{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "global_step": 717, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 9.090909090909091e-07, "loss": 0.7678, "step": 1 }, { "epoch": 0.01, "learning_rate": 1.8181818181818183e-06, "loss": 0.7731, "step": 2 }, { "epoch": 0.01, "learning_rate": 2.7272727272727272e-06, "loss": 0.8476, "step": 3 }, { "epoch": 0.02, "learning_rate": 3.6363636363636366e-06, "loss": 0.783, "step": 4 }, { "epoch": 0.02, "learning_rate": 4.5454545454545455e-06, "loss": 0.7332, "step": 5 }, { "epoch": 0.03, "learning_rate": 5.4545454545454545e-06, "loss": 0.6563, "step": 6 }, { "epoch": 0.03, "learning_rate": 6.363636363636364e-06, "loss": 0.6574, "step": 7 }, { "epoch": 0.03, "learning_rate": 7.272727272727273e-06, "loss": 0.6471, "step": 8 }, { "epoch": 0.04, "learning_rate": 8.181818181818183e-06, "loss": 0.5971, "step": 9 }, { "epoch": 0.04, "learning_rate": 9.090909090909091e-06, "loss": 0.5837, "step": 10 }, { "epoch": 0.05, "learning_rate": 1e-05, "loss": 0.5884, "step": 11 }, { "epoch": 0.05, "learning_rate": 1.0909090909090909e-05, "loss": 0.5916, "step": 12 }, { "epoch": 0.05, "learning_rate": 1.181818181818182e-05, "loss": 0.5759, "step": 13 }, { "epoch": 0.06, "learning_rate": 1.2727272727272728e-05, "loss": 0.5464, "step": 14 }, { "epoch": 0.06, "learning_rate": 1.3636363636363637e-05, "loss": 0.5675, "step": 15 }, { "epoch": 0.07, "learning_rate": 1.4545454545454546e-05, "loss": 0.5477, "step": 16 }, { "epoch": 0.07, "learning_rate": 1.5454545454545454e-05, "loss": 0.5162, "step": 17 }, { "epoch": 0.08, "learning_rate": 1.6363636363636366e-05, "loss": 0.5018, "step": 18 }, { "epoch": 0.08, "learning_rate": 1.7272727272727274e-05, "loss": 0.5149, "step": 19 }, { "epoch": 0.08, "learning_rate": 1.8181818181818182e-05, "loss": 0.5485, "step": 20 }, { "epoch": 0.09, "learning_rate": 1.9090909090909094e-05, "loss": 0.5174, "step": 21 }, { "epoch": 0.09, "learning_rate": 2e-05, "loss": 0.5476, "step": 22 }, { "epoch": 0.1, "learning_rate": 1.9999897835644166e-05, "loss": 0.5322, "step": 23 }, { "epoch": 0.1, "learning_rate": 1.9999591344664163e-05, "loss": 0.4921, "step": 24 }, { "epoch": 0.1, "learning_rate": 1.9999080533322486e-05, "loss": 0.5514, "step": 25 }, { "epoch": 0.11, "learning_rate": 1.9998365412056476e-05, "loss": 0.4966, "step": 26 }, { "epoch": 0.11, "learning_rate": 1.999744599547812e-05, "loss": 0.4834, "step": 27 }, { "epoch": 0.12, "learning_rate": 1.999632230237373e-05, "loss": 0.5289, "step": 28 }, { "epoch": 0.12, "learning_rate": 1.999499435570359e-05, "loss": 0.4914, "step": 29 }, { "epoch": 0.13, "learning_rate": 1.999346218260146e-05, "loss": 0.5273, "step": 30 }, { "epoch": 0.13, "learning_rate": 1.999172581437403e-05, "loss": 0.4999, "step": 31 }, { "epoch": 0.13, "learning_rate": 1.9989785286500294e-05, "loss": 0.4953, "step": 32 }, { "epoch": 0.14, "learning_rate": 1.9987640638630812e-05, "loss": 0.4888, "step": 33 }, { "epoch": 0.14, "learning_rate": 1.998529191458689e-05, "loss": 0.4968, "step": 34 }, { "epoch": 0.15, "learning_rate": 1.9982739162359707e-05, "loss": 0.4915, "step": 35 }, { "epoch": 0.15, "learning_rate": 1.997998243410932e-05, "loss": 0.4958, "step": 36 }, { "epoch": 0.15, "learning_rate": 1.99770217861636e-05, "loss": 0.5136, "step": 37 }, { "epoch": 0.16, "learning_rate": 1.9973857279017092e-05, "loss": 0.4989, "step": 38 }, { "epoch": 0.16, "learning_rate": 1.9970488977329757e-05, "loss": 0.4797, "step": 39 }, { "epoch": 0.17, "learning_rate": 1.996691694992567e-05, "loss": 0.4806, "step": 40 }, { "epoch": 0.17, "learning_rate": 1.9963141269791606e-05, "loss": 0.4641, "step": 41 }, { "epoch": 0.18, "learning_rate": 1.9959162014075553e-05, "loss": 0.4734, "step": 42 }, { "epoch": 0.18, "learning_rate": 1.995497926408513e-05, "loss": 0.4716, "step": 43 }, { "epoch": 0.18, "learning_rate": 1.9950593105285927e-05, "loss": 0.4856, "step": 44 }, { "epoch": 0.19, "learning_rate": 1.9946003627299766e-05, "loss": 0.4658, "step": 45 }, { "epoch": 0.19, "learning_rate": 1.9941210923902853e-05, "loss": 0.4677, "step": 46 }, { "epoch": 0.2, "learning_rate": 1.9936215093023884e-05, "loss": 0.4633, "step": 47 }, { "epoch": 0.2, "learning_rate": 1.9931016236742026e-05, "loss": 0.4699, "step": 48 }, { "epoch": 0.21, "learning_rate": 1.992561446128484e-05, "loss": 0.44, "step": 49 }, { "epoch": 0.21, "learning_rate": 1.9920009877026106e-05, "loss": 0.4759, "step": 50 }, { "epoch": 0.21, "learning_rate": 1.9914202598483576e-05, "loss": 0.4693, "step": 51 }, { "epoch": 0.22, "learning_rate": 1.990819274431662e-05, "loss": 0.4647, "step": 52 }, { "epoch": 0.22, "learning_rate": 1.9901980437323818e-05, "loss": 0.4502, "step": 53 }, { "epoch": 0.23, "learning_rate": 1.9895565804440435e-05, "loss": 0.5081, "step": 54 }, { "epoch": 0.23, "learning_rate": 1.9888948976735843e-05, "loss": 0.4724, "step": 55 }, { "epoch": 0.23, "learning_rate": 1.9882130089410822e-05, "loss": 0.4941, "step": 56 }, { "epoch": 0.24, "learning_rate": 1.9875109281794828e-05, "loss": 0.4827, "step": 57 }, { "epoch": 0.24, "learning_rate": 1.986788669734311e-05, "loss": 0.4633, "step": 58 }, { "epoch": 0.25, "learning_rate": 1.986046248363381e-05, "loss": 0.4893, "step": 59 }, { "epoch": 0.25, "learning_rate": 1.985283679236493e-05, "loss": 0.4672, "step": 60 }, { "epoch": 0.26, "learning_rate": 1.9845009779351235e-05, "loss": 0.4666, "step": 61 }, { "epoch": 0.26, "learning_rate": 1.9836981604521077e-05, "loss": 0.4673, "step": 62 }, { "epoch": 0.26, "learning_rate": 1.9828752431913116e-05, "loss": 0.4754, "step": 63 }, { "epoch": 0.27, "learning_rate": 1.9820322429672978e-05, "loss": 0.5032, "step": 64 }, { "epoch": 0.27, "learning_rate": 1.9811691770049806e-05, "loss": 0.4799, "step": 65 }, { "epoch": 0.28, "learning_rate": 1.9802860629392765e-05, "loss": 0.4699, "step": 66 }, { "epoch": 0.28, "learning_rate": 1.9793829188147406e-05, "loss": 0.472, "step": 67 }, { "epoch": 0.28, "learning_rate": 1.9784597630852008e-05, "loss": 0.5005, "step": 68 }, { "epoch": 0.29, "learning_rate": 1.97751661461338e-05, "loss": 0.4388, "step": 69 }, { "epoch": 0.29, "learning_rate": 1.9765534926705082e-05, "loss": 0.4659, "step": 70 }, { "epoch": 0.3, "learning_rate": 1.975570416935932e-05, "loss": 0.4816, "step": 71 }, { "epoch": 0.3, "learning_rate": 1.974567407496712e-05, "loss": 0.4659, "step": 72 }, { "epoch": 0.31, "learning_rate": 1.9735444848472108e-05, "loss": 0.472, "step": 73 }, { "epoch": 0.31, "learning_rate": 1.9725016698886748e-05, "loss": 0.468, "step": 74 }, { "epoch": 0.31, "learning_rate": 1.9714389839288073e-05, "loss": 0.4568, "step": 75 }, { "epoch": 0.32, "learning_rate": 1.9703564486813342e-05, "loss": 0.4627, "step": 76 }, { "epoch": 0.32, "learning_rate": 1.9692540862655587e-05, "loss": 0.497, "step": 77 }, { "epoch": 0.33, "learning_rate": 1.96813191920591e-05, "loss": 0.496, "step": 78 }, { "epoch": 0.33, "learning_rate": 1.9669899704314828e-05, "loss": 0.4655, "step": 79 }, { "epoch": 0.33, "learning_rate": 1.9658282632755694e-05, "loss": 0.4611, "step": 80 }, { "epoch": 0.34, "learning_rate": 1.964646821475183e-05, "loss": 0.4795, "step": 81 }, { "epoch": 0.34, "learning_rate": 1.9634456691705705e-05, "loss": 0.4558, "step": 82 }, { "epoch": 0.35, "learning_rate": 1.9622248309047233e-05, "loss": 0.476, "step": 83 }, { "epoch": 0.35, "learning_rate": 1.960984331622872e-05, "loss": 0.4417, "step": 84 }, { "epoch": 0.36, "learning_rate": 1.959724196671978e-05, "loss": 0.4682, "step": 85 }, { "epoch": 0.36, "learning_rate": 1.9584444518002178e-05, "loss": 0.485, "step": 86 }, { "epoch": 0.36, "learning_rate": 1.9571451231564523e-05, "loss": 0.4674, "step": 87 }, { "epoch": 0.37, "learning_rate": 1.955826237289697e-05, "loss": 0.4464, "step": 88 }, { "epoch": 0.37, "learning_rate": 1.9544878211485763e-05, "loss": 0.4677, "step": 89 }, { "epoch": 0.38, "learning_rate": 1.9531299020807752e-05, "loss": 0.4343, "step": 90 }, { "epoch": 0.38, "learning_rate": 