{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.10438413361169102, "eval_steps": 500, "global_step": 500, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 5.263157894736843e-07, "loss": 5.1732, "step": 1 }, { "epoch": 0.0, "learning_rate": 1.0526315789473685e-06, "loss": 5.8161, "step": 2 }, { "epoch": 0.0, "learning_rate": 1.5789473684210526e-06, "loss": 5.6552, "step": 3 }, { "epoch": 0.0, "learning_rate": 2.105263157894737e-06, "loss": 5.3255, "step": 4 }, { "epoch": 0.0, "learning_rate": 2.631578947368421e-06, "loss": 5.8869, "step": 5 }, { "epoch": 0.0, "learning_rate": 3.157894736842105e-06, "loss": 4.0768, "step": 6 }, { "epoch": 0.0, "learning_rate": 3.6842105263157896e-06, "loss": 3.9681, "step": 7 }, { "epoch": 0.0, "learning_rate": 4.210526315789474e-06, "loss": 4.2244, "step": 8 }, { "epoch": 0.0, "learning_rate": 4.736842105263158e-06, "loss": 3.1797, "step": 9 }, { "epoch": 0.0, "learning_rate": 5.263157894736842e-06, "loss": 3.2658, "step": 10 }, { "epoch": 0.0, "learning_rate": 5.789473684210527e-06, "loss": 2.925, "step": 11 }, { "epoch": 0.0, "learning_rate": 6.31578947368421e-06, "loss": 2.8324, "step": 12 }, { "epoch": 0.0, "learning_rate": 6.842105263157896e-06, "loss": 2.42, "step": 13 }, { "epoch": 0.0, "learning_rate": 7.368421052631579e-06, "loss": 2.1725, "step": 14 }, { "epoch": 0.0, "learning_rate": 7.894736842105265e-06, "loss": 2.482, "step": 15 }, { "epoch": 0.0, "learning_rate": 8.421052631578948e-06, "loss": 2.2798, "step": 16 }, { "epoch": 0.0, "learning_rate": 8.947368421052632e-06, "loss": 2.1004, "step": 17 }, { "epoch": 0.0, "learning_rate": 9.473684210526315e-06, "loss": 1.9609, "step": 18 }, { "epoch": 0.0, "learning_rate": 1e-05, "loss": 2.0091, "step": 19 }, { "epoch": 0.0, "learning_rate": 1.0526315789473684e-05, "loss": 1.8047, "step": 20 }, { "epoch": 0.0, "learning_rate": 1.105263157894737e-05, "loss": 1.9016, "step": 21 }, { "epoch": 0.0, "learning_rate": 1.1578947368421053e-05, "loss": 1.8817, "step": 22 }, { "epoch": 0.0, "learning_rate": 1.2105263157894737e-05, "loss": 1.9054, "step": 23 }, { "epoch": 0.01, "learning_rate": 1.263157894736842e-05, "loss": 1.6584, "step": 24 }, { "epoch": 0.01, "learning_rate": 1.3157894736842108e-05, "loss": 1.835, "step": 25 }, { "epoch": 0.01, "learning_rate": 1.3684210526315791e-05, "loss": 1.8795, "step": 26 }, { "epoch": 0.01, "learning_rate": 1.4210526315789475e-05, "loss": 2.0087, "step": 27 }, { "epoch": 0.01, "learning_rate": 1.4736842105263159e-05, "loss": 2.0281, "step": 28 }, { "epoch": 0.01, "learning_rate": 1.5263157894736846e-05, "loss": 1.8621, "step": 29 }, { "epoch": 0.01, "learning_rate": 1.578947368421053e-05, "loss": 2.1057, "step": 30 }, { "epoch": 0.01, "learning_rate": 1.6315789473684213e-05, "loss": 1.9834, "step": 31 }, { "epoch": 0.01, "learning_rate": 1.6842105263157896e-05, "loss": 1.8857, "step": 32 }, { "epoch": 0.01, "learning_rate": 1.736842105263158e-05, "loss": 1.861, "step": 33 }, { "epoch": 0.01, "learning_rate": 1.7894736842105264e-05, "loss": 1.9277, "step": 34 }, { "epoch": 0.01, "learning_rate": 1.8421052631578947e-05, "loss": 2.0571, "step": 35 }, { "epoch": 0.01, "learning_rate": 1.894736842105263e-05, "loss": 2.0525, "step": 36 }, { "epoch": 0.01, "learning_rate": 1.9473684210526318e-05, "loss": 1.8807, "step": 37 }, { "epoch": 0.01, "learning_rate": 2e-05, "loss": 1.84, "step": 38 }, { "epoch": 0.01, "learning_rate": 1.998353909465021e-05, "loss": 1.7472, "step": 39 }, { "epoch": 0.01, "learning_rate": 1.9967078189300412e-05, "loss": 1.8333, "step": 40 }, { "epoch": 0.01, "learning_rate": 1.995061728395062e-05, "loss": 2.0465, "step": 41 }, { "epoch": 0.01, "learning_rate": 1.9934156378600823e-05, "loss": 1.9453, "step": 42 }, { "epoch": 0.01, "learning_rate": 1.991769547325103e-05, "loss": 1.6707, "step": 43 }, { "epoch": 0.01, "learning_rate": 1.9901234567901237e-05, "loss": 1.8428, "step": 44 }, { "epoch": 0.01, "learning_rate": 1.988477366255144e-05, "loss": 1.8087, "step": 45 }, { "epoch": 0.01, "learning_rate": 1.9868312757201648e-05, "loss": 2.0397, "step": 46 }, { "epoch": 0.01, "learning_rate": 1.9851851851851855e-05, "loss": 1.7608, "step": 47 }, { "epoch": 0.01, "learning_rate": 1.983539094650206e-05, "loss": 1.7768, "step": 48 }, { "epoch": 0.01, "learning_rate": 1.9818930041152265e-05, "loss": 1.9012, "step": 49 }, { "epoch": 0.01, "learning_rate": 1.9802469135802472e-05, "loss": 1.7903, "step": 50 }, { "epoch": 0.01, "learning_rate": 1.9786008230452676e-05, "loss": 1.7743, "step": 51 }, { "epoch": 0.01, "learning_rate": 1.9769547325102883e-05, "loss": 1.9404, "step": 52 }, { "epoch": 0.01, "learning_rate": 1.9753086419753087e-05, "loss": 2.0701, "step": 53 }, { "epoch": 0.01, "learning_rate": 1.9736625514403294e-05, "loss": 1.8122, "step": 54 }, { "epoch": 0.01, "learning_rate": 1.97201646090535e-05, "loss": 1.7869, "step": 55 }, { "epoch": 0.01, "learning_rate": 1.9703703703703704e-05, "loss": 2.0089, "step": 56 }, { "epoch": 0.01, "learning_rate": 1.968724279835391e-05, "loss": 1.9942, "step": 57 }, { "epoch": 0.01, "learning_rate": 1.9670781893004115e-05, "loss": 1.7982, "step": 58 }, { "epoch": 0.01, "learning_rate": 1.9654320987654322e-05, "loss": 1.9373, "step": 59 }, { "epoch": 0.01, "learning_rate": 1.963786008230453e-05, "loss": 2.0311, "step": 60 }, { "epoch": 0.01, "learning_rate": 1.9621399176954733e-05, "loss": 2.0759, "step": 61 }, { "epoch": 0.01, "learning_rate": 1.960493827160494e-05, "loss": 1.8915, "step": 62 }, { "epoch": 0.01, "learning_rate": 1.9588477366255147e-05, "loss": 