{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.9988398717753015, "eval_steps": 500, "global_step": 2046, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 3.2258064516129035e-07, "loss": 1.3492, "step": 1 }, { "epoch": 0.0, "learning_rate": 6.451612903225807e-07, "loss": 1.2643, "step": 2 }, { "epoch": 0.0, "learning_rate": 9.67741935483871e-07, "loss": 1.3581, "step": 3 }, { "epoch": 0.0, "learning_rate": 1.2903225806451614e-06, "loss": 1.305, "step": 4 }, { "epoch": 0.0, "learning_rate": 1.6129032258064516e-06, "loss": 1.2447, "step": 5 }, { "epoch": 0.01, "learning_rate": 1.935483870967742e-06, "loss": 1.2918, "step": 6 }, { "epoch": 0.01, "learning_rate": 2.2580645161290324e-06, "loss": 1.2726, "step": 7 }, { "epoch": 0.01, "learning_rate": 2.580645161290323e-06, "loss": 1.2502, "step": 8 }, { "epoch": 0.01, "learning_rate": 2.903225806451613e-06, "loss": 1.2216, "step": 9 }, { "epoch": 0.01, "learning_rate": 3.225806451612903e-06, "loss": 1.216, "step": 10 }, { "epoch": 0.01, "learning_rate": 3.548387096774194e-06, "loss": 1.2476, "step": 11 }, { "epoch": 0.01, "learning_rate": 3.870967741935484e-06, "loss": 1.1138, "step": 12 }, { "epoch": 0.01, "learning_rate": 4.193548387096774e-06, "loss": 1.0871, "step": 13 }, { "epoch": 0.01, "learning_rate": 4.516129032258065e-06, "loss": 1.018, "step": 14 }, { "epoch": 0.01, "learning_rate": 4.838709677419355e-06, "loss": 1.04, "step": 15 }, { "epoch": 0.02, "learning_rate": 5.161290322580646e-06, "loss": 0.9968, "step": 16 }, { "epoch": 0.02, "learning_rate": 5.483870967741935e-06, "loss": 0.9403, "step": 17 }, { "epoch": 0.02, "learning_rate": 5.806451612903226e-06, "loss": 0.9632, "step": 18 }, { "epoch": 0.02, "learning_rate": 6.129032258064517e-06, "loss": 0.9037, "step": 19 }, { "epoch": 0.02, "learning_rate": 6.451612903225806e-06, "loss": 0.8698, "step": 20 }, { "epoch": 0.02, "learning_rate": 6.774193548387097e-06, "loss": 0.8872, "step": 21 }, { "epoch": 0.02, "learning_rate": 7.096774193548388e-06, "loss": 0.8249, "step": 22 }, { "epoch": 0.02, "learning_rate": 7.4193548387096784e-06, "loss": 0.8331, "step": 23 }, { "epoch": 0.02, "learning_rate": 7.741935483870968e-06, "loss": 0.8508, "step": 24 }, { "epoch": 0.02, "learning_rate": 8.064516129032258e-06, "loss": 0.8231, "step": 25 }, { "epoch": 0.03, "learning_rate": 8.387096774193549e-06, "loss": 0.8378, "step": 26 }, { "epoch": 0.03, "learning_rate": 8.70967741935484e-06, "loss": 0.8082, "step": 27 }, { "epoch": 0.03, "learning_rate": 9.03225806451613e-06, "loss": 0.7791, "step": 28 }, { "epoch": 0.03, "learning_rate": 9.35483870967742e-06, "loss": 0.7921, "step": 29 }, { "epoch": 0.03, "learning_rate": 9.67741935483871e-06, "loss": 0.7567, "step": 30 }, { "epoch": 0.03, "learning_rate": 1e-05, "loss": 0.7616, "step": 31 }, { "epoch": 0.03, "learning_rate": 1.0322580645161291e-05, "loss": 0.7854, "step": 32 }, { "epoch": 0.03, "learning_rate": 1.0645161290322582e-05, "loss": 0.8004, "step": 33 }, { "epoch": 0.03, "learning_rate": 1.096774193548387e-05, "loss": 0.6993, "step": 34 }, { "epoch": 0.03, "learning_rate": 1.1290322580645164e-05, "loss": 0.7483, "step": 35 }, { "epoch": 0.04, "learning_rate": 1.1612903225806453e-05, "loss": 0.7488, "step": 36 }, { "epoch": 0.04, "learning_rate": 1.1935483870967743e-05, "loss": 0.7289, "step": 37 }, { "epoch": 0.04, "learning_rate": 1.2258064516129034e-05, "loss": 0.7379, "step": 38 }, { "epoch": 0.04, "learning_rate": 1.2580645161290324e-05, "loss": 0.78, "step": 39 }, { "epoch": 0.04, "learning_rate": 1.2903225806451613e-05, "loss": 0.7743, "step": 40 }, { "epoch": 0.04, "learning_rate": 1.3225806451612903e-05, "loss": 0.691, "step": 41 }, { "epoch": 0.04, "learning_rate": 1.3548387096774194e-05, "loss": 0.688, "step": 42 }, { "epoch": 0.04, "learning_rate": 1.3870967741935486e-05, "loss": 0.7568, "step": 43 }, { "epoch": 0.04, "learning_rate": 1.4193548387096776e-05, "loss": 0.7057, "step": 44 }, { "epoch": 0.04, "learning_rate": 1.4516129032258066e-05, "loss": 0.6976, "step": 45 }, { "epoch": 0.04, "learning_rate": 1.4838709677419357e-05, "loss": 0.6915, "step": 46 }, { "epoch": 0.05, "learning_rate": 1.5161290322580646e-05, "loss": 0.6547, "step": 47 }, { "epoch": 0.05, "learning_rate": 1.5483870967741936e-05, "loss": 0.6715, "step": 48 }, { "epoch": 0.05, "learning_rate": 1.5806451612903226e-05, "loss": 0.6537, "step": 49 }, { "epoch": 0.05, "learning_rate": 1.6129032258064517e-05, "loss": 0.6247, "step": 50 }, { "epoch": 0.05, "learning_rate": 1.6451612903225807e-05, "loss": 0.709, "step": 51 }, { "epoch": 0.05, "learning_rate": 1.6774193548387098e-05, "loss": 0.731, "step": 52 }, { "epoch": 0.05, "learning_rate": 1.7096774193548388e-05, "loss": 0.6956, "step": 53 }, { "epoch": 0.05, "learning_rate": 1.741935483870968e-05, "loss": 0.661, "step": 54 }, { "epoch": 0.05, "learning_rate": 1.774193548387097e-05, "loss": 0.7303, "step": 55 }, { "epoch": 0.05, "learning_rate": 1.806451612903226e-05, "loss": 0.6676, "step": 56 }, { "epoch": 0.06, "learning_rate": 1.838709677419355e-05, "loss": 0.7452, "step": 57 }, { "epoch": 0.06, "learning_rate": 1.870967741935484e-05, "loss": 0.7, "step": 58 }, { "epoch": 0.06, "learning_rate": 1.903225806451613e-05, "loss": 0.6063, "step": 59 }, { "epoch": 0.06, "learning_rate": 1.935483870967742e-05, "loss": 0.6786, "step": 60 }, { "epoch": 0.06, "learning_rate": 1.967741935483871e-05, "loss": 0.6517, "step": 61 }, { "epoch": 0.06, "learning_rate": 2e-05, "loss": 0.676, "step": 62 }, { "epoch": 0.06, "learning_rate": 1.9999987463210805e-05, "loss": 0.688, "step": 63 }, { "epoch": 0.06, "learning_rate": 1.999994985287465e-05, "loss": 0.6555, "step": 64 }, { "epoch": 0.06, "learning_rate": 1.999988716908584e-05, "loss": 0.6365, "step": 65 }, { "epoch": 0.06, "learning_rate": 1.9999799412001547e-05, "loss": 0.6324, "step": 66 }, { "epoch": 0.07, "learning_rate": 1.9999686581841805e-05, "loss": 0.6636, "step": 67 }, { "epoch": 0.07, "learning_rate": 1.9999548678889523e-05, "loss": 0.7018, "step": 68 }, { "epoch": 0.07, "learning_rate": 1.999938570349047e-05, "loss": 0.603, "step": 69 }, { "epoch": 0.07, "learning_rate": 1.9999197656053288e-05, "loss": 0.6499, "step": 70 }, { "epoch": 0.07, "learning_rate": 1.9998984537049476e-05, "loss": 0.6041, "step": 71 }, { "epoch": 0.07, "learning_rate": 1.99987463470134e-05, "loss": 0.6411, "step": 72 }, { "epoch": 0.07, "learning_rate": 1.999848308654229e-05, "loss": 0.6731, "step": 73 }, { "epoch": 0.07, "learning_rate": 1.999819475629623e-05, "loss": 0.6046, "step": 74 }, { "epoch": 0.07, "learning_rate": 1.9997881356998172e-05, "loss": 0.6407, "step": 75 }, { "epoch": 0.07, "learning_rate": 1.9997542889433917e-05, "loss": 0.6315, "step": 76 }, { "epoch": 0.08, "learning_rate": 1.9997179354452126e-05, "loss": 0.5949, "step": 77 }, { "epoch": 0.08, "learning_rate": 1.9996790752964305e-05, "loss": 0.7021, "step": 78 }, { "epoch": 0.08, "learning_rate": 1.9996377085944826e-05, "loss": 0.6794, "step": 79 }, { "epoch": 0.08, "learning_rate": 1.9995938354430898e-05, "loss": 0.6318, "step": 80 }, { "epoch": 0.08, "learning_rate": 1.9995474559522576e-05, "loss": 0.6538, "step": 81 }, { "epoch": 0.08, "learning_rate": 1.999498570238276e-05, "loss": 0.7083, "step": 82 }, { "epoch": 0.08, "learning_rate": 1.9994471784237188e-05, "loss": 0.6271, "step": 83 }, { "epoch": 0.08, "learning_rate": 1.999393280637444e-05, "loss": 0.63, "step": 84 }, { "epoch": 0.08, "learning_rate": 1.9993368770145927e-05, "loss": 0.6771, "step": 85 }, { "epoch": 0.08, "learning_rate": 1.9992779676965884e-05, "loss": 0.6195, "step": 86 }, { "epoch": 0.08, "learning_rate": 1.9992165528311385e-05, "loss": 0.5925, "step": 87 }, { "epoch": 0.09, "learning_rate": 1.9991526325722316e-05, "loss": 0.6554, "step": 88 }, { "epoch": 0.09, "learning_rate": 1.9990862070801388e-05, "loss": 0.6351, "step": 89 }, { "epoch": 0.09, "learning_rate": 1.999017276521413e-05, "loss": 0.6296, "step": 90 }, { "epoch": 0.09, "learning_rate": 1.9989458410688865e-05, "loss": 0.5696, "step": 91 }, { "epoch": 0.09, "learning_rate": 1.9988719009016753e-05, "loss": 0.6469, "step": 92 }, { "epoch": 0.09, "learning_rate": 1.9987954562051724e-05, "loss": 0.6266, "step": 93 }, { "epoch": 0.09, "learning_rate": 1.998716507171053e-05, "loss": 0.5775, "step": 94 }, { "epoch": 0.09, "learning_rate": 1.99863505399727e-05, "loss": 0.6117, "step": 95 }, { "epoch": 0.09, "learning_rate": 1.9985510968880555e-05, "loss": 0.5736, "step": 96 }, { "epoch": 0.09, "learning_rate": 1.998464636053921e-05, "loss": 0.5961, "step": 97 }, { "epoch": 0.1, "learning_rate": 1.9983756717116534e-05, "loss": 0.6247, "step": 98 }, { "epoch": 0.1, "learning_rate": 1.9982842040843193e-05, "loss": 0.5591, "step": 99 }, { "epoch": 0.1, "learning_rate": 1.99819023340126e-05, "loss": 0.5952, "step": 100 }, { "epoch": 0.1, "learning_rate": 1.9980937598980943e-05, "loss": 0.601, "step": 101 }, { "epoch": 0.1, "learning_rate": 1.9979947838167152e-05, "loss": 0.5958, "step": 102 }, { "epoch": 0.1, "learning_rate": 1.9978933054052913e-05, "loss": 0.6028, "step": 103 }, { "epoch": 0.1, "learning_rate": 1.9977893249182654e-05, "loss": 0.5957, "step": 104 }, { "epoch": 0.1, "learning_rate": 1.9976828426163538e-05, "loss": 0.5807, "step": 105 }, { "epoch": 0.1, "learning_rate": 1.9975738587665455e-05, "loss": 0.6048, "step": 106 }, { "epoch": 0.1, "learning_rate": 1.9974623736421025e-05, "loss": 0.5636, "step": 107 }, { "epoch": 0.11, "learning_rate": 1.9973483875225573e-05, "loss": 0.6059, "step": 108 }, { "epoch": 0.11, "learning_rate": 1.9972319006937143e-05, "loss": 0.6127, "step": 109 }, { "epoch": 0.11, "learning_rate": 1.9971129134476474e-05, "loss": 0.6312, "step": 110 }, { "epoch": 0.11, "learning_rate": 1.996991426082701e-05, "loss": 0.6463, "step": 111 }, { "epoch": 0.11, "learning_rate": 1.996867438903486e-05, "loss": 0.6158, "step": 112 }, { "epoch": 0.11, "learning_rate": 1.9967409522208835e-05, "loss": 0.5442, "step": 113 }, { "epoch": 0.11, "learning_rate": 1.996611966352041e-05, "loss": 0.5618, "step": 114 }, { "epoch": 0.11, "learning_rate": 1.9964804816203723e-05, "loss": 0.6125, "step": 115 }, { "epoch": 0.11, "learning_rate": 1.9963464983555557e-05, "loss": 0.5966, "step": 116 }, { "epoch": 0.11, "learning_rate": 1.996210016893536e-05, "loss": 0.6303, "step": 117 }, { "epoch": 0.12, "learning_rate": 1.9960710375765212e-05, "loss": 0.5725, "step": 118 }, { "epoch": 0.12, "learning_rate": 1.9959295607529818e-05, "loss": 0.6239, "step": 119 }, { "epoch": 0.12, "learning_rate": 1.9957855867776507e-05, "loss": 0.5591, "step": 120 }, { "epoch": 0.12, "learning_rate": 1.9956391160115224e-05, "loss": 0.6227, "step": 121 }, { "epoch": 0.12, "learning_rate": 1.9954901488218515e-05, "loss": 0.5941, "step": 122 }, { "epoch": 0.12, "learning_rate": 1.9953386855821523e-05, "loss": 0.5833, "step": 123 }, { "epoch": 0.12, "learning_rate": 1.995184726672197e-05, "loss": 0.5678, "step": 124 }, { "epoch": 0.12, "learning_rate": 1.995028272478016e-05, "loss": 0.5532, "step": 125 }, { "epoch": 0.12, "learning_rate": 1.994869323391895e-05, "loss": 0.5698, "step": 126 }, { "epoch": 0.12, "learning_rate": 1.9947078798123778e-05, "loss": 0.5388, "step": 127 }, { "epoch": 0.13, "learning_rate": 1.9945439421442602e-05, "loss": 0.532, "step": 128 }, { "epoch": 0.13, "learning_rate": 1.9943775107985925e-05, "loss": 0.5624, "step": 129 }, { "epoch": 0.13, "learning_rate": 1.994208586192678e-05, "loss": 0.6045, "step": 130 }, { "epoch": 0.13, "learning_rate": 1.9940371687500713e-05, "loss": 0.5469, "step": 131 }, { "epoch": 0.13, "learning_rate": 1.993863258900577e-05, "loss": 0.5807, "step": 132 }, { "epoch": 0.13, "learning_rate": 1.993686857080249e-05, "loss": 0.5309, "step": 133 }, { "epoch": 0.13, "learning_rate": 1.9935079637313906e-05, "loss": 0.5688, "step": 134 }, { "epoch": 0.13, "learning_rate": 1.993326579302551e-05, "loss": 0.5997, "step": 135 }, { "epoch": 0.13, "learning_rate": 1.9931427042485252e-05, "loss": 0.5614, "step": 136 }, { "epoch": 0.13, "learning_rate": 1.992956339030355e-05, "loss": 0.5718, "step": 137 }, { "epoch": 0.13, "learning_rate": 1.992767484115324e-05, "loss": 0.5724, "step": 138 }, { "epoch": 0.14, "learning_rate": 1.992576139976959e-05, "loss": 0.5572, "step": 139 }, { "epoch": 0.14, "learning_rate": 1.9923823070950282e-05, "loss": 0.5284, "step": 140 }, { "epoch": 0.14, "learning_rate": 1.992185985955541e-05, "loss": 0.5566, "step": 141 }, { "epoch": 0.14, "learning_rate": 1.991987177050743e-05, "loss": 0.5403, "step": 142 }, { "epoch": 0.14, "learning_rate": 1.9917858808791205e-05, "loss": 0.5711, "step": 143 }, { "epoch": 0.14, "learning_rate": 1.991582097945395e-05, "loss": 0.5588, "step": 144 }, { "epoch": 0.14, "learning_rate": 1.9913758287605227e-05, "loss": 0.5948, "step": 145 }, { "epoch": 0.14, "learning_rate": 1.991167073841695e-05, "loss": 0.5692, "step": 146 }, { "epoch": 0.14, "learning_rate": 1.990955833712334e-05, "loss": 0.5125, "step": 147 }, { "epoch": 0.14, "learning_rate": 1.9907421089020956e-05, "loss": 0.5543, "step": 148 }, { "epoch": 0.15, "learning_rate": 1.9905258999468634e-05, "loss": 0.5712, "step": 149 }, { "epoch": 0.15, "learning_rate": 1.9903072073887507e-05, "loss": 0.6422, "step": 150 }, { "epoch": 0.15, "learning_rate": 1.990086031776099e-05, "loss": 0.5705, "step": 151 }, { "epoch": 0.15, "learning_rate": 1.9898623736634738e-05, "loss": 0.5528, "step": 152 }, { "epoch": 0.15, "learning_rate": 1.989636233611666e-05, "loss": 0.5147, "step": 153 }, { "epoch": 0.15, "learning_rate": 1.98940761218769e-05, "loss": 0.5461, "step": 154 }, { "epoch": 0.15, "learning_rate": 1.989176509964781e-05, "loss": 0.5166, "step": 155 }, { "epoch": 0.15, "learning_rate": 1.9889429275223958e-05, "loss": 0.531, "step": 156 }, { "epoch": 0.15, "learning_rate": 1.9887068654462088e-05, "loss": 0.563, "step": 157 }, { "epoch": 0.15, "learning_rate": 1.9884683243281117e-05, "loss": 0.5626, "step": 158 }, { "epoch": 0.16, "learning_rate": 1.9882273047662128e-05, "loss": 0.5751, "step": 159 }, { "epoch": 0.16, "learning_rate": 1.9879838073648342e-05, "loss": 0.6089, "step": 160 }, { "epoch": 0.16, "learning_rate": 1.9877378327345115e-05, "loss": 0.5546, "step": 161 }, { "epoch": 0.16, "learning_rate": 1.9874893814919908e-05, "loss": 0.5201, "step": 162 }, { "epoch": 0.16, "learning_rate": 1.9872384542602278e-05, "loss": 0.5265, "step": 163 }, { "epoch": 0.16, "learning_rate": 1.9869850516683875e-05, "loss": 0.5223, "step": 164 }, { "epoch": 0.16, "learning_rate": 1.9867291743518407e-05, "loss": 0.5595, "step": 165 }, { "epoch": 0.16, "learning_rate": 1.9864708229521637e-05, "loss": 0.5394, "step": 166 }, { "epoch": 0.16, "learning_rate": 1.986209998117135e-05, "loss": 0.6096, "step": 167 }, { "epoch": 0.16, "learning_rate": 1.985946700500737e-05, "loss": 0.5869, "step": 168 }, { "epoch": 0.17, "learning_rate": 1.9856809307631498e-05, "loss": 0.5593, "step": 169 }, { "epoch": 0.17, "learning_rate": 1.985412689570754e-05, "loss": 0.5314, "step": 170 }, { "epoch": 0.17, "learning_rate": 1.9851419775961265e-05, "loss": 0.5075, "step": 171 }, { "epoch": 0.17, "learning_rate": 1.9848687955180386e-05, "loss": 0.5531, "step": 172 }, { "epoch": 0.17, "learning_rate": 1.9845931440214557e-05, "loss": 0.5119, "step": 173 }, { "epoch": 0.17, "learning_rate": 1.9843150237975343e-05, "loss": 0.5471, "step": 174 }, { "epoch": 0.17, "learning_rate": 1.984034435543622e-05, "loss": 0.5247, "step": 175 }, { "epoch": 0.17, "learning_rate": 1.9837513799632536e-05, "loss": 0.5215, "step": 176 }, { "epoch": 0.17, "learning_rate": 1.9834658577661505e-05, "loss": 0.5237, "step": 177 }, { "epoch": 0.17, "learning_rate": 1.9831778696682195e-05, "loss": 0.5432, "step": 178 }, { "epoch": 0.17, "learning_rate": 1.9828874163915496e-05, "loss": 0.5245, "step": 179 }, { "epoch": 0.18, "learning_rate": 1.9825944986644116e-05, "loss": 0.5952, "step": 180 }, { "epoch": 0.18, "learning_rate": 1.982299117221254e-05, "loss": 0.5093, "step": 181 }, { "epoch": 0.18, "learning_rate": 1.9820012728027044e-05, "loss": 0.5416, "step": 182 }, { "epoch": 0.18, "learning_rate": 1.9817009661555654e-05, "loss": 0.5325, "step": 183 }, { "epoch": 0.18, "learning_rate": 1.981398198032813e-05, "loss": 0.5486, "step": 184 }, { "epoch": 0.18, "learning_rate": 1.9810929691935956e-05, "loss": 0.5517, "step": 185 }, { "epoch": 0.18, "learning_rate": 1.9807852804032306e-05, "loss": 0.4836, "step": 186 }, { "epoch": 0.18, "learning_rate": 1.9804751324332043e-05, "loss": 0.5404, "step": 187 }, { "epoch": 0.18, "learning_rate": 1.9801625260611684e-05, "loss": 0.5618, "step": 188 }, { "epoch": 0.18, "learning_rate": 1.9798474620709395e-05, "loss": 0.5195, "step": 189 }, { "epoch": 0.19, "learning_rate": 1.9795299412524948e-05, "loss": 0.545, "step": 190 }, { "epoch": 0.19, "learning_rate": 1.979209964401973e-05, "loss": 0.5394, "step": 191 }, { "epoch": 0.19, "learning_rate": 1.978887532321671e-05, "loss": 0.5178, "step": 192 }, { "epoch": 0.19, "learning_rate": 1.9785626458200413e-05, "loss": 0.5361, "step": 193 }, { "epoch": 0.19, "learning_rate": 1.9782353057116902e-05, "loss": 0.5322, "step": 194 }, { "epoch": 0.19, "learning_rate": 1.9779055128173766e-05, "loss": 0.5629, "step": 195 }, { "epoch": 0.19, "learning_rate": 1.9775732679640093e-05, "loss": 0.6049, "step": 196 }, { "epoch": 0.19, "learning_rate": 1.9772385719846454e-05, "loss": 0.5246, "step": 197 }, { "epoch": 0.19, "learning_rate": 1.976901425718487e-05, "loss": 0.4952, "step": 198 }, { "epoch": 0.19, "learning_rate": 1.976561830010881e-05, "loss": 0.505, "step": 199 }, { "epoch": 0.2, "learning_rate": 1.9762197857133148e-05, "loss": 0.5165, "step": 200 }, { "epoch": 0.2, "learning_rate": 1.975875293683416e-05, "loss": 0.5345, "step": 201 }, { "epoch": 0.2, "learning_rate": 1.9755283547849496e-05, "loss": 0.518, "step": 202 }, { "epoch": 0.2, "learning_rate": 1.9751789698878153e-05, "loss": 0.5048, "step": 203 }, { "epoch": 0.2, "learning_rate": 1.974827139868046e-05, "loss": 0.5409, "step": 204 }, { "epoch": 0.2, "learning_rate": 1.974472865607806e-05, "loss": 0.5395, "step": 205 }, { "epoch": 0.2, "learning_rate": 1.9741161479953872e-05, "loss": 0.4847, "step": 206 }, { "epoch": 0.2, "learning_rate": 1.9737569879252082e-05, "loss": 0.5422, "step": 207 }, { "epoch": 0.2, "learning_rate": 1.9733953862978125e-05, "loss": 0.5161, "step": 208 }, { "epoch": 0.2, "learning_rate": 1.9730313440198637e-05, "loss": 0.5273, "step": 209 }, { "epoch": 0.21, "learning_rate": 1.972664862004147e-05, "loss": 0.5225, "step": 210 }, { "epoch": 0.21, "learning_rate": 1.9722959411695636e-05, "loss": 0.5152, "step": 211 }, { "epoch": 0.21, "learning_rate": 1.9719245824411298e-05, "loss": 0.4985, "step": 212 }, { "epoch": 0.21, "learning_rate": 1.9715507867499754e-05, "loss": 0.5388, "step": 213 }, { "epoch": 0.21, "learning_rate": 1.9711745550333392e-05, "loss": 0.5609, "step": 214 }, { "epoch": 0.21, "learning_rate": 1.9707958882345693e-05, "loss": 0.5054, "step": 215 }, { "epoch": 0.21, "learning_rate": 1.970414787303119e-05, "loss": 0.529, "step": 216 }, { "epoch": 0.21, "learning_rate": 1.9700312531945444e-05, "loss": 0.5133, "step": 217 }, { "epoch": 0.21, "learning_rate": 1.9696452868705026e-05, "loss": 0.4866, "step": 218 }, { "epoch": 0.21, "learning_rate": 1.9692568892987494e-05, "loss": 0.4853, "step": 219 }, { "epoch": 0.21, "learning_rate": 1.968866061453137e-05, "loss": 0.5206, "step": 220 }, { "epoch": 0.22, "learning_rate": 1.9684728043136093e-05, "loss": 0.5141, "step": 221 }, { "epoch": 0.22, "learning_rate": 1.9680771188662044e-05, "loss": 0.4991, "step": 222 }, { "epoch": 0.22, "learning_rate": 1.9676790061030466e-05, "loss": 0.5194, "step": 223 }, { "epoch": 0.22, "learning_rate": 1.9672784670223465e-05, "loss": 0.4866, "step": 224 }, { "epoch": 0.22, "learning_rate": 1.9668755026283995e-05, "loss": 0.4937, "step": 225 }, { "epoch": 0.22, "learning_rate": 1.966470113931582e-05, "loss": 0.5248, "step": 226 }, { "epoch": 0.22, "learning_rate": 1.966062301948347e-05, "loss": 0.508, "step": 227 }, { "epoch": 0.22, "learning_rate": 1.9656520677012264e-05, "loss": 0.5231, "step": 228 }, { "epoch": 0.22, "learning_rate": 1.9652394122188242e-05, "loss": 0.4906, "step": 229 }, { "epoch": 0.22, "learning_rate": 1.9648243365358145e-05, "loss": 0.4693, "step": 230 }, { "epoch": 0.23, "learning_rate": 1.9644068416929417e-05, "loss": 0.5033, "step": 231 }, { "epoch": 0.23, "learning_rate": 1.963986928737014e-05, "loss": 0.4746, "step": 232 }, { "epoch": 0.23, "learning_rate": 1.963564598720903e-05, "loss": 0.5282, "step": 233 }, { "epoch": 0.23, "learning_rate": 1.9631398527035424e-05, "loss": 0.4799, "step": 234 }, { "epoch": 0.23, "learning_rate": 1.962712691749922e-05, "loss": 0.4588, "step": 235 }, { "epoch": 0.23, "learning_rate": 1.9622831169310864e-05, "loss": 0.468, "step": 236 }, { "epoch": 0.23, "learning_rate": 1.961851129324134e-05, "loss": 0.5684, "step": 237 }, { "epoch": 0.23, "learning_rate": 1.9614167300122126e-05, "loss": 0.5175, "step": 238 }, { "epoch": 0.23, "learning_rate": 1.9609799200845163e-05, "loss": 0.499, "step": 239 }, { "epoch": 0.23, "learning_rate": 1.9605407006362843e-05, "loss": 0.4789, "step": 240 }, { "epoch": 0.24, "learning_rate": 1.9600990727687964e-05, "loss": 0.4925, "step": 241 }, { "epoch": 0.24, "learning_rate": 1.9596550375893718e-05, "loss": 0.5082, "step": 242 }, { "epoch": 0.24, "learning_rate": 1.959208596211366e-05, "loss": 0.4733, "step": 243 }, { "epoch": 0.24, "learning_rate": 1.958759749754167e-05, "loss": 0.5066, "step": 244 }, { "epoch": 0.24, "learning_rate": 1.9583084993431935e-05, "loss": 0.4839, "step": 245 }, { "epoch": 0.24, "learning_rate": 1.9578548461098912e-05, "loss": 0.4864, "step": 246 }, { "epoch": 0.24, "learning_rate": 1.9573987911917325e-05, "loss": 0.4951, "step": 247 }, { "epoch": 0.24, "learning_rate": 1.956940335732209e-05, "loss": 0.5186, "step": 248 }, { "epoch": 0.24, "learning_rate": 1.956479480880833e-05, "loss": 0.4811, "step": 249 }, { "epoch": 0.24, "learning_rate": 1.9560162277931326e-05, "loss": 0.4886, "step": 250 }, { "epoch": 0.25, "learning_rate": 1.9555505776306492e-05, "loss": 0.4864, "step": 251 }, { "epoch": 0.25, "learning_rate": 1.955082531560934e-05, "loss": 0.4696, "step": 252 }, { "epoch": 0.25, "learning_rate": 1.954612090757546e-05, "loss": 0.4639, "step": 253 }, { "epoch": 0.25, "learning_rate": 1.954139256400049e-05, "loss": 0.4629, "step": 254 }, { "epoch": 0.25, "learning_rate": 1.9536640296740078e-05, "loss": 0.4856, "step": 255 }, { "epoch": 0.25, "learning_rate": 1.9531864117709855e-05, "loss": 0.5, "step": 256 }, { "epoch": 0.25, "learning_rate": 1.952706403888542e-05, "loss": 0.5017, "step": 257 }, { "epoch": 0.25, "learning_rate": 