06, "loss": 0.3581, "step": 848 }, { "epoch": 1.58, "learning_rate": 9.745523856230044e-06, "loss": 0.3092, "step": 849 }, { "epoch": 1.59, "learning_rate": 9.725170701888831e-06, "loss": 0.3257, "step": 850 }, { "epoch": 1.59, "learning_rate": 9.704818686828395e-06, "loss": 0.3293, "step": 851 }, { "epoch": 1.59, "learning_rate": 9.684467895416238e-06, "loss": 0.333, "step": 852 }, { "epoch": 1.59, "learning_rate": 9.664118412014788e-06, "loss": 0.327, "step": 853 }, { "epoch": 1.59, "learning_rate": 9.643770320981037e-06, "loss": 0.289, "step": 854 }, { "epoch": 1.6, "learning_rate": 9.62342370666622e-06, "loss": 0.3192, "step": 855 }, { "epoch": 1.6, "learning_rate": 9.60307865341544e-06, "loss": 0.3244, "step": 856 }, { "epoch": 1.6, "learning_rate": 9.58273524556734e-06, "loss": 0.3029, "step": 857 }, { "epoch": 1.6, "learning_rate": 9.562393567453729e-06, "loss": 0.3133, "step": 858 }, { "epoch": 1.6, "learning_rate": 9.542053703399254e-06, "loss": 0.3043, "step": 859 }, { "epoch": 1.6, "learning_rate": 9.52171573772104e-06, "loss": 0.3037, "step": 860 }, { "epoch": 1.61, "learning_rate": 9.501379754728346e-06, "loss": 0.3297, "step": 861 }, { "epoch": 1.61, "learning_rate": 9.481045838722201e-06, "loss": 0.33, "step": 862 }, { "epoch": 1.61, "learning_rate": 9.460714073995076e-06, "loss": 0.3185, "step": 863 }, { "epoch": 1.61, "learning_rate": 9.440384544830526e-06, "loss": 0.3082, "step": 864 }, { "epoch": 1.61, "learning_rate": 9.420057335502826e-06, "loss": 0.3339, "step": 865 }, { "epoch": 1.62, "learning_rate": 9.399732530276644e-06, "loss": 0.3174, "step": 866 }, { "epoch": 1.62, "learning_rate": 9.37941021340668e-06, "loss": 0.3185, "step": 867 }, { "epoch": 1.62, "learning_rate": 9.359090469137322e-06, "loss": 0.3139, "step": 868 }, { "epoch": 1.62, "learning_rate": 9.338773381702285e-06, "loss": 0.3273, "step": 869 }, { "epoch": 1.62, "learning_rate": 9.318459035324274e-06, "loss": 0.3477, "step": 870 }, { "epoch": 1.62, "learning_rate": 9.298147514214641e-06, "loss": 0.3324, "step": 871 }, { "epoch": 1.63, "learning_rate": 9.277838902573013e-06, "loss": 0.3116, "step": 872 }, { "epoch": 1.63, "learning_rate": 9.25753328458696e-06, "loss": 0.3017, "step": 873 }, { "epoch": 1.63, "learning_rate": 9.23723074443164e-06, "loss": 0.3471, "step": 874 }, { "epoch": 1.63, "learning_rate": 9.216931366269462e-06, "loss": 0.3404, "step": 875 }, { "epoch": 1.63, "learning_rate": 9.196635234249716e-06, "loss": 0.3135, "step": 876 }, { "epoch": 1.64, "learning_rate": 9.176342432508239e-06, "loss": 0.3366, "step": 877 }, { "epoch": 1.64, "learning_rate": 9.156053045167061e-06, "loss": 0.2991, "step": 878 }, { "epoch": 1.64, "learning_rate": 9.13576715633407e-06, "loss": 0.3101, "step": 879 }, { "epoch": 1.64, "learning_rate": 9.11548485010263e-06, "loss": 0.3134, "step": 880 }, { "epoch": 1.64, "learning_rate": 9.095206210551268e-06, "loss": 0.3236, "step": 881 }, { "epoch": 1.65, "learning_rate": 9.074931321743312e-06, "loss": 0.3121, "step": 882 }, { "epoch": 1.65, "learning_rate": 9.054660267726537e-06, "loss": 0.3209, "step": 883 }, { "epoch": 1.65, "learning_rate": 9.034393132532818e-06, "loss": 0.2728, "step": 884 }, { "epoch": 1.65, "learning_rate": 9.014130000177788e-06, "loss": 0.3143, "step": 885 }, { "epoch": 1.65, "learning_rate": 8.993870954660496e-06, "loss": 0.3105, "step": 886 }, { "epoch": 1.65, "learning_rate": 8.973616079963031e-06, "loss": 0.3279, "step": 887 }, { "epoch": 1.66, "learning_rate": 8.953365460050206e-06, "loss": 0.2954, "step": 888 }, { "epoch": 1.66, "learning_rate": 8.933119178869194e-06, "loss": 0.3066, "step": 889 }, { "epoch": 1.66, "learning_rate": 8.912877320349176e-06, "loss": 0.3175, "step": 890 }, { "epoch": 1.66, "learning_rate": 8.892639968401009e-06, "loss": 0.3232, "step": 891 }, { "epoch": 1.66, "learning_rate": 8.872407206916856e-06, "loss": 0.376, "step": 892 }, { "epoch": 1.67, "learning_rate": 8.852179119769861e-06, "loss": 0.3056, "step": 893 }, { "epoch": 1.67, "learning_rate": 8.831955790813793e-06, "loss": 0.3037, "step": 894 }, { "epoch": 1.67, "learning_rate": 8.81173730388268e-06, "loss": 0.3036, "step": 895 }, { "epoch": 1.67, "learning_rate": 8.791523742790495e-06, "loss": 0.2926, "step": 896 }, { "epoch": 1.67, "learning_rate": 8.771315191330788e-06, "loss": 0.3233, "step": 897 }, { "epoch": 1.68, "learning_rate": 8.751111733276331e-06, "loss": 0.3128, "step": 898 }, { "epoch": 1.68, "learning_rate": 8.730913452378795e-06, "loss": 0.3192, "step": 899 }, { "epoch": 1.68, "learning_rate": 8.710720432368382e-06, "loss": 0.331, "step": 900 }, { "epoch": 1.68, "learning_rate": 8.690532756953494e-06, "loss": 0.3483, "step": 901 }, { "epoch": 1.68, "learning_rate": 8.67035050982036e-06, "loss": 0.3207, "step": 902 }, { "epoch": 1.68, "learning_rate": 8.650173774632727e-06, "loss": 0.3067, "step": 903 }, { "epoch": 1.69, "learning_rate": 8.63000263503148e-06, "loss": 0.3006, "step": 904 }, { "epoch": 1.69, "learning_rate": 8.609837174634312e-06, "loss": 0.3197, "step": 905 }, { "epoch": 1.69, "learning_rate": 8.589677477035372e-06, "loss": 0.3127, "step": 906 }, { "epoch": 1.69, "learning_rate": 8.569523625804922e-06, "loss": 0.2825, "step": 907 }, { "epoch": 1.69, "learning_rate": 8.549375704488988e-06, "loss": 0.3252, "step": 908 }, { "epoch": 1.7, "learning_rate": 8.52923379660901e-06, "loss": 0.347, "step": 909 }, { "epoch": 1.7, "learning_rate": 8.509097985661502e-06, "loss": 0.2836, "step": 910 }, { "epoch": 1.7, "learning_rate": 8.488968355117706e-06, "loss": 0.3397, "step": 911 }, { "epoch": 1.7, "learning_rate": 8.468844988423247e-06, "loss": 0.3264, "step": 912 }, { "epoch": 1.7, "learning_rate": 8.448727968997772e-06, "loss": 0.3229, "step": 913 }, { "epoch": 1.71, "learning_rate": 8.428617380234626e-06, "loss": 0.3004, "step": 914 }, { "epoch": 1.71, "learning_rate": 8.408513305500493e-06, "loss": 0.3105, "step": 915 }, { "epoch": 1.71, "learning_rate": 8.38841582813506e-06, "loss": 0.2887, "step": 916 }, { "epoch": 1.71, "learning_rate": 8.368325031450648e-06, "loss": 0.3139, "step": 917 }, { "epoch": 1.71, "learning_rate": 8.348240998731898e-06, "loss": 0.2922, "step": 918 }, { "epoch": 1.71, "learning_rate": 8.328163813235418e-06, "loss": 0.2939, "step": 919 }, { "epoch": 1.72, "learning_rate": 8.308093558189408e-06, "loss": 0.2952, "step": 920 }, { "epoch": 1.72, "learning_rate": 8.288030316793361e-06, "loss": 0.3009, "step": 921 }, { "epoch": 1.72, "learning_rate": 8.267974172217683e-06, "loss": 0.3113, "step": 922 }, { "epoch": 1.72, "learning_rate": 8.247925207603372e-06, "loss": 0.3074, "step": 923 }, { "epoch": 1.72, "learning_rate": 8.227883506061645e-06, "loss": 0.2949, "step": 924 }, { "epoch": 1.73, "learning_rate": 8.207849150673626e-06, "loss": 0.2965, "step": 925 }, { "epoch": 1.73, "learning_rate": 8.187822224489977e-06, "loss": 0.2847, "step": 926 }, { "epoch": 1.73, "learning_rate": 8.16780281053057e-06, "loss": 0.3044, "step": 927 }, { "epoch": 1.73, "learning_rate": 8.14779099178413e-06, "loss": 0.3193, "step": 928 }, { "epoch": 1.73, "learning_rate": 8.127786851207897e-06, "loss": 0.3317, "step": 929 }, { "epoch": 1.74, "learning_rate": 8.10779047172729e-06, "loss": 0.2743, "step": 930 }, { "epoch": 1.74, "learning_rate": 8.08780193623554e-06, "loss": 0.262, "step": 931 }, { "epoch": 1.74, "learning_rate": 8.067821327593375e-06, "loss": 0.2912, "step": 932 }, { "epoch": 1.74, "learning_rate": 8.047848728628659e-06, "loss": 0.2962, "step": 933 }, { "epoch": 1.74, "learning_rate": 8.027884222136052e-06, "loss": 0.3107, "step": 934 }, { "epoch": 1.74, "learning_rate": 8.007927890876662e-06, "loss": 0.3286, "step": 935 }, { "epoch": 1.75, "learning_rate": 7.987979817577715e-06, "loss": 0.2858, "step": 936 }, { "epoch": 1.75, "learning_rate": 7.968040084932202e-06, "loss": 0.2903, "step": 937 }, { "epoch": 1.75, "learning_rate": 7.948108775598542e-06, "loss": 0.2515, "step": 938 }, { "epoch": 1.75, "learning_rate": 7.928185972200224e-06, "loss": 0.2926, "step": 939 }, { "epoch": 1.75, "learning_rate": 7.90827175732549e-06, "loss": 0.2931, "step": 940 }, { "epoch": 1.76, "learning_rate": 7.888366213526975e-06, "loss": 0.282, "step": 941 }, { "epoch": 1.76, "learning_rate": 7.86846942332136e-06, "loss": 0.2778, "step": 942 }, { "epoch": 1.76, "learning_rate": 7.848581469189054e-06, "loss": 0.2925, "step": 943 }, { "epoch": 1.76, "learning_rate": 7.828702433573823e-06, "loss": 0.3086, "step": 944 }, { "epoch": 1.76, "learning_rate": 