1.9517525078324787e-05, "loss": 0.4506, "step": 91 }, { "epoch": 0.38, "learning_rate": 1.9503556665478066e-05, "loss": 0.4669, "step": 92 }, { "epoch": 0.39, "learning_rate": 1.9489394067682365e-05, "loss": 0.4587, "step": 93 }, { "epoch": 0.39, "learning_rate": 1.9475037574320217e-05, "loss": 0.4337, "step": 94 }, { "epoch": 0.4, "learning_rate": 1.946048747873601e-05, "loss": 0.4547, "step": 95 }, { "epoch": 0.4, "learning_rate": 1.9445744078229967e-05, "loss": 0.4605, "step": 96 }, { "epoch": 0.41, "learning_rate": 1.9430807674052092e-05, "loss": 0.4508, "step": 97 }, { "epoch": 0.41, "learning_rate": 1.9415678571396006e-05, "loss": 0.4642, "step": 98 }, { "epoch": 0.41, "learning_rate": 1.9400357079392714e-05, "loss": 0.4528, "step": 99 }, { "epoch": 0.42, "learning_rate": 1.9384843511104294e-05, "loss": 0.4679, "step": 100 }, { "epoch": 0.42, "learning_rate": 1.936913818351748e-05, "loss": 0.4425, "step": 101 }, { "epoch": 0.43, "learning_rate": 1.9353241417537216e-05, "loss": 0.4758, "step": 102 }, { "epoch": 0.43, "learning_rate": 1.933715353798006e-05, "loss": 0.4516, "step": 103 }, { "epoch": 0.44, "learning_rate": 1.9320874873567598e-05, "loss": 0.4519, "step": 104 }, { "epoch": 0.44, "learning_rate": 1.930440575691967e-05, "loss": 0.4861, "step": 105 }, { "epoch": 0.44, "learning_rate": 1.9287746524547627e-05, "loss": 0.4635, "step": 106 }, { "epoch": 0.45, "learning_rate": 1.9270897516847406e-05, "loss": 0.4607, "step": 107 }, { "epoch": 0.45, "learning_rate": 1.9253859078092616e-05, "loss": 0.4538, "step": 108 }, { "epoch": 0.46, "learning_rate": 1.923663155642748e-05, "loss": 0.4647, "step": 109 }, { "epoch": 0.46, "learning_rate": 1.9219215303859732e-05, "loss": 0.4524, "step": 110 }, { "epoch": 0.46, "learning_rate": 1.9201610676253412e-05, "loss": 0.4296, "step": 111 }, { "epoch": 0.47, "learning_rate": 1.9183818033321612e-05, "loss": 0.4378, "step": 112 }, { "epoch": 0.47, "learning_rate": 1.916583773861911e-05, "loss": 0.4793, "step": 113 }, { "epoch": 0.48, "learning_rate": 1.9147670159534953e-05, "loss": 0.4423, "step": 114 }, { "epoch": 0.48, "learning_rate": 1.912931566728494e-05, "loss": 0.4824, "step": 115 }, { "epoch": 0.49, "learning_rate": 1.9110774636904052e-05, "loss": 0.4399, "step": 116 }, { "epoch": 0.49, "learning_rate": 1.9092047447238775e-05, "loss": 0.478, "step": 117 }, { "epoch": 0.49, "learning_rate": 1.9073134480939353e-05, "loss": 0.4661, "step": 118 }, { "epoch": 0.5, "learning_rate": 1.9054036124452e-05, "loss": 0.4806, "step": 119 }, { "epoch": 0.5, "learning_rate": 1.9034752768010965e-05, "loss": 0.4437, "step": 120 }, { "epoch": 0.51, "learning_rate": 1.901528480563059e-05, "loss": 0.4863, "step": 121 }, { "epoch": 0.51, "learning_rate": 1.899563263509725e-05, "loss": 0.4434, "step": 122 }, { "epoch": 0.51, "learning_rate": 1.89757966579612e-05, "loss": 0.443, "step": 123 }, { "epoch": 0.52, "learning_rate": 1.8955777279528414e-05, "loss": 0.4813, "step": 124 }, { "epoch": 0.52, "learning_rate": 1.8935574908852272e-05, "loss": 0.4609, "step": 125 }, { "epoch": 0.53, "learning_rate": 1.8915189958725207e-05, "loss": 0.4542, "step": 126 }, { "epoch": 0.53, "learning_rate": 1.8894622845670282e-05, "loss": 0.4285, "step": 127 }, { "epoch": 0.54, "learning_rate": 1.8873873989932666e-05, "loss": 0.4887, "step": 128 }, { "epoch": 0.54, "learning_rate": 1.8852943815471058e-05, "loss": 0.4553, "step": 129 }, { "epoch": 0.54, "learning_rate": 1.8831832749949015e-05, "loss": 0.4411, "step": 130 }, { "epoch": 0.55, "learning_rate": 1.8810541224726217e-05, "loss": 0.4653, "step": 131 }, { "epoch": 0.55, "learning_rate": 1.878906967484966e-05, "loss": 0.4594, "step": 132 }, { "epoch": 0.56, "learning_rate": 1.8767418539044753e-05, "loss": 0.4602, "step": 133 }, { "epoch": 0.56, "learning_rate": 1.8745588259706366e-05, "loss": 0.4504, "step": 134 }, { "epoch": 0.56, "learning_rate": 1.8723579282889784e-05, "loss": 0.4721, "step": 135 }, { "epoch": 0.57, "learning_rate": 1.8701392058301595e-05, "loss": 0.4561, "step": 136 }, { "epoch": 0.57, "learning_rate": 1.86790270392905e-05, "loss": 0.4376, "step": 137 }, { "epoch": 0.58, "learning_rate": 1.865648468283805e-05, "loss": 0.4513, "step": 138 }, { "epoch": 0.58, "learning_rate": 1.863376544954931e-05, "loss": 0.4416, "step": 139 }, { "epoch": 0.59, "learning_rate": 1.8610869803643454e-05, "loss": 0.4298, "step": 140 }, { "epoch": 0.59, "learning_rate": 1.8587798212944255e-05, "loss": 0.4596, "step": 141 }, { "epoch": 0.59, "learning_rate": 1.856455114887056e-05, "loss": 0.4627, "step": 142 }, { "epoch": 0.6, "learning_rate": 1.854112908642663e-05, "loss": 0.472, "step": 143 }, { "epoch": 0.6, "learning_rate": 1.8517532504192456e-05, "loss": 0.4671, "step": 144 }, { "epoch": 0.61, "learning_rate": 1.849376188431396e-05, "loss": 0.4807, "step": 145 }, { "epoch": 0.61, "learning_rate": 1.8469817712493148e-05, "loss": 0.4428, "step": 146 }, { "epoch": 0.62, "learning_rate": 1.8445700477978207e-05, "loss": 0.4461, "step": 147 }, { "epoch": 0.62, "learning_rate": 1.8421410673553475e-05, "loss": 0.4507, "step": 148 }, { "epoch": 0.62, "learning_rate": 1.8396948795529405e-05, "loss": 0.4594, "step": 149 }, { "epoch": 0.63, "learning_rate": 1.8372315343732395e-05, "loss": 0.4423, "step": 150 }, { "epoch": 0.63, "learning_rate": 1.8347510821494593e-05, "loss": 0.4668, "step": 151 }, { "epoch": 0.64, "learning_rate": 1.8322535735643604e-05, "loss": 0.4286, "step": 152 }, { "epoch": 0.64, "learning_rate": 1.8297390596492143e-05, "loss": 0.4313, "step": 153 }, { "epoch": 0.64, "learning_rate": 1.8272075917827597e-05, "loss": 0.4507, "step": 154 }, { "epoch": 0.65, "learning_rate": 1.824659221690153e-05, "loss": 0.4631, "step": 155 }, { "epoch": 0.65, "learning_rate": 1.822094001441913e-05, "loss": 0.4839, "step": 156 }, { "epoch": 0.66, "learning_rate": 1.8195119834528535e-05, "loss": 0.4634, "step": 157 }, { "epoch": 0.66, "learning_rate": 1.8169132204810157e-05, "loss": 0.442, "step": 158 }, { "epoch": 0.67, "learning_rate": 1.814297765626589e-05, "loss": 0.4671, "step": 159 }, { "epoch": 0.67, "learning_rate": 1.8116656723308253e-05, "loss": 0.4622, "step": 160 }, { "epoch": 0.67, "learning_rate": 1.8090169943749477e-05, "loss": 0.4721, "step": 161 }, { "epoch": 0.68, "learning_rate": 1.8063517858790517e-05, "loss": 0.4728, "step": 162 }, { "epoch": 0.68, "learning_rate": 1.8036701013009988e-05, "loss": 0.4662, "step": 163 }, { "epoch": 0.69, "learning_rate": 1.800971995435305e-05, "loss": 0.4916, "step": 164 }, { "epoch": 0.69, "learning_rate": 1.7982575234120196e-05, "loss": 0.4598, "step": 165 }, { "epoch": 0.69, "learning_rate": 1.7955267406955997e-05, "loss": 0.4434, "step": 166 }, { "epoch": 0.7, "learning_rate": 1.792779703083777e-05, "loss": 0.4565, "step": 167 }, { "epoch": 0.7, "learning_rate": 1.790016466706417e-05, "loss": 0.4633, "step": 168 }, { "epoch": 0.71, "learning_rate": 1.787237088024372e-05, "loss": 0.4623, "step": 169 }, { "epoch": 0.71, "learning_rate": 1.78444162382833e-05, "loss": 0.4559, "step": 170 }, { "epoch": 0.72, "learning_rate": 1.781630131237649e-05, "loss": 0.4421, "step": 171 }, { "epoch": 0.72, "learning_rate": 1.778802667699196e-05, "loss": 0.4357, "step": 172 }, { "epoch": 0.72, "learning_rate": 1.7759592909861694e-05, "loss": 0.4538, "step": 173 }, { "epoch": 0.73, "learning_rate": 1.7731000591969182e-05, "loss": 0.4342, "step": 174 }, { "epoch": 0.73, "learning_rate": 1.7702250307537583e-05, "loss": 0.4581, "step": 175 }, { "epoch": 0.74, "learning_rate": 1.7673342644017744e-05, "loss": 0.4485, "step": 176 }, { "epoch": 0.74, "learning_rate": 1.764427819207624e-05, "loss": 0.4574, "step": 177 }, { "epoch": 0.74, "learning_rate": 1.761505754558327e-05, "loss": 0.4474, "step": 178 }, { "epoch": 0.75, "learning_rate": 1.758568130160053e-05, "loss": 0.4478, "step": 179 }, { "epoch": 0.75, "learning_rate": 1.755615006036904e-05, "loss": 0.4543, "step": 180 }, { "epoch": 