1.9522240072302275e-05, "loss": 0.4967, "step": 258 }, { "epoch": 0.25, "learning_rate": 1.951739223005584e-05, "loss": 0.4838, "step": 259 }, { "epoch": 0.25, "learning_rate": 1.9512520524301388e-05, "loss": 0.5261, "step": 260 }, { "epoch": 0.25, "learning_rate": 1.950762496725403e-05, "loss": 0.4957, "step": 261 }, { "epoch": 0.26, "learning_rate": 1.9502705571188675e-05, "loss": 0.4763, "step": 262 }, { "epoch": 0.26, "learning_rate": 1.949776234844001e-05, "loss": 0.4788, "step": 263 }, { "epoch": 0.26, "learning_rate": 1.949279531140247e-05, "loss": 0.4691, "step": 264 }, { "epoch": 0.26, "learning_rate": 1.948780447253019e-05, "loss": 0.4703, "step": 265 }, { "epoch": 0.26, "learning_rate": 1.948278984433699e-05, "loss": 0.4738, "step": 266 }, { "epoch": 0.26, "learning_rate": 1.947775143939633e-05, "loss": 0.5067, "step": 267 }, { "epoch": 0.26, "learning_rate": 1.9472689270341303e-05, "loss": 0.4723, "step": 268 }, { "epoch": 0.26, "learning_rate": 1.946760334986458e-05, "loss": 0.4718, "step": 269 }, { "epoch": 0.26, "learning_rate": 1.9462493690718373e-05, "loss": 0.4786, "step": 270 }, { "epoch": 0.26, "learning_rate": 1.945736030571443e-05, "loss": 0.5425, "step": 271 }, { "epoch": 0.27, "learning_rate": 1.945220320772399e-05, "loss": 0.4705, "step": 272 }, { "epoch": 0.27, "learning_rate": 1.9447022409677736e-05, "loss": 0.4648, "step": 273 }, { "epoch": 0.27, "learning_rate": 1.9441817924565787e-05, "loss": 0.4775, "step": 274 }, { "epoch": 0.27, "learning_rate": 1.9436589765437646e-05, "loss": 0.4865, "step": 275 }, { "epoch": 0.27, "learning_rate": 1.9431337945402186e-05, "loss": 0.4973, "step": 276 }, { "epoch": 0.27, "learning_rate": 1.942606247762759e-05, "loss": 0.4896, "step": 277 }, { "epoch": 0.27, "learning_rate": 1.942076337534135e-05, "loss": 0.4617, "step": 278 }, { "epoch": 0.27, "learning_rate": 1.941544065183021e-05, "loss": 0.4651, "step": 279 }, { "epoch": 0.27, "learning_rate": 1.941009432044014e-05, "loss": 0.5159, "step": 280 }, { "epoch": 0.27, "learning_rate": 1.9404724394576305e-05, "loss": 0.4467, "step": 281 }, { "epoch": 0.28, "learning_rate": 1.9399330887703035e-05, "loss": 0.4559, "step": 282 }, { "epoch": 0.28, "learning_rate": 1.9393913813343784e-05, "loss": 0.5078, "step": 283 }, { "epoch": 0.28, "learning_rate": 1.938847318508109e-05, "loss": 0.4779, "step": 284 }, { "epoch": 0.28, "learning_rate": 1.9383009016556555e-05, "loss": 0.4724, "step": 285 }, { "epoch": 0.28, "learning_rate": 1.9377521321470806e-05, "loss": 0.4806, "step": 286 }, { "epoch": 0.28, "learning_rate": 1.937201011358346e-05, "loss": 0.4644, "step": 287 }, { "epoch": 0.28, "learning_rate": 1.9366475406713085e-05, "loss": 0.4417, "step": 288 }, { "epoch": 0.28, "learning_rate": 1.9360917214737177e-05, "loss": 0.4647, "step": 289 }, { "epoch": 0.28, "learning_rate": 1.9355335551592104e-05, "loss": 0.4803, "step": 290 }, { "epoch": 0.28, "learning_rate": 1.93497304312731e-05, "loss": 0.4619, "step": 291 }, { "epoch": 0.29, "learning_rate": 1.9344101867834202e-05, "loss": 0.484, "step": 292 }, { "epoch": 0.29, "learning_rate": 1.9338449875388234e-05, "loss": 0.4949, "step": 293 }, { "epoch": 0.29, "learning_rate": 1.933277446810677e-05, "loss": 0.5335, "step": 294 }, { "epoch": 0.29, "learning_rate": 1.9327075660220076e-05, "loss": 0.4737, "step": 295 }, { "epoch": 0.29, "learning_rate": 1.932135346601711e-05, "loss": 0.49, "step": 296 }, { "epoch": 0.29, "learning_rate": 1.931560789984546e-05, "loss": 0.5163, "step": 297 }, { "epoch": 0.29, "learning_rate": 1.9309838976111312e-05, "loss": 0.4582, "step": 298 }, { "epoch": 0.29, "learning_rate": 1.9304046709279426e-05, "loss": 0.4992, "step": 299 }, { "epoch": 0.29, "learning_rate": 1.9298231113873086e-05, "loss": 0.4695, "step": 300 }, { "epoch": 0.29, "learning_rate": 1.9292392204474075e-05, "loss": 0.4657, "step": 301 }, { "epoch": 0.3, "learning_rate": 1.9286529995722624e-05, "loss": 0.4851, "step": 302 }, { "epoch": 0.3, "learning_rate": 1.928064450231739e-05, "loss": 0.4681, "step": 303 }, { "epoch": 0.3, "learning_rate": 1.9274735739015405e-05, "loss": 0.4617, "step": 304 }, { "epoch": 0.3, "learning_rate": 1.926880372063206e-05, "loss": 0.4372, "step": 305 }, { "epoch": 0.3, "learning_rate": 1.9262848462041046e-05, "loss": 0.4674, "step": 306 }, { "epoch": 0.3, "learning_rate": 1.9256869978174326e-05, "loss": 0.4967, "step": 307 }, { "epoch": 0.3, "learning_rate": 1.9250868284022102e-05, "loss": 0.4762, "step": 308 }, { "epoch": 0.3, "learning_rate": 1.9244843394632765e-05, "loss": 0.4591, "step": 309 }, { "epoch": 0.3, "learning_rate": 1.9238795325112867e-05, "loss": 0.4422, "step": 310 }, { "epoch": 0.3, "learning_rate": 1.923272409062709e-05, "loss": 0.4955, "step": 311 }, { "epoch": 0.3, "learning_rate": 1.9226629706398186e-05, "loss": 0.5336, "step": 312 }, { "epoch": 0.31, "learning_rate": 1.9220512187706956e-05, "loss": 0.4836, "step": 313 }, { "epoch": 0.31, "learning_rate": 1.921437154989221e-05, "loss": 0.4452, "step": 314 }, { "epoch": 0.31, "learning_rate": 1.9208207808350727e-05, "loss": 0.5073, "step": 315 }, { "epoch": 0.31, "learning_rate": 1.920202097853721e-05, "loss": 0.5123, "step": 316 }, { "epoch": 0.31, "learning_rate": 1.9195811075964253e-05, "loss": 0.4532, "step": 317 }, { "epoch": 0.31, "learning_rate": 1.918957811620231e-05, "loss": 0.4545, "step": 318 }, { "epoch": 0.31, "learning_rate": 1.9183322114879633e-05, "loss": 0.4396, "step": 319 }, { "epoch": 0.31, "learning_rate": 1.9177043087682266e-05, "loss": 0.4577, "step": 320 }, { "epoch": 0.31, "learning_rate": 1.917074105035397e-05, "loss": 0.437, "step": 321 }, { "epoch": 0.31, "learning_rate": 1.916441601869621e-05, "loss": 0.4566, "step": 322 }, { "epoch": 0.32, "learning_rate": 1.9158068008568102e-05, "loss": 0.4876, "step": 323 }, { "epoch": 0.32, "learning_rate": 1.9151697035886384e-05, "loss": 0.4698, "step": 324 }, { "epoch": 0.32, "learning_rate": 1.9145303116625357e-05, "loss": 0.4623, "step": 325 }, { "epoch": 0.32, "learning_rate": 1.9138886266816868e-05, "loss": 0.4936, "step": 326 }, { "epoch": 0.32, "learning_rate": 1.9132446502550257e-05, "loss": 0.4579, "step": 327 }, { "epoch": 0.32, "learning_rate": 1.9125983839972317e-05, "loss": 0.4773, "step": 328 }, { "epoch": 0.32, "learning_rate": 1.9119498295287256e-05, "loss": 0.4882, "step": 329 }, { "epoch": 0.32, "learning_rate": 1.9112989884756655e-05, "loss": 0.4822, "step": 330 }, { "epoch": 0.32, "learning_rate": 1.9106458624699425e-05, "loss": 0.4653, "step": 331 }, { "epoch": 0.32, "learning_rate": 1.9099904531491776e-05, "loss": 0.4639, "step": 332 }, { "epoch": 0.33, "learning_rate": 1.9093327621567162e-05, "loss": 0.492, "step": 333 }, { "epoch": 0.33, "learning_rate": 1.908672791141625e-05, "loss": 0.5084, "step": 334 }, { "epoch": 0.33, "learning_rate": 1.9080105417586878e-05, "loss": 0.445, "step": 335 }, { "epoch": 0.33, "learning_rate": 1.907346015668401e-05, "loss": 0.4803, "step": 336 }, { "epoch": 0.33, "learning_rate": 1.9066792145369685e-05, "loss": 0.464, "step": 337 }, { "epoch": 0.33, "learning_rate": 1.9060101400362998e-05, "loss": 0.4684, "step": 338 }, { "epoch": 0.33, "learning_rate": 1.905338793844004e-05, "loss": 0.475, "step": 339 }, { "epoch": 0.33, "learning_rate": 1.9046651776433863e-05, "loss": 0.5054, "step": 340 }, { "epoch": 0.33, "learning_rate": 1.9039892931234434e-05, "loss": 0.4836, "step": 341 }, { "epoch": 0.33, "learning_rate": 1.90331114197886e-05, "loss": 0.4874, "step": 342 }, { "epoch": 0.34, "learning_rate": 1.9026307259100037e-05, "loss": 0.5096, "step": 343 }, { "epoch": 0.34, "learning_rate": 1.9019480466229203e-05, "loss": 0.4955, "step": 344 }, { "epoch": 0.34, "learning_rate": 1.9012631058293322e-05, "loss": 0.4578, "step": 345 }, { "epoch": 0.34, "learning_rate": 1.9005759052466303e-05, "loss": 0.4322, "step": 346 }, { "epoch": 0.34, "learning_rate": 1.899886446597872e-05, "loss": 0.4398, "step": 347 }, { "epoch": 0.34, "learning_rate": 1.899194731611778e-05, "loss": 0.4074, "step": 348 }, { "epoch": 0.34, "learning_rate": 1.8985007620227246e-05, "loss": 0.4615, "step": 349 }, { "epoch": 0.34, "learning_rate": 1.897804539570742e-05, "loss": 0.4656, "step": 350 }, { "epoch": 0.34, "learning_rate": 1.897106066001509e-05, "loss": 0.455, "step": 351 }, { "epoch": 0.34, "learning_rate": 1.8964053430663485e-05, "loss": 0.4644, "step": 352 }, { "epoch": 0.34, "learning_rate": 1.8957023725222238e-05, "loss": 0.438, "step": 353 }, { "epoch": 0.35, "learning_rate": 1.894997156131734e-05, "loss": 0.45, "step": 354 }, { "epoch": 0.35, "learning_rate": 1.894289695663109e-05, "loss": 0.4728, "step": 355 }, { "epoch": 0.35, "learning_rate": 1.8935799928902046e-05, "loss": 0.4339, "step": 356 }, { "epoch": 0.35, "learning_rate": 1.8928680495925e-05, "loss": 0.4525, "step": 357 }, { "epoch": 0.35, "learning_rate": 1.8921538675550923e-05, "loss": 0.4317, "step": 358 }, { "epoch": 0.35, "learning_rate": 1.8914374485686905e-05, "loss": 0.4735, "step": 359 }, { "epoch": 0.35, "learning_rate": 1.890718794429614e-05, "loss": 0.4247, "step": 360 }, { "epoch": 0.35, "learning_rate": 1.8899979069397858e-05, "loss": 0.4906, "step": 361 }, { "epoch": 0.35, "learning_rate": 1.8892747879067284e-05, "loss": 0.4523, "step": 362 }, { "epoch": 0.35, "learning_rate": 1.8885494391435607e-05, "loss": 0.4869, "step": 363 }, { "epoch": 0.36, "learning_rate": 1.8878218624689913e-05, "loss": 0.4435, "step": 364 }, { "epoch": 0.36, "learning_rate": 1.887092059707315e-05, "loss": 0.4661, "step": 365 }, { "epoch": 0.36, "learning_rate": 1.8863600326884085e-05, "loss": 0.4109, "step": 366 }, { "epoch": 0.36, "learning_rate": 1.8856257832477255e-05, "loss": 0.4528, "step": 367 }, { "epoch": 0.36, "learning_rate": 1.8848893132262927e-05, "loss": 0.4528, "step": 368 }, { "epoch": 0.36, "learning_rate": 1.884150624470703e-05, "loss": 0.4409, "step": 369 }, { "epoch": 0.36, "learning_rate": 1.8834097188331143e-05, "loss": 0.4557, "step": 370 }, { "epoch": 0.36, "learning_rate": 1.882666598171242e-05, "loss": 0.4378, "step": 371 }, { "epoch": 0.36, "learning_rate": 1.881921264348355e-05, "loss": 0.4485, "step": 372 }, { "epoch": 0.36, "learning_rate": 1.8811737192332725e-05, "loss": 0.4859, "step": 373 }, { "epoch": 0.37, "learning_rate": 1.8804239647003574e-05, "loss": 0.4281, "step": 374 }, { "epoch": 0.37, "learning_rate": 1.8796720026295122e-05, "loss": 0.445, "step": 375 }, { "epoch": 0.37, "learning_rate": 1.8789178349061755e-05, "loss": 0.4423, "step": 376 }, { "epoch": 0.37, "learning_rate": 1.8781614634213153e-05, "loss": 0.4452, "step": 377 }, { "epoch": 0.37, "learning_rate": 1.8774028900714257e-05, "loss": 0.4384, "step": 378 }, { "epoch": 0.37, "learning_rate": 1.8766421167585216e-05, "loss": 0.4517, "step": 379 }, { "epoch": 0.37, "learning_rate": 1.8758791453901337e-05, "loss": 0.4763, "step": 380 }, { "epoch": 0.37, "learning_rate": 1.8751139778793043e-05, "loss": 0.4785, "step": 381 }, { "epoch": 0.37, "learning_rate": 1.8743466161445823e-05, "loss": 0.434, "step": 382 }, { "epoch": 0.37, "learning_rate": 1.8735770621100182e-05, "loss": 0.4567, "step": 383 }, { "epoch": 0.38, "learning_rate": 1.872805317705159e-05, "loss": 0.4638, "step": 384 }, { "epoch": 0.38, "learning_rate": 1.8720313848650448e-05, "loss": 0.4225, "step": 385 }, { "epoch": 0.38, "learning_rate": 1.871255265530201e-05, "loss": 0.4374, "step": 386 }, { "epoch": 0.38, "learning_rate": 1.8704769616466377e-05, "loss": 0.4704, "step": 387 }, { "epoch": 0.38, "learning_rate": 1.8696964751658405e-05, "loss": 0.4532, "step": 388 }, { "epoch": 0.38, "learning_rate": 1.8689138080447687e-05, "loss": 0.4368, "step": 389 }, { "epoch": 0.38, "learning_rate": 1.8681289622458485e-05, "loss": 0.4526, "step": 390 }, { "epoch": 0.38, "learning_rate": 1.8673419397369693e-05, "loss": 0.4145, "step": 391 }, { "epoch": 0.38, "learning_rate": 1.8665527424914786e-05, "loss": 0.4485, "step": 392 }, { "epoch": 0.38, "learning_rate": 1.8657613724881755e-05, "loss": 0.4693, "step": 393 }, { "epoch": 0.38, "learning_rate": 1.8649678317113084e-05, "loss": 0.405, "step": 394 }, { "epoch": 0.39, "learning_rate": 1.8641721221505674e-05, "loss": 0.4416, "step": 395 }, { "epoch": 0.39, "learning_rate": 1.863374245801082e-05, "loss": 0.4233, "step": 396 }, { "epoch": 0.39, "learning_rate": 1.862574204663413e-05, "loss": 0.4021, "step": 397 }, { "epoch": 0.39, "learning_rate": 1.8617720007435497e-05, "loss": 0.4341, "step": 398 }, { "epoch": 0.39, "learning_rate": 1.860967636052905e-05, "loss": 0.4717, "step": 399 }, { "epoch": 0.39, "learning_rate": 1.860161112608309e-05, "loss": 0.4203, "step": 400 }, { "epoch": 0.39, "learning_rate": 1.8593524324320035e-05, "loss": 0.4429, "step": 401 }, { "epoch": 0.39, "learning_rate": 1.8585415975516405e-05, "loss": 0.4422, "step": 402 }, { "epoch": 0.39, "learning_rate": 1.8577286100002723e-05, "loss": 0.4332, "step": 403 }, { "epoch": 0.39, "learning_rate": 1.8569134718163496e-05, "loss": 0.4534, "step": 404 }, { "epoch": 0.4, "learning_rate": 1.8560961850437163e-05, "loss": 0.4554, "step": 405 }, { "epoch": 0.4, "learning_rate": 1.855276751731602e-05, "loss": 0.4418, "step": 406 }, { "epoch": 0.4, "learning_rate": 1.85445517393462e-05, "loss": 0.4297, "step": 407 }, { "epoch": 0.4, "learning_rate": 1.8536314537127586e-05, "loss": 0.4138, "step": 408 }, { "epoch": 0.4, "learning_rate": 1.8528055931313803e-05, "loss": 0.4057, "step": 409 }, { "epoch": 0.4, "learning_rate": 1.8519775942612128e-05, "loss": 0.4211, "step": 410 }, { "epoch": 0.4, "learning_rate": 1.8511474591783454e-05, "loss": 0.4344, "step": 411 }, { "epoch": 0.4, "learning_rate": 1.8503151899642237e-05, "loss": 0.4245, "step": 412 }, { "epoch": 0.4, "learning_rate": 1.849480788705645e-05, "loss": 0.3849, "step": 413 }, { "epoch": 0.4, "learning_rate": 1.848644257494751e-05, "loss": 0.4424, "step": 414 }, { "epoch": 0.41, "learning_rate": 1.8478055984290258e-05, "loss": 0.4281, "step": 415 }, { "epoch": 0.41, "learning_rate": 1.8469648136112867e-05, "loss": 0.3952, "step": 416 }, { "epoch": 0.41, "learning_rate": 1.846121905149683e-05, "loss": 0.4211, "step": 417 }, { "epoch": 0.41, "learning_rate": 1.845276875157687e-05, "loss": 0.4508, "step": 418 }, { "epoch": 0.41, "learning_rate": 1.844429725754092e-05, "loss": 0.3808, "step": 419 }, { "epoch": 0.41, "learning_rate": 1.8435804590630045e-05, "loss": 0.4243, "step": 420 }, { "epoch": 0.41, "learning_rate": 1.8427290772138397e-05, "loss": 0.4031, "step": 421 }, { "epoch": 0.41, "learning_rate": 1.841875582341317e-05, "loss": 0.4114, "step": 422 }, { "epoch": 0.41, "learning_rate": 1.8410199765854532e-05, "loss": 0.3893, "step": 423 }, { "epoch": 0.41, "learning_rate": 1.840162262091558e-05, "loss": 0.443, "step": 424 }, { "epoch": 0.42, "learning_rate": 1.839302441010229e-05, "loss": 0.4253, "step": 425 }, { "epoch": 0.42, "learning_rate": 1.838440515497345e-05, "loss": 0.4145, "step": 426 }, { "epoch": 0.42, "learning_rate": 1.8375764877140617e-05, "loss": 0.42, "step": 427 }, { "epoch": 0.42, "learning_rate": 1.836710359826806e-05, "loss": 0.3958, "step": 428 }, { "epoch": 0.42, "learning_rate": 1.8358421340072704e-05, "loss": 0.4109, "step": 429 }, { "epoch": 0.42, "learning_rate": 1.8349718124324075e-05, "loss": 0.4446, "step": 430 }, { "epoch": 0.42, "learning_rate": 1.8340993972844252e-05, "loss": 0.4563, "step": 431 }, { "epoch": 0.42, "learning_rate": 1.8332248907507808e-05, "loss": 0.4029, "step": 432 }, { "epoch": 0.42, "learning_rate": 1.8323482950241743e-05, "loss": 0.4165, "step": 433 }, { "epoch": 0.42, "learning_rate": 1.8314696123025456e-05, "loss": 0.4268, "step": 434 }, { "epoch": 0.42, "learning_rate": 1.830588844789066e-05, "loss": 0.4338, "step": 435 }, { "epoch": 0.43, "learning_rate": 1.8297059946921357e-05, "loss": 0.4392, "step": 436 }, { "epoch": 0.43, "learning_rate": 1.828821064225375e-05, "loss": 0.4559, "step": 437 }, { "epoch": 0.43, "learning_rate": 1.8279340556076218e-05, "loss": 0.4377, "step": 438 }, { "epoch": 0.43, "learning_rate": 1.8270449710629236e-05, "loss": 0.4159, "step": 439 }, { "epoch": 0.43, "learning_rate": 1.8261538128205337e-05, "loss": 0.4227, "step": 440 }, { "epoch": 0.43, "learning_rate": 1.8252605831149052e-05, "loss": 0.45, "step": 441 }, { "epoch": 0.43, "learning_rate": 1.8243652841856842e-05, "loss": 0.4306, "step": 442 }, { "epoch": 0.43, "learning_rate": 1.8234679182777055e-05, "loss": 0.4387, "step": 443 }, { "epoch": 0.43, "learning_rate": 1.8225684876409863e-05, "loss": 0.4006, "step": 444 }, { "epoch": 0.43, "learning_rate": 1.8216669945307214e-05, "loss": 0.3614, "step": 445 }, { "epoch": 0.44, "learning_rate": 1.8207634412072765e-05, "loss": 0.443, "step": 446 }, { "epoch": 0.44, "learning_rate": 1.8198578299361832e-05, "loss": 0.4341, "step": 447 }, { "epoch": 0.44, "learning_rate": 1.818950162988133e-05, "loss": 0.4205, "step": 448 }, { "epoch": 0.44, "learning_rate": 1.818040442638971e-05, "loss": 0.4034, "step": 449 }, { "epoch": 0.44, "learning_rate": 1.8171286711696935e-05, "loss": 0.4184, "step": 450 }, { "epoch": 0.44, "learning_rate": 1.816214850866436e-05, "loss": 0.3959, "step": 451 }, { "epoch": 0.44, "learning_rate": 1.8152989840204734e-05, "loss": 0.4073, "step": 452 }, { "epoch": 0.44, "learning_rate": 1.8143810729282125e-05, "loss": 0.4084, "step": 453 }, { "epoch": 0.44, "learning_rate": 1.813461119891184e-05, "loss": 0.4378, "step": 454 }, { "epoch": 0.44, "learning_rate": 1.8125391272160397e-05, "loss": 0.4132, "step": 455 }, { "epoch": 0.45, "learning_rate": 1.811615097214545e-05, "loss": 0.4377, "step": 456 }, { "epoch": 0.45, "learning_rate": 1.8106890322035737e-05, "loss": 0.4223, "step": 457 }, { "epoch": 0.45, "learning_rate": 1.8097609345051027e-05, "loss": 0.4512, "step": 458 }, { "epoch": 0.45, "learning_rate": 1.8088308064462043e-05, "loss": 0.4255, "step": 459 }, { "epoch": 0.45, "learning_rate": 1.807898650359043e-05, "loss": 0.4058, "step": 460 }, { "epoch": 0.45, "learning_rate": 1.8069644685808673e-05, "loss": 0.3845, "step": 461 }, { "epoch": 0.45, "learning_rate": 1.8060282634540053e-05, "loss": 0.4468, "step": 462 }, { "epoch": 0.45, "learning_rate": 1.805090037325858e-05, "loss": 0.4255, "step": 463 }, { "epoch": 0.45, "learning_rate": 1.804149792548895e-05, "loss": 0.4363, "step": 464 }, { "epoch": 0.45, "learning_rate": 1.803207531480645e-05, "loss": 0.4256, "step": 465 }, { "epoch": 0.46, "learning_rate": 1.8022632564836948e-05, "loss": 0.4118, "step": 466 }, { "epoch": 0.46, "learning_rate": 1.801316969925679e-05, "loss": 0.4207, "step": 467 }, { "epoch": 0.46, "learning_rate": 1.8003686741792773e-05, "loss": 0.3921, "step": 468 }, { "epoch": 0.46, "learning_rate": 1.799418371622206e-05, "loss": 0.4257, "step": 469 }, { "epoch": 0.46, "learning_rate": 1.7984660646372138e-05, "loss": 0.4075, "step": 470 }, { "epoch": 0.46, "learning_rate": 1.797511755612075e-05, "loss": 0.3811, "step": 471 }, { "epoch": 0.46, "learning_rate": 1.7965554469395837e-05, "loss": 0.4024, "step": 472 }, { "epoch": 0.46, "learning_rate": 1.7955971410175484e-05, "loss": 0.4315, "step": 473 }, { "epoch": 0.46, "learning_rate": 1.7946368402487845e-05, "loss": 0.3929, "step": 474 }, { "epoch": 0.46, "learning_rate": 1.79367454704111e-05, "loss": 0.3879, "step": 475 }, { "epoch": 0.47, "learning_rate": 1.7927102638073384e-05, "loss": 0.4073, "step": 476 }, { "epoch": 0.47, "learning_rate": 1.7917439929652723e-05, "loss": 0.4559, "step": 477 }, { "epoch": 0.47, "learning_rate": 1.7907757369376984e-05, "loss": 0.4298, "step": 478 }, { "epoch": 0.47, "learning_rate": 1.789805498152382e-05, "loss": 0.3755, "step": 479 }, { "epoch": 0.47, "learning_rate": 1.7888332790420582e-05, "loss": 0.4494, "step": 480 }, { "epoch": 0.47, "learning_rate": 1.7878590820444283e-05, "loss": 0.4108, "step": 481 }, { "epoch": 0.47, "learning_rate": 1.786882909602153e-05, "loss": 0.4367, "step": 482 }, { "epoch": 0.47, "learning_rate": 1.7859047641628452e-05, "loss": 0.3866, "step": 483 }, { "epoch": 0.47, "learning_rate": 1.7849246481790664e-05, "loss": 0.3998, "step": 484 }, { "epoch": 0.47, "learning_rate": 1.783942564108318e-05, "loss": 0.4318, "step": 485 }, { "epoch": 0.47, "learning_rate": 1.7829585144130356e-05, "loss": 0.4111, "step": 486 }, { "epoch": 0.48, "learning_rate": 1.7819725015605843e-05, "loss": 0.3706, "step": 487 }, { "epoch": 0.48, "learning_rate": 1.7809845280232512e-05, "loss": 0.452, "step": 488 }, { "epoch": 0.48, "learning_rate": 1.7799945962782397e-05, "loss": 0.3923, "step": 489 }, { "epoch": 0.48, "learning_rate": 1.779002708807662e-05, "loss": 0.4125, "step": 490 }, { "epoch": 0.48, "learning_rate": 1.7780088680985365e-05, "loss": 0.3747, "step": 491 }, { "epoch": 0.48, "learning_rate": 1.777013076642776e-05, "loss": 0.3989, "step": 492 }, { "epoch": 0.48, "learning_rate": 1.776015336937187e-05, "loss": 0.4282, "step": 493 }, { "epoch": 0.48, "learning_rate": 1.775015651483459e-05, "loss": 0.405, "step": 494 }, { "epoch": 0.48, "learning_rate": 1.774014022788162e-05, "loss": 0.4097, "step": 495 }, { "epoch": 0.48, "learning_rate": 1.773010453362737e-05, "loss": 0.4025, "step": 496 }, { "epoch": 0.49, "learning_rate": 1.772004945723492e-05, "loss": 0.3915, "step": 497 }, { "epoch": 0.49, "learning_rate": 1.7709975023915948e-05, "loss": 0.3835, "step": 498 }, { "epoch": 0.49, "learning_rate": 1.7699881258930658e-05, "loss": 0.3871, "step": 499 }, { "epoch": 0.49, "learning_rate": 1.7689768187587732e-05, "loss": 0.4001, "step": 500 }, { "epoch": 0.49, "learning_rate": 1.7679635835244256e-05, "loss": 0.3755, "step": 501 }, { "epoch": 0.49, "learning_rate": 1.766948422730567e-05, "loss": 0.3873, "step": 502 }, { "epoch": 0.49, "learning_rate": 1.765931338922568e-05, "loss": 0.4069, "step": 503 }, { "epoch": 0.49, "learning_rate": 1.7649123346506223e-05, "loss": 0.4029, "step": 504 }, { "epoch": 0.49, "learning_rate": 1.763891412469738e-05, "loss": 0.4251, "step": 505 }, { "epoch": 0.49, "learning_rate": 1.762868574939732e-05, "loss": 0.4217, "step": 506 }, { "epoch": 0.5, "learning_rate": 1.761843824625225e-05, "loss": 0.4181, "step": 507 }, { "epoch": 0.5, "learning_rate": 1.7608171640956312e-05, "loss": 0.4037, "step": 508 }, { "epoch": 0.5, "learning_rate": 1.7597885959251574e-05, "loss": 0.4204, "step": 509 }, { "epoch": 0.5, "learning_rate": 1.758758122692791e-05, "loss": 0.3817, "step": 510 }, { "epoch": 0.5, "learning_rate": 1.7577257469822976e-05, "loss": 0.3902, "step": 511 }, { "epoch": 0.5, "learning_rate": 1.756691471382213e-05, "loss": 0.3967, "step": 512 }, { "epoch": 0.5, "learning_rate": 1.7556552984858353e-05, "loss": 0.3403, "step": 513 }, { "epoch": 0.5, "learning_rate": 1.7546172308912213e-05, "loss": 0.39, "step": 514 }, { "epoch": 0.5, "learning_rate": 1.7535772712011775e-05, "loss": 0.4309, "step": 