7.808832398882472e-06, "loss": 0.288, "step": 945 }, { "epoch": 1.76, "learning_rate": 7.788971447484486e-06, "loss": 0.3148, "step": 946 }, { "epoch": 1.77, "learning_rate": 7.7691196617117e-06, "loss": 0.2861, "step": 947 }, { "epoch": 1.77, "learning_rate": 7.749277123857956e-06, "loss": 0.3122, "step": 948 }, { "epoch": 1.77, "learning_rate": 7.729443916178758e-06, "loss": 0.3141, "step": 949 }, { "epoch": 1.77, "learning_rate": 7.709620120890922e-06, "loss": 0.3012, "step": 950 }, { "epoch": 1.77, "learning_rate": 7.689805820172264e-06, "loss": 0.3244, "step": 951 }, { "epoch": 1.78, "learning_rate": 7.670001096161232e-06, "loss": 0.2879, "step": 952 }, { "epoch": 1.78, "learning_rate": 7.650206030956569e-06, "loss": 0.2848, "step": 953 }, { "epoch": 1.78, "learning_rate": 7.630420706616984e-06, "loss": 0.2828, "step": 954 }, { "epoch": 1.78, "learning_rate": 7.610645205160812e-06, "loss": 0.3005, "step": 955 }, { "epoch": 1.78, "learning_rate": 7.590879608565662e-06, "loss": 0.3139, "step": 956 }, { "epoch": 1.79, "learning_rate": 7.571123998768076e-06, "loss": 0.276, "step": 957 }, { "epoch": 1.79, "learning_rate": 7.5513784576632085e-06, "loss": 0.2957, "step": 958 }, { "epoch": 1.79, "learning_rate": 7.531643067104476e-06, "loss": 0.2802, "step": 959 }, { "epoch": 1.79, "learning_rate": 7.511917908903202e-06, "loss": 0.2987, "step": 960 }, { "epoch": 1.79, "learning_rate": 7.492203064828307e-06, "loss": 0.2765, "step": 961 }, { "epoch": 1.79, "learning_rate": 7.472498616605948e-06, "loss": 0.2787, "step": 962 }, { "epoch": 1.8, "learning_rate": 7.452804645919194e-06, "loss": 0.2976, "step": 963 }, { "epoch": 1.8, "learning_rate": 7.43312123440767e-06, "loss": 0.3024, "step": 964 }, { "epoch": 1.8, "learning_rate": 7.413448463667237e-06, "loss": 0.288, "step": 965 }, { "epoch": 1.8, "learning_rate": 7.39378641524964e-06, "loss": 0.2916, "step": 966 }, { "epoch": 1.8, "learning_rate": 7.374135170662186e-06, "loss": 0.3152, "step": 967 }, { "epoch": 1.81, "learning_rate": 7.354494811367381e-06, "loss": 0.2736, "step": 968 }, { "epoch": 1.81, "learning_rate": 7.334865418782615e-06, "loss": 0.2788, "step": 969 }, { "epoch": 1.81, "learning_rate": 7.315247074279821e-06, "loss": 0.2957, "step": 970 }, { "epoch": 1.81, "learning_rate": 7.29563985918512e-06, "loss": 0.2964, "step": 971 }, { "epoch": 1.81, "learning_rate": 7.276043854778509e-06, "loss": 0.3048, "step": 972 }, { "epoch": 1.82, "learning_rate": 7.256459142293507e-06, "loss": 0.2943, "step": 973 }, { "epoch": 1.82, "learning_rate": 7.2368858029168285e-06, "loss": 0.2757, "step": 974 }, { "epoch": 1.82, "learning_rate": 7.217323917788031e-06, "loss": 0.3006, "step": 975 }, { "epoch": 1.82, "learning_rate": 7.197773567999197e-06, "loss": 0.2963, "step": 976 }, { "epoch": 1.82, "learning_rate": 7.178234834594593e-06, "loss": 0.3173, "step": 977 }, { "epoch": 1.82, "learning_rate": 7.1587077985703245e-06, "loss": 0.3053, "step": 978 }, { "epoch": 1.83, "learning_rate": 7.139192540874009e-06, "loss": 0.4696, "step": 979 }, { "epoch": 1.83, "learning_rate": 7.119689142404437e-06, "loss": 0.2859, "step": 980 }, { "epoch": 1.83, "learning_rate": 7.100197684011241e-06, "loss": 0.3192, "step": 981 }, { "epoch": 1.83, "learning_rate": 7.080718246494553e-06, "loss": 0.2785, "step": 982 }, { "epoch": 1.83, "learning_rate": 7.061250910604674e-06, "loss": 0.2969, "step": 983 }, { "epoch": 1.84, "learning_rate": 7.041795757041738e-06, "loss": 0.3096, "step": 984 }, { "epoch": 1.84, "learning_rate": 7.02235286645539e-06, "loss": 0.3148, "step": 985 }, { "epoch": 1.84, "learning_rate": 7.002922319444418e-06, "loss": 0.2995, "step": 986 }, { "epoch": 1.84, "learning_rate": 6.983504196556456e-06, "loss": 0.2817, "step": 987 }, { "epoch": 1.84, "learning_rate": 6.964098578287635e-06, "loss": 0.3066, "step": 988 }, { "epoch": 1.85, "learning_rate": 6.9447055450822485e-06, "loss": 0.2985, "step": 989 }, { "epoch": 1.85, "learning_rate": 6.925325177332407e-06, "loss": 0.2871, "step": 990 }, { "epoch": 1.85, "learning_rate": 6.905957555377733e-06, "loss": 0.3084, "step": 991 }, { "epoch": 1.85, "learning_rate": 6.886602759505012e-06, "loss": 0.2708, "step": 992 }, { "epoch": 1.85, "learning_rate": 6.867260869947845e-06, "loss": 0.288, "step": 993 }, { "epoch": 1.85, "learning_rate": 6.8479319668863465e-06, "loss": 0.3096, "step": 994 }, { "epoch": 1.86, "learning_rate": 6.828616130446792e-06, "loss": 0.277, "step": 995 }, { "epoch": 1.86, "learning_rate": 6.809313440701288e-06, "loss": 0.3025, "step": 996 }, { "epoch": 1.86, "learning_rate": 6.790023977667446e-06, "loss": 0.3181, "step": 997 }, { "epoch": 1.86, "learning_rate": 6.770747821308039e-06, "loss": 0.2835, "step": 998 }, { "epoch": 1.86, "learning_rate": 6.7514850515306904e-06, "loss": 0.2954, "step": 999 }, { "epoch": 1.87, "learning_rate": 6.73223574818753e-06, "loss": 0.2849, "step": 1000 }, { "epoch": 1.87, "learning_rate": 6.712999991074847e-06, "loss": 0.302, "step": 1001 }, { "epoch": 1.87, "learning_rate": 6.6937778599327955e-06, "loss": 0.2706, "step": 1002 }, { "epoch": 1.87, "learning_rate": 6.6745694344450365e-06, "loss": 0.3134, "step": 1003 }, { "epoch": 1.87, "learning_rate": 6.65537479423841e-06, "loss": 0.323, "step": 1004 }, { "epoch": 1.88, "learning_rate": 6.63619401888262e-06, "loss": 0.2936, "step": 1005 }, { "epoch": 1.88, "learning_rate": 6.617027187889889e-06, "loss": 0.3019, "step": 1006 }, { "epoch": 1.88, "learning_rate": 6.5978743807146415e-06, "loss": 0.2836, "step": 1007 }, { "epoch": 1.88, "learning_rate": 6.578735676753154e-06, "loss": 0.2539, "step": 1008 }, { "epoch": 1.88, "learning_rate": 6.5596111553432505e-06, "loss": 0.3023, "step": 1009 }, { "epoch": 1.88, "learning_rate": 6.540500895763959e-06, "loss": 0.2983, "step": 1010 }, { "epoch": 1.89, "learning_rate": 6.521404977235193e-06, "loss": 0.3032, "step": 1011 }, { "epoch": 1.89, "learning_rate": 6.5023234789174004e-06, "loss": 0.2912, "step": 1012 }, { "epoch": 1.89, "learning_rate": 6.483256479911267e-06, "loss": 0.2888, "step": 1013 }, { "epoch": 1.89, "learning_rate": 6.464204059257366e-06, "loss": 0.297, "step": 1014 }, { "epoch": 1.89, "learning_rate": 6.445166295935837e-06, "loss": 0.3141, "step": 1015 }, { "epoch": 1.9, "learning_rate": 6.426143268866061e-06, "loss": 0.2806, "step": 1016 }, { "epoch": 1.9, "learning_rate": 6.4071350569063305e-06, "loss": 0.2673, "step": 1017 }, { "epoch": 1.9, "learning_rate": 6.388141738853526e-06, "loss": 0.2781, "step": 1018 }, { "epoch": 1.9, "learning_rate": 6.3691633934427785e-06, "loss": 0.2905, "step": 1019 }, { "epoch": 1.9, "learning_rate": 6.35020009934716e-06, "loss": 0.2902, "step": 1020 }, { "epoch": 1.9, "learning_rate": 6.331251935177345e-06, "loss": 0.3032, "step": 1021 }, { "epoch": 1.91, "learning_rate": 6.312318979481291e-06, "loss": 0.2771, "step": 1022 }, { "epoch": 1.91, "learning_rate": 6.2934013107439e-06, "loss": 0.2839, "step": 1023 }, { "epoch": 1.91, "learning_rate": 6.274499007386718e-06, "loss": 0.3008, "step": 1024 }, { "epoch": 1.91, "learning_rate": 6.255612147767588e-06, "loss": 0.2815, "step": 1025 }, { "epoch": 1.91, "learning_rate": 6.236740810180325e-06, "loss": 0.2848, "step": 1026 }, { "epoch": 1.92, "learning_rate": 6.217885072854412e-06, "loss": 0.2853, "step": 1027 }, { "epoch": 1.92, "learning_rate": 6.1990450139546535e-06, "loss": 0.3025, "step": 1028 }, { "epoch": 1.92, "learning_rate": 6.18022071158087e-06, "loss": 0.2943, "step": 1029 }, { "epoch": 1.92, "learning_rate": 6.161412243767549e-06, "loss": 0.2651, "step": 1030 }, { "epoch": 1.92, "learning_rate": 6.142619688483553e-06, "loss": 0.3088, "step": 1031 }, { "epoch": 1.93, "learning_rate": 6.123843123631768e-06, "loss": 0.3142, "step": 1032 }, { "epoch": 1.93, "learning_rate": 6.105082627048806e-06, "loss": 0.2784, "step": 1033 }, { "epoch": 1.93, "learning_rate": 6.08633827650466e-06, "loss": 0.241, "step": 1034 }, { "epoch": 1.93, "learning_rate": 6.067610149702387e-06, "loss": 0.2758, "step": 1035 }, { "epoch": 1.93, "learning_rate": 6.048898324277809e-06, "loss": 0.2969, "step": 1036 }, { "epoch": 1.93, "learning_rate": 6.030202877799146e-06, "loss": 0.2688, "step": 1037 }, { "epoch": 1.94, "learning_rate": 6.01152388776674e-06, "loss": 0.2849, "step": 1038 }, { "epoch": 1.94, "learning_rate": 5.992861431612709e-06, "loss": 0.2888, "step": 1039 }, { "epoch": 1.94, "learning_rate": 5.974215586700632e-06, "loss": 0.2794, "step": 1040 }, { "epoch": 1.94, "learning_rate": 5.955586430325218e-06, "loss": 