0.76, "learning_rate": 1.7526464425296846e-05, "loss": 0.4528, "step": 181 }, { "epoch": 0.76, "learning_rate": 1.7496625002946702e-05, "loss": 0.4313, "step": 182 }, { "epoch": 0.77, "learning_rate": 1.746663240302368e-05, "loss": 0.4869, "step": 183 }, { "epoch": 0.77, "learning_rate": 1.743648723836271e-05, "loss": 0.472, "step": 184 }, { "epoch": 0.77, "learning_rate": 1.7406190124916064e-05, "loss": 0.4585, "step": 185 }, { "epoch": 0.78, "learning_rate": 1.737574168174075e-05, "loss": 0.4215, "step": 186 }, { "epoch": 0.78, "learning_rate": 1.734514253098589e-05, "loss": 0.452, "step": 187 }, { "epoch": 0.79, "learning_rate": 1.7314393297879982e-05, "loss": 0.456, "step": 188 }, { "epoch": 0.79, "learning_rate": 1.7283494610718153e-05, "loss": 0.4557, "step": 189 }, { "epoch": 0.79, "learning_rate": 1.7252447100849294e-05, "loss": 0.4679, "step": 190 }, { "epoch": 0.8, "learning_rate": 1.7221251402663176e-05, "loss": 0.4364, "step": 191 }, { "epoch": 0.8, "learning_rate": 1.7189908153577473e-05, "loss": 0.4641, "step": 192 }, { "epoch": 0.81, "learning_rate": 1.7158417994024766e-05, "loss": 0.4387, "step": 193 }, { "epoch": 0.81, "learning_rate": 1.7126781567439418e-05, "loss": 0.4487, "step": 194 }, { "epoch": 0.82, "learning_rate": 1.709499952024447e-05, "loss": 0.4381, "step": 195 }, { "epoch": 0.82, "learning_rate": 1.7063072501838388e-05, "loss": 0.4622, "step": 196 }, { "epoch": 0.82, "learning_rate": 1.7031001164581828e-05, "loss": 0.4528, "step": 197 }, { "epoch": 0.83, "learning_rate": 1.6998786163784295e-05, "loss": 0.4374, "step": 198 }, { "epoch": 0.83, "learning_rate": 1.696642815769075e-05, "loss": 0.4468, "step": 199 }, { "epoch": 0.84, "learning_rate": 1.6933927807468155e-05, "loss": 0.4716, "step": 200 }, { "epoch": 0.84, "learning_rate": 1.690128577719199e-05, "loss": 0.4599, "step": 201 }, { "epoch": 0.85, "learning_rate": 1.6868502733832647e-05, "loss": 0.4494, "step": 202 }, { "epoch": 0.85, "learning_rate": 1.683557934724183e-05, "loss": 0.4539, "step": 203 }, { "epoch": 0.85, "learning_rate": 1.680251629013885e-05, "loss": 0.445, "step": 204 }, { "epoch": 0.86, "learning_rate": 1.6769314238096906e-05, "loss": 0.4293, "step": 205 }, { "epoch": 0.86, "learning_rate": 1.673597386952924e-05, "loss": 0.4578, "step": 206 }, { "epoch": 0.87, "learning_rate": 1.670249586567531e-05, "loss": 0.434, "step": 207 }, { "epoch": 0.87, "learning_rate": 1.6668880910586853e-05, "loss": 0.4491, "step": 208 }, { "epoch": 0.87, "learning_rate": 1.663512969111392e-05, "loss": 0.4461, "step": 209 }, { "epoch": 0.88, "learning_rate": 1.6601242896890832e-05, "loss": 0.4375, "step": 210 }, { "epoch": 0.88, "learning_rate": 1.6567221220322082e-05, "loss": 0.4456, "step": 211 }, { "epoch": 0.89, "learning_rate": 1.6533065356568206e-05, "loss": 0.4541, "step": 212 }, { "epoch": 0.89, "learning_rate": 1.6498776003531575e-05, "loss": 0.4385, "step": 213 }, { "epoch": 0.9, "learning_rate": 1.6464353861842115e-05, "loss": 0.4304, "step": 214 }, { "epoch": 0.9, "learning_rate": 1.6429799634843012e-05, "loss": 0.4517, "step": 215 }, { "epoch": 0.9, "learning_rate": 1.6395114028576344e-05, "loss": 0.4442, "step": 216 }, { "epoch": 0.91, "learning_rate": 1.636029775176862e-05, "loss": 0.437, "step": 217 }, { "epoch": 0.91, "learning_rate": 1.6325351515816353e-05, "loss": 0.4193, "step": 218 }, { "epoch": 0.92, "learning_rate": 1.629027603477147e-05, "loss": 0.4421, "step": 219 }, { "epoch": 0.92, "learning_rate": 1.6255072025326763e-05, "loss": 0.4511, "step": 220 }, { "epoch": 0.92, "learning_rate": 1.621974020680122e-05, "loss": 0.4409, "step": 221 }, { "epoch": 0.93, "learning_rate": 1.618428130112533e-05, "loss": 0.4239, "step": 222 }, { "epoch": 0.93, "learning_rate": 1.6148696032826354e-05, "loss": 0.4479, "step": 223 }, { "epoch": 0.94, "learning_rate": 1.611298512901349e-05, "loss": 0.4601, "step": 224 }, { "epoch": 0.94, "learning_rate": 1.6077149319363035e-05, "loss": 0.435, "step": 225 }, { "epoch": 0.95, "learning_rate": 1.6041189336103475e-05, "loss": 0.4369, "step": 226 }, { "epoch": 0.95, "learning_rate": 1.6005105914000508e-05, "loss": 0.452, "step": 227 }, { "epoch": 0.95, "learning_rate": 1.596889979034205e-05, "loss": 0.4772, "step": 228 }, { "epoch": 0.96, "learning_rate": 1.5932571704923168e-05, "loss": 0.4528, "step": 229 }, { "epoch": 0.96, "learning_rate": 1.589612240003095e-05, "loss": 0.441, "step": 230 }, { "epoch": 0.97, "learning_rate": 1.585955262042934e-05, "loss": 0.445, "step": 231 }, { "epoch": 0.97, "learning_rate": 1.5822863113343934e-05, "loss": 0.4712, "step": 232 }, { "epoch": 0.97, "learning_rate": 1.5786054628446712e-05, "loss": 0.4349, "step": 233 }, { "epoch": 0.98, "learning_rate": 1.57491279178407e-05, "loss": 0.4509, "step": 234 }, { "epoch": 0.98, "learning_rate": 1.5712083736044613e-05, "loss": 0.435, "step": 235 }, { "epoch": 0.99, "learning_rate": 1.5674922839977446e-05, "loss": 0.4306, "step": 236 }, { "epoch": 0.99, "learning_rate": 1.5637645988943008e-05, "loss": 0.4595, "step": 237 }, { "epoch": 1.0, "learning_rate": 1.560025394461439e-05, "loss": 0.4597, "step": 238 }, { "epoch": 1.0, "learning_rate": 1.5562747471018415e-05, "loss": 0.4572, "step": 239 }, { "epoch": 1.0, "learning_rate": 1.552512733452003e-05, "loss": 0.376, "step": 240 }, { "epoch": 1.01, "learning_rate": 1.5487394303806632e-05, "loss": 0.3759, "step": 241 }, { "epoch": 1.01, "learning_rate": 1.544954914987238e-05, "loss": 0.3626, "step": 242 }, { "epoch": 1.02, "learning_rate": 1.541159264600242e-05, "loss": 0.397, "step": 243 }, { "epoch": 1.02, "learning_rate": 1.5373525567757124e-05, "loss": 0.3663, "step": 244 }, { "epoch": 1.03, "learning_rate": 1.5335348692956177e-05, "loss": 0.3769, "step": 245 }, { "epoch": 1.03, "learning_rate": 1.529706280166276e-05, "loss": 0.3705, "step": 246 }, { "epoch": 1.03, "learning_rate": 1.5258668676167548e-05, "loss": 0.3748, "step": 247 }, { "epoch": 1.04, "learning_rate": 1.5220167100972763e-05, "loss": 0.3654, "step": 248 }, { "epoch": 1.04, "learning_rate": 1.518155886277613e-05, "loss": 0.3639, "step": 249 }, { "epoch": 1.05, "learning_rate": 1.5142844750454807e-05, "loss": 0.3645, "step": 250 }, { "epoch": 1.05, "learning_rate": 1.5104025555049262e-05, "loss": 0.3606, "step": 251 }, { "epoch": 1.05, "learning_rate": 1.5065102069747117e-05, "loss": 0.3607, "step": 252 }, { "epoch": 1.06, "learning_rate": 1.502607508986693e-05, "loss": 0.35, "step": 253 }, { "epoch": 1.06, "learning_rate": 1.498694541284195e-05, "loss": 0.3839, "step": 254 }, { "epoch": 1.07, "learning_rate": 1.4947713838203835e-05, "loss": 0.3718, "step": 255 }, { "epoch": 1.07, "learning_rate": 1.4908381167566286e-05, "loss": 0.3666, "step": 256 }, { "epoch": 1.08, "learning_rate": 1.48689482046087e-05, "loss": 0.3587, "step": 257 }, { "epoch": 1.08, "learning_rate": 1.4829415755059726e-05, "loss": 0.3605, "step": 258 }, { "epoch": 1.08, "learning_rate": 1.4789784626680819e-05, "loss": 0.3575, "step": 259 }, { "epoch": 1.09, "learning_rate": 1.475005562924971e-05, "loss": 0.3515, "step": 260 }, { "epoch": 1.09, "learning_rate": 1.4710229574543893e-05, "loss": 0.3763, "step": 261 }, { "epoch": 1.1, "learning_rate": 1.467030727632401e-05, "loss": 0.3653, "step": 262 }, { "epoch": 1.1, "learning_rate": 1.4630289550317234e-05, "loss": 0.3454, "step": 263 }, { "epoch": 1.1, "learning_rate": 1.4590177214200609e-05, "loss": 0.3394, "step": 264 }, { "epoch": 1.11, "learning_rate": 1.4549971087584329e-05, "loss": 0.3479, "step": 265 }, { "epoch": 1.11, "learning_rate": 1.4509671991995003e-05, "loss": 0.3624, "step": 266 }, { "epoch": 1.12, "learning_rate": 1.4469280750858854e-05, "loss": 0.383, "step": 267 }, { "epoch": 1.12, "learning_rate": 1.4428798189484914e-05, "loss": 0.3767, "step": 268 }, { "epoch": 1.13, "learning_rate": 1.4388225135048137e-05, "loss": 0.3593, "step": 269 }, { "epoch": 1.13, "learning_rate": 1.4347562416572525e-05, "loss": 0.3576, "step": 270 }, { "epoch": 