515 }, { "epoch": 0.5, "learning_rate": 1.7525354220232558e-05, "loss": 0.4088, "step": 516 }, { "epoch": 0.51, "learning_rate": 1.7514916859697443e-05, "loss": 0.3714, "step": 517 }, { "epoch": 0.51, "learning_rate": 1.750446065657663e-05, "loss": 0.4077, "step": 518 }, { "epoch": 0.51, "learning_rate": 1.7493985637087555e-05, "loss": 0.4305, "step": 519 }, { "epoch": 0.51, "learning_rate": 1.7483491827494846e-05, "loss": 0.3955, "step": 520 }, { "epoch": 0.51, "learning_rate": 1.747297925411024e-05, "loss": 0.3929, "step": 521 }, { "epoch": 0.51, "learning_rate": 1.7462447943292522e-05, "loss": 0.4226, "step": 522 }, { "epoch": 0.51, "learning_rate": 1.7451897921447448e-05, "loss": 0.4106, "step": 523 }, { "epoch": 0.51, "learning_rate": 1.7441329215027707e-05, "loss": 0.4095, "step": 524 }, { "epoch": 0.51, "learning_rate": 1.7430741850532824e-05, "loss": 0.3962, "step": 525 }, { "epoch": 0.51, "learning_rate": 1.742013585450911e-05, "loss": 0.4525, "step": 526 }, { "epoch": 0.51, "learning_rate": 1.7409511253549592e-05, "loss": 0.4398, "step": 527 }, { "epoch": 0.52, "learning_rate": 1.7398868074293947e-05, "loss": 0.4022, "step": 528 }, { "epoch": 0.52, "learning_rate": 1.7388206343428438e-05, "loss": 0.3816, "step": 529 }, { "epoch": 0.52, "learning_rate": 1.7377526087685832e-05, "loss": 0.3999, "step": 530 }, { "epoch": 0.52, "learning_rate": 1.736682733384536e-05, "loss": 0.4143, "step": 531 }, { "epoch": 0.52, "learning_rate": 1.735611010873262e-05, "loss": 0.386, "step": 532 }, { "epoch": 0.52, "learning_rate": 1.734537443921953e-05, "loss": 0.4008, "step": 533 }, { "epoch": 0.52, "learning_rate": 1.733462035222426e-05, "loss": 0.4143, "step": 534 }, { "epoch": 0.52, "learning_rate": 1.7323847874711152e-05, "loss": 0.3649, "step": 535 }, { "epoch": 0.52, "learning_rate": 1.7313057033690662e-05, "loss": 0.3702, "step": 536 }, { "epoch": 0.52, "learning_rate": 1.730224785621929e-05, "loss": 0.3431, "step": 537 }, { "epoch": 0.53, "learning_rate": 1.729142036939951e-05, "loss": 0.3756, "step": 538 }, { "epoch": 0.53, "learning_rate": 1.728057460037971e-05, "loss": 0.3912, "step": 539 }, { "epoch": 0.53, "learning_rate": 1.7269710576354112e-05, "loss": 0.3778, "step": 540 }, { "epoch": 0.53, "learning_rate": 1.7258828324562705e-05, "loss": 0.4261, "step": 541 }, { "epoch": 0.53, "learning_rate": 1.72479278722912e-05, "loss": 0.3866, "step": 542 }, { "epoch": 0.53, "learning_rate": 1.723700924687093e-05, "loss": 0.3947, "step": 543 }, { "epoch": 0.53, "learning_rate": 1.7226072475678783e-05, "loss": 0.4084, "step": 544 }, { "epoch": 0.53, "learning_rate": 1.7215117586137174e-05, "loss": 0.3903, "step": 545 }, { "epoch": 0.53, "learning_rate": 1.7204144605713922e-05, "loss": 0.4124, "step": 546 }, { "epoch": 0.53, "learning_rate": 1.7193153561922214e-05, "loss": 0.3677, "step": 547 }, { "epoch": 0.54, "learning_rate": 1.718214448232054e-05, "loss": 0.3901, "step": 548 }, { "epoch": 0.54, "learning_rate": 1.7171117394512594e-05, "loss": 0.4179, "step": 549 }, { "epoch": 0.54, "learning_rate": 1.716007232614723e-05, "loss": 0.3661, "step": 550 }, { "epoch": 0.54, "learning_rate": 1.7149009304918392e-05, "loss": 0.3973, "step": 551 }, { "epoch": 0.54, "learning_rate": 1.713792835856503e-05, "loss": 0.3764, "step": 552 }, { "epoch": 0.54, "learning_rate": 1.7126829514871043e-05, "loss": 0.4227, "step": 553 }, { "epoch": 0.54, "learning_rate": 1.71157128016652e-05, "loss": 0.3789, "step": 554 }, { "epoch": 0.54, "learning_rate": 1.7104578246821083e-05, "loss": 0.3771, "step": 555 }, { "epoch": 0.54, "learning_rate": 1.7093425878257007e-05, "loss": 0.3881, "step": 556 }, { "epoch": 0.54, "learning_rate": 1.7082255723935944e-05, "loss": 0.3792, "step": 557 }, { "epoch": 0.55, "learning_rate": 1.7071067811865477e-05, "loss": 0.4094, "step": 558 }, { "epoch": 0.55, "learning_rate": 1.7059862170097696e-05, "loss": 0.404, "step": 559 }, { "epoch": 0.55, "learning_rate": 1.7048638826729163e-05, "loss": 0.3918, "step": 560 }, { "epoch": 0.55, "learning_rate": 1.7037397809900807e-05, "loss": 0.3723, "step": 561 }, { "epoch": 0.55, "learning_rate": 1.7026139147797887e-05, "loss": 0.3611, "step": 562 }, { "epoch": 0.55, "learning_rate": 1.7014862868649894e-05, "loss": 0.4033, "step": 563 }, { "epoch": 0.55, "learning_rate": 1.7003569000730498e-05, "loss": 0.3868, "step": 564 }, { "epoch": 0.55, "learning_rate": 1.6992257572357465e-05, "loss": 0.3505, "step": 565 }, { "epoch": 0.55, "learning_rate": 1.698092861189259e-05, "loss": 0.3751, "step": 566 }, { "epoch": 0.55, "learning_rate": 1.696958214774164e-05, "loss": 0.4134, "step": 567 }, { "epoch": 0.55, "learning_rate": 1.695821820835425e-05, "loss": 0.3583, "step": 568 }, { "epoch": 0.56, "learning_rate": 1.6946836822223895e-05, "loss": 0.3998, "step": 569 }, { "epoch": 0.56, "learning_rate": 1.693543801788777e-05, "loss": 0.3852, "step": 570 }, { "epoch": 0.56, "learning_rate": 1.6924021823926766e-05, "loss": 0.4289, "step": 571 }, { "epoch": 0.56, "learning_rate": 1.6912588268965363e-05, "loss": 0.3663, "step": 572 }, { "epoch": 0.56, "learning_rate": 1.690113738167157e-05, "loss": 0.3652, "step": 573 }, { "epoch": 0.56, "learning_rate": 1.688966919075687e-05, "loss": 0.3567, "step": 574 }, { "epoch": 0.56, "learning_rate": 1.6878183724976107e-05, "loss": 0.4081, "step": 575 }, { "epoch": 0.56, "learning_rate": 1.6866681013127466e-05, "loss": 0.4025, "step": 576 }, { "epoch": 0.56, "learning_rate": 1.6855161084052358e-05, "loss": 0.3854, "step": 577 }, { "epoch": 0.56, "learning_rate": 1.6843623966635364e-05, "loss": 0.3479, "step": 578 }, { "epoch": 0.57, "learning_rate": 1.683206968980417e-05, "loss": 0.3601, "step": 579 }, { "epoch": 0.57, "learning_rate": 1.682049828252948e-05, "loss": 0.3485, "step": 580 }, { "epoch": 0.57, "learning_rate": 1.6808909773824952e-05, "loss": 0.3704, "step": 581 }, { "epoch": 0.57, "learning_rate": 1.679730419274713e-05, "loss": 0.3687, "step": 582 }, { "epoch": 0.57, "learning_rate": 1.6785681568395353e-05, "loss": 0.3801, "step": 583 }, { "epoch": 0.57, "learning_rate": 1.67740419299117e-05, "loss": 0.4069, "step": 584 }, { "epoch": 0.57, "learning_rate": 1.676238530648091e-05, "loss": 0.4198, "step": 585 }, { "epoch": 0.57, "learning_rate": 1.675071172733031e-05, "loss": 0.417, "step": 586 }, { "epoch": 0.57, "learning_rate": 1.6739021221729743e-05, "loss": 0.3856, "step": 587 }, { "epoch": 0.57, "learning_rate": 1.6727313818991485e-05, "loss": 0.3865, "step": 588 }, { "epoch": 0.58, "learning_rate": 1.6715589548470187e-05, "loss": 0.4093, "step": 589 }, { "epoch": 0.58, "learning_rate": 1.6703848439562787e-05, "loss": 0.3748, "step": 590 }, { "epoch": 0.58, "learning_rate": 1.669209052170845e-05, "loss": 0.4007, "step": 591 }, { "epoch": 0.58, "learning_rate": 1.668031582438848e-05, "loss": 0.4043, "step": 592 }, { "epoch": 0.58, "learning_rate": 1.666852437712626e-05, "loss": 0.3447, "step": 593 }, { "epoch": 0.58, "learning_rate": 1.6656716209487175e-05, "loss": 0.3666, "step": 594 }, { "epoch": 0.58, "learning_rate": 1.664489135107851e-05, "loss": 0.3534, "step": 595 }, { "epoch": 0.58, "learning_rate": 1.6633049831549424e-05, "loss": 0.3804, "step": 596 }, { "epoch": 0.58, "learning_rate": 1.6621191680590853e-05, "loss": 0.3684, "step": 597 }, { "epoch": 0.58, "learning_rate": 1.660931692793541e-05, "loss": 0.3836, "step": 598 }, { "epoch": 0.59, "learning_rate": 1.6597425603357357e-05, "loss": 0.3628, "step": 599 }, { "epoch": 0.59, "learning_rate": 1.6585517736672498e-05, "loss": 0.4019, "step": 600 }, { "epoch": 0.59, "learning_rate": 1.657359335773812e-05, "loss": 0.3836, "step": 601 }, { "epoch": 0.59, "learning_rate": 1.65616524964529e-05, "loss": 0.3634, "step": 602 }, { "epoch": 0.59, "learning_rate": 1.6549695182756857e-05, "loss": 0.3966, "step": 603 }, { "epoch": 0.59, "learning_rate": 1.653772144663125e-05, "loss": 0.3724, "step": 604 }, { "epoch": 0.59, "learning_rate": 1.6525731318098526e-05, "loss": 0.3724, "step": 605 }, { "epoch": 0.59, "learning_rate": 1.6513724827222225e-05, "loss": 0.387, "step": 606 }, { "epoch": 0.59, "learning_rate": 1.6501702004106914e-05, "loss": 0.3845, "step": 607 }, { "epoch": 0.59, "learning_rate": 1.6489662878898115e-05, "loss": 0.4027, "step": 608 }, { "epoch": 0.59, "learning_rate": 1.6477607481782222e-05, "loss": 0.3682, "step": 609 }, { "epoch": 0.6, "learning_rate": 1.6465535842986433e-05, "loss": 0.3525, "step": 610 }, { "epoch": 0.6, "learning_rate": 1.645344799277866e-05, "loss": 0.3515, "step": 611 }, { "epoch": 0.6, "learning_rate": 1.6441343961467473e-05, "loss": 0.4041, "step": 612 }, { "epoch": 0.6, "learning_rate": 1.642922377940201e-05, "loss": 0.397, "step": 613 }, { "epoch": 0.6, "learning_rate": 1.64170874769719e-05, "loss": 0.3655, "step": 614 }, { "epoch": 0.6, "learning_rate": 1.6404935084607202e-05, "loss": 0.3829, "step": 615 }, { "epoch": 0.6, "learning_rate": 1.639276663277831e-05, "loss": 0.349, "step": 616 }, { "epoch": 0.6, "learning_rate": 1.6380582151995886e-05, "loss": 0.3579, "step": 617 }, { "epoch": 0.6, "learning_rate": 1.6368381672810788e-05, "loss": 0.3782, "step": 618 }, { "epoch": 0.6, "learning_rate": 1.6356165225813975e-05, "loss": 0.3745, "step": 619 }, { "epoch": 0.61, "learning_rate": 1.6343932841636455e-05, "loss": 0.3655, "step": 620 }, { "epoch": 0.61, "learning_rate": 1.6331684550949197e-05, "loss": 0.3759, "step": 621 }, { "epoch": 0.61, "learning_rate": 1.631942038446304e-05, "loss": 0.3861, "step": 622 }, { "epoch": 0.61, "learning_rate": 1.630714037292865e-05, "loss": 0.404, "step": 623 }, { "epoch": 0.61, "learning_rate": 1.6294844547136394e-05, "loss": 0.3307, "step": 624 }, { "epoch": 0.61, "learning_rate": 1.628253293791632e-05, "loss": 0.3611, "step": 625 }, { "epoch": 0.61, "learning_rate": 1.627020557613803e-05, "loss": 0.3628, "step": 626 }, { "epoch": 0.61, "learning_rate": 1.625786249271064e-05, "loss": 0.3609, "step": 627 }, { "epoch": 0.61, "learning_rate": 1.624550371858267e-05, "loss": 0.387, "step": 628 }, { "epoch": 0.61, "learning_rate": 1.6233129284741992e-05, "loss": 0.3432, "step": 629 }, { "epoch": 0.62, "learning_rate": 1.6220739222215738e-05, "loss": 0.3397, "step": 630 }, { "epoch": 0.62, "learning_rate": 1.6208333562070232e-05, "loss": 0.3893, "step": 631 }, { "epoch": 0.62, "learning_rate": 1.6195912335410896e-05, "loss": 0.3829, "step": 632 }, { "epoch": 0.62, "learning_rate": 1.6183475573382196e-05, "loss": 0.3668, "step": 633 }, { "epoch": 0.62, "learning_rate": 1.6171023307167545e-05, "loss": 0.3538, "step": 634 }, { "epoch": 0.62, "learning_rate": 1.615855556798923e-05, "loss": 0.342, "step": 635 }, { "epoch": 0.62, "learning_rate": 1.614607238710833e-05, "loss": 0.3845, "step": 636 }, { "epoch": 0.62, "learning_rate": 1.613357379582465e-05, "loss": 0.3473, "step": 637 }, { "epoch": 0.62, "learning_rate": 1.612105982547663e-05, "loss": 0.3458, "step": 638 }, { "epoch": 0.62, "learning_rate": 1.6108530507441273e-05, "loss": 0.3569, "step": 639 }, { "epoch": 0.63, "learning_rate": 1.6095985873134063e-05, "loss": 0.392, "step": 640 }, { "epoch": 0.63, "learning_rate": 1.6083425954008883e-05, "loss": 0.3827, "step": 641 }, { "epoch": 0.63, "learning_rate": 1.607085078155795e-05, "loss": 0.389, "step": 642 }, { "epoch": 0.63, "learning_rate": 1.605826038731172e-05, "loss": 0.385, "step": 643 }, { "epoch": 0.63, "learning_rate": 1.6045654802838812e-05, "loss": 0.3379, "step": 644 }, { "epoch": 0.63, "learning_rate": 1.6033034059745943e-05, "loss": 0.3549, "step": 645 }, { "epoch": 0.63, "learning_rate": 1.602039818967783e-05, "loss": 0.3336, "step": 646 }, { "epoch": 0.63, "learning_rate": 1.6007747224317124e-05, "loss": 0.3684, "step": 647 }, { "epoch": 0.63, "learning_rate": 1.5995081195384314e-05, "loss": 0.3919, "step": 648 }, { "epoch": 0.63, "learning_rate": 1.5982400134637674e-05, "loss": 0.3918, "step": 649 }, { "epoch": 0.64, "learning_rate": 1.5969704073873157e-05, "loss": 0.345, "step": 650 }, { "epoch": 0.64, "learning_rate": 1.5956993044924334e-05, "loss": 0.3573, "step": 651 }, { "epoch": 0.64, "learning_rate": 1.5944267079662302e-05, "loss": 0.3734, "step": 652 }, { "epoch": 0.64, "learning_rate": 1.5931526209995608e-05, "loss": 0.3414, "step": 653 }, { "epoch": 0.64, "learning_rate": 1.5918770467870174e-05, "loss": 0.353, "step": 654 }, { "epoch": 0.64, "learning_rate": 1.5905999885269208e-05, "loss": 0.3622, "step": 655 }, { "epoch": 0.64, "learning_rate": 1.589321449421313e-05, "loss": 0.3589, "step": 656 }, { "epoch": 0.64, "learning_rate": 1.5880414326759493e-05, "loss": 0.3864, "step": 657 }, { "epoch": 0.64, "learning_rate": 1.5867599415002896e-05, "loss": 0.3914, "step": 658 }, { "epoch": 0.64, "learning_rate": 1.5854769791074906e-05, "loss": 0.3459, "step": 659 }, { "epoch": 0.64, "learning_rate": 1.5841925487143986e-05, "loss": 0.3634, "step": 660 }, { "epoch": 0.65, "learning_rate": 1.5829066535415402e-05, "loss": 0.3595, "step": 661 }, { "epoch": 0.65, "learning_rate": 1.5816192968131138e-05, "loss": 0.3712, "step": 662 }, { "epoch": 0.65, "learning_rate": 1.5803304817569847e-05, "loss": 0.3386, "step": 663 }, { "epoch": 0.65, "learning_rate": 1.5790402116046725e-05, "loss": 0.3772, "step": 664 }, { "epoch": 0.65, "learning_rate": 1.5777484895913462e-05, "loss": 0.3677, "step": 665 }, { "epoch": 0.65, "learning_rate": 1.576455318955816e-05, "loss": 0.3806, "step": 666 }, { "epoch": 0.65, "learning_rate": 1.5751607029405226e-05, "loss": 0.3425, "step": 667 }, { "epoch": 0.65, "learning_rate": 1.573864644791532e-05, "loss": 0.3517, "step": 668 }, { "epoch": 0.65, "learning_rate": 1.5725671477585255e-05, "loss": 0.3693, "step": 669 }, { "epoch": 0.65, "learning_rate": 1.5712682150947926e-05, "loss": 0.3794, "step": 670 }, { "epoch": 0.66, "learning_rate": 1.569967850057222e-05, "loss": 0.371, "step": 671 }, { "epoch": 0.66, "learning_rate": 1.568666055906295e-05, "loss": 0.3822, "step": 672 }, { "epoch": 0.66, "learning_rate": 1.567362835906074e-05, "loss": 0.3144, "step": 673 }, { "epoch": 0.66, "learning_rate": 1.5660581933241994e-05, "loss": 0.412, "step": 674 }, { "epoch": 0.66, "learning_rate": 1.564752131431876e-05, "loss": 0.3966, "step": 675 }, { "epoch": 0.66, "learning_rate": 1.5634446535038688e-05, "loss": 0.3469, "step": 676 }, { "epoch": 0.66, "learning_rate": 1.5621357628184924e-05, "loss": 0.3555, "step": 677 }, { "epoch": 0.66, "learning_rate": 1.5608254626576046e-05, "loss": 0.3418, "step": 678 }, { "epoch": 0.66, "learning_rate": 1.5595137563065965e-05, "loss": 0.3528, "step": 679 }, { "epoch": 0.66, "learning_rate": 1.5582006470543855e-05, "loss": 0.3664, "step": 680 }, { "epoch": 0.67, "learning_rate": 1.556886138193406e-05, "loss": 0.3651, "step": 681 }, { "epoch": 0.67, "learning_rate": 1.5555702330196024e-05, "loss": 0.3257, "step": 682 }, { "epoch": 0.67, "learning_rate": 1.55425293483242e-05, "loss": 0.3325, "step": 683 }, { "epoch": 0.67, "learning_rate": 1.5529342469347958e-05, "loss": 0.3292, "step": 684 }, { "epoch": 0.67, "learning_rate": 1.551614172633154e-05, "loss": 0.324, "step": 685 }, { "epoch": 0.67, "learning_rate": 1.5502927152373913e-05, "loss": 0.3485, "step": 686 }, { "epoch": 0.67, "learning_rate": 1.548969878060876e-05, "loss": 0.3353, "step": 687 }, { "epoch": 0.67, "learning_rate": 1.5476456644204328e-05, "loss": 0.3811, "step": 688 }, { "epoch": 0.67, "learning_rate": 1.54632007763634e-05, "loss": 0.3466, "step": 689 }, { "epoch": 0.67, "learning_rate": 1.544993121032318e-05, "loss": 0.3269, "step": 690 }, { "epoch": 0.68, "learning_rate": 1.5436647979355214e-05, "loss": 0.3702, "step": 691 }, { "epoch": 0.68, "learning_rate": 1.5423351116765316e-05, "loss": 0.3496, "step": 692 }, { "epoch": 0.68, "learning_rate": 1.5410040655893484e-05, "loss": 0.3322, "step": 693 }, { "epoch": 0.68, "learning_rate": 1.53967166301138e-05, "loss": 0.3518, "step": 694 }, { "epoch": 0.68, "learning_rate": 1.5383379072834373e-05, "loss": 0.3295, "step": 695 }, { "epoch": 0.68, "learning_rate": 1.5370028017497217e-05, "loss": 0.3459, "step": 696 }, { "epoch": 0.68, "learning_rate": 1.5356663497578223e-05, "loss": 0.3622, "step": 697 }, { "epoch": 0.68, "learning_rate": 1.534328554658701e-05, "loss": 0.3246, "step": 698 }, { "epoch": 0.68, "learning_rate": 1.53298941980669e-05, "loss": 0.3564, "step": 699 }, { "epoch": 0.68, "learning_rate": 1.5316489485594785e-05, "loss": 0.3508, "step": 700 }, { "epoch": 0.68, "learning_rate": 1.5303071442781083e-05, "loss": 0.3468, "step": 701 }, { "epoch": 0.69, "learning_rate": 1.5289640103269626e-05, "loss": 0.3542, "step": 702 }, { "epoch": 0.69, "learning_rate": 1.5276195500737592e-05, "loss": 0.3542, "step": 703 }, { "epoch": 0.69, "learning_rate": 1.5262737668895403e-05, "loss": 0.3598, "step": 704 }, { "epoch": 0.69, "learning_rate": 1.5249266641486666e-05, "loss": 0.3434, "step": 705 }, { "epoch": 0.69, "learning_rate": 1.5235782452288068e-05, "loss": 0.3474, "step": 706 }, { "epoch": 0.69, "learning_rate": 1.5222285135109291e-05, "loss": 0.3652, "step": 707 }, { "epoch": 0.69, "learning_rate": 1.5208774723792943e-05, "loss": 0.366, "step": 708 }, { "epoch": 0.69, "learning_rate": 1.5195251252214461e-05, "loss": 0.3401, "step": 709 }, { "epoch": 0.69, "learning_rate": 1.518171475428202e-05, "loss": 0.3075, "step": 710 }, { "epoch": 0.69, "learning_rate": 1.5168165263936472e-05, "loss": 0.3378, "step": 711 }, { "epoch": 0.7, "learning_rate": 1.5154602815151233e-05, "loss": 0.3716, "step": 712 }, { "epoch": 0.7, "learning_rate": 1.5141027441932217e-05, "loss": 0.3741, "step": 713 }, { "epoch": 0.7, "learning_rate": 1.5127439178317747e-05, "loss": 0.3317, "step": 714 }, { "epoch": 0.7, "learning_rate": 1.5113838058378454e-05, "loss": 0.3362, "step": 715 }, { "epoch": 0.7, "learning_rate": 1.5100224116217217e-05, "loss": 0.36, "step": 716 }, { "epoch": 0.7, "learning_rate": 1.5086597385969062e-05, "loss": 0.3256, "step": 717 }, { "epoch": 0.7, "learning_rate": 1.5072957901801075e-05, "loss": 0.3361, "step": 718 }, { "epoch": 0.7, "learning_rate": 1.5059305697912323e-05, "loss": 0.3208, "step": 719 }, { "epoch": 0.7, "learning_rate": 1.5045640808533772e-05, "loss": 0.3487, "step": 720 }, { "epoch": 0.7, "learning_rate": 1.5031963267928185e-05, "loss": 0.3709, "step": 721 }, { "epoch": 0.71, "learning_rate": 1.501827311039005e-05, "loss": 0.3263, "step": 722 }, { "epoch": 0.71, "learning_rate": 1.5004570370245492e-05, "loss": 0.3512, "step": 723 }, { "epoch": 0.71, "learning_rate": 1.4990855081852185e-05, "loss": 0.3695, "step": 724 }, { "epoch": 0.71, "learning_rate": 1.4977127279599264e-05, "loss": 0.3625, "step": 725 }, { "epoch": 0.71, "learning_rate": 1.4963386997907242e-05, "loss": 0.3454, "step": 726 }, { "epoch": 0.71, "learning_rate": 1.4949634271227918e-05, "loss": 0.3436, "step": 727 }, { "epoch": 0.71, "learning_rate": 1.4935869134044308e-05, "loss": 0.3548, "step": 728 }, { "epoch": 0.71, "learning_rate": 1.4922091620870527e-05, "loss": 0.3467, "step": 729 }, { "epoch": 0.71, "learning_rate": 1.4908301766251739e-05, "loss": 0.3285, "step": 730 }, { "epoch": 0.71, "learning_rate": 1.4894499604764035e-05, "loss": 0.3332, "step": 731 }, { "epoch": 0.72, "learning_rate": 1.4880685171014382e-05, "loss": 0.3406, "step": 732 }, { "epoch": 0.72, "learning_rate": 1.4866858499640504e-05, "loss": 0.3422, "step": 733 }, { "epoch": 0.72, "learning_rate": 1.4853019625310813e-05, "loss": 0.3576, "step": 734 }, { "epoch": 0.72, "learning_rate": 1.483916858272432e-05, "loss": 0.3684, "step": 735 }, { "epoch": 0.72, "learning_rate": 1.4825305406610547e-05, "loss": 0.3359, "step": 736 }, { "epoch": 0.72, "learning_rate": 1.4811430131729436e-05, "loss": 0.3545, "step": 737 }, { "epoch": 0.72, "learning_rate": 1.4797542792871267e-05, "loss": 0.3211, "step": 738 }, { "epoch": 0.72, "learning_rate": 1.4783643424856564e-05, "loss": 0.3409, "step": 739 }, { "epoch": 0.72, "learning_rate": 1.4769732062536022e-05, "loss": 0.3765, "step": 740 }, { "epoch": 0.72, "learning_rate": 1.4755808740790403e-05, "loss": 0.3345, "step": 741 }, { "epoch": 0.72, "learning_rate": 1.4741873494530452e-05, "loss": 0.3265, "step": 742 }, { "epoch": 0.73, "learning_rate": 1.4727926358696825e-05, "loss": 0.3693, "step": 743 }, { "epoch": 0.73, "learning_rate": 1.4713967368259981e-05, "loss": 0.3149, "step": 744 }, { "epoch": 0.73, "learning_rate": 1.4699996558220095e-05, "loss": 0.3262, "step": 745 }, { "epoch": 0.73, "learning_rate": 1.4686013963607e-05, "loss": 0.3622, "step": 746 }, { "epoch": 0.73, "learning_rate": 1.4672019619480056e-05, "loss": 0.33, "step": 747 }, { "epoch": 0.73, "learning_rate": 1.4658013560928098e-05, "loss": 0.3311, "step": 748 }, { "epoch": 0.73, "learning_rate": 1.4643995823069318e-05, "loss": 0.2914, "step": 749 }, { "epoch": 0.73, "learning_rate": 1.4629966441051208e-05, "loss": 0.3232, "step": 750 }, { "epoch": 0.73, "learning_rate": 1.4615925450050448e-05, "loss": 0.331, "step": 751 }, { "epoch": 0.73, "learning_rate": 1.4601872885272824e-05, "loss": 0.3366, "step": 752 }, { "epoch": 0.74, "learning_rate": 1.4587808781953146e-05, "loss": 0.3337, "step": 753 }, { "epoch": 0.74, "learning_rate": 1.4573733175355152e-05, "loss": 0.3215, "step": 754 }, { "epoch": 0.74, "learning_rate": 1.4559646100771428e-05, "loss": 0.3084, "step": 755 }, { "epoch": 0.74, "learning_rate": 1.4545547593523308e-05, "loss": 0.3417, "step": 756 }, { "epoch": 0.74, "learning_rate": 1.4531437688960796e-05, "loss": 0.3703, "step": 757 }, { "epoch": 0.74, "learning_rate": 1.4517316422462471e-05, "loss": 0.3198, "step": 758 }, { "epoch": 0.74, "learning_rate": 1.4503183829435403e-05, "loss": 0.3495, "step": 759 }, { "epoch": 0.74, "learning_rate": 1.4489039945315059e-05, "loss": 0.3373, "step": 760 }, { "epoch": 0.74, "learning_rate": 1.4474884805565217e-05, "loss": 0.3479, "step": 761 }, { "epoch": 0.74, "learning_rate": 1.4460718445677877e-05, "loss": 0.3732, "step": 762 }, { "epoch": 0.75, "learning_rate": 1.4446540901173176e-05, "loss": 0.3469, "step": 763 }, { "epoch": 0.75, "learning_rate": 1.4432352207599288e-05, "loss": 0.3209, "step": 764 }, { "epoch": 0.75, "learning_rate": 1.4418152400532344e-05, "loss": 0.3198, "step": 765 }, { "epoch": 0.75, "learning_rate": 1.4403941515576344e-05, "loss": 0.3382, "step": 766 }, { "epoch": 0.75, "learning_rate": 1.4389719588363062e-05, "loss": 0.3177, "step": 767 }, { "epoch": 0.75, "learning_rate": 1.437548665455196e-05, "loss": 0.3069, "step": 768 }, { "epoch": 0.75, "learning_rate": 1.4361242749830093e-05, "loss": 0.3221, "step": 769 }, { "epoch": 0.75, "learning_rate": 1.4346987909912024e-05, "loss": 0.3441, "step": 770 }, { "epoch": 0.75, "learning_rate": 1.4332722170539748e-05, "loss": 0.3823, "step": 771 }, { "epoch": 0.75, "learning_rate": 1.431844556748257e-05, "loss": 0.3567, "step": 