1.7898, "step": 63 }, { "epoch": 0.01, "learning_rate": 1.9572016460905354e-05, "loss": 1.8118, "step": 64 }, { "epoch": 0.01, "learning_rate": 1.9555555555555557e-05, "loss": 1.9399, "step": 65 }, { "epoch": 0.01, "learning_rate": 1.9539094650205764e-05, "loss": 1.8565, "step": 66 }, { "epoch": 0.01, "learning_rate": 1.9522633744855968e-05, "loss": 1.8078, "step": 67 }, { "epoch": 0.01, "learning_rate": 1.9506172839506175e-05, "loss": 1.9831, "step": 68 }, { "epoch": 0.01, "learning_rate": 1.9489711934156382e-05, "loss": 1.7514, "step": 69 }, { "epoch": 0.01, "learning_rate": 1.9473251028806586e-05, "loss": 1.9392, "step": 70 }, { "epoch": 0.01, "learning_rate": 1.9456790123456793e-05, "loss": 1.8271, "step": 71 }, { "epoch": 0.02, "learning_rate": 1.9440329218106996e-05, "loss": 1.7618, "step": 72 }, { "epoch": 0.02, "learning_rate": 1.9423868312757203e-05, "loss": 1.9523, "step": 73 }, { "epoch": 0.02, "learning_rate": 1.9407407407407407e-05, "loss": 1.9452, "step": 74 }, { "epoch": 0.02, "learning_rate": 1.9390946502057614e-05, "loss": 1.8205, "step": 75 }, { "epoch": 0.02, "learning_rate": 1.937448559670782e-05, "loss": 1.9265, "step": 76 }, { "epoch": 0.02, "learning_rate": 1.9358024691358025e-05, "loss": 1.8792, "step": 77 }, { "epoch": 0.02, "learning_rate": 1.934156378600823e-05, "loss": 1.7625, "step": 78 }, { "epoch": 0.02, "learning_rate": 1.932510288065844e-05, "loss": 1.8257, "step": 79 }, { "epoch": 0.02, "learning_rate": 1.9308641975308646e-05, "loss": 1.9733, "step": 80 }, { "epoch": 0.02, "learning_rate": 1.929218106995885e-05, "loss": 2.0385, "step": 81 }, { "epoch": 0.02, "learning_rate": 1.9275720164609056e-05, "loss": 1.9586, "step": 82 }, { "epoch": 0.02, "learning_rate": 1.925925925925926e-05, "loss": 2.0534, "step": 83 }, { "epoch": 0.02, "learning_rate": 1.9242798353909467e-05, "loss": 1.9244, "step": 84 }, { "epoch": 0.02, "learning_rate": 1.9226337448559674e-05, "loss": 1.9197, "step": 85 }, { "epoch": 0.02, "learning_rate": 1.9209876543209878e-05, "loss": 1.7914, "step": 86 }, { "epoch": 0.02, "learning_rate": 1.9193415637860085e-05, "loss": 1.7272, "step": 87 }, { "epoch": 0.02, "learning_rate": 1.9176954732510288e-05, "loss": 1.8011, "step": 88 }, { "epoch": 0.02, "learning_rate": 1.9160493827160495e-05, "loss": 1.9281, "step": 89 }, { "epoch": 0.02, "learning_rate": 1.91440329218107e-05, "loss": 1.8483, "step": 90 }, { "epoch": 0.02, "learning_rate": 1.9127572016460906e-05, "loss": 1.7125, "step": 91 }, { "epoch": 0.02, "learning_rate": 1.9111111111111113e-05, "loss": 1.8657, "step": 92 }, { "epoch": 0.02, "learning_rate": 1.9094650205761317e-05, "loss": 1.7929, "step": 93 }, { "epoch": 0.02, "learning_rate": 1.9078189300411524e-05, "loss": 1.9798, "step": 94 }, { "epoch": 0.02, "learning_rate": 1.906172839506173e-05, "loss": 1.7697, "step": 95 }, { "epoch": 0.02, "learning_rate": 1.9045267489711938e-05, "loss": 1.9684, "step": 96 }, { "epoch": 0.02, "learning_rate": 1.902880658436214e-05, "loss": 1.7967, "step": 97 }, { "epoch": 0.02, "learning_rate": 1.901234567901235e-05, "loss": 1.6673, "step": 98 }, { "epoch": 0.02, "learning_rate": 1.8995884773662555e-05, "loss": 1.8858, "step": 99 }, { "epoch": 0.02, "learning_rate": 1.897942386831276e-05, "loss": 1.9368, "step": 100 }, { "epoch": 0.02, "learning_rate": 1.8962962962962966e-05, "loss": 1.8163, "step": 101 }, { "epoch": 0.02, "learning_rate": 1.894650205761317e-05, "loss": 1.8437, "step": 102 }, { "epoch": 0.02, "learning_rate": 1.8930041152263377e-05, "loss": 1.749, "step": 103 }, { "epoch": 0.02, "learning_rate": 1.891358024691358e-05, "loss": 1.7382, "step": 104 }, { "epoch": 0.02, "learning_rate": 1.8897119341563787e-05, "loss": 1.8233, "step": 105 }, { "epoch": 0.02, "learning_rate": 1.8880658436213994e-05, "loss": 1.9109, "step": 106 }, { "epoch": 0.02, "learning_rate": 1.8864197530864198e-05, "loss": 1.891, "step": 107 }, { "epoch": 0.02, "learning_rate": 1.8847736625514405e-05, "loss": 1.7295, "step": 108 }, { "epoch": 0.02, "learning_rate": 1.883127572016461e-05, "loss": 1.9295, "step": 109 }, { "epoch": 0.02, "learning_rate": 1.8814814814814816e-05, "loss": 2.0191, "step": 110 }, { "epoch": 0.02, "learning_rate": 1.8798353909465023e-05, "loss": 1.8702, "step": 111 }, { "epoch": 0.02, "learning_rate": 1.878189300411523e-05, "loss": 1.7945, "step": 112 }, { "epoch": 0.02, "learning_rate": 1.8765432098765433e-05, "loss": 1.7584, "step": 113 }, { "epoch": 0.02, "learning_rate": 1.874897119341564e-05, "loss": 1.7666, "step": 114 }, { "epoch": 0.02, "learning_rate": 1.8732510288065847e-05, "loss": 1.7273, "step": 115 }, { "epoch": 0.02, "learning_rate": 1.871604938271605e-05, "loss": 1.7538, "step": 116 }, { "epoch": 0.02, "learning_rate": 1.8699588477366258e-05, "loss": 1.8405, "step": 117 }, { "epoch": 0.02, "learning_rate": 1.868312757201646e-05, "loss": 1.9431, "step": 118 }, { "epoch": 0.02, "learning_rate": 1.866666666666667e-05, "loss": 1.7894, "step": 119 }, { "epoch": 0.03, "learning_rate": 1.8650205761316872e-05, "loss": 1.7503, "step": 120 }, { "epoch": 0.03, "learning_rate": 1.863374485596708e-05, "loss": 1.9076, "step": 121 }, { "epoch": 0.03, "learning_rate": 1.8617283950617286e-05, "loss": 1.7864, "step": 122 }, { "epoch": 0.03, "learning_rate": 1.860082304526749e-05, "loss": 1.8883, "step": 123 }, { "epoch": 0.03, "learning_rate": 1.8584362139917697e-05, "loss": 1.7145, "step": 124 }, { "epoch": 0.03, "learning_rate": 1.85679012345679e-05, "loss": 1.7949, "step": 125 }, { "epoch": 0.03, "learning_rate": 1.8551440329218108e-05, "loss": 