1.13, "learning_rate": 1.430681086491416e-05, "loss": 0.3578, "step": 271 }, { "epoch": 1.14, "learning_rate": 1.4265971312744252e-05, "loss": 0.3413, "step": 272 }, { "epoch": 1.14, "learning_rate": 1.4225044594532104e-05, "loss": 0.3641, "step": 273 }, { "epoch": 1.15, "learning_rate": 1.4184031546528077e-05, "loss": 0.3536, "step": 274 }, { "epoch": 1.15, "learning_rate": 1.4142933006746502e-05, "loss": 0.3691, "step": 275 }, { "epoch": 1.15, "learning_rate": 1.4101749814948544e-05, "loss": 0.3735, "step": 276 }, { "epoch": 1.16, "learning_rate": 1.4060482812625055e-05, "loss": 0.3634, "step": 277 }, { "epoch": 1.16, "learning_rate": 1.4019132842979375e-05, "loss": 0.3649, "step": 278 }, { "epoch": 1.17, "learning_rate": 1.3977700750910112e-05, "loss": 0.3546, "step": 279 }, { "epoch": 1.17, "learning_rate": 1.3936187382993862e-05, "loss": 0.3672, "step": 280 }, { "epoch": 1.18, "learning_rate": 1.3894593587467924e-05, "loss": 0.3381, "step": 281 }, { "epoch": 1.18, "learning_rate": 1.3852920214212966e-05, "loss": 0.3708, "step": 282 }, { "epoch": 1.18, "learning_rate": 1.3811168114735647e-05, "loss": 0.3776, "step": 283 }, { "epoch": 1.19, "learning_rate": 1.3769338142151245e-05, "loss": 0.3588, "step": 284 }, { "epoch": 1.19, "learning_rate": 1.3727431151166196e-05, "loss": 0.3656, "step": 285 }, { "epoch": 1.2, "learning_rate": 1.3685447998060651e-05, "loss": 0.378, "step": 286 }, { "epoch": 1.2, "learning_rate": 1.3643389540670963e-05, "loss": 0.3652, "step": 287 }, { "epoch": 1.21, "learning_rate": 1.3601256638372182e-05, "loss": 0.3688, "step": 288 }, { "epoch": 1.21, "learning_rate": 1.3559050152060465e-05, "loss": 0.3577, "step": 289 }, { "epoch": 1.21, "learning_rate": 1.3516770944135514e-05, "loss": 0.3593, "step": 290 }, { "epoch": 1.22, "learning_rate": 1.3474419878482935e-05, "loss": 0.3425, "step": 291 }, { "epoch": 1.22, "learning_rate": 1.3431997820456592e-05, "loss": 0.38, "step": 292 }, { "epoch": 1.23, "learning_rate": 1.3389505636860944e-05, "loss": 0.3717, "step": 293 }, { "epoch": 1.23, "learning_rate": 1.3346944195933294e-05, "loss": 0.3476, "step": 294 }, { "epoch": 1.23, "learning_rate": 1.330431436732608e-05, "loss": 0.3779, "step": 295 }, { "epoch": 1.24, "learning_rate": 1.3261617022089103e-05, "loss": 0.3492, "step": 296 }, { "epoch": 1.24, "learning_rate": 1.3218853032651719e-05, "loss": 0.3657, "step": 297 }, { "epoch": 1.25, "learning_rate": 1.3176023272805008e-05, "loss": 0.3524, "step": 298 }, { "epoch": 1.25, "learning_rate": 1.313312861768394e-05, "loss": 0.3704, "step": 299 }, { "epoch": 1.26, "learning_rate": 1.3090169943749475e-05, "loss": 0.3631, "step": 300 }, { "epoch": 1.26, "learning_rate": 1.3047148128770664e-05, "loss": 0.3806, "step": 301 }, { "epoch": 1.26, "learning_rate": 1.3004064051806712e-05, "loss": 0.3577, "step": 302 }, { "epoch": 1.27, "learning_rate": 1.2960918593189005e-05, "loss": 0.3629, "step": 303 }, { "epoch": 1.27, "learning_rate": 1.2917712634503148e-05, "loss": 0.3581, "step": 304 }, { "epoch": 1.28, "learning_rate": 1.2874447058570927e-05, "loss": 0.3801, "step": 305 }, { "epoch": 1.28, "learning_rate": 1.2831122749432278e-05, "loss": 0.3409, "step": 306 }, { "epoch": 1.28, "learning_rate": 1.2787740592327232e-05, "loss": 0.3563, "step": 307 }, { "epoch": 1.29, "learning_rate": 1.2744301473677814e-05, "loss": 0.3664, "step": 308 }, { "epoch": 1.29, "learning_rate": 1.2700806281069942e-05, "loss": 0.3702, "step": 309 }, { "epoch": 1.3, "learning_rate": 1.2657255903235278e-05, "loss": 0.3679, "step": 310 }, { "epoch": 1.3, "learning_rate": 1.2613651230033085e-05, "loss": 0.3626, "step": 311 }, { "epoch": 1.31, "learning_rate": 1.2569993152432028e-05, "loss": 0.3574, "step": 312 }, { "epoch": 1.31, "learning_rate": 1.2526282562491991e-05, "loss": 0.3684, "step": 313 }, { "epoch": 1.31, "learning_rate": 1.2482520353345819e-05, "loss": 0.3683, "step": 314 }, { "epoch": 1.32, "learning_rate": 1.2438707419181097e-05, "loss": 0.3704, "step": 315 }, { "epoch": 1.32, "learning_rate": 1.2394844655221863e-05, "loss": 0.3782, "step": 316 }, { "epoch": 1.33, "learning_rate": 1.2350932957710322e-05, "loss": 0.3704, "step": 317 }, { "epoch": 1.33, "learning_rate": 1.2306973223888535e-05, "loss": 0.3752, "step": 318 }, { "epoch": 1.33, "learning_rate": 1.2262966351980075e-05, "loss": 0.3592, "step": 319 }, { "epoch": 1.34, "learning_rate": 1.2218913241171691e-05, "loss": 0.3506, "step": 320 }, { "epoch": 1.34, "learning_rate": 1.2174814791594913e-05, "loss": 0.3413, "step": 321 }, { "epoch": 1.35, "learning_rate": 1.2130671904307692e-05, "loss": 0.3435, "step": 322 }, { "epoch": 1.35, "learning_rate": 1.2086485481275943e-05, "loss": 0.3685, "step": 323 }, { "epoch": 1.36, "learning_rate": 1.2042256425355165e-05, "loss": 0.3643, "step": 324 }, { "epoch": 1.36, "learning_rate": 1.1997985640271956e-05, "loss": 0.3758, "step": 325 }, { "epoch": 1.36, "learning_rate": 1.1953674030605568e-05, "loss": 0.3781, "step": 326 }, { "epoch": 1.37, "learning_rate": 1.1909322501769407e-05, "loss": 0.3549, "step": 327 }, { "epoch": 1.37, "learning_rate": 1.186493195999255e-05, "loss": 0.363, "step": 328 }, { "epoch": 1.38, "learning_rate": 1.1820503312301218e-05, "loss": 0.3435, "step": 329 }, { "epoch": 1.38, "learning_rate": 1.1776037466500245e-05, "loss": 0.3626, "step": 330 }, { "epoch": 1.38, "learning_rate": 1.1731535331154532e-05, "loss": 0.3714, "step": 331 }, { "epoch": 1.39, "learning_rate": 1.1686997815570473e-05, "loss": 0.358, "step": 332 }, { "epoch": 1.39, "learning_rate": 1.1642425829777391e-05, "loss": 0.3592, "step": 333 }, { "epoch": 1.4, "learning_rate": 1.1597820284508927e-05, "loss": 0.3675, "step": 334 }, { "epoch": 1.4, "learning_rate": 1.1553182091184439e-05, "loss": 0.3545, "step": 335 }, { "epoch": 1.41, "learning_rate": 1.1508512161890381e-05, "loss": 0.3593, "step": 336 }, { "epoch": 1.41, "learning_rate": 1.1463811409361667e-05, "loss": 0.3663, "step": 337 }, { "epoch": 1.41, "learning_rate": 1.1419080746963012e-05, "loss": 0.3528, "step": 338 }, { "epoch": 1.42, "learning_rate": 1.1374321088670277e-05, "loss": 0.3664, "step": 339 }, { "epoch": 1.42, "learning_rate": 1.1329533349051794e-05, "loss": 0.3702, "step": 340 }, { "epoch": 1.43, "learning_rate": 1.1284718443249676e-05, "loss": 0.3712, "step": 341 }, { "epoch": 1.43, "learning_rate": 1.1239877286961123e-05, "loss": 0.3572, "step": 342 }, { "epoch": 1.44, "learning_rate": 1.11950107964197e-05, "loss": 0.3646, "step": 343 }, { "epoch": 1.44, "learning_rate": 1.1150119888376631e-05, "loss": 0.3399, "step": 344 }, { "epoch": 1.44, "learning_rate": 1.1105205480082052e-05, "loss": 0.3683, "step": 345 }, { "epoch": 1.45, "learning_rate": 1.106026848926629e-05, "loss": 0.356, "step": 346 }, { "epoch": 1.45, "learning_rate": 1.1015309834121083e-05, "loss": 0.3749, "step": 347 }, { "epoch": 1.46, "learning_rate": 1.0970330433280838e-05, "loss": 0.3572, "step": 348 }, { "epoch": 1.46, "learning_rate": 1.0925331205803861e-05, "loss": 0.3536, "step": 349 }, { "epoch": 1.46, "learning_rate": 1.0880313071153568e-05, "loss": 0.3611, "step": 350 }, { "epoch": 1.47, "learning_rate": 1.0835276949179707e-05, "loss": 0.3735, "step": 351 }, { "epoch": 1.47, "learning_rate": 1.079022376009955e-05, "loss": 0.3728, "step": 352 }, { "epoch": 1.48, "learning_rate": 1.0745154424479112e-05, "loss": 0.3526, "step": 353 }, { "epoch": 1.48, "learning_rate": 1.0700069863214317e-05, "loss": 0.3574, "step": 354 }, { "epoch": 1.49, "learning_rate": 1.0654970997512201e-05, "loss": 0.3753, "step": 355 }, { "epoch": 1.49, "learning_rate": 1.0609858748872073e-05, "loss": 0.3666, "step": 356 }, { "epoch": 1.49, "learning_rate": 1.05647340390667e-05, "loss": 0.346, "step": 357 }, { "epoch": 1.5, "learning_rate": 1.0519597790123463e-05, "loss": 0.3615, "step": 358 }, { "epoch": 1.5, "learning_rate": 1.047445092430552e-05, "loss": 0.3601, "step": 359 }, { "epoch": 1.51, "learning_rate": 1.0429294364092968e-05, "loss": 