772 }, { "epoch": 0.76, "learning_rate": 1.4304158136537047e-05, "loss": 0.3154, "step": 773 }, { "epoch": 0.76, "learning_rate": 1.4289859913526876e-05, "loss": 0.3336, "step": 774 }, { "epoch": 0.76, "learning_rate": 1.4275550934302822e-05, "loss": 0.3078, "step": 775 }, { "epoch": 0.76, "learning_rate": 1.4261231234742618e-05, "loss": 0.3402, "step": 776 }, { "epoch": 0.76, "learning_rate": 1.424690085075087e-05, "loss": 0.3645, "step": 777 }, { "epoch": 0.76, "learning_rate": 1.4232559818258983e-05, "loss": 0.341, "step": 778 }, { "epoch": 0.76, "learning_rate": 1.4218208173225057e-05, "loss": 0.3421, "step": 779 }, { "epoch": 0.76, "learning_rate": 1.4203845951633799e-05, "loss": 0.3259, "step": 780 }, { "epoch": 0.76, "learning_rate": 1.4189473189496437e-05, "loss": 0.3393, "step": 781 }, { "epoch": 0.76, "learning_rate": 1.4175089922850633e-05, "loss": 0.3324, "step": 782 }, { "epoch": 0.76, "learning_rate": 1.4160696187760383e-05, "loss": 0.3654, "step": 783 }, { "epoch": 0.77, "learning_rate": 1.4146292020315926e-05, "loss": 0.3264, "step": 784 }, { "epoch": 0.77, "learning_rate": 1.413187745663367e-05, "loss": 0.3215, "step": 785 }, { "epoch": 0.77, "learning_rate": 1.4117452532856084e-05, "loss": 0.3293, "step": 786 }, { "epoch": 0.77, "learning_rate": 1.4103017285151607e-05, "loss": 0.3315, "step": 787 }, { "epoch": 0.77, "learning_rate": 1.408857174971458e-05, "loss": 0.328, "step": 788 }, { "epoch": 0.77, "learning_rate": 1.4074115962765125e-05, "loss": 0.354, "step": 789 }, { "epoch": 0.77, "learning_rate": 1.4059649960549071e-05, "loss": 0.3346, "step": 790 }, { "epoch": 0.77, "learning_rate": 1.4045173779337866e-05, "loss": 0.3238, "step": 791 }, { "epoch": 0.77, "learning_rate": 1.4030687455428473e-05, "loss": 0.3346, "step": 792 }, { "epoch": 0.77, "learning_rate": 1.4016191025143289e-05, "loss": 0.3293, "step": 793 }, { "epoch": 0.78, "learning_rate": 1.4001684524830057e-05, "loss": 0.3277, "step": 794 }, { "epoch": 0.78, "learning_rate": 1.3987167990861763e-05, "loss": 0.2971, "step": 795 }, { "epoch": 0.78, "learning_rate": 1.3972641459636548e-05, "loss": 0.3252, "step": 796 }, { "epoch": 0.78, "learning_rate": 1.3958104967577627e-05, "loss": 0.3216, "step": 797 }, { "epoch": 0.78, "learning_rate": 1.3943558551133186e-05, "loss": 0.3292, "step": 798 }, { "epoch": 0.78, "learning_rate": 1.39290022467763e-05, "loss": 0.3587, "step": 799 }, { "epoch": 0.78, "learning_rate": 1.3914436091004829e-05, "loss": 0.3072, "step": 800 }, { "epoch": 0.78, "learning_rate": 1.3899860120341338e-05, "loss": 0.3441, "step": 801 }, { "epoch": 0.78, "learning_rate": 1.3885274371333001e-05, "loss": 0.3214, "step": 802 }, { "epoch": 0.78, "learning_rate": 1.3870678880551516e-05, "loss": 0.3376, "step": 803 }, { "epoch": 0.79, "learning_rate": 1.3856073684592994e-05, "loss": 0.3347, "step": 804 }, { "epoch": 0.79, "learning_rate": 1.3841458820077889e-05, "loss": 0.3146, "step": 805 }, { "epoch": 0.79, "learning_rate": 1.3826834323650899e-05, "loss": 0.2887, "step": 806 }, { "epoch": 0.79, "learning_rate": 1.3812200231980869e-05, "loss": 0.3588, "step": 807 }, { "epoch": 0.79, "learning_rate": 1.37975565817607e-05, "loss": 0.342, "step": 808 }, { "epoch": 0.79, "learning_rate": 1.3782903409707266e-05, "loss": 0.3123, "step": 809 }, { "epoch": 0.79, "learning_rate": 1.3768240752561315e-05, "loss": 0.3395, "step": 810 }, { "epoch": 0.79, "learning_rate": 1.3753568647087372e-05, "loss": 0.3014, "step": 811 }, { "epoch": 0.79, "learning_rate": 1.3738887130073655e-05, "loss": 0.3324, "step": 812 }, { "epoch": 0.79, "learning_rate": 1.3724196238331983e-05, "loss": 0.3195, "step": 813 }, { "epoch": 0.8, "learning_rate": 1.370949600869768e-05, "loss": 0.3301, "step": 814 }, { "epoch": 0.8, "learning_rate": 1.3694786478029478e-05, "loss": 0.3149, "step": 815 }, { "epoch": 0.8, "learning_rate": 1.3680067683209438e-05, "loss": 0.303, "step": 816 }, { "epoch": 0.8, "learning_rate": 1.366533966114284e-05, "loss": 0.3333, "step": 817 }, { "epoch": 0.8, "learning_rate": 1.3650602448758113e-05, "loss": 0.3516, "step": 818 }, { "epoch": 0.8, "learning_rate": 1.3635856083006715e-05, "loss": 0.3044, "step": 819 }, { "epoch": 0.8, "learning_rate": 1.3621100600863066e-05, "loss": 0.3101, "step": 820 }, { "epoch": 0.8, "learning_rate": 1.3606336039324439e-05, "loss": 0.2977, "step": 821 }, { "epoch": 0.8, "learning_rate": 1.3591562435410873e-05, "loss": 0.3234, "step": 822 }, { "epoch": 0.8, "learning_rate": 1.357677982616508e-05, "loss": 0.3342, "step": 823 }, { "epoch": 0.81, "learning_rate": 1.3561988248652346e-05, "loss": 0.3466, "step": 824 }, { "epoch": 0.81, "learning_rate": 1.3547187739960458e-05, "loss": 0.3351, "step": 825 }, { "epoch": 0.81, "learning_rate": 1.353237833719958e-05, "loss": 0.3056, "step": 826 }, { "epoch": 0.81, "learning_rate": 1.3517560077502191e-05, "loss": 0.3341, "step": 827 }, { "epoch": 0.81, "learning_rate": 1.3502732998022965e-05, "loss": 0.3317, "step": 828 }, { "epoch": 0.81, "learning_rate": 1.3487897135938697e-05, "loss": 0.3295, "step": 829 }, { "epoch": 0.81, "learning_rate": 1.3473052528448203e-05, "loss": 0.3191, "step": 830 }, { "epoch": 0.81, "learning_rate": 1.3458199212772227e-05, "loss": 0.3267, "step": 831 }, { "epoch": 0.81, "learning_rate": 1.3443337226153343e-05, "loss": 0.3818, "step": 832 }, { "epoch": 0.81, "learning_rate": 1.3428466605855874e-05, "loss": 0.3121, "step": 833 }, { "epoch": 0.81, "learning_rate": 1.3413587389165783e-05, "loss": 0.3281, "step": 834 }, { "epoch": 0.82, "learning_rate": 1.3398699613390593e-05, "loss": 0.3154, "step": 835 }, { "epoch": 0.82, "learning_rate": 1.3383803315859281e-05, "loss": 0.3515, "step": 836 }, { "epoch": 0.82, "learning_rate": 1.3368898533922202e-05, "loss": 0.3182, "step": 837 }, { "epoch": 0.82, "learning_rate": 1.3353985304950974e-05, "loss": 0.3167, "step": 838 }, { "epoch": 0.82, "learning_rate": 1.3339063666338396e-05, "loss": 0.3186, "step": 839 }, { "epoch": 0.82, "learning_rate": 1.3324133655498361e-05, "loss": 0.2975, "step": 840 }, { "epoch": 0.82, "learning_rate": 1.3309195309865746e-05, "loss": 0.2934, "step": 841 }, { "epoch": 0.82, "learning_rate": 1.329424866689633e-05, "loss": 0.3129, "step": 842 }, { "epoch": 0.82, "learning_rate": 1.3279293764066693e-05, "loss": 0.3187, "step": 843 }, { "epoch": 0.82, "learning_rate": 1.3264330638874128e-05, "loss": 0.3139, "step": 844 }, { "epoch": 0.83, "learning_rate": 1.3249359328836549e-05, "loss": 0.3176, "step": 845 }, { "epoch": 0.83, "learning_rate": 1.3234379871492381e-05, "loss": 0.281, "step": 846 }, { "epoch": 0.83, "learning_rate": 1.3219392304400489e-05, "loss": 0.3202, "step": 847 }, { "epoch": 0.83, "learning_rate": 1.3204396665140066e-05, "loss": 0.3187, "step": 848 }, { "epoch": 0.83, "learning_rate": 1.3189392991310545e-05, "loss": 0.3328, "step": 849 }, { "epoch": 0.83, "learning_rate": 1.3174381320531504e-05, "loss": 0.3071, "step": 850 }, { "epoch": 0.83, "learning_rate": 1.315936169044257e-05, "loss": 0.3083, "step": 851 }, { "epoch": 0.83, "learning_rate": 1.3144334138703341e-05, "loss": 0.3071, "step": 852 }, { "epoch": 0.83, "learning_rate": 1.3129298702993256e-05, "loss": 0.3047, "step": 853 }, { "epoch": 0.83, "learning_rate": 1.311425542101154e-05, "loss": 0.3344, "step": 854 }, { "epoch": 0.84, "learning_rate": 1.3099204330477078e-05, "loss": 0.3172, "step": 855 }, { "epoch": 0.84, "learning_rate": 1.3084145469128343e-05, "loss": 0.3365, "step": 856 }, { "epoch": 0.84, "learning_rate": 1.306907887472329e-05, "loss": 0.3319, "step": 857 }, { "epoch": 0.84, "learning_rate": 1.305400458503926e-05, "loss": 0.328, "step": 858 }, { "epoch": 0.84, "learning_rate": 1.303892263787289e-05, "loss": 0.2892, "step": 859 }, { "epoch": 0.84, "learning_rate": 1.3023833071040026e-05, "loss": 0.3362, "step": 860 }, { "epoch": 0.84, "learning_rate": 1.3008735922375607e-05, "loss": 0.2863, "step": 861 }, { "epoch": 0.84, "learning_rate": 1.2993631229733584e-05, "loss": 0.3089, "step": 862 }, { "epoch": 0.84, "learning_rate": 1.2978519030986827e-05, "loss": 0.3326, "step": 863 }, { "epoch": 0.84, "learning_rate": 1.2963399364027031e-05, "loss": 0.3131, "step": 864 }, { "epoch": 0.85, "learning_rate": 1.294827226676461e-05, "loss": 0.3197, "step": 865 }, { "epoch": 0.85, "learning_rate": 1.2933137777128607e-05, "loss": 0.3134, "step": 866 }, { "epoch": 0.85, "learning_rate": 1.2917995933066604e-05, "loss": 0.2754, "step": 867 }, { "epoch": 0.85, "learning_rate": 1.2902846772544625e-05, "loss": 0.323, "step": 868 }, { "epoch": 0.85, "learning_rate": 1.2887690333547034e-05, "loss": 0.2604, "step": 869 }, { "epoch": 0.85, "learning_rate": 1.287252665407645e-05, "loss": 0.3257, "step": 870 }, { "epoch": 0.85, "learning_rate": 1.2857355772153637e-05, "loss": 0.2993, "step": 871 }, { "epoch": 0.85, "learning_rate": 1.2842177725817433e-05, "loss": 0.3104, "step": 872 }, { "epoch": 0.85, "learning_rate": 1.2826992553124628e-05, "loss": 0.291, "step": 873 }, { "epoch": 0.85, "learning_rate": 1.2811800292149881e-05, "loss": 0.3022, "step": 874 }, { "epoch": 0.85, "learning_rate": 1.279660098098563e-05, "loss": 0.3404, "step": 875 }, { "epoch": 0.86, "learning_rate": 1.2781394657741988e-05, "loss": 0.3573, "step": 876 }, { "epoch": 0.86, "learning_rate": 1.2766181360546646e-05, "loss": 0.2998, "step": 877 }, { "epoch": 0.86, "learning_rate": 1.2750961127544782e-05, "loss": 0.3011, "step": 878 }, { "epoch": 0.86, "learning_rate": 1.2735733996898972e-05, "loss": 0.2855, "step": 879 }, { "epoch": 0.86, "learning_rate": 1.2720500006789079e-05, "loss": 0.3041, "step": 880 }, { "epoch": 0.86, "learning_rate": 1.2705259195412168e-05, "loss": 0.3108, "step": 881 }, { "epoch": 0.86, "learning_rate": 1.2690011600982401e-05, "loss": 0.3215, "step": 882 }, { "epoch": 0.86, "learning_rate": 1.2674757261730963e-05, "loss": 0.3095, "step": 883 }, { "epoch": 0.86, "learning_rate": 1.2659496215905937e-05, "loss": 0.3124, "step": 884 }, { "epoch": 0.86, "learning_rate": 1.2644228501772225e-05, "loss": 0.3004, "step": 885 }, { "epoch": 0.87, "learning_rate": 1.2628954157611449e-05, "loss": 0.3308, "step": 886 }, { "epoch": 0.87, "learning_rate": 1.2613673221721859e-05, "loss": 0.3425, "step": 887 }, { "epoch": 0.87, "learning_rate": 1.2598385732418226e-05, "loss": 0.2931, "step": 888 }, { "epoch": 0.87, "learning_rate": 1.2583091728031757e-05, "loss": 0.2711, "step": 889 }, { "epoch": 0.87, "learning_rate": 1.2567791246909995e-05, "loss": 0.2731, "step": 890 }, { "epoch": 0.87, "learning_rate": 1.255248432741672e-05, "loss": 0.2857, "step": 891 }, { "epoch": 0.87, "learning_rate": 1.2537171007931859e-05, "loss": 0.3037, "step": 892 }, { "epoch": 0.87, "learning_rate": 1.252185132685138e-05, "loss": 0.332, "step": 893 }, { "epoch": 0.87, "learning_rate": 1.2506525322587207e-05, "loss": 0.2714, "step": 894 }, { "epoch": 0.87, "learning_rate": 1.2491193033567117e-05, "loss": 0.3199, "step": 895 }, { "epoch": 0.88, "learning_rate": 1.2475854498234647e-05, "loss": 0.3205, "step": 896 }, { "epoch": 0.88, "learning_rate": 1.2460509755048991e-05, "loss": 0.3232, "step": 897 }, { "epoch": 0.88, "learning_rate": 1.2445158842484913e-05, "loss": 0.2896, "step": 898 }, { "epoch": 0.88, "learning_rate": 1.242980179903264e-05, "loss": 0.2885, "step": 899 }, { "epoch": 0.88, "learning_rate": 1.2414438663197782e-05, "loss": 0.3238, "step": 900 }, { "epoch": 0.88, "learning_rate": 1.239906947350121e-05, "loss": 0.3087, "step": 901 }, { "epoch": 0.88, "learning_rate": 1.2383694268478992e-05, "loss": 0.3161, "step": 902 }, { "epoch": 0.88, "learning_rate": 1.2368313086682262e-05, "loss": 0.3267, "step": 903 }, { "epoch": 0.88, "learning_rate": 1.2352925966677147e-05, "loss": 0.3067, "step": 904 }, { "epoch": 0.88, "learning_rate": 1.2337532947044664e-05, "loss": 0.3211, "step": 905 }, { "epoch": 0.89, "learning_rate": 1.2322134066380622e-05, "loss": 0.2915, "step": 906 }, { "epoch": 0.89, "learning_rate": 1.2306729363295529e-05, "loss": 0.3232, "step": 907 }, { "epoch": 0.89, "learning_rate": 1.2291318876414477e-05, "loss": 0.2803, "step": 908 }, { "epoch": 0.89, "learning_rate": 1.2275902644377082e-05, "loss": 0.2964, "step": 909 }, { "epoch": 0.89, "learning_rate": 1.226048070583735e-05, "loss": 0.3088, "step": 910 }, { "epoch": 0.89, "learning_rate": 1.22450530994636e-05, "loss": 0.3, "step": 911 }, { "epoch": 0.89, "learning_rate": 1.222961986393836e-05, "loss": 0.2819, "step": 912 }, { "epoch": 0.89, "learning_rate": 1.2214181037958274e-05, "loss": 0.2991, "step": 913 }, { "epoch": 0.89, "learning_rate": 1.2198736660234009e-05, "loss": 0.305, "step": 914 }, { "epoch": 0.89, "learning_rate": 1.2183286769490143e-05, "loss": 0.2996, "step": 915 }, { "epoch": 0.89, "learning_rate": 1.2167831404465078e-05, "loss": 0.2961, "step": 916 }, { "epoch": 0.9, "learning_rate": 1.2152370603910946e-05, "loss": 0.3507, "step": 917 }, { "epoch": 0.9, "learning_rate": 1.2136904406593507e-05, "loss": 0.2986, "step": 918 }, { "epoch": 0.9, "learning_rate": 1.2121432851292057e-05, "loss": 0.3277, "step": 919 }, { "epoch": 0.9, "learning_rate": 1.2105955976799316e-05, "loss": 0.2776, "step": 920 }, { "epoch": 0.9, "learning_rate": 1.2090473821921343e-05, "loss": 0.3248, "step": 921 }, { "epoch": 0.9, "learning_rate": 1.2074986425477447e-05, "loss": 0.3331, "step": 922 }, { "epoch": 0.9, "learning_rate": 1.205949382630007e-05, "loss": 0.2722, "step": 923 }, { "epoch": 0.9, "learning_rate": 1.2043996063234707e-05, "loss": 0.3091, "step": 924 }, { "epoch": 0.9, "learning_rate": 1.2028493175139784e-05, "loss": 0.3274, "step": 925 }, { "epoch": 0.9, "learning_rate": 1.2012985200886602e-05, "loss": 0.3096, "step": 926 }, { "epoch": 0.91, "learning_rate": 1.1997472179359196e-05, "loss": 0.2939, "step": 927 }, { "epoch": 0.91, "learning_rate": 1.1981954149454263e-05, "loss": 0.2987, "step": 928 }, { "epoch": 0.91, "learning_rate": 1.1966431150081053e-05, "loss": 0.3106, "step": 929 }, { "epoch": 0.91, "learning_rate": 1.1950903220161286e-05, "loss": 0.2991, "step": 930 }, { "epoch": 0.91, "learning_rate": 1.1935370398629033e-05, "loss": 0.3072, "step": 931 }, { "epoch": 0.91, "learning_rate": 1.1919832724430642e-05, "loss": 0.296, "step": 932 }, { "epoch": 0.91, "learning_rate": 1.1904290236524618e-05, "loss": 0.3088, "step": 933 }, { "epoch": 0.91, "learning_rate": 1.1888742973881544e-05, "loss": 0.2866, "step": 934 }, { "epoch": 0.91, "learning_rate": 1.1873190975483965e-05, "loss": 0.3234, "step": 935 }, { "epoch": 0.91, "learning_rate": 1.185763428032631e-05, "loss": 0.2892, "step": 936 }, { "epoch": 0.92, "learning_rate": 1.1842072927414781e-05, "loss": 0.3046, "step": 937 }, { "epoch": 0.92, "learning_rate": 1.1826506955767259e-05, "loss": 0.2939, "step": 938 }, { "epoch": 0.92, "learning_rate": 1.18109364044132e-05, "loss": 0.3316, "step": 939 }, { "epoch": 0.92, "learning_rate": 1.179536131239355e-05, "loss": 0.2922, "step": 940 }, { "epoch": 0.92, "learning_rate": 1.1779781718760641e-05, "loss": 0.3142, "step": 941 }, { "epoch": 0.92, "learning_rate": 1.1764197662578087e-05, "loss": 0.3107, "step": 942 }, { "epoch": 0.92, "learning_rate": 1.1748609182920694e-05, "loss": 0.2977, "step": 943 }, { "epoch": 0.92, "learning_rate": 1.1733016318874357e-05, "loss": 0.2858, "step": 944 }, { "epoch": 0.92, "learning_rate": 1.1717419109535967e-05, "loss": 0.301, "step": 945 }, { "epoch": 0.92, "learning_rate": 1.1701817594013312e-05, "loss": 0.297, "step": 946 }, { "epoch": 0.93, "learning_rate": 1.1686211811424971e-05, "loss": 0.3281, "step": 947 }, { "epoch": 0.93, "learning_rate": 1.1670601800900225e-05, "loss": 0.3009, "step": 948 }, { "epoch": 0.93, "learning_rate": 1.1654987601578958e-05, "loss": 0.2981, "step": 949 }, { "epoch": 0.93, "learning_rate": 1.1639369252611552e-05, "loss": 0.2898, "step": 950 }, { "epoch": 0.93, "learning_rate": 1.1623746793158803e-05, "loss": 0.286, "step": 951 }, { "epoch": 0.93, "learning_rate": 1.1608120262391803e-05, "loss": 0.3037, "step": 952 }, { "epoch": 0.93, "learning_rate": 1.159248969949185e-05, "loss": 0.3036, "step": 953 }, { "epoch": 0.93, "learning_rate": 1.1576855143650372e-05, "loss": 0.2887, "step": 954 }, { "epoch": 0.93, "learning_rate": 1.1561216634068785e-05, "loss": 0.2793, "step": 955 }, { "epoch": 0.93, "learning_rate": 1.1545574209958433e-05, "loss": 0.2823, "step": 956 }, { "epoch": 0.93, "learning_rate": 1.152992791054047e-05, "loss": 0.321, "step": 957 }, { "epoch": 0.94, "learning_rate": 1.1514277775045768e-05, "loss": 0.2756, "step": 958 }, { "epoch": 0.94, "learning_rate": 1.1498623842714816e-05, "loss": 0.2741, "step": 959 }, { "epoch": 0.94, "learning_rate": 1.148296615279762e-05, "loss": 0.2956, "step": 960 }, { "epoch": 0.94, "learning_rate": 1.1467304744553618e-05, "loss": 0.3186, "step": 961 }, { "epoch": 0.94, "learning_rate": 1.1451639657251564e-05, "loss": 0.3058, "step": 962 }, { "epoch": 0.94, "learning_rate": 1.143597093016943e-05, "loss": 0.2974, "step": 963 }, { "epoch": 0.94, "learning_rate": 1.1420298602594334e-05, "loss": 0.2969, "step": 964 }, { "epoch": 0.94, "learning_rate": 1.14046227138224e-05, "loss": 0.2914, "step": 965 }, { "epoch": 0.94, "learning_rate": 1.1388943303158692e-05, "loss": 0.2433, "step": 966 }, { "epoch": 0.94, "learning_rate": 1.1373260409917104e-05, "loss": 0.2948, "step": 967 }, { "epoch": 0.95, "learning_rate": 1.1357574073420265e-05, "loss": 0.2859, "step": 968 }, { "epoch": 0.95, "learning_rate": 1.1341884332999431e-05, "loss": 0.3022, "step": 969 }, { "epoch": 0.95, "learning_rate": 1.1326191227994392e-05, "loss": 0.3499, "step": 970 }, { "epoch": 0.95, "learning_rate": 1.1310494797753382e-05, "loss": 0.291, "step": 971 }, { "epoch": 0.95, "learning_rate": 1.1294795081632968e-05, "loss": 0.2919, "step": 972 }, { "epoch": 0.95, "learning_rate": 1.1279092118997958e-05, "loss": 0.2963, "step": 973 }, { "epoch": 0.95, "learning_rate": 1.1263385949221294e-05, "loss": 0.3224, "step": 974 }, { "epoch": 0.95, "learning_rate": 1.1247676611683964e-05, "loss": 0.349, "step": 975 }, { "epoch": 0.95, "learning_rate": 1.1231964145774906e-05, "loss": 0.259, "step": 976 }, { "epoch": 0.95, "learning_rate": 1.1216248590890886e-05, "loss": 0.2914, "step": 977 }, { "epoch": 0.96, "learning_rate": 1.120052998643643e-05, "loss": 0.3298, "step": 978 }, { "epoch": 0.96, "learning_rate": 1.1184808371823696e-05, "loss": 0.2973, "step": 979 }, { "epoch": 0.96, "learning_rate": 1.1169083786472407e-05, "loss": 0.2678, "step": 980 }, { "epoch": 0.96, "learning_rate": 1.1153356269809721e-05, "loss": 0.3348, "step": 981 }, { "epoch": 0.96, "learning_rate": 1.1137625861270151e-05, "loss": 0.2817, "step": 982 }, { "epoch": 0.96, "learning_rate": 1.1121892600295456e-05, "loss": 0.2869, "step": 983 }, { "epoch": 0.96, "learning_rate": 1.1106156526334559e-05, "loss": 0.2958, "step": 984 }, { "epoch": 0.96, "learning_rate": 1.1090417678843423e-05, "loss": 0.2942, "step": 985 }, { "epoch": 0.96, "learning_rate": 1.1074676097284973e-05, "loss": 0.2753, "step": 986 }, { "epoch": 0.96, "learning_rate": 1.1058931821128982e-05, "loss": 0.346, "step": 987 }, { "epoch": 0.97, "learning_rate": 1.1043184889851992e-05, "loss": 0.3207, "step": 988 }, { "epoch": 0.97, "learning_rate": 1.1027435342937189e-05, "loss": 0.2874, "step": 989 }, { "epoch": 0.97, "learning_rate": 1.1011683219874324e-05, "loss": 0.2894, "step": 990 }, { "epoch": 0.97, "learning_rate": 1.0995928560159608e-05, "loss": 0.3257, "step": 991 }, { "epoch": 0.97, "learning_rate": 1.098017140329561e-05, "loss": 0.2656, "step": 992 }, { "epoch": 0.97, "learning_rate": 1.0964411788791156e-05, "loss": 0.2925, "step": 993 }, { "epoch": 0.97, "learning_rate": 1.0948649756161246e-05, "loss": 0.2916, "step": 994 }, { "epoch": 0.97, "learning_rate": 1.0932885344926931e-05, "loss": 0.2802, "step": 995 }, { "epoch": 0.97, "learning_rate": 1.0917118594615237e-05, "loss": 0.2785, "step": 996 }, { "epoch": 0.97, "learning_rate": 1.0901349544759046e-05, "loss": 0.276, "step": 997 }, { "epoch": 0.97, "learning_rate": 1.0885578234897003e-05, "loss": 0.3103, "step": 998 }, { "epoch": 0.98, "learning_rate": 1.0869804704573435e-05, "loss": 0.2986, "step": 999 }, { "epoch": 0.98, "learning_rate": 1.0854028993338222e-05, "loss": 0.2976, "step": 1000 }, { "epoch": 0.98, "learning_rate": 1.0838251140746717e-05, "loss": 0.2923, "step": 1001 }, { "epoch": 0.98, "learning_rate": 1.082247118635964e-05, "loss": 0.3062, "step": 1002 }, { "epoch": 0.98, "learning_rate": 1.0806689169742988e-05, "loss": 0.3397, "step": 1003 }, { "epoch": 0.98, "learning_rate": 1.0790905130467923e-05, "loss": 0.3132, "step": 1004 }, { "epoch": 0.98, "learning_rate": 1.077511910811068e-05, "loss": 0.2838, "step": 1005 }, { "epoch": 0.98, "learning_rate": 1.0759331142252463e-05, "loss": 0.2892, "step": 1006 }, { "epoch": 0.98, "learning_rate": 1.0743541272479356e-05, "loss": 0.298, "step": 1007 }, { "epoch": 0.98, "learning_rate": 1.072774953838221e-05, "loss": 0.2813, "step": 1008 }, { "epoch": 0.99, "learning_rate": 1.0711955979556555e-05, "loss": 0.2409, "step": 1009 }, { "epoch": 0.99, "learning_rate": 1.0696160635602488e-05, "loss": 0.2431, "step": 1010 }, { "epoch": 0.99, "learning_rate": 1.0680363546124599e-05, "loss": 0.2778, "step": 1011 }, { "epoch": 0.99, "learning_rate": 1.0664564750731838e-05, "loss": 0.2929, "step": 1012 }, { "epoch": 0.99, "learning_rate": 1.064876428903744e-05, "loss": 0.2932, "step": 1013 }, { "epoch": 0.99, "learning_rate": 1.0632962200658816e-05, "loss": 0.2705, "step": 1014 }, { "epoch": 0.99, "learning_rate": 1.0617158525217457e-05, "loss": 0.2943, "step": 1015 }, { "epoch": 0.99, "learning_rate": 1.060135330233883e-05, "loss": 0.2732, "step": 1016 }, { "epoch": 0.99, "learning_rate": 1.0585546571652288e-05, "loss": 0.2989, "step": 1017 }, { "epoch": 0.99, "learning_rate": 1.0569738372790956e-05, "loss": 0.3025, "step": 1018 }, { "epoch": 1.0, "learning_rate": 1.055392874539165e-05, "loss": 0.2634, "step": 1019 }, { "epoch": 1.0, "learning_rate": 1.0538117729094766e-05, "loss": 0.3399, "step": 1020 }, { "epoch": 1.0, "learning_rate": 1.0522305363544172e-05, "loss": 0.2801, "step": 1021 }, { "epoch": 1.0, "learning_rate": 1.0506491688387128e-05, "loss": 0.3158, "step": 1022 }, { "epoch": 1.0, "learning_rate": 1.0490676743274181e-05, "loss": 0.2899, "step": 1023 }, { "epoch": 1.0, "learning_rate": 1.0474860567859058e-05, "loss": 0.2949, "step": 1024 }, { "epoch": 1.0, "learning_rate": 1.0459043201798563e-05, "loss": 0.2915, "step": 1025 }, { "epoch": 1.0, "learning_rate": 1.04432246847525e-05, "loss": 0.294, "step": 1026 }, { "epoch": 1.0, "learning_rate": 1.0427405056383548e-05, "loss": 0.2863, "step": 1027 }, { "epoch": 1.0, "learning_rate": 1.0411584356357178e-05, "loss": 0.329, "step": 1028 }, { "epoch": 1.01, "learning_rate": 