0.265, "step": 1041 }, { "epoch": 1.94, "learning_rate": 5.936974039712009e-06, "loss": 0.2657, "step": 1042 }, { "epoch": 1.95, "learning_rate": 5.918378492017038e-06, "loss": 0.2669, "step": 1043 }, { "epoch": 1.95, "learning_rate": 5.899799864326526e-06, "loss": 0.2982, "step": 1044 }, { "epoch": 1.95, "learning_rate": 5.881238233656537e-06, "loss": 0.2881, "step": 1045 }, { "epoch": 1.95, "learning_rate": 5.862693676952689e-06, "loss": 0.2823, "step": 1046 }, { "epoch": 1.95, "learning_rate": 5.844166271089822e-06, "loss": 0.3002, "step": 1047 }, { "epoch": 1.96, "learning_rate": 5.825656092871665e-06, "loss": 0.2825, "step": 1048 }, { "epoch": 1.96, "learning_rate": 5.807163219030547e-06, "loss": 0.2937, "step": 1049 }, { "epoch": 1.96, "learning_rate": 5.788687726227052e-06, "loss": 0.2785, "step": 1050 }, { "epoch": 1.96, "learning_rate": 5.770229691049729e-06, "loss": 0.2789, "step": 1051 }, { "epoch": 1.96, "learning_rate": 5.75178919001473e-06, "loss": 0.2878, "step": 1052 }, { "epoch": 1.96, "learning_rate": 5.733366299565546e-06, "loss": 0.2718, "step": 1053 }, { "epoch": 1.97, "learning_rate": 5.714961096072651e-06, "loss": 0.2624, "step": 1054 }, { "epoch": 1.97, "learning_rate": 5.696573655833214e-06, "loss": 0.2627, "step": 1055 }, { "epoch": 1.97, "learning_rate": 5.678204055070744e-06, "loss": 0.2905, "step": 1056 }, { "epoch": 1.97, "learning_rate": 5.659852369934822e-06, "loss": 0.2992, "step": 1057 }, { "epoch": 1.97, "learning_rate": 5.641518676500749e-06, "loss": 0.2918, "step": 1058 }, { "epoch": 1.98, "learning_rate": 5.623203050769244e-06, "loss": 0.3021, "step": 1059 }, { "epoch": 1.98, "learning_rate": 5.604905568666131e-06, "loss": 0.2692, "step": 1060 }, { "epoch": 1.98, "learning_rate": 5.5866263060420115e-06, "loss": 0.2858, "step": 1061 }, { "epoch": 1.98, "learning_rate": 5.568365338671984e-06, "loss": 0.2515, "step": 1062 }, { "epoch": 1.98, "learning_rate": 5.5501227422552705e-06, "loss": 0.284, "step": 1063 }, { "epoch": 1.99, "learning_rate": 5.53189859241497e-06, "loss": 0.2917, "step": 1064 }, { "epoch": 1.99, "learning_rate": 5.51369296469769e-06, "loss": 0.2908, "step": 1065 }, { "epoch": 1.99, "learning_rate": 5.495505934573279e-06, "loss": 0.2777, "step": 1066 }, { "epoch": 1.99, "learning_rate": 5.477337577434463e-06, "loss": 0.2921, "step": 1067 }, { "epoch": 1.99, "learning_rate": 5.459187968596582e-06, "loss": 0.2818, "step": 1068 }, { "epoch": 1.99, "learning_rate": 5.441057183297251e-06, "loss": 0.2614, "step": 1069 }, { "epoch": 2.0, "learning_rate": 5.4229452966960495e-06, "loss": 0.2596, "step": 1070 }, { "epoch": 2.0, "learning_rate": 5.404852383874213e-06, "loss": 0.2774, "step": 1071 }, { "epoch": 2.0, "learning_rate": 5.386778519834335e-06, "loss": 0.2551, "step": 1072 }, { "epoch": 2.0, "learning_rate": 5.368723779500034e-06, "loss": 0.2463, "step": 1073 }, { "epoch": 2.0, "learning_rate": 5.350688237715651e-06, "loss": 0.2499, "step": 1074 }, { "epoch": 2.01, "learning_rate": 5.332671969245948e-06, "loss": 0.2728, "step": 1075 }, { "epoch": 2.01, "learning_rate": 5.314675048775786e-06, "loss": 0.2499, "step": 1076 }, { "epoch": 2.01, "learning_rate": 5.2966975509098195e-06, "loss": 0.2606, "step": 1077 }, { "epoch": 2.01, "learning_rate": 5.2787395501722e-06, "loss": 0.263, "step": 1078 }, { "epoch": 2.01, "learning_rate": 5.260801121006239e-06, "loss": 0.2348, "step": 1079 }, { "epoch": 2.01, "learning_rate": 5.242882337774126e-06, "loss": 0.2745, "step": 1080 }, { "epoch": 2.02, "learning_rate": 5.22498327475661e-06, "loss": 0.2423, "step": 1081 }, { "epoch": 2.02, "learning_rate": 5.207104006152679e-06, "loss": 0.2336, "step": 1082 }, { "epoch": 2.02, "learning_rate": 5.189244606079288e-06, "loss": 0.2664, "step": 1083 }, { "epoch": 2.02, "learning_rate": 5.171405148571009e-06, "loss": 0.2524, "step": 1084 }, { "epoch": 2.02, "learning_rate": 5.153585707579752e-06, "loss": 0.2653, "step": 1085 }, { "epoch": 2.03, "learning_rate": 5.135786356974444e-06, "loss": 0.2816, "step": 1086 }, { "epoch": 2.03, "learning_rate": 5.118007170540745e-06, "loss": 0.2608, "step": 1087 }, { "epoch": 2.03, "learning_rate": 5.100248221980702e-06, "loss": 0.2823, "step": 1088 }, { "epoch": 2.03, "learning_rate": 5.082509584912489e-06, "loss": 0.2871, "step": 1089 }, { "epoch": 2.03, "learning_rate": 5.064791332870067e-06, "loss": 0.2754, "step": 1090 }, { "epoch": 2.04, "learning_rate": 5.04709353930291e-06, "loss": 0.2627, "step": 1091 }, { "epoch": 2.04, "learning_rate": 5.029416277575654e-06, "loss": 0.2593, "step": 1092 }, { "epoch": 2.04, "learning_rate": 5.01175962096785e-06, "loss": 0.2607, "step": 1093 }, { "epoch": 2.04, "learning_rate": 4.994123642673619e-06, "loss": 0.2611, "step": 1094 }, { "epoch": 2.04, "learning_rate": 4.976508415801365e-06, "loss": 0.2486, "step": 1095 }, { "epoch": 2.04, "learning_rate": 4.958914013373467e-06, "loss": 0.2464, "step": 1096 }, { "epoch": 2.05, "learning_rate": 4.941340508325974e-06, "loss": 0.2494, "step": 1097 }, { "epoch": 2.05, "learning_rate": 4.923787973508326e-06, "loss": 0.2744, "step": 1098 }, { "epoch": 2.05, "learning_rate": 4.906256481683002e-06, "loss": 0.2736, "step": 1099 }, { "epoch": 2.05, "learning_rate": 4.888746105525278e-06, "loss": 0.2564, "step": 1100 }, { "epoch": 2.05, "learning_rate": 4.871256917622876e-06, "loss": 0.2921, "step": 1101 }, { "epoch": 2.06, "learning_rate": 4.853788990475705e-06, "loss": 0.2837, "step": 1102 }, { "epoch": 2.06, "learning_rate": 4.836342396495511e-06, "loss": 0.2684, "step": 1103 }, { "epoch": 2.06, "learning_rate": 4.818917208005632e-06, "loss": 0.2468, "step": 1104 }, { "epoch": 2.06, "learning_rate": 4.8015134972406554e-06, "loss": 0.2271, "step": 1105 }, { "epoch": 2.06, "learning_rate": 4.784131336346148e-06, "loss": 0.2646, "step": 1106 }, { "epoch": 2.07, "learning_rate": 4.766770797378323e-06, "loss": 0.2708, "step": 1107 }, { "epoch": 2.07, "learning_rate": 4.749431952303784e-06, "loss": 0.2546, "step": 1108 }, { "epoch": 2.07, "learning_rate": 4.73211487299919e-06, "loss": 0.2633, "step": 1109 }, { "epoch": 2.07, "learning_rate": 4.714819631250978e-06, "loss": 0.2556, "step": 1110 }, { "epoch": 2.07, "learning_rate": 4.697546298755058e-06, "loss": 0.2434, "step": 1111 }, { "epoch": 2.07, "learning_rate": 4.680294947116511e-06, "loss": 0.2399, "step": 1112 }, { "epoch": 2.08, "learning_rate": 4.663065647849316e-06, "loss": 0.2728, "step": 1113 }, { "epoch": 2.08, "learning_rate": 4.645858472376014e-06, "loss": 0.2391, "step": 1114 }, { "epoch": 2.08, "learning_rate": 4.6286734920274475e-06, "loss": 0.2363, "step": 1115 }, { "epoch": 2.08, "learning_rate": 4.611510778042445e-06, "loss": 0.2648, "step": 1116 }, { "epoch": 2.08, "learning_rate": 4.594370401567542e-06, "loss": 0.27, "step": 1117 }, { "epoch": 2.09, "learning_rate": 4.577252433656655e-06, "loss": 0.2633, "step": 1118 }, { "epoch": 2.09, "learning_rate": 4.56015694527083e-06, "loss": 0.2587, "step": 1119 }, { "epoch": 2.09, "learning_rate": 4.543084007277915e-06, "loss": 0.2758, "step": 1120 }, { "epoch": 2.09, "learning_rate": 4.526033690452277e-06, "loss": 0.2664, "step": 1121 }, { "epoch": 2.09, "learning_rate": 4.509006065474509e-06, "loss": 0.2682, "step": 1122 }, { "epoch": 2.1, "learning_rate": 4.492001202931147e-06, "loss": 0.2526, "step": 1123 }, { "epoch": 2.1, "learning_rate": 4.475019173314353e-06, "loss": 0.2683, "step": 1124 }, { "epoch": 2.1, "learning_rate": 4.458060047021645e-06, "loss": 0.237, "step": 1125 }, { "epoch": 2.1, "learning_rate": 4.441123894355591e-06, "loss": 0.2792, "step": 1126 }, { "epoch": 2.1, "learning_rate": 4.424210785523536e-06, "loss": 0.2838, "step": 1127 }, { "epoch": 2.1, "learning_rate": 4.4073207906372885e-06, "loss": 0.2461, "step": 1128 }, { "epoch": 2.11, "learning_rate": 4.390453979712842e-06, "loss": 0.2624, "step": 1129 }, { "epoch": 2.11, "learning_rate": 4.373610422670085e-06, "loss": 0.2624, "step": 1130 }, { "epoch": 2.11, "learning_rate": 4.3567901893325056e-06, "loss": 0.2517, "step": 1131 }, { "epoch": 2.11, "learning_rate": 4.33999334942691e-06, "loss": 0.2404, "step": 1132 }, { "epoch": 2.11, "learning_rate": 4.323219972583122e-06, "loss": 0.2609, "step": 1133 }, { "epoch": 2.12, "learning_rate": 4.306470128333714e-06, "loss": 0.2767, "step": 1134 }, { "epoch": 2.12, "learning_rate": 4.289743886113694e-06, "loss": 0.2468, "step": 1135 }, { "epoch": 2.12, "learning_rate": 4.273041315260234e-06, "loss": 0.2466, "step": 1136 }, { "epoch": 