0.3692, "step": 360 }, { "epoch": 1.51, "learning_rate": 1.0384129032163976e-05, "loss": 0.3886, "step": 361 }, { "epoch": 1.51, "learning_rate": 1.0338955851375962e-05, "loss": 0.3539, "step": 362 }, { "epoch": 1.52, "learning_rate": 1.0293775744746705e-05, "loss": 0.3746, "step": 363 }, { "epoch": 1.52, "learning_rate": 1.0248589635435505e-05, "loss": 0.3851, "step": 364 }, { "epoch": 1.53, "learning_rate": 1.0203398446724306e-05, "loss": 0.3546, "step": 365 }, { "epoch": 1.53, "learning_rate": 1.0158203101998854e-05, "loss": 0.3599, "step": 366 }, { "epoch": 1.54, "learning_rate": 1.01130045247298e-05, "loss": 0.3639, "step": 367 }, { "epoch": 1.54, "learning_rate": 1.0067803638453847e-05, "loss": 0.3592, "step": 368 }, { "epoch": 1.54, "learning_rate": 1.0022601366754889e-05, "loss": 0.3565, "step": 369 }, { "epoch": 1.55, "learning_rate": 9.977398633245116e-06, "loss": 0.3535, "step": 370 }, { "epoch": 1.55, "learning_rate": 9.932196361546156e-06, "loss": 0.354, "step": 371 }, { "epoch": 1.56, "learning_rate": 9.886995475270205e-06, "loss": 0.3416, "step": 372 }, { "epoch": 1.56, "learning_rate": 9.84179689800115e-06, "loss": 0.3462, "step": 373 }, { "epoch": 1.56, "learning_rate": 9.796601553275697e-06, "loss": 0.3709, "step": 374 }, { "epoch": 1.57, "learning_rate": 9.751410364564499e-06, "loss": 0.3574, "step": 375 }, { "epoch": 1.57, "learning_rate": 9.706224255253297e-06, "loss": 0.3694, "step": 376 }, { "epoch": 1.58, "learning_rate": 9.661044148624038e-06, "loss": 0.354, "step": 377 }, { "epoch": 1.58, "learning_rate": 9.615870967836026e-06, "loss": 0.3834, "step": 378 }, { "epoch": 1.59, "learning_rate": 9.570705635907038e-06, "loss": 0.3805, "step": 379 }, { "epoch": 1.59, "learning_rate": 9.525549075694484e-06, "loss": 0.3694, "step": 380 }, { "epoch": 1.59, "learning_rate": 9.48040220987654e-06, "loss": 0.3533, "step": 381 }, { "epoch": 1.6, "learning_rate": 9.435265960933304e-06, "loss": 0.3654, "step": 382 }, { "epoch": 1.6, "learning_rate": 9.39014125112793e-06, "loss": 0.3586, "step": 383 }, { "epoch": 1.61, "learning_rate": 9.3450290024878e-06, "loss": 0.3707, "step": 384 }, { "epoch": 1.61, "learning_rate": 9.299930136785685e-06, "loss": 0.3409, "step": 385 }, { "epoch": 1.62, "learning_rate": 9.25484557552089e-06, "loss": 0.3458, "step": 386 }, { "epoch": 1.62, "learning_rate": 9.209776239900453e-06, "loss": 0.3624, "step": 387 }, { "epoch": 1.62, "learning_rate": 9.164723050820298e-06, "loss": 0.3684, "step": 388 }, { "epoch": 1.63, "learning_rate": 9.119686928846437e-06, "loss": 0.3856, "step": 389 }, { "epoch": 1.63, "learning_rate": 9.074668794196142e-06, "loss": 0.3841, "step": 390 }, { "epoch": 1.64, "learning_rate": 9.029669566719165e-06, "loss": 0.3658, "step": 391 }, { "epoch": 1.64, "learning_rate": 8.98469016587892e-06, "loss": 0.3515, "step": 392 }, { "epoch": 1.64, "learning_rate": 8.939731510733711e-06, "loss": 0.3672, "step": 393 }, { "epoch": 1.65, "learning_rate": 8.894794519917947e-06, "loss": 0.386, "step": 394 }, { "epoch": 1.65, "learning_rate": 8.849880111623374e-06, "loss": 0.3662, "step": 395 }, { "epoch": 1.66, "learning_rate": 8.804989203580303e-06, "loss": 0.3821, "step": 396 }, { "epoch": 1.66, "learning_rate": 8.76012271303888e-06, "loss": 0.3603, "step": 397 }, { "epoch": 1.67, "learning_rate": 8.715281556750327e-06, "loss": 0.3587, "step": 398 }, { "epoch": 1.67, "learning_rate": 8.670466650948208e-06, "loss": 0.3516, "step": 399 }, { "epoch": 1.67, "learning_rate": 8.625678911329727e-06, "loss": 0.3782, "step": 400 }, { "epoch": 1.68, "learning_rate": 8.580919253036991e-06, "loss": 0.3443, "step": 401 }, { "epoch": 1.68, "learning_rate": 8.536188590638334e-06, "loss": 0.3498, "step": 402 }, { "epoch": 1.69, "learning_rate": 8.491487838109622e-06, "loss": 0.3547, "step": 403 }, { "epoch": 1.69, "learning_rate": 8.446817908815566e-06, "loss": 0.3432, "step": 404 }, { "epoch": 1.69, "learning_rate": 8.402179715491078e-06, "loss": 0.3499, "step": 405 }, { "epoch": 1.7, "learning_rate": 8.357574170222612e-06, "loss": 0.3522, "step": 406 }, { "epoch": 1.7, "learning_rate": 8.313002184429529e-06, "loss": 0.3561, "step": 407 }, { "epoch": 1.71, "learning_rate": 8.268464668845471e-06, "loss": 0.345, "step": 408 }, { "epoch": 1.71, "learning_rate": 8.223962533499757e-06, "loss": 0.358, "step": 409 }, { "epoch": 1.72, "learning_rate": 8.179496687698785e-06, "loss": 0.3514, "step": 410 }, { "epoch": 1.72, "learning_rate": 8.135068040007452e-06, "loss": 0.3495, "step": 411 }, { "epoch": 1.72, "learning_rate": 8.090677498230598e-06, "loss": 0.3693, "step": 412 }, { "epoch": 1.73, "learning_rate": 8.046325969394437e-06, "loss": 0.3638, "step": 413 }, { "epoch": 1.73, "learning_rate": 8.002014359728046e-06, "loss": 0.363, "step": 414 }, { "epoch": 1.74, "learning_rate": 7.957743574644837e-06, "loss": 0.3701, "step": 415 }, { "epoch": 1.74, "learning_rate": 7.913514518724059e-06, "loss": 0.3653, "step": 416 }, { "epoch": 1.74, "learning_rate": 7.869328095692313e-06, "loss": 0.3685, "step": 417 }, { "epoch": 1.75, "learning_rate": 7.825185208405089e-06, "loss": 0.3587, "step": 418 }, { "epoch": 1.75, "learning_rate": 7.781086758828314e-06, "loss": 0.3902, "step": 419 }, { "epoch": 1.76, "learning_rate": 7.73703364801993e-06, "loss": 0.3687, "step": 420 }, { "epoch": 1.76, "learning_rate": 7.69302677611147e-06, "loss": 0.3711, "step": 421 }, { "epoch": 1.77, "learning_rate": 7.649067042289681e-06, "loss": 0.3389, "step": 422 }, { "epoch": 1.77, "learning_rate": 7.6051553447781415e-06, "loss": 0.3502, "step": 423 }, { "epoch": 1.77, "learning_rate": 7.561292580818906e-06, "loss": 0.3586, "step": 424 }, { "epoch": 1.78, "learning_rate": 7.517479646654184e-06, "loss": 0.3741, "step": 425 }, { "epoch": 1.78, "learning_rate": 7.47371743750801e-06, "loss": 0.3612, "step": 426 }, { "epoch": 1.79, "learning_rate": 7.430006847567972e-06, "loss": 0.3683, "step": 427 }, { "epoch": 1.79, "learning_rate": 7.386348769966918e-06, "loss": 0.3602, "step": 428 }, { "epoch": 1.79, "learning_rate": 7.342744096764727e-06, "loss": 0.3432, "step": 429 }, { "epoch": 1.8, "learning_rate": 7.299193718930062e-06, "loss": 0.3879, "step": 430 }, { "epoch": 1.8, "learning_rate": 7.255698526322188e-06, "loss": 0.3776, "step": 431 }, { "epoch": 1.81, "learning_rate": 7.2122594076727705e-06, "loss": 0.3681, "step": 432 }, { "epoch": 1.81, "learning_rate": 7.1688772505677225e-06, "loss": 0.3502, "step": 433 }, { "epoch": 1.82, "learning_rate": 7.125552941429077e-06, "loss": 0.3609, "step": 434 }, { "epoch": 1.82, "learning_rate": 7.082287365496852e-06, "loss": 0.3782, "step": 435 }, { "epoch": 1.82, "learning_rate": 7.0390814068109965e-06, "loss": 0.3778, "step": 436 }, { "epoch": 1.83, "learning_rate": 6.995935948193294e-06, "loss": 0.3512, "step": 437 }, { "epoch": 1.83, "learning_rate": 6.9528518712293405e-06, "loss": 0.371, "step": 438 }, { "epoch": 1.84, "learning_rate": 6.909830056250527e-06, "loss": 0.3671, "step": 439 }, { "epoch": 1.84, "learning_rate": 6.866871382316063e-06, "loss": 0.3607, "step": 440 }, { "epoch": 1.85, "learning_rate": 6.823976727194994e-06, "loss": 0.3655, "step": 441 }, { "epoch": 1.85, "learning_rate": 6.781146967348283e-06, "loss": 0.3604, "step": 442 }, { "epoch": 1.85, "learning_rate": 6.738382977910898e-06, "loss": 0.3622, "step": 443 }, { "epoch": 1.86, "learning_rate": 6.695685632673919e-06, "loss": 0.3552, "step": 444 }, { "epoch": 1.86, "learning_rate": 6.653055804066712e-06, "loss": 0.3643, "step": 445 }, { "epoch": 1.87, "learning_rate": 6.6104943631390596e-06, "loss": 0.351, "step": 446 }, { "epoch": 1.87, "learning_rate": 6.568002179543409e-06, "loss": 0.3676, "step": 447 }, { "epoch": 1.87, "learning_rate": 6.525580121517069e-06, "loss": 0.3563, "step": 448 }, { "epoch": 1.88, "learning_rate": 6.48322905586449e-06, "loss": 0.3502, "step": 449 }, { "epoch": 1.88, "learning_rate": 6.440949847939538e-06, "loss": 0.3845, "step": 450 }, { "epoch": 