1.8263, "step": 126 }, { "epoch": 0.03, "learning_rate": 1.8534979423868315e-05, "loss": 1.9629, "step": 127 }, { "epoch": 0.03, "learning_rate": 1.851851851851852e-05, "loss": 1.8152, "step": 128 }, { "epoch": 0.03, "learning_rate": 1.8502057613168725e-05, "loss": 2.0334, "step": 129 }, { "epoch": 0.03, "learning_rate": 1.8485596707818932e-05, "loss": 1.7458, "step": 130 }, { "epoch": 0.03, "learning_rate": 1.846913580246914e-05, "loss": 1.8612, "step": 131 }, { "epoch": 0.03, "learning_rate": 1.8452674897119343e-05, "loss": 1.8139, "step": 132 }, { "epoch": 0.03, "learning_rate": 1.843621399176955e-05, "loss": 1.7461, "step": 133 }, { "epoch": 0.03, "learning_rate": 1.8419753086419754e-05, "loss": 1.7212, "step": 134 }, { "epoch": 0.03, "learning_rate": 1.840329218106996e-05, "loss": 1.9717, "step": 135 }, { "epoch": 0.03, "learning_rate": 1.8386831275720164e-05, "loss": 1.7914, "step": 136 }, { "epoch": 0.03, "learning_rate": 1.837037037037037e-05, "loss": 1.8589, "step": 137 }, { "epoch": 0.03, "learning_rate": 1.835390946502058e-05, "loss": 1.8321, "step": 138 }, { "epoch": 0.03, "learning_rate": 1.8337448559670782e-05, "loss": 1.7982, "step": 139 }, { "epoch": 0.03, "learning_rate": 1.832098765432099e-05, "loss": 1.7839, "step": 140 }, { "epoch": 0.03, "learning_rate": 1.8304526748971193e-05, "loss": 1.7034, "step": 141 }, { "epoch": 0.03, "learning_rate": 1.82880658436214e-05, "loss": 1.6992, "step": 142 }, { "epoch": 0.03, "learning_rate": 1.8271604938271607e-05, "loss": 1.8831, "step": 143 }, { "epoch": 0.03, "learning_rate": 1.8255144032921814e-05, "loss": 1.8455, "step": 144 }, { "epoch": 0.03, "learning_rate": 1.8238683127572017e-05, "loss": 1.9118, "step": 145 }, { "epoch": 0.03, "learning_rate": 1.8222222222222224e-05, "loss": 1.8513, "step": 146 }, { "epoch": 0.03, "learning_rate": 1.820576131687243e-05, "loss": 1.7875, "step": 147 }, { "epoch": 0.03, "learning_rate": 1.8189300411522635e-05, "loss": 1.8067, "step": 148 }, { "epoch": 0.03, "learning_rate": 1.8172839506172842e-05, "loss": 1.7377, "step": 149 }, { "epoch": 0.03, "learning_rate": 1.8156378600823046e-05, "loss": 1.8481, "step": 150 }, { "epoch": 0.03, "learning_rate": 1.8139917695473253e-05, "loss": 1.7652, "step": 151 }, { "epoch": 0.03, "learning_rate": 1.812345679012346e-05, "loss": 1.829, "step": 152 }, { "epoch": 0.03, "learning_rate": 1.8106995884773663e-05, "loss": 1.6218, "step": 153 }, { "epoch": 0.03, "learning_rate": 1.809053497942387e-05, "loss": 1.8349, "step": 154 }, { "epoch": 0.03, "learning_rate": 1.8074074074074074e-05, "loss": 1.7485, "step": 155 }, { "epoch": 0.03, "learning_rate": 1.805761316872428e-05, "loss": 1.7279, "step": 156 }, { "epoch": 0.03, "learning_rate": 1.8041152263374485e-05, "loss": 1.6958, "step": 157 }, { "epoch": 0.03, "learning_rate": 1.802469135802469e-05, "loss": 1.8523, "step": 158 }, { "epoch": 0.03, "learning_rate": 1.80082304526749e-05, "loss": 1.7583, "step": 159 }, { "epoch": 0.03, "learning_rate": 1.7991769547325106e-05, "loss": 1.8854, "step": 160 }, { "epoch": 0.03, "learning_rate": 1.797530864197531e-05, "loss": 1.7936, "step": 161 }, { "epoch": 0.03, "learning_rate": 1.7958847736625516e-05, "loss": 1.6418, "step": 162 }, { "epoch": 0.03, "learning_rate": 1.7942386831275723e-05, "loss": 1.7516, "step": 163 }, { "epoch": 0.03, "learning_rate": 1.7925925925925927e-05, "loss": 1.8995, "step": 164 }, { "epoch": 0.03, "learning_rate": 1.7909465020576134e-05, "loss": 1.7528, "step": 165 }, { "epoch": 0.03, "learning_rate": 1.7893004115226338e-05, "loss": 1.744, "step": 166 }, { "epoch": 0.03, "learning_rate": 1.7876543209876545e-05, "loss": 1.7649, "step": 167 }, { "epoch": 0.04, "learning_rate": 1.786008230452675e-05, "loss": 1.7355, "step": 168 }, { "epoch": 0.04, "learning_rate": 1.7843621399176955e-05, "loss": 1.6679, "step": 169 }, { "epoch": 0.04, "learning_rate": 1.7827160493827162e-05, "loss": 1.8228, "step": 170 }, { "epoch": 0.04, "learning_rate": 1.7810699588477366e-05, "loss": 1.7407, "step": 171 }, { "epoch": 0.04, "learning_rate": 1.7794238683127573e-05, "loss": 1.8014, "step": 172 }, { "epoch": 0.04, "learning_rate": 1.7777777777777777e-05, "loss": 1.8253, "step": 173 }, { "epoch": 0.04, "learning_rate": 1.7761316872427984e-05, "loss": 1.782, "step": 174 }, { "epoch": 0.04, "learning_rate": 1.774485596707819e-05, "loss": 1.7854, "step": 175 }, { "epoch": 0.04, "learning_rate": 1.7728395061728398e-05, "loss": 1.6355, "step": 176 }, { "epoch": 0.04, "learning_rate": 1.77119341563786e-05, "loss": 1.7025, "step": 177 }, { "epoch": 0.04, "learning_rate": 1.769547325102881e-05, "loss": 1.7653, "step": 178 }, { "epoch": 0.04, "learning_rate": 1.7679012345679015e-05, "loss": 1.7699, "step": 179 }, { "epoch": 0.04, "learning_rate": 1.766255144032922e-05, "loss": 1.9603, "step": 180 }, { "epoch": 0.04, "learning_rate": 1.7646090534979426e-05, "loss": 1.8155, "step": 181 }, { "epoch": 0.04, "learning_rate": 1.7629629629629633e-05, "loss": 1.7607, "step": 182 }, { "epoch": 0.04, "learning_rate": 1.7613168724279837e-05, "loss": 1.7496, "step": 183 }, { "epoch": 0.04, "learning_rate": 1.7596707818930044e-05, "loss": 1.7708, "step": 184 }, { "epoch": 0.04, "learning_rate": 1.7580246913580247e-05, "loss": 1.7439, "step": 185 }, { "epoch": 0.04, "learning_rate": 1.7563786008230454e-05, "loss": 2.0802, "step": 186 }, { "epoch": 0.04, "learning_rate": 1.7547325102880658e-05, "loss": 2.0493, "step": 187 }, { "epoch": 0.04, "learning_rate": 1.7530864197530865e-05, "loss": 1.8499, "step": 188 }, { "epoch": 0.04, "learning_rate": 