2.12, "learning_rate": 4.256362485012377e-06, "loss": 0.2262, "step": 1137 }, { "epoch": 2.12, "learning_rate": 4.239707464510757e-06, "loss": 0.2573, "step": 1138 }, { "epoch": 2.12, "learning_rate": 4.223076322797302e-06, "loss": 0.2383, "step": 1139 }, { "epoch": 2.13, "learning_rate": 4.206469128814949e-06, "loss": 0.2688, "step": 1140 }, { "epoch": 2.13, "learning_rate": 4.189885951407368e-06, "loss": 0.2589, "step": 1141 }, { "epoch": 2.13, "learning_rate": 4.173326859318675e-06, "loss": 0.2334, "step": 1142 }, { "epoch": 2.13, "learning_rate": 4.156791921193123e-06, "loss": 0.2473, "step": 1143 }, { "epoch": 2.13, "learning_rate": 4.140281205574861e-06, "loss": 0.2445, "step": 1144 }, { "epoch": 2.14, "learning_rate": 4.12379478090761e-06, "loss": 0.2533, "step": 1145 }, { "epoch": 2.14, "learning_rate": 4.107332715534399e-06, "loss": 0.2541, "step": 1146 }, { "epoch": 2.14, "learning_rate": 4.090895077697276e-06, "loss": 0.2693, "step": 1147 }, { "epoch": 2.14, "learning_rate": 4.074481935537035e-06, "loss": 0.258, "step": 1148 }, { "epoch": 2.14, "learning_rate": 4.058093357092915e-06, "loss": 0.221, "step": 1149 }, { "epoch": 2.15, "learning_rate": 4.041729410302334e-06, "loss": 0.2522, "step": 1150 }, { "epoch": 2.15, "learning_rate": 4.0253901630005985e-06, "loss": 0.2622, "step": 1151 }, { "epoch": 2.15, "learning_rate": 4.009075682920626e-06, "loss": 0.2494, "step": 1152 }, { "epoch": 2.15, "learning_rate": 3.992786037692673e-06, "loss": 0.292, "step": 1153 }, { "epoch": 2.15, "learning_rate": 3.976521294844022e-06, "loss": 0.2411, "step": 1154 }, { "epoch": 2.15, "learning_rate": 3.960281521798755e-06, "loss": 0.2457, "step": 1155 }, { "epoch": 2.16, "learning_rate": 3.944066785877416e-06, "loss": 0.2597, "step": 1156 }, { "epoch": 2.16, "learning_rate": 3.927877154296788e-06, "loss": 0.2303, "step": 1157 }, { "epoch": 2.16, "learning_rate": 3.911712694169553e-06, "loss": 0.2383, "step": 1158 }, { "epoch": 2.16, "learning_rate": 3.895573472504076e-06, "loss": 0.2593, "step": 1159 }, { "epoch": 2.16, "learning_rate": 3.879459556204081e-06, "loss": 0.2446, "step": 1160 }, { "epoch": 2.17, "learning_rate": 3.863371012068407e-06, "loss": 0.2545, "step": 1161 }, { "epoch": 2.17, "learning_rate": 3.847307906790688e-06, "loss": 0.2688, "step": 1162 }, { "epoch": 2.17, "learning_rate": 3.831270306959134e-06, "loss": 0.2441, "step": 1163 }, { "epoch": 2.17, "learning_rate": 3.8152582790562045e-06, "loss": 0.2401, "step": 1164 }, { "epoch": 2.17, "learning_rate": 3.79927188945836e-06, "loss": 0.2824, "step": 1165 }, { "epoch": 2.18, "learning_rate": 3.783311204435778e-06, "loss": 0.2654, "step": 1166 }, { "epoch": 2.18, "learning_rate": 3.767376290152075e-06, "loss": 0.244, "step": 1167 }, { "epoch": 2.18, "learning_rate": 3.751467212664056e-06, "loss": 0.2712, "step": 1168 }, { "epoch": 2.18, "learning_rate": 3.7355840379213926e-06, "loss": 0.2704, "step": 1169 }, { "epoch": 2.18, "learning_rate": 3.719726831766405e-06, "loss": 0.2618, "step": 1170 }, { "epoch": 2.18, "learning_rate": 3.703895659933745e-06, "loss": 0.246, "step": 1171 }, { "epoch": 2.19, "learning_rate": 3.6880905880501592e-06, "loss": 0.2605, "step": 1172 }, { "epoch": 2.19, "learning_rate": 3.6723116816341764e-06, "loss": 0.246, "step": 1173 }, { "epoch": 2.19, "learning_rate": 3.65655900609588e-06, "loss": 0.2369, "step": 1174 }, { "epoch": 2.19, "learning_rate": 3.6408326267366043e-06, "loss": 0.2669, "step": 1175 }, { "epoch": 2.19, "learning_rate": 3.625132608748676e-06, "loss": 0.2493, "step": 1176 }, { "epoch": 2.2, "learning_rate": 3.6094590172151424e-06, "loss": 0.2571, "step": 1177 }, { "epoch": 2.2, "learning_rate": 3.593811917109511e-06, "loss": 0.2523, "step": 1178 }, { "epoch": 2.2, "learning_rate": 3.578191373295461e-06, "loss": 0.2591, "step": 1179 }, { "epoch": 2.2, "learning_rate": 3.562597450526588e-06, "loss": 0.2175, "step": 1180 }, { "epoch": 2.2, "learning_rate": 3.5470302134461343e-06, "loss": 0.2525, "step": 1181 }, { "epoch": 2.21, "learning_rate": 3.5314897265867132e-06, "loss": 0.2652, "step": 1182 }, { "epoch": 2.21, "learning_rate": 3.5159760543700594e-06, "loss": 0.2415, "step": 1183 }, { "epoch": 2.21, "learning_rate": 3.5004892611067377e-06, "loss": 0.2588, "step": 1184 }, { "epoch": 2.21, "learning_rate": 3.4850294109958937e-06, "loss": 0.2661, "step": 1185 }, { "epoch": 2.21, "learning_rate": 3.469596568124983e-06, "loss": 0.2455, "step": 1186 }, { "epoch": 2.21, "learning_rate": 3.454190796469502e-06, "loss": 0.2385, "step": 1187 }, { "epoch": 2.22, "learning_rate": 3.438812159892726e-06, "loss": 0.2385, "step": 1188 }, { "epoch": 2.22, "learning_rate": 3.423460722145452e-06, "loss": 0.2593, "step": 1189 }, { "epoch": 2.22, "learning_rate": 3.4081365468657166e-06, "loss": 0.2627, "step": 1190 }, { "epoch": 2.22, "learning_rate": 3.392839697578547e-06, "loss": 0.2621, "step": 1191 }, { "epoch": 2.22, "learning_rate": 3.377570237695689e-06, "loss": 0.2454, "step": 1192 }, { "epoch": 2.23, "learning_rate": 3.3623282305153604e-06, "loss": 0.2604, "step": 1193 }, { "epoch": 2.23, "learning_rate": 3.347113739221953e-06, "loss": 0.2492, "step": 1194 }, { "epoch": 2.23, "learning_rate": 3.3319268268858198e-06, "loss": 0.2372, "step": 1195 }, { "epoch": 2.23, "learning_rate": 3.3167675564629664e-06, "loss": 0.2396, "step": 1196 }, { "epoch": 2.23, "learning_rate": 3.3016359907948335e-06, "loss": 0.2397, "step": 1197 }, { "epoch": 2.24, "learning_rate": 3.286532192607985e-06, "loss": 0.2618, "step": 1198 }, { "epoch": 2.24, "learning_rate": 3.271456224513906e-06, "loss": 0.2337, "step": 1199 }, { "epoch": 2.24, "learning_rate": 3.256408149008696e-06, "loss": 0.2512, "step": 1200 }, { "epoch": 2.24, "learning_rate": 3.241388028472835e-06, "loss": 0.2379, "step": 1201 }, { "epoch": 2.24, "learning_rate": 3.2263959251709178e-06, "loss": 0.2422, "step": 1202 }, { "epoch": 2.24, "learning_rate": 3.2114319012513908e-06, "loss": 0.2468, "step": 1203 }, { "epoch": 2.25, "learning_rate": 3.1964960187463156e-06, "loss": 0.245, "step": 1204 }, { "epoch": 2.25, "learning_rate": 3.181588339571071e-06, "loss": 0.243, "step": 1205 }, { "epoch": 2.25, "learning_rate": 3.1667089255241446e-06, "loss": 0.2455, "step": 1206 }, { "epoch": 2.25, "learning_rate": 3.1518578382868392e-06, "loss": 0.2453, "step": 1207 }, { "epoch": 2.25, "learning_rate": 3.1370351394230446e-06, "loss": 0.2495, "step": 1208 }, { "epoch": 2.26, "learning_rate": 3.122240890378947e-06, "loss": 0.2884, "step": 1209 }, { "epoch": 2.26, "learning_rate": 3.107475152482822e-06, "loss": 0.2396, "step": 1210 }, { "epoch": 2.26, "learning_rate": 3.092737986944734e-06, "loss": 0.2377, "step": 1211 }, { "epoch": 2.26, "learning_rate": 3.0780294548563227e-06, "loss": 0.2212, "step": 1212 }, { "epoch": 2.26, "learning_rate": 3.0633496171905064e-06, "loss": 0.2456, "step": 1213 }, { "epoch": 2.26, "learning_rate": 3.0486985348012763e-06, "loss": 0.245, "step": 1214 }, { "epoch": 2.27, "learning_rate": 3.0340762684234082e-06, "loss": 0.235, "step": 1215 }, { "epoch": 2.27, "learning_rate": 3.0194828786722252e-06, "loss": 0.261, "step": 1216 }, { "epoch": 2.27, "learning_rate": 3.004918426043344e-06, "loss": 0.2381, "step": 1217 }, { "epoch": 2.27, "learning_rate": 2.9903829709124345e-06, "loss": 0.2465, "step": 1218 }, { "epoch": 2.27, "learning_rate": 2.975876573534948e-06, "loss": 0.254, "step": 1219 }, { "epoch": 2.28, "learning_rate": 2.9613992940458845e-06, "loss": 0.2254, "step": 1220 }, { "epoch": 2.28, "learning_rate": 2.9469511924595394e-06, "loss": 0.2168, "step": 1221 }, { "epoch": 2.28, "learning_rate": 2.9325323286692486e-06, "loss": 0.2807, "step": 1222 }, { "epoch": 2.28, "learning_rate": 2.918142762447157e-06, "loss": 0.2548, "step": 1223 }, { "epoch": 2.28, "learning_rate": 2.9037825534439403e-06, "loss": 0.2569, "step": 1224 }, { "epoch": 2.29, "learning_rate": 2.889451761188595e-06, "loss": 0.2294, "step": 1225 }, { "epoch": 2.29, "learning_rate": 2.875150445088164e-06, "loss": 0.2651, "step": 1226 }, { "epoch": 2.29, "learning_rate": 2.860878664427499e-06, "loss": 0.2637, "step": 1227 }, { "epoch": 2.29, "learning_rate": 2.8466364783690137e-06, "loss": 0.2457, "step": 1228 }, { "epoch": 2.29, "learning_rate": 2.8324239459524493e-06, "loss": 0.2558, "step": 1229 }, { "epoch": 2.29, "learning_rate": 2.8182411260946118e-06, "loss": 0.2729, "step": 1230 }, { "epoch": 2.3, "learning_rate": 2.8040880775891366e-06, "loss": 0.2173, "step": 1231 }, { "epoch": 