1.89, "learning_rate": 6.39874336162782e-06, "loss": 0.3567, "step": 451 }, { "epoch": 1.89, "learning_rate": 6.356610459329038e-06, "loss": 0.3552, "step": 452 }, { "epoch": 1.9, "learning_rate": 6.314552001939351e-06, "loss": 0.353, "step": 453 }, { "epoch": 1.9, "learning_rate": 6.272568848833809e-06, "loss": 0.3603, "step": 454 }, { "epoch": 1.9, "learning_rate": 6.230661857848759e-06, "loss": 0.3501, "step": 455 }, { "epoch": 1.91, "learning_rate": 6.188831885264357e-06, "loss": 0.3576, "step": 456 }, { "epoch": 1.91, "learning_rate": 6.147079785787038e-06, "loss": 0.3458, "step": 457 }, { "epoch": 1.92, "learning_rate": 6.105406412532078e-06, "loss": 0.3639, "step": 458 }, { "epoch": 1.92, "learning_rate": 6.06381261700614e-06, "loss": 0.3604, "step": 459 }, { "epoch": 1.92, "learning_rate": 6.022299249089889e-06, "loss": 0.358, "step": 460 }, { "epoch": 1.93, "learning_rate": 5.980867157020624e-06, "loss": 0.3592, "step": 461 }, { "epoch": 1.93, "learning_rate": 5.93951718737495e-06, "loss": 0.3664, "step": 462 }, { "epoch": 1.94, "learning_rate": 5.8982501850514614e-06, "loss": 0.351, "step": 463 }, { "epoch": 1.94, "learning_rate": 5.857066993253501e-06, "loss": 0.3587, "step": 464 }, { "epoch": 1.95, "learning_rate": 5.815968453471923e-06, "loss": 0.3763, "step": 465 }, { "epoch": 1.95, "learning_rate": 5.7749554054679015e-06, "loss": 0.3431, "step": 466 }, { "epoch": 1.95, "learning_rate": 5.7340286872557515e-06, "loss": 0.3664, "step": 467 }, { "epoch": 1.96, "learning_rate": 5.693189135085839e-06, "loss": 0.3623, "step": 468 }, { "epoch": 1.96, "learning_rate": 5.652437583427478e-06, "loss": 0.3609, "step": 469 }, { "epoch": 1.97, "learning_rate": 5.6117748649518665e-06, "loss": 0.3651, "step": 470 }, { "epoch": 1.97, "learning_rate": 5.5712018105150914e-06, "loss": 0.3439, "step": 471 }, { "epoch": 1.97, "learning_rate": 5.530719249141148e-06, "loss": 0.3526, "step": 472 }, { "epoch": 1.98, "learning_rate": 5.490328008005002e-06, "loss": 0.3275, "step": 473 }, { "epoch": 1.98, "learning_rate": 5.450028912415672e-06, "loss": 0.3615, "step": 474 }, { "epoch": 1.99, "learning_rate": 5.409822785799393e-06, "loss": 0.3678, "step": 475 }, { "epoch": 1.99, "learning_rate": 5.369710449682767e-06, "loss": 0.3561, "step": 476 }, { "epoch": 2.0, "learning_rate": 5.329692723675994e-06, "loss": 0.37, "step": 477 }, { "epoch": 2.0, "learning_rate": 5.289770425456109e-06, "loss": 0.3358, "step": 478 }, { "epoch": 2.0, "learning_rate": 5.249944370750293e-06, "loss": 0.2953, "step": 479 }, { "epoch": 2.01, "learning_rate": 5.210215373319183e-06, "loss": 0.282, "step": 480 }, { "epoch": 2.01, "learning_rate": 5.170584244940275e-06, "loss": 0.2803, "step": 481 }, { "epoch": 2.02, "learning_rate": 5.131051795391302e-06, "loss": 0.3133, "step": 482 }, { "epoch": 2.02, "learning_rate": 5.091618832433716e-06, "loss": 0.2831, "step": 483 }, { "epoch": 2.03, "learning_rate": 5.0522861617961694e-06, "loss": 0.2965, "step": 484 }, { "epoch": 2.03, "learning_rate": 5.0130545871580504e-06, "loss": 0.2828, "step": 485 }, { "epoch": 2.03, "learning_rate": 4.973924910133071e-06, "loss": 0.277, "step": 486 }, { "epoch": 2.04, "learning_rate": 4.934897930252887e-06, "loss": 0.2744, "step": 487 }, { "epoch": 2.04, "learning_rate": 4.895974444950743e-06, "loss": 0.2799, "step": 488 }, { "epoch": 2.05, "learning_rate": 4.857155249545197e-06, "loss": 0.2943, "step": 489 }, { "epoch": 2.05, "learning_rate": 4.8184411372238724e-06, "loss": 0.2936, "step": 490 }, { "epoch": 2.05, "learning_rate": 4.779832899027243e-06, "loss": 0.2746, "step": 491 }, { "epoch": 2.06, "learning_rate": 4.7413313238324556e-06, "loss": 0.2795, "step": 492 }, { "epoch": 2.06, "learning_rate": 4.702937198337241e-06, "loss": 0.2914, "step": 493 }, { "epoch": 2.07, "learning_rate": 4.66465130704382e-06, "loss": 0.2793, "step": 494 }, { "epoch": 2.07, "learning_rate": 4.626474432242879e-06, "loss": 0.2842, "step": 495 }, { "epoch": 2.08, "learning_rate": 4.58840735399758e-06, "loss": 0.2617, "step": 496 }, { "epoch": 2.08, "learning_rate": 4.550450850127626e-06, "loss": 0.2662, "step": 497 }, { "epoch": 2.08, "learning_rate": 4.512605696193371e-06, "loss": 0.2748, "step": 498 }, { "epoch": 2.09, "learning_rate": 4.474872665479974e-06, "loss": 0.2757, "step": 499 }, { "epoch": 2.09, "learning_rate": 4.437252528981586e-06, "loss": 0.2774, "step": 500 }, { "epoch": 2.1, "learning_rate": 4.3997460553856095e-06, "loss": 0.2918, "step": 501 }, { "epoch": 2.1, "learning_rate": 4.3623540110569935e-06, "loss": 0.2629, "step": 502 }, { "epoch": 2.1, "learning_rate": 4.3250771600225536e-06, "loss": 0.2864, "step": 503 }, { "epoch": 2.11, "learning_rate": 4.2879162639553925e-06, "loss": 0.2888, "step": 504 }, { "epoch": 2.11, "learning_rate": 4.250872082159305e-06, "loss": 0.2739, "step": 505 }, { "epoch": 2.12, "learning_rate": 4.213945371553292e-06, "loss": 0.2943, "step": 506 }, { "epoch": 2.12, "learning_rate": 4.177136886656067e-06, "loss": 0.2941, "step": 507 }, { "epoch": 2.13, "learning_rate": 4.140447379570663e-06, "loss": 0.2793, "step": 508 }, { "epoch": 2.13, "learning_rate": 4.103877599969056e-06, "loss": 0.2721, "step": 509 }, { "epoch": 2.13, "learning_rate": 4.067428295076833e-06, "loss": 0.2887, "step": 510 }, { "epoch": 2.14, "learning_rate": 4.0311002096579486e-06, "loss": 0.2767, "step": 511 }, { "epoch": 2.14, "learning_rate": 3.9948940859994964e-06, "loss": 0.2794, "step": 512 }, { "epoch": 2.15, "learning_rate": 3.958810663896531e-06, "loss": 0.2671, "step": 513 }, { "epoch": 2.15, "learning_rate": 3.922850680636968e-06, "loss": 0.2853, "step": 514 }, { "epoch": 2.15, "learning_rate": 3.8870148709865115e-06, "loss": 0.2874, "step": 515 }, { "epoch": 2.16, "learning_rate": 3.851303967173647e-06, "loss": 0.285, "step": 516 }, { "epoch": 2.16, "learning_rate": 3.815718698874672e-06, "loss": 0.2774, "step": 517 }, { "epoch": 2.17, "learning_rate": 3.780259793198784e-06, "loss": 0.2798, "step": 518 }, { "epoch": 2.17, "learning_rate": 3.744927974673237e-06, "loss": 0.2784, "step": 519 }, { "epoch": 2.18, "learning_rate": 3.709723965228531e-06, "loss": 0.2739, "step": 520 }, { "epoch": 2.18, "learning_rate": 3.6746484841836516e-06, "loss": 0.2825, "step": 521 }, { "epoch": 2.18, "learning_rate": 3.6397022482313804e-06, "loss": 0.2929, "step": 522 }, { "epoch": 2.19, "learning_rate": 3.6048859714236597e-06, "loss": 0.2661, "step": 523 }, { "epoch": 2.19, "learning_rate": 3.5702003651569883e-06, "loss": 0.2726, "step": 524 }, { "epoch": 2.2, "learning_rate": 3.5356461381578865e-06, "loss": 0.2776, "step": 525 }, { "epoch": 2.2, "learning_rate": 3.501223996468426e-06, "loss": 0.2857, "step": 526 }, { "epoch": 2.21, "learning_rate": 3.466934643431795e-06, "loss": 0.2654, "step": 527 }, { "epoch": 2.21, "learning_rate": 3.432778779677921e-06, "loss": 0.2733, "step": 528 }, { "epoch": 2.21, "learning_rate": 3.3987571031091735e-06, "loss": 0.2708, "step": 529 }, { "epoch": 2.22, "learning_rate": 3.36487030888608e-06, "loss": 0.2654, "step": 530 }, { "epoch": 2.22, "learning_rate": 3.3311190894131495e-06, "loss": 0.2674, "step": 531 }, { "epoch": 2.23, "learning_rate": 3.2975041343246937e-06, "loss": 0.2899, "step": 532 }, { "epoch": 2.23, "learning_rate": 3.264026130470762e-06, "loss": 0.2919, "step": 533 }, { "epoch": 2.23, "learning_rate": 3.230685761903094e-06, "loss": 0.2797, "step": 534 }, { "epoch": 2.24, "learning_rate": 3.1974837098611487e-06, "loss": 0.2717, "step": 535 }, { "epoch": 2.24, "learning_rate": 3.1644206527581734e-06, "loss": 0.2965, "step": 536 }, { "epoch": 2.25, "learning_rate": 3.1314972661673572e-06, "loss": 0.2806, "step": 537 }, { "epoch": 2.25, "learning_rate": 3.0987142228080137e-06, "loss": 0.2781, "step": 538 }, { "epoch": 2.26, "learning_rate": 3.0660721925318483e-06, "loss": 0.2628, "step": 539 }, { "epoch": 2.26, "learning_rate": 3.0335718423092553e-06, "loss": 0.2812, "step": 540 }, { "epoch": 2.26, "learning_rate": 