1.7514403292181072e-05, "loss": 2.0229, "step": 189 }, { "epoch": 0.04, "learning_rate": 1.7497942386831276e-05, "loss": 1.9342, "step": 190 }, { "epoch": 0.04, "learning_rate": 1.7481481481481483e-05, "loss": 1.8764, "step": 191 }, { "epoch": 0.04, "learning_rate": 1.746502057613169e-05, "loss": 1.9374, "step": 192 }, { "epoch": 0.04, "learning_rate": 1.7448559670781893e-05, "loss": 1.8678, "step": 193 }, { "epoch": 0.04, "learning_rate": 1.74320987654321e-05, "loss": 1.903, "step": 194 }, { "epoch": 0.04, "learning_rate": 1.7415637860082307e-05, "loss": 2.0272, "step": 195 }, { "epoch": 0.04, "learning_rate": 1.739917695473251e-05, "loss": 1.9598, "step": 196 }, { "epoch": 0.04, "learning_rate": 1.7382716049382718e-05, "loss": 1.8752, "step": 197 }, { "epoch": 0.04, "learning_rate": 1.7366255144032925e-05, "loss": 1.9103, "step": 198 }, { "epoch": 0.04, "learning_rate": 1.734979423868313e-05, "loss": 1.8263, "step": 199 }, { "epoch": 0.04, "learning_rate": 1.7333333333333336e-05, "loss": 1.8219, "step": 200 }, { "epoch": 0.04, "learning_rate": 1.731687242798354e-05, "loss": 1.6993, "step": 201 }, { "epoch": 0.04, "learning_rate": 1.7300411522633746e-05, "loss": 1.8284, "step": 202 }, { "epoch": 0.04, "learning_rate": 1.728395061728395e-05, "loss": 1.894, "step": 203 }, { "epoch": 0.04, "learning_rate": 1.7267489711934157e-05, "loss": 1.6447, "step": 204 }, { "epoch": 0.04, "learning_rate": 1.7251028806584364e-05, "loss": 1.7097, "step": 205 }, { "epoch": 0.04, "learning_rate": 1.7234567901234568e-05, "loss": 1.6909, "step": 206 }, { "epoch": 0.04, "learning_rate": 1.7218106995884775e-05, "loss": 1.7155, "step": 207 }, { "epoch": 0.04, "learning_rate": 1.720164609053498e-05, "loss": 1.5556, "step": 208 }, { "epoch": 0.04, "learning_rate": 1.7185185185185185e-05, "loss": 1.8037, "step": 209 }, { "epoch": 0.04, "learning_rate": 1.7168724279835392e-05, "loss": 1.5867, "step": 210 }, { "epoch": 0.04, "learning_rate": 1.71522633744856e-05, "loss": 1.6997, "step": 211 }, { "epoch": 0.04, "learning_rate": 1.7135802469135806e-05, "loss": 1.6818, "step": 212 }, { "epoch": 0.04, "learning_rate": 1.711934156378601e-05, "loss": 1.6912, "step": 213 }, { "epoch": 0.04, "learning_rate": 1.7102880658436217e-05, "loss": 1.7557, "step": 214 }, { "epoch": 0.04, "learning_rate": 1.708641975308642e-05, "loss": 1.8177, "step": 215 }, { "epoch": 0.05, "learning_rate": 1.7069958847736628e-05, "loss": 1.6848, "step": 216 }, { "epoch": 0.05, "learning_rate": 1.705349794238683e-05, "loss": 1.5541, "step": 217 }, { "epoch": 0.05, "learning_rate": 1.7037037037037038e-05, "loss": 1.6116, "step": 218 }, { "epoch": 0.05, "learning_rate": 1.7020576131687242e-05, "loss": 1.5938, "step": 219 }, { "epoch": 0.05, "learning_rate": 1.700411522633745e-05, "loss": 1.7408, "step": 220 }, { "epoch": 0.05, "learning_rate": 1.6987654320987656e-05, "loss": 1.6173, "step": 221 }, { "epoch": 0.05, "learning_rate": 1.697119341563786e-05, "loss": 1.5369, "step": 222 }, { "epoch": 0.05, "learning_rate": 1.6954732510288067e-05, "loss": 1.5388, "step": 223 }, { "epoch": 0.05, "learning_rate": 1.6938271604938274e-05, "loss": 1.726, "step": 224 }, { "epoch": 0.05, "learning_rate": 1.692181069958848e-05, "loss": 2.0651, "step": 225 }, { "epoch": 0.05, "learning_rate": 1.6905349794238684e-05, "loss": 1.7892, "step": 226 }, { "epoch": 0.05, "learning_rate": 1.688888888888889e-05, "loss": 1.7085, "step": 227 }, { "epoch": 0.05, "learning_rate": 1.68724279835391e-05, "loss": 1.5394, "step": 228 }, { "epoch": 0.05, "learning_rate": 1.6855967078189302e-05, "loss": 1.7522, "step": 229 }, { "epoch": 0.05, "learning_rate": 1.683950617283951e-05, "loss": 1.6039, "step": 230 }, { "epoch": 0.05, "learning_rate": 1.6823045267489713e-05, "loss": 1.6965, "step": 231 }, { "epoch": 0.05, "learning_rate": 1.680658436213992e-05, "loss": 1.7489, "step": 232 }, { "epoch": 0.05, "learning_rate": 1.6790123456790123e-05, "loss": 1.6951, "step": 233 }, { "epoch": 0.05, "learning_rate": 1.677366255144033e-05, "loss": 1.6705, "step": 234 }, { "epoch": 0.05, "learning_rate": 1.6757201646090537e-05, "loss": 1.908, "step": 235 }, { "epoch": 0.05, "learning_rate": 1.674074074074074e-05, "loss": 1.6546, "step": 236 }, { "epoch": 0.05, "learning_rate": 1.6724279835390948e-05, "loss": 1.8372, "step": 237 }, { "epoch": 0.05, "learning_rate": 1.670781893004115e-05, "loss": 1.6317, "step": 238 }, { "epoch": 0.05, "learning_rate": 1.669135802469136e-05, "loss": 2.0595, "step": 239 }, { "epoch": 0.05, "learning_rate": 1.6674897119341566e-05, "loss": 1.5238, "step": 240 }, { "epoch": 0.05, "learning_rate": 1.6658436213991773e-05, "loss": 1.6517, "step": 241 }, { "epoch": 0.05, "learning_rate": 1.6641975308641976e-05, "loss": 1.7394, "step": 242 }, { "epoch": 0.05, "learning_rate": 1.6625514403292183e-05, "loss": 1.6853, "step": 243 }, { "epoch": 0.05, "learning_rate": 1.660905349794239e-05, "loss": 1.7295, "step": 244 }, { "epoch": 0.05, "learning_rate": 1.6592592592592594e-05, "loss": 1.6205, "step": 245 }, { "epoch": 0.05, "learning_rate": 1.65761316872428e-05, "loss": 1.5589, "step": 246 }, { "epoch": 0.05, "learning_rate": 1.6559670781893005e-05, "loss": 1.7131, "step": 247 }, { "epoch": 0.05, "learning_rate": 1.654320987654321e-05, "loss": 1.8024, "step": 248 }, { "epoch": 0.05, "learning_rate": 1.6526748971193415e-05, "loss": 1.6896, "step": 249 }, { "epoch": 0.05, "learning_rate": 1.6510288065843622e-05, "loss": 1.6344, "step": 250 }, { "epoch": 0.05, "learning_rate": 1.649382716049383e-05, "loss": 1.7318, "step": 251 }, { "epoch": 0.05, "learning_rate": 1.6477366255144033e-05, "loss": 1.7474, "step": 252 }, { "epoch": 0.05, "learning_rate": 1.646090534979424e-05, "loss": 1.759, "step": 253 }, { "epoch": 0.05, "learning_rate": 1.6444444444444444e-05, "loss": 1.6141, "step": 254 }, { "epoch": 0.05, "learning_rate": 1.642798353909465e-05, "loss": 1.6292, "step": 255 }, { "epoch": 0.05, "learning_rate": 1.6411522633744858e-05, "loss": 1.547, "step": 256 }, { "epoch": 0.05, "learning_rate": 1.6395061728395065e-05, "loss": 1.5423, "step": 257 }, { "epoch": 0.05, "learning_rate": 1.6378600823045268e-05, "loss": 1.6976, "step": 258 }, { "epoch": 0.05, "learning_rate": 1.6362139917695475e-05, "loss": 1.5929, "step": 259 }, { "epoch": 0.05, "learning_rate": 1.6345679012345682e-05, "loss": 1.5716, "step": 260 }, { "epoch": 0.05, "learning_rate": 1.6329218106995886e-05, "loss": 1.5875, "step": 261 }, { "epoch": 0.05, "learning_rate": 1.6312757201646093e-05, "loss": 1.5418, "step": 262 }, { "epoch": 0.05, "learning_rate": 1.6296296296296297e-05, "loss": 1.6039, "step": 263 }, { "epoch": 0.06, "learning_rate": 1.6279835390946504e-05, "loss": 1.6753, "step": 264 }, { "epoch": 0.06, "learning_rate": 1.626337448559671e-05, "loss": 1.8461, "step": 265 }, { "epoch": 0.06, "learning_rate": 1.6246913580246914e-05, "loss": 1.722, "step": 266 }, { "epoch": 0.06, "learning_rate": 1.623045267489712e-05, "loss": 1.6512, "step": 267 }, { "epoch": 0.06, "learning_rate": 1.6213991769547325e-05, "loss": 1.6056, "step": 268 }, { "epoch": 0.06, "learning_rate": 1.6197530864197532e-05, "loss": 1.6164, "step": 269 }, { "epoch": 0.06, "learning_rate": 1.6181069958847736e-05, "loss": 1.6998, "step": 270 }, { "epoch": 0.06, "learning_rate": 1.6164609053497943e-05, "loss": 1.6863, "step": 271 }, { "epoch": 0.06, "learning_rate": 1.614814814814815e-05, "loss": 1.6065, "step": 272 }, { "epoch": 0.06, "learning_rate": 1.6131687242798357e-05, "loss": 1.6511, "step": 273 }, { "epoch": 0.06, "learning_rate": 1.611522633744856e-05, "loss": 1.7618, "step": 274 }, { "epoch": 0.06, "learning_rate": 1.6098765432098767e-05, "loss": 1.837, "step": 275 }, { "epoch": 0.06, "learning_rate": 1.6082304526748974e-05, "loss": 1.5698, "step": 276 }, { "epoch": 0.06, "learning_rate": 1.6065843621399178e-05, "loss": 1.7519, "step": 277 }, { "epoch": 0.06, "learning_rate": 1.6049382716049385e-05, "loss": 1.6268, "step": 278 }, { "epoch": 0.06, "learning_rate": 1.603292181069959e-05, "loss": 1.6616, "step": 279 }, { "epoch": 0.06, "learning_rate": 1.6016460905349796e-05, "loss": 1.7359, "step": 280 }, { "epoch": 0.06, "learning_rate": 1.6000000000000003e-05, "loss": 1.5477, "step": 281 }, { "epoch": 0.06, "learning_rate": 1.5983539094650206e-05, "loss": 1.8325, "step": 282 }, { "epoch": 0.06, "learning_rate": 1.5967078189300413e-05, "loss": 1.7376, "step": 283 }, { "epoch": 0.06, "learning_rate": 1.5950617283950617e-05, "loss": 1.523, "step": 284 }, { "epoch": 0.06, "learning_rate": 1.5934156378600824e-05, "loss": 1.5001, "step": 285 }, { "epoch": 0.06, "learning_rate": 1.5917695473251028e-05, "loss": 1.6449, "step": 286 }, { "epoch": 0.06, "learning_rate": 1.5901234567901235e-05, "loss": 1.8229, "step": 287 }, { "epoch": 0.06, "learning_rate": 1.588477366255144e-05, "loss": 1.8811, "step": 288 }, { "epoch": 0.06, "learning_rate": 1.586831275720165e-05, "loss": 1.8031, "step": 289 }, { "epoch": 0.06, "learning_rate": 1.5851851851851852e-05, "loss": 1.7526, "step": 290 }, { "epoch": 0.06, "learning_rate": 1.583539094650206e-05, "loss": 1.6877, "step": 291 }, { "epoch": 0.06, "learning_rate": 1.5818930041152266e-05, "loss": 1.75, "step": 292 }, { "epoch": 0.06, "learning_rate": 1.580246913580247e-05, "loss": 1.8438, "step": 293 }, { "epoch": 0.06, "learning_rate": 1.5786008230452677e-05, "loss": 2.0571, "step": 294 }, { "epoch": 0.06, "learning_rate": 1.5769547325102884e-05, "loss": 1.7655, "step": 295 }, { "epoch": 0.06, "learning_rate": 1.5753086419753088e-05, "loss": 1.8687, "step": 296 }, { "epoch": 0.06, "learning_rate": 1.5736625514403295e-05, "loss": 1.7157, "step": 297 }, { "epoch": 0.06, "learning_rate": 1.5720164609053498e-05, "loss": 1.805, "step": 298 }, { "epoch": 0.06, "learning_rate": 1.5703703703703705e-05, "loss": 1.8976, "step": 299 }, { "epoch": 0.06, "learning_rate": 1.568724279835391e-05, "loss": 1.9084, "step": 300 }, { "epoch": 0.06, "learning_rate": 1.5670781893004116e-05, "loss": 1.6888, "step": 301 }, { "epoch": 0.06, "learning_rate": 1.565432098765432e-05, "loss": 1.5784, "step": 302 }, { "epoch": 0.06, "learning_rate": 1.5637860082304527e-05, "loss": 1.799, "step": 303 }, { "epoch": 0.06, "learning_rate": 1.5621399176954734e-05, "loss": 1.7829, "step": 304 }, { "epoch": 0.06, "learning_rate": 1.560493827160494e-05, "loss": 1.8252, "step": 305 }, { "epoch": 0.06, "learning_rate": 1.5588477366255144e-05, "loss": 1.8971, "step": 306 }, { "epoch": 0.06, "learning_rate": 1.557201646090535e-05, "loss": 1.8824, "step": 307 }, { "epoch": 0.06, "learning_rate": 1.555555555555556e-05, "loss": 1.778, "step": 308 }, { "epoch": 0.06, "learning_rate": 1.5539094650205762e-05, "loss": 1.7415, "step": 309 }, { "epoch": 0.06, "learning_rate": 1.552263374485597e-05, "loss": 1.7882, "step": 310 }, { "epoch": 0.06, "learning_rate": 1.5506172839506176e-05, "loss": 1.7233, "step": 311 }, { "epoch": 0.07, "learning_rate": 1.548971193415638e-05, "loss": 1.726, "step": 312 }, { "epoch": 0.07, "learning_rate": 1.5473251028806587e-05, "loss": 1.6958, "step": 313 }, { "epoch": 0.07, "learning_rate": 1.545679012345679e-05, "loss": 