2.3, "learning_rate": 2.7899648591062455e-06, "loss": 0.2379, "step": 1232 }, { "epoch": 2.3, "learning_rate": 2.7758715291925098e-06, "loss": 0.2637, "step": 1233 }, { "epoch": 2.3, "learning_rate": 2.7618081462705894e-06, "loss": 0.2335, "step": 1234 }, { "epoch": 2.3, "learning_rate": 2.747774768639009e-06, "loss": 0.2603, "step": 1235 }, { "epoch": 2.31, "learning_rate": 2.733771454471903e-06, "loss": 0.2514, "step": 1236 }, { "epoch": 2.31, "learning_rate": 2.7197982618187867e-06, "loss": 0.2614, "step": 1237 }, { "epoch": 2.31, "learning_rate": 2.7058552486043056e-06, "loss": 0.2458, "step": 1238 }, { "epoch": 2.31, "learning_rate": 2.6919424726279952e-06, "loss": 0.2733, "step": 1239 }, { "epoch": 2.31, "learning_rate": 2.678059991564057e-06, "loss": 0.2553, "step": 1240 }, { "epoch": 2.32, "learning_rate": 2.664207862961098e-06, "loss": 0.2566, "step": 1241 }, { "epoch": 2.32, "learning_rate": 2.650386144241903e-06, "loss": 0.2319, "step": 1242 }, { "epoch": 2.32, "learning_rate": 2.6365948927031936e-06, "loss": 0.2612, "step": 1243 }, { "epoch": 2.32, "learning_rate": 2.622834165515401e-06, "loss": 0.2461, "step": 1244 }, { "epoch": 2.32, "learning_rate": 2.6091040197224103e-06, "loss": 0.2379, "step": 1245 }, { "epoch": 2.32, "learning_rate": 2.595404512241341e-06, "loss": 0.2446, "step": 1246 }, { "epoch": 2.33, "learning_rate": 2.5817356998622954e-06, "loss": 0.2205, "step": 1247 }, { "epoch": 2.33, "learning_rate": 2.5680976392481494e-06, "loss": 0.2364, "step": 1248 }, { "epoch": 2.33, "learning_rate": 2.554490386934275e-06, "loss": 0.2623, "step": 1249 }, { "epoch": 2.33, "learning_rate": 2.540913999328355e-06, "loss": 0.2591, "step": 1250 }, { "epoch": 2.33, "learning_rate": 2.5273685327101117e-06, "loss": 0.2657, "step": 1251 }, { "epoch": 2.34, "learning_rate": 2.5138540432310897e-06, "loss": 0.2617, "step": 1252 }, { "epoch": 2.34, "learning_rate": 2.50037058691442e-06, "loss": 0.2516, "step": 1253 }, { "epoch": 2.34, "learning_rate": 2.486918219654595e-06, "loss": 0.2486, "step": 1254 }, { "epoch": 2.34, "learning_rate": 2.473496997217221e-06, "loss": 0.2482, "step": 1255 }, { "epoch": 2.34, "learning_rate": 2.4601069752388006e-06, "loss": 0.2336, "step": 1256 }, { "epoch": 2.35, "learning_rate": 2.4467482092264984e-06, "loss": 0.2348, "step": 1257 }, { "epoch": 2.35, "learning_rate": 2.4334207545579037e-06, "loss": 0.2631, "step": 1258 }, { "epoch": 2.35, "learning_rate": 2.420124666480823e-06, "loss": 0.2527, "step": 1259 }, { "epoch": 2.35, "learning_rate": 2.4068600001130115e-06, "loss": 0.2726, "step": 1260 }, { "epoch": 2.35, "learning_rate": 2.3936268104419923e-06, "loss": 0.2387, "step": 1261 }, { "epoch": 2.35, "learning_rate": 2.380425152324788e-06, "loss": 0.252, "step": 1262 }, { "epoch": 2.36, "learning_rate": 2.3672550804877236e-06, "loss": 0.2461, "step": 1263 }, { "epoch": 2.36, "learning_rate": 2.354116649526167e-06, "loss": 0.234, "step": 1264 }, { "epoch": 2.36, "learning_rate": 2.3410099139043427e-06, "loss": 0.2665, "step": 1265 }, { "epoch": 2.36, "learning_rate": 2.3279349279550677e-06, "loss": 0.2654, "step": 1266 }, { "epoch": 2.36, "learning_rate": 2.3148917458795616e-06, "loss": 0.2554, "step": 1267 }, { "epoch": 2.37, "learning_rate": 2.30188042174718e-06, "loss": 0.2198, "step": 1268 }, { "epoch": 2.37, "learning_rate": 2.288901009495238e-06, "loss": 0.2319, "step": 1269 }, { "epoch": 2.37, "learning_rate": 2.2759535629287477e-06, "loss": 0.2725, "step": 1270 }, { "epoch": 2.37, "learning_rate": 2.263038135720215e-06, "loss": 0.2692, "step": 1271 }, { "epoch": 2.37, "learning_rate": 2.2501547814094115e-06, "loss": 0.2312, "step": 1272 }, { "epoch": 2.38, "learning_rate": 2.237303553403154e-06, "loss": 0.2245, "step": 1273 }, { "epoch": 2.38, "learning_rate": 2.2244845049750884e-06, "loss": 0.2158, "step": 1274 }, { "epoch": 2.38, "learning_rate": 2.211697689265446e-06, "loss": 0.2652, "step": 1275 }, { "epoch": 2.38, "learning_rate": 2.1989431592808607e-06, "loss": 0.2392, "step": 1276 }, { "epoch": 2.38, "learning_rate": 2.186220967894114e-06, "loss": 0.2349, "step": 1277 }, { "epoch": 2.38, "learning_rate": 2.173531167843944e-06, "loss": 0.241, "step": 1278 }, { "epoch": 2.39, "learning_rate": 2.1608738117347925e-06, "loss": 0.2439, "step": 1279 }, { "epoch": 2.39, "learning_rate": 2.148248952036632e-06, "loss": 0.247, "step": 1280 }, { "epoch": 2.39, "learning_rate": 2.135656641084708e-06, "loss": 0.226, "step": 1281 }, { "epoch": 2.39, "learning_rate": 2.1230969310793425e-06, "loss": 0.2191, "step": 1282 }, { "epoch": 2.39, "learning_rate": 2.1105698740857104e-06, "loss": 0.2558, "step": 1283 }, { "epoch": 2.4, "learning_rate": 2.098075522033636e-06, "loss": 0.2645, "step": 1284 }, { "epoch": 2.4, "learning_rate": 2.0856139267173568e-06, "loss": 0.2623, "step": 1285 }, { "epoch": 2.4, "learning_rate": 2.073185139795326e-06, "loss": 0.2284, "step": 1286 }, { "epoch": 2.4, "learning_rate": 2.0607892127899887e-06, "loss": 0.217, "step": 1287 }, { "epoch": 2.4, "learning_rate": 2.0484261970875783e-06, "loss": 0.2676, "step": 1288 }, { "epoch": 2.4, "learning_rate": 2.0360961439378924e-06, "loss": 0.2411, "step": 1289 }, { "epoch": 2.41, "learning_rate": 2.023799104454085e-06, "loss": 0.2453, "step": 1290 }, { "epoch": 2.41, "learning_rate": 2.0115351296124573e-06, "loss": 0.2426, "step": 1291 }, { "epoch": 2.41, "learning_rate": 1.9993042702522435e-06, "loss": 0.2298, "step": 1292 }, { "epoch": 2.41, "learning_rate": 1.9871065770753974e-06, "loss": 0.2199, "step": 1293 }, { "epoch": 2.41, "learning_rate": 1.9749421006463875e-06, "loss": 0.2609, "step": 1294 }, { "epoch": 2.42, "learning_rate": 1.9628108913919885e-06, "loss": 0.259, "step": 1295 }, { "epoch": 2.42, "learning_rate": 1.9507129996010644e-06, "loss": 0.2523, "step": 1296 }, { "epoch": 2.42, "learning_rate": 1.938648475424366e-06, "loss": 0.2688, "step": 1297 }, { "epoch": 2.42, "learning_rate": 1.9266173688743182e-06, "loss": 0.2409, "step": 1298 }, { "epoch": 2.42, "learning_rate": 1.914619729824826e-06, "loss": 0.2548, "step": 1299 }, { "epoch": 2.43, "learning_rate": 1.902655608011047e-06, "loss": 0.244, "step": 1300 }, { "epoch": 2.43, "learning_rate": 1.890725053029201e-06, "loss": 0.2371, "step": 1301 }, { "epoch": 2.43, "learning_rate": 1.8788281143363562e-06, "loss": 0.2302, "step": 1302 }, { "epoch": 2.43, "learning_rate": 1.8669648412502372e-06, "loss": 0.2429, "step": 1303 }, { "epoch": 2.43, "learning_rate": 1.8551352829489944e-06, "loss": 0.2356, "step": 1304 }, { "epoch": 2.43, "learning_rate": 1.8433394884710309e-06, "loss": 0.2478, "step": 1305 }, { "epoch": 2.44, "learning_rate": 1.831577506714779e-06, "loss": 0.2157, "step": 1306 }, { "epoch": 2.44, "learning_rate": 1.8198493864385036e-06, "loss": 0.2964, "step": 1307 }, { "epoch": 2.44, "learning_rate": 1.808155176260099e-06, "loss": 0.2619, "step": 1308 }, { "epoch": 2.44, "learning_rate": 1.7964949246568885e-06, "loss": 0.2268, "step": 1309 }, { "epoch": 2.44, "learning_rate": 1.7848686799654268e-06, "loss": 0.2629, "step": 1310 }, { "epoch": 2.45, "learning_rate": 1.7732764903812915e-06, "loss": 0.2287, "step": 1311 }, { "epoch": 2.45, "learning_rate": 1.7617184039588887e-06, "loss": 0.219, "step": 1312 }, { "epoch": 2.45, "learning_rate": 1.7501944686112516e-06, "loss": 0.2468, "step": 1313 }, { "epoch": 2.45, "learning_rate": 1.7387047321098515e-06, "loss": 0.256, "step": 1314 }, { "epoch": 2.45, "learning_rate": 1.7272492420843745e-06, "loss": 0.2346, "step": 1315 }, { "epoch": 2.46, "learning_rate": 1.7158280460225595e-06, "loss": 0.2313, "step": 1316 }, { "epoch": 2.46, "learning_rate": 1.70444119126997e-06, "loss": 0.1966, "step": 1317 }, { "epoch": 2.46, "learning_rate": 1.69308872502982e-06, "loss": 0.2434, "step": 1318 }, { "epoch": 2.46, "learning_rate": 1.6817706943627566e-06, "loss": 0.2402, "step": 1319 }, { "epoch": 2.46, "learning_rate": 1.67048714618669e-06, "loss": 0.2671, "step": 1320 }, { "epoch": 2.46, "learning_rate": 1.65923812727658e-06, "loss": 0.2585, "step": 1321 }, { "epoch": 2.47, "learning_rate": 1.6480236842642473e-06, "loss": 0.2298, "step": 1322 }, { "epoch": 2.47, "learning_rate": 1.6368438636381833e-06, "loss": 0.259, "step": 1323 }, { "epoch": 2.47, "learning_rate": 1.6256987117433576e-06, "loss": 0.2214, "step": 1324 }, { "epoch": 2.47, "learning_rate": 1.6145882747810205e-06, "loss": 0.2357, "step": 1325 }, { "epoch": 2.47, "learning_rate": 1.6035125988085132e-06, "loss": 0.2348, "step": 1326 }, { "epoch": 