{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.0, "global_step": 11072, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 2.999729046242775e-05, "loss": 6.0029, "step": 1 }, { "epoch": 0.0, "learning_rate": 2.9994580924855493e-05, "loss": 5.7369, "step": 2 }, { "epoch": 0.0, "learning_rate": 2.9991871387283237e-05, "loss": 5.6962, "step": 3 }, { "epoch": 0.0, "learning_rate": 2.998916184971098e-05, "loss": 5.4921, "step": 4 }, { "epoch": 0.0, "learning_rate": 2.998916184971098e-05, "loss": 5.0974, "step": 5 }, { "epoch": 0.0, "learning_rate": 2.998645231213873e-05, "loss": 5.5466, "step": 6 }, { "epoch": 0.0, "learning_rate": 2.9983742774566477e-05, "loss": 5.28, "step": 7 }, { "epoch": 0.0, "learning_rate": 2.9981033236994218e-05, "loss": 4.8861, "step": 8 }, { "epoch": 0.0, "learning_rate": 2.9981033236994218e-05, "loss": 4.7655, "step": 9 }, { "epoch": 0.0, "learning_rate": 2.9978323699421966e-05, "loss": 4.578, "step": 10 }, { "epoch": 0.0, "learning_rate": 2.997561416184971e-05, "loss": 4.2609, "step": 11 }, { "epoch": 0.0, "learning_rate": 2.9972904624277458e-05, "loss": 4.4784, "step": 12 }, { "epoch": 0.0, "learning_rate": 2.9970195086705206e-05, "loss": 4.6246, "step": 13 }, { "epoch": 0.0, "learning_rate": 2.9967485549132947e-05, "loss": 4.3428, "step": 14 }, { "epoch": 0.0, "learning_rate": 2.9964776011560694e-05, "loss": 4.392, "step": 15 }, { "epoch": 0.0, "learning_rate": 2.996206647398844e-05, "loss": 4.424, "step": 16 }, { "epoch": 0.0, "learning_rate": 2.9959356936416187e-05, "loss": 4.2842, "step": 17 }, { "epoch": 0.0, "learning_rate": 2.9956647398843934e-05, "loss": 3.567, "step": 18 }, { "epoch": 0.0, "learning_rate": 2.9953937861271675e-05, "loss": 3.8844, "step": 19 }, { "epoch": 0.0, "learning_rate": 2.9951228323699423e-05, "loss": 3.7604, "step": 20 }, { "epoch": 0.0, "learning_rate": 2.9948518786127167e-05, "loss": 4.5084, "step": 21 }, { "epoch": 0.0, "learning_rate": 2.9945809248554915e-05, "loss": 3.8354, "step": 22 }, { "epoch": 0.0, "learning_rate": 2.994309971098266e-05, "loss": 3.7624, "step": 23 }, { "epoch": 0.0, "learning_rate": 2.9940390173410404e-05, "loss": 3.903, "step": 24 }, { "epoch": 0.0, "learning_rate": 2.993768063583815e-05, "loss": 3.828, "step": 25 }, { "epoch": 0.0, "learning_rate": 2.9934971098265896e-05, "loss": 4.0247, "step": 26 }, { "epoch": 0.0, "learning_rate": 2.9932261560693644e-05, "loss": 3.8889, "step": 27 }, { "epoch": 0.01, "learning_rate": 2.9929552023121388e-05, "loss": 3.5419, "step": 28 }, { "epoch": 0.01, "learning_rate": 2.9926842485549132e-05, "loss": 3.6345, "step": 29 }, { "epoch": 0.01, "learning_rate": 2.992413294797688e-05, "loss": 3.7963, "step": 30 }, { "epoch": 0.01, "learning_rate": 2.9921423410404625e-05, "loss": 4.0733, "step": 31 }, { "epoch": 0.01, "learning_rate": 2.991871387283237e-05, "loss": 4.1185, "step": 32 }, { "epoch": 0.01, "learning_rate": 2.9916004335260117e-05, "loss": 3.1793, "step": 33 }, { "epoch": 0.01, "learning_rate": 2.991329479768786e-05, "loss": 2.7593, "step": 34 }, { "epoch": 0.01, "learning_rate": 2.991058526011561e-05, "loss": 2.5375, "step": 35 }, { "epoch": 0.01, "learning_rate": 2.9907875722543353e-05, "loss": 3.2089, "step": 36 }, { "epoch": 0.01, "learning_rate": 2.9905166184971098e-05, "loss": 2.3329, "step": 37 }, { "epoch": 0.01, "learning_rate": 2.9902456647398845e-05, "loss": 2.5808, "step": 38 }, { "epoch": 0.01, "learning_rate": 2.9902456647398845e-05, "loss": 3.3864, "step": 39 }, { "epoch": 0.01, "learning_rate": 2.989974710982659e-05, "loss": 2.6318, "step": 40 }, { "epoch": 0.01, "learning_rate": 2.9897037572254337e-05, "loss": 2.2492, "step": 41 }, { "epoch": 0.01, "learning_rate": 2.9897037572254337e-05, "loss": 2.3163, "step": 42 }, { "epoch": 0.01, "learning_rate": 2.9894328034682082e-05, "loss": 2.3263, "step": 43 }, { "epoch": 0.01, "learning_rate": 2.9891618497109826e-05, "loss": 2.2069, "step": 44 }, { "epoch": 0.01, "learning_rate": 2.9891618497109826e-05, "loss": 2.877, "step": 45 }, { "epoch": 0.01, "learning_rate": 2.9888908959537574e-05, "loss": 2.5843, "step": 46 }, { "epoch": 0.01, "learning_rate": 2.9886199421965318e-05, "loss": 3.4973, "step": 47 }, { "epoch": 0.01, "learning_rate": 2.9883489884393066e-05, "loss": 2.3729, "step": 48 }, { "epoch": 0.01, "learning_rate": 2.9880780346820807e-05, "loss": 1.5728, "step": 49 }, { "epoch": 0.01, "learning_rate": 2.9878070809248555e-05, "loss": 1.4839, "step": 50 }, { "epoch": 0.01, "learning_rate": 2.9875361271676303e-05, "loss": 1.8104, "step": 51 }, { "epoch": 0.01, "learning_rate": 2.9872651734104047e-05, "loss": 2.1644, "step": 52 }, { "epoch": 0.01, "learning_rate": 2.9869942196531795e-05, "loss": 1.7248, "step": 53 }, { "epoch": 0.01, "learning_rate": 2.9867232658959536e-05, "loss": 2.2838, "step": 54 }, { "epoch": 0.01, "learning_rate": 2.9864523121387283e-05, "loss": 2.7636, "step": 55 }, { "epoch": 0.01, "learning_rate": 2.986181358381503e-05, "loss": 2.878, "step": 56 }, { "epoch": 0.01, "learning_rate": 2.9859104046242776e-05, "loss": 2.3818, "step": 57 }, { "epoch": 0.01, "learning_rate": 2.985639450867052e-05, "loss": 2.8538, "step": 58 }, { "epoch": 0.01, "learning_rate": 2.9853684971098264e-05, "loss": 2.9684, "step": 59 }, { "epoch": 0.01, "learning_rate": 2.9850975433526012e-05, "loss": 2.4561, "step": 60 }, { "epoch": 0.01, "learning_rate": 2.984826589595376e-05, "loss": 2.8596, "step": 61 }, { "epoch": 0.01, "learning_rate": 2.9845556358381504e-05, "loss": 2.2277, "step": 62 }, { "epoch": 0.01, "learning_rate": 2.984284682080925e-05, "loss": 2.1485, "step": 63 }, { "epoch": 0.01, "learning_rate": 2.9840137283236993e-05, "loss": 2.1652, "step": 64 }, { "epoch": 0.01, "learning_rate": 2.983742774566474e-05, "loss": 1.7944, "step": 65 }, { "epoch": 0.01, "learning_rate": 2.983471820809249e-05, "loss": 2.798, "step": 66 }, { "epoch": 0.01, "learning_rate": 2.9832008670520233e-05, "loss": 3.2707, "step": 67 }, { "epoch": 0.01, "learning_rate": 2.9829299132947977e-05, "loss": 2.6508, "step": 68 }, { "epoch": 0.01, "learning_rate": 2.982658959537572e-05, "loss": 3.0388, "step": 69 }, { "epoch": 0.01, "learning_rate": 2.982388005780347e-05, "loss": 2.544, "step": 70 }, { "epoch": 0.01, "learning_rate": 2.9821170520231217e-05, "loss": 3.0902, "step": 71 }, { "epoch": 0.01, "learning_rate": 2.9818460982658958e-05, "loss": 2.2919, "step": 72 }, { "epoch": 0.01, "learning_rate": 2.9815751445086706e-05, "loss": 1.8127, "step": 73 }, { "epoch": 0.01, "learning_rate": 2.981304190751445e-05, "loss": 1.5428, "step": 74 }, { "epoch": 0.01, "learning_rate": 2.9810332369942198e-05, "loss": 2.5988, "step": 75 }, { "epoch": 0.01, "learning_rate": 2.9807622832369946e-05, "loss": 1.0102, "step": 76 }, { "epoch": 0.01, "learning_rate": 2.9804913294797687e-05, "loss": 1.9384, "step": 77 }, { "epoch": 0.01, "learning_rate": 2.9802203757225434e-05, "loss": 2.5157, "step": 78 }, { "epoch": 0.01, "learning_rate": 2.979949421965318e-05, "loss": 1.3872, "step": 79 }, { "epoch": 0.01, "learning_rate": 2.9796784682080926e-05, "loss": 2.1752, "step": 80 }, { "epoch": 0.01, "learning_rate": 2.979407514450867e-05, "loss": 1.6651, "step": 81 }, { "epoch": 0.01, "learning_rate": 2.9791365606936415e-05, "loss": 2.1614, "step": 82 }, { "epoch": 0.01, "learning_rate": 2.9788656069364163e-05, "loss": 1.5121, "step": 83 }, { "epoch": 0.02, "learning_rate": 2.9785946531791907e-05, "loss": 1.2271, "step": 84 }, { "epoch": 0.02, "learning_rate": 2.9783236994219655e-05, "loss": 2.0331, "step": 85 }, { "epoch": 0.02, "learning_rate": 2.97805274566474e-05, "loss": 1.5456, "step": 86 }, { "epoch": 0.02, "learning_rate": 2.9777817919075144e-05, "loss": 1.7287, "step": 87 }, { "epoch": 0.02, "learning_rate": 2.977510838150289e-05, "loss": 1.6018, "step": 88 }, { "epoch": 0.02, "learning_rate": 2.9772398843930636e-05, "loss": 1.0361, "step": 89 }, { "epoch": 0.02, "learning_rate": 2.9769689306358384e-05, "loss": 1.4037, "step": 90 }, { "epoch": 0.02, "learning_rate": 2.9766979768786128e-05, "loss": 1.0691, "step": 91 }, { "epoch": 0.02, "learning_rate": 2.9766979768786128e-05, "loss": 1.14, "step": 92 }, { "epoch": 0.02, "learning_rate": 2.9764270231213872e-05, "loss": 1.684, "step": 93 }, { "epoch": 0.02, "learning_rate": 2.976156069364162e-05, "loss": 1.2114, "step": 94 }, { "epoch": 0.02, "learning_rate": 2.9758851156069368e-05, "loss": 1.6098, "step": 95 }, { "epoch": 0.02, "learning_rate": 2.975614161849711e-05, "loss": 2.2249, "step": 96 }, { "epoch": 0.02, "learning_rate": 2.9753432080924857e-05, "loss": 1.7815, "step": 97 }, { "epoch": 0.02, "learning_rate": 2.97507225433526e-05, "loss": 1.2908, "step": 98 }, { "epoch": 0.02, "learning_rate": 2.974801300578035e-05, "loss": 1.97, "step": 99 }, { "epoch": 0.02, "learning_rate": 2.9745303468208096e-05, "loss": 1.0364, "step": 100 }, { "epoch": 0.02, "learning_rate": 2.9742593930635837e-05, "loss": 1.2791, "step": 101 }, { "epoch": 0.02, "learning_rate": 2.9739884393063585e-05, "loss": 1.6525, "step": 102 }, { "epoch": 0.02, "learning_rate": 2.973717485549133e-05, "loss": 0.981, "step": 103 }, { "epoch": 0.02, "learning_rate": 2.9734465317919077e-05, "loss": 1.8666, "step": 104 }, { "epoch": 0.02, "learning_rate": 2.973175578034682e-05, "loss": 1.0264, "step": 105 }, { "epoch": 0.02, "learning_rate": 2.9729046242774566e-05, "loss": 1.2713, "step": 106 }, { "epoch": 0.02, "learning_rate": 2.9726336705202314e-05, "loss": 1.4446, "step": 107 }, { "epoch": 0.02, "learning_rate": 2.9723627167630058e-05, "loss": 1.3603, "step": 108 }, { "epoch": 0.02, "learning_rate": 2.9720917630057806e-05, "loss": 1.4707, "step": 109 }, { "epoch": 0.02, "learning_rate": 2.971820809248555e-05, "loss": 1.4574, "step": 110 }, { "epoch": 0.02, "learning_rate": 2.9715498554913295e-05, "loss": 1.353, "step": 111 }, { "epoch": 0.02, "learning_rate": 2.9712789017341042e-05, "loss": 1.1728, "step": 112 }, { "epoch": 0.02, "learning_rate": 2.9710079479768787e-05, "loss": 1.6632, "step": 113 }, { "epoch": 0.02, "learning_rate": 2.9707369942196534e-05, "loss": 1.4636, "step": 114 }, { "epoch": 0.02, "learning_rate": 2.970466040462428e-05, "loss": 2.0169, "step": 115 }, { "epoch": 0.02, "learning_rate": 2.9701950867052023e-05, "loss": 2.26, "step": 116 }, { "epoch": 0.02, "learning_rate": 2.969924132947977e-05, "loss": 2.0054, "step": 117 }, { "epoch": 0.02, "learning_rate": 2.9696531791907515e-05, "loss": 1.2421, "step": 118 }, { "epoch": 0.02, "learning_rate": 2.969382225433526e-05, "loss": 1.477, "step": 119 }, { "epoch": 0.02, "learning_rate": 2.9691112716763007e-05, "loss": 1.6373, "step": 120 }, { "epoch": 0.02, "learning_rate": 2.9688403179190752e-05, "loss": 1.2219, "step": 121 }, { "epoch": 0.02, "learning_rate": 2.96856936416185e-05, "loss": 0.9804, "step": 122 }, { "epoch": 0.02, "learning_rate": 2.9682984104046244e-05, "loss": 1.2825, "step": 123 }, { "epoch": 0.02, "learning_rate": 2.9680274566473988e-05, "loss": 1.5537, "step": 124 }, { "epoch": 0.02, "learning_rate": 2.9677565028901736e-05, "loss": 0.8252, "step": 125 }, { "epoch": 0.02, "learning_rate": 2.967485549132948e-05, "loss": 1.1001, "step": 126 }, { "epoch": 0.02, "learning_rate": 2.9672145953757228e-05, "loss": 1.9383, "step": 127 }, { "epoch": 0.02, "learning_rate": 2.966943641618497e-05, "loss": 2.439, "step": 128 }, { "epoch": 0.02, "learning_rate": 2.9666726878612717e-05, "loss": 2.1564, "step": 129 }, { "epoch": 0.02, "learning_rate": 2.9664017341040465e-05, "loss": 1.4668, "step": 130 }, { "epoch": 0.02, "learning_rate": 2.966130780346821e-05, "loss": 1.5228, "step": 131 }, { "epoch": 0.02, "learning_rate": 2.9658598265895957e-05, "loss": 1.6344, "step": 132 }, { "epoch": 0.02, "learning_rate": 2.9655888728323698e-05, "loss": 1.8996, "step": 133 }, { "epoch": 0.02, "learning_rate": 2.9653179190751446e-05, "loss": 1.8291, "step": 134 }, { "epoch": 0.02, "learning_rate": 2.9650469653179193e-05, "loss": 1.1515, "step": 135 }, { "epoch": 0.02, "learning_rate": 2.9647760115606938e-05, "loss": 1.3583, "step": 136 }, { "epoch": 0.02, "learning_rate": 2.9645050578034682e-05, "loss": 2.143, "step": 137 }, { "epoch": 0.02, "learning_rate": 2.9642341040462426e-05, "loss": 2.2675, "step": 138 }, { "epoch": 0.03, "learning_rate": 2.9639631502890174e-05, "loss": 1.6176, "step": 139 }, { "epoch": 0.03, "learning_rate": 2.9636921965317922e-05, "loss": 1.1897, "step": 140 }, { "epoch": 0.03, "learning_rate": 2.9634212427745666e-05, "loss": 1.5488, "step": 141 }, { "epoch": 0.03, "learning_rate": 2.963150289017341e-05, "loss": 2.713, "step": 142 }, { "epoch": 0.03, "learning_rate": 2.9628793352601155e-05, "loss": 1.2192, "step": 143 }, { "epoch": 0.03, "learning_rate": 2.9626083815028903e-05, "loss": 1.9724, "step": 144 }, { "epoch": 0.03, "learning_rate": 2.962337427745665e-05, "loss": 0.8454, "step": 145 }, { "epoch": 0.03, "learning_rate": 2.9620664739884395e-05, "loss": 1.7501, "step": 146 }, { "epoch": 0.03, "learning_rate": 2.961795520231214e-05, "loss": 2.4765, "step": 147 }, { "epoch": 0.03, "learning_rate": 2.9615245664739884e-05, "loss": 1.3128, "step": 148 }, { "epoch": 0.03, "learning_rate": 2.961253612716763e-05, "loss": 1.7202, "step": 149 }, { "epoch": 0.03, "learning_rate": 2.960982658959538e-05, "loss": 1.883, "step": 150 }, { "epoch": 0.03, "learning_rate": 2.960711705202312e-05, "loss": 1.3797, "step": 151 }, { "epoch": 0.03, "learning_rate": 2.9604407514450868e-05, "loss": 1.3444, "step": 152 }, { "epoch": 0.03, "learning_rate": 2.9601697976878612e-05, "loss": 1.3918, "step": 153 }, { "epoch": 0.03, "learning_rate": 2.959898843930636e-05, "loss": 1.0595, "step": 154 }, { "epoch": 0.03, "learning_rate": 2.9596278901734108e-05, "loss": 1.9921, "step": 155 }, { "epoch": 0.03, "learning_rate": 2.959356936416185e-05, "loss": 1.2975, "step": 156 }, { "epoch": 0.03, "learning_rate": 2.9590859826589596e-05, "loss": 2.208, "step": 157 }, { "epoch": 0.03, "learning_rate": 2.958815028901734e-05, "loss": 2.0924, "step": 158 }, { "epoch": 0.03, "learning_rate": 2.958544075144509e-05, "loss": 1.7646, "step": 159 }, { "epoch": 0.03, "learning_rate": 2.9582731213872833e-05, "loss": 1.9905, "step": 160 }, { "epoch": 0.03, "learning_rate": 2.9580021676300577e-05, "loss": 1.672, "step": 161 }, { "epoch": 0.03, "learning_rate": 2.9577312138728325e-05, "loss": 1.5096, "step": 162 }, { "epoch": 0.03, "learning_rate": 2.957460260115607e-05, "loss": 1.3315, "step": 163 }, { "epoch": 0.03, "learning_rate": 2.9571893063583817e-05, "loss": 2.5057, "step": 164 }, { "epoch": 0.03, "learning_rate": 2.956918352601156e-05, "loss": 1.6053, "step": 165 }, { "epoch": 0.03, "learning_rate": 2.9566473988439306e-05, "loss": 1.4412, "step": 166 }, { "epoch": 0.03, "learning_rate": 2.9563764450867054e-05, "loss": 1.5113, "step": 167 }, { "epoch": 0.03, "learning_rate": 