1.0395762624341544e-05, "loss": 0.2607, "step": 1029 }, { "epoch": 1.01, "learning_rate": 1.0379939900007394e-05, "loss": 0.2888, "step": 1030 }, { "epoch": 1.01, "learning_rate": 1.0364116223027956e-05, "loss": 0.2723, "step": 1031 }, { "epoch": 1.01, "learning_rate": 1.0348291633078851e-05, "loss": 0.2491, "step": 1032 }, { "epoch": 1.01, "learning_rate": 1.0332466169837992e-05, "loss": 0.259, "step": 1033 }, { "epoch": 1.01, "learning_rate": 1.0316639872985471e-05, "loss": 0.2836, "step": 1034 }, { "epoch": 1.01, "learning_rate": 1.0300812782203486e-05, "loss": 0.2803, "step": 1035 }, { "epoch": 1.01, "learning_rate": 1.0284984937176213e-05, "loss": 0.268, "step": 1036 }, { "epoch": 1.01, "learning_rate": 1.0269156377589722e-05, "loss": 0.2912, "step": 1037 }, { "epoch": 1.01, "learning_rate": 1.025332714313188e-05, "loss": 0.2572, "step": 1038 }, { "epoch": 1.02, "learning_rate": 1.023749727349224e-05, "loss": 0.2974, "step": 1039 }, { "epoch": 1.02, "learning_rate": 1.0221666808361947e-05, "loss": 0.2533, "step": 1040 }, { "epoch": 1.02, "learning_rate": 1.0205835787433645e-05, "loss": 0.2855, "step": 1041 }, { "epoch": 1.02, "learning_rate": 1.0190004250401369e-05, "loss": 0.2585, "step": 1042 }, { "epoch": 1.02, "learning_rate": 1.0174172236960447e-05, "loss": 0.2888, "step": 1043 }, { "epoch": 1.02, "learning_rate": 1.0158339786807401e-05, "loss": 0.255, "step": 1044 }, { "epoch": 1.02, "learning_rate": 1.0142506939639847e-05, "loss": 0.2582, "step": 1045 }, { "epoch": 1.02, "learning_rate": 1.0126673735156402e-05, "loss": 0.2404, "step": 1046 }, { "epoch": 1.02, "learning_rate": 1.0110840213056575e-05, "loss": 0.2721, "step": 1047 }, { "epoch": 1.02, "learning_rate": 1.009500641304067e-05, "loss": 0.2714, "step": 1048 }, { "epoch": 1.02, "learning_rate": 1.0079172374809689e-05, "loss": 0.2728, "step": 1049 }, { "epoch": 1.03, "learning_rate": 1.0063338138065235e-05, "loss": 0.2802, "step": 1050 }, { "epoch": 1.03, "learning_rate": 1.0047503742509405e-05, "loss": 0.2626, "step": 1051 }, { "epoch": 1.03, "learning_rate": 1.0031669227844693e-05, "loss": 0.2612, "step": 1052 }, { "epoch": 1.03, "learning_rate": 1.0015834633773893e-05, "loss": 0.2653, "step": 1053 }, { "epoch": 1.03, "learning_rate": 1e-05, "loss": 0.2395, "step": 1054 }, { "epoch": 1.03, "learning_rate": 9.98416536622611e-06, "loss": 0.2506, "step": 1055 }, { "epoch": 1.03, "learning_rate": 9.968330772155312e-06, "loss": 0.2458, "step": 1056 }, { "epoch": 1.03, "learning_rate": 9.9524962574906e-06, "loss": 0.2411, "step": 1057 }, { "epoch": 1.03, "learning_rate": 9.936661861934765e-06, "loss": 0.2548, "step": 1058 }, { "epoch": 1.03, "learning_rate": 9.920827625190311e-06, "loss": 0.2406, "step": 1059 }, { "epoch": 1.04, "learning_rate": 9.904993586959333e-06, "loss": 0.2296, "step": 1060 }, { "epoch": 1.04, "learning_rate": 9.889159786943428e-06, "loss": 0.2761, "step": 1061 }, { "epoch": 1.04, "learning_rate": 9.873326264843601e-06, "loss": 0.2444, "step": 1062 }, { "epoch": 1.04, "learning_rate": 9.857493060360157e-06, "loss": 0.2481, "step": 1063 }, { "epoch": 1.04, "learning_rate": 9.841660213192606e-06, "loss": 0.2666, "step": 1064 }, { "epoch": 1.04, "learning_rate": 9.825827763039558e-06, "loss": 0.254, "step": 1065 }, { "epoch": 1.04, "learning_rate": 9.809995749598633e-06, "loss": 0.2602, "step": 1066 }, { "epoch": 1.04, "learning_rate": 9.794164212566355e-06, "loss": 0.2619, "step": 1067 }, { "epoch": 1.04, "learning_rate": 9.778333191638055e-06, "loss": 0.2306, "step": 1068 }, { "epoch": 1.04, "learning_rate": 9.762502726507764e-06, "loss": 0.2307, "step": 1069 }, { "epoch": 1.05, "learning_rate": 9.746672856868124e-06, "loss": 0.2435, "step": 1070 }, { "epoch": 1.05, "learning_rate": 9.730843622410282e-06, "loss": 0.2508, "step": 1071 }, { "epoch": 1.05, "learning_rate": 9.715015062823789e-06, "loss": 0.1935, "step": 1072 }, { "epoch": 1.05, "learning_rate": 9.699187217796518e-06, "loss": 0.2467, "step": 1073 }, { "epoch": 1.05, "learning_rate": 9.68336012701453e-06, "loss": 0.22, "step": 1074 }, { "epoch": 1.05, "learning_rate": 9.667533830162013e-06, "loss": 0.2552, "step": 1075 }, { "epoch": 1.05, "learning_rate": 9.651708366921152e-06, "loss": 0.2615, "step": 1076 }, { "epoch": 1.05, "learning_rate": 9.635883776972046e-06, "loss": 0.2495, "step": 1077 }, { "epoch": 1.05, "learning_rate": 9.620060099992609e-06, "loss": 0.2355, "step": 1078 }, { "epoch": 1.05, "learning_rate": 9.604237375658458e-06, "loss": 0.2434, "step": 1079 }, { "epoch": 1.06, "learning_rate": 9.588415643642827e-06, "loss": 0.232, "step": 1080 }, { "epoch": 1.06, "learning_rate": 9.572594943616457e-06, "loss": 0.2521, "step": 1081 }, { "epoch": 1.06, "learning_rate": 9.556775315247502e-06, "loss": 0.2398, "step": 1082 }, { "epoch": 1.06, "learning_rate": 9.540956798201439e-06, "loss": 0.2487, "step": 1083 }, { "epoch": 1.06, "learning_rate": 9.525139432140946e-06, "loss": 0.2091, "step": 1084 }, { "epoch": 1.06, "learning_rate": 9.50932325672582e-06, "loss": 0.2155, "step": 1085 }, { "epoch": 1.06, "learning_rate": 9.493508311612874e-06, "loss": 0.225, "step": 1086 }, { "epoch": 1.06, "learning_rate": 9.477694636455833e-06, "loss": 0.2288, "step": 1087 }, { "epoch": 1.06, "learning_rate": 9.46188227090524e-06, "loss": 0.2348, "step": 1088 }, { "epoch": 1.06, "learning_rate": 9.44607125460835e-06, "loss": 0.2145, "step": 1089 }, { "epoch": 1.06, "learning_rate": 9.430261627209044e-06, "loss": 0.2698, "step": 1090 }, { "epoch": 1.07, "learning_rate": 9.414453428347715e-06, "loss": 0.2278, "step": 1091 }, { "epoch": 1.07, "learning_rate": 9.398646697661173e-06, "loss": 0.2417, "step": 1092 }, { "epoch": 1.07, "learning_rate": 9.382841474782546e-06, "loss": 0.2252, "step": 1093 }, { "epoch": 1.07, "learning_rate": 9.367037799341187e-06, "loss": 0.2323, "step": 1094 }, { "epoch": 1.07, "learning_rate": 9.351235710962565e-06, "loss": 0.2258, "step": 1095 }, { "epoch": 1.07, "learning_rate": 9.335435249268165e-06, "loss": 0.2416, "step": 1096 }, { "epoch": 1.07, "learning_rate": 9.3196364538754e-06, "loss": 0.2357, "step": 1097 }, { "epoch": 1.07, "learning_rate": 9.303839364397512e-06, "loss": 0.219, "step": 1098 }, { "epoch": 1.07, "learning_rate": 9.288044020443449e-06, "loss": 0.2319, "step": 1099 }, { "epoch": 1.07, "learning_rate": 9.272250461617794e-06, "loss": 0.226, "step": 1100 }, { "epoch": 1.08, "learning_rate": 9.256458727520648e-06, "loss": 0.2411, "step": 1101 }, { "epoch": 1.08, "learning_rate": 9.24066885774754e-06, "loss": 0.2375, "step": 1102 }, { "epoch": 1.08, "learning_rate": 9.224880891889324e-06, "loss": 0.2686, "step": 1103 }, { "epoch": 1.08, "learning_rate": 9.209094869532082e-06, "loss": 0.2546, "step": 1104 }, { "epoch": 1.08, "learning_rate": 9.193310830257012e-06, "loss": 0.2295, "step": 1105 }, { "epoch": 1.08, "learning_rate": 9.177528813640362e-06, "loss": 0.2389, "step": 1106 }, { "epoch": 1.08, "learning_rate": 9.161748859253288e-06, "loss": 0.2217, "step": 1107 }, { "epoch": 1.08, "learning_rate": 9.145971006661783e-06, "loss": 0.2354, "step": 1108 }, { "epoch": 1.08, "learning_rate": 9.13019529542657e-06, "loss": 0.2494, "step": 1109 }, { "epoch": 1.08, "learning_rate": 9.114421765103e-06, "loss": 0.2391, "step": 1110 }, { "epoch": 1.09, "learning_rate": 9.098650455240959e-06, "loss": 0.2198, "step": 1111 }, { "epoch": 1.09, "learning_rate": 9.082881405384767e-06, "loss": 0.2373, "step": 1112 }, { "epoch": 1.09, "learning_rate": 9.067114655073069e-06, "loss": 0.2167, "step": 1113 }, { "epoch": 1.09, "learning_rate": 9.051350243838757e-06, "loss": 0.219, "step": 1114 }, { "epoch": 1.09, "learning_rate": 9.035588211208847e-06, "loss": 0.2298, "step": 1115 }, { "epoch": 1.09, "learning_rate": 9.019828596704394e-06, "loss": 0.2297, "step": 1116 }, { "epoch": 1.09, "learning_rate": 9.004071439840396e-06, "loss": 0.1967, "step": 1117 }, { "epoch": 1.09, "learning_rate": 8.98831678012568e-06, "loss": 0.2298, "step": 1118 }, { "epoch": 1.09, "learning_rate": 8.972564657062816e-06, "loss": 0.2264, "step": 1119 }, { "epoch": 1.09, "learning_rate": 8.956815110148012e-06, "loss": 0.242, "step": 1120 }, { "epoch": 1.1, "learning_rate": 8.941068178871021e-06, "loss": 0.2587, "step": 1121 }, { "epoch": 1.1, "learning_rate": 8.92532390271503e-06, "loss": 0.215, "step": 1122 }, { "epoch": 1.1, "learning_rate": 8.90958232115658e-06, "loss": 0.2197, "step": 1123 }, { "epoch": 1.1, "learning_rate": 8.893843473665443e-06, "loss": 0.2369, "step": 1124 }, { "epoch": 1.1, "learning_rate": 8.878107399704546e-06, "loss": 0.1944, "step": 1125 }, { "epoch": 1.1, "learning_rate": 8.862374138729854e-06, "loss": 0.2349, "step": 1126 }, { "epoch": 1.1, "learning_rate": 8.846643730190284e-06, "loss": 0.2288, "step": 1127 }, { "epoch": 1.1, "learning_rate": 8.830916213527593e-06, "loss": 0.2132, "step": 1128 }, { "epoch": 1.1, "learning_rate": 8.815191628176304e-06, "loss": 0.2386, "step": 1129 }, { "epoch": 1.1, "learning_rate": 8.799470013563573e-06, "loss": 0.2219, "step": 1130 }, { "epoch": 1.1, "learning_rate": 8.783751409109116e-06, "loss": 0.2542, "step": 1131 }, { "epoch": 1.11, "learning_rate": 8.768035854225098e-06, "loss": 0.2085, "step": 1132 }, { "epoch": 1.11, "learning_rate": 8.752323388316038e-06, "loss": 0.2385, "step": 1133 }, { "epoch": 1.11, "learning_rate": 8.73661405077871e-06, "loss": 0.2332, "step": 1134 }, { "epoch": 1.11, "learning_rate": 8.720907881002047e-06, "loss": 0.2178, "step": 1135 }, { "epoch": 1.11, "learning_rate": 8.705204918367032e-06, "loss": 0.2304, "step": 1136 }, { "epoch": 1.11, "learning_rate": 8.689505202246618e-06, "loss": 0.1939, "step": 1137 }, { "epoch": 1.11, "learning_rate": 8.67380877200561e-06, "loss": 0.2253, "step": 1138 }, { "epoch": 1.11, "learning_rate": 8.658115667000572e-06, "loss": 0.2411, "step": 1139 }, { "epoch": 1.11, "learning_rate": 8.642425926579738e-06, "loss": 0.2127, "step": 1140 }, { "epoch": 1.11, "learning_rate": 8.626739590082897e-06, "loss": 0.2175, "step": 1141 }, { "epoch": 1.12, "learning_rate": 8.611056696841313e-06, "loss": 0.2314, "step": 1142 }, { "epoch": 1.12, "learning_rate": 8.595377286177606e-06, "loss": 0.2078, "step": 1143 }, { "epoch": 1.12, "learning_rate": 8.579701397405668e-06, "loss": 0.2383, "step": 1144 }, { "epoch": 1.12, "learning_rate": 8.564029069830569e-06, "loss": 0.2371, "step": 1145 }, { "epoch": 1.12, "learning_rate": 8.54836034274844e-06, "loss": 0.2226, "step": 1146 }, { "epoch": 1.12, "learning_rate": 8.532695255446384e-06, "loss": 0.2111, "step": 1147 }, { "epoch": 1.12, "learning_rate": 8.517033847202383e-06, "loss": 0.2113, "step": 1148 }, { "epoch": 1.12, "learning_rate": 8.501376157285191e-06, "loss": 0.2051, "step": 1149 }, { "epoch": 1.12, "learning_rate": 8.485722224954237e-06, "loss": 0.2078, "step": 1150 }, { "epoch": 1.12, "learning_rate": 8.47007208945953e-06, "loss": 0.2165, "step": 1151 }, { "epoch": 1.13, "learning_rate": 8.454425790041567e-06, "loss": 0.2029, "step": 1152 }, { "epoch": 1.13, "learning_rate": 8.438783365931216e-06, "loss": 0.217, "step": 1153 }, { "epoch": 1.13, "learning_rate": 8.423144856349631e-06, "loss": 0.1981, "step": 1154 }, { "epoch": 1.13, "learning_rate": 8.407510300508151e-06, "loss": 0.2092, "step": 1155 }, { "epoch": 1.13, "learning_rate": 8.391879737608202e-06, "loss": 0.2143, "step": 1156 }, { "epoch": 1.13, "learning_rate": 8.3762532068412e-06, "loss": 0.2128, "step": 1157 }, { "epoch": 1.13, "learning_rate": 8.36063074738845e-06, "loss": 0.2131, "step": 1158 }, { "epoch": 1.13, "learning_rate": 8.345012398421046e-06, "loss": 0.2032, "step": 1159 }, { "epoch": 1.13, "learning_rate": 8.329398199099778e-06, "loss": 0.199, "step": 1160 }, { "epoch": 1.13, "learning_rate": 8.313788188575032e-06, "loss": 0.2167, "step": 1161 }, { "epoch": 1.14, "learning_rate": 8.29818240598669e-06, "loss": 0.2112, "step": 1162 }, { "epoch": 1.14, "learning_rate": 8.282580890464034e-06, "loss": 0.2123, "step": 1163 }, { "epoch": 1.14, "learning_rate": 8.266983681125647e-06, "loss": 0.2134, "step": 1164 }, { "epoch": 1.14, "learning_rate": 8.25139081707931e-06, "loss": 0.2201, "step": 1165 }, { "epoch": 1.14, "learning_rate": 8.23580233742192e-06, "loss": 0.2423, "step": 1166 }, { "epoch": 1.14, "learning_rate": 8.22021828123936e-06, "loss": 0.2202, "step": 1167 }, { "epoch": 1.14, "learning_rate": 8.20463868760645e-06, "loss": 0.2203, "step": 1168 }, { "epoch": 1.14, "learning_rate": 8.189063595586804e-06, "loss": 0.225, "step": 1169 }, { "epoch": 1.14, "learning_rate": 8.173493044232745e-06, "loss": 0.1941, "step": 1170 }, { "epoch": 1.14, "learning_rate": 8.15792707258522e-06, "loss": 0.1988, "step": 1171 }, { "epoch": 1.14, "learning_rate": 8.142365719673693e-06, "loss": 0.2305, "step": 1172 }, { "epoch": 1.15, "learning_rate": 8.126809024516038e-06, "loss": 0.2048, "step": 1173 }, { "epoch": 1.15, "learning_rate": 8.111257026118461e-06, "loss": 0.2374, "step": 1174 }, { "epoch": 1.15, "learning_rate": 8.09570976347538e-06, "loss": 0.2266, "step": 1175 }, { "epoch": 1.15, "learning_rate": 8.08016727556936e-06, "loss": 0.2083, "step": 1176 }, { "epoch": 1.15, "learning_rate": 8.064629601370968e-06, "loss": 0.2051, "step": 1177 }, { "epoch": 1.15, "learning_rate": 8.04909677983872e-06, "loss": 0.2059, "step": 1178 }, { "epoch": 1.15, "learning_rate": 8.03356884991895e-06, "loss": 0.1942, "step": 1179 }, { "epoch": 1.15, "learning_rate": 8.018045850545744e-06, "loss": 0.2026, "step": 1180 }, { "epoch": 1.15, "learning_rate": 8.002527820640809e-06, "loss": 0.2349, "step": 1181 }, { "epoch": 1.15, "learning_rate": 7.987014799113398e-06, "loss": 0.1985, "step": 1182 }, { "epoch": 1.16, "learning_rate": 7.971506824860216e-06, "loss": 0.2296, "step": 1183 }, { "epoch": 1.16, "learning_rate": 7.956003936765298e-06, "loss": 0.2141, "step": 1184 }, { "epoch": 1.16, "learning_rate": 7.940506173699933e-06, "loss": 0.2147, "step": 1185 }, { "epoch": 1.16, "learning_rate": 7.925013574522556e-06, "loss": 0.208, "step": 1186 }, { "epoch": 1.16, "learning_rate": 7.90952617807866e-06, "loss": 0.1924, "step": 1187 }, { "epoch": 1.16, "learning_rate": 7.894044023200691e-06, "loss": 0.2048, "step": 1188 }, { "epoch": 1.16, "learning_rate": 7.878567148707948e-06, "loss": 0.1999, "step": 1189 }, { "epoch": 1.16, "learning_rate": 7.86309559340649e-06, "loss": 0.2145, "step": 1190 }, { "epoch": 1.16, "learning_rate": 7.847629396089054e-06, "loss": 0.2078, "step": 1191 }, { "epoch": 1.16, "learning_rate": 7.832168595534925e-06, "loss": 0.2223, "step": 1192 }, { "epoch": 1.17, "learning_rate": 7.81671323050986e-06, "loss": 0.1966, "step": 1193 }, { "epoch": 1.17, "learning_rate": 7.801263339765992e-06, "loss": 0.192, "step": 1194 }, { "epoch": 1.17, "learning_rate": 7.785818962041727e-06, "loss": 0.2052, "step": 1195 }, { "epoch": 1.17, "learning_rate": 7.770380136061643e-06, "loss": 0.2138, "step": 1196 }, { "epoch": 1.17, "learning_rate": 7.754946900536403e-06, "loss": 0.2308, "step": 1197 }, { "epoch": 1.17, "learning_rate": 7.739519294162652e-06, "loss": 0.2062, "step": 1198 }, { "epoch": 1.17, "learning_rate": 7.72409735562292e-06, "loss": 0.1983, "step": 1199 }, { "epoch": 1.17, "learning_rate": 7.708681123585525e-06, "loss": 0.2056, "step": 1200 }, { "epoch": 1.17, "learning_rate": 7.693270636704476e-06, "loss": 0.1924, "step": 1201 }, { "epoch": 1.17, "learning_rate": 7.67786593361938e-06, "loss": 0.2151, "step": 1202 }, { "epoch": 1.18, "learning_rate": 7.662467052955337e-06, "loss": 0.2047, "step": 1203 }, { "epoch": 1.18, "learning_rate": 7.647074033322856e-06, "loss": 0.227, "step": 1204 }, { "epoch": 1.18, "learning_rate": 7.631686913317743e-06, "loss": 0.2017, "step": 1205 }, { "epoch": 1.18, "learning_rate": 7.616305731521009e-06, "loss": 0.2202, "step": 1206 }, { "epoch": 1.18, "learning_rate": 7.600930526498788e-06, "loss": 0.2076, "step": 1207 }, { "epoch": 1.18, "learning_rate": 7.585561336802221e-06, "loss": 0.2188, "step": 1208 }, { "epoch": 1.18, "learning_rate": 7.570198200967363e-06, "loss": 0.2184, "step": 1209 }, { "epoch": 1.18, "learning_rate": 7.554841157515091e-06, "loss": 0.1745, "step": 1210 }, { "epoch": 1.18, "learning_rate": 7.539490244951013e-06, "loss": 0.223, "step": 1211 }, { "epoch": 1.18, "learning_rate": 7.524145501765357e-06, "loss": 0.2236, "step": 1212 }, { "epoch": 1.19, "learning_rate": 7.508806966432882e-06, "loss": 0.2008, "step": 1213 }, { "epoch": 1.19, "learning_rate": 7.493474677412795e-06, "loss": 0.2046, "step": 1214 }, { "epoch": 1.19, "learning_rate": 7.4781486731486215e-06, "loss": 0.2001, "step": 1215 }, { "epoch": 1.19, "learning_rate": 7.462828992068144e-06, "loss": 0.2053, "step": 1216 }, { "epoch": 1.19, "learning_rate": 7.447515672583282e-06, "loss": 0.2036, "step": 1217 }, { "epoch": 1.19, "learning_rate": 7.432208753090009e-06, "loss": 0.2103, "step": 1218 }, { "epoch": 1.19, "learning_rate": 7.416908271968246e-06, "loss": 0.1984, "step": 1219 }, { "epoch": 1.19, "learning_rate": 7.401614267581779e-06, "loss": 0.2123, "step": 1220 }, { "epoch": 1.19, "learning_rate": 7.386326778278142e-06, "loss": 0.2017, "step": 1221 }, { "epoch": 1.19, "learning_rate": 7.371045842388552e-06, "loss": 0.1807, "step": 1222 }, { "epoch": 1.19, "learning_rate": 7.355771498227777e-06, "loss": 0.2036, "step": 1223 }, { "epoch": 1.2, "learning_rate": 7.340503784094066e-06, "loss": 0.2133, "step": 1224 }, { "epoch": 1.2, "learning_rate": 7.325242738269039e-06, "loss": 0.1802, "step": 1225 }, { "epoch": 1.2, "learning_rate": 7.3099883990176025e-06, "loss": 0.1934, "step": 1226 }, { "epoch": 1.2, "learning_rate": 7.294740804587838e-06, "loss": 0.1944, "step": 1227 }, { "epoch": 1.2, "learning_rate": 7.279499993210928e-06, "loss": 0.2214, "step": 1228 }, { "epoch": 1.2, "learning_rate": 7.26426600310103e-06, "loss": 0.1838, "step": 1229 }, { "epoch": 1.2, "learning_rate": 7.24903887245522e-06, "loss": 0.2009, "step": 1230 }, { "epoch": 1.2, "learning_rate": 7.233818639453358e-06, "loss": 0.1918, "step": 1231 }, { "epoch": 1.2, "learning_rate": 7.218605342258016e-06, "loss": 0.2135, "step": 1232 }, { "epoch": 1.2, "learning_rate": 7.203399019014374e-06, "loss": 0.1846, "step": 1233 }, { "epoch": 1.21, "learning_rate": 7.188199707850123e-06, "loss": 0.1952, "step": 1234 }, { "epoch": 1.21, "learning_rate": 7.173007446875375e-06, "loss": 0.1844, "step": 1235 }, { "epoch": 1.21, "learning_rate": 7.15782227418257e-06, "loss": 0.1852, "step": 1236 }, { "epoch": 1.21, "learning_rate": 7.1426442278463626e-06, "loss": 0.2067, "step": 1237 }, { "epoch": 1.21, "learning_rate": 7.127473345923553e-06, "loss": 0.2104, "step": 1238 }, { "epoch": 1.21, "learning_rate": 7.112309666452968e-06, "loss": 0.215, "step": 1239 }, { "epoch": 1.21, "learning_rate": 7.097153227455379e-06, "loss": 0.2461, "step": 1240 }, { "epoch": 1.21, "learning_rate": 7.0820040669333975e-06, "loss": 0.1898, "step": 1241 }, { "epoch": 1.21, "learning_rate": 7.066862222871397e-06, "loss": 0.2092, "step": 1242 }, { "epoch": 1.21, "learning_rate": 7.051727733235395e-06, "loss": 0.2046, "step": 1243 }, { "epoch": 1.22, "learning_rate": 7.036600635972971e-06, "loss": 0.1973, "step": 1244 }, { "epoch": 1.22, "learning_rate": 7.021480969013176e-06, "loss": 0.2013, "step": 1245 }, { "epoch": 1.22, "learning_rate": 7.006368770266421e-06, "loss": 0.1879, "step": 1246 }, { "epoch": 1.22, "learning_rate": 6.9912640776243974e-06, "loss": 0.1754, "step": 1247 }, { "epoch": 1.22, "learning_rate": 6.976166928959978e-06, "loss": 0.1992, "step": 1248 }, { "epoch": 1.22, "learning_rate": 6.961077362127111e-06, "loss": 0.2077, "step": 1249 }, { "epoch": 1.22, "learning_rate": 6.945995414960744e-06, "loss": 0.1905, "step": 1250 }, { "epoch": 1.22, "learning_rate": 6.930921125276715e-06, "loss": 0.2068, "step": 1251 }, { "epoch": 1.22, "learning_rate": 6.915854530871657e-06, "loss": 0.2108, "step": 1252 }, { "epoch": 1.22, "learning_rate": 6.900795669522924e-06, "loss": 0.1961, "step": 1253 }, { "epoch": 1.23, "learning_rate": 6.885744578988463e-06, "loss": 0.1882, "step": 1254 }, { "epoch": 1.23, "learning_rate": 6.870701297006746e-06, "loss": 0.2054, "step": 1255 }, { "epoch": 1.23, "learning_rate": 6.855665861296662e-06, "loss": 0.1859, "step": 1256 }, { "epoch": 1.23, "learning_rate": 6.84063830955743e-06, "loss": 0.2025, "step": 1257 }, { "epoch": 1.23, "learning_rate": 6.8256186794685016e-06, "loss": 0.1726, "step": 1258 }, { "epoch": 1.23, "learning_rate": 6.810607008689461e-06, "loss": 0.2002, "step": 1259 }, { "epoch": 1.23, "learning_rate": 6.795603334859935e-06, "loss": 0.1695, "step": 1260 }, { "epoch": 1.23, "learning_rate": 6.78060769559951e-06, "loss": 0.2171, "step": 1261 }, { "epoch": 1.23, "learning_rate": 6.7656201285076195e-06, "loss": 0.1975, "step": 1262 }, { "epoch": 1.23, "learning_rate": 6.7506406711634545e-06, "loss": 0.1961, "step": 1263 }, { "epoch": 1.23, "learning_rate": 6.735669361125874e-06, "loss": 0.2233, "step": 1264 }, { "epoch": 1.24, "learning_rate": 6.720706235933312e-06, "loss": 0.1757, "step": 1265 }, { "epoch": 1.24, "learning_rate": 6.705751333103676e-06, "loss": 0.1795, "step": 1266 }, { "epoch": 1.24, "learning_rate": 6.690804690134259e-06, "loss": 0.1836, "step": 1267 }, { "epoch": 1.24, "learning_rate": 6.675866344501641e-06, "loss": 0.1871, "step": 1268 }, { "epoch": 1.24, "learning_rate": 6.660936333661605e-06, "loss": 0.2182, "step": 1269 }, { "epoch": 1.24, "learning_rate": 6.64601469504903e-06, "loss": 0.1826, "step": 1270 }, { "epoch": 1.24, "learning_rate": 6.631101466077801e-06, "loss": 0.1897, "step": 1271 }, { "epoch": 1.24, "learning_rate": 6.616196684140721e-06, "loss": 0.1959, "step": 1272 }, { "epoch": 1.24, "learning_rate": 6.601300386609412e-06, "loss": 0.1893, "step": 1273 }, { "epoch": 1.24, "learning_rate": 6.5864126108342215e-06, "loss": 0.1771, "step": 1274 }, { "epoch": 1.25, "learning_rate": 6.571533394144127e-06, "loss": 0.1951, "step": 1275 }, { "epoch": 1.25, "learning_rate": 6.556662773846658e-06, "loss": 0.1912, "step": 1276 }, { "epoch": 1.25, "learning_rate": 6.541800787227776e-06, "loss": 0.1655, "step": 1277 }, { "epoch": 1.25, "learning_rate": 6.526947471551799e-06, "loss": 0.1815, "step": 1278 }, { "epoch": 1.25, "learning_rate": 6.512102864061305e-06, "loss": 0.1865, "step": 1279 }, { "epoch": 1.25, "learning_rate": 6.497267001977037e-06, "loss": 0.2028, "step": 1280 }, { "epoch": 1.25, "learning_rate": 6.48243992249781e-06, "loss": 0.2128, "step": 1281 }, { "epoch": 1.25, "learning_rate": 6.4676216628004204e-06, "loss": 0.1873, "step": 1282 }, { "epoch": 1.25, "learning_rate": 6.452812260039542e-06, "loss": 0.2013, "step": 1283 }, { "epoch": 1.25, "learning_rate": 6.4380117513476545e-06, "loss": 0.1969, "step": 1284 }, { "epoch": 1.26, "learning_rate": 6.423220173834923e-06, "loss": 