2.48, "learning_rate": 1.5924717297390825e-06, "loss": 0.2578, "step": 1327 }, { "epoch": 2.48, "learning_rate": 1.581465713341681e-06, "loss": 0.284, "step": 1328 }, { "epoch": 2.48, "learning_rate": 1.5704945952407924e-06, "loss": 0.2397, "step": 1329 }, { "epoch": 2.48, "learning_rate": 1.5595584209162163e-06, "loss": 0.2143, "step": 1330 }, { "epoch": 2.48, "learning_rate": 1.548657235702913e-06, "loss": 0.2409, "step": 1331 }, { "epoch": 2.49, "learning_rate": 1.5377910847907884e-06, "loss": 0.2294, "step": 1332 }, { "epoch": 2.49, "learning_rate": 1.52696001322452e-06, "loss": 0.2146, "step": 1333 }, { "epoch": 2.49, "learning_rate": 1.5161640659033627e-06, "loss": 0.2123, "step": 1334 }, { "epoch": 2.49, "learning_rate": 1.5054032875809754e-06, "loss": 0.2357, "step": 1335 }, { "epoch": 2.49, "learning_rate": 1.494677722865221e-06, "loss": 0.2545, "step": 1336 }, { "epoch": 2.49, "learning_rate": 1.4839874162179869e-06, "loss": 0.2122, "step": 1337 }, { "epoch": 2.5, "learning_rate": 1.4733324119550018e-06, "loss": 0.2576, "step": 1338 }, { "epoch": 2.5, "learning_rate": 1.4627127542456576e-06, "loss": 0.2114, "step": 1339 }, { "epoch": 2.5, "learning_rate": 1.4521284871128116e-06, "loss": 0.2164, "step": 1340 }, { "epoch": 2.5, "learning_rate": 1.4415796544326166e-06, "loss": 0.2095, "step": 1341 }, { "epoch": 2.5, "learning_rate": 1.4310662999343339e-06, "loss": 0.2393, "step": 1342 }, { "epoch": 2.51, "learning_rate": 1.4205884672001558e-06, "loss": 0.2279, "step": 1343 }, { "epoch": 2.51, "learning_rate": 1.4101461996650179e-06, "loss": 0.219, "step": 1344 }, { "epoch": 2.51, "learning_rate": 1.3997395406164238e-06, "loss": 0.2464, "step": 1345 }, { "epoch": 2.51, "learning_rate": 1.389368533194273e-06, "loss": 0.2238, "step": 1346 }, { "epoch": 2.51, "learning_rate": 1.3790332203906642e-06, "loss": 0.2317, "step": 1347 }, { "epoch": 2.51, "learning_rate": 1.3687336450497334e-06, "loss": 0.2357, "step": 1348 }, { "epoch": 2.52, "learning_rate": 1.3584698498674632e-06, "loss": 0.2079, "step": 1349 }, { "epoch": 2.52, "learning_rate": 1.3482418773915251e-06, "loss": 0.2161, "step": 1350 }, { "epoch": 2.52, "learning_rate": 1.3380497700210783e-06, "loss": 0.2423, "step": 1351 }, { "epoch": 2.52, "learning_rate": 1.327893570006612e-06, "loss": 0.2335, "step": 1352 }, { "epoch": 2.52, "learning_rate": 1.3177733194497622e-06, "loss": 0.2473, "step": 1353 }, { "epoch": 2.53, "learning_rate": 1.3076890603031466e-06, "loss": 0.2178, "step": 1354 }, { "epoch": 2.53, "learning_rate": 1.2976408343701707e-06, "loss": 0.2662, "step": 1355 }, { "epoch": 2.53, "learning_rate": 1.2876286833048812e-06, "loss": 0.2391, "step": 1356 }, { "epoch": 2.53, "learning_rate": 1.2776526486117692e-06, "loss": 0.2464, "step": 1357 }, { "epoch": 2.53, "learning_rate": 1.2677127716456183e-06, "loss": 0.2174, "step": 1358 }, { "epoch": 2.54, "learning_rate": 1.2578090936113097e-06, "loss": 0.2519, "step": 1359 }, { "epoch": 2.54, "learning_rate": 1.2479416555636792e-06, "loss": 0.2371, "step": 1360 }, { "epoch": 2.54, "learning_rate": 1.2381104984073255e-06, "loss": 0.2586, "step": 1361 }, { "epoch": 2.54, "learning_rate": 1.22831566289645e-06, "loss": 0.2303, "step": 1362 }, { "epoch": 2.54, "learning_rate": 1.2185571896346838e-06, "loss": 0.2551, "step": 1363 }, { "epoch": 2.54, "learning_rate": 1.2088351190749226e-06, "loss": 0.2429, "step": 1364 }, { "epoch": 2.55, "learning_rate": 1.1991494915191625e-06, "loss": 0.2442, "step": 1365 }, { "epoch": 2.55, "learning_rate": 1.1895003471183185e-06, "loss": 0.2598, "step": 1366 }, { "epoch": 2.55, "learning_rate": 1.1798877258720776e-06, "loss": 0.2361, "step": 1367 }, { "epoch": 2.55, "learning_rate": 1.1703116676287173e-06, "loss": 0.2217, "step": 1368 }, { "epoch": 2.55, "learning_rate": 1.1607722120849519e-06, "loss": 0.2122, "step": 1369 }, { "epoch": 2.56, "learning_rate": 1.1512693987857527e-06, "loss": 0.2234, "step": 1370 }, { "epoch": 2.56, "learning_rate": 1.1418032671242042e-06, "loss": 0.2497, "step": 1371 }, { "epoch": 2.56, "learning_rate": 1.1323738563413233e-06, "loss": 0.2462, "step": 1372 }, { "epoch": 2.56, "learning_rate": 1.1229812055259115e-06, "loss": 0.2443, "step": 1373 }, { "epoch": 2.56, "learning_rate": 1.1136253536143737e-06, "loss": 0.2062, "step": 1374 }, { "epoch": 2.57, "learning_rate": 1.1043063393905796e-06, "loss": 0.219, "step": 1375 }, { "epoch": 2.57, "learning_rate": 1.0950242014856837e-06, "loss": 0.2534, "step": 1376 }, { "epoch": 2.57, "learning_rate": 1.085778978377976e-06, "loss": 0.2504, "step": 1377 }, { "epoch": 2.57, "learning_rate": 1.07657070839272e-06, "loss": 0.2587, "step": 1378 }, { "epoch": 2.57, "learning_rate": 1.0673994297019897e-06, "loss": 0.2318, "step": 1379 }, { "epoch": 2.57, "learning_rate": 1.0582651803245214e-06, "loss": 0.2471, "step": 1380 }, { "epoch": 2.58, "learning_rate": 1.0491679981255443e-06, "loss": 0.2674, "step": 1381 }, { "epoch": 2.58, "learning_rate": 1.04010792081663e-06, "loss": 0.2206, "step": 1382 }, { "epoch": 2.58, "learning_rate": 1.0310849859555339e-06, "loss": 0.2175, "step": 1383 }, { "epoch": 2.58, "learning_rate": 1.0220992309460476e-06, "loss": 0.2368, "step": 1384 }, { "epoch": 2.58, "learning_rate": 1.0131506930378233e-06, "loss": 0.2198, "step": 1385 }, { "epoch": 2.59, "learning_rate": 1.0042394093262476e-06, "loss": 0.2267, "step": 1386 }, { "epoch": 2.59, "learning_rate": 9.953654167522654e-07, "loss": 0.2375, "step": 1387 }, { "epoch": 2.59, "learning_rate": 9.865287521022338e-07, "loss": 0.2254, "step": 1388 }, { "epoch": 2.59, "learning_rate": 9.777294520077718e-07, "loss": 0.2308, "step": 1389 }, { "epoch": 2.59, "learning_rate": 9.68967552945609e-07, "loss": 0.2332, "step": 1390 }, { "epoch": 2.6, "learning_rate": 9.602430912374317e-07, "loss": 0.241, "step": 1391 }, { "epoch": 2.6, "learning_rate": 9.515561030497289e-07, "loss": 0.2365, "step": 1392 }, { "epoch": 2.6, "learning_rate": 9.42906624393648e-07, "loss": 0.2409, "step": 1393 }, { "epoch": 2.6, "learning_rate": 9.342946911248508e-07, "loss": 0.2499, "step": 1394 }, { "epoch": 2.6, "learning_rate": 9.257203389433478e-07, "loss": 0.2499, "step": 1395 }, { "epoch": 2.6, "learning_rate": 9.171836033933668e-07, "loss": 0.2321, "step": 1396 }, { "epoch": 2.61, "learning_rate": 9.086845198631966e-07, "loss": 0.2008, "step": 1397 }, { "epoch": 2.61, "learning_rate": 9.002231235850434e-07, "loss": 0.2222, "step": 1398 }, { "epoch": 2.61, "learning_rate": 8.917994496348847e-07, "loss": 0.2291, "step": 1399 }, { "epoch": 2.61, "learning_rate": 8.834135329323213e-07, "loss": 0.2274, "step": 1400 }, { "epoch": 2.61, "learning_rate": 8.750654082404386e-07, "loss": 0.2099, "step": 1401 }, { "epoch": 2.62, "learning_rate": 8.667551101656568e-07, "loss": 0.2485, "step": 1402 }, { "epoch": 2.62, "learning_rate": 8.584826731575868e-07, "loss": 0.2227, "step": 1403 }, { "epoch": 2.62, "learning_rate": 8.502481315088917e-07, "loss": 0.2231, "step": 1404 }, { "epoch": 2.62, "learning_rate": 8.420515193551437e-07, "loss": 0.2417, "step": 1405 }, { "epoch": 2.62, "learning_rate": 8.338928706746818e-07, "loss": 0.2337, "step": 1406 }, { "epoch": 2.62, "learning_rate": 8.257722192884665e-07, "loss": 0.2075, "step": 1407 }, { "epoch": 2.63, "learning_rate": 8.176895988599465e-07, "loss": 0.2398, "step": 1408 }, { "epoch": 2.63, "learning_rate": 8.09645042894922e-07, "loss": 0.2605, "step": 1409 }, { "epoch": 2.63, "learning_rate": 8.016385847413887e-07, "loss": 0.2192, "step": 1410 }, { "epoch": 2.63, "learning_rate": 7.936702575894228e-07, "loss": 0.2314, "step": 1411 }, { "epoch": 2.63, "learning_rate": 7.857400944710236e-07, "loss": 0.2233, "step": 1412 }, { "epoch": 2.64, "learning_rate": 7.778481282599882e-07, "loss": 0.2472, "step": 1413 }, { "epoch": 2.64, "learning_rate": 7.699943916717712e-07, "loss": 0.2437, "step": 1414 }, { "epoch": 2.64, "learning_rate": 7.621789172633487e-07, "loss": 0.2352, "step": 1415 }, { "epoch": 2.64, "learning_rate": 7.544017374330881e-07, "loss": 0.2465, "step": 1416 }, { "epoch": 2.64, "learning_rate": 7.466628844206059e-07, "loss": 0.2414, "step": 1417 }, { "epoch": 2.65, "learning_rate": 7.389623903066401e-07, "loss": 0.2408, "step": 1418 }, { "epoch": 2.65, "learning_rate": 7.313002870129104e-07, "loss": 0.2577, "step": 1419 }, { "epoch": 2.65, "learning_rate": 7.236766063020028e-07, "loss": 0.2337, "step": 1420 }, { "epoch": 2.65, "learning_rate": 7.160913797772084e-07, "loss": 0.2658, "step": 1421 }, { "epoch": 