2.9561054913294798e-05, "loss": 2.8537, "step": 168 }, { "epoch": 0.03, "learning_rate": 2.9558345375722546e-05, "loss": 2.0066, "step": 169 }, { "epoch": 0.03, "learning_rate": 2.955563583815029e-05, "loss": 1.3753, "step": 170 }, { "epoch": 0.03, "learning_rate": 2.9552926300578034e-05, "loss": 2.0167, "step": 171 }, { "epoch": 0.03, "learning_rate": 2.9550216763005782e-05, "loss": 1.9721, "step": 172 }, { "epoch": 0.03, "learning_rate": 2.9547507225433527e-05, "loss": 2.2747, "step": 173 }, { "epoch": 0.03, "learning_rate": 2.954479768786127e-05, "loss": 2.0196, "step": 174 }, { "epoch": 0.03, "learning_rate": 2.954208815028902e-05, "loss": 1.6383, "step": 175 }, { "epoch": 0.03, "learning_rate": 2.9539378612716763e-05, "loss": 1.563, "step": 176 }, { "epoch": 0.03, "learning_rate": 2.953666907514451e-05, "loss": 1.7827, "step": 177 }, { "epoch": 0.03, "learning_rate": 2.9533959537572255e-05, "loss": 1.6064, "step": 178 }, { "epoch": 0.03, "learning_rate": 2.953125e-05, "loss": 1.6565, "step": 179 }, { "epoch": 0.03, "learning_rate": 2.9528540462427747e-05, "loss": 0.8854, "step": 180 }, { "epoch": 0.03, "learning_rate": 2.952583092485549e-05, "loss": 1.6186, "step": 181 }, { "epoch": 0.03, "learning_rate": 2.952312138728324e-05, "loss": 1.6449, "step": 182 }, { "epoch": 0.03, "learning_rate": 2.952041184971098e-05, "loss": 1.3314, "step": 183 }, { "epoch": 0.03, "learning_rate": 2.9517702312138728e-05, "loss": 1.8894, "step": 184 }, { "epoch": 0.03, "learning_rate": 2.9514992774566476e-05, "loss": 1.5366, "step": 185 }, { "epoch": 0.03, "learning_rate": 2.951228323699422e-05, "loss": 1.2572, "step": 186 }, { "epoch": 0.03, "learning_rate": 2.9509573699421968e-05, "loss": 2.1115, "step": 187 }, { "epoch": 0.03, "learning_rate": 2.950686416184971e-05, "loss": 1.9616, "step": 188 }, { "epoch": 0.03, "learning_rate": 2.9504154624277457e-05, "loss": 0.7411, "step": 189 }, { "epoch": 0.03, "learning_rate": 2.9501445086705204e-05, "loss": 1.7372, "step": 190 }, { "epoch": 0.03, "learning_rate": 2.949873554913295e-05, "loss": 2.199, "step": 191 }, { "epoch": 0.03, "learning_rate": 2.9496026011560697e-05, "loss": 2.068, "step": 192 }, { "epoch": 0.03, "learning_rate": 2.9493316473988438e-05, "loss": 1.5029, "step": 193 }, { "epoch": 0.04, "learning_rate": 2.9490606936416185e-05, "loss": 1.6792, "step": 194 }, { "epoch": 0.04, "learning_rate": 2.9487897398843933e-05, "loss": 1.4367, "step": 195 }, { "epoch": 0.04, "learning_rate": 2.9485187861271677e-05, "loss": 1.4671, "step": 196 }, { "epoch": 0.04, "learning_rate": 2.9482478323699422e-05, "loss": 1.5008, "step": 197 }, { "epoch": 0.04, "learning_rate": 2.9479768786127166e-05, "loss": 1.379, "step": 198 }, { "epoch": 0.04, "learning_rate": 2.9477059248554914e-05, "loss": 2.3672, "step": 199 }, { "epoch": 0.04, "learning_rate": 2.947434971098266e-05, "loss": 2.1122, "step": 200 }, { "epoch": 0.04, "learning_rate": 2.9471640173410406e-05, "loss": 1.749, "step": 201 }, { "epoch": 0.04, "learning_rate": 2.946893063583815e-05, "loss": 1.732, "step": 202 }, { "epoch": 0.04, "learning_rate": 2.9466221098265895e-05, "loss": 1.4645, "step": 203 }, { "epoch": 0.04, "learning_rate": 2.9463511560693643e-05, "loss": 1.977, "step": 204 }, { "epoch": 0.04, "learning_rate": 2.946080202312139e-05, "loss": 2.3195, "step": 205 }, { "epoch": 0.04, "learning_rate": 2.945809248554913e-05, "loss": 1.7405, "step": 206 }, { "epoch": 0.04, "learning_rate": 2.945538294797688e-05, "loss": 1.4941, "step": 207 }, { "epoch": 0.04, "learning_rate": 2.9452673410404623e-05, "loss": 1.1666, "step": 208 }, { "epoch": 0.04, "learning_rate": 2.944996387283237e-05, "loss": 0.9503, "step": 209 }, { "epoch": 0.04, "learning_rate": 2.944725433526012e-05, "loss": 1.0446, "step": 210 }, { "epoch": 0.04, "learning_rate": 2.944454479768786e-05, "loss": 0.8933, "step": 211 }, { "epoch": 0.04, "learning_rate": 2.9441835260115608e-05, "loss": 1.2807, "step": 212 }, { "epoch": 0.04, "learning_rate": 2.9439125722543352e-05, "loss": 1.102, "step": 213 }, { "epoch": 0.04, "learning_rate": 2.94364161849711e-05, "loss": 1.9299, "step": 214 }, { "epoch": 0.04, "learning_rate": 2.9433706647398847e-05, "loss": 1.3893, "step": 215 }, { "epoch": 0.04, "learning_rate": 2.943099710982659e-05, "loss": 1.5195, "step": 216 }, { "epoch": 0.04, "learning_rate": 2.9428287572254336e-05, "loss": 1.0148, "step": 217 }, { "epoch": 0.04, "learning_rate": 2.9428287572254336e-05, "loss": 3.1645, "step": 218 }, { "epoch": 0.04, "learning_rate": 2.942557803468208e-05, "loss": 2.1426, "step": 219 }, { "epoch": 0.04, "learning_rate": 2.942286849710983e-05, "loss": 2.1436, "step": 220 }, { "epoch": 0.04, "learning_rate": 2.9420158959537573e-05, "loss": 2.1376, "step": 221 }, { "epoch": 0.04, "learning_rate": 2.9417449421965317e-05, "loss": 2.1972, "step": 222 }, { "epoch": 0.04, "learning_rate": 2.9414739884393065e-05, "loss": 1.2251, "step": 223 }, { "epoch": 0.04, "learning_rate": 2.941203034682081e-05, "loss": 1.9406, "step": 224 }, { "epoch": 0.04, "learning_rate": 2.9409320809248557e-05, "loss": 1.2662, "step": 225 }, { "epoch": 0.04, "learning_rate": 2.94066112716763e-05, "loss": 1.9186, "step": 226 }, { "epoch": 0.04, "learning_rate": 2.9403901734104046e-05, "loss": 1.4199, "step": 227 }, { "epoch": 0.04, "learning_rate": 2.9401192196531793e-05, "loss": 1.5161, "step": 228 }, { "epoch": 0.04, "learning_rate": 2.9398482658959538e-05, "loss": 1.3762, "step": 229 }, { "epoch": 0.04, "learning_rate": 2.9395773121387282e-05, "loss": 1.1713, "step": 230 }, { "epoch": 0.04, "learning_rate": 2.939306358381503e-05, "loss": 1.6551, "step": 231 }, { "epoch": 0.04, "learning_rate": 2.9390354046242774e-05, "loss": 1.1923, "step": 232 }, { "epoch": 0.04, "learning_rate": 2.9387644508670522e-05, "loss": 1.5711, "step": 233 }, { "epoch": 0.04, "learning_rate": 2.9384934971098266e-05, "loss": 1.069, "step": 234 }, { "epoch": 0.04, "learning_rate": 2.938222543352601e-05, "loss": 1.4646, "step": 235 }, { "epoch": 0.04, "learning_rate": 2.937951589595376e-05, "loss": 1.21, "step": 236 }, { "epoch": 0.04, "learning_rate": 2.9376806358381503e-05, "loss": 1.5779, "step": 237 }, { "epoch": 0.04, "learning_rate": 2.937409682080925e-05, "loss": 0.7351, "step": 238 }, { "epoch": 0.04, "learning_rate": 2.9371387283236995e-05, "loss": 1.3077, "step": 239 }, { "epoch": 0.04, "learning_rate": 2.936867774566474e-05, "loss": 1.0847, "step": 240 }, { "epoch": 0.04, "learning_rate": 2.9365968208092487e-05, "loss": 0.9142, "step": 241 }, { "epoch": 0.04, "learning_rate": 2.936325867052023e-05, "loss": 1.3838, "step": 242 }, { "epoch": 0.04, "learning_rate": 2.936054913294798e-05, "loss": 0.7446, "step": 243 }, { "epoch": 0.04, "learning_rate": 2.935783959537572e-05, "loss": 1.0166, "step": 244 }, { "epoch": 0.04, "learning_rate": 2.9355130057803468e-05, "loss": 1.6872, "step": 245 }, { "epoch": 0.04, "learning_rate": 2.9352420520231216e-05, "loss": 1.3202, "step": 246 }, { "epoch": 0.04, "learning_rate": 2.934971098265896e-05, "loss": 0.7227, "step": 247 }, { "epoch": 0.04, "learning_rate": 2.9347001445086708e-05, "loss": 0.8761, "step": 248 }, { "epoch": 0.04, "learning_rate": 2.934429190751445e-05, "loss": 0.8374, "step": 249 }, { "epoch": 0.05, "learning_rate": 2.9341582369942197e-05, "loss": 1.7207, "step": 250 }, { "epoch": 0.05, "learning_rate": 2.9338872832369944e-05, "loss": 1.3417, "step": 251 }, { "epoch": 0.05, "learning_rate": 2.933616329479769e-05, "loss": 1.6895, "step": 252 }, { "epoch": 0.05, "learning_rate": 2.933616329479769e-05, "loss": 0.9692, "step": 253 }, { "epoch": 0.05, "learning_rate": 2.9333453757225433e-05, "loss": 1.6529, "step": 254 }, { "epoch": 0.05, "learning_rate": 2.9330744219653177e-05, "loss": 1.1815, "step": 255 }, { "epoch": 0.05, "learning_rate": 2.9328034682080925e-05, "loss": 1.5466, "step": 256 }, { "epoch": 0.05, "learning_rate": 2.9325325144508673e-05, "loss": 1.2494, "step": 257 }, { "epoch": 0.05, "learning_rate": 2.9322615606936417e-05, "loss": 0.9553, "step": 258 }, { "epoch": 0.05, "learning_rate": 2.931990606936416e-05, "loss": 0.5832, "step": 259 }, { "epoch": 0.05, "learning_rate": 2.9317196531791906e-05, "loss": 1.0864, "step": 260 }, { "epoch": 0.05, "learning_rate": 2.9314486994219654e-05, "loss": 0.7342, "step": 261 }, { "epoch": 0.05, "learning_rate": 2.93117774566474e-05, "loss": 1.1602, "step": 262 }, { "epoch": 0.05, "learning_rate": 2.9309067919075146e-05, "loss": 1.5399, "step": 263 }, { "epoch": 0.05, "learning_rate": 2.930635838150289e-05, "loss": 1.002, "step": 264 }, { "epoch": 0.05, "learning_rate": 2.9303648843930635e-05, "loss": 1.4376, "step": 265 }, { "epoch": 0.05, "learning_rate": 2.9300939306358382e-05, "loss": 1.1273, "step": 266 }, { "epoch": 0.05, "learning_rate": 2.929822976878613e-05, "loss": 1.7952, "step": 267 }, { "epoch": 0.05, "learning_rate": 2.929552023121387e-05, "loss": 0.7032, "step": 268 }, { "epoch": 0.05, "learning_rate": 2.929281069364162e-05, "loss": 0.8798, "step": 269 }, { "epoch": 0.05, "learning_rate": 2.9290101156069367e-05, "loss": 1.5013, "step": 270 }, { "epoch": 0.05, "learning_rate": 2.928739161849711e-05, "loss": 0.7004, "step": 271 }, { "epoch": 0.05, "learning_rate": 2.928468208092486e-05, "loss": 1.5285, "step": 272 }, { "epoch": 0.05, "learning_rate": 2.92819725433526e-05, "loss": 0.8041, "step": 273 }, { "epoch": 0.05, "learning_rate": 2.9279263005780347e-05, "loss": 1.903, "step": 274 }, { "epoch": 0.05, "learning_rate": 2.9276553468208095e-05, "loss": 1.7845, "step": 275 }, { "epoch": 0.05, "learning_rate": 2.927384393063584e-05, "loss": 1.7031, "step": 276 }, { "epoch": 0.05, "learning_rate": 2.9271134393063584e-05, "loss": 1.0912, "step": 277 }, { "epoch": 0.05, "learning_rate": 2.9268424855491328e-05, "loss": 1.2554, "step": 278 }, { "epoch": 0.05, "learning_rate": 2.9265715317919076e-05, "loss": 1.736, "step": 279 }, { "epoch": 0.05, "learning_rate": 2.9263005780346824e-05, "loss": 1.3687, "step": 280 }, { "epoch": 0.05, "learning_rate": 2.9260296242774568e-05, "loss": 1.301, "step": 281 }, { "epoch": 0.05, "learning_rate": 2.9257586705202313e-05, "loss": 1.1124, "step": 282 }, { "epoch": 0.05, "learning_rate": 2.9254877167630057e-05, "loss": 0.9286, "step": 283 }, { "epoch": 0.05, "learning_rate": 2.9252167630057805e-05, "loss": 1.097, "step": 284 }, { "epoch": 0.05, "learning_rate": 2.9249458092485552e-05, "loss": 1.4175, "step": 285 }, { "epoch": 0.05, "learning_rate": 2.9246748554913297e-05, "loss": 1.5524, "step": 286 }, { "epoch": 0.05, "learning_rate": 2.924403901734104e-05, "loss": 1.2111, "step": 287 }, { "epoch": 0.05, "learning_rate": 2.9241329479768786e-05, "loss": 1.7854, "step": 288 }, { "epoch": 0.05, "learning_rate": 2.9238619942196533e-05, "loss": 0.8642, "step": 289 }, { "epoch": 0.05, "learning_rate": 2.923591040462428e-05, "loss": 0.9187, "step": 290 }, { "epoch": 0.05, "learning_rate": 2.9233200867052022e-05, "loss": 0.7244, "step": 291 }, { "epoch": 0.05, "learning_rate": 2.923049132947977e-05, "loss": 1.0837, "step": 292 }, { "epoch": 0.05, "learning_rate": 2.9227781791907514e-05, "loss": 1.6898, "step": 293 }, { "epoch": 0.05, "learning_rate": 2.9225072254335262e-05, "loss": 1.678, "step": 294 }, { "epoch": 0.05, "learning_rate": 2.922236271676301e-05, "loss": 1.1091, "step": 295 }, { "epoch": 0.05, "learning_rate": 2.921965317919075e-05, "loss": 1.2225, "step": 296 }, { "epoch": 0.05, "learning_rate": 2.92169436416185e-05, "loss": 1.1925, "step": 297 }, { "epoch": 0.05, "learning_rate": 2.9214234104046243e-05, "loss": 0.9641, "step": 298 }, { "epoch": 0.05, "learning_rate": 2.921152456647399e-05, "loss": 1.7946, "step": 299 }, { "epoch": 0.05, "learning_rate": 2.9208815028901735e-05, "loss": 1.4299, "step": 300 }, { "epoch": 0.05, "learning_rate": 2.920610549132948e-05, "loss": 0.9644, "step": 301 }, { "epoch": 0.05, "learning_rate": 2.9203395953757227e-05, "loss": 1.2934, "step": 302 }, { "epoch": 0.05, "learning_rate": 2.920068641618497e-05, "loss": 2.3356, "step": 303 }, { "epoch": 0.05, "learning_rate": 2.919797687861272e-05, "loss": 1.4643, "step": 304 }, { "epoch": 0.06, "learning_rate": 2.9195267341040463e-05, "loss": 2.1057, "step": 305 }, { "epoch": 0.06, "learning_rate": 2.9192557803468208e-05, "loss": 0.7703, "step": 306 }, { "epoch": 0.06, "learning_rate": 2.9189848265895956e-05, "loss": 1.5093, "step": 307 }, { "epoch": 0.06, "learning_rate": 2.91871387283237e-05, "loss": 1.6469, "step": 308 }, { "epoch": 0.06, "learning_rate": 2.9184429190751448e-05, "loss": 1.1257, "step": 309 }, { "epoch": 0.06, "learning_rate": 2.9181719653179192e-05, "loss": 1.4473, "step": 310 }, { "epoch": 0.06, "learning_rate": 2.9179010115606936e-05, "loss": 1.027, "step": 311 }, { "epoch": 0.06, "learning_rate": 2.9176300578034684e-05, "loss": 0.575, "step": 312 }, { "epoch": 0.06, "learning_rate": 2.917359104046243e-05, "loss": 1.522, "step": 313 }, { "epoch": 0.06, "learning_rate": 2.9170881502890173e-05, "loss": 0.8784, "step": 314 }, { "epoch": 0.06, "learning_rate": 2.916817196531792e-05, "loss": 1.9842, "step": 315 }, { "epoch": 0.06, "learning_rate": 2.9165462427745665e-05, "loss": 0.4692, "step": 316 }, { "epoch": 0.06, "learning_rate": 2.9162752890173413e-05, "loss": 2.0814, "step": 317 }, { "epoch": 0.06, "learning_rate": 2.9160043352601157e-05, "loss": 1.6593, "step": 318 }, { "epoch": 0.06, "learning_rate": 2.91573338150289e-05, "loss": 1.9345, "step": 319 }, { "epoch": 0.06, "learning_rate": 2.915462427745665e-05, "loss": 1.6148, "step": 320 }, { "epoch": 0.06, "learning_rate": 2.9151914739884394e-05, "loss": 1.2971, "step": 321 }, { "epoch": 0.06, "learning_rate": 2.914920520231214e-05, "loss": 1.5239, "step": 322 }, { "epoch": 0.06, "learning_rate": 2.9146495664739882e-05, "loss": 1.9796, "step": 323 }, { "epoch": 0.06, "learning_rate": 2.914378612716763e-05, "loss": 1.4466, "step": 324 }, { "epoch": 0.06, "learning_rate": 2.9141076589595378e-05, "loss": 0.7011, "step": 325 }, { "epoch": 0.06, "learning_rate": 2.9138367052023122e-05, "loss": 0.8702, "step": 326 }, { "epoch": 0.06, "learning_rate": 2.913565751445087e-05, "loss": 1.3672, "step": 327 }, { "epoch": 0.06, "learning_rate": 2.913294797687861e-05, "loss": 1.678, "step": 328 }, { "epoch": 0.06, "learning_rate": 2.913023843930636e-05, "loss": 1.7328, "step": 329 }, { "epoch": 0.06, "learning_rate": 2.9127528901734106e-05, "loss": 0.9691, "step": 330 }, { "epoch": 0.06, "learning_rate": 2.912481936416185e-05, "loss": 1.4539, "step": 331 }, { "epoch": 0.06, "learning_rate": 2.91221098265896e-05, "loss": 0.8445, "step": 332 }, { "epoch": 0.06, "learning_rate": 2.911940028901734e-05, "loss": 1.17, "step": 333 }, { "epoch": 0.06, "learning_rate": 2.9116690751445087e-05, "loss": 0.7378, "step": 334 }, { "epoch": 0.06, "learning_rate": 2.9113981213872835e-05, "loss": 1.6912, "step": 335 }, { "epoch": 0.06, "learning_rate": 2.911127167630058e-05, "loss": 1.036, "step": 336 }, { "epoch": 0.06, "learning_rate": 2.9108562138728324e-05, "loss": 1.6561, "step": 337 }, { "epoch": 0.06, "learning_rate": 2.9105852601156068e-05, "loss": 1.1738, "step": 338 }, { "epoch": 0.06, "learning_rate": 2.9103143063583816e-05, "loss": 0.5129, "step": 339 }, { "epoch": 0.06, "learning_rate": 2.9100433526011564e-05, "loss": 0.6967, "step": 340 }, { "epoch": 0.06, "learning_rate": 2.9097723988439308e-05, "loss": 1.2419, "step": 341 }, { "epoch": 0.06, "learning_rate": 2.9095014450867052e-05, "loss": 0.6997, "step": 342 }, { "epoch": 0.06, "learning_rate": 2.9092304913294797e-05, "loss": 1.135, "step": 343 }, { "epoch": 0.06, "learning_rate": 2.9089595375722544e-05, "loss": 0.7314, "step": 344 }, { "epoch": 0.06, "learning_rate": 2.9086885838150292e-05, "loss": 0.9359, "step": 345 }, { "epoch": 0.06, "learning_rate": 2.9084176300578033e-05, "loss": 0.8861, "step": 346 }, { "epoch": 0.06, "learning_rate": 2.908146676300578e-05, "loss": 0.6239, "step": 347 }, { "epoch": 0.06, "learning_rate": 2.9078757225433525e-05, "loss": 0.947, "step": 348 }, { "epoch": 0.06, "learning_rate": 2.9076047687861273e-05, "loss": 1.6445, "step": 349 }, { "epoch": 0.06, "learning_rate": 2.907333815028902e-05, "loss": 0.7975, "step": 350 }, { "epoch": 0.06, "learning_rate": 2.9070628612716762e-05, "loss": 1.4226, "step": 351 }, { "epoch": 0.06, "learning_rate": 2.906791907514451e-05, "loss": 1.1544, "step": 352 }, { "epoch": 0.06, "learning_rate": 2.9065209537572254e-05, "loss": 1.2154, "step": 353 }, { "epoch": 0.06, "learning_rate": 2.90625e-05, "loss": 0.9052, "step": 354 }, { "epoch": 0.06, "learning_rate": 2.9059790462427746e-05, "loss": 1.3925, "step": 355 }, { "epoch": 0.06, "learning_rate": 2.905708092485549e-05, "loss": 1.5051, "step": 356 }, { "epoch": 0.06, "learning_rate": 2.9054371387283238e-05, "loss": 0.7921, "step": 357 }, { "epoch": 0.06, "learning_rate": 2.9051661849710983e-05, "loss": 1.0797, "step": 358 }, { "epoch": 0.06, "learning_rate": 2.904895231213873e-05, "loss": 1.7384, "step": 359 }, { "epoch": 0.07, "learning_rate": 2.9046242774566475e-05, "loss": 0.8775, "step": 360 }, { "epoch": 0.07, "learning_rate": 2.904353323699422e-05, "loss": 1.0257, "step": 361 }, { "epoch": 0.07, "learning_rate": 2.9040823699421967e-05, "loss": 1.2738, "step": 362 }, { "epoch": 0.07, "learning_rate": 2.903811416184971e-05, "loss": 0.9697, "step": 363 }, { "epoch": 0.07, "learning_rate": 2.903540462427746e-05, "loss": 1.1358, "step": 364 }, { "epoch": 0.07, "learning_rate": 2.9032695086705203e-05, "loss": 1.332, "step": 365 }, { "epoch": 0.07, "learning_rate": 2.9029985549132948e-05, "loss": 0.9769, "step": 366 }, { "epoch": 0.07, "learning_rate": 2.9027276011560695e-05, "loss": 1.8165, "step": 367 }, { "epoch": 0.07, "learning_rate": 2.902456647398844e-05, "loss": 1.0187, "step": 368 }, { "epoch": 0.07, "learning_rate": 2.9021856936416184e-05, "loss": 1.8718, "step": 369 }, { "epoch": 0.07, "learning_rate": 2.9019147398843932e-05, "loss": 0.744, "step": 370 }, { "epoch": 0.07, "learning_rate": 2.9016437861271676e-05, "loss": 0.8548, "step": 371 }, { "epoch": 0.07, "learning_rate": 2.9013728323699424e-05, "loss": 1.3342, "step": 372 }, { "epoch": 0.07, "learning_rate": 2.901101878612717e-05, "loss": 0.9315, "step": 373 }, { "epoch": 0.07, "learning_rate": 2.9008309248554913e-05, "loss": 1.7974, "step": 374 }, { "epoch": 0.07, "learning_rate": 2.900559971098266e-05, "loss": 0.752, "step": 375 }, { "epoch": 0.07, "learning_rate": 2.9002890173410405e-05, "loss": 0.8306, "step": 376 }, { "epoch": 0.07, "learning_rate": 2.9000180635838153e-05, "loss": 1.021, "step": 377 }, { "epoch": 0.07, "learning_rate": 2.8997471098265897e-05, "loss": 0.9224, "step": 378 }, { "epoch": 0.07, "learning_rate": 2.899476156069364e-05, "loss": 0.729, "step": 379 }, { "epoch": 0.07, "learning_rate": 2.899205202312139e-05, "loss": 1.1612, "step": 380 }, { "epoch": 0.07, "learning_rate": 2.8989342485549133e-05, "loss": 2.2147, "step": 381 }, { "epoch": 0.07, "learning_rate": 2.898663294797688e-05, "loss": 0.8605, "step": 382 }, { "epoch": 0.07, "learning_rate": 2.8983923410404622e-05, "loss": 1.0656, "step": 383 }, { "epoch": 0.07, "learning_rate": 2.898121387283237e-05, "loss": 1.7819, "step": 384 }, { "epoch": 0.07, "learning_rate": 2.8978504335260118e-05, "loss": 0.7608, "step": 385 }, { "epoch": 0.07, "learning_rate": 2.8975794797687862e-05, "loss": 1.1914, "step": 386 }, { "epoch": 0.07, "learning_rate": 2.897308526011561e-05, "loss": 1.2433, "step": 387 }, { "epoch": 0.07, "learning_rate": 2.897037572254335e-05, "loss": 0.7466, "step": 388 }, { "epoch": 0.07, "learning_rate": 2.89676661849711e-05, "loss": 1.6111, "step": 389 }, { "epoch": 0.07, "learning_rate": 2.8964956647398846e-05, "loss": 1.6797, "step": 390 }, { "epoch": 0.07, "learning_rate": 2.896224710982659e-05, "loss": 1.404, "step": 391 }, { "epoch": 0.07, "learning_rate": 2.8959537572254335e-05, "loss": 1.0939, "step": 392 }, { "epoch": 0.07, "learning_rate": 2.895682803468208e-05, "loss": 0.8134, "step": 393 }, { "epoch": 0.07, "learning_rate": 2.8954118497109827e-05, "loss": 1.4968, "step": 394 }, { "epoch": 0.07, "learning_rate": 2.8951408959537575e-05, "loss": 1.0969, "step": 395 }, { "epoch": 0.07, "learning_rate": 2.894869942196532e-05, "loss": 1.309, "step": 396 }, { "epoch": 0.07, "learning_rate": 2.8945989884393064e-05, "loss": 0.984, "step": 397 }, { "epoch": 0.07, "learning_rate": 2.8943280346820808e-05, "loss": 0.962, "step": 398 }, { "epoch": 0.07, "learning_rate": 2.8940570809248556e-05, "loss": 1.0153, "step": 399 }, { "epoch": 0.07, "learning_rate": 2.8937861271676303e-05, "loss": 0.8706, "step": 400 }, { "epoch": 0.07, "learning_rate": 2.8935151734104044e-05, "loss": 1.402, "step": 401 }, { "epoch": 0.07, "learning_rate": 2.8932442196531792e-05, "loss": 0.66, "step": 402 }, { "epoch": 0.07, "learning_rate": 2.8929732658959537e-05, "loss": 1.856, "step": 403 }, { "epoch": 0.07, "learning_rate": 2.8927023121387284e-05, "loss": 1.0784, "step": 404 }, { "epoch": 0.07, "learning_rate": 2.8924313583815032e-05, "loss": 0.6838, "step": 405 }, { "epoch": 0.07, "learning_rate": 2.8921604046242773e-05, "loss": 1.2457, "step": 406 }, { "epoch": 0.07, "learning_rate": 2.891889450867052e-05, "loss": 1.0205, "step": 407 }, { "epoch": 0.07, "learning_rate": 2.8916184971098265e-05, "loss": 1.4482, "step": 408 }, { "epoch": 0.07, "learning_rate": 2.8913475433526013e-05, "loss": 2.3198, "step": 409 }, { "epoch": 0.07, "learning_rate": 2.891076589595376e-05, "loss": 0.6993, "step": 410 }, { "epoch": 0.07, "learning_rate": 2.89080563583815e-05, "loss": 1.027, "step": 411 }, { "epoch": 0.07, "learning_rate": 2.890534682080925e-05, "loss": 1.0304, "step": 412 }, { "epoch": 0.07, "learning_rate": 2.8902637283236994e-05, "loss": 0.7002, "step": 413 }, { "epoch": 0.07, "learning_rate": 2.889992774566474e-05, "loss": 1.5891, "step": 414 }, { "epoch": 0.07, "learning_rate": 2.8897218208092486e-05, "loss": 1.522, "step": 415 }, { "epoch": 0.08, "learning_rate": 2.889450867052023e-05, "loss": 0.4835, "step": 416 }, { "epoch": 0.08, "learning_rate": 2.8891799132947978e-05, "loss": 1.1112, "step": 417 }, { "epoch": 0.08, "learning_rate": 2.8889089595375722e-05, "loss": 1.0025, "step": 418 }, { "epoch": 0.08, "learning_rate": 2.888638005780347e-05, "loss": 1.7857, "step": 419 }, { "epoch": 0.08, "learning_rate": 2.8883670520231214e-05, "loss": 1.3256, "step": 420 }, { "epoch": 0.08, "learning_rate": 2.888096098265896e-05, "loss": 1.6149, "step": 421 }, { "epoch": 0.08, "learning_rate": 2.8878251445086707e-05, "loss": 1.1021, "step": 422 }, { "epoch": 0.08, "learning_rate": 2.887554190751445e-05, "loss": 0.9701, "step": 423 }, { "epoch": 0.08, "learning_rate": 2.8872832369942195e-05, "loss": 0.8237, "step": 424 }, { "epoch": 0.08, "learning_rate": 2.8870122832369943e-05, "loss": 0.9994, "step": 425 }, { "epoch": 0.08, "learning_rate": 2.8867413294797687e-05, "loss": 0.7446, "step": 426 }, { "epoch": 0.08, "learning_rate": 2.8864703757225435e-05, "loss": 1.1883, "step": 427 }, { "epoch": 0.08, "learning_rate": 2.886199421965318e-05, "loss": 1.6658, "step": 428 }, { "epoch": 0.08, "learning_rate": 2.8859284682080924e-05, "loss": 1.5371, "step": 429 }, { "epoch": 0.08, "learning_rate": 2.885657514450867e-05, "loss": 0.9305, "step": 430 }, { "epoch": 0.08, "learning_rate": 2.8853865606936416e-05, "loss": 1.138, "step": 431 }, { "epoch": 0.08, "learning_rate": 2.8851156069364164e-05, "loss": 1.4915, "step": 432 }, { "epoch": 0.08, "learning_rate": 2.8848446531791908e-05, "loss": 1.0739, "step": 433 }, { "epoch": 0.08, "learning_rate": 2.8845736994219653e-05, "loss": 1.2119, "step": 434 }, { "epoch": 0.08, "learning_rate": 2.88430274566474e-05, "loss": 0.8537, "step": 435 }, { "epoch": 0.08, "learning_rate": 2.8840317919075145e-05, "loss": 0.8299, "step": 436 }, { "epoch": 0.08, "learning_rate": 2.8837608381502892e-05, "loss": 0.9536, "step": 437 }, { "epoch": 0.08, "learning_rate": 2.8834898843930633e-05, "loss": 1.0752, "step": 438 }, { "epoch": 0.08, "learning_rate": 2.883218930635838e-05, "loss": 1.3141, "step": 439 }, { "epoch": 0.08, "learning_rate": 2.882947976878613e-05, "loss": 1.5263, "step": 440 }, { "epoch": 0.08, "learning_rate": 2.8826770231213873e-05, "loss": 1.2908, "step": 441 }, { "epoch": 0.08, "learning_rate": 2.882406069364162e-05, "loss": 0.8354, "step": 442 }, { "epoch": 0.08, "learning_rate": 2.8821351156069365e-05, "loss": 0.7611, "step": 443 }, { "epoch": 0.08, "learning_rate": 2.881864161849711e-05, "loss": 0.9089, "step": 444 }, { "epoch": 0.08, "learning_rate": 2.8815932080924857e-05, "loss": 1.087, "step": 445 }, { "epoch": 0.08, "learning_rate": 2.8813222543352602e-05, "loss": 1.3376, "step": 446 }, { "epoch": 0.08, "learning_rate": 2.8810513005780346e-05, "loss": 1.246, "step": 447 }, { "epoch": 0.08, "learning_rate": 2.8807803468208094e-05, "loss": 1.219, "step": 448 }, { "epoch": 0.08, "learning_rate": 2.880509393063584e-05, "loss": 1.0728, "step": 449 }, { "epoch": 0.08, "learning_rate": 2.8802384393063586e-05, "loss": 0.7439, "step": 450 }, { "epoch": 0.08, "learning_rate": 2.879967485549133e-05, "loss": 0.8955, "step": 451 }, { "epoch": 0.08, "learning_rate": 2.8796965317919075e-05, "loss": 0.7856, "step": 452 }, { "epoch": 0.08, "learning_rate": 2.8794255780346823e-05, "loss": 0.5935, "step": 453 }, { "epoch": 0.08, "learning_rate": 2.8791546242774567e-05, "loss": 1.344, "step": 454 }, { "epoch": 0.08, "learning_rate": 2.8788836705202315e-05, "loss": 1.4335, "step": 455 }, { "epoch": 0.08, "learning_rate": 2.878612716763006e-05, "loss": 0.5768, "step": 456 }, { "epoch": 0.08, "learning_rate": 2.8783417630057803e-05, "loss": 1.8961, "step": 457 }, { "epoch": 0.08, "learning_rate": 2.878070809248555e-05, "loss": 0.8616, "step": 458 }, { "epoch": 0.08, "learning_rate": 2.8777998554913296e-05, "loss": 2.0795, "step": 459 }, { "epoch": 0.08, "learning_rate": 2.8775289017341043e-05, "loss": 1.1068, "step": 460 }, { "epoch": 0.08, "learning_rate": 2.8772579479768784e-05, "loss": 1.6946, "step": 461 }, { "epoch": 0.08, "learning_rate": 2.8769869942196532e-05, "loss": 0.5073, "step": 462 }, { "epoch": 0.08, "learning_rate": 2.876716040462428e-05, "loss": 0.9181, "step": 463 }, { "epoch": 0.08, "learning_rate": 2.8764450867052024e-05, "loss": 0.8269, "step": 464 }, { "epoch": 0.08, "learning_rate": 2.8761741329479772e-05, "loss": 1.3797, "step": 465 }, { "epoch": 0.08, "learning_rate": 2.8759031791907513e-05, "loss": 0.9057, "step": 466 }, { "epoch": 0.08, "learning_rate": 2.875632225433526e-05, "loss": 1.3883, "step": 467 }, { "epoch": 0.08, "learning_rate": 2.875361271676301e-05, "loss": 1.2743, "step": 468 }, { "epoch": 0.08, "learning_rate": 2.8750903179190753e-05, "loss": 1.2918, "step": 469 }, { "epoch": 0.08, "learning_rate": 2.8748193641618497e-05, "loss": 1.2931, "step": 470 }, { "epoch": 0.09, "learning_rate": 2.874548410404624e-05, "loss": 0.765, "step": 471 }, { "epoch": 0.09, "learning_rate": 2.874277456647399e-05, "loss": 0.9086, "step": 472 }, { "epoch": 0.09, "learning_rate": 2.8740065028901737e-05, "loss": 1.2416, "step": 473 }, { "epoch": 0.09, "learning_rate": 2.873735549132948e-05, "loss": 0.3998, "step": 474 }, { "epoch": 0.09, "learning_rate": 2.8734645953757226e-05, "loss": 0.9603, "step": 475 }, { "epoch": 0.09, "learning_rate": 2.873193641618497e-05, "loss": 1.1081, "step": 476 }, { "epoch": 0.09, "learning_rate": 2.8729226878612718e-05, "loss": 1.0197, "step": 477 }, { "epoch": 0.09, "learning_rate": 2.8726517341040466e-05, "loss": 0.6497, "step": 478 }, { "epoch": 0.09, "learning_rate": 2.872380780346821e-05, "loss": 1.004, "step": 479 }, { "epoch": 0.09, "learning_rate": 2.8721098265895954e-05, "loss": 1.1636, "step": 480 }, { "epoch": 0.09, "learning_rate": 2.87183887283237e-05, "loss": 1.0338, "step": 481 }, { "epoch": 0.09, "learning_rate": 2.8715679190751446e-05, "loss": 1.0464, "step": 482 }, { "epoch": 0.09, "learning_rate": 2.8712969653179194e-05, "loss": 0.774, "step": 483 }, { "epoch": 0.09, "learning_rate": 2.8710260115606935e-05, "loss": 0.7939, "step": 484 }, { "epoch": 0.09, "learning_rate": 2.8707550578034683e-05, "loss": 1.6576, "step": 485 }, { "epoch": 0.09, "learning_rate": 2.8704841040462427e-05, "loss": 1.3796, "step": 486 }, { "epoch": 0.09, "learning_rate": 2.8702131502890175e-05, "loss": 1.4268, "step": 487 }, { "epoch": 0.09, "learning_rate": 2.8699421965317923e-05, "loss": 0.8099, "step": 488 }, { "epoch": 0.09, "learning_rate": 2.8696712427745664e-05, "loss": 1.7765, "step": 489 }, { "epoch": 0.09, "learning_rate": 2.869400289017341e-05, "loss": 0.9584, "step": 490 }, { "epoch": 0.09, "learning_rate": 2.8691293352601156e-05, "loss": 1.2832, "step": 491 }, { "epoch": 0.09, "learning_rate": 2.8688583815028904e-05, "loss": 0.9506, "step": 492 }, { "epoch": 0.09, "learning_rate": 2.8685874277456648e-05, "loss": 0.6271, "step": 493 }, { "epoch": 0.09, "learning_rate": 2.8683164739884392e-05, "loss": 1.6061, "step": 494 }, { "epoch": 0.09, "learning_rate": 2.868045520231214e-05, "loss": 0.6622, "step": 495 }, { "epoch": 0.09, "learning_rate": 2.8677745664739884e-05, "loss": 0.6103, "step": 496 }, { "epoch": 0.09, "learning_rate": 2.8675036127167632e-05, "loss": 1.142, "step": 497 }, { "epoch": 0.09, "learning_rate": 2.8672326589595377e-05, "loss": 0.9069, "step": 498 }, { "epoch": 0.09, "learning_rate": 2.866961705202312e-05, "loss": 1.9021, "step": 499 }, { "epoch": 0.09, "learning_rate": 2.866690751445087e-05, "loss": 1.0694, "step": 500 }, { "epoch": 0.09, "eval_exact_match": 80.51087984862819, "eval_f1": 89.09379655562964, "step": 500 }, { "epoch": 0.09, "learning_rate": 2.8664197976878613e-05, "loss": 0.8671, "step": 501 }, { "epoch": 