0.1996, "step": 1285 }, { "epoch": 1.26, "learning_rate": 6.40843756458913e-06, "loss": 0.1906, "step": 1286 }, { "epoch": 1.26, "learning_rate": 6.393663960675565e-06, "loss": 0.1868, "step": 1287 }, { "epoch": 1.26, "learning_rate": 6.378899399136937e-06, "loss": 0.1863, "step": 1288 }, { "epoch": 1.26, "learning_rate": 6.3641439169932895e-06, "loss": 0.1935, "step": 1289 }, { "epoch": 1.26, "learning_rate": 6.349397551241894e-06, "loss": 0.1976, "step": 1290 }, { "epoch": 1.26, "learning_rate": 6.3346603388571605e-06, "loss": 0.2012, "step": 1291 }, { "epoch": 1.26, "learning_rate": 6.319932316790565e-06, "loss": 0.1947, "step": 1292 }, { "epoch": 1.26, "learning_rate": 6.305213521970523e-06, "loss": 0.2128, "step": 1293 }, { "epoch": 1.26, "learning_rate": 6.290503991302324e-06, "loss": 0.1965, "step": 1294 }, { "epoch": 1.27, "learning_rate": 6.275803761668019e-06, "loss": 0.2045, "step": 1295 }, { "epoch": 1.27, "learning_rate": 6.261112869926348e-06, "loss": 0.1808, "step": 1296 }, { "epoch": 1.27, "learning_rate": 6.246431352912632e-06, "loss": 0.1774, "step": 1297 }, { "epoch": 1.27, "learning_rate": 6.231759247438689e-06, "loss": 0.1816, "step": 1298 }, { "epoch": 1.27, "learning_rate": 6.217096590292734e-06, "loss": 0.2092, "step": 1299 }, { "epoch": 1.27, "learning_rate": 6.202443418239301e-06, "loss": 0.2027, "step": 1300 }, { "epoch": 1.27, "learning_rate": 6.187799768019134e-06, "loss": 0.1889, "step": 1301 }, { "epoch": 1.27, "learning_rate": 6.173165676349103e-06, "loss": 0.1846, "step": 1302 }, { "epoch": 1.27, "learning_rate": 6.158541179922113e-06, "loss": 0.2045, "step": 1303 }, { "epoch": 1.27, "learning_rate": 6.143926315407011e-06, "loss": 0.1836, "step": 1304 }, { "epoch": 1.27, "learning_rate": 6.1293211194484895e-06, "loss": 0.1992, "step": 1305 }, { "epoch": 1.28, "learning_rate": 6.114725628666997e-06, "loss": 0.1824, "step": 1306 }, { "epoch": 1.28, "learning_rate": 6.1001398796586644e-06, "loss": 0.1986, "step": 1307 }, { "epoch": 1.28, "learning_rate": 6.085563908995174e-06, "loss": 0.2066, "step": 1308 }, { "epoch": 1.28, "learning_rate": 6.070997753223703e-06, "loss": 0.1864, "step": 1309 }, { "epoch": 1.28, "learning_rate": 6.056441448866817e-06, "loss": 0.182, "step": 1310 }, { "epoch": 1.28, "learning_rate": 6.041895032422377e-06, "loss": 0.1883, "step": 1311 }, { "epoch": 1.28, "learning_rate": 6.027358540363457e-06, "loss": 0.175, "step": 1312 }, { "epoch": 1.28, "learning_rate": 6.012832009138243e-06, "loss": 0.1846, "step": 1313 }, { "epoch": 1.28, "learning_rate": 5.998315475169942e-06, "loss": 0.1837, "step": 1314 }, { "epoch": 1.28, "learning_rate": 5.983808974856711e-06, "loss": 0.1748, "step": 1315 }, { "epoch": 1.29, "learning_rate": 5.969312544571529e-06, "loss": 0.1918, "step": 1316 }, { "epoch": 1.29, "learning_rate": 5.9548262206621375e-06, "loss": 0.2084, "step": 1317 }, { "epoch": 1.29, "learning_rate": 5.94035003945093e-06, "loss": 0.1851, "step": 1318 }, { "epoch": 1.29, "learning_rate": 5.925884037234879e-06, "loss": 0.2109, "step": 1319 }, { "epoch": 1.29, "learning_rate": 5.911428250285422e-06, "loss": 0.2137, "step": 1320 }, { "epoch": 1.29, "learning_rate": 5.8969827148483935e-06, "loss": 0.2027, "step": 1321 }, { "epoch": 1.29, "learning_rate": 5.88254746714392e-06, "loss": 0.2062, "step": 1322 }, { "epoch": 1.29, "learning_rate": 5.868122543366332e-06, "loss": 0.2082, "step": 1323 }, { "epoch": 1.29, "learning_rate": 5.853707979684077e-06, "loss": 0.1805, "step": 1324 }, { "epoch": 1.29, "learning_rate": 5.8393038122396205e-06, "loss": 0.1986, "step": 1325 }, { "epoch": 1.3, "learning_rate": 5.824910077149372e-06, "loss": 0.1927, "step": 1326 }, { "epoch": 1.3, "learning_rate": 5.810526810503567e-06, "loss": 0.1873, "step": 1327 }, { "epoch": 1.3, "learning_rate": 5.796154048366209e-06, "loss": 0.1875, "step": 1328 }, { "epoch": 1.3, "learning_rate": 5.7817918267749505e-06, "loss": 0.16, "step": 1329 }, { "epoch": 1.3, "learning_rate": 5.76744018174102e-06, "loss": 0.1904, "step": 1330 }, { "epoch": 1.3, "learning_rate": 5.753099149249133e-06, "loss": 0.1966, "step": 1331 }, { "epoch": 1.3, "learning_rate": 5.738768765257386e-06, "loss": 0.1724, "step": 1332 }, { "epoch": 1.3, "learning_rate": 5.724449065697182e-06, "loss": 0.1686, "step": 1333 }, { "epoch": 1.3, "learning_rate": 5.7101400864731294e-06, "loss": 0.1923, "step": 1334 }, { "epoch": 1.3, "learning_rate": 5.69584186346296e-06, "loss": 0.2012, "step": 1335 }, { "epoch": 1.31, "learning_rate": 5.681554432517435e-06, "loss": 0.2104, "step": 1336 }, { "epoch": 1.31, "learning_rate": 5.667277829460254e-06, "loss": 0.1734, "step": 1337 }, { "epoch": 1.31, "learning_rate": 5.6530120900879774e-06, "loss": 0.1664, "step": 1338 }, { "epoch": 1.31, "learning_rate": 5.638757250169913e-06, "loss": 0.2323, "step": 1339 }, { "epoch": 1.31, "learning_rate": 5.6245133454480446e-06, "loss": 0.1894, "step": 1340 }, { "epoch": 1.31, "learning_rate": 5.610280411636941e-06, "loss": 0.1947, "step": 1341 }, { "epoch": 1.31, "learning_rate": 5.5960584844236565e-06, "loss": 0.1551, "step": 1342 }, { "epoch": 1.31, "learning_rate": 5.581847599467658e-06, "loss": 0.2261, "step": 1343 }, { "epoch": 1.31, "learning_rate": 5.5676477924007165e-06, "loss": 0.1769, "step": 1344 }, { "epoch": 1.31, "learning_rate": 5.553459098826828e-06, "loss": 0.1804, "step": 1345 }, { "epoch": 1.31, "learning_rate": 5.539281554322126e-06, "loss": 0.1765, "step": 1346 }, { "epoch": 1.32, "learning_rate": 5.5251151944347825e-06, "loss": 0.1809, "step": 1347 }, { "epoch": 1.32, "learning_rate": 5.510960054684942e-06, "loss": 0.1847, "step": 1348 }, { "epoch": 1.32, "learning_rate": 5.496816170564597e-06, "loss": 0.1849, "step": 1349 }, { "epoch": 1.32, "learning_rate": 5.482683577537529e-06, "loss": 0.2178, "step": 1350 }, { "epoch": 1.32, "learning_rate": 5.468562311039205e-06, "loss": 0.1784, "step": 1351 }, { "epoch": 1.32, "learning_rate": 5.4544524064766944e-06, "loss": 0.1757, "step": 1352 }, { "epoch": 1.32, "learning_rate": 5.440353899228572e-06, "loss": 0.2012, "step": 1353 }, { "epoch": 1.32, "learning_rate": 5.426266824644848e-06, "loss": 0.2123, "step": 1354 }, { "epoch": 1.32, "learning_rate": 5.412191218046856e-06, "loss": 0.2026, "step": 1355 }, { "epoch": 1.32, "learning_rate": 5.3981271147271786e-06, "loss": 0.1904, "step": 1356 }, { "epoch": 1.33, "learning_rate": 5.384074549949554e-06, "loss": 0.2211, "step": 1357 }, { "epoch": 1.33, "learning_rate": 5.370033558948793e-06, "loss": 0.1837, "step": 1358 }, { "epoch": 1.33, "learning_rate": 5.356004176930683e-06, "loss": 0.1779, "step": 1359 }, { "epoch": 1.33, "learning_rate": 5.341986439071907e-06, "loss": 0.1972, "step": 1360 }, { "epoch": 1.33, "learning_rate": 5.327980380519942e-06, "loss": 0.1912, "step": 1361 }, { "epoch": 1.33, "learning_rate": 5.313986036393e-06, "loss": 0.1715, "step": 1362 }, { "epoch": 1.33, "learning_rate": 5.300003441779904e-06, "loss": 0.1735, "step": 1363 }, { "epoch": 1.33, "learning_rate": 5.286032631740023e-06, "loss": 0.1963, "step": 1364 }, { "epoch": 1.33, "learning_rate": 5.272073641303177e-06, "loss": 0.2037, "step": 1365 }, { "epoch": 1.33, "learning_rate": 5.25812650546955e-06, "loss": 0.2105, "step": 1366 }, { "epoch": 1.34, "learning_rate": 5.244191259209602e-06, "loss": 0.2025, "step": 1367 }, { "epoch": 1.34, "learning_rate": 5.230267937463977e-06, "loss": 0.18, "step": 1368 }, { "epoch": 1.34, "learning_rate": 5.216356575143436e-06, "loss": 0.1671, "step": 1369 }, { "epoch": 1.34, "learning_rate": 5.202457207128736e-06, "loss": 0.1789, "step": 1370 }, { "epoch": 1.34, "learning_rate": 5.188569868270566e-06, "loss": 0.1579, "step": 1371 }, { "epoch": 1.34, "learning_rate": 5.1746945933894555e-06, "loss": 0.1773, "step": 1372 }, { "epoch": 1.34, "learning_rate": 5.160831417275683e-06, "loss": 0.1904, "step": 1373 }, { "epoch": 1.34, "learning_rate": 5.146980374689192e-06, "loss": 0.1626, "step": 1374 }, { "epoch": 1.34, "learning_rate": 5.133141500359502e-06, "loss": 0.2017, "step": 1375 }, { "epoch": 1.34, "learning_rate": 5.11931482898562e-06, "loss": 0.1692, "step": 1376 }, { "epoch": 1.35, "learning_rate": 5.105500395235965e-06, "loss": 0.1918, "step": 1377 }, { "epoch": 1.35, "learning_rate": 5.091698233748264e-06, "loss": 0.193, "step": 1378 }, { "epoch": 1.35, "learning_rate": 5.077908379129475e-06, "loss": 0.1686, "step": 1379 }, { "epoch": 1.35, "learning_rate": 5.064130865955696e-06, "loss": 0.1777, "step": 1380 }, { "epoch": 1.35, "learning_rate": 5.050365728772084e-06, "loss": 0.1739, "step": 1381 }, { "epoch": 1.35, "learning_rate": 5.0366130020927625e-06, "loss": 0.161, "step": 1382 }, { "epoch": 1.35, "learning_rate": 5.022872720400741e-06, "loss": 0.177, "step": 1383 }, { "epoch": 1.35, "learning_rate": 5.009144918147817e-06, "loss": 0.196, "step": 1384 }, { "epoch": 1.35, "learning_rate": 4.995429629754509e-06, "loss": 0.1843, "step": 1385 }, { "epoch": 1.35, "learning_rate": 4.981726889609952e-06, "loss": 0.1831, "step": 1386 }, { "epoch": 1.36, "learning_rate": 4.968036732071818e-06, "loss": 0.194, "step": 1387 }, { "epoch": 1.36, "learning_rate": 4.954359191466232e-06, "loss": 0.1698, "step": 1388 }, { "epoch": 1.36, "learning_rate": 4.940694302087679e-06, "loss": 0.1636, "step": 1389 }, { "epoch": 1.36, "learning_rate": 4.9270420981989295e-06, "loss": 0.1701, "step": 1390 }, { "epoch": 1.36, "learning_rate": 4.913402614030944e-06, "loss": 0.1806, "step": 1391 }, { "epoch": 1.36, "learning_rate": 4.899775883782784e-06, "loss": 0.1768, "step": 1392 }, { "epoch": 1.36, "learning_rate": 4.8861619416215475e-06, "loss": 0.1668, "step": 1393 }, { "epoch": 1.36, "learning_rate": 4.872560821682256e-06, "loss": 0.1815, "step": 1394 }, { "epoch": 1.36, "learning_rate": 4.858972558067784e-06, "loss": 0.1767, "step": 1395 }, { "epoch": 1.36, "learning_rate": 4.84539718484877e-06, "loss": 0.1785, "step": 1396 }, { "epoch": 1.36, "learning_rate": 4.831834736063533e-06, "loss": 0.1642, "step": 1397 }, { "epoch": 1.37, "learning_rate": 4.818285245717984e-06, "loss": 0.161, "step": 1398 }, { "epoch": 1.37, "learning_rate": 4.804748747785542e-06, "loss": 0.1806, "step": 1399 }, { "epoch": 1.37, "learning_rate": 4.791225276207058e-06, "loss": 0.1675, "step": 1400 }, { "epoch": 1.37, "learning_rate": 4.77771486489071e-06, "loss": 0.1777, "step": 1401 }, { "epoch": 1.37, "learning_rate": 4.764217547711935e-06, "loss": 0.1893, "step": 1402 }, { "epoch": 1.37, "learning_rate": 4.750733358513335e-06, "loss": 0.185, "step": 1403 }, { "epoch": 1.37, "learning_rate": 4.7372623311045995e-06, "loss": 0.2085, "step": 1404 }, { "epoch": 1.37, "learning_rate": 4.723804499262414e-06, "loss": 0.1611, "step": 1405 }, { "epoch": 1.37, "learning_rate": 4.710359896730379e-06, "loss": 0.1671, "step": 1406 }, { "epoch": 1.37, "learning_rate": 4.696928557218919e-06, "loss": 0.1932, "step": 1407 }, { "epoch": 1.38, "learning_rate": 4.683510514405219e-06, "loss": 0.1829, "step": 1408 }, { "epoch": 1.38, "learning_rate": 4.670105801933106e-06, "loss": 0.1801, "step": 1409 }, { "epoch": 1.38, "learning_rate": 4.6567144534129926e-06, "loss": 0.1888, "step": 1410 }, { "epoch": 1.38, "learning_rate": 4.643336502421783e-06, "loss": 0.2027, "step": 1411 }, { "epoch": 1.38, "learning_rate": 4.629971982502786e-06, "loss": 0.1931, "step": 1412 }, { "epoch": 1.38, "learning_rate": 4.616620927165635e-06, "loss": 0.186, "step": 1413 }, { "epoch": 1.38, "learning_rate": 4.603283369886205e-06, "loss": 0.1726, "step": 1414 }, { "epoch": 1.38, "learning_rate": 4.5899593441065195e-06, "loss": 0.1704, "step": 1415 }, { "epoch": 1.38, "learning_rate": 4.576648883234686e-06, "loss": 0.1781, "step": 1416 }, { "epoch": 1.38, "learning_rate": 4.563352020644791e-06, "loss": 0.1702, "step": 1417 }, { "epoch": 1.39, "learning_rate": 4.550068789676826e-06, "loss": 0.1723, "step": 1418 }, { "epoch": 1.39, "learning_rate": 4.536799223636604e-06, "loss": 0.1732, "step": 1419 }, { "epoch": 1.39, "learning_rate": 4.523543355795676e-06, "loss": 0.1745, "step": 1420 }, { "epoch": 1.39, "learning_rate": 4.510301219391245e-06, "loss": 0.1556, "step": 1421 }, { "epoch": 1.39, "learning_rate": 4.497072847626087e-06, "loss": 0.1695, "step": 1422 }, { "epoch": 1.39, "learning_rate": 4.483858273668464e-06, "loss": 0.1956, "step": 1423 }, { "epoch": 1.39, "learning_rate": 4.470657530652042e-06, "loss": 0.1761, "step": 1424 }, { "epoch": 1.39, "learning_rate": 4.457470651675806e-06, "loss": 0.1881, "step": 1425 }, { "epoch": 1.39, "learning_rate": 4.444297669803981e-06, "loss": 0.1771, "step": 1426 }, { "epoch": 1.39, "learning_rate": 4.431138618065942e-06, "loss": 0.1977, "step": 1427 }, { "epoch": 1.4, "learning_rate": 4.417993529456148e-06, "loss": 0.1605, "step": 1428 }, { "epoch": 1.4, "learning_rate": 4.404862436934037e-06, "loss": 0.1986, "step": 1429 }, { "epoch": 1.4, "learning_rate": 4.391745373423957e-06, "loss": 0.1797, "step": 1430 }, { "epoch": 1.4, "learning_rate": 4.378642371815078e-06, "loss": 0.1582, "step": 1431 }, { "epoch": 1.4, "learning_rate": 4.365553464961313e-06, "loss": 0.1595, "step": 1432 }, { "epoch": 1.4, "learning_rate": 4.3524786856812406e-06, "loss": 0.1706, "step": 1433 }, { "epoch": 1.4, "learning_rate": 4.339418066758008e-06, "loss": 0.1564, "step": 1434 }, { "epoch": 1.4, "learning_rate": 4.32637164093926e-06, "loss": 0.1803, "step": 1435 }, { "epoch": 1.4, "learning_rate": 4.313339440937055e-06, "loss": 0.1725, "step": 1436 }, { "epoch": 1.4, "learning_rate": 4.300321499427782e-06, "loss": 0.1743, "step": 1437 }, { "epoch": 1.4, "learning_rate": 4.287317849052075e-06, "loss": 0.1718, "step": 1438 }, { "epoch": 1.41, "learning_rate": 4.274328522414747e-06, "loss": 0.1652, "step": 1439 }, { "epoch": 1.41, "learning_rate": 4.261353552084682e-06, "loss": 0.1715, "step": 1440 }, { "epoch": 1.41, "learning_rate": 4.248392970594774e-06, "loss": 0.1621, "step": 1441 }, { "epoch": 1.41, "learning_rate": 4.2354468104418415e-06, "loss": 0.1827, "step": 1442 }, { "epoch": 1.41, "learning_rate": 4.2225151040865375e-06, "loss": 0.1637, "step": 1443 }, { "epoch": 1.41, "learning_rate": 4.209597883953278e-06, "loss": 0.1662, "step": 1444 }, { "epoch": 1.41, "learning_rate": 4.196695182430157e-06, "loss": 0.1714, "step": 1445 }, { "epoch": 1.41, "learning_rate": 4.18380703186886e-06, "loss": 0.1603, "step": 1446 }, { "epoch": 1.41, "learning_rate": 4.170933464584601e-06, "loss": 0.176, "step": 1447 }, { "epoch": 1.41, "learning_rate": 4.158074512856014e-06, "loss": 0.1802, "step": 1448 }, { "epoch": 1.42, "learning_rate": 4.145230208925094e-06, "loss": 0.173, "step": 1449 }, { "epoch": 1.42, "learning_rate": 4.132400584997106e-06, "loss": 0.1603, "step": 1450 }, { "epoch": 1.42, "learning_rate": 4.1195856732405094e-06, "loss": 0.1659, "step": 1451 }, { "epoch": 1.42, "learning_rate": 4.106785505786872e-06, "loss": 0.1681, "step": 1452 }, { "epoch": 1.42, "learning_rate": 4.094000114730795e-06, "loss": 0.1591, "step": 1453 }, { "epoch": 1.42, "learning_rate": 4.081229532129826e-06, "loss": 0.1823, "step": 1454 }, { "epoch": 1.42, "learning_rate": 4.068473790004393e-06, "loss": 0.182, "step": 1455 }, { "epoch": 1.42, "learning_rate": 4.055732920337699e-06, "loss": 0.1608, "step": 1456 }, { "epoch": 1.42, "learning_rate": 4.043006955075667e-06, "loss": 0.1748, "step": 1457 }, { "epoch": 1.42, "learning_rate": 4.030295926126845e-06, "loss": 0.1798, "step": 1458 }, { "epoch": 1.43, "learning_rate": 4.0175998653623295e-06, "loss": 0.166, "step": 1459 }, { "epoch": 1.43, "learning_rate": 4.004918804615689e-06, "loss": 0.1702, "step": 1460 }, { "epoch": 1.43, "learning_rate": 3.992252775682877e-06, "loss": 0.165, "step": 1461 }, { "epoch": 1.43, "learning_rate": 3.979601810322169e-06, "loss": 0.1686, "step": 1462 }, { "epoch": 1.43, "learning_rate": 3.966965940254057e-06, "loss": 0.192, "step": 1463 }, { "epoch": 1.43, "learning_rate": 3.954345197161188e-06, "loss": 0.1777, "step": 1464 }, { "epoch": 1.43, "learning_rate": 3.941739612688284e-06, "loss": 0.1657, "step": 1465 }, { "epoch": 1.43, "learning_rate": 3.929149218442052e-06, "loss": 0.1765, "step": 1466 }, { "epoch": 1.43, "learning_rate": 3.91657404599112e-06, "loss": 0.1726, "step": 1467 }, { "epoch": 1.43, "learning_rate": 3.904014126865943e-06, "loss": 0.1539, "step": 1468 }, { "epoch": 1.44, "learning_rate": 3.891469492558728e-06, "loss": 0.1523, "step": 1469 }, { "epoch": 1.44, "learning_rate": 3.878940174523371e-06, "loss": 0.1955, "step": 1470 }, { "epoch": 1.44, "learning_rate": 3.866426204175353e-06, "loss": 0.164, "step": 1471 }, { "epoch": 1.44, "learning_rate": 3.8539276128916736e-06, "loss": 0.1713, "step": 1472 }, { "epoch": 1.44, "learning_rate": 3.841444432010775e-06, "loss": 0.1499, "step": 1473 }, { "epoch": 1.44, "learning_rate": 3.828976692832458e-06, "loss": 0.1707, "step": 1474 }, { "epoch": 1.44, "learning_rate": 3.816524426617807e-06, "loss": 0.1838, "step": 1475 }, { "epoch": 1.44, "learning_rate": 3.804087664589108e-06, "loss": 0.1704, "step": 1476 }, { "epoch": 1.44, "learning_rate": 3.791666437929771e-06, "loss": 0.1866, "step": 1477 }, { "epoch": 1.44, "learning_rate": 3.7792607777842626e-06, "loss": 0.1658, "step": 1478 }, { "epoch": 1.44, "learning_rate": 3.7668707152580097e-06, "loss": 0.1873, "step": 1479 }, { "epoch": 1.45, "learning_rate": 3.754496281417331e-06, "loss": 0.171, "step": 1480 }, { "epoch": 1.45, "learning_rate": 3.742137507289363e-06, "loss": 0.1499, "step": 1481 }, { "epoch": 1.45, "learning_rate": 3.729794423861971e-06, "loss": 0.1784, "step": 1482 }, { "epoch": 1.45, "learning_rate": 3.717467062083685e-06, "loss": 0.1784, "step": 1483 }, { "epoch": 1.45, "learning_rate": 3.7051554528636114e-06, "loss": 0.1679, "step": 1484 }, { "epoch": 1.45, "learning_rate": 3.6928596270713558e-06, "loss": 0.1652, "step": 1485 }, { "epoch": 1.45, "learning_rate": 3.680579615536961e-06, "loss": 0.1934, "step": 1486 }, { "epoch": 1.45, "learning_rate": 3.6683154490508064e-06, "loss": 0.1893, "step": 1487 }, { "epoch": 1.45, "learning_rate": 3.6560671583635467e-06, "loss": 0.1832, "step": 1488 }, { "epoch": 1.45, "learning_rate": 3.643834774186029e-06, "loss": 0.1615, "step": 1489 }, { "epoch": 1.46, "learning_rate": 3.631618327189218e-06, "loss": 0.1655, "step": 1490 }, { "epoch": 1.46, "learning_rate": 3.6194178480041174e-06, "loss": 0.1725, "step": 1491 }, { "epoch": 1.46, "learning_rate": 3.607233367221691e-06, "loss": 0.1722, "step": 1492 }, { "epoch": 1.46, "learning_rate": 3.5950649153927997e-06, "loss": 0.1632, "step": 1493 }, { "epoch": 1.46, "learning_rate": 3.5829125230281014e-06, "loss": 0.1773, "step": 1494 }, { "epoch": 1.46, "learning_rate": 3.5707762205979946e-06, "loss": 0.1526, "step": 1495 }, { "epoch": 1.46, "learning_rate": 3.558656038532532e-06, "loss": 0.1588, "step": 1496 }, { "epoch": 1.46, "learning_rate": 3.5465520072213455e-06, "loss": 0.1666, "step": 1497 }, { "epoch": 1.46, "learning_rate": 3.5344641570135742e-06, "loss": 0.1598, "step": 1498 }, { "epoch": 1.46, "learning_rate": 3.5223925182177833e-06, "loss": 0.1597, "step": 1499 }, { "epoch": 1.47, "learning_rate": 3.510337121101888e-06, "loss": 0.1825, "step": 1500 }, { "epoch": 1.47, "learning_rate": 3.4982979958930896e-06, "loss": 0.1778, "step": 1501 }, { "epoch": 1.47, "learning_rate": 3.48627517277778e-06, "loss": 0.1807, "step": 1502 }, { "epoch": 1.47, "learning_rate": 3.4742686819014782e-06, "loss": 0.1712, "step": 1503 }, { "epoch": 1.47, "learning_rate": 3.462278553368753e-06, "loss": 0.1692, "step": 1504 }, { "epoch": 1.47, "learning_rate": 3.4503048172431495e-06, "loss": 0.1644, "step": 1505 }, { "epoch": 1.47, "learning_rate": 3.4383475035471026e-06, "loss": 0.1848, "step": 1506 }, { "epoch": 1.47, "learning_rate": 3.426406642261885e-06, "loss": 0.1487, "step": 1507 }, { "epoch": 1.47, "learning_rate": 3.4144822633275042e-06, "loss": 0.1933, "step": 1508 }, { "epoch": 1.47, "learning_rate": 3.402574396642646e-06, "loss": 0.1602, "step": 1509 }, { "epoch": 1.48, "learning_rate": 3.3906830720645943e-06, "loss": 0.1563, "step": 1510 }, { "epoch": 1.48, "learning_rate": 3.378808319409149e-06, "loss": 0.1667, "step": 1511 }, { "epoch": 1.48, "learning_rate": 3.3669501684505734e-06, "loss": 0.1753, "step": 1512 }, { "epoch": 1.48, "learning_rate": 3.3551086489214913e-06, "loss": 0.1665, "step": 1513 }, { "epoch": 1.48, "learning_rate": 3.343283790512829e-06, "loss": 0.1685, "step": 1514 }, { "epoch": 1.48, "learning_rate": 3.331475622873738e-06, "loss": 0.1341, "step": 1515 }, { "epoch": 1.48, "learning_rate": 3.319684175611517e-06, "loss": 0.1712, "step": 1516 }, { "epoch": 1.48, "learning_rate": 3.30790947829155e-06, "loss": 0.1747, "step": 1517 }, { "epoch": 1.48, "learning_rate": 3.296151560437214e-06, "loss": 0.1719, "step": 1518 }, { "epoch": 1.48, "learning_rate": 3.284410451529816e-06, "loss": 0.1483, "step": 1519 }, { "epoch": 1.48, "learning_rate": 3.2726861810085163e-06, "loss": 0.1713, "step": 1520 }, { "epoch": 1.49, "learning_rate": 3.2609787782702595e-06, "loss": 0.1594, "step": 1521 }, { "epoch": 1.49, "learning_rate": 3.2492882726696907e-06, "loss": 0.1686, "step": 1522 }, { "epoch": 1.49, "learning_rate": 3.237614693519089e-06, "loss": 0.1661, "step": 1523 }, { "epoch": 1.49, "learning_rate": 3.225958070088301e-06, "loss": 0.1786, "step": 1524 }, { "epoch": 1.49, "learning_rate": 3.2143184316046485e-06, "loss": 0.1507, "step": 1525 }, { "epoch": 1.49, "learning_rate": 3.2026958072528715e-06, "loss": 0.1596, "step": 1526 }, { "epoch": 1.49, "learning_rate": 3.191090226175049e-06, "loss": 0.1667, "step": 1527 }, { "epoch": 1.49, "learning_rate": 3.179501717470522e-06, "loss": 0.186, "step": 1528 }, { "epoch": 1.49, "learning_rate": 3.167930310195834e-06, "loss": 0.1839, "step": 1529 }, { "epoch": 1.49, "learning_rate": 3.15637603336464e-06, "loss": 0.1708, "step": 1530 }, { "epoch": 1.5, "learning_rate": 3.1448389159476433e-06, "loss": 0.178, "step": 1531 }, { "epoch": 1.5, "learning_rate": 3.1333189868725343e-06, "loss": 0.1761, "step": 1532 }, { "epoch": 1.5, "learning_rate": 3.1218162750238933e-06, "loss": 0.1577, "step": 1533 }, { "epoch": 1.5, "learning_rate": 3.110330809243134e-06, "loss": 0.1663, "step": 1534 }, { "epoch": 1.5, "learning_rate": 3.098862618328431e-06, "loss": 0.161, "step": 1535 }, { "epoch": 1.5, "learning_rate": 3.087411731034641e-06, "loss": 0.158, "step": 1536 }, { "epoch": 1.5, "learning_rate": 3.0759781760732365e-06, "loss": 0.1492, "step": 1537 }, { "epoch": 1.5, "learning_rate": 3.064561982112232e-06, "loss": 0.1671, "step": 1538 }, { "epoch": 1.5, "learning_rate": 3.053163177776106e-06, "loss": 0.169, "step": 1539 }, { "epoch": 1.5, "learning_rate": 3.0417817916457482e-06, "loss": 0.1785, "step": 1540 }, { "epoch": 1.51, "learning_rate": 