1.6803, "step": 314 }, { "epoch": 0.07, "learning_rate": 1.5440329218106997e-05, "loss": 1.6209, "step": 315 }, { "epoch": 0.07, "learning_rate": 1.54238683127572e-05, "loss": 1.6254, "step": 316 }, { "epoch": 0.07, "learning_rate": 1.5407407407407408e-05, "loss": 1.6218, "step": 317 }, { "epoch": 0.07, "learning_rate": 1.5390946502057615e-05, "loss": 1.8733, "step": 318 }, { "epoch": 0.07, "learning_rate": 1.537448559670782e-05, "loss": 1.6984, "step": 319 }, { "epoch": 0.07, "learning_rate": 1.5358024691358026e-05, "loss": 1.7601, "step": 320 }, { "epoch": 0.07, "learning_rate": 1.5341563786008233e-05, "loss": 1.8202, "step": 321 }, { "epoch": 0.07, "learning_rate": 1.5325102880658436e-05, "loss": 1.8141, "step": 322 }, { "epoch": 0.07, "learning_rate": 1.5308641975308643e-05, "loss": 1.8886, "step": 323 }, { "epoch": 0.07, "learning_rate": 1.529218106995885e-05, "loss": 1.6267, "step": 324 }, { "epoch": 0.07, "learning_rate": 1.5275720164609057e-05, "loss": 1.7532, "step": 325 }, { "epoch": 0.07, "learning_rate": 1.525925925925926e-05, "loss": 1.8506, "step": 326 }, { "epoch": 0.07, "learning_rate": 1.5242798353909466e-05, "loss": 2.0644, "step": 327 }, { "epoch": 0.07, "learning_rate": 1.5226337448559672e-05, "loss": 1.7376, "step": 328 }, { "epoch": 0.07, "learning_rate": 1.5209876543209879e-05, "loss": 1.8176, "step": 329 }, { "epoch": 0.07, "learning_rate": 1.5193415637860082e-05, "loss": 1.6352, "step": 330 }, { "epoch": 0.07, "learning_rate": 1.517695473251029e-05, "loss": 1.6898, "step": 331 }, { "epoch": 0.07, "learning_rate": 1.5160493827160495e-05, "loss": 1.595, "step": 332 }, { "epoch": 0.07, "learning_rate": 1.51440329218107e-05, "loss": 1.7354, "step": 333 }, { "epoch": 0.07, "learning_rate": 1.5127572016460907e-05, "loss": 1.7988, "step": 334 }, { "epoch": 0.07, "learning_rate": 1.5111111111111112e-05, "loss": 1.9662, "step": 335 }, { "epoch": 0.07, "learning_rate": 1.509465020576132e-05, "loss": 1.9025, "step": 336 }, { "epoch": 0.07, "learning_rate": 1.5078189300411523e-05, "loss": 1.5785, "step": 337 }, { "epoch": 0.07, "learning_rate": 1.506172839506173e-05, "loss": 1.783, "step": 338 }, { "epoch": 0.07, "learning_rate": 1.5045267489711934e-05, "loss": 1.7056, "step": 339 }, { "epoch": 0.07, "learning_rate": 1.502880658436214e-05, "loss": 1.5769, "step": 340 }, { "epoch": 0.07, "learning_rate": 1.5012345679012348e-05, "loss": 1.7728, "step": 341 }, { "epoch": 0.07, "learning_rate": 1.4995884773662553e-05, "loss": 2.0067, "step": 342 }, { "epoch": 0.07, "learning_rate": 1.4979423868312758e-05, "loss": 1.8344, "step": 343 }, { "epoch": 0.07, "learning_rate": 1.4962962962962964e-05, "loss": 1.6755, "step": 344 }, { "epoch": 0.07, "learning_rate": 1.494650205761317e-05, "loss": 1.9847, "step": 345 }, { "epoch": 0.07, "learning_rate": 1.4930041152263374e-05, "loss": 1.8202, "step": 346 }, { "epoch": 0.07, "learning_rate": 1.4913580246913581e-05, "loss": 1.6834, "step": 347 }, { "epoch": 0.07, "learning_rate": 1.4897119341563788e-05, "loss": 1.786, "step": 348 }, { "epoch": 0.07, "learning_rate": 1.4880658436213992e-05, "loss": 1.8855, "step": 349 }, { "epoch": 0.07, "learning_rate": 1.4864197530864199e-05, "loss": 1.7576, "step": 350 }, { "epoch": 0.07, "learning_rate": 1.4847736625514404e-05, "loss": 1.8606, "step": 351 }, { "epoch": 0.07, "learning_rate": 1.4831275720164611e-05, "loss": 1.6801, "step": 352 }, { "epoch": 0.07, "learning_rate": 1.4814814814814815e-05, "loss": 1.7803, "step": 353 }, { "epoch": 0.07, "learning_rate": 1.4798353909465022e-05, "loss": 1.7041, "step": 354 }, { "epoch": 0.07, "learning_rate": 1.4781893004115229e-05, "loss": 1.4677, "step": 355 }, { "epoch": 0.07, "learning_rate": 1.4765432098765433e-05, "loss": 1.5933, "step": 356 }, { "epoch": 0.07, "learning_rate": 1.474897119341564e-05, "loss": 1.6796, "step": 357 }, { "epoch": 0.07, "learning_rate": 1.4732510288065845e-05, "loss": 1.6971, "step": 358 }, { "epoch": 0.07, "learning_rate": 1.471604938271605e-05, "loss": 1.6451, "step": 359 }, { "epoch": 0.08, "learning_rate": 1.4699588477366256e-05, "loss": 1.496, "step": 360 }, { "epoch": 0.08, "learning_rate": 1.4683127572016463e-05, "loss": 1.7427, "step": 361 }, { "epoch": 0.08, "learning_rate": 1.4666666666666666e-05, "loss": 1.7515, "step": 362 }, { "epoch": 0.08, "learning_rate": 1.4650205761316873e-05, "loss": 1.5581, "step": 363 }, { "epoch": 0.08, "learning_rate": 1.463374485596708e-05, "loss": 1.7021, "step": 364 }, { "epoch": 0.08, "learning_rate": 1.4617283950617284e-05, "loss": 1.8126, "step": 365 }, { "epoch": 0.08, "learning_rate": 1.4600823045267491e-05, "loss": 1.7294, "step": 366 }, { "epoch": 0.08, "learning_rate": 1.4584362139917696e-05, "loss": 1.753, "step": 367 }, { "epoch": 0.08, "learning_rate": 1.4567901234567903e-05, "loss": 1.7073, "step": 368 }, { "epoch": 0.08, "learning_rate": 1.4551440329218107e-05, "loss": 1.8555, "step": 369 }, { "epoch": 0.08, "learning_rate": 1.4534979423868314e-05, "loss": 1.5657, "step": 370 }, { "epoch": 0.08, "learning_rate": 1.4518518518518521e-05, "loss": 1.913, "step": 371 }, { "epoch": 0.08, "learning_rate": 1.4502057613168725e-05, "loss": 1.78, "step": 372 }, { "epoch": 0.08, "learning_rate": 1.4485596707818932e-05, "loss": 1.635, "step": 373 }, { "epoch": 0.08, "learning_rate": 1.4469135802469137e-05, "loss": 1.9096, "step": 374 }, { "epoch": 0.08, "learning_rate": 1.4452674897119342e-05, "loss": 1.919, "step": 375 }, { "epoch": 0.08, "learning_rate": 1.4436213991769548e-05, "loss": 1.8191, "step": 376 }, { "epoch": 