0.09, "learning_rate": 2.866148843930636e-05, "loss": 1.5387, "step": 502 }, { "epoch": 0.09, "learning_rate": 2.8658778901734105e-05, "loss": 1.0624, "step": 503 }, { "epoch": 0.09, "learning_rate": 2.865606936416185e-05, "loss": 0.6828, "step": 504 }, { "epoch": 0.09, "learning_rate": 2.8653359826589597e-05, "loss": 1.6497, "step": 505 }, { "epoch": 0.09, "learning_rate": 2.865065028901734e-05, "loss": 1.207, "step": 506 }, { "epoch": 0.09, "learning_rate": 2.8647940751445086e-05, "loss": 1.1402, "step": 507 }, { "epoch": 0.09, "learning_rate": 2.8645231213872834e-05, "loss": 1.21, "step": 508 }, { "epoch": 0.09, "learning_rate": 2.8642521676300578e-05, "loss": 1.2745, "step": 509 }, { "epoch": 0.09, "learning_rate": 2.8639812138728326e-05, "loss": 0.8349, "step": 510 }, { "epoch": 0.09, "learning_rate": 2.863710260115607e-05, "loss": 1.1062, "step": 511 }, { "epoch": 0.09, "learning_rate": 2.8634393063583815e-05, "loss": 0.9844, "step": 512 }, { "epoch": 0.09, "learning_rate": 2.8631683526011562e-05, "loss": 1.191, "step": 513 }, { "epoch": 0.09, "learning_rate": 2.8628973988439307e-05, "loss": 1.0218, "step": 514 }, { "epoch": 0.09, "learning_rate": 2.8626264450867055e-05, "loss": 1.8342, "step": 515 }, { "epoch": 0.09, "learning_rate": 2.8623554913294796e-05, "loss": 0.5208, "step": 516 }, { "epoch": 0.09, "learning_rate": 2.8620845375722543e-05, "loss": 1.227, "step": 517 }, { "epoch": 0.09, "learning_rate": 2.861813583815029e-05, "loss": 1.1391, "step": 518 }, { "epoch": 0.09, "learning_rate": 2.8615426300578035e-05, "loss": 0.7868, "step": 519 }, { "epoch": 0.09, "learning_rate": 2.8612716763005783e-05, "loss": 1.2241, "step": 520 }, { "epoch": 0.09, "learning_rate": 2.8610007225433524e-05, "loss": 1.4511, "step": 521 }, { "epoch": 0.09, "learning_rate": 2.8610007225433524e-05, "loss": 2.2577, "step": 522 }, { "epoch": 0.09, "learning_rate": 2.8607297687861272e-05, "loss": 1.1285, "step": 523 }, { "epoch": 0.09, "learning_rate": 2.860458815028902e-05, "loss": 1.4214, "step": 524 }, { "epoch": 0.09, "learning_rate": 2.8601878612716764e-05, "loss": 1.4151, "step": 525 }, { "epoch": 0.1, "learning_rate": 2.8599169075144512e-05, "loss": 1.318, "step": 526 }, { "epoch": 0.1, "learning_rate": 2.8596459537572253e-05, "loss": 1.3459, "step": 527 }, { "epoch": 0.1, "learning_rate": 2.859375e-05, "loss": 0.9052, "step": 528 }, { "epoch": 0.1, "learning_rate": 2.8591040462427748e-05, "loss": 1.0672, "step": 529 }, { "epoch": 0.1, "learning_rate": 2.8588330924855493e-05, "loss": 0.8096, "step": 530 }, { "epoch": 0.1, "learning_rate": 2.8585621387283237e-05, "loss": 1.2041, "step": 531 }, { "epoch": 0.1, "learning_rate": 2.858291184971098e-05, "loss": 1.3795, "step": 532 }, { "epoch": 0.1, "learning_rate": 2.858020231213873e-05, "loss": 1.2542, "step": 533 }, { "epoch": 0.1, "learning_rate": 2.8577492774566477e-05, "loss": 0.7437, "step": 534 }, { "epoch": 0.1, "learning_rate": 2.857478323699422e-05, "loss": 0.6378, "step": 535 }, { "epoch": 0.1, "learning_rate": 2.8572073699421966e-05, "loss": 0.6441, "step": 536 }, { "epoch": 0.1, "learning_rate": 2.856936416184971e-05, "loss": 0.7308, "step": 537 }, { "epoch": 0.1, "learning_rate": 2.8566654624277458e-05, "loss": 0.4273, "step": 538 }, { "epoch": 0.1, "learning_rate": 2.8563945086705205e-05, "loss": 0.952, "step": 539 }, { "epoch": 0.1, "learning_rate": 2.8561235549132946e-05, "loss": 0.5108, "step": 540 }, { "epoch": 0.1, "learning_rate": 2.8558526011560694e-05, "loss": 0.6903, "step": 541 }, { "epoch": 0.1, "learning_rate": 2.855581647398844e-05, "loss": 1.7838, "step": 542 }, { "epoch": 0.1, "learning_rate": 2.8553106936416186e-05, "loss": 2.0875, "step": 543 }, { "epoch": 0.1, "learning_rate": 2.8550397398843934e-05, "loss": 2.1477, "step": 544 }, { "epoch": 0.1, "learning_rate": 2.8547687861271675e-05, "loss": 0.8692, "step": 545 }, { "epoch": 0.1, "learning_rate": 2.8544978323699423e-05, "loss": 1.1506, "step": 546 }, { "epoch": 0.1, "learning_rate": 2.8542268786127167e-05, "loss": 1.3362, "step": 547 }, { "epoch": 0.1, "learning_rate": 2.8539559248554915e-05, "loss": 0.958, "step": 548 }, { "epoch": 0.1, "learning_rate": 2.8536849710982663e-05, "loss": 1.0285, "step": 549 }, { "epoch": 0.1, "learning_rate": 2.8534140173410404e-05, "loss": 0.7079, "step": 550 }, { "epoch": 0.1, "learning_rate": 2.853143063583815e-05, "loss": 0.8858, "step": 551 }, { "epoch": 0.1, "learning_rate": 2.8528721098265896e-05, "loss": 1.157, "step": 552 }, { "epoch": 0.1, "learning_rate": 2.8526011560693643e-05, "loss": 0.8209, "step": 553 }, { "epoch": 0.1, "learning_rate": 2.8523302023121388e-05, "loss": 0.7403, "step": 554 }, { "epoch": 0.1, "learning_rate": 2.8520592485549132e-05, "loss": 2.1, "step": 555 }, { "epoch": 0.1, "learning_rate": 2.851788294797688e-05, "loss": 0.3468, "step": 556 }, { "epoch": 0.1, "learning_rate": 2.8515173410404624e-05, "loss": 0.6712, "step": 557 }, { "epoch": 0.1, "learning_rate": 2.8512463872832372e-05, "loss": 1.118, "step": 558 }, { "epoch": 0.1, "learning_rate": 2.8509754335260116e-05, "loss": 1.7443, "step": 559 }, { "epoch": 0.1, "learning_rate": 2.850704479768786e-05, "loss": 1.4867, "step": 560 }, { "epoch": 0.1, "learning_rate": 2.850433526011561e-05, "loss": 1.1988, "step": 561 }, { "epoch": 0.1, "learning_rate": 2.8501625722543353e-05, "loss": 0.5668, "step": 562 }, { "epoch": 0.1, "learning_rate": 2.8498916184971097e-05, "loss": 1.4325, "step": 563 }, { "epoch": 0.1, "learning_rate": 2.8496206647398845e-05, "loss": 1.5739, "step": 564 }, { "epoch": 0.1, "learning_rate": 2.849349710982659e-05, "loss": 0.9845, "step": 565 }, { "epoch": 0.1, "learning_rate": 2.8490787572254337e-05, "loss": 0.7639, "step": 566 }, { "epoch": 0.1, "learning_rate": 2.848807803468208e-05, "loss": 0.9859, "step": 567 }, { "epoch": 0.1, "learning_rate": 2.8485368497109826e-05, "loss": 0.7231, "step": 568 }, { "epoch": 0.1, "learning_rate": 2.8482658959537574e-05, "loss": 0.7022, "step": 569 }, { "epoch": 0.1, "learning_rate": 2.8479949421965318e-05, "loss": 1.3989, "step": 570 }, { "epoch": 0.1, "learning_rate": 2.8477239884393066e-05, "loss": 1.4953, "step": 571 }, { "epoch": 0.1, "learning_rate": 2.847453034682081e-05, "loss": 0.8334, "step": 572 }, { "epoch": 0.1, "learning_rate": 2.8471820809248554e-05, "loss": 0.6756, "step": 573 }, { "epoch": 0.1, "learning_rate": 2.8469111271676302e-05, "loss": 0.9142, "step": 574 }, { "epoch": 0.1, "learning_rate": 2.8466401734104047e-05, "loss": 1.9946, "step": 575 }, { "epoch": 0.1, "learning_rate": 2.8463692196531794e-05, "loss": 0.8419, "step": 576 }, { "epoch": 0.1, "learning_rate": 2.8460982658959535e-05, "loss": 0.8533, "step": 577 }, { "epoch": 0.1, "learning_rate": 2.8458273121387283e-05, "loss": 0.9288, "step": 578 }, { "epoch": 0.1, "learning_rate": 2.845556358381503e-05, "loss": 1.3689, "step": 579 }, { "epoch": 0.1, "learning_rate": 2.8452854046242775e-05, "loss": 1.4635, "step": 580 }, { "epoch": 0.1, "learning_rate": 2.8450144508670523e-05, "loss": 1.0293, "step": 581 }, { "epoch": 0.11, "learning_rate": 2.8447434971098264e-05, "loss": 1.4442, "step": 582 }, { "epoch": 0.11, "learning_rate": 2.844472543352601e-05, "loss": 0.8678, "step": 583 }, { "epoch": 0.11, "learning_rate": 2.844201589595376e-05, "loss": 1.4972, "step": 584 }, { "epoch": 0.11, "learning_rate": 2.8439306358381504e-05, "loss": 1.5716, "step": 585 }, { "epoch": 0.11, "learning_rate": 2.8436596820809248e-05, "loss": 1.8056, "step": 586 }, { "epoch": 0.11, "learning_rate": 2.8433887283236993e-05, "loss": 1.097, "step": 587 }, { "epoch": 0.11, "learning_rate": 2.843117774566474e-05, "loss": 0.8157, "step": 588 }, { "epoch": 0.11, "learning_rate": 2.8428468208092488e-05, "loss": 0.9916, "step": 589 }, { "epoch": 0.11, "learning_rate": 2.8425758670520232e-05, "loss": 0.8678, "step": 590 }, { "epoch": 0.11, "learning_rate": 2.8423049132947977e-05, "loss": 0.7199, "step": 591 }, { "epoch": 0.11, "learning_rate": 2.842033959537572e-05, "loss": 1.1353, "step": 592 }, { "epoch": 0.11, "learning_rate": 2.841763005780347e-05, "loss": 0.6147, "step": 593 }, { "epoch": 0.11, "learning_rate": 2.8414920520231217e-05, "loss": 0.4136, "step": 594 }, { "epoch": 0.11, "learning_rate": 2.841221098265896e-05, "loss": 0.9666, "step": 595 }, { "epoch": 0.11, "learning_rate": 2.8409501445086705e-05, "loss": 0.5661, "step": 596 }, { "epoch": 0.11, "learning_rate": 2.840679190751445e-05, "loss": 1.2103, "step": 597 }, { "epoch": 0.11, "learning_rate": 2.8404082369942197e-05, "loss": 0.743, "step": 598 }, { "epoch": 0.11, "learning_rate": 2.8401372832369945e-05, "loss": 0.7178, "step": 599 }, { "epoch": 0.11, "learning_rate": 2.8398663294797686e-05, "loss": 1.5222, "step": 600 }, { "epoch": 0.11, "learning_rate": 2.8395953757225434e-05, "loss": 1.2921, "step": 601 }, { "epoch": 0.11, "learning_rate": 2.839324421965318e-05, "loss": 0.4188, "step": 602 }, { "epoch": 0.11, "learning_rate": 2.8390534682080926e-05, "loss": 1.3431, "step": 603 }, { "epoch": 0.11, "learning_rate": 2.8387825144508674e-05, "loss": 0.727, "step": 604 }, { "epoch": 0.11, "learning_rate": 2.8385115606936415e-05, "loss": 1.8642, "step": 605 }, { "epoch": 0.11, "learning_rate": 2.8382406069364163e-05, "loss": 1.3227, "step": 606 }, { "epoch": 0.11, "learning_rate": 2.8379696531791907e-05, "loss": 0.4103, "step": 607 }, { "epoch": 0.11, "learning_rate": 2.8376986994219655e-05, "loss": 1.2053, "step": 608 }, { "epoch": 0.11, "learning_rate": 2.83742774566474e-05, "loss": 0.8875, "step": 609 }, { "epoch": 0.11, "learning_rate": 2.8371567919075143e-05, "loss": 0.5992, "step": 610 }, { "epoch": 0.11, "learning_rate": 2.836885838150289e-05, "loss": 1.3221, "step": 611 }, { "epoch": 0.11, "learning_rate": 2.8366148843930636e-05, "loss": 1.0118, "step": 612 }, { "epoch": 0.11, "learning_rate": 2.8363439306358383e-05, "loss": 1.2161, "step": 613 }, { "epoch": 0.11, "learning_rate": 2.8360729768786128e-05, "loss": 1.6648, "step": 614 }, { "epoch": 0.11, "learning_rate": 2.8358020231213872e-05, "loss": 1.1621, "step": 615 }, { "epoch": 0.11, "learning_rate": 2.835531069364162e-05, "loss": 0.9289, "step": 616 }, { "epoch": 0.11, "learning_rate": 2.8352601156069368e-05, "loss": 1.085, "step": 617 }, { "epoch": 0.11, "learning_rate": 2.834989161849711e-05, "loss": 1.023, "step": 618 }, { "epoch": 0.11, "learning_rate": 2.8347182080924856e-05, "loss": 1.2731, "step": 619 }, { "epoch": 0.11, "learning_rate": 2.83444725433526e-05, "loss": 0.9813, "step": 620 }, { "epoch": 0.11, "learning_rate": 2.834176300578035e-05, "loss": 0.8787, "step": 621 }, { "epoch": 0.11, "learning_rate": 2.8339053468208096e-05, "loss": 0.6438, "step": 622 }, { "epoch": 0.11, "learning_rate": 2.8336343930635837e-05, "loss": 0.4154, "step": 623 }, { "epoch": 0.11, "learning_rate": 2.8333634393063585e-05, "loss": 0.8459, "step": 624 }, { "epoch": 0.11, "learning_rate": 2.833092485549133e-05, "loss": 0.7929, "step": 625 }, { "epoch": 0.11, "learning_rate": 2.8328215317919077e-05, "loss": 0.9054, "step": 626 }, { "epoch": 0.11, "learning_rate": 2.8325505780346825e-05, "loss": 1.1176, "step": 627 }, { "epoch": 0.11, "learning_rate": 2.8322796242774566e-05, "loss": 0.5923, "step": 628 }, { "epoch": 0.11, "learning_rate": 2.8320086705202313e-05, "loss": 1.1442, "step": 629 }, { "epoch": 0.11, "learning_rate": 2.8317377167630058e-05, "loss": 0.7509, "step": 630 }, { "epoch": 0.11, "learning_rate": 2.8314667630057806e-05, "loss": 1.0459, "step": 631 }, { "epoch": 0.11, "learning_rate": 2.831195809248555e-05, "loss": 0.8004, "step": 632 }, { "epoch": 0.11, "learning_rate": 2.8309248554913294e-05, "loss": 1.2911, "step": 633 }, { "epoch": 0.11, "learning_rate": 2.8306539017341042e-05, "loss": 1.0115, "step": 634 }, { "epoch": 0.11, "learning_rate": 2.8303829479768786e-05, "loss": 1.1634, "step": 635 }, { "epoch": 0.11, "learning_rate": 2.8301119942196534e-05, "loss": 1.168, "step": 636 }, { "epoch": 0.12, "learning_rate": 2.829841040462428e-05, "loss": 1.0149, "step": 637 }, { "epoch": 0.12, "learning_rate": 2.8295700867052023e-05, "loss": 1.117, "step": 638 }, { "epoch": 0.12, "learning_rate": 2.829299132947977e-05, "loss": 0.9764, "step": 639 }, { "epoch": 0.12, "learning_rate": 2.8290281791907515e-05, "loss": 1.6267, "step": 640 }, { "epoch": 0.12, "learning_rate": 2.828757225433526e-05, "loss": 1.041, "step": 641 }, { "epoch": 0.12, "learning_rate": 2.8284862716763007e-05, "loss": 0.7687, "step": 642 }, { "epoch": 0.12, "learning_rate": 2.828215317919075e-05, "loss": 1.0714, "step": 643 }, { "epoch": 0.12, "learning_rate": 2.82794436416185e-05, "loss": 0.6583, "step": 644 }, { "epoch": 0.12, "learning_rate": 2.8276734104046244e-05, "loss": 0.7783, "step": 645 }, { "epoch": 0.12, "learning_rate": 2.8274024566473988e-05, "loss": 1.0408, "step": 646 }, { "epoch": 0.12, "learning_rate": 2.8271315028901736e-05, "loss": 1.5236, "step": 647 }, { "epoch": 0.12, "learning_rate": 2.826860549132948e-05, "loss": 2.1246, "step": 648 }, { "epoch": 0.12, "learning_rate": 2.8265895953757228e-05, "loss": 0.9366, "step": 649 }, { "epoch": 0.12, "learning_rate": 2.8263186416184972e-05, "loss": 0.861, "step": 650 }, { "epoch": 0.12, "learning_rate": 2.8260476878612717e-05, "loss": 1.4661, "step": 651 }, { "epoch": 0.12, "learning_rate": 2.8257767341040464e-05, "loss": 1.4802, "step": 652 }, { "epoch": 0.12, "learning_rate": 2.825505780346821e-05, "loss": 1.3482, "step": 653 }, { "epoch": 0.12, "learning_rate": 2.8252348265895956e-05, "loss": 1.2126, "step": 654 }, { "epoch": 0.12, "learning_rate": 2.8249638728323697e-05, "loss": 0.9379, "step": 655 }, { "epoch": 0.12, "learning_rate": 2.8246929190751445e-05, "loss": 1.0329, "step": 656 }, { "epoch": 0.12, "learning_rate": 2.8244219653179193e-05, "loss": 0.565, "step": 657 }, { "epoch": 0.12, "learning_rate": 2.8241510115606937e-05, "loss": 0.7525, "step": 658 }, { "epoch": 0.12, "learning_rate": 2.8238800578034685e-05, "loss": 1.386, "step": 659 }, { "epoch": 0.12, "learning_rate": 2.8236091040462426e-05, "loss": 0.8356, "step": 660 }, { "epoch": 0.12, "learning_rate": 2.8233381502890174e-05, "loss": 1.0046, "step": 661 }, { "epoch": 0.12, "learning_rate": 2.823067196531792e-05, "loss": 1.0156, "step": 662 }, { "epoch": 0.12, "learning_rate": 2.8227962427745666e-05, "loss": 1.101, "step": 663 }, { "epoch": 0.12, "learning_rate": 2.822525289017341e-05, "loss": 1.0776, "step": 664 }, { "epoch": 0.12, "learning_rate": 2.8222543352601155e-05, "loss": 1.3226, "step": 665 }, { "epoch": 0.12, "learning_rate": 2.8219833815028902e-05, "loss": 1.1723, "step": 666 }, { "epoch": 0.12, "learning_rate": 2.821712427745665e-05, "loss": 0.7684, "step": 667 }, { "epoch": 0.12, "learning_rate": 2.8214414739884395e-05, "loss": 1.4882, "step": 668 }, { "epoch": 0.12, "learning_rate": 2.821170520231214e-05, "loss": 0.5021, "step": 669 }, { "epoch": 0.12, "learning_rate": 2.8208995664739883e-05, "loss": 1.0459, "step": 670 }, { "epoch": 0.12, "learning_rate": 2.820628612716763e-05, "loss": 2.0005, "step": 671 }, { "epoch": 0.12, "learning_rate": 2.820357658959538e-05, "loss": 2.4441, "step": 672 }, { "epoch": 0.12, "learning_rate": 2.8200867052023123e-05, "loss": 1.1614, "step": 673 }, { "epoch": 0.12, "learning_rate": 2.8198157514450867e-05, "loss": 0.833, "step": 674 }, { "epoch": 0.12, "learning_rate": 2.8195447976878612e-05, "loss": 1.1358, "step": 675 }, { "epoch": 0.12, "learning_rate": 2.819273843930636e-05, "loss": 0.8824, "step": 676 }, { "epoch": 0.12, "learning_rate": 2.8190028901734107e-05, "loss": 1.2139, "step": 677 }, { "epoch": 0.12, "learning_rate": 2.818731936416185e-05, "loss": 1.1212, "step": 678 }, { "epoch": 0.12, "learning_rate": 2.8184609826589596e-05, "loss": 0.8534, "step": 679 }, { "epoch": 0.12, "learning_rate": 2.818190028901734e-05, "loss": 0.9712, "step": 680 }, { "epoch": 0.12, "learning_rate": 2.8179190751445088e-05, "loss": 0.8208, "step": 681 }, { "epoch": 0.12, "learning_rate": 2.8176481213872836e-05, "loss": 0.8995, "step": 682 }, { "epoch": 0.12, "learning_rate": 2.8173771676300577e-05, "loss": 0.9161, "step": 683 }, { "epoch": 0.12, "learning_rate": 2.8171062138728325e-05, "loss": 1.0773, "step": 684 }, { "epoch": 0.12, "learning_rate": 2.816835260115607e-05, "loss": 1.1221, "step": 685 }, { "epoch": 0.12, "learning_rate": 2.8165643063583817e-05, "loss": 0.8966, "step": 686 }, { "epoch": 0.12, "learning_rate": 2.816293352601156e-05, "loss": 1.4251, "step": 687 }, { "epoch": 0.12, "learning_rate": 2.8160223988439306e-05, "loss": 1.183, "step": 688 }, { "epoch": 0.12, "learning_rate": 2.8157514450867053e-05, "loss": 1.3651, "step": 689 }, { "epoch": 0.12, "learning_rate": 2.8154804913294798e-05, "loss": 0.8681, "step": 690 }, { "epoch": 0.12, "learning_rate": 2.8152095375722545e-05, "loss": 0.7526, "step": 691 }, { "epoch": 0.12, "learning_rate": 2.814938583815029e-05, "loss": 1.6744, "step": 692 }, { "epoch": 0.13, "learning_rate": 2.8146676300578034e-05, "loss": 0.9075, "step": 693 }, { "epoch": 0.13, "learning_rate": 2.8143966763005782e-05, "loss": 0.7806, "step": 694 }, { "epoch": 0.13, "learning_rate": 2.8141257225433526e-05, "loss": 1.337, "step": 695 }, { "epoch": 0.13, "learning_rate": 2.8138547687861274e-05, "loss": 0.6916, "step": 696 }, { "epoch": 0.13, "learning_rate": 2.813583815028902e-05, "loss": 1.3674, "step": 697 }, { "epoch": 0.13, "learning_rate": 2.8133128612716763e-05, "loss": 1.1732, "step": 698 }, { "epoch": 0.13, "learning_rate": 2.813041907514451e-05, "loss": 0.8698, "step": 699 }, { "epoch": 0.13, "learning_rate": 2.8127709537572255e-05, "loss": 1.0658, "step": 700 }, { "epoch": 0.13, "learning_rate": 2.8125e-05, "loss": 1.0119, "step": 701 }, { "epoch": 0.13, "learning_rate": 2.8122290462427747e-05, "loss": 1.2235, "step": 702 }, { "epoch": 0.13, "learning_rate": 2.811958092485549e-05, "loss": 0.6745, "step": 703 }, { "epoch": 0.13, "learning_rate": 2.811687138728324e-05, "loss": 0.7916, "step": 704 }, { "epoch": 0.13, "learning_rate": 2.8114161849710983e-05, "loss": 1.0572, "step": 705 }, { "epoch": 0.13, "learning_rate": 2.8111452312138728e-05, "loss": 1.1007, "step": 706 }, { "epoch": 0.13, "learning_rate": 2.8108742774566476e-05, "loss": 0.3892, "step": 707 }, { "epoch": 0.13, "learning_rate": 2.810603323699422e-05, "loss": 1.2284, "step": 708 }, { "epoch": 0.13, "learning_rate": 2.8103323699421968e-05, "loss": 1.5721, "step": 709 }, { "epoch": 0.13, "learning_rate": 2.810061416184971e-05, "loss": 0.5643, "step": 710 }, { "epoch": 0.13, "learning_rate": 2.8097904624277456e-05, "loss": 0.4365, "step": 711 }, { "epoch": 0.13, "learning_rate": 2.8095195086705204e-05, "loss": 0.9921, "step": 712 }, { "epoch": 0.13, "learning_rate": 2.809248554913295e-05, "loss": 1.0118, "step": 713 }, { "epoch": 0.13, "learning_rate": 2.8089776011560696e-05, "loss": 1.2083, "step": 714 }, { "epoch": 0.13, "learning_rate": 2.8087066473988437e-05, "loss": 0.8985, "step": 715 }, { "epoch": 0.13, "learning_rate": 2.8084356936416185e-05, "loss": 1.4607, "step": 716 }, { "epoch": 0.13, "learning_rate": 2.8081647398843933e-05, "loss": 0.913, "step": 717 }, { "epoch": 0.13, "learning_rate": 2.8078937861271677e-05, "loss": 0.6669, "step": 718 }, { "epoch": 0.13, "learning_rate": 2.8076228323699425e-05, "loss": 0.5583, "step": 719 }, { "epoch": 0.13, "learning_rate": 2.8073518786127166e-05, "loss": 0.7889, "step": 720 }, { "epoch": 0.13, "learning_rate": 2.8070809248554914e-05, "loss": 0.8314, "step": 721 }, { "epoch": 0.13, "learning_rate": 2.806809971098266e-05, "loss": 1.0347, "step": 722 }, { "epoch": 0.13, "learning_rate": 2.8065390173410406e-05, "loss": 0.7854, "step": 723 }, { "epoch": 0.13, "learning_rate": 2.806268063583815e-05, "loss": 1.1869, "step": 724 }, { "epoch": 0.13, "learning_rate": 2.8059971098265894e-05, "loss": 1.4428, "step": 725 }, { "epoch": 0.13, "learning_rate": 2.8057261560693642e-05, "loss": 1.2581, "step": 726 }, { "epoch": 0.13, "learning_rate": 2.805455202312139e-05, "loss": 2.4176, "step": 727 }, { "epoch": 0.13, "learning_rate": 2.8051842485549134e-05, "loss": 1.0237, "step": 728 }, { "epoch": 0.13, "learning_rate": 2.804913294797688e-05, "loss": 0.6517, "step": 729 }, { "epoch": 0.13, "learning_rate": 2.8046423410404623e-05, "loss": 1.4238, "step": 730 }, { "epoch": 0.13, "learning_rate": 2.804371387283237e-05, "loss": 1.438, "step": 731 }, { "epoch": 0.13, "learning_rate": 2.804100433526012e-05, "loss": 1.277, "step": 732 }, { "epoch": 0.13, "learning_rate": 2.803829479768786e-05, "loss": 1.2226, "step": 733 }, { "epoch": 0.13, "learning_rate": 2.8035585260115607e-05, "loss": 0.5095, "step": 734 }, { "epoch": 0.13, "learning_rate": 2.803287572254335e-05, "loss": 1.4432, "step": 735 }, { "epoch": 0.13, "learning_rate": 2.80301661849711e-05, "loss": 0.8539, "step": 736 }, { "epoch": 0.13, "learning_rate": 2.8027456647398847e-05, "loss": 1.5294, "step": 737 }, { "epoch": 0.13, "learning_rate": 2.8024747109826588e-05, "loss": 0.9817, "step": 738 }, { "epoch": 0.13, "learning_rate": 2.8022037572254336e-05, "loss": 0.9258, "step": 739 }, { "epoch": 0.13, "learning_rate": 2.801932803468208e-05, "loss": 0.841, "step": 740 }, { "epoch": 0.13, "learning_rate": 2.8016618497109828e-05, "loss": 1.5561, "step": 741 }, { "epoch": 0.13, "learning_rate": 2.8013908959537576e-05, "loss": 1.6248, "step": 742 }, { "epoch": 0.13, "learning_rate": 2.8011199421965317e-05, "loss": 0.7492, "step": 743 }, { "epoch": 0.13, "learning_rate": 2.8008489884393065e-05, "loss": 1.457, "step": 744 }, { "epoch": 0.13, "learning_rate": 2.800578034682081e-05, "loss": 1.3646, "step": 745 }, { "epoch": 0.13, "learning_rate": 2.8003070809248557e-05, "loss": 0.9751, "step": 746 }, { "epoch": 0.13, "learning_rate": 2.80003612716763e-05, "loss": 1.1111, "step": 747 }, { "epoch": 0.14, "learning_rate": 2.7997651734104045e-05, "loss": 1.1189, "step": 748 }, { "epoch": 0.14, "learning_rate": 2.7994942196531793e-05, "loss": 1.49, "step": 749 }, { "epoch": 0.14, "learning_rate": 2.7992232658959537e-05, "loss": 0.9961, "step": 750 }, { "epoch": 0.14, "learning_rate": 2.7989523121387285e-05, "loss": 1.051, "step": 751 }, { "epoch": 0.14, "learning_rate": 2.798681358381503e-05, "loss": 1.0765, "step": 752 }, { "epoch": 0.14, "learning_rate": 2.7984104046242774e-05, "loss": 0.6818, "step": 753 }, { "epoch": 0.14, "learning_rate": 2.7981394508670522e-05, "loss": 1.2363, "step": 754 }, { "epoch": 0.14, "learning_rate": 2.7978684971098266e-05, "loss": 1.0966, "step": 755 }, { "epoch": 0.14, "learning_rate": 2.797597543352601e-05, "loss": 0.7551, "step": 756 }, { "epoch": 0.14, "learning_rate": 2.7973265895953758e-05, "loss": 1.0322, "step": 757 }, { "epoch": 0.14, "learning_rate": 2.7970556358381503e-05, "loss": 1.7443, "step": 758 }, { "epoch": 0.14, "learning_rate": 2.796784682080925e-05, "loss": 0.553, "step": 759 }, { "epoch": 0.14, "learning_rate": 2.7965137283236995e-05, "loss": 0.5706, "step": 760 }, { "epoch": 0.14, "learning_rate": 2.796242774566474e-05, "loss": 1.0929, "step": 761 }, { "epoch": 0.14, "learning_rate": 2.7959718208092487e-05, "loss": 0.7925, "step": 762 }, { "epoch": 0.14, "learning_rate": 2.795700867052023e-05, "loss": 1.2743, "step": 763 }, { "epoch": 0.14, "learning_rate": 2.795429913294798e-05, "loss": 1.4745, "step": 764 }, { "epoch": 0.14, "learning_rate": 2.7951589595375723e-05, "loss": 1.131, "step": 765 }, { "epoch": 0.14, "learning_rate": 2.7948880057803468e-05, "loss": 1.0005, "step": 766 }, { "epoch": 0.14, "learning_rate": 2.7946170520231215e-05, "loss": 1.2322, "step": 767 }, { "epoch": 0.14, "learning_rate": 2.794346098265896e-05, "loss": 0.9362, "step": 768 }, { "epoch": 0.14, "learning_rate": 2.7940751445086708e-05, "loss": 1.4414, "step": 769 }, { "epoch": 0.14, "learning_rate": 2.793804190751445e-05, "loss": 1.5657, "step": 770 }, { "epoch": 0.14, "learning_rate": 2.7935332369942196e-05, "loss": 1.1016, "step": 771 }, { "epoch": 0.14, "learning_rate": 2.7932622832369944e-05, "loss": 1.3445, "step": 772 }, { "epoch": 0.14, "learning_rate": 2.792991329479769e-05, "loss": 1.2473, "step": 773 }, { "epoch": 0.14, "learning_rate": 2.7927203757225436e-05, "loss": 0.7537, "step": 774 }, { "epoch": 0.14, "learning_rate": 2.7924494219653177e-05, "loss": 0.784, "step": 775 }, { "epoch": 0.14, "learning_rate": 2.7921784682080925e-05, "loss": 1.2959, "step": 776 }, { "epoch": 0.14, "learning_rate": 2.7919075144508673e-05, "loss": 1.0931, "step": 777 }, { "epoch": 0.14, "learning_rate": 2.7916365606936417e-05, "loss": 0.7818, "step": 778 }, { "epoch": 0.14, "learning_rate": 2.791365606936416e-05, "loss": 0.7417, "step": 779 }, { "epoch": 0.14, "learning_rate": 2.7910946531791906e-05, "loss": 1.3747, "step": 780 }, { "epoch": 0.14, "learning_rate": 2.7908236994219653e-05, "loss": 0.5721, "step": 781 }, { "epoch": 0.14, "learning_rate": 2.79055274566474e-05, "loss": 0.922, "step": 782 }, { "epoch": 0.14, "learning_rate": 2.7902817919075146e-05, "loss": 1.5071, "step": 783 }, { "epoch": 0.14, "learning_rate": 2.790010838150289e-05, "loss": 1.4358, "step": 784 }, { "epoch": 0.14, "learning_rate": 2.7897398843930634e-05, "loss": 1.0161, "step": 785 }, { "epoch": 0.14, "learning_rate": 2.7894689306358382e-05, "loss": 0.6486, "step": 786 }, { "epoch": 0.14, "learning_rate": 2.789197976878613e-05, "loss": 0.7483, "step": 787 }, { "epoch": 0.14, "learning_rate": 2.7889270231213874e-05, "loss": 1.0414, "step": 788 }, { "epoch": 0.14, "learning_rate": 2.788656069364162e-05, "loss": 0.6672, "step": 789 }, { "epoch": 0.14, "learning_rate": 2.7883851156069366e-05, "loss": 0.6806, "step": 790 }, { "epoch": 0.14, "learning_rate": 2.788114161849711e-05, "loss": 0.8446, "step": 791 }, { "epoch": 0.14, "learning_rate": 2.787843208092486e-05, "loss": 1.4472, "step": 792 }, { "epoch": 0.14, "learning_rate": 2.78757225433526e-05, "loss": 0.6006, "step": 793 }, { "epoch": 0.14, "learning_rate": 2.7873013005780347e-05, "loss": 1.6945, "step": 794 }, { "epoch": 0.14, "learning_rate": 2.7870303468208095e-05, "loss": 0.9115, "step": 795 }, { "epoch": 0.14, "learning_rate": 2.786759393063584e-05, "loss": 1.4451, "step": 796 }, { "epoch": 0.14, "learning_rate": 2.7864884393063587e-05, "loss": 0.5979, "step": 797 }, { "epoch": 0.14, "learning_rate": 2.7862174855491328e-05, "loss": 0.9074, "step": 798 }, { "epoch": 0.14, "learning_rate": 2.7859465317919076e-05, "loss": 0.8161, "step": 799 }, { "epoch": 0.14, "learning_rate": 2.7856755780346824e-05, "loss": 0.8894, "step": 800 }, { "epoch": 0.14, "learning_rate": 2.7854046242774568e-05, "loss": 0.8568, "step": 801 }, { "epoch": 0.14, "learning_rate": 2.7851336705202312e-05, "loss": 0.5771, "step": 802 }, { "epoch": 0.15, "learning_rate": 2.7848627167630057e-05, "loss": 1.3506, "step": 803 }, { "epoch": 0.15, "learning_rate": 2.7845917630057804e-05, "loss": 1.19, "step": 804 }, { "epoch": 0.15, "learning_rate": 2.7843208092485552e-05, "loss": 1.1031, "step": 805 }, { "epoch": 0.15, "learning_rate": 2.7840498554913296e-05, "loss": 1.0725, "step": 806 }, { "epoch": 0.15, "learning_rate": 2.783778901734104e-05, "loss": 0.8459, "step": 807 }, { "epoch": 0.15, "learning_rate": 2.7835079479768785e-05, "loss": 0.9394, "step": 808 }, { "epoch": 0.15, "learning_rate": 2.7832369942196533e-05, "loss": 0.8313, "step": 809 }, { "epoch": 0.15, "learning_rate": 2.782966040462428e-05, "loss": 0.7609, "step": 810 }, { "epoch": 0.15, "learning_rate": 2.7826950867052025e-05, "loss": 1.1903, "step": 811 }, { "epoch": 0.15, "learning_rate": 2.782424132947977e-05, "loss": 0.757, "step": 812 }, { "epoch": 0.15, "learning_rate": 2.7821531791907514e-05, "loss": 1.0068, "step": 813 }, { "epoch": 0.15, "learning_rate": 2.781882225433526e-05, "loss": 1.271, "step": 814 }, { "epoch": 0.15, "learning_rate": 2.781611271676301e-05, "loss": 0.853, "step": 815 }, { "epoch": 0.15, "learning_rate": 2.781340317919075e-05, "loss": 0.7774, "step": 816 }, { "epoch": 0.15, "learning_rate": 2.7810693641618498e-05, "loss": 1.7015, "step": 817 }, { "epoch": 0.15, "learning_rate": 2.7807984104046242e-05, "loss": 0.9571, "step": 818 }, { "epoch": 0.15, "learning_rate": 2.780527456647399e-05, "loss": 0.7968, "step": 819 }, { "epoch": 0.15, "learning_rate": 2.7802565028901738e-05, "loss": 1.2678, "step": 820 }, { "epoch": 0.15, "learning_rate": 2.779985549132948e-05, "loss": 1.0387, "step": 821 }, { "epoch": 0.15, "learning_rate": 2.7797145953757227e-05, "loss": 0.7127, "step": 822 }, { "epoch": 0.15, "learning_rate": 2.779443641618497e-05, "loss": 1.0757, "step": 823 }, { "epoch": 0.15, "learning_rate": 2.779172687861272e-05, "loss": 0.8965, "step": 824 }, { "epoch": 0.15, "learning_rate": 2.7789017341040463e-05, "loss": 0.9955, "step": 825 }, { "epoch": 0.15, "learning_rate": 2.7786307803468207e-05, "loss": 0.5395, "step": 826 }, { "epoch": 0.15, "learning_rate": 2.7783598265895955e-05, "loss": 0.7345, "step": 827 }, { "epoch": 0.15, "learning_rate": 2.77808887283237e-05, "loss": 1.1234, "step": 828 }, { "epoch": 0.15, "learning_rate": 2.7778179190751447e-05, "loss": 0.531, "step": 829 }, { "epoch": 0.15, "learning_rate": 2.7775469653179192e-05, "loss": 1.3141, "step": 830 }, { "epoch": 0.15, "learning_rate": 2.7772760115606936e-05, "loss": 0.8297, "step": 831 }, { "epoch": 0.15, "learning_rate": 2.7770050578034684e-05, "loss": 1.021, "step": 832 }, { "epoch": 0.15, "learning_rate": 2.7767341040462428e-05, "loss": 1.19, "step": 833 }, { "epoch": 0.15, "learning_rate": 2.7764631502890173e-05, "loss": 1.6564, "step": 834 }, { "epoch": 0.15, "learning_rate": 2.776192196531792e-05, "loss": 0.5593, "step": 835 }, { "epoch": 0.15, "learning_rate": 2.7759212427745665e-05, "loss": 0.9268, "step": 836 }, { "epoch": 0.15, "learning_rate": 