2.65, "learning_rate": 7.085446388824279e-07, "loss": 0.2491, "step": 1422 }, { "epoch": 2.65, "learning_rate": 7.010364149020077e-07, "loss": 0.223, "step": 1423 }, { "epoch": 2.66, "learning_rate": 6.935667389606405e-07, "loss": 0.2236, "step": 1424 }, { "epoch": 2.66, "learning_rate": 6.861356420232046e-07, "loss": 0.2559, "step": 1425 }, { "epoch": 2.66, "learning_rate": 6.787431548946688e-07, "loss": 0.2467, "step": 1426 }, { "epoch": 2.66, "learning_rate": 6.713893082199374e-07, "loss": 0.2256, "step": 1427 }, { "epoch": 2.66, "learning_rate": 6.640741324837385e-07, "loss": 0.2312, "step": 1428 }, { "epoch": 2.67, "learning_rate": 6.567976580104918e-07, "loss": 0.215, "step": 1429 }, { "epoch": 2.67, "learning_rate": 6.495599149641862e-07, "loss": 0.2148, "step": 1430 }, { "epoch": 2.67, "learning_rate": 6.423609333482505e-07, "loss": 0.2503, "step": 1431 }, { "epoch": 2.67, "learning_rate": 6.35200743005433e-07, "loss": 0.2207, "step": 1432 }, { "epoch": 2.67, "learning_rate": 6.28079373617675e-07, "loss": 0.2315, "step": 1433 }, { "epoch": 2.68, "learning_rate": 6.209968547059886e-07, "loss": 0.2405, "step": 1434 }, { "epoch": 2.68, "learning_rate": 6.139532156303407e-07, "loss": 0.2366, "step": 1435 }, { "epoch": 2.68, "learning_rate": 6.069484855895125e-07, "loss": 0.229, "step": 1436 }, { "epoch": 2.68, "learning_rate": 5.99982693621004e-07, "loss": 0.2507, "step": 1437 }, { "epoch": 2.68, "learning_rate": 5.930558686008936e-07, "loss": 0.2579, "step": 1438 }, { "epoch": 2.68, "learning_rate": 5.861680392437297e-07, "loss": 0.2504, "step": 1439 }, { "epoch": 2.69, "learning_rate": 5.793192341024024e-07, "loss": 0.2253, "step": 1440 }, { "epoch": 2.69, "learning_rate": 5.725094815680365e-07, "loss": 0.243, "step": 1441 }, { "epoch": 2.69, "learning_rate": 5.657388098698636e-07, "loss": 0.2392, "step": 1442 }, { "epoch": 2.69, "learning_rate": 5.590072470751106e-07, "loss": 0.2535, "step": 1443 }, { "epoch": 2.69, "learning_rate": 5.523148210888796e-07, "loss": 0.2003, "step": 1444 }, { "epoch": 2.7, "learning_rate": 5.456615596540394e-07, "loss": 0.2473, "step": 1445 }, { "epoch": 2.7, "learning_rate": 5.390474903511001e-07, "loss": 0.2395, "step": 1446 }, { "epoch": 2.7, "learning_rate": 5.324726405981074e-07, "loss": 0.2506, "step": 1447 }, { "epoch": 2.7, "learning_rate": 5.259370376505258e-07, "loss": 0.2579, "step": 1448 }, { "epoch": 2.7, "learning_rate": 5.194407086011244e-07, "loss": 0.2174, "step": 1449 }, { "epoch": 2.71, "learning_rate": 5.129836803798649e-07, "loss": 0.2374, "step": 1450 }, { "epoch": 2.71, "learning_rate": 5.065659797537925e-07, "loss": 0.2514, "step": 1451 }, { "epoch": 2.71, "learning_rate": 5.001876333269263e-07, "loss": 0.2079, "step": 1452 }, { "epoch": 2.71, "learning_rate": 4.938486675401388e-07, "loss": 0.2313, "step": 1453 }, { "epoch": 2.71, "learning_rate": 4.875491086710594e-07, "loss": 0.2666, "step": 1454 }, { "epoch": 2.71, "learning_rate": 4.812889828339562e-07, "loss": 0.226, "step": 1455 }, { "epoch": 2.72, "learning_rate": 4.7506831597963543e-07, "loss": 0.2289, "step": 1456 }, { "epoch": 2.72, "learning_rate": 4.688871338953238e-07, "loss": 0.2476, "step": 1457 }, { "epoch": 2.72, "learning_rate": 4.627454622045713e-07, "loss": 0.2173, "step": 1458 }, { "epoch": 2.72, "learning_rate": 4.566433263671388e-07, "loss": 0.2489, "step": 1459 }, { "epoch": 2.72, "learning_rate": 4.505807516788996e-07, "loss": 0.2518, "step": 1460 }, { "epoch": 2.73, "learning_rate": 4.4455776327172017e-07, "loss": 0.2235, "step": 1461 }, { "epoch": 2.73, "learning_rate": 4.385743861133762e-07, "loss": 0.2381, "step": 1462 }, { "epoch": 2.73, "learning_rate": 4.326306450074313e-07, "loss": 0.223, "step": 1463 }, { "epoch": 2.73, "learning_rate": 4.267265645931462e-07, "loss": 0.2476, "step": 1464 }, { "epoch": 2.73, "learning_rate": 4.2086216934536625e-07, "loss": 0.2315, "step": 1465 }, { "epoch": 2.74, "learning_rate": 4.1503748357442976e-07, "loss": 0.2575, "step": 1466 }, { "epoch": 2.74, "learning_rate": 4.092525314260609e-07, "loss": 0.2294, "step": 1467 }, { "epoch": 2.74, "learning_rate": 4.035073368812714e-07, "loss": 0.2402, "step": 1468 }, { "epoch": 2.74, "learning_rate": 3.978019237562636e-07, "loss": 0.2493, "step": 1469 }, { "epoch": 2.74, "learning_rate": 3.9213631570232615e-07, "loss": 0.2395, "step": 1470 }, { "epoch": 2.74, "learning_rate": 3.8651053620574417e-07, "loss": 0.2603, "step": 1471 }, { "epoch": 2.75, "learning_rate": 3.8092460858768944e-07, "loss": 0.2332, "step": 1472 }, { "epoch": 2.75, "learning_rate": 3.75378556004139e-07, "loss": 0.2174, "step": 1473 }, { "epoch": 2.75, "learning_rate": 3.6987240144576553e-07, "loss": 0.2019, "step": 1474 }, { "epoch": 2.75, "learning_rate": 3.644061677378541e-07, "loss": 0.2289, "step": 1475 }, { "epoch": 2.75, "learning_rate": 3.58979877540192e-07, "loss": 0.2202, "step": 1476 }, { "epoch": 2.76, "learning_rate": 3.5359355334699584e-07, "loss": 0.2609, "step": 1477 }, { "epoch": 2.76, "learning_rate": 3.482472174867968e-07, "loss": 0.2383, "step": 1478 }, { "epoch": 2.76, "learning_rate": 3.429408921223665e-07, "loss": 0.216, "step": 1479 }, { "epoch": 2.76, "learning_rate": 3.3767459925060585e-07, "loss": 0.2564, "step": 1480 }, { "epoch": 2.76, "learning_rate": 3.324483607024742e-07, "loss": 0.228, "step": 1481 }, { "epoch": 2.76, "learning_rate": 3.2726219814288584e-07, "loss": 0.2259, "step": 1482 }, { "epoch": 2.77, "learning_rate": 3.221161330706235e-07, "loss": 0.2727, "step": 1483 }, { "epoch": 2.77, "learning_rate": 3.1701018681824737e-07, "loss": 0.2283, "step": 1484 }, { "epoch": 2.77, "learning_rate": 3.119443805520106e-07, "loss": 0.213, "step": 1485 }, { "epoch": 2.77, "learning_rate": 3.0691873527177175e-07, "loss": 0.238, "step": 1486 }, { "epoch": 2.77, "learning_rate": 3.019332718109014e-07, "loss": 0.2555, "step": 1487 }, { "epoch": 2.78, "learning_rate": 2.969880108362022e-07, "loss": 0.2341, "step": 1488 }, { "epoch": 2.78, "learning_rate": 2.920829728478192e-07, "loss": 0.236, "step": 1489 }, { "epoch": 2.78, "learning_rate": 2.8721817817915944e-07, "loss": 0.2334, "step": 1490 }, { "epoch": 2.78, "learning_rate": 2.8239364699680136e-07, "loss": 0.2447, "step": 1491 }, { "epoch": 2.78, "learning_rate": 2.776093993004181e-07, "loss": 0.2288, "step": 1492 }, { "epoch": 2.79, "learning_rate": 2.7286545492268835e-07, "loss": 0.2428, "step": 1493 }, { "epoch": 2.79, "learning_rate": 2.681618335292191e-07, "loss": 0.2494, "step": 1494 }, { "epoch": 2.79, "learning_rate": 2.6349855461845766e-07, "loss": 0.2409, "step": 1495 }, { "epoch": 2.79, "learning_rate": 2.588756375216228e-07, "loss": 0.227, "step": 1496 }, { "epoch": 2.79, "learning_rate": 2.5429310140260954e-07, "loss": 0.2334, "step": 1497 }, { "epoch": 2.79, "learning_rate": 2.497509652579222e-07, "loss": 0.2118, "step": 1498 }, { "epoch": 2.8, "learning_rate": 2.4524924791658465e-07, "loss": 0.273, "step": 1499 }, { "epoch": 2.8, "learning_rate": 2.407879680400749e-07, "loss": 0.2172, "step": 1500 }, { "epoch": 2.8, "learning_rate": 2.3636714412223816e-07, "loss": 0.213, "step": 1501 }, { "epoch": 2.8, "learning_rate": 2.319867944892107e-07, "loss": 0.231, "step": 1502 }, { "epoch": 2.8, "learning_rate": 2.276469372993495e-07, "loss": 0.2252, "step": 1503 }, { "epoch": 2.81, "learning_rate": 2.233475905431526e-07, "loss": 0.2279, "step": 1504 }, { "epoch": 2.81, "learning_rate": 2.1908877204318447e-07, "loss": 0.2528, "step": 1505 }, { "epoch": 2.81, "learning_rate": 2.1487049945400408e-07, "loss": 0.2257, "step": 1506 }, { "epoch": 2.81, "learning_rate": 2.1069279026209145e-07, "loss": 0.2398, "step": 1507 }, { "epoch": 2.81, "learning_rate": 2.0655566178577558e-07, "loss": 0.2594, "step": 1508 }, { "epoch": 2.82, "learning_rate": 2.024591311751578e-07, "loss": 0.2304, "step": 1509 }, { "epoch": 2.82, "learning_rate": 1.9840321541204743e-07, "loss": 0.2233, "step": 1510 }, { "epoch": 2.82, "learning_rate": 1.9438793130988954e-07, "loss": 0.2549, "step": 1511 }, { "epoch": 2.82, "learning_rate": 1.904132955136917e-07, "loss": 0.2369, "step": 1512 }, { "epoch": 2.82, "learning_rate": 1.8647932449995855e-07, "loss": 0.2281, "step": 1513 }, { "epoch": 2.82, "learning_rate": 1.825860345766206e-07, "loss": 0.2298, "step": 1514 }, { "epoch": 2.83, "learning_rate": 1.787334418829745e-07, "loss": 0.2244, "step": 1515 }, { "epoch": 2.83, "learning_rate": 1.7492156238960057e-07, "loss": 0.2263, "step": 1516 }, { "epoch": 2.83, "learning_rate": 