3.0012138362157062e-06, "loss": 0.2826, "step": 541 }, { "epoch": 2.27, "learning_rate": 2.9689988354181742e-06, "loss": 0.2956, "step": 542 }, { "epoch": 2.27, "learning_rate": 2.9369274981616137e-06, "loss": 0.276, "step": 543 }, { "epoch": 2.28, "learning_rate": 2.905000479755531e-06, "loss": 0.2887, "step": 544 }, { "epoch": 2.28, "learning_rate": 2.8732184325605815e-06, "loss": 0.2927, "step": 545 }, { "epoch": 2.28, "learning_rate": 2.8415820059752397e-06, "loss": 0.3025, "step": 546 }, { "epoch": 2.29, "learning_rate": 2.8100918464225304e-06, "loss": 0.2713, "step": 547 }, { "epoch": 2.29, "learning_rate": 2.7787485973368288e-06, "loss": 0.2926, "step": 548 }, { "epoch": 2.3, "learning_rate": 2.7475528991507106e-06, "loss": 0.2858, "step": 549 }, { "epoch": 2.3, "learning_rate": 2.7165053892818495e-06, "loss": 0.2805, "step": 550 }, { "epoch": 2.31, "learning_rate": 2.685606702120019e-06, "loss": 0.2966, "step": 551 }, { "epoch": 2.31, "learning_rate": 2.654857469014113e-06, "loss": 0.2799, "step": 552 }, { "epoch": 2.31, "learning_rate": 2.624258318259253e-06, "loss": 0.2879, "step": 553 }, { "epoch": 2.32, "learning_rate": 2.5938098750839414e-06, "loss": 0.2838, "step": 554 }, { "epoch": 2.32, "learning_rate": 2.563512761637291e-06, "loss": 0.287, "step": 555 }, { "epoch": 2.33, "learning_rate": 2.5333675969763215e-06, "loss": 0.2933, "step": 556 }, { "epoch": 2.33, "learning_rate": 2.5033749970533015e-06, "loss": 0.2679, "step": 557 }, { "epoch": 2.33, "learning_rate": 2.4735355747031566e-06, "loss": 0.2697, "step": 558 }, { "epoch": 2.34, "learning_rate": 2.443849939630959e-06, "loss": 0.2877, "step": 559 }, { "epoch": 2.34, "learning_rate": 2.4143186983994715e-06, "loss": 0.2805, "step": 560 }, { "epoch": 2.35, "learning_rate": 2.384942454416734e-06, "loss": 0.2653, "step": 561 }, { "epoch": 2.35, "learning_rate": 2.3557218079237608e-06, "loss": 0.2629, "step": 562 }, { "epoch": 2.36, "learning_rate": 2.3266573559822568e-06, "loss": 0.2791, "step": 563 }, { "epoch": 2.36, "learning_rate": 2.2977496924624223e-06, "loss": 0.2759, "step": 564 }, { "epoch": 2.36, "learning_rate": 2.26899940803082e-06, "loss": 0.299, "step": 565 }, { "epoch": 2.37, "learning_rate": 2.240407090138309e-06, "loss": 0.2782, "step": 566 }, { "epoch": 2.37, "learning_rate": 2.211973323008041e-06, "loss": 0.2876, "step": 567 }, { "epoch": 2.38, "learning_rate": 2.183698687623511e-06, "loss": 0.2667, "step": 568 }, { "epoch": 2.38, "learning_rate": 2.155583761716703e-06, "loss": 0.2801, "step": 569 }, { "epoch": 2.38, "learning_rate": 2.1276291197562772e-06, "loss": 0.2823, "step": 570 }, { "epoch": 2.39, "learning_rate": 2.0998353329358355e-06, "loss": 0.2687, "step": 571 }, { "epoch": 2.39, "learning_rate": 2.072202969162234e-06, "loss": 0.2793, "step": 572 }, { "epoch": 2.4, "learning_rate": 2.0447325930440043e-06, "loss": 0.2905, "step": 573 }, { "epoch": 2.4, "learning_rate": 2.0174247658798054e-06, "loss": 0.2711, "step": 574 }, { "epoch": 2.41, "learning_rate": 1.990280045646954e-06, "loss": 0.2812, "step": 575 }, { "epoch": 2.41, "learning_rate": 1.9632989869900145e-06, "loss": 0.2889, "step": 576 }, { "epoch": 2.41, "learning_rate": 1.936482141209486e-06, "loss": 0.2894, "step": 577 }, { "epoch": 2.42, "learning_rate": 1.9098300562505266e-06, "loss": 0.287, "step": 578 }, { "epoch": 2.42, "learning_rate": 1.8833432766917514e-06, "loss": 0.265, "step": 579 }, { "epoch": 2.43, "learning_rate": 1.8570223437341118e-06, "loss": 0.267, "step": 580 }, { "epoch": 2.43, "learning_rate": 1.8308677951898435e-06, "loss": 0.2806, "step": 581 }, { "epoch": 2.44, "learning_rate": 1.8048801654714687e-06, "loss": 0.2855, "step": 582 }, { "epoch": 2.44, "learning_rate": 1.7790599855808732e-06, "loss": 0.2801, "step": 583 }, { "epoch": 2.44, "learning_rate": 1.7534077830984697e-06, "loss": 0.3075, "step": 584 }, { "epoch": 2.45, "learning_rate": 1.7279240821724063e-06, "loss": 0.2642, "step": 585 }, { "epoch": 2.45, "learning_rate": 1.7026094035078589e-06, "loss": 0.2687, "step": 586 }, { "epoch": 2.46, "learning_rate": 1.6774642643563955e-06, "loss": 0.292, "step": 587 }, { "epoch": 2.46, "learning_rate": 1.6524891785054097e-06, "loss": 0.2845, "step": 588 }, { "epoch": 2.46, "learning_rate": 1.6276846562676085e-06, "loss": 0.2811, "step": 589 }, { "epoch": 2.47, "learning_rate": 1.603051204470597e-06, "loss": 0.2693, "step": 590 }, { "epoch": 2.47, "learning_rate": 1.5785893264465257e-06, "loss": 0.2862, "step": 591 }, { "epoch": 2.48, "learning_rate": 1.5542995220217961e-06, "loss": 0.2855, "step": 592 }, { "epoch": 2.48, "learning_rate": 1.530182287506855e-06, "loss": 0.2739, "step": 593 }, { "epoch": 2.49, "learning_rate": 1.506238115686044e-06, "loss": 0.2747, "step": 594 }, { "epoch": 2.49, "learning_rate": 1.4824674958075436e-06, "loss": 0.2855, "step": 595 }, { "epoch": 2.49, "learning_rate": 1.458870913573368e-06, "loss": 0.2549, "step": 596 }, { "epoch": 2.5, "learning_rate": 1.4354488511294418e-06, "loss": 0.2839, "step": 597 }, { "epoch": 2.5, "learning_rate": 1.4122017870557458e-06, "loss": 0.2761, "step": 598 }, { "epoch": 2.51, "learning_rate": 1.3891301963565473e-06, "loss": 0.2748, "step": 599 }, { "epoch": 2.51, "learning_rate": 1.3662345504506903e-06, "loss": 0.2749, "step": 600 }, { "epoch": 2.51, "learning_rate": 1.343515317161952e-06, "loss": 0.2668, "step": 601 }, { "epoch": 2.52, "learning_rate": 1.3209729607095022e-06, "loss": 0.269, "step": 602 }, { "epoch": 2.52, "learning_rate": 1.2986079416984088e-06, "loss": 0.262, "step": 603 }, { "epoch": 2.53, "learning_rate": 1.2764207171102206e-06, "loss": 0.2749, "step": 604 }, { "epoch": 2.53, "learning_rate": 1.2544117402936373e-06, "loss": 0.2641, "step": 605 }, { "epoch": 2.54, "learning_rate": 1.232581460955249e-06, "loss": 0.2747, "step": 606 }, { "epoch": 2.54, "learning_rate": 1.2109303251503434e-06, "loss": 0.2792, "step": 607 }, { "epoch": 2.54, "learning_rate": 1.189458775273784e-06, "loss": 0.294, "step": 608 }, { "epoch": 2.55, "learning_rate": 1.1681672500509866e-06, "loss": 0.2683, "step": 609 }, { "epoch": 2.55, "learning_rate": 1.147056184528943e-06, "loss": 0.2803, "step": 610 }, { "epoch": 2.56, "learning_rate": 1.1261260100673355e-06, "loss": 0.2867, "step": 611 }, { "epoch": 2.56, "learning_rate": 1.1053771543297198e-06, "loss": 0.2863, "step": 612 }, { "epoch": 2.56, "learning_rate": 1.0848100412747954e-06, "loss": 0.2759, "step": 613 }, { "epoch": 2.57, "learning_rate": 1.0644250911477306e-06, "loss": 0.269, "step": 614 }, { "epoch": 2.57, "learning_rate": 1.0442227204715872e-06, "loss": 0.2931, "step": 615 }, { "epoch": 2.58, "learning_rate": 1.0242033420388008e-06, "loss": 0.2823, "step": 616 }, { "epoch": 2.58, "learning_rate": 1.0043673649027519e-06, "loss": 0.2825, "step": 617 }, { "epoch": 2.59, "learning_rate": 9.8471519436941e-07, "loss": 0.2799, "step": 618 }, { "epoch": 2.59, "learning_rate": 9.652472319890372e-07, "loss": 0.2811, "step": 619 }, { "epoch": 2.59, "learning_rate": 9.459638755480038e-07, "loss": 0.271, "step": 620 }, { "epoch": 2.6, "learning_rate": 9.268655190606501e-07, "loss": 0.2781, "step": 621 }, { "epoch": 2.6, "learning_rate": 9.079525527612321e-07, "loss": 0.275, "step": 622 }, { "epoch": 2.61, "learning_rate": 8.892253630959502e-07, "loss": 0.2699, "step": 623 }, { "epoch": 2.61, "learning_rate": 8.706843327150605e-07, "loss": 0.2765, "step": 624 }, { "epoch": 2.62, "learning_rate": 8.523298404650504e-07, "loss": 0.2713, "step": 625 }, { "epoch": 2.62, "learning_rate": 8.34162261380892e-07, "loss": 0.286, "step": 626 }, { "epoch": 2.62, "learning_rate": 8.161819666783888e-07, "loss": 0.2642, "step": 627 }, { "epoch": 2.63, "learning_rate": 7.983893237465878e-07, "loss": 0.2822, "step": 628 }, { "epoch": 2.63, "learning_rate": 7.807846961402699e-07, "loss": 0.2743, "step": 629 }, { "epoch": 2.64, "learning_rate": 7.633684435725208e-07, "loss": 0.2573, "step": 630 }, { "epoch": 2.64, "learning_rate": 