3.0304178522583626e-06, "loss": 0.1724, "step": 1541 }, { "epoch": 1.51, "learning_rate": 3.0190713881074106e-06, "loss": 0.1609, "step": 1542 }, { "epoch": 1.51, "learning_rate": 3.007742427642539e-06, "loss": 0.1673, "step": 1543 }, { "epoch": 1.51, "learning_rate": 2.9964309992695053e-06, "loss": 0.1605, "step": 1544 }, { "epoch": 1.51, "learning_rate": 2.985137131350109e-06, "loss": 0.1756, "step": 1545 }, { "epoch": 1.51, "learning_rate": 2.973860852202117e-06, "loss": 0.1729, "step": 1546 }, { "epoch": 1.51, "learning_rate": 2.962602190099193e-06, "loss": 0.1835, "step": 1547 }, { "epoch": 1.51, "learning_rate": 2.9513611732708404e-06, "loss": 0.1666, "step": 1548 }, { "epoch": 1.51, "learning_rate": 2.9401378299023043e-06, "loss": 0.1819, "step": 1549 }, { "epoch": 1.51, "learning_rate": 2.9289321881345257e-06, "loss": 0.193, "step": 1550 }, { "epoch": 1.52, "learning_rate": 2.917744276064056e-06, "loss": 0.1868, "step": 1551 }, { "epoch": 1.52, "learning_rate": 2.9065741217429964e-06, "loss": 0.1793, "step": 1552 }, { "epoch": 1.52, "learning_rate": 2.8954217531789186e-06, "loss": 0.1802, "step": 1553 }, { "epoch": 1.52, "learning_rate": 2.8842871983348e-06, "loss": 0.1974, "step": 1554 }, { "epoch": 1.52, "learning_rate": 2.8731704851289598e-06, "loss": 0.1728, "step": 1555 }, { "epoch": 1.52, "learning_rate": 2.8620716414349714e-06, "loss": 0.1742, "step": 1556 }, { "epoch": 1.52, "learning_rate": 2.85099069508161e-06, "loss": 0.1726, "step": 1557 }, { "epoch": 1.52, "learning_rate": 2.8399276738527716e-06, "loss": 0.1853, "step": 1558 }, { "epoch": 1.52, "learning_rate": 2.8288826054874095e-06, "loss": 0.1691, "step": 1559 }, { "epoch": 1.52, "learning_rate": 2.817855517679464e-06, "loss": 0.1532, "step": 1560 }, { "epoch": 1.53, "learning_rate": 2.806846438077787e-06, "loss": 0.1395, "step": 1561 }, { "epoch": 1.53, "learning_rate": 2.795855394286081e-06, "loss": 0.1592, "step": 1562 }, { "epoch": 1.53, "learning_rate": 2.7848824138628295e-06, "loss": 0.1532, "step": 1563 }, { "epoch": 1.53, "learning_rate": 2.7739275243212183e-06, "loss": 0.1701, "step": 1564 }, { "epoch": 1.53, "learning_rate": 2.7629907531290767e-06, "loss": 0.1537, "step": 1565 }, { "epoch": 1.53, "learning_rate": 2.7520721277088023e-06, "loss": 0.1737, "step": 1566 }, { "epoch": 1.53, "learning_rate": 2.7411716754372964e-06, "loss": 0.1684, "step": 1567 }, { "epoch": 1.53, "learning_rate": 2.730289423645894e-06, "loss": 0.1599, "step": 1568 }, { "epoch": 1.53, "learning_rate": 2.719425399620296e-06, "loss": 0.1667, "step": 1569 }, { "epoch": 1.53, "learning_rate": 2.7085796306004907e-06, "loss": 0.1542, "step": 1570 }, { "epoch": 1.53, "learning_rate": 2.697752143780713e-06, "loss": 0.1524, "step": 1571 }, { "epoch": 1.54, "learning_rate": 2.6869429663093405e-06, "loss": 0.1859, "step": 1572 }, { "epoch": 1.54, "learning_rate": 2.676152125288851e-06, "loss": 0.1693, "step": 1573 }, { "epoch": 1.54, "learning_rate": 2.665379647775743e-06, "loss": 0.1644, "step": 1574 }, { "epoch": 1.54, "learning_rate": 2.6546255607804726e-06, "loss": 0.1604, "step": 1575 }, { "epoch": 1.54, "learning_rate": 2.643889891267386e-06, "loss": 0.1644, "step": 1576 }, { "epoch": 1.54, "learning_rate": 2.633172666154645e-06, "loss": 0.1785, "step": 1577 }, { "epoch": 1.54, "learning_rate": 2.6224739123141684e-06, "loss": 0.1525, "step": 1578 }, { "epoch": 1.54, "learning_rate": 2.611793656571565e-06, "loss": 0.1683, "step": 1579 }, { "epoch": 1.54, "learning_rate": 2.601131925706054e-06, "loss": 0.153, "step": 1580 }, { "epoch": 1.54, "learning_rate": 2.5904887464504115e-06, "loss": 0.1676, "step": 1581 }, { "epoch": 1.55, "learning_rate": 2.5798641454908945e-06, "loss": 0.1714, "step": 1582 }, { "epoch": 1.55, "learning_rate": 2.569258149467181e-06, "loss": 0.18, "step": 1583 }, { "epoch": 1.55, "learning_rate": 2.558670784972298e-06, "loss": 0.1696, "step": 1584 }, { "epoch": 1.55, "learning_rate": 2.5481020785525534e-06, "loss": 0.1675, "step": 1585 }, { "epoch": 1.55, "learning_rate": 2.537552056707483e-06, "loss": 0.1591, "step": 1586 }, { "epoch": 1.55, "learning_rate": 2.5270207458897622e-06, "loss": 0.1722, "step": 1587 }, { "epoch": 1.55, "learning_rate": 2.5165081725051564e-06, "loss": 0.1554, "step": 1588 }, { "epoch": 1.55, "learning_rate": 2.50601436291245e-06, "loss": 0.1486, "step": 1589 }, { "epoch": 1.55, "learning_rate": 2.4955393434233756e-06, "loss": 0.1449, "step": 1590 }, { "epoch": 1.55, "learning_rate": 2.4850831403025597e-06, "loss": 0.1778, "step": 1591 }, { "epoch": 1.56, "learning_rate": 2.4746457797674438e-06, "loss": 0.1697, "step": 1592 }, { "epoch": 1.56, "learning_rate": 2.4642272879882245e-06, "loss": 0.1649, "step": 1593 }, { "epoch": 1.56, "learning_rate": 2.45382769108779e-06, "loss": 0.175, "step": 1594 }, { "epoch": 1.56, "learning_rate": 2.443447015141648e-06, "loss": 0.1594, "step": 1595 }, { "epoch": 1.56, "learning_rate": 2.433085286177872e-06, "loss": 0.1544, "step": 1596 }, { "epoch": 1.56, "learning_rate": 2.4227425301770236e-06, "loss": 0.1708, "step": 1597 }, { "epoch": 1.56, "learning_rate": 2.4124187730720916e-06, "loss": 0.1485, "step": 1598 }, { "epoch": 1.56, "learning_rate": 2.402114040748429e-06, "loss": 0.1678, "step": 1599 }, { "epoch": 1.56, "learning_rate": 2.3918283590436897e-06, "loss": 0.1771, "step": 1600 }, { "epoch": 1.56, "learning_rate": 2.381561753747753e-06, "loss": 0.171, "step": 1601 }, { "epoch": 1.57, "learning_rate": 2.3713142506026786e-06, "loss": 0.1536, "step": 1602 }, { "epoch": 1.57, "learning_rate": 2.361085875302621e-06, "loss": 0.182, "step": 1603 }, { "epoch": 1.57, "learning_rate": 2.3508766534937776e-06, "loss": 0.1543, "step": 1604 }, { "epoch": 1.57, "learning_rate": 2.3406866107743196e-06, "loss": 0.1528, "step": 1605 }, { "epoch": 1.57, "learning_rate": 2.330515772694333e-06, "loss": 0.16, "step": 1606 }, { "epoch": 1.57, "learning_rate": 2.320364164755745e-06, "loss": 0.1528, "step": 1607 }, { "epoch": 1.57, "learning_rate": 2.3102318124122714e-06, "loss": 0.1802, "step": 1608 }, { "epoch": 1.57, "learning_rate": 2.3001187410693427e-06, "loss": 0.1855, "step": 1609 }, { "epoch": 1.57, "learning_rate": 2.290024976084052e-06, "loss": 0.1881, "step": 1610 }, { "epoch": 1.57, "learning_rate": 2.279950542765078e-06, "loss": 0.17, "step": 1611 }, { "epoch": 1.57, "learning_rate": 2.26989546637263e-06, "loss": 0.1733, "step": 1612 }, { "epoch": 1.58, "learning_rate": 2.2598597721183834e-06, "loss": 0.1755, "step": 1613 }, { "epoch": 1.58, "learning_rate": 2.2498434851654125e-06, "loss": 0.1675, "step": 1614 }, { "epoch": 1.58, "learning_rate": 2.2398466306281364e-06, "loss": 0.1673, "step": 1615 }, { "epoch": 1.58, "learning_rate": 2.2298692335722403e-06, "loss": 0.1637, "step": 1616 }, { "epoch": 1.58, "learning_rate": 2.219911319014637e-06, "loss": 0.1428, "step": 1617 }, { "epoch": 1.58, "learning_rate": 2.209972911923377e-06, "loss": 0.1744, "step": 1618 }, { "epoch": 1.58, "learning_rate": 2.200054037217605e-06, "loss": 0.147, "step": 1619 }, { "epoch": 1.58, "learning_rate": 2.190154719767489e-06, "loss": 0.1492, "step": 1620 }, { "epoch": 1.58, "learning_rate": 2.1802749843941583e-06, "loss": 0.1631, "step": 1621 }, { "epoch": 1.58, "learning_rate": 2.170414855869647e-06, "loss": 0.1763, "step": 1622 }, { "epoch": 1.59, "learning_rate": 2.1605743589168247e-06, "loss": 0.1682, "step": 1623 }, { "epoch": 1.59, "learning_rate": 2.1507535182093353e-06, "loss": 0.1784, "step": 1624 }, { "epoch": 1.59, "learning_rate": 2.1409523583715486e-06, "loss": 0.1687, "step": 1625 }, { "epoch": 1.59, "learning_rate": 2.1311709039784734e-06, "loss": 0.1832, "step": 1626 }, { "epoch": 1.59, "learning_rate": 2.121409179555719e-06, "loss": 0.1518, "step": 1627 }, { "epoch": 1.59, "learning_rate": 2.11166720957942e-06, "loss": 0.1697, "step": 1628 }, { "epoch": 1.59, "learning_rate": 2.1019450184761814e-06, "loss": 0.1509, "step": 1629 }, { "epoch": 1.59, "learning_rate": 2.092242630623016e-06, "loss": 0.1781, "step": 1630 }, { "epoch": 1.59, "learning_rate": 2.0825600703472814e-06, "loss": 0.1656, "step": 1631 }, { "epoch": 1.59, "learning_rate": 2.0728973619266178e-06, "loss": 0.1545, "step": 1632 }, { "epoch": 1.6, "learning_rate": 2.0632545295888996e-06, "loss": 0.1625, "step": 1633 }, { "epoch": 1.6, "learning_rate": 2.0536315975121545e-06, "loss": 0.1415, "step": 1634 }, { "epoch": 1.6, "learning_rate": 2.044028589824517e-06, "loss": 0.1569, "step": 1635 }, { "epoch": 1.6, "learning_rate": 2.0344455306041633e-06, "loss": 0.1564, "step": 1636 }, { "epoch": 1.6, "learning_rate": 2.0248824438792526e-06, "loss": 0.1571, "step": 1637 }, { "epoch": 1.6, "learning_rate": 2.015339353627865e-06, "loss": 0.1705, "step": 1638 }, { "epoch": 1.6, "learning_rate": 2.0058162837779437e-06, "loss": 0.1675, "step": 1639 }, { "epoch": 1.6, "learning_rate": 1.9963132582072277e-06, "loss": 0.1468, "step": 1640 }, { "epoch": 1.6, "learning_rate": 1.98683030074321e-06, "loss": 0.139, "step": 1641 }, { "epoch": 1.6, "learning_rate": 1.9773674351630543e-06, "loss": 0.1747, "step": 1642 }, { "epoch": 1.61, "learning_rate": 1.967924685193552e-06, "loss": 0.1643, "step": 1643 }, { "epoch": 1.61, "learning_rate": 1.958502074511055e-06, "loss": 0.1717, "step": 1644 }, { "epoch": 1.61, "learning_rate": 1.949099626741422e-06, "loss": 0.1548, "step": 1645 }, { "epoch": 1.61, "learning_rate": 1.939717365459952e-06, "loss": 0.1768, "step": 1646 }, { "epoch": 1.61, "learning_rate": 1.9303553141913287e-06, "loss": 0.1672, "step": 1647 }, { "epoch": 1.61, "learning_rate": 1.9210134964095728e-06, "loss": 0.1398, "step": 1648 }, { "epoch": 1.61, "learning_rate": 1.911691935537958e-06, "loss": 0.1841, "step": 1649 }, { "epoch": 1.61, "learning_rate": 1.9023906549489767e-06, "loss": 0.1477, "step": 1650 }, { "epoch": 1.61, "learning_rate": 1.8931096779642644e-06, "loss": 0.1682, "step": 1651 }, { "epoch": 1.61, "learning_rate": 1.8838490278545528e-06, "loss": 0.1546, "step": 1652 }, { "epoch": 1.61, "learning_rate": 1.8746087278396074e-06, "loss": 0.1482, "step": 1653 }, { "epoch": 1.62, "learning_rate": 1.8653888010881637e-06, "loss": 0.1553, "step": 1654 }, { "epoch": 1.62, "learning_rate": 1.8561892707178765e-06, "loss": 0.1622, "step": 1655 }, { "epoch": 1.62, "learning_rate": 1.847010159795265e-06, "loss": 0.1861, "step": 1656 }, { "epoch": 1.62, "learning_rate": 1.8378514913356437e-06, "loss": 0.1488, "step": 1657 }, { "epoch": 1.62, "learning_rate": 1.82871328830307e-06, "loss": 0.1603, "step": 1658 }, { "epoch": 1.62, "learning_rate": 1.8195955736102888e-06, "loss": 0.1526, "step": 1659 }, { "epoch": 1.62, "learning_rate": 1.8104983701186751e-06, "loss": 0.1608, "step": 1660 }, { "epoch": 1.62, "learning_rate": 1.8014217006381728e-06, "loss": 0.1436, "step": 1661 }, { "epoch": 1.62, "learning_rate": 1.7923655879272395e-06, "loss": 0.1458, "step": 1662 }, { "epoch": 1.62, "learning_rate": 1.783330054692789e-06, "loss": 0.1675, "step": 1663 }, { "epoch": 1.63, "learning_rate": 1.7743151235901401e-06, "loss": 0.1958, "step": 1664 }, { "epoch": 1.63, "learning_rate": 1.7653208172229497e-06, "loss": 0.1627, "step": 1665 }, { "epoch": 1.63, "learning_rate": 1.7563471581431623e-06, "loss": 0.1697, "step": 1666 }, { "epoch": 1.63, "learning_rate": 1.7473941688509511e-06, "loss": 0.1566, "step": 1667 }, { "epoch": 1.63, "learning_rate": 1.7384618717946656e-06, "loss": 0.1522, "step": 1668 }, { "epoch": 1.63, "learning_rate": 1.7295502893707672e-06, "loss": 0.1508, "step": 1669 }, { "epoch": 1.63, "learning_rate": 1.7206594439237867e-06, "loss": 0.1566, "step": 1670 }, { "epoch": 1.63, "learning_rate": 1.7117893577462541e-06, "loss": 0.1816, "step": 1671 }, { "epoch": 1.63, "learning_rate": 1.7029400530786478e-06, "loss": 0.1606, "step": 1672 }, { "epoch": 1.63, "learning_rate": 1.6941115521093433e-06, "loss": 0.1805, "step": 1673 }, { "epoch": 1.64, "learning_rate": 1.6853038769745466e-06, "loss": 0.1615, "step": 1674 }, { "epoch": 1.64, "learning_rate": 1.6765170497582583e-06, "loss": 0.177, "step": 1675 }, { "epoch": 1.64, "learning_rate": 1.6677510924921958e-06, "loss": 0.144, "step": 1676 }, { "epoch": 1.64, "learning_rate": 1.6590060271557485e-06, "loss": 0.1469, "step": 1677 }, { "epoch": 1.64, "learning_rate": 1.6502818756759275e-06, "loss": 0.1687, "step": 1678 }, { "epoch": 1.64, "learning_rate": 1.6415786599272998e-06, "loss": 0.1496, "step": 1679 }, { "epoch": 1.64, "learning_rate": 1.6328964017319415e-06, "loss": 0.1804, "step": 1680 }, { "epoch": 1.64, "learning_rate": 1.6242351228593833e-06, "loss": 0.1436, "step": 1681 }, { "epoch": 1.64, "learning_rate": 1.6155948450265501e-06, "loss": 0.1781, "step": 1682 }, { "epoch": 1.64, "learning_rate": 1.6069755898977102e-06, "loss": 0.17, "step": 1683 }, { "epoch": 1.65, "learning_rate": 1.5983773790844193e-06, "loss": 0.1462, "step": 1684 }, { "epoch": 1.65, "learning_rate": 1.5898002341454688e-06, "loss": 0.1806, "step": 1685 }, { "epoch": 1.65, "learning_rate": 1.5812441765868292e-06, "loss": 0.1599, "step": 1686 }, { "epoch": 1.65, "learning_rate": 1.5727092278616018e-06, "loss": 0.1583, "step": 1687 }, { "epoch": 1.65, "learning_rate": 1.5641954093699562e-06, "loss": 0.1678, "step": 1688 }, { "epoch": 1.65, "learning_rate": 1.5557027424590808e-06, "loss": 0.1685, "step": 1689 }, { "epoch": 1.65, "learning_rate": 1.5472312484231322e-06, "loss": 0.1705, "step": 1690 }, { "epoch": 1.65, "learning_rate": 1.5387809485031745e-06, "loss": 0.1595, "step": 1691 }, { "epoch": 1.65, "learning_rate": 1.5303518638871361e-06, "loss": 0.1588, "step": 1692 }, { "epoch": 1.65, "learning_rate": 1.5219440157097476e-06, "loss": 0.1708, "step": 1693 }, { "epoch": 1.65, "learning_rate": 1.5135574250524898e-06, "loss": 0.1702, "step": 1694 }, { "epoch": 1.66, "learning_rate": 1.5051921129435521e-06, "loss": 0.1822, "step": 1695 }, { "epoch": 1.66, "learning_rate": 1.4968481003577628e-06, "loss": 0.1506, "step": 1696 }, { "epoch": 1.66, "learning_rate": 1.4885254082165479e-06, "loss": 0.1767, "step": 1697 }, { "epoch": 1.66, "learning_rate": 1.4802240573878735e-06, "loss": 0.1716, "step": 1698 }, { "epoch": 1.66, "learning_rate": 1.4719440686861975e-06, "loss": 0.1753, "step": 1699 }, { "epoch": 1.66, "learning_rate": 1.4636854628724152e-06, "loss": 0.1584, "step": 1700 }, { "epoch": 1.66, "learning_rate": 1.4554482606538044e-06, "loss": 0.1624, "step": 1701 }, { "epoch": 1.66, "learning_rate": 1.447232482683979e-06, "loss": 0.1466, "step": 1702 }, { "epoch": 1.66, "learning_rate": 1.439038149562838e-06, "loss": 0.1619, "step": 1703 }, { "epoch": 1.66, "learning_rate": 1.4308652818365031e-06, "loss": 0.1664, "step": 1704 }, { "epoch": 1.67, "learning_rate": 1.4227138999972801e-06, "loss": 0.1725, "step": 1705 }, { "epoch": 1.67, "learning_rate": 1.4145840244835985e-06, "loss": 0.1408, "step": 1706 }, { "epoch": 1.67, "learning_rate": 1.4064756756799669e-06, "loss": 0.1368, "step": 1707 }, { "epoch": 1.67, "learning_rate": 1.398388873916916e-06, "loss": 0.1412, "step": 1708 }, { "epoch": 1.67, "learning_rate": 1.3903236394709507e-06, "loss": 0.1479, "step": 1709 }, { "epoch": 1.67, "learning_rate": 1.3822799925645036e-06, "loss": 0.1615, "step": 1710 }, { "epoch": 1.67, "learning_rate": 1.3742579533658729e-06, "loss": 0.1591, "step": 1711 }, { "epoch": 1.67, "learning_rate": 1.3662575419891822e-06, "loss": 0.1788, "step": 1712 }, { "epoch": 1.67, "learning_rate": 1.3582787784943264e-06, "loss": 0.1531, "step": 1713 }, { "epoch": 1.67, "learning_rate": 1.3503216828869192e-06, "loss": 0.1533, "step": 1714 }, { "epoch": 1.68, "learning_rate": 1.342386275118247e-06, "loss": 0.1672, "step": 1715 }, { "epoch": 1.68, "learning_rate": 1.3344725750852183e-06, "loss": 0.1613, "step": 1716 }, { "epoch": 1.68, "learning_rate": 1.3265806026303063e-06, "loss": 0.1443, "step": 1717 }, { "epoch": 1.68, "learning_rate": 1.3187103775415156e-06, "loss": 0.1515, "step": 1718 }, { "epoch": 1.68, "learning_rate": 1.3108619195523153e-06, "loss": 0.1513, "step": 1719 }, { "epoch": 1.68, "learning_rate": 1.3030352483415965e-06, "loss": 0.1495, "step": 1720 }, { "epoch": 1.68, "learning_rate": 1.2952303835336256e-06, "loss": 0.1771, "step": 1721 }, { "epoch": 1.68, "learning_rate": 1.2874473446979917e-06, "loss": 0.1491, "step": 1722 }, { "epoch": 1.68, "learning_rate": 1.2796861513495572e-06, "loss": 0.1785, "step": 1723 }, { "epoch": 1.68, "learning_rate": 1.2719468229484133e-06, "loss": 0.1528, "step": 1724 }, { "epoch": 1.69, "learning_rate": 1.2642293788998206e-06, "loss": 0.1643, "step": 1725 }, { "epoch": 1.69, "learning_rate": 1.2565338385541792e-06, "loss": 0.1436, "step": 1726 }, { "epoch": 1.69, "learning_rate": 1.24886022120696e-06, "loss": 0.1569, "step": 1727 }, { "epoch": 1.69, "learning_rate": 1.2412085460986668e-06, "loss": 0.1545, "step": 1728 }, { "epoch": 1.69, "learning_rate": 1.233578832414788e-06, "loss": 0.1629, "step": 1729 }, { "epoch": 1.69, "learning_rate": 1.2259710992857464e-06, "loss": 0.1615, "step": 1730 }, { "epoch": 1.69, "learning_rate": 1.2183853657868504e-06, "loss": 0.1564, "step": 1731 }, { "epoch": 1.69, "learning_rate": 1.2108216509382487e-06, "loss": 0.1851, "step": 1732 }, { "epoch": 1.69, "learning_rate": 1.2032799737048795e-06, "loss": 0.1564, "step": 1733 }, { "epoch": 1.69, "learning_rate": 1.195760352996429e-06, "loss": 0.1504, "step": 1734 }, { "epoch": 1.7, "learning_rate": 1.1882628076672765e-06, "loss": 0.1592, "step": 1735 }, { "epoch": 1.7, "learning_rate": 1.1807873565164507e-06, "loss": 0.1905, "step": 1736 }, { "epoch": 1.7, "learning_rate": 1.173334018287583e-06, "loss": 0.1482, "step": 1737 }, { "epoch": 1.7, "learning_rate": 1.1659028116688575e-06, "loss": 0.1491, "step": 1738 }, { "epoch": 1.7, "learning_rate": 1.158493755292971e-06, "loss": 0.1727, "step": 1739 }, { "epoch": 1.7, "learning_rate": 1.151106867737075e-06, "loss": 0.1568, "step": 1740 }, { "epoch": 1.7, "learning_rate": 1.1437421675227457e-06, "loss": 0.1726, "step": 1741 }, { "epoch": 1.7, "learning_rate": 1.1363996731159188e-06, "loss": 0.1495, "step": 1742 }, { "epoch": 1.7, "learning_rate": 1.1290794029268547e-06, "loss": 0.1618, "step": 1743 }, { "epoch": 1.7, "learning_rate": 1.1217813753100914e-06, "loss": 0.1652, "step": 1744 }, { "epoch": 1.7, "learning_rate": 1.1145056085643957e-06, "loss": 0.1694, "step": 1745 }, { "epoch": 1.71, "learning_rate": 1.107252120932717e-06, "loss": 0.1517, "step": 1746 }, { "epoch": 1.71, "learning_rate": 1.100020930602146e-06, "loss": 0.1776, "step": 1747 }, { "epoch": 1.71, "learning_rate": 1.0928120557038612e-06, "loss": 0.1507, "step": 1748 }, { "epoch": 1.71, "learning_rate": 1.0856255143130967e-06, "loss": 0.1608, "step": 1749 }, { "epoch": 1.71, "learning_rate": 1.0784613244490816e-06, "loss": 0.1438, "step": 1750 }, { "epoch": 1.71, "learning_rate": 1.0713195040750012e-06, "loss": 0.1696, "step": 1751 }, { "epoch": 1.71, "learning_rate": 1.0642000710979573e-06, "loss": 0.1466, "step": 1752 }, { "epoch": 1.71, "learning_rate": 1.0571030433689145e-06, "loss": 0.1653, "step": 1753 }, { "epoch": 1.71, "learning_rate": 1.0500284386826598e-06, "loss": 0.1589, "step": 1754 }, { "epoch": 1.71, "learning_rate": 1.0429762747777627e-06, "loss": 0.1521, "step": 1755 }, { "epoch": 1.72, "learning_rate": 1.035946569336519e-06, "loss": 0.1678, "step": 1756 }, { "epoch": 1.72, "learning_rate": 1.0289393399849156e-06, "loss": 0.1368, "step": 1757 }, { "epoch": 1.72, "learning_rate": 1.0219546042925842e-06, "loss": 0.1821, "step": 1758 }, { "epoch": 1.72, "learning_rate": 1.0149923797727556e-06, "loss": 0.1762, "step": 1759 }, { "epoch": 1.72, "learning_rate": 1.0080526838822214e-06, "loss": 0.1686, "step": 1760 }, { "epoch": 1.72, "learning_rate": 1.0011355340212802e-06, "loss": 0.1675, "step": 1761 }, { "epoch": 1.72, "learning_rate": 9.942409475337012e-07, "loss": 0.1451, "step": 1762 }, { "epoch": 1.72, "learning_rate": 9.873689417066823e-07, "loss": 0.1716, "step": 1763 }, { "epoch": 1.72, "learning_rate": 9.805195337707962e-07, "loss": 0.1623, "step": 1764 }, { "epoch": 1.72, "learning_rate": 9.736927408999653e-07, "loss": 0.1625, "step": 1765 }, { "epoch": 1.73, "learning_rate": 9.668885802114002e-07, "loss": 0.1568, "step": 1766 }, { "epoch": 1.73, "learning_rate": 9.601070687655667e-07, "loss": 0.169, "step": 1767 }, { "epoch": 1.73, "learning_rate": 9.533482235661395e-07, "loss": 0.1402, "step": 1768 }, { "epoch": 1.73, "learning_rate": 9.466120615599628e-07, "loss": 0.1554, "step": 1769 }, { "epoch": 1.73, "learning_rate": 9.398985996370058e-07, "loss": 0.1645, "step": 1770 }, { "epoch": 1.73, "learning_rate": 9.33207854630317e-07, "loss": 0.1529, "step": 1771 }, { "epoch": 1.73, "learning_rate": 9.265398433159933e-07, "loss": 0.1562, "step": 1772 }, { "epoch": 1.73, "learning_rate": 9.198945824131222e-07, "loss": 0.156, "step": 1773 }, { "epoch": 1.73, "learning_rate": 9.132720885837509e-07, "loss": 0.1413, "step": 1774 }, { "epoch": 1.73, "learning_rate": 9.066723784328412e-07, "loss": 0.1787, "step": 1775 }, { "epoch": 1.74, "learning_rate": 9.000954685082286e-07, "loss": 0.1636, "step": 1776 }, { "epoch": 1.74, "learning_rate": 8.935413753005784e-07, "loss": 0.1739, "step": 1777 }, { "epoch": 1.74, "learning_rate": 8.870101152433497e-07, "loss": 0.1455, "step": 1778 }, { "epoch": 1.74, "learning_rate": 8.805017047127451e-07, "loss": 0.1436, "step": 1779 }, { "epoch": 1.74, "learning_rate": 8.74016160027683e-07, "loss": 0.1721, "step": 1780 }, { "epoch": 1.74, "learning_rate": 8.675534974497435e-07, "loss": 0.1706, "step": 1781 }, { "epoch": 1.74, "learning_rate": 8.611137331831331e-07, "loss": 0.1533, "step": 1782 }, { "epoch": 1.74, "learning_rate": 8.54696883374646e-07, "loss": 0.1476, "step": 1783 }, { "epoch": 1.74, "learning_rate": 8.483029641136209e-07, "loss": 0.1703, "step": 1784 }, { "epoch": 1.74, "learning_rate": 8.419319914319002e-07, "loss": 0.1743, "step": 1785 }, { "epoch": 1.74, "learning_rate": 8.355839813037936e-07, "loss": 0.1544, "step": 1786 }, { "epoch": 1.75, "learning_rate": 8.292589496460323e-07, "loss": 0.1563, "step": 1787 }, { "epoch": 1.75, "learning_rate": 8.229569123177361e-07, "loss": 0.1478, "step": 1788 }, { "epoch": 1.75, "learning_rate": 8.166778851203672e-07, "loss": 0.166, "step": 1789 }, { "epoch": 1.75, "learning_rate": 8.10421883797694e-07, "loss": 0.1706, "step": 1790 }, { "epoch": 1.75, "learning_rate": 8.041889240357493e-07, "loss": 0.154, "step": 1791 }, { "epoch": 1.75, "learning_rate": 7.979790214627937e-07, "loss": 0.1487, "step": 1792 }, { "epoch": 1.75, "learning_rate": 7.917921916492765e-07, "loss": 0.1582, "step": 1793 }, { "epoch": 1.75, "learning_rate": 7.856284501077927e-07, "loss": 0.1445, "step": 1794 }, { "epoch": 1.75, "learning_rate": 7.79487812293046e-07, "loss": 0.1637, "step": 