1.711504118983154e-07, "loss": 0.2325, "step": 1517 }, { "epoch": 2.83, "learning_rate": 1.6742000604209163e-07, "loss": 0.2093, "step": 1518 }, { "epoch": 2.83, "learning_rate": 1.6373036028499933e-07, "loss": 0.2287, "step": 1519 }, { "epoch": 2.84, "learning_rate": 1.6008148992214366e-07, "loss": 0.2273, "step": 1520 }, { "epoch": 2.84, "learning_rate": 1.5647341007959394e-07, "loss": 0.2327, "step": 1521 }, { "epoch": 2.84, "learning_rate": 1.5290613571433244e-07, "loss": 0.2346, "step": 1522 }, { "epoch": 2.84, "learning_rate": 1.4937968161418127e-07, "loss": 0.1901, "step": 1523 }, { "epoch": 2.84, "learning_rate": 1.4589406239774672e-07, "loss": 0.225, "step": 1524 }, { "epoch": 2.85, "learning_rate": 1.4244929251435724e-07, "loss": 0.2301, "step": 1525 }, { "epoch": 2.85, "learning_rate": 1.3904538624400775e-07, "loss": 0.2435, "step": 1526 }, { "epoch": 2.85, "learning_rate": 1.356823576972899e-07, "loss": 0.2486, "step": 1527 }, { "epoch": 2.85, "learning_rate": 1.3236022081534627e-07, "loss": 0.2323, "step": 1528 }, { "epoch": 2.85, "learning_rate": 1.290789893698019e-07, "loss": 0.2446, "step": 1529 }, { "epoch": 2.85, "learning_rate": 1.2583867696271847e-07, "loss": 0.2584, "step": 1530 }, { "epoch": 2.86, "learning_rate": 1.2263929702652223e-07, "loss": 0.2607, "step": 1531 }, { "epoch": 2.86, "learning_rate": 1.1948086282396632e-07, "loss": 0.2522, "step": 1532 }, { "epoch": 2.86, "learning_rate": 1.1636338744806186e-07, "loss": 0.2309, "step": 1533 }, { "epoch": 2.86, "learning_rate": 1.1328688382203024e-07, "loss": 0.2064, "step": 1534 }, { "epoch": 2.86, "learning_rate": 1.1025136469924646e-07, "loss": 0.2455, "step": 1535 }, { "epoch": 2.87, "learning_rate": 1.0725684266319036e-07, "loss": 0.2332, "step": 1536 }, { "epoch": 2.87, "learning_rate": 1.0430333012739103e-07, "loss": 0.2441, "step": 1537 }, { "epoch": 2.87, "learning_rate": 1.0139083933537463e-07, "loss": 0.2192, "step": 1538 }, { "epoch": 2.87, "learning_rate": 9.851938236061786e-08, "loss": 0.2429, "step": 1539 }, { "epoch": 2.87, "learning_rate": 9.568897110649345e-08, "loss": 0.2448, "step": 1540 }, { "epoch": 2.88, "learning_rate": 9.289961730622465e-08, "loss": 0.2364, "step": 1541 }, { "epoch": 2.88, "learning_rate": 9.015133252282981e-08, "loss": 0.2181, "step": 1542 }, { "epoch": 2.88, "learning_rate": 8.744412814908787e-08, "loss": 0.2238, "step": 1543 }, { "epoch": 2.88, "learning_rate": 8.477801540747288e-08, "loss": 0.2212, "step": 1544 }, { "epoch": 2.88, "learning_rate": 8.215300535012516e-08, "loss": 0.2096, "step": 1545 }, { "epoch": 2.88, "learning_rate": 7.956910885879132e-08, "loss": 0.2472, "step": 1546 }, { "epoch": 2.89, "learning_rate": 7.702633664478876e-08, "loss": 0.2385, "step": 1547 }, { "epoch": 2.89, "learning_rate": 7.452469924895789e-08, "loss": 0.2364, "step": 1548 }, { "epoch": 2.89, "learning_rate": 7.206420704161665e-08, "loss": 0.2161, "step": 1549 }, { "epoch": 2.89, "learning_rate": 6.964487022251942e-08, "loss": 0.2321, "step": 1550 }, { "epoch": 2.89, "learning_rate": 6.726669882081705e-08, "loss": 0.212, "step": 1551 }, { "epoch": 2.9, "learning_rate": 6.492970269500909e-08, "loss": 0.2415, "step": 1552 }, { "epoch": 2.9, "learning_rate": 6.263389153290834e-08, "loss": 0.2536, "step": 1553 }, { "epoch": 2.9, "learning_rate": 6.037927485159966e-08, "loss": 0.2179, "step": 1554 }, { "epoch": 2.9, "learning_rate": 5.816586199739793e-08, "loss": 0.2287, "step": 1555 }, { "epoch": 2.9, "learning_rate": 5.5993662145812364e-08, "loss": 0.2381, "step": 1556 }, { "epoch": 2.9, "learning_rate": 5.386268430150887e-08, "loss": 0.2474, "step": 1557 }, { "epoch": 2.91, "learning_rate": 5.1772937298268934e-08, "loss": 0.2229, "step": 1558 }, { "epoch": 2.91, "learning_rate": 4.972442979895409e-08, "loss": 0.2488, "step": 1559 }, { "epoch": 2.91, "learning_rate": 4.7717170295473737e-08, "loss": 0.2451, "step": 1560 }, { "epoch": 2.91, "learning_rate": 4.575116710874627e-08, "loss": 0.2495, "step": 1561 }, { "epoch": 2.91, "learning_rate": 4.3826428388665795e-08, "loss": 0.2112, "step": 1562 }, { "epoch": 2.92, "learning_rate": 4.194296211406768e-08, "loss": 0.218, "step": 1563 }, { "epoch": 2.92, "learning_rate": 4.010077609269747e-08, "loss": 0.2337, "step": 1564 }, { "epoch": 2.92, "learning_rate": 3.8299877961175404e-08, "loss": 0.2279, "step": 1565 }, { "epoch": 2.92, "learning_rate": 3.654027518496639e-08, "loss": 0.2412, "step": 1566 }, { "epoch": 2.92, "learning_rate": 3.4821975058350056e-08, "loss": 0.2402, "step": 1567 }, { "epoch": 2.93, "learning_rate": 3.3144984704389646e-08, "loss": 0.2421, "step": 1568 }, { "epoch": 2.93, "learning_rate": 3.150931107489985e-08, "loss": 0.2464, "step": 1569 }, { "epoch": 2.93, "learning_rate": 2.9914960950425674e-08, "loss": 0.2621, "step": 1570 }, { "epoch": 2.93, "learning_rate": 2.8361940940202505e-08, "loss": 0.2483, "step": 1571 }, { "epoch": 2.93, "learning_rate": 2.6850257482140542e-08, "loss": 0.227, "step": 1572 }, { "epoch": 2.93, "learning_rate": 2.537991684279151e-08, "loss": 0.2366, "step": 1573 }, { "epoch": 2.94, "learning_rate": 2.3950925117322e-08, "loss": 0.208, "step": 1574 }, { "epoch": 2.94, "learning_rate": 2.2563288229494608e-08, "loss": 0.2238, "step": 1575 }, { "epoch": 2.94, "learning_rate": 2.1217011931633504e-08, "loss": 0.2139, "step": 1576 }, { "epoch": 2.94, "learning_rate": 1.9912101804612226e-08, "loss": 0.2536, "step": 1577 }, { "epoch": 2.94, "learning_rate": 1.8648563257818165e-08, "loss": 0.2276, "step": 1578 }, { "epoch": 2.95, "learning_rate": 1.7426401529142546e-08, "loss": 0.2607, "step": 1579 }, { "epoch": 2.95, "learning_rate": 1.6245621684948253e-08, "loss": 0.2258, "step": 1580 }, { "epoch": 2.95, "learning_rate": 1.5106228620056506e-08, "loss": 0.2219, "step": 1581 }, { "epoch": 2.95, "learning_rate": 1.4008227057717983e-08, "loss": 0.204, "step": 1582 }, { "epoch": 2.95, "learning_rate": 1.2951621549605053e-08, "loss": 0.2679, "step": 1583 }, { "epoch": 2.96, "learning_rate": 1.1936416475781808e-08, "loss": 0.2439, "step": 1584 }, { "epoch": 2.96, "learning_rate": 1.0962616044694063e-08, "loss": 0.2268, "step": 1585 }, { "epoch": 2.96, "learning_rate": 1.0030224293142709e-08, "loss": 0.2453, "step": 1586 }, { "epoch": 2.96, "learning_rate": 9.139245086279281e-09, "loss": 0.2266, "step": 1587 }, { "epoch": 2.96, "learning_rate": 8.28968211757819e-09, "loss": 0.257, "step": 1588 }, { "epoch": 2.96, "learning_rate": 7.481538908828968e-09, "loss": 0.2528, "step": 1589 }, { "epoch": 2.97, "learning_rate": 6.714818810117374e-09, "loss": 0.242, "step": 1590 }, { "epoch": 2.97, "learning_rate": 5.9895249998165315e-09, "loss": 0.2264, "step": 1591 }, { "epoch": 2.97, "learning_rate": 5.305660484566932e-09, "loss": 0.2411, "step": 1592 }, { "epoch": 2.97, "learning_rate": 4.663228099269779e-09, "loss": 0.2522, "step": 1593 }, { "epoch": 2.97, "learning_rate": 4.062230507071441e-09, "loss": 0.2657, "step": 1594 }, { "epoch": 2.98, "learning_rate": 3.5026701993556845e-09, "loss": 0.2265, "step": 1595 }, { "epoch": 2.98, "learning_rate": 2.984549495730349e-09, "loss": 0.2307, "step": 1596 }, { "epoch": 2.98, "learning_rate": 2.5078705440184648e-09, "loss": 0.2722, "step": 1597 }, { "epoch": 2.98, "learning_rate": 2.0726353202527027e-09, "loss": 0.2322, "step": 1598 }, { "epoch": 2.98, "learning_rate": 1.6788456286620513e-09, "loss": 0.2441, "step": 1599 }, { "epoch": 2.99, "learning_rate": 1.3265031016662655e-09, "loss": 0.2531, "step": 1600 }, { "epoch": 2.99, "learning_rate": 1.0156091998703156e-09, "loss": 0.2157, "step": 1601 }, { "epoch": 2.99, "learning_rate": 7.461652120588359e-10, "loss": 0.2116, "step": 1602 }, { "epoch": 2.99, "learning_rate": 5.181722551872437e-10, "loss": 0.2378, "step": 1603 }, { "epoch": 2.99, "learning_rate": 3.316312743817385e-10, "loss": 0.23, "step": 1604 }, { "epoch": 2.99, "learning_rate": 1.8654304293042048e-10, "loss": 0.247, "step": 1605 }, { "epoch": 3.0, "learning_rate": 8.290816228329057e-11, "loss": 0.2574, "step": 1606 }, { "epoch": 3.0, "learning_rate": 2.0727062051140166e-11, "loss": 0.2239, "step": 1607 }, { "epoch": 3.0, "learning_rate": 0.0, "loss": 0.2326, "step": 1608 }, { "epoch": 3.0, "step": 1608, "total_flos": 4.0108451008956334e+18, "train_loss": 0.1779733608055174, "train_runtime": 71136.3444, "train_samples_per_second": 2.893, "train_steps_per_second": 0.023 } ], "max_steps": 1608, "num_train_epochs": 3, "total_flos": 4.0108451008956334e+18, "trial_name": null, "trial_params": null }