0.08, "learning_rate": 1.4419753086419755e-05, "loss": 1.791, "step": 377 }, { "epoch": 0.08, "learning_rate": 1.4403292181069962e-05, "loss": 1.6717, "step": 378 }, { "epoch": 0.08, "learning_rate": 1.4386831275720165e-05, "loss": 1.7856, "step": 379 }, { "epoch": 0.08, "learning_rate": 1.4370370370370372e-05, "loss": 1.6008, "step": 380 }, { "epoch": 0.08, "learning_rate": 1.4353909465020578e-05, "loss": 1.6308, "step": 381 }, { "epoch": 0.08, "learning_rate": 1.4337448559670783e-05, "loss": 1.6867, "step": 382 }, { "epoch": 0.08, "learning_rate": 1.4320987654320988e-05, "loss": 1.6689, "step": 383 }, { "epoch": 0.08, "learning_rate": 1.4304526748971195e-05, "loss": 1.6858, "step": 384 }, { "epoch": 0.08, "learning_rate": 1.4288065843621399e-05, "loss": 1.5937, "step": 385 }, { "epoch": 0.08, "learning_rate": 1.4271604938271606e-05, "loss": 1.7199, "step": 386 }, { "epoch": 0.08, "learning_rate": 1.4255144032921813e-05, "loss": 1.6229, "step": 387 }, { "epoch": 0.08, "learning_rate": 1.4238683127572017e-05, "loss": 1.5914, "step": 388 }, { "epoch": 0.08, "learning_rate": 1.4222222222222224e-05, "loss": 1.7565, "step": 389 }, { "epoch": 0.08, "learning_rate": 1.4205761316872429e-05, "loss": 1.7659, "step": 390 }, { "epoch": 0.08, "learning_rate": 1.4189300411522636e-05, "loss": 1.616, "step": 391 }, { "epoch": 0.08, "learning_rate": 1.417283950617284e-05, "loss": 1.7515, "step": 392 }, { "epoch": 0.08, "learning_rate": 1.4156378600823047e-05, "loss": 1.6814, "step": 393 }, { "epoch": 0.08, "learning_rate": 1.4139917695473254e-05, "loss": 1.7268, "step": 394 }, { "epoch": 0.08, "learning_rate": 1.4123456790123457e-05, "loss": 1.5832, "step": 395 }, { "epoch": 0.08, "learning_rate": 1.4106995884773664e-05, "loss": 1.6465, "step": 396 }, { "epoch": 0.08, "learning_rate": 1.409053497942387e-05, "loss": 1.7856, "step": 397 }, { "epoch": 0.08, "learning_rate": 1.4074074074074075e-05, "loss": 1.6983, "step": 398 }, { "epoch": 0.08, "learning_rate": 1.405761316872428e-05, "loss": 1.7528, "step": 399 }, { "epoch": 0.08, "learning_rate": 1.4041152263374487e-05, "loss": 1.5827, "step": 400 }, { "epoch": 0.08, "learning_rate": 1.4024691358024694e-05, "loss": 1.6184, "step": 401 }, { "epoch": 0.08, "learning_rate": 1.4008230452674898e-05, "loss": 1.5953, "step": 402 }, { "epoch": 0.08, "learning_rate": 1.3991769547325105e-05, "loss": 1.6917, "step": 403 }, { "epoch": 0.08, "learning_rate": 1.3975308641975309e-05, "loss": 1.6809, "step": 404 }, { "epoch": 0.08, "learning_rate": 1.3958847736625516e-05, "loss": 1.6142, "step": 405 }, { "epoch": 0.08, "learning_rate": 1.3942386831275721e-05, "loss": 1.7029, "step": 406 }, { "epoch": 0.08, "learning_rate": 1.3925925925925928e-05, "loss": 1.7562, "step": 407 }, { "epoch": 0.09, "learning_rate": 1.3909465020576133e-05, "loss": 1.6457, "step": 408 }, { "epoch": 0.09, "learning_rate": 1.3893004115226339e-05, "loss": 1.6634, "step": 409 }, { "epoch": 0.09, "learning_rate": 1.3876543209876546e-05, "loss": 1.6898, "step": 410 }, { "epoch": 0.09, "learning_rate": 1.386008230452675e-05, "loss": 1.5601, "step": 411 }, { "epoch": 0.09, "learning_rate": 1.3843621399176956e-05, "loss": 1.6238, "step": 412 }, { "epoch": 0.09, "learning_rate": 1.3827160493827162e-05, "loss": 1.7202, "step": 413 }, { "epoch": 0.09, "learning_rate": 1.3810699588477367e-05, "loss": 1.8377, "step": 414 }, { "epoch": 0.09, "learning_rate": 1.3794238683127572e-05, "loss": 1.6738, "step": 415 }, { "epoch": 0.09, "learning_rate": 1.377777777777778e-05, "loss": 1.6144, "step": 416 }, { "epoch": 0.09, "learning_rate": 1.3761316872427986e-05, "loss": 1.6512, "step": 417 }, { "epoch": 0.09, "learning_rate": 1.374485596707819e-05, "loss": 1.7001, "step": 418 }, { "epoch": 0.09, "learning_rate": 1.3728395061728397e-05, "loss": 1.682, "step": 419 }, { "epoch": 0.09, "learning_rate": 1.37119341563786e-05, "loss": 1.6197, "step": 420 }, { "epoch": 0.09, "learning_rate": 1.3695473251028808e-05, "loss": 1.755, "step": 421 }, { "epoch": 0.09, "learning_rate": 1.3679012345679013e-05, "loss": 1.7426, "step": 422 }, { "epoch": 0.09, "learning_rate": 1.366255144032922e-05, "loss": 1.742, "step": 423 }, { "epoch": 0.09, "learning_rate": 1.3646090534979425e-05, "loss": 1.6996, "step": 424 }, { "epoch": 0.09, "learning_rate": 1.362962962962963e-05, "loss": 1.8073, "step": 425 }, { "epoch": 0.09, "learning_rate": 1.3613168724279838e-05, "loss": 1.7936, "step": 426 }, { "epoch": 0.09, "learning_rate": 1.3596707818930041e-05, "loss": 1.7277, "step": 427 }, { "epoch": 0.09, "learning_rate": 1.3580246913580248e-05, "loss": 1.6047, "step": 428 }, { "epoch": 0.09, "learning_rate": 1.3563786008230454e-05, "loss": 1.7015, "step": 429 }, { "epoch": 0.09, "learning_rate": 1.3547325102880659e-05, "loss": 1.6791, "step": 430 }, { "epoch": 0.09, "learning_rate": 1.3530864197530866e-05, "loss": 1.6497, "step": 431 }, { "epoch": 0.09, "learning_rate": 1.3514403292181071e-05, "loss": 1.6037, "step": 432 }, { "epoch": 0.09, "learning_rate": 1.3497942386831278e-05, "loss": 1.8162, "step": 433 }, { "epoch": 0.09, "learning_rate": 1.3481481481481482e-05, "loss": 1.7498, "step": 434 }, { "epoch": 0.09, "learning_rate": 1.3465020576131689e-05, "loss": 1.7131, "step": 435 }, { "epoch": 0.09, "learning_rate": 1.3448559670781893e-05, "loss": 1.8016, "step": 436 }, { "epoch": 0.09, "learning_rate": 1.34320987654321e-05, "loss": 1.8082, "step": 437 }, { "epoch": 0.09, "learning_rate": 1.3415637860082307e-05, "loss": 1.6797, "step": 438 }, { "epoch": 0.09, "learning_rate": 1.3399176954732512e-05, "loss": 