1795 }, { "epoch": 1.75, "learning_rate": 7.733702936018162e-07, "loss": 0.1704, "step": 1796 }, { "epoch": 1.76, "learning_rate": 7.672759093729121e-07, "loss": 0.145, "step": 1797 }, { "epoch": 1.76, "learning_rate": 7.612046748871327e-07, "loss": 0.1433, "step": 1798 }, { "epoch": 1.76, "learning_rate": 7.551566053672377e-07, "loss": 0.1661, "step": 1799 }, { "epoch": 1.76, "learning_rate": 7.49131715977901e-07, "loss": 0.1737, "step": 1800 }, { "epoch": 1.76, "learning_rate": 7.431300218256754e-07, "loss": 0.1814, "step": 1801 }, { "epoch": 1.76, "learning_rate": 7.371515379589555e-07, "loss": 0.1826, "step": 1802 }, { "epoch": 1.76, "learning_rate": 7.311962793679417e-07, "loss": 0.151, "step": 1803 }, { "epoch": 1.76, "learning_rate": 7.252642609845973e-07, "loss": 0.1627, "step": 1804 }, { "epoch": 1.76, "learning_rate": 7.193554976826145e-07, "loss": 0.1582, "step": 1805 }, { "epoch": 1.76, "learning_rate": 7.13470004277379e-07, "loss": 0.1703, "step": 1806 }, { "epoch": 1.77, "learning_rate": 7.076077955259275e-07, "loss": 0.1599, "step": 1807 }, { "epoch": 1.77, "learning_rate": 7.017688861269145e-07, "loss": 0.1522, "step": 1808 }, { "epoch": 1.77, "learning_rate": 6.959532907205758e-07, "loss": 0.1514, "step": 1809 }, { "epoch": 1.77, "learning_rate": 6.901610238886891e-07, "loss": 0.1537, "step": 1810 }, { "epoch": 1.77, "learning_rate": 6.843921001545429e-07, "loss": 0.1568, "step": 1811 }, { "epoch": 1.77, "learning_rate": 6.786465339828918e-07, "loss": 0.181, "step": 1812 }, { "epoch": 1.77, "learning_rate": 6.729243397799268e-07, "loss": 0.161, "step": 1813 }, { "epoch": 1.77, "learning_rate": 6.672255318932342e-07, "loss": 0.1481, "step": 1814 }, { "epoch": 1.77, "learning_rate": 6.615501246117673e-07, "loss": 0.1647, "step": 1815 }, { "epoch": 1.77, "learning_rate": 6.558981321658009e-07, "loss": 0.1514, "step": 1816 }, { "epoch": 1.78, "learning_rate": 6.502695687269034e-07, "loss": 0.1491, "step": 1817 }, { "epoch": 1.78, "learning_rate": 6.446644484078968e-07, "loss": 0.1548, "step": 1818 }, { "epoch": 1.78, "learning_rate": 6.390827852628256e-07, "loss": 0.1506, "step": 1819 }, { "epoch": 1.78, "learning_rate": 6.33524593286915e-07, "loss": 0.1552, "step": 1820 }, { "epoch": 1.78, "learning_rate": 6.279898864165423e-07, "loss": 0.1597, "step": 1821 }, { "epoch": 1.78, "learning_rate": 6.22478678529197e-07, "loss": 0.1644, "step": 1822 }, { "epoch": 1.78, "learning_rate": 6.169909834434484e-07, "loss": 0.1692, "step": 1823 }, { "epoch": 1.78, "learning_rate": 6.115268149189147e-07, "loss": 0.1631, "step": 1824 }, { "epoch": 1.78, "learning_rate": 6.060861866562196e-07, "loss": 0.1763, "step": 1825 }, { "epoch": 1.78, "learning_rate": 6.006691122969644e-07, "loss": 0.1639, "step": 1826 }, { "epoch": 1.78, "learning_rate": 5.952756054236953e-07, "loss": 0.1592, "step": 1827 }, { "epoch": 1.79, "learning_rate": 5.899056795598635e-07, "loss": 0.1426, "step": 1828 }, { "epoch": 1.79, "learning_rate": 5.845593481697931e-07, "loss": 0.1481, "step": 1829 }, { "epoch": 1.79, "learning_rate": 5.792366246586512e-07, "loss": 0.1532, "step": 1830 }, { "epoch": 1.79, "learning_rate": 5.739375223724108e-07, "loss": 0.1709, "step": 1831 }, { "epoch": 1.79, "learning_rate": 5.686620545978161e-07, "loss": 0.1612, "step": 1832 }, { "epoch": 1.79, "learning_rate": 5.634102345623526e-07, "loss": 0.1473, "step": 1833 }, { "epoch": 1.79, "learning_rate": 5.581820754342138e-07, "loss": 0.1516, "step": 1834 }, { "epoch": 1.79, "learning_rate": 5.529775903222656e-07, "loss": 0.1689, "step": 1835 }, { "epoch": 1.79, "learning_rate": 5.477967922760141e-07, "loss": 0.1658, "step": 1836 }, { "epoch": 1.79, "learning_rate": 5.426396942855727e-07, "loss": 0.1462, "step": 1837 }, { "epoch": 1.8, "learning_rate": 5.375063092816313e-07, "loss": 0.1644, "step": 1838 }, { "epoch": 1.8, "learning_rate": 5.323966501354261e-07, "loss": 0.1391, "step": 1839 }, { "epoch": 1.8, "learning_rate": 5.273107296586987e-07, "loss": 0.1502, "step": 1840 }, { "epoch": 1.8, "learning_rate": 5.222485606036709e-07, "loss": 0.1703, "step": 1841 }, { "epoch": 1.8, "learning_rate": 5.172101556630149e-07, "loss": 0.1584, "step": 1842 }, { "epoch": 1.8, "learning_rate": 5.121955274698098e-07, "loss": 0.1409, "step": 1843 }, { "epoch": 1.8, "learning_rate": 5.072046885975291e-07, "loss": 0.1622, "step": 1844 }, { "epoch": 1.8, "learning_rate": 5.02237651559988e-07, "loss": 0.1623, "step": 1845 }, { "epoch": 1.8, "learning_rate": 4.972944288113268e-07, "loss": 0.1524, "step": 1846 }, { "epoch": 1.8, "learning_rate": 4.923750327459731e-07, "loss": 0.1639, "step": 1847 }, { "epoch": 1.81, "learning_rate": 4.874794756986145e-07, "loss": 0.1744, "step": 1848 }, { "epoch": 1.81, "learning_rate": 4.826077699441611e-07, "loss": 0.1506, "step": 1849 }, { "epoch": 1.81, "learning_rate": 4.777599276977262e-07, "loss": 0.1572, "step": 1850 }, { "epoch": 1.81, "learning_rate": 4.729359611145845e-07, "loss": 0.1558, "step": 1851 }, { "epoch": 1.81, "learning_rate": 4.6813588229014605e-07, "loss": 0.1854, "step": 1852 }, { "epoch": 1.81, "learning_rate": 4.6335970325992463e-07, "loss": 0.1507, "step": 1853 }, { "epoch": 1.81, "learning_rate": 4.5860743599951186e-07, "loss": 0.1595, "step": 1854 }, { "epoch": 1.81, "learning_rate": 4.538790924245418e-07, "loss": 0.1719, "step": 1855 }, { "epoch": 1.81, "learning_rate": 4.49174684390663e-07, "loss": 0.1643, "step": 1856 }, { "epoch": 1.81, "learning_rate": 4.4449422369351013e-07, "loss": 0.1694, "step": 1857 }, { "epoch": 1.82, "learning_rate": 4.3983772206867446e-07, "loss": 0.1541, "step": 1858 }, { "epoch": 1.82, "learning_rate": 4.35205191191671e-07, "loss": 0.1531, "step": 1859 }, { "epoch": 1.82, "learning_rate": 4.305966426779118e-07, "loss": 0.167, "step": 1860 }, { "epoch": 1.82, "learning_rate": 4.260120880826768e-07, "loss": 0.1586, "step": 1861 }, { "epoch": 1.82, "learning_rate": 4.214515389010865e-07, "loss": 0.1461, "step": 1862 }, { "epoch": 1.82, "learning_rate": 4.1691500656806825e-07, "loss": 0.1591, "step": 1863 }, { "epoch": 1.82, "learning_rate": 4.1240250245833226e-07, "loss": 0.1519, "step": 1864 }, { "epoch": 1.82, "learning_rate": 4.079140378863411e-07, "loss": 0.1445, "step": 1865 }, { "epoch": 1.82, "learning_rate": 4.034496241062824e-07, "loss": 0.1575, "step": 1866 }, { "epoch": 1.82, "learning_rate": 3.9900927231203866e-07, "loss": 0.145, "step": 1867 }, { "epoch": 1.82, "learning_rate": 3.945929936371595e-07, "loss": 0.1633, "step": 1868 }, { "epoch": 1.83, "learning_rate": 3.9020079915483733e-07, "loss": 0.1636, "step": 1869 }, { "epoch": 1.83, "learning_rate": 3.8583269987787607e-07, "loss": 0.1344, "step": 1870 }, { "epoch": 1.83, "learning_rate": 3.8148870675866145e-07, "loss": 0.1692, "step": 1871 }, { "epoch": 1.83, "learning_rate": 3.7716883068913857e-07, "loss": 0.1609, "step": 1872 }, { "epoch": 1.83, "learning_rate": 3.7287308250078535e-07, "loss": 0.1624, "step": 1873 }, { "epoch": 1.83, "learning_rate": 3.6860147296457814e-07, "loss": 0.1582, "step": 1874 }, { "epoch": 1.83, "learning_rate": 3.643540127909695e-07, "loss": 0.1498, "step": 1875 }, { "epoch": 1.83, "learning_rate": 3.601307126298648e-07, "loss": 0.1538, "step": 1876 }, { "epoch": 1.83, "learning_rate": 3.559315830705856e-07, "loss": 0.146, "step": 1877 }, { "epoch": 1.83, "learning_rate": 3.517566346418544e-07, "loss": 0.178, "step": 1878 }, { "epoch": 1.84, "learning_rate": 3.476058778117608e-07, "loss": 0.1569, "step": 1879 }, { "epoch": 1.84, "learning_rate": 3.434793229877353e-07, "loss": 0.1631, "step": 1880 }, { "epoch": 1.84, "learning_rate": 3.3937698051653034e-07, "loss": 0.1412, "step": 1881 }, { "epoch": 1.84, "learning_rate": 3.352988606841845e-07, "loss": 0.1616, "step": 1882 }, { "epoch": 1.84, "learning_rate": 3.312449737160051e-07, "loss": 0.1511, "step": 1883 }, { "epoch": 1.84, "learning_rate": 3.272153297765368e-07, "loss": 0.1562, "step": 1884 }, { "epoch": 1.84, "learning_rate": 3.2320993896953756e-07, "loss": 0.1581, "step": 1885 }, { "epoch": 1.84, "learning_rate": 3.1922881133795827e-07, "loss": 0.1536, "step": 1886 }, { "epoch": 1.84, "learning_rate": 3.152719568639073e-07, "loss": 0.1785, "step": 1887 }, { "epoch": 1.84, "learning_rate": 3.113393854686353e-07, "loss": 0.1604, "step": 1888 }, { "epoch": 1.85, "learning_rate": 3.0743110701250913e-07, "loss": 0.1547, "step": 1889 }, { "epoch": 1.85, "learning_rate": 3.035471312949778e-07, "loss": 0.1385, "step": 1890 }, { "epoch": 1.85, "learning_rate": 2.996874680545603e-07, "loss": 0.1396, "step": 1891 }, { "epoch": 1.85, "learning_rate": 2.9585212696881307e-07, "loss": 0.1342, "step": 1892 }, { "epoch": 1.85, "learning_rate": 2.920411176543081e-07, "loss": 0.1366, "step": 1893 }, { "epoch": 1.85, "learning_rate": 2.8825444966661064e-07, "loss": 0.1695, "step": 1894 }, { "epoch": 1.85, "learning_rate": 2.844921325002492e-07, "loss": 0.1374, "step": 1895 }, { "epoch": 1.85, "learning_rate": 2.8075417558870333e-07, "loss": 0.1663, "step": 1896 }, { "epoch": 1.85, "learning_rate": 2.7704058830436696e-07, "loss": 0.1522, "step": 1897 }, { "epoch": 1.85, "learning_rate": 2.733513799585319e-07, "loss": 0.1659, "step": 1898 }, { "epoch": 1.86, "learning_rate": 2.6968655980136425e-07, "loss": 0.1631, "step": 1899 }, { "epoch": 1.86, "learning_rate": 2.660461370218792e-07, "loss": 0.1763, "step": 1900 }, { "epoch": 1.86, "learning_rate": 2.624301207479185e-07, "loss": 0.1479, "step": 1901 }, { "epoch": 1.86, "learning_rate": 2.588385200461307e-07, "loss": 0.1409, "step": 1902 }, { "epoch": 1.86, "learning_rate": 2.552713439219412e-07, "loss": 0.1509, "step": 1903 }, { "epoch": 1.86, "learning_rate": 2.517286013195397e-07, "loss": 0.1608, "step": 1904 }, { "epoch": 1.86, "learning_rate": 2.482103011218495e-07, "loss": 0.1528, "step": 1905 }, { "epoch": 1.86, "learning_rate": 2.447164521505074e-07, "loss": 0.1583, "step": 1906 }, { "epoch": 1.86, "learning_rate": 2.4124706316584255e-07, "loss": 0.1569, "step": 1907 }, { "epoch": 1.86, "learning_rate": 2.3780214286685533e-07, "loss": 0.1558, "step": 1908 }, { "epoch": 1.86, "learning_rate": 2.3438169989119408e-07, "loss": 0.1511, "step": 1909 }, { "epoch": 1.87, "learning_rate": 2.3098574281513185e-07, "loss": 0.1602, "step": 1910 }, { "epoch": 1.87, "learning_rate": 2.276142801535486e-07, "loss": 0.1789, "step": 1911 }, { "epoch": 1.87, "learning_rate": 2.2426732035990772e-07, "loss": 0.1486, "step": 1912 }, { "epoch": 1.87, "learning_rate": 2.2094487182623747e-07, "loss": 0.1336, "step": 1913 }, { "epoch": 1.87, "learning_rate": 2.1764694288310185e-07, "loss": 0.1465, "step": 1914 }, { "epoch": 1.87, "learning_rate": 2.143735417995907e-07, "loss": 0.1468, "step": 1915 }, { "epoch": 1.87, "learning_rate": 2.1112467678329197e-07, "loss": 0.1742, "step": 1916 }, { "epoch": 1.87, "learning_rate": 2.079003559802706e-07, "loss": 0.1511, "step": 1917 }, { "epoch": 1.87, "learning_rate": 2.0470058747505516e-07, "loss": 0.1522, "step": 1918 }, { "epoch": 1.87, "learning_rate": 2.0152537929061023e-07, "loss": 0.1727, "step": 1919 }, { "epoch": 1.88, "learning_rate": 1.983747393883173e-07, "loss": 0.163, "step": 1920 }, { "epoch": 1.88, "learning_rate": 1.9524867566795945e-07, "loss": 0.1546, "step": 1921 }, { "epoch": 1.88, "learning_rate": 1.921471959676957e-07, "loss": 0.1531, "step": 1922 }, { "epoch": 1.88, "learning_rate": 1.890703080640466e-07, "loss": 0.1636, "step": 1923 }, { "epoch": 1.88, "learning_rate": 1.8601801967187083e-07, "loss": 0.1384, "step": 1924 }, { "epoch": 1.88, "learning_rate": 1.8299033844434878e-07, "loss": 0.1807, "step": 1925 }, { "epoch": 1.88, "learning_rate": 1.7998727197295785e-07, "loss": 0.1631, "step": 1926 }, { "epoch": 1.88, "learning_rate": 1.7700882778746374e-07, "loss": 0.1684, "step": 1927 }, { "epoch": 1.88, "learning_rate": 1.7405501335588825e-07, "loss": 0.1655, "step": 1928 }, { "epoch": 1.88, "learning_rate": 1.7112583608450361e-07, "loss": 0.1777, "step": 1929 }, { "epoch": 1.89, "learning_rate": 1.6822130331780485e-07, "loss": 0.1675, "step": 1930 }, { "epoch": 1.89, "learning_rate": 1.6534142233849527e-07, "loss": 0.1659, "step": 1931 }, { "epoch": 1.89, "learning_rate": 1.6248620036746764e-07, "loss": 0.1624, "step": 1932 }, { "epoch": 1.89, "learning_rate": 1.5965564456378313e-07, "loss": 0.1509, "step": 1933 }, { "epoch": 1.89, "learning_rate": 1.5684976202465786e-07, "loss": 0.146, "step": 1934 }, { "epoch": 1.89, "learning_rate": 1.5406855978544634e-07, "loss": 0.1575, "step": 1935 }, { "epoch": 1.89, "learning_rate": 1.5131204481961592e-07, "loss": 0.1601, "step": 1936 }, { "epoch": 1.89, "learning_rate": 1.4858022403873573e-07, "loss": 0.1431, "step": 1937 }, { "epoch": 1.89, "learning_rate": 1.4587310429245883e-07, "loss": 0.1667, "step": 1938 }, { "epoch": 1.89, "learning_rate": 1.4319069236850224e-07, "loss": 0.1481, "step": 1939 }, { "epoch": 1.9, "learning_rate": 1.4053299499263374e-07, "loss": 0.1843, "step": 1940 }, { "epoch": 1.9, "learning_rate": 1.3790001882865056e-07, "loss": 0.1795, "step": 1941 }, { "epoch": 1.9, "learning_rate": 1.3529177047836628e-07, "loss": 0.1723, "step": 1942 }, { "epoch": 1.9, "learning_rate": 1.3270825648159403e-07, "loss": 0.1513, "step": 1943 }, { "epoch": 1.9, "learning_rate": 1.3014948331612653e-07, "loss": 0.1686, "step": 1944 }, { "epoch": 1.9, "learning_rate": 1.2761545739772396e-07, "loss": 0.1619, "step": 1945 }, { "epoch": 1.9, "learning_rate": 1.251061850800961e-07, "loss": 0.1733, "step": 1946 }, { "epoch": 1.9, "learning_rate": 1.226216726548879e-07, "loss": 0.1566, "step": 1947 }, { "epoch": 1.9, "learning_rate": 1.2016192635165958e-07, "loss": 0.1669, "step": 1948 }, { "epoch": 1.9, "learning_rate": 1.1772695233787545e-07, "loss": 0.1604, "step": 1949 }, { "epoch": 1.91, "learning_rate": 1.1531675671888621e-07, "loss": 0.1602, "step": 1950 }, { "epoch": 1.91, "learning_rate": 1.1293134553791551e-07, "loss": 0.1614, "step": 1951 }, { "epoch": 1.91, "learning_rate": 1.1057072477604347e-07, "loss": 0.1643, "step": 1952 }, { "epoch": 1.91, "learning_rate": 1.0823490035218986e-07, "loss": 0.1825, "step": 1953 }, { "epoch": 1.91, "learning_rate": 1.0592387812310312e-07, "loss": 0.153, "step": 1954 }, { "epoch": 1.91, "learning_rate": 1.0363766388334362e-07, "loss": 0.1568, "step": 1955 }, { "epoch": 1.91, "learning_rate": 1.0137626336526596e-07, "loss": 0.1455, "step": 1956 }, { "epoch": 1.91, "learning_rate": 9.913968223901227e-08, "loss": 0.1567, "step": 1957 }, { "epoch": 1.91, "learning_rate": 9.692792611249224e-08, "loss": 0.1501, "step": 1958 }, { "epoch": 1.91, "learning_rate": 9.47410005313687e-08, "loss": 0.1645, "step": 1959 }, { "epoch": 1.91, "learning_rate": 9.257891097904759e-08, "loss": 0.1498, "step": 1960 }, { "epoch": 1.92, "learning_rate": 9.044166287666134e-08, "loss": 0.1566, "step": 1961 }, { "epoch": 1.92, "learning_rate": 8.832926158305443e-08, "loss": 0.1651, "step": 1962 }, { "epoch": 1.92, "learning_rate": 8.624171239477342e-08, "loss": 0.1463, "step": 1963 }, { "epoch": 1.92, "learning_rate": 8.417902054605131e-08, "loss": 0.1638, "step": 1964 }, { "epoch": 1.92, "learning_rate": 8.214119120879437e-08, "loss": 0.1815, "step": 1965 }, { "epoch": 1.92, "learning_rate": 8.012822949256981e-08, "loss": 0.1383, "step": 1966 }, { "epoch": 1.92, "learning_rate": 7.814014044459362e-08, "loss": 0.1703, "step": 1967 }, { "epoch": 1.92, "learning_rate": 7.617692904971718e-08, "loss": 0.1507, "step": 1968 }, { "epoch": 1.92, "learning_rate": 7.423860023041185e-08, "loss": 0.1721, "step": 1969 }, { "epoch": 1.92, "learning_rate": 7.232515884676327e-08, "loss": 0.1631, "step": 1970 }, { "epoch": 1.93, "learning_rate": 7.043660969645261e-08, "loss": 0.1505, "step": 1971 }, { "epoch": 1.93, "learning_rate": 6.857295751474979e-08, "loss": 0.1734, "step": 1972 }, { "epoch": 1.93, "learning_rate": 6.673420697449473e-08, "loss": 0.1429, "step": 1973 }, { "epoch": 1.93, "learning_rate": 6.492036268609725e-08, "loss": 0.1441, "step": 1974 }, { "epoch": 1.93, "learning_rate": 6.313142919751159e-08, "loss": 0.1595, "step": 1975 }, { "epoch": 1.93, "learning_rate": 6.136741099423416e-08, "loss": 0.1696, "step": 1976 }, { "epoch": 1.93, "learning_rate": 5.962831249928913e-08, "loss": 0.1575, "step": 1977 }, { "epoch": 1.93, "learning_rate": 5.791413807322066e-08, "loss": 0.1727, "step": 1978 }, { "epoch": 1.93, "learning_rate": 5.6224892014077324e-08, "loss": 0.1422, "step": 1979 }, { "epoch": 1.93, "learning_rate": 5.456057855740215e-08, "loss": 0.1501, "step": 1980 }, { "epoch": 1.94, "learning_rate": 5.2921201876223737e-08, "loss": 0.1627, "step": 1981 }, { "epoch": 1.94, "learning_rate": 5.1306766081048456e-08, "loss": 0.1491, "step": 1982 }, { "epoch": 1.94, "learning_rate": 4.971727521984382e-08, "loss": 0.1607, "step": 1983 }, { "epoch": 1.94, "learning_rate": 4.815273327803183e-08, "loss": 0.1507, "step": 1984 }, { "epoch": 1.94, "learning_rate": 4.6613144178477844e-08, "loss": 0.1511, "step": 1985 }, { "epoch": 1.94, "learning_rate": 4.5098511781485056e-08, "loss": 0.1608, "step": 1986 }, { "epoch": 1.94, "learning_rate": 4.360883988477782e-08, "loss": 0.162, "step": 1987 }, { "epoch": 1.94, "learning_rate": 4.2144132223495e-08, "loss": 0.1527, "step": 1988 }, { "epoch": 1.94, "learning_rate": 4.070439247018554e-08, "loss": 0.1406, "step": 1989 }, { "epoch": 1.94, "learning_rate": 3.928962423479066e-08, "loss": 0.1587, "step": 1990 }, { "epoch": 1.95, "learning_rate": 3.789983106464057e-08, "loss": 0.1461, "step": 1991 }, { "epoch": 1.95, "learning_rate": 3.653501644444446e-08, "loss": 0.1639, "step": 1992 }, { "epoch": 1.95, "learning_rate": 3.519518379628162e-08, "loss": 0.1682, "step": 1993 }, { "epoch": 1.95, "learning_rate": 3.3880336479590324e-08, "loss": 0.1731, "step": 1994 }, { "epoch": 1.95, "learning_rate": 3.259047779116453e-08, "loss": 0.1547, "step": 1995 }, { "epoch": 1.95, "learning_rate": 3.132561096514164e-08, "loss": 0.1788, "step": 1996 }, { "epoch": 1.95, "learning_rate": 3.0085739172993623e-08, "loss": 0.1649, "step": 1997 }, { "epoch": 1.95, "learning_rate": 2.8870865523525916e-08, "loss": 0.1651, "step": 1998 }, { "epoch": 1.95, "learning_rate": 2.7680993062858543e-08, "loss": 0.1651, "step": 1999 }, { "epoch": 1.95, "learning_rate": 2.651612477442833e-08, "loss": 0.1557, "step": 2000 }, { "epoch": 1.95, "learning_rate": 2.5376263578977823e-08, "loss": 0.1787, "step": 2001 }, { "epoch": 1.96, "learning_rate": 2.4261412334546373e-08, "loss": 0.1567, "step": 2002 }, { "epoch": 1.96, "learning_rate": 2.3171573836464623e-08, "loss": 0.1506, "step": 2003 }, { "epoch": 1.96, "learning_rate": 2.210675081734892e-08, "loss": 0.1781, "step": 2004 }, { "epoch": 1.96, "learning_rate": 2.1066945947090244e-08, "loss": 0.1531, "step": 2005 }, { "epoch": 1.96, "learning_rate": 2.0052161832850858e-08, "loss": 0.1381, "step": 2006 }, { "epoch": 1.96, "learning_rate": 1.9062401019059874e-08, "loss": 0.1628, "step": 2007 }, { "epoch": 1.96, "learning_rate": 1.8097665987399925e-08, "loss": 0.1662, "step": 2008 }, { "epoch": 1.96, "learning_rate": 1.7157959156808292e-08, "loss": 0.1608, "step": 2009 }, { "epoch": 1.96, "learning_rate": 1.6243282883465772e-08, "loss": 0.1728, "step": 2010 }, { "epoch": 1.96, "learning_rate": 1.5353639460793378e-08, "loss": 0.1963, "step": 2011 }, { "epoch": 1.97, "learning_rate": 1.4489031119444553e-08, "loss": 0.1663, "step": 2012 }, { "epoch": 1.97, "learning_rate": 1.364946002730183e-08, "loss": 0.1621, "step": 2013 }, { "epoch": 1.97, "learning_rate": 1.2834928289472415e-08, "loss": 0.1824, "step": 2014 }, { "epoch": 1.97, "learning_rate": 1.2045437948275952e-08, "loss": 0.138, "step": 2015 }, { "epoch": 1.97, "learning_rate": 1.1280990983248975e-08, "loss": 0.1261, "step": 2016 }, { "epoch": 1.97, "learning_rate": 1.0541589311133804e-08, "loss": 0.1627, "step": 2017 }, { "epoch": 1.97, "learning_rate": 9.827234785874107e-09, "loss": 0.1704, "step": 2018 }, { "epoch": 1.97, "learning_rate": 9.137929198612672e-09, "loss": 0.1403, "step": 2019 }, { "epoch": 1.97, "learning_rate": 8.473674277685862e-09, "loss": 0.1511, "step": 2020 }, { "epoch": 1.97, "learning_rate": 7.834471688616952e-09, "loss": 0.1653, "step": 2021 }, { "epoch": 1.98, "learning_rate": 7.220323034117238e-09, "loss": 0.1594, "step": 2022 }, { "epoch": 1.98, "learning_rate": 6.631229854076049e-09, "loss": 0.1732, "step": 2023 }, { "epoch": 1.98, "learning_rate": 6.067193625560741e-09, "loss": 0.1628, "step": 2024 }, { "epoch": 1.98, "learning_rate": 5.528215762813372e-09, "loss": 0.1586, "step": 2025 }, { "epoch": 1.98, "learning_rate": 5.014297617242925e-09, "loss": 0.1541, "step": 2026 }, { "epoch": 1.98, "learning_rate": 4.525440477425314e-09, "loss": 0.1879, "step": 2027 }, { "epoch": 1.98, "learning_rate": 4.061645569103379e-09, "loss": 0.1808, "step": 2028 }, { "epoch": 1.98, "learning_rate": 3.6229140551735655e-09, "loss": 0.1566, "step": 2029 }, { "epoch": 1.98, "learning_rate": 3.209247035694807e-09, "loss": 0.1634, "step": 2030 }, { "epoch": 1.98, "learning_rate": 2.8206455478774206e-09, "loss": 0.1761, "step": 2031 }, { "epoch": 1.99, "learning_rate": 2.45711056608533e-09, "loss": 0.1326, "step": 2032 }, { "epoch": 1.99, "learning_rate": 2.1186430018294015e-09, "loss": 0.1299, "step": 2033 }, { "epoch": 1.99, "learning_rate": 1.805243703770776e-09, "loss": 0.1484, "step": 2034 }, { "epoch": 1.99, "learning_rate": 1.5169134577119882e-09, "loss": 0.1588, "step": 2035 }, { "epoch": 1.99, "learning_rate": 1.2536529866014058e-09, "loss": 0.1503, "step": 2036 }, { "epoch": 1.99, "learning_rate": 1.0154629505254587e-09, "loss": 0.1594, "step": 2037 }, { "epoch": 1.99, "learning_rate": 8.023439467141902e-10, "loss": 0.1441, "step": 2038 }, { "epoch": 1.99, "learning_rate": 6.142965095312648e-10, "loss": 0.1666, "step": 2039 }, { "epoch": 1.99, "learning_rate": 4.51321110479519e-10, "loss": 0.1522, "step": 2040 }, { "epoch": 1.99, "learning_rate": 3.1341815819763146e-10, "loss": 0.1631, "step": 2041 }, { "epoch": 1.99, "learning_rate": 2.0058799845568134e-10, "loss": 0.1638, "step": 2042 }, { "epoch": 2.0, "learning_rate": 1.128309141606998e-10, "loss": 0.16, "step": 2043 }, { "epoch": 2.0, "learning_rate": 5.014712535111876e-11, "loss": 0.177, "step": 2044 }, { "epoch": 2.0, "learning_rate": 1.2536789196770927e-11, "loss": 0.1758, "step": 2045 }, { "epoch": 2.0, "learning_rate": 0.0, "loss": 0.1662, "step": 2046 }, { "epoch": 2.0, "step": 2046, "total_flos": 7.408872884052951e+17, "train_loss": 0.30992321503273085, "train_runtime": 24450.4494, "train_samples_per_second": 21.434, "train_steps_per_second": 0.084 } ], "logging_steps": 1.0, "max_steps": 2046, "num_train_epochs": 2, "save_steps": 2000, "total_flos": 7.408872884052951e+17, "trial_name": null, "trial_params": null }