2.7756502890173412e-05, "loss": 0.8848, "step": 837 }, { "epoch": 0.15, "learning_rate": 2.7753793352601157e-05, "loss": 0.8073, "step": 838 }, { "epoch": 0.15, "learning_rate": 2.77510838150289e-05, "loss": 1.2339, "step": 839 }, { "epoch": 0.15, "learning_rate": 2.774837427745665e-05, "loss": 0.7006, "step": 840 }, { "epoch": 0.15, "learning_rate": 2.7745664739884393e-05, "loss": 0.7606, "step": 841 }, { "epoch": 0.15, "learning_rate": 2.774295520231214e-05, "loss": 1.2458, "step": 842 }, { "epoch": 0.15, "learning_rate": 2.7740245664739885e-05, "loss": 0.8123, "step": 843 }, { "epoch": 0.15, "learning_rate": 2.773753612716763e-05, "loss": 0.7925, "step": 844 }, { "epoch": 0.15, "learning_rate": 2.7734826589595378e-05, "loss": 1.2151, "step": 845 }, { "epoch": 0.15, "learning_rate": 2.7732117052023122e-05, "loss": 0.6452, "step": 846 }, { "epoch": 0.15, "learning_rate": 2.772940751445087e-05, "loss": 0.5853, "step": 847 }, { "epoch": 0.15, "learning_rate": 2.772669797687861e-05, "loss": 0.6683, "step": 848 }, { "epoch": 0.15, "learning_rate": 2.772398843930636e-05, "loss": 0.4423, "step": 849 }, { "epoch": 0.15, "learning_rate": 2.7721278901734106e-05, "loss": 1.4691, "step": 850 }, { "epoch": 0.15, "learning_rate": 2.771856936416185e-05, "loss": 1.0571, "step": 851 }, { "epoch": 0.15, "learning_rate": 2.7715859826589598e-05, "loss": 1.5251, "step": 852 }, { "epoch": 0.15, "learning_rate": 2.771315028901734e-05, "loss": 1.0191, "step": 853 }, { "epoch": 0.15, "learning_rate": 2.7710440751445087e-05, "loss": 0.5007, "step": 854 }, { "epoch": 0.15, "learning_rate": 2.7707731213872835e-05, "loss": 0.5689, "step": 855 }, { "epoch": 0.15, "learning_rate": 2.770502167630058e-05, "loss": 1.1781, "step": 856 }, { "epoch": 0.15, "learning_rate": 2.7702312138728323e-05, "loss": 1.1913, "step": 857 }, { "epoch": 0.15, "learning_rate": 2.7699602601156068e-05, "loss": 0.8704, "step": 858 }, { "epoch": 0.16, "learning_rate": 2.7696893063583816e-05, "loss": 0.6323, "step": 859 }, { "epoch": 0.16, "learning_rate": 2.7694183526011563e-05, "loss": 1.1579, "step": 860 }, { "epoch": 0.16, "learning_rate": 2.7691473988439308e-05, "loss": 1.5664, "step": 861 }, { "epoch": 0.16, "learning_rate": 2.7688764450867052e-05, "loss": 0.5971, "step": 862 }, { "epoch": 0.16, "learning_rate": 2.7686054913294796e-05, "loss": 0.5582, "step": 863 }, { "epoch": 0.16, "learning_rate": 2.7683345375722544e-05, "loss": 1.3122, "step": 864 }, { "epoch": 0.16, "learning_rate": 2.7680635838150292e-05, "loss": 0.5589, "step": 865 }, { "epoch": 0.16, "learning_rate": 2.7677926300578036e-05, "loss": 1.6883, "step": 866 }, { "epoch": 0.16, "learning_rate": 2.767521676300578e-05, "loss": 1.0956, "step": 867 }, { "epoch": 0.16, "learning_rate": 2.7672507225433525e-05, "loss": 0.7818, "step": 868 }, { "epoch": 0.16, "learning_rate": 2.7669797687861273e-05, "loss": 1.0561, "step": 869 }, { "epoch": 0.16, "learning_rate": 2.766708815028902e-05, "loss": 1.0981, "step": 870 }, { "epoch": 0.16, "learning_rate": 2.766437861271676e-05, "loss": 1.464, "step": 871 }, { "epoch": 0.16, "learning_rate": 2.766166907514451e-05, "loss": 1.7068, "step": 872 }, { "epoch": 0.16, "learning_rate": 2.7658959537572254e-05, "loss": 1.3775, "step": 873 }, { "epoch": 0.16, "learning_rate": 2.765625e-05, "loss": 1.1988, "step": 874 }, { "epoch": 0.16, "learning_rate": 2.765354046242775e-05, "loss": 1.1765, "step": 875 }, { "epoch": 0.16, "learning_rate": 2.765083092485549e-05, "loss": 1.3704, "step": 876 }, { "epoch": 0.16, "learning_rate": 2.7648121387283238e-05, "loss": 1.3244, "step": 877 }, { "epoch": 0.16, "learning_rate": 2.7645411849710982e-05, "loss": 0.7842, "step": 878 }, { "epoch": 0.16, "learning_rate": 2.764270231213873e-05, "loss": 0.4093, "step": 879 }, { "epoch": 0.16, "learning_rate": 2.7639992774566474e-05, "loss": 1.0794, "step": 880 }, { "epoch": 0.16, "learning_rate": 2.763728323699422e-05, "loss": 1.5416, "step": 881 }, { "epoch": 0.16, "learning_rate": 2.7634573699421966e-05, "loss": 1.0149, "step": 882 }, { "epoch": 0.16, "learning_rate": 2.763186416184971e-05, "loss": 0.7616, "step": 883 }, { "epoch": 0.16, "learning_rate": 2.762915462427746e-05, "loss": 0.5628, "step": 884 }, { "epoch": 0.16, "learning_rate": 2.7626445086705203e-05, "loss": 0.9771, "step": 885 }, { "epoch": 0.16, "learning_rate": 2.7623735549132947e-05, "loss": 0.7611, "step": 886 }, { "epoch": 0.16, "learning_rate": 2.7621026011560695e-05, "loss": 1.4908, "step": 887 }, { "epoch": 0.16, "learning_rate": 2.761831647398844e-05, "loss": 0.7137, "step": 888 }, { "epoch": 0.16, "learning_rate": 2.7615606936416187e-05, "loss": 1.3083, "step": 889 }, { "epoch": 0.16, "learning_rate": 2.761289739884393e-05, "loss": 1.0475, "step": 890 }, { "epoch": 0.16, "learning_rate": 2.7610187861271676e-05, "loss": 1.6508, "step": 891 }, { "epoch": 0.16, "learning_rate": 2.7607478323699424e-05, "loss": 1.0542, "step": 892 }, { "epoch": 0.16, "learning_rate": 2.7604768786127168e-05, "loss": 1.0106, "step": 893 }, { "epoch": 0.16, "learning_rate": 2.7602059248554912e-05, "loss": 0.6363, "step": 894 }, { "epoch": 0.16, "learning_rate": 2.759934971098266e-05, "loss": 0.6879, "step": 895 }, { "epoch": 0.16, "learning_rate": 2.7596640173410405e-05, "loss": 1.5139, "step": 896 }, { "epoch": 0.16, "learning_rate": 2.7593930635838152e-05, "loss": 0.4219, "step": 897 }, { "epoch": 0.16, "learning_rate": 2.7591221098265897e-05, "loss": 1.0325, "step": 898 }, { "epoch": 0.16, "learning_rate": 2.758851156069364e-05, "loss": 0.8847, "step": 899 }, { "epoch": 0.16, "learning_rate": 2.758580202312139e-05, "loss": 1.1198, "step": 900 }, { "epoch": 0.16, "learning_rate": 2.7583092485549133e-05, "loss": 0.823, "step": 901 }, { "epoch": 0.16, "learning_rate": 2.758038294797688e-05, "loss": 0.9938, "step": 902 }, { "epoch": 0.16, "learning_rate": 2.7577673410404622e-05, "loss": 1.328, "step": 903 }, { "epoch": 0.16, "learning_rate": 2.757496387283237e-05, "loss": 1.484, "step": 904 }, { "epoch": 0.16, "learning_rate": 2.7572254335260117e-05, "loss": 1.427, "step": 905 }, { "epoch": 0.16, "learning_rate": 2.7569544797687862e-05, "loss": 1.5971, "step": 906 }, { "epoch": 0.16, "learning_rate": 2.756683526011561e-05, "loss": 1.0224, "step": 907 }, { "epoch": 0.16, "learning_rate": 2.756412572254335e-05, "loss": 1.4796, "step": 908 }, { "epoch": 0.16, "learning_rate": 2.7561416184971098e-05, "loss": 1.1755, "step": 909 }, { "epoch": 0.16, "learning_rate": 2.7558706647398846e-05, "loss": 0.6793, "step": 910 }, { "epoch": 0.16, "learning_rate": 2.755599710982659e-05, "loss": 0.8102, "step": 911 }, { "epoch": 0.16, "learning_rate": 2.7553287572254338e-05, "loss": 0.9328, "step": 912 }, { "epoch": 0.16, "learning_rate": 2.755057803468208e-05, "loss": 1.0017, "step": 913 }, { "epoch": 0.17, "learning_rate": 2.7547868497109827e-05, "loss": 0.6738, "step": 914 }, { "epoch": 0.17, "learning_rate": 2.7545158959537575e-05, "loss": 1.0676, "step": 915 }, { "epoch": 0.17, "learning_rate": 2.754244942196532e-05, "loss": 0.6348, "step": 916 }, { "epoch": 0.17, "learning_rate": 2.7539739884393063e-05, "loss": 0.9518, "step": 917 }, { "epoch": 0.17, "learning_rate": 2.7537030346820808e-05, "loss": 1.9245, "step": 918 }, { "epoch": 0.17, "learning_rate": 2.7534320809248555e-05, "loss": 0.717, "step": 919 }, { "epoch": 0.17, "learning_rate": 2.7531611271676303e-05, "loss": 0.571, "step": 920 }, { "epoch": 0.17, "learning_rate": 2.7528901734104048e-05, "loss": 1.8078, "step": 921 }, { "epoch": 0.17, "learning_rate": 2.7526192196531792e-05, "loss": 1.0936, "step": 922 }, { "epoch": 0.17, "learning_rate": 2.7523482658959536e-05, "loss": 1.8783, "step": 923 }, { "epoch": 0.17, "learning_rate": 2.7520773121387284e-05, "loss": 0.8174, "step": 924 }, { "epoch": 0.17, "learning_rate": 2.7518063583815032e-05, "loss": 0.8706, "step": 925 }, { "epoch": 0.17, "learning_rate": 2.7515354046242773e-05, "loss": 0.7113, "step": 926 }, { "epoch": 0.17, "learning_rate": 2.751264450867052e-05, "loss": 1.1932, "step": 927 }, { "epoch": 0.17, "learning_rate": 2.7509934971098265e-05, "loss": 1.1753, "step": 928 }, { "epoch": 0.17, "learning_rate": 2.7507225433526013e-05, "loss": 1.1405, "step": 929 }, { "epoch": 0.17, "learning_rate": 2.750451589595376e-05, "loss": 0.7717, "step": 930 }, { "epoch": 0.17, "learning_rate": 2.75018063583815e-05, "loss": 0.8579, "step": 931 }, { "epoch": 0.17, "learning_rate": 2.749909682080925e-05, "loss": 2.2406, "step": 932 }, { "epoch": 0.17, "learning_rate": 2.7496387283236993e-05, "loss": 1.6968, "step": 933 }, { "epoch": 0.17, "learning_rate": 2.749367774566474e-05, "loss": 1.1287, "step": 934 }, { "epoch": 0.17, "learning_rate": 2.749096820809249e-05, "loss": 1.1099, "step": 935 }, { "epoch": 0.17, "learning_rate": 2.748825867052023e-05, "loss": 0.4451, "step": 936 }, { "epoch": 0.17, "learning_rate": 2.7485549132947978e-05, "loss": 1.1993, "step": 937 }, { "epoch": 0.17, "learning_rate": 2.7482839595375722e-05, "loss": 1.0067, "step": 938 }, { "epoch": 0.17, "learning_rate": 2.748013005780347e-05, "loss": 1.2121, "step": 939 }, { "epoch": 0.17, "learning_rate": 2.7477420520231214e-05, "loss": 1.1094, "step": 940 }, { "epoch": 0.17, "learning_rate": 2.747471098265896e-05, "loss": 0.2531, "step": 941 }, { "epoch": 0.17, "learning_rate": 2.7472001445086706e-05, "loss": 1.6664, "step": 942 }, { "epoch": 0.17, "learning_rate": 2.746929190751445e-05, "loss": 0.647, "step": 943 }, { "epoch": 0.17, "learning_rate": 2.74665823699422e-05, "loss": 0.5705, "step": 944 }, { "epoch": 0.17, "learning_rate": 2.7463872832369943e-05, "loss": 1.2014, "step": 945 }, { "epoch": 0.17, "learning_rate": 2.7461163294797687e-05, "loss": 0.7785, "step": 946 }, { "epoch": 0.17, "learning_rate": 2.7458453757225435e-05, "loss": 0.7269, "step": 947 }, { "epoch": 0.17, "learning_rate": 2.745574421965318e-05, "loss": 1.0316, "step": 948 }, { "epoch": 0.17, "learning_rate": 2.7453034682080924e-05, "loss": 0.8364, "step": 949 }, { "epoch": 0.17, "learning_rate": 2.745032514450867e-05, "loss": 0.9091, "step": 950 }, { "epoch": 0.17, "learning_rate": 2.7447615606936416e-05, "loss": 1.1259, "step": 951 }, { "epoch": 0.17, "learning_rate": 2.7444906069364164e-05, "loss": 1.0319, "step": 952 }, { "epoch": 0.17, "learning_rate": 2.7442196531791908e-05, "loss": 0.9675, "step": 953 }, { "epoch": 0.17, "learning_rate": 2.7439486994219652e-05, "loss": 1.1224, "step": 954 }, { "epoch": 0.17, "learning_rate": 2.74367774566474e-05, "loss": 0.9946, "step": 955 }, { "epoch": 0.17, "learning_rate": 2.7434067919075144e-05, "loss": 0.885, "step": 956 }, { "epoch": 0.17, "learning_rate": 2.7431358381502892e-05, "loss": 1.4718, "step": 957 }, { "epoch": 0.17, "learning_rate": 2.7428648843930636e-05, "loss": 0.9098, "step": 958 }, { "epoch": 0.17, "learning_rate": 2.742593930635838e-05, "loss": 1.5386, "step": 959 }, { "epoch": 0.17, "learning_rate": 2.742322976878613e-05, "loss": 0.6942, "step": 960 }, { "epoch": 0.17, "learning_rate": 2.7420520231213873e-05, "loss": 1.4515, "step": 961 }, { "epoch": 0.17, "learning_rate": 2.741781069364162e-05, "loss": 1.1143, "step": 962 }, { "epoch": 0.17, "learning_rate": 2.7415101156069365e-05, "loss": 0.6921, "step": 963 }, { "epoch": 0.17, "learning_rate": 2.741239161849711e-05, "loss": 0.5639, "step": 964 }, { "epoch": 0.17, "learning_rate": 2.7409682080924857e-05, "loss": 1.0967, "step": 965 }, { "epoch": 0.17, "learning_rate": 2.74069725433526e-05, "loss": 1.158, "step": 966 }, { "epoch": 0.17, "learning_rate": 2.740426300578035e-05, "loss": 0.6437, "step": 967 }, { "epoch": 0.17, "learning_rate": 2.7401553468208094e-05, "loss": 0.3945, "step": 968 }, { "epoch": 0.18, "learning_rate": 2.7398843930635838e-05, "loss": 0.9302, "step": 969 }, { "epoch": 0.18, "learning_rate": 2.7396134393063586e-05, "loss": 0.8364, "step": 970 }, { "epoch": 0.18, "learning_rate": 2.739342485549133e-05, "loss": 1.1711, "step": 971 }, { "epoch": 0.18, "learning_rate": 2.7390715317919075e-05, "loss": 1.075, "step": 972 }, { "epoch": 0.18, "learning_rate": 2.7388005780346822e-05, "loss": 0.7932, "step": 973 }, { "epoch": 0.18, "learning_rate": 2.7385296242774567e-05, "loss": 0.7642, "step": 974 }, { "epoch": 0.18, "learning_rate": 2.7382586705202314e-05, "loss": 0.9651, "step": 975 }, { "epoch": 0.18, "learning_rate": 2.737987716763006e-05, "loss": 1.1608, "step": 976 }, { "epoch": 0.18, "learning_rate": 2.7377167630057803e-05, "loss": 0.7735, "step": 977 }, { "epoch": 0.18, "learning_rate": 2.737445809248555e-05, "loss": 0.8107, "step": 978 }, { "epoch": 0.18, "learning_rate": 2.7371748554913295e-05, "loss": 1.8141, "step": 979 }, { "epoch": 0.18, "learning_rate": 2.7369039017341043e-05, "loss": 0.7384, "step": 980 }, { "epoch": 0.18, "learning_rate": 2.7366329479768787e-05, "loss": 1.4917, "step": 981 }, { "epoch": 0.18, "learning_rate": 2.7363619942196532e-05, "loss": 0.8097, "step": 982 }, { "epoch": 0.18, "learning_rate": 2.736091040462428e-05, "loss": 0.7886, "step": 983 }, { "epoch": 0.18, "learning_rate": 2.7358200867052024e-05, "loss": 0.4284, "step": 984 }, { "epoch": 0.18, "learning_rate": 2.735549132947977e-05, "loss": 1.1153, "step": 985 }, { "epoch": 0.18, "learning_rate": 2.7352781791907513e-05, "loss": 0.9451, "step": 986 }, { "epoch": 0.18, "learning_rate": 2.735007225433526e-05, "loss": 1.2661, "step": 987 }, { "epoch": 0.18, "learning_rate": 2.7347362716763008e-05, "loss": 1.2026, "step": 988 }, { "epoch": 0.18, "learning_rate": 2.7344653179190752e-05, "loss": 0.3456, "step": 989 }, { "epoch": 0.18, "learning_rate": 2.73419436416185e-05, "loss": 1.108, "step": 990 }, { "epoch": 0.18, "learning_rate": 2.733923410404624e-05, "loss": 0.5651, "step": 991 }, { "epoch": 0.18, "learning_rate": 2.733652456647399e-05, "loss": 1.3087, "step": 992 }, { "epoch": 0.18, "learning_rate": 2.7333815028901737e-05, "loss": 0.9802, "step": 993 }, { "epoch": 0.18, "learning_rate": 2.733110549132948e-05, "loss": 0.929, "step": 994 }, { "epoch": 0.18, "learning_rate": 2.7328395953757225e-05, "loss": 1.0242, "step": 995 }, { "epoch": 0.18, "learning_rate": 2.732568641618497e-05, "loss": 0.7341, "step": 996 }, { "epoch": 0.18, "learning_rate": 2.7322976878612718e-05, "loss": 1.2786, "step": 997 }, { "epoch": 0.18, "learning_rate": 2.7320267341040465e-05, "loss": 0.5967, "step": 998 }, { "epoch": 0.18, "learning_rate": 2.731755780346821e-05, "loss": 1.8771, "step": 999 }, { "epoch": 0.18, "learning_rate": 2.7314848265895954e-05, "loss": 1.0514, "step": 1000 }, { "epoch": 0.18, "eval_exact_match": 83.41532639545885, "eval_f1": 90.96549037923651, "step": 1000 }, { "epoch": 0.18, "learning_rate": 2.73121387283237e-05, "loss": 0.9793, "step": 1001 }, { "epoch": 0.18, "learning_rate": 2.7309429190751446e-05, "loss": 1.9368, "step": 1002 }, { "epoch": 0.18, "learning_rate": 