1.6706, "step": 439 }, { "epoch": 0.09, "learning_rate": 1.3382716049382717e-05, "loss": 1.8749, "step": 440 }, { "epoch": 0.09, "learning_rate": 1.3366255144032923e-05, "loss": 1.7863, "step": 441 }, { "epoch": 0.09, "learning_rate": 1.334979423868313e-05, "loss": 1.5737, "step": 442 }, { "epoch": 0.09, "learning_rate": 1.3333333333333333e-05, "loss": 1.6434, "step": 443 }, { "epoch": 0.09, "learning_rate": 1.331687242798354e-05, "loss": 1.6443, "step": 444 }, { "epoch": 0.09, "learning_rate": 1.3300411522633746e-05, "loss": 1.6842, "step": 445 }, { "epoch": 0.09, "learning_rate": 1.3283950617283951e-05, "loss": 1.6486, "step": 446 }, { "epoch": 0.09, "learning_rate": 1.3267489711934158e-05, "loss": 1.7764, "step": 447 }, { "epoch": 0.09, "learning_rate": 1.3251028806584363e-05, "loss": 1.7846, "step": 448 }, { "epoch": 0.09, "learning_rate": 1.323456790123457e-05, "loss": 1.5419, "step": 449 }, { "epoch": 0.09, "learning_rate": 1.3218106995884774e-05, "loss": 1.6142, "step": 450 }, { "epoch": 0.09, "learning_rate": 1.3201646090534981e-05, "loss": 1.6508, "step": 451 }, { "epoch": 0.09, "learning_rate": 1.3185185185185185e-05, "loss": 1.6308, "step": 452 }, { "epoch": 0.09, "learning_rate": 1.3168724279835392e-05, "loss": 1.6784, "step": 453 }, { "epoch": 0.09, "learning_rate": 1.3152263374485599e-05, "loss": 1.7455, "step": 454 }, { "epoch": 0.09, "learning_rate": 1.3135802469135804e-05, "loss": 1.6929, "step": 455 }, { "epoch": 0.1, "learning_rate": 1.311934156378601e-05, "loss": 1.6376, "step": 456 }, { "epoch": 0.1, "learning_rate": 1.3102880658436215e-05, "loss": 1.7233, "step": 457 }, { "epoch": 0.1, "learning_rate": 1.3086419753086422e-05, "loss": 1.8233, "step": 458 }, { "epoch": 0.1, "learning_rate": 1.3069958847736625e-05, "loss": 1.7667, "step": 459 }, { "epoch": 0.1, "learning_rate": 1.3053497942386832e-05, "loss": 1.7881, "step": 460 }, { "epoch": 0.1, "learning_rate": 1.303703703703704e-05, "loss": 1.7351, "step": 461 }, { "epoch": 0.1, "learning_rate": 1.3020576131687243e-05, "loss": 1.7448, "step": 462 }, { "epoch": 0.1, "learning_rate": 1.300411522633745e-05, "loss": 1.6304, "step": 463 }, { "epoch": 0.1, "learning_rate": 1.2987654320987655e-05, "loss": 1.6109, "step": 464 }, { "epoch": 0.1, "learning_rate": 1.2971193415637862e-05, "loss": 1.6274, "step": 465 }, { "epoch": 0.1, "learning_rate": 1.2954732510288066e-05, "loss": 1.6732, "step": 466 }, { "epoch": 0.1, "learning_rate": 1.2938271604938273e-05, "loss": 1.6309, "step": 467 }, { "epoch": 0.1, "learning_rate": 1.2921810699588477e-05, "loss": 1.7273, "step": 468 }, { "epoch": 0.1, "learning_rate": 1.2905349794238684e-05, "loss": 1.7379, "step": 469 }, { "epoch": 0.1, "learning_rate": 1.288888888888889e-05, "loss": 1.6326, "step": 470 }, { "epoch": 0.1, "learning_rate": 1.2872427983539096e-05, "loss": 1.5787, "step": 471 }, { "epoch": 0.1, "learning_rate": 1.2855967078189301e-05, "loss": 1.6708, "step": 472 }, { "epoch": 0.1, "learning_rate": 1.2839506172839507e-05, "loss": 1.7834, "step": 473 }, { "epoch": 0.1, "learning_rate": 1.2823045267489714e-05, "loss": 1.78, "step": 474 }, { "epoch": 0.1, "learning_rate": 1.2806584362139917e-05, "loss": 1.7862, "step": 475 }, { "epoch": 0.1, "learning_rate": 1.2790123456790124e-05, "loss": 1.6101, "step": 476 }, { "epoch": 0.1, "learning_rate": 1.2773662551440331e-05, "loss": 1.6263, "step": 477 }, { "epoch": 0.1, "learning_rate": 1.2757201646090535e-05, "loss": 1.7108, "step": 478 }, { "epoch": 0.1, "learning_rate": 1.2740740740740742e-05, "loss": 1.6909, "step": 479 }, { "epoch": 0.1, "learning_rate": 1.2724279835390947e-05, "loss": 1.7026, "step": 480 }, { "epoch": 0.1, "learning_rate": 1.2707818930041154e-05, "loss": 1.7886, "step": 481 }, { "epoch": 0.1, "learning_rate": 1.2691358024691358e-05, "loss": 1.6503, "step": 482 }, { "epoch": 0.1, "learning_rate": 1.2674897119341565e-05, "loss": 1.7342, "step": 483 }, { "epoch": 0.1, "learning_rate": 1.2658436213991772e-05, "loss": 1.5623, "step": 484 }, { "epoch": 0.1, "learning_rate": 1.2641975308641976e-05, "loss": 1.6877, "step": 485 }, { "epoch": 0.1, "learning_rate": 1.2625514403292183e-05, "loss": 1.6536, "step": 486 }, { "epoch": 0.1, "learning_rate": 1.2609053497942388e-05, "loss": 1.7222, "step": 487 }, { "epoch": 0.1, "learning_rate": 1.2592592592592593e-05, "loss": 1.5253, "step": 488 }, { "epoch": 0.1, "learning_rate": 1.2576131687242799e-05, "loss": 1.7865, "step": 489 }, { "epoch": 0.1, "learning_rate": 1.2559670781893006e-05, "loss": 1.7195, "step": 490 }, { "epoch": 0.1, "learning_rate": 1.2543209876543213e-05, "loss": 1.5562, "step": 491 }, { "epoch": 0.1, "learning_rate": 1.2526748971193416e-05, "loss": 1.7468, "step": 492 }, { "epoch": 0.1, "learning_rate": 1.2510288065843623e-05, "loss": 1.5502, "step": 493 }, { "epoch": 0.1, "learning_rate": 1.2493827160493827e-05, "loss": 1.6516, "step": 494 }, { "epoch": 0.1, "learning_rate": 1.2477366255144034e-05, "loss": 1.6465, "step": 495 }, { "epoch": 0.1, "learning_rate": 1.246090534979424e-05, "loss": 1.603, "step": 496 }, { "epoch": 0.1, "learning_rate": 1.2444444444444446e-05, "loss": 1.8198, "step": 497 }, { "epoch": 0.1, "learning_rate": 1.242798353909465e-05, "loss": 1.6344, "step": 498 }, { "epoch": 0.1, "learning_rate": 1.2411522633744857e-05, "loss": 1.6642, "step": 499 }, { "epoch": 0.1, "learning_rate": 1.2395061728395064e-05, "loss": 1.7555, "step": 500 } ], "logging_steps": 1.0, "max_steps": 1253, "num_train_epochs": 1, "save_steps": 500, "total_flos": 0.0, "trial_name": null, "trial_params": null }