7.461409219073857e-07, "loss": 0.2813, "step": 631 }, { "epoch": 2.64, "learning_rate": 7.291024831525961e-07, "loss": 0.2854, "step": 632 }, { "epoch": 2.65, "learning_rate": 7.122534754523768e-07, "loss": 0.2888, "step": 633 }, { "epoch": 2.65, "learning_rate": 6.955942430803298e-07, "loss": 0.27, "step": 634 }, { "epoch": 2.66, "learning_rate": 6.791251264324039e-07, "loss": 0.2792, "step": 635 }, { "epoch": 2.66, "learning_rate": 6.628464620199404e-07, "loss": 0.2774, "step": 636 }, { "epoch": 2.67, "learning_rate": 6.467585824627886e-07, "loss": 0.2874, "step": 637 }, { "epoch": 2.67, "learning_rate": 6.30861816482522e-07, "loss": 0.2792, "step": 638 }, { "epoch": 2.67, "learning_rate": 6.151564888957084e-07, "loss": 0.2688, "step": 639 }, { "epoch": 2.68, "learning_rate": 5.996429206072874e-07, "loss": 0.2653, "step": 640 }, { "epoch": 2.68, "learning_rate": 5.843214286039956e-07, "loss": 0.2846, "step": 641 }, { "epoch": 2.69, "learning_rate": 5.691923259479093e-07, "loss": 0.275, "step": 642 }, { "epoch": 2.69, "learning_rate": 5.542559217700339e-07, "loss": 0.2796, "step": 643 }, { "epoch": 2.69, "learning_rate": 5.395125212639895e-07, "loss": 0.2788, "step": 644 }, { "epoch": 2.7, "learning_rate": 5.249624256797803e-07, "loss": 0.2688, "step": 645 }, { "epoch": 2.7, "learning_rate": 5.106059323176371e-07, "loss": 0.2817, "step": 646 }, { "epoch": 2.71, "learning_rate": 4.964433345219354e-07, "loss": 0.2784, "step": 647 }, { "epoch": 2.71, "learning_rate": 4.824749216752134e-07, "loss": 0.2789, "step": 648 }, { "epoch": 2.72, "learning_rate": 4.6870097919224923e-07, "loss": 0.2691, "step": 649 }, { "epoch": 2.72, "learning_rate": 4.551217885142378e-07, "loss": 0.2759, "step": 650 }, { "epoch": 2.72, "learning_rate": 4.417376271030327e-07, "loss": 0.2658, "step": 651 }, { "epoch": 2.73, "learning_rate": 4.285487684354772e-07, "loss": 0.2678, "step": 652 }, { "epoch": 2.73, "learning_rate": 4.1555548199782357e-07, "loss": 0.2867, "step": 653 }, { "epoch": 2.74, "learning_rate": 4.0275803328021946e-07, "loss": 0.2882, "step": 654 }, { "epoch": 2.74, "learning_rate": 3.9015668377128446e-07, "loss": 0.2879, "step": 655 }, { "epoch": 2.74, "learning_rate": 3.777516909527701e-07, "loss": 0.2676, "step": 656 }, { "epoch": 2.75, "learning_rate": 3.6554330829429716e-07, "loss": 0.2806, "step": 657 }, { "epoch": 2.75, "learning_rate": 3.5353178524817566e-07, "loss": 0.2793, "step": 658 }, { "epoch": 2.76, "learning_rate": 3.417173672443075e-07, "loss": 0.28, "step": 659 }, { "epoch": 2.76, "learning_rate": 3.30100295685174e-07, "loss": 0.281, "step": 660 }, { "epoch": 2.77, "learning_rate": 3.1868080794090316e-07, "loss": 0.288, "step": 661 }, { "epoch": 2.77, "learning_rate": 3.0745913734441357e-07, "loss": 0.2726, "step": 662 }, { "epoch": 2.77, "learning_rate": 2.9643551318665917e-07, "loss": 0.2707, "step": 663 }, { "epoch": 2.78, "learning_rate": 2.8561016071192884e-07, "loss": 0.2706, "step": 664 }, { "epoch": 2.78, "learning_rate": 2.7498330111325635e-07, "loss": 0.2862, "step": 665 }, { "epoch": 2.79, "learning_rate": 2.6455515152789435e-07, "loss": 0.2803, "step": 666 }, { "epoch": 2.79, "learning_rate": 2.5432592503288e-07, "loss": 0.288, "step": 667 }, { "epoch": 2.79, "learning_rate": 2.442958306406795e-07, "loss": 0.2819, "step": 668 }, { "epoch": 2.8, "learning_rate": 2.3446507329492274e-07, "loss": 0.2679, "step": 669 }, { "epoch": 2.8, "learning_rate": 2.2483385386620317e-07, "loss": 0.2654, "step": 670 }, { "epoch": 2.81, "learning_rate": 2.1540236914799116e-07, "loss": 0.2812, "step": 671 }, { "epoch": 2.81, "learning_rate": 2.0617081185259512e-07, "loss": 0.2898, "step": 672 }, { "epoch": 2.82, "learning_rate": 1.9713937060723887e-07, "loss": 0.2848, "step": 673 }, { "epoch": 2.82, "learning_rate": 1.8830822995019593e-07, "loss": 0.29, "step": 674 }, { "epoch": 2.82, "learning_rate": 1.7967757032702481e-07, "loss": 0.2836, "step": 675 }, { "epoch": 2.83, "learning_rate": 1.7124756808688525e-07, "loss": 0.2878, "step": 676 }, { "epoch": 2.83, "learning_rate": 1.630183954789233e-07, "loss": 0.2695, "step": 677 }, { "epoch": 2.84, "learning_rate": 1.5499022064876412e-07, "loss": 0.2855, "step": 678 }, { "epoch": 2.84, "learning_rate": 1.4716320763507152e-07, "loss": 0.2836, "step": 679 }, { "epoch": 2.85, "learning_rate": 1.3953751636619162e-07, "loss": 0.2726, "step": 680 }, { "epoch": 2.85, "learning_rate": 1.3211330265689104e-07, "loss": 0.2808, "step": 681 }, { "epoch": 2.85, "learning_rate": 1.2489071820517394e-07, "loss": 0.2708, "step": 682 }, { "epoch": 2.86, "learning_rate": 1.1786991058917785e-07, "loss": 0.2905, "step": 683 }, { "epoch": 2.86, "learning_rate": 1.1105102326415929e-07, "loss": 0.2977, "step": 684 }, { "epoch": 2.87, "learning_rate": 1.0443419555956402e-07, "loss": 0.2726, "step": 685 }, { "epoch": 2.87, "learning_rate": 9.801956267618262e-08, "loss": 0.2702, "step": 686 }, { "epoch": 2.87, "learning_rate": 9.180725568338045e-08, "loss": 0.2987, "step": 687 }, { "epoch": 2.88, "learning_rate": 8.579740151642534e-08, "loss": 0.2706, "step": 688 }, { "epoch": 2.88, "learning_rate": 7.999012297389419e-08, "loss": 0.2755, "step": 689 }, { "epoch": 2.89, "learning_rate": 7.438553871516152e-08, "loss": 0.28, "step": 690 }, { "epoch": 2.89, "learning_rate": 6.898376325797596e-08, "loss": 0.2785, "step": 691 }, { "epoch": 2.9, "learning_rate": 6.378490697611761e-08, "loss": 0.2775, "step": 692 }, { "epoch": 2.9, "learning_rate": 5.878907609714879e-08, "loss": 0.2705, "step": 693 }, { "epoch": 2.9, "learning_rate": 5.399637270023683e-08, "loss": 0.2546, "step": 694 }, { "epoch": 2.91, "learning_rate": 4.940689471407356e-08, "loss": 0.2658, "step": 695 }, { "epoch": 2.91, "learning_rate": 4.502073591487244e-08, "loss": 0.2786, "step": 696 }, { "epoch": 2.92, "learning_rate": 4.083798592444899e-08, "loss": 0.2753, "step": 697 }, { "epoch": 2.92, "learning_rate": 3.68587302083967e-08, "loss": 0.2914, "step": 698 }, { "epoch": 2.92, "learning_rate": 3.308305007433399e-08, "loss": 0.2827, "step": 699 }, { "epoch": 2.93, "learning_rate": 2.9511022670246635e-08, "loss": 0.2731, "step": 700 }, { "epoch": 2.93, "learning_rate": 2.6142720982911264e-08, "loss": 0.2901, "step": 701 }, { "epoch": 2.94, "learning_rate": 2.2978213836400974e-08, "loss": 0.2711, "step": 702 }, { "epoch": 2.94, "learning_rate": 2.0017565890683154e-08, "loss": 0.2774, "step": 703 }, { "epoch": 2.95, "learning_rate": 1.726083764029607e-08, "loss": 0.2903, "step": 704 }, { "epoch": 2.95, "learning_rate": 1.4708085413113194e-08, "loss": 0.2848, "step": 705 }, { "epoch": 2.95, "learning_rate": 1.2359361369190804e-08, "loss": 0.2837, "step": 706 }, { "epoch": 2.96, "learning_rate": 1.0214713499706596e-08, "loss": 0.2665, "step": 707 }, { "epoch": 2.96, "learning_rate": 8.274185625971598e-09, "loss": 0.2779, "step": 708 }, { "epoch": 2.97, "learning_rate": 6.5378173985441994e-09, "loss": 0.2707, "step": 709 }, { "epoch": 2.97, "learning_rate": 5.0056442964119265e-09, "loss": 0.2554, "step": 710 }, { "epoch": 2.97, "learning_rate": 3.6776976262697937e-09, "loss": 0.2767, "step": 711 }, { "epoch": 2.98, "learning_rate": 2.5540045218819256e-09, "loss": 0.2892, "step": 712 }, { "epoch": 2.98, "learning_rate": 1.6345879435231138e-09, "loss": 0.2843, "step": 713 }, { "epoch": 2.99, "learning_rate": 9.194666775158567e-10, "loss": 0.2735, "step": 714 }, { "epoch": 2.99, "learning_rate": 4.086553358395584e-10, "loss": 0.2775, "step": 715 }, { "epoch": 3.0, "learning_rate": 1.0216435583743079e-10, "loss": 0.2786, "step": 716 }, { "epoch": 3.0, "learning_rate": 0.0, "loss": 0.2579, "step": 717 }, { "epoch": 3.0, "step": 717, "total_flos": 1.9663471898819297e+18, "train_loss": 0.3724504075788554, "train_runtime": 6685.3329, "train_samples_per_second": 54.728, "train_steps_per_second": 0.107 } ], "max_steps": 717, "num_train_epochs": 3, "total_flos": 1.9663471898819297e+18, "trial_name": null, "trial_params": null }