2.7306719653179194e-05, "loss": 0.4733, "step": 1003 }, { "epoch": 0.18, "learning_rate": 2.7304010115606938e-05, "loss": 1.2391, "step": 1004 }, { "epoch": 0.18, "learning_rate": 2.7301300578034683e-05, "loss": 0.9021, "step": 1005 }, { "epoch": 0.18, "learning_rate": 2.7298591040462427e-05, "loss": 1.4822, "step": 1006 }, { "epoch": 0.18, "learning_rate": 2.7295881502890175e-05, "loss": 1.2301, "step": 1007 }, { "epoch": 0.18, "learning_rate": 2.7293171965317922e-05, "loss": 1.1901, "step": 1008 }, { "epoch": 0.18, "learning_rate": 2.7290462427745663e-05, "loss": 1.3238, "step": 1009 }, { "epoch": 0.18, "learning_rate": 2.728775289017341e-05, "loss": 1.237, "step": 1010 }, { "epoch": 0.18, "learning_rate": 2.7285043352601156e-05, "loss": 0.6872, "step": 1011 }, { "epoch": 0.18, "learning_rate": 2.7282333815028903e-05, "loss": 1.3957, "step": 1012 }, { "epoch": 0.18, "learning_rate": 2.727962427745665e-05, "loss": 1.2964, "step": 1013 }, { "epoch": 0.18, "learning_rate": 2.7276914739884392e-05, "loss": 1.8045, "step": 1014 }, { "epoch": 0.18, "learning_rate": 2.727420520231214e-05, "loss": 0.7651, "step": 1015 }, { "epoch": 0.18, "learning_rate": 2.7271495664739884e-05, "loss": 0.8639, "step": 1016 }, { "epoch": 0.18, "learning_rate": 2.7268786127167632e-05, "loss": 1.3237, "step": 1017 }, { "epoch": 0.18, "learning_rate": 2.7266076589595376e-05, "loss": 0.8747, "step": 1018 }, { "epoch": 0.18, "learning_rate": 2.726336705202312e-05, "loss": 0.8774, "step": 1019 }, { "epoch": 0.18, "learning_rate": 2.726065751445087e-05, "loss": 0.7344, "step": 1020 }, { "epoch": 0.18, "learning_rate": 2.7257947976878613e-05, "loss": 0.8646, "step": 1021 }, { "epoch": 0.18, "learning_rate": 2.725523843930636e-05, "loss": 1.257, "step": 1022 }, { "epoch": 0.18, "learning_rate": 2.7252528901734105e-05, "loss": 0.7544, "step": 1023 }, { "epoch": 0.18, "learning_rate": 2.724981936416185e-05, "loss": 1.7874, "step": 1024 }, { "epoch": 0.19, "learning_rate": 2.7247109826589597e-05, "loss": 0.6331, "step": 1025 }, { "epoch": 0.19, "learning_rate": 2.724440028901734e-05, "loss": 1.0685, "step": 1026 }, { "epoch": 0.19, "learning_rate": 2.724169075144509e-05, "loss": 1.0122, "step": 1027 }, { "epoch": 0.19, "learning_rate": 2.7238981213872834e-05, "loss": 1.6617, "step": 1028 }, { "epoch": 0.19, "learning_rate": 2.7236271676300578e-05, "loss": 1.4971, "step": 1029 }, { "epoch": 0.19, "learning_rate": 2.7233562138728326e-05, "loss": 0.9055, "step": 1030 }, { "epoch": 0.19, "learning_rate": 2.723085260115607e-05, "loss": 1.2115, "step": 1031 }, { "epoch": 0.19, "learning_rate": 2.7228143063583814e-05, "loss": 1.0632, "step": 1032 }, { "epoch": 0.19, "learning_rate": 2.7225433526011562e-05, "loss": 1.624, "step": 1033 }, { "epoch": 0.19, "learning_rate": 2.7222723988439306e-05, "loss": 1.7084, "step": 1034 }, { "epoch": 0.19, "learning_rate": 2.7220014450867054e-05, "loss": 0.7457, "step": 1035 }, { "epoch": 0.19, "learning_rate": 2.72173049132948e-05, "loss": 0.8145, "step": 1036 }, { "epoch": 0.19, "learning_rate": 2.7214595375722543e-05, "loss": 0.6774, "step": 1037 }, { "epoch": 0.19, "learning_rate": 2.721188583815029e-05, "loss": 0.5473, "step": 1038 }, { "epoch": 0.19, "learning_rate": 2.7209176300578035e-05, "loss": 0.8095, "step": 1039 }, { "epoch": 0.19, "learning_rate": 2.7206466763005783e-05, "loss": 1.1625, "step": 1040 }, { "epoch": 0.19, "learning_rate": 2.7203757225433524e-05, "loss": 1.1033, "step": 1041 }, { "epoch": 0.19, "learning_rate": 2.720104768786127e-05, "loss": 1.1684, "step": 1042 }, { "epoch": 0.19, "learning_rate": 2.719833815028902e-05, "loss": 0.6701, "step": 1043 }, { "epoch": 0.19, "learning_rate": 2.7195628612716764e-05, "loss": 0.4339, "step": 1044 }, { "epoch": 0.19, "learning_rate": 2.719291907514451e-05, "loss": 1.1732, "step": 1045 }, { "epoch": 0.19, "learning_rate": 2.7190209537572252e-05, "loss": 0.5982, "step": 1046 }, { "epoch": 0.19, "learning_rate": 2.71875e-05, "loss": 1.2712, "step": 1047 }, { "epoch": 0.19, "learning_rate": 2.7184790462427748e-05, "loss": 0.4404, "step": 1048 }, { "epoch": 0.19, "learning_rate": 2.7182080924855492e-05, "loss": 0.7799, "step": 1049 }, { "epoch": 0.19, "learning_rate": 2.717937138728324e-05, "loss": 0.3648, "step": 1050 }, { "epoch": 0.19, "learning_rate": 2.717666184971098e-05, "loss": 0.9863, "step": 1051 }, { "epoch": 0.19, "learning_rate": 2.717395231213873e-05, "loss": 1.6153, "step": 1052 }, { "epoch": 0.19, "learning_rate": 2.7171242774566477e-05, "loss": 0.7225, "step": 1053 }, { "epoch": 0.19, "learning_rate": 2.716853323699422e-05, "loss": 2.0897, "step": 1054 }, { "epoch": 0.19, "learning_rate": 2.7165823699421965e-05, "loss": 0.8011, "step": 1055 }, { "epoch": 0.19, "learning_rate": 2.716311416184971e-05, "loss": 1.339, "step": 1056 }, { "epoch": 0.19, "learning_rate": 2.7160404624277457e-05, "loss": 1.2824, "step": 1057 }, { "epoch": 0.19, "learning_rate": 2.7157695086705205e-05, "loss": 0.7495, "step": 1058 }, { "epoch": 0.19, "learning_rate": 2.715498554913295e-05, "loss": 1.5843, "step": 1059 }, { "epoch": 0.19, "learning_rate": 2.7152276011560694e-05, "loss": 0.9116, "step": 1060 }, { "epoch": 0.19, "learning_rate": 2.7149566473988438e-05, "loss": 0.7527, "step": 1061 }, { "epoch": 0.19, "learning_rate": 2.7146856936416186e-05, "loss": 0.8393, "step": 1062 }, { "epoch": 0.19, "learning_rate": 2.7144147398843934e-05, "loss": 1.0802, "step": 1063 }, { "epoch": 0.19, "learning_rate": 2.7141437861271675e-05, "loss": 1.0102, "step": 1064 }, { "epoch": 0.19, "learning_rate": 2.7138728323699422e-05, "loss": 0.9359, "step": 1065 }, { "epoch": 0.19, "learning_rate": 2.7136018786127167e-05, "loss": 0.6967, "step": 1066 }, { "epoch": 0.19, "learning_rate": 2.7133309248554915e-05, "loss": 0.7792, "step": 1067 }, { "epoch": 0.19, "learning_rate": 2.7130599710982662e-05, "loss": 0.8438, "step": 1068 }, { "epoch": 0.19, "learning_rate": 2.7127890173410403e-05, "loss": 1.1055, "step": 1069 }, { "epoch": 0.19, "learning_rate": 2.712518063583815e-05, "loss": 0.7737, "step": 1070 }, { "epoch": 0.19, "learning_rate": 2.7122471098265895e-05, "loss": 1.1372, "step": 1071 }, { "epoch": 0.19, "learning_rate": 2.7119761560693643e-05, "loss": 0.6037, "step": 1072 }, { "epoch": 0.19, "learning_rate": 2.7117052023121388e-05, "loss": 0.717, "step": 1073 }, { "epoch": 0.19, "learning_rate": 2.7114342485549132e-05, "loss": 0.497, "step": 1074 }, { "epoch": 0.19, "learning_rate": 2.711163294797688e-05, "loss": 1.3696, "step": 1075 }, { "epoch": 0.19, "learning_rate": 2.7108923410404624e-05, "loss": 0.5952, "step": 1076 }, { "epoch": 0.19, "learning_rate": 2.7106213872832372e-05, "loss": 1.3445, "step": 1077 }, { "epoch": 0.19, "learning_rate": 2.7103504335260116e-05, "loss": 0.4471, "step": 1078 }, { "epoch": 0.19, "learning_rate": 2.710079479768786e-05, "loss": 0.9116, "step": 1079 }, { "epoch": 0.2, "learning_rate": 2.7098085260115608e-05, "loss": 1.2229, "step": 1080 }, { "epoch": 0.2, "learning_rate": 2.7095375722543353e-05, "loss": 0.746, "step": 1081 }, { "epoch": 0.2, "learning_rate": 2.70926661849711e-05, "loss": 0.7186, "step": 1082 }, { "epoch": 0.2, "learning_rate": 2.7089956647398845e-05, "loss": 0.9119, "step": 1083 }, { "epoch": 0.2, "learning_rate": 2.708724710982659e-05, "loss": 0.5659, "step": 1084 }, { "epoch": 0.2, "learning_rate": 2.7084537572254337e-05, "loss": 1.4232, "step": 1085 }, { "epoch": 0.2, "learning_rate": 2.708182803468208e-05, "loss": 1.1085, "step": 1086 }, { "epoch": 0.2, "learning_rate": 2.7079118497109826e-05, "loss": 0.8229, "step": 1087 }, { "epoch": 0.2, "learning_rate": 2.7076408959537573e-05, "loss": 1.551, "step": 1088 }, { "epoch": 0.2, "learning_rate": 2.7073699421965318e-05, "loss": 1.2515, "step": 1089 }, { "epoch": 0.2, "learning_rate": 2.7070989884393065e-05, "loss": 1.5315, "step": 1090 }, { "epoch": 0.2, "learning_rate": 2.706828034682081e-05, "loss": 0.8115, "step": 1091 }, { "epoch": 0.2, "learning_rate": 2.7065570809248554e-05, "loss": 0.9974, "step": 1092 }, { "epoch": 0.2, "learning_rate": 2.7062861271676302e-05, "loss": 0.8943, "step": 1093 }, { "epoch": 0.2, "learning_rate": 2.7060151734104046e-05, "loss": 0.9966, "step": 1094 }, { "epoch": 0.2, "learning_rate": 2.7057442196531794e-05, "loss": 1.189, "step": 1095 }, { "epoch": 0.2, "learning_rate": 2.705473265895954e-05, "loss": 1.9612, "step": 1096 }, { "epoch": 0.2, "learning_rate": 2.7052023121387283e-05, "loss": 1.5424, "step": 1097 }, { "epoch": 0.2, "learning_rate": 2.704931358381503e-05, "loss": 0.963, "step": 1098 }, { "epoch": 0.2, "learning_rate": 2.7046604046242775e-05, "loss": 1.0821, "step": 1099 }, { "epoch": 0.2, "learning_rate": 2.7043894508670523e-05, "loss": 1.5107, "step": 1100 }, { "epoch": 0.2, "learning_rate": 2.7041184971098264e-05, "loss": 1.172, "step": 1101 }, { "epoch": 0.2, "learning_rate": 2.703847543352601e-05, "loss": 1.142, "step": 1102 }, { "epoch": 0.2, "learning_rate": 2.703576589595376e-05, "loss": 0.8442, "step": 1103 }, { "epoch": 0.2, "learning_rate": 2.7033056358381504e-05, "loss": 0.9876, "step": 1104 }, { "epoch": 0.2, "learning_rate": 2.703034682080925e-05, "loss": 1.0599, "step": 1105 }, { "epoch": 0.2, "learning_rate": 2.7027637283236992e-05, "loss": 0.4758, "step": 1106 }, { "epoch": 0.2, "learning_rate": 2.702492774566474e-05, "loss": 1.2898, "step": 1107 }, { "epoch": 0.2, "learning_rate": 2.7022218208092488e-05, "loss": 0.6462, "step": 1108 }, { "epoch": 0.2, "learning_rate": 2.7019508670520232e-05, "loss": 0.8419, "step": 1109 }, { "epoch": 0.2, "learning_rate": 2.7016799132947976e-05, "loss": 0.7829, "step": 1110 }, { "epoch": 0.2, "learning_rate": 2.701408959537572e-05, "loss": 1.0832, "step": 1111 }, { "epoch": 0.2, "learning_rate": 2.701138005780347e-05, "loss": 0.971, "step": 1112 }, { "epoch": 0.2, "learning_rate": 2.7008670520231216e-05, "loss": 0.9336, "step": 1113 }, { "epoch": 0.2, "learning_rate": 2.700596098265896e-05, "loss": 1.0812, "step": 1114 }, { "epoch": 0.2, "learning_rate": 2.7003251445086705e-05, "loss": 0.8433, "step": 1115 }, { "epoch": 0.2, "learning_rate": 2.700054190751445e-05, "loss": 0.8826, "step": 1116 }, { "epoch": 0.2, "learning_rate": 2.6997832369942197e-05, "loss": 1.5459, "step": 1117 }, { "epoch": 0.2, "learning_rate": 2.6995122832369945e-05, "loss": 0.8715, "step": 1118 }, { "epoch": 0.2, "learning_rate": 2.6992413294797686e-05, "loss": 0.5444, "step": 1119 }, { "epoch": 0.2, "learning_rate": 2.6989703757225434e-05, "loss": 0.9588, "step": 1120 }, { "epoch": 0.2, "learning_rate": 2.6986994219653178e-05, "loss": 1.006, "step": 1121 }, { "epoch": 0.2, "learning_rate": 2.6984284682080926e-05, "loss": 1.378, "step": 1122 }, { "epoch": 0.2, "learning_rate": 2.6981575144508674e-05, "loss": 0.828, "step": 1123 }, { "epoch": 0.2, "learning_rate": 2.6978865606936415e-05, "loss": 1.5789, "step": 1124 }, { "epoch": 0.2, "learning_rate": 2.6976156069364162e-05, "loss": 1.045, "step": 1125 }, { "epoch": 0.2, "learning_rate": 2.6973446531791907e-05, "loss": 1.0519, "step": 1126 }, { "epoch": 0.2, "learning_rate": 2.6970736994219654e-05, "loss": 0.707, "step": 1127 }, { "epoch": 0.2, "learning_rate": 2.6968027456647402e-05, "loss": 0.8252, "step": 1128 }, { "epoch": 0.2, "learning_rate": 2.6965317919075143e-05, "loss": 0.9567, "step": 1129 }, { "epoch": 0.2, "learning_rate": 2.696260838150289e-05, "loss": 0.6954, "step": 1130 }, { "epoch": 0.2, "learning_rate": 2.6959898843930635e-05, "loss": 0.6698, "step": 1131 }, { "epoch": 0.2, "learning_rate": 2.6957189306358383e-05, "loss": 0.6616, "step": 1132 }, { "epoch": 0.2, "learning_rate": 2.6954479768786127e-05, "loss": 0.6018, "step": 1133 }, { "epoch": 0.2, "learning_rate": 2.6951770231213872e-05, "loss": 1.1157, "step": 1134 }, { "epoch": 0.21, "learning_rate": 2.694906069364162e-05, "loss": 1.0575, "step": 1135 }, { "epoch": 0.21, "learning_rate": 2.6946351156069367e-05, "loss": 1.2215, "step": 1136 }, { "epoch": 0.21, "learning_rate": 2.694364161849711e-05, "loss": 1.6457, "step": 1137 }, { "epoch": 0.21, "learning_rate": 2.6940932080924856e-05, "loss": 0.6107, "step": 1138 }, { "epoch": 0.21, "learning_rate": 2.69382225433526e-05, "loss": 0.7521, "step": 1139 }, { "epoch": 0.21, "learning_rate": 2.6935513005780348e-05, "loss": 0.986, "step": 1140 }, { "epoch": 0.21, "learning_rate": 2.6932803468208096e-05, "loss": 1.0247, "step": 1141 }, { "epoch": 0.21, "learning_rate": 2.6930093930635837e-05, "loss": 0.7389, "step": 1142 }, { "epoch": 0.21, "learning_rate": 2.6927384393063585e-05, "loss": 0.675, "step": 1143 }, { "epoch": 0.21, "learning_rate": 2.692467485549133e-05, "loss": 0.6293, "step": 1144 }, { "epoch": 0.21, "learning_rate": 2.6921965317919077e-05, "loss": 0.7512, "step": 1145 }, { "epoch": 0.21, "learning_rate": 2.6919255780346824e-05, "loss": 0.6611, "step": 1146 }, { "epoch": 0.21, "learning_rate": 2.6916546242774565e-05, "loss": 0.4679, "step": 1147 }, { "epoch": 0.21, "learning_rate": 2.6913836705202313e-05, "loss": 1.0634, "step": 1148 }, { "epoch": 0.21, "learning_rate": 2.6911127167630058e-05, "loss": 0.6244, "step": 1149 }, { "epoch": 0.21, "learning_rate": 2.6908417630057805e-05, "loss": 1.2666, "step": 1150 }, { "epoch": 0.21, "learning_rate": 2.6905708092485553e-05, "loss": 1.5806, "step": 1151 }, { "epoch": 0.21, "learning_rate": 2.6902998554913294e-05, "loss": 0.7, "step": 1152 }, { "epoch": 0.21, "learning_rate": 2.6900289017341042e-05, "loss": 0.962, "step": 1153 }, { "epoch": 0.21, "learning_rate": 2.6897579479768786e-05, "loss": 0.7093, "step": 1154 }, { "epoch": 0.21, "learning_rate": 2.6894869942196534e-05, "loss": 0.775, "step": 1155 }, { "epoch": 0.21, "learning_rate": 2.6892160404624278e-05, "loss": 0.8472, "step": 1156 }, { "epoch": 0.21, "learning_rate": 2.6889450867052023e-05, "loss": 0.833, "step": 1157 }, { "epoch": 0.21, "learning_rate": 2.688674132947977e-05, "loss": 0.8718, "step": 1158 }, { "epoch": 0.21, "learning_rate": 2.6884031791907515e-05, "loss": 0.6528, "step": 1159 }, { "epoch": 0.21, "learning_rate": 2.6881322254335262e-05, "loss": 1.8493, "step": 1160 }, { "epoch": 0.21, "learning_rate": 2.6878612716763007e-05, "loss": 0.9411, "step": 1161 }, { "epoch": 0.21, "learning_rate": 2.687590317919075e-05, "loss": 0.9501, "step": 1162 }, { "epoch": 0.21, "learning_rate": 2.68731936416185e-05, "loss": 1.2891, "step": 1163 }, { "epoch": 0.21, "learning_rate": 2.6870484104046243e-05, "loss": 1.2988, "step": 1164 }, { "epoch": 0.21, "learning_rate": 2.6867774566473988e-05, "loss": 1.3373, "step": 1165 }, { "epoch": 0.21, "learning_rate": 2.6865065028901735e-05, "loss": 1.2573, "step": 1166 }, { "epoch": 0.21, "learning_rate": 2.686235549132948e-05, "loss": 0.7833, "step": 1167 }, { "epoch": 0.21, "learning_rate": 2.6859645953757228e-05, "loss": 0.8511, "step": 1168 }, { "epoch": 0.21, "learning_rate": 2.6856936416184972e-05, "loss": 0.8306, "step": 1169 }, { "epoch": 0.21, "learning_rate": 2.6854226878612716e-05, "loss": 0.6562, "step": 1170 }, { "epoch": 0.21, "learning_rate": 2.6851517341040464e-05, "loss": 1.3816, "step": 1171 }, { "epoch": 0.21, "learning_rate": 2.684880780346821e-05, "loss": 0.753, "step": 1172 }, { "epoch": 0.21, "learning_rate": 2.6846098265895956e-05, "loss": 0.5603, "step": 1173 }, { "epoch": 0.21, "learning_rate": 2.68433887283237e-05, "loss": 0.8922, "step": 1174 }, { "epoch": 0.21, "learning_rate": 2.6840679190751445e-05, "loss": 0.3406, "step": 1175 }, { "epoch": 0.21, "learning_rate": 2.6837969653179193e-05, "loss": 1.1338, "step": 1176 }, { "epoch": 0.21, "learning_rate": 2.6835260115606937e-05, "loss": 0.7302, "step": 1177 }, { "epoch": 0.21, "learning_rate": 2.6832550578034685e-05, "loss": 0.8155, "step": 1178 }, { "epoch": 0.21, "learning_rate": 2.6829841040462426e-05, "loss": 1.1487, "step": 1179 }, { "epoch": 0.21, "learning_rate": 2.6827131502890174e-05, "loss": 0.586, "step": 1180 }, { "epoch": 0.21, "learning_rate": 2.682442196531792e-05, "loss": 0.4378, "step": 1181 }, { "epoch": 0.21, "learning_rate": 2.6821712427745666e-05, "loss": 0.9424, "step": 1182 }, { "epoch": 0.21, "learning_rate": 2.6819002890173413e-05, "loss": 1.1997, "step": 1183 }, { "epoch": 0.21, "learning_rate": 2.6816293352601154e-05, "loss": 1.0158, "step": 1184 }, { "epoch": 0.21, "learning_rate": 2.6813583815028902e-05, "loss": 2.1056, "step": 1185 }, { "epoch": 0.21, "learning_rate": 2.681087427745665e-05, "loss": 1.0592, "step": 1186 }, { "epoch": 0.21, "learning_rate": 2.6808164739884394e-05, "loss": 1.2213, "step": 1187 }, { "epoch": 0.21, "learning_rate": 2.680545520231214e-05, "loss": 0.6901, "step": 1188 }, { "epoch": 0.21, "learning_rate": 2.6802745664739883e-05, "loss": 0.9758, "step": 1189 }, { "epoch": 0.21, "learning_rate": 2.680003612716763e-05, "loss": 0.7693, "step": 1190 }, { "epoch": 0.22, "learning_rate": 2.679732658959538e-05, "loss": 0.8249, "step": 1191 }, { "epoch": 0.22, "learning_rate": 2.6794617052023123e-05, "loss": 1.1914, "step": 1192 }, { "epoch": 0.22, "learning_rate": 2.6791907514450867e-05, "loss": 1.4644, "step": 1193 }, { "epoch": 0.22, "learning_rate": 2.678919797687861e-05, "loss": 1.2628, "step": 1194 }, { "epoch": 0.22, "learning_rate": 2.678648843930636e-05, "loss": 0.3873, "step": 1195 }, { "epoch": 0.22, "learning_rate": 2.6783778901734107e-05, "loss": 0.9276, "step": 1196 }, { "epoch": 0.22, "learning_rate": 2.678106936416185e-05, "loss": 0.7635, "step": 1197 }, { "epoch": 0.22, "learning_rate": 2.6778359826589596e-05, "loss": 0.9765, "step": 1198 }, { "epoch": 0.22, "learning_rate": 2.677565028901734e-05, "loss": 0.8229, "step": 1199 }, { "epoch": 0.22, "learning_rate": 2.6772940751445088e-05, "loss": 1.0628, "step": 1200 }, { "epoch": 0.22, "learning_rate": 2.6770231213872836e-05, "loss": 1.0733, "step": 1201 }, { "epoch": 0.22, "learning_rate": 2.6767521676300577e-05, "loss": 0.7727, "step": 1202 }, { "epoch": 0.22, "learning_rate": 2.6764812138728324e-05, "loss": 0.6638, "step": 1203 }, { "epoch": 0.22, "learning_rate": 2.676210260115607e-05, "loss": 0.7615, "step": 1204 }, { "epoch": 0.22, "learning_rate": 2.6759393063583817e-05, "loss": 0.8312, "step": 1205 }, { "epoch": 0.22, "learning_rate": 2.6756683526011564e-05, "loss": 1.4289, "step": 1206 }, { "epoch": 0.22, "learning_rate": 2.6753973988439305e-05, "loss": 0.8262, "step": 1207 }, { "epoch": 0.22, "learning_rate": 2.6751264450867053e-05, "loss": 0.9705, "step": 1208 }, { "epoch": 0.22, "learning_rate": 2.6748554913294797e-05, "loss": 0.9771, "step": 1209 }, { "epoch": 0.22, "learning_rate": 2.6745845375722545e-05, "loss": 1.5916, "step": 1210 }, { "epoch": 0.22, "learning_rate": 2.674313583815029e-05, "loss": 0.6808, "step": 1211 }, { "epoch": 0.22, "learning_rate": 2.6740426300578034e-05, "loss": 1.1654, "step": 1212 }, { "epoch": 0.22, "learning_rate": 2.673771676300578e-05, "loss": 1.0642, "step": 1213 }, { "epoch": 0.22, "learning_rate": 2.6735007225433526e-05, "loss": 1.9257, "step": 1214 }, { "epoch": 0.22, "learning_rate": 2.6732297687861274e-05, "loss": 0.7654, "step": 1215 }, { "epoch": 0.22, "learning_rate": 2.6729588150289018e-05, "loss": 1.1881, "step": 1216 }, { "epoch": 0.22, "learning_rate": 2.6726878612716762e-05, "loss": 0.6488, "step": 1217 }, { "epoch": 0.22, "learning_rate": 2.672416907514451e-05, "loss": 0.8516, "step": 1218 }, { "epoch": 0.22, "learning_rate": 2.6721459537572255e-05, "loss": 1.0994, "step": 1219 }, { "epoch": 0.22, "learning_rate": 2.6718750000000002e-05, "loss": 0.6765, "step": 1220 }, { "epoch": 0.22, "learning_rate": 2.6716040462427747e-05, "loss": 1.0965, "step": 1221 }, { "epoch": 0.22, "learning_rate": 2.671333092485549e-05, "loss": 0.7484, "step": 1222 }, { "epoch": 0.22, "learning_rate": 2.671062138728324e-05, "loss": 0.3908, "step": 1223 }, { "epoch": 0.22, "learning_rate": 2.6707911849710983e-05, "loss": 0.2956, "step": 1224 }, { "epoch": 0.22, "learning_rate": 2.6705202312138728e-05, "loss": 0.7114, "step": 1225 }, { "epoch": 0.22, "learning_rate": 2.6702492774566475e-05, "loss": 0.8971, "step": 1226 }, { "epoch": 0.22, "learning_rate": 2.669978323699422e-05, "loss": 1.3958, "step": 1227 }, { "epoch": 0.22, "learning_rate": 2.6697073699421967e-05, "loss": 1.5596, "step": 1228 }, { "epoch": 0.22, "learning_rate": 2.6694364161849712e-05, "loss": 0.9563, "step": 1229 }, { "epoch": 0.22, "learning_rate": 2.6691654624277456e-05, "loss": 1.3855, "step": 1230 }, { "epoch": 0.22, "learning_rate": 2.6688945086705204e-05, "loss": 0.7033, "step": 1231 }, { "epoch": 0.22, "learning_rate": 2.6686235549132948e-05, "loss": 1.1944, "step": 1232 }, { "epoch": 0.22, "learning_rate": 2.6683526011560696e-05, "loss": 0.7125, "step": 1233 }, { "epoch": 0.22, "learning_rate": 2.6680816473988437e-05, "loss": 1.4732, "step": 1234 }, { "epoch": 0.22, "learning_rate": 2.6678106936416185e-05, "loss": 1.3327, "step": 1235 }, { "epoch": 0.22, "learning_rate": 2.6675397398843932e-05, "loss": 1.3204, "step": 1236 }, { "epoch": 0.22, "learning_rate": 2.6672687861271677e-05, "loss": 0.8787, "step": 1237 }, { "epoch": 0.22, "learning_rate": 2.6669978323699425e-05, "loss": 0.9403, "step": 1238 }, { "epoch": 0.22, "learning_rate": 2.6667268786127166e-05, "loss": 0.6545, "step": 1239 }, { "epoch": 0.22, "learning_rate": 2.6664559248554913e-05, "loss": 1.1682, "step": 1240 }, { "epoch": 0.22, "learning_rate": 2.666184971098266e-05, "loss": 0.9842, "step": 1241 }, { "epoch": 0.22, "learning_rate": 2.6659140173410405e-05, "loss": 1.0057, "step": 1242 }, { "epoch": 0.22, "learning_rate": 2.6656430635838153e-05, "loss": 1.3208, "step": 1243 }, { "epoch": 0.22, "learning_rate": 2.6653721098265894e-05, "loss": 0.9822, "step": 1244 }, { "epoch": 0.22, "learning_rate": 2.6651011560693642e-05, "loss": 0.7545, "step": 1245 }, { "epoch": 0.23, "learning_rate": 2.664830202312139e-05, "loss": 0.8387, "step": 1246 }, { "epoch": 0.23, "learning_rate": 2.6645592485549134e-05, "loss": 0.6109, "step": 1247 }, { "epoch": 0.23, "learning_rate": 2.664288294797688e-05, "loss": 0.9099, "step": 1248 }, { "epoch": 0.23, "learning_rate": 2.6640173410404623e-05, "loss": 1.7031, "step": 1249 }, { "epoch": 0.23, "learning_rate": 2.663746387283237e-05, "loss": 0.5355, "step": 1250 }, { "epoch": 0.23, "learning_rate": 2.6634754335260118e-05, "loss": 0.7195, "step": 1251 }, { "epoch": 0.23, "learning_rate": 2.6632044797687863e-05, "loss": 0.9015, "step": 1252 }, { "epoch": 0.23, "learning_rate": 2.6629335260115607e-05, "loss": 0.9365, "step": 1253 }, { "epoch": 0.23, "learning_rate": 2.662662572254335e-05, "loss": 0.6945, "step": 1254 }, { "epoch": 0.23, "learning_rate": 2.66239161849711e-05, "loss": 1.4557, "step": 1255 }, { "epoch": 0.23, "learning_rate": 2.6621206647398847e-05, "loss": 0.5301, "step": 1256 }, { "epoch": 0.23, "learning_rate": 2.6618497109826588e-05, "loss": 0.5143, "step": 1257 }, { "epoch": 0.23, "learning_rate": 2.6615787572254336e-05, "loss": 0.5665, "step": 1258 }, { "epoch": 0.23, "learning_rate": 2.661307803468208e-05, "loss": 0.51, "step": 1259 }, { "epoch": 0.23, "learning_rate": 2.6610368497109828e-05, "loss": 0.4235, "step": 1260 }, { "epoch": 0.23, "learning_rate": 2.6607658959537575e-05, "loss": 1.4211, "step": 1261 }, { "epoch": 0.23, "learning_rate": 2.6604949421965316e-05, "loss": 0.6286, "step": 1262 }, { "epoch": 0.23, "learning_rate": 2.6602239884393064e-05, "loss": 1.4407, "step": 1263 }, { "epoch": 0.23, "learning_rate": 2.659953034682081e-05, "loss": 0.622, "step": 1264 }, { "epoch": 0.23, "learning_rate": 2.6596820809248556e-05, "loss": 1.2582, "step": 1265 }, { "epoch": 0.23, "learning_rate": 2.6594111271676304e-05, "loss": 1.2798, "step": 1266 }, { "epoch": 0.23, "learning_rate": 2.6591401734104045e-05, "loss": 1.284, "step": 1267 }, { "epoch": 0.23, "learning_rate": 2.6588692196531793e-05, "loss": 1.2132, "step": 1268 }, { "epoch": 0.23, "learning_rate": 2.6585982658959537e-05, "loss": 1.006, "step": 1269 }, { "epoch": 0.23, "learning_rate": 2.6583273121387285e-05, "loss": 1.0743, "step": 1270 }, { "epoch": 0.23, "learning_rate": 2.658056358381503e-05, "loss": 0.7779, "step": 1271 }, { "epoch": 0.23, "learning_rate": 2.6577854046242774e-05, "loss": 1.7024, "step": 1272 }, { "epoch": 0.23, "learning_rate": 2.657514450867052e-05, "loss": 0.4912, "step": 1273 }, { "epoch": 0.23, "learning_rate": 2.6572434971098266e-05, "loss": 0.8276, "step": 1274 }, { "epoch": 0.23, "learning_rate": 2.6569725433526014e-05, "loss": 1.0763, "step": 1275 }, { "epoch": 0.23, "learning_rate": 2.6567015895953758e-05, "loss": 1.2453, "step": 1276 }, { "epoch": 0.23, "learning_rate": 2.6564306358381502e-05, "loss": 0.5205, "step": 1277 }, { "epoch": 0.23, "learning_rate": 2.656159682080925e-05, "loss": 1.1193, "step": 1278 }, { "epoch": 0.23, "learning_rate": 2.6558887283236994e-05, "loss": 1.3914, "step": 1279 }, { "epoch": 0.23, "learning_rate": 2.655617774566474e-05, "loss": 1.9408, "step": 1280 }, { "epoch": 0.23, "learning_rate": 2.6553468208092487e-05, "loss": 0.683, "step": 1281 }, { "epoch": 0.23, "learning_rate": 2.655075867052023e-05, "loss": 0.7231, "step": 1282 }, { "epoch": 0.23, "learning_rate": 2.654804913294798e-05, "loss": 0.5978, "step": 1283 }, { "epoch": 0.23, "learning_rate": 2.6545339595375723e-05, "loss": 0.8613, "step": 1284 }, { "epoch": 0.23, "learning_rate": 2.6542630057803467e-05, "loss": 0.9938, "step": 1285 }, { "epoch": 0.23, "learning_rate": 2.6539920520231215e-05, "loss": 0.7461, "step": 1286 }, { "epoch": 0.23, "learning_rate": 2.653721098265896e-05, "loss": 0.7354, "step": 1287 }, { "epoch": 0.23, "learning_rate": 2.6534501445086707e-05, "loss": 0.9111, "step": 1288 }, { "epoch": 0.23, "learning_rate": 2.653179190751445e-05, "loss": 0.8914, "step": 1289 }, { "epoch": 0.23, "learning_rate": 2.6529082369942196e-05, "loss": 0.5252, "step": 1290 }, { "epoch": 0.23, "learning_rate": 2.6526372832369944e-05, "loss": 1.2253, "step": 1291 }, { "epoch": 0.23, "learning_rate": 2.6523663294797688e-05, "loss": 0.9362, "step": 1292 }, { "epoch": 0.23, "learning_rate": 2.6520953757225436e-05, "loss": 0.6827, "step": 1293 }, { "epoch": 0.23, "learning_rate": 2.6518244219653177e-05, "loss": 0.8196, "step": 1294 }, { "epoch": 0.23, "learning_rate": 2.6515534682080925e-05, "loss": 0.7863, "step": 1295 }, { "epoch": 0.23, "learning_rate": 2.6512825144508672e-05, "loss": 1.2426, "step": 1296 }, { "epoch": 0.23, "learning_rate": 2.6510115606936417e-05, "loss": 1.0204, "step": 1297 }, { "epoch": 0.23, "learning_rate": 2.6507406069364164e-05, "loss": 0.5357, "step": 1298 }, { "epoch": 0.23, "learning_rate": 2.6504696531791905e-05, "loss": 1.0654, "step": 1299 }, { "epoch": 0.23, "learning_rate": 2.6501986994219653e-05, "loss": 0.6551, "step": 1300 }, { "epoch": 0.24, "learning_rate": 2.64992774566474e-05, "loss": 1.2112, "step": 1301 }, { "epoch": 0.24, "learning_rate": 2.6496567919075145e-05, "loss": 0.9445, "step": 1302 }, { "epoch": 0.24, "learning_rate": 2.649385838150289e-05, "loss": 1.1587, "step": 1303 }, { "epoch": 0.24, "learning_rate": 2.6491148843930634e-05, "loss": 0.5917, "step": 1304 }, { "epoch": 0.24, "learning_rate": 2.6488439306358382e-05, "loss": 0.7932, "step": 1305 }, { "epoch": 0.24, "learning_rate": 2.648572976878613e-05, "loss": 0.6368, "step": 1306 }, { "epoch": 0.24, "learning_rate": 2.6483020231213874e-05, "loss": 0.6153, "step": 1307 }, { "epoch": 0.24, "learning_rate": 2.6480310693641618e-05, "loss": 1.696, "step": 1308 }, { "epoch": 0.24, "learning_rate": 2.6477601156069366e-05, "loss": 0.8892, "step": 1309 }, { "epoch": 0.24, "learning_rate": 2.647489161849711e-05, "loss": 1.0183, "step": 1310 }, { "epoch": 0.24, "learning_rate": 2.6472182080924858e-05, "loss": 1.0198, "step": 1311 }, { "epoch": 0.24, "learning_rate": 2.6469472543352602e-05, "loss": 1.6817, "step": 1312 }, { "epoch": 0.24, "learning_rate": 2.6466763005780347e-05, "loss": 1.1915, "step": 1313 }, { "epoch": 0.24, "learning_rate": 2.6464053468208095e-05, "loss": 1.0358, "step": 1314 }, { "epoch": 0.24, "learning_rate": 2.646134393063584e-05, "loss": 1.2326, "step": 1315 }, { "epoch": 0.24, "learning_rate": 2.6458634393063587e-05, "loss": 0.8147, "step": 1316 }, { "epoch": 0.24, "learning_rate": 2.6455924855491328e-05, "loss": 0.7627, "step": 1317 }, { "epoch": 0.24, "learning_rate": 2.6453215317919075e-05, "loss": 0.5513, "step": 1318 }, { "epoch": 0.24, "learning_rate": 2.6450505780346823e-05, "loss": 0.6314, "step": 1319 }, { "epoch": 0.24, "learning_rate": 2.6447796242774568e-05, "loss": 1.3421, "step": 1320 }, { "epoch": 0.24, "learning_rate": 2.6445086705202315e-05, "loss": 0.9358, "step": 1321 }, { "epoch": 0.24, "learning_rate": 2.6442377167630056e-05, "loss": 0.9391, "step": 1322 }, { "epoch": 0.24, "learning_rate": 2.6439667630057804e-05, "loss": 0.3876, "step": 1323 }, { "epoch": 0.24, "learning_rate": 2.6436958092485552e-05, "loss": 0.5452, "step": 1324 }, { "epoch": 0.24, "learning_rate": 2.6434248554913296e-05, "loss": 0.7376, "step": 1325 }, { "epoch": 0.24, "learning_rate": 2.643153901734104e-05, "loss": 0.9234, "step": 1326 }, { "epoch": 0.24, "learning_rate": 2.6428829479768785e-05, "loss": 0.7701, "step": 1327 }, { "epoch": 0.24, "learning_rate": 2.6426119942196533e-05, "loss": 2.1077, "step": 1328 }, { "epoch": 0.24, "learning_rate": 2.642341040462428e-05, "loss": 0.5509, "step": 1329 }, { "epoch": 0.24, "learning_rate": 2.6420700867052025e-05, "loss": 1.0306, "step": 1330 }, { "epoch": 0.24, "learning_rate": 2.641799132947977e-05, "loss": 1.2233, "step": 1331 }, { "epoch": 0.24, "learning_rate": 2.6415281791907514e-05, "loss": 1.0975, "step": 1332 }, { "epoch": 0.24, "learning_rate": 2.641257225433526e-05, "loss": 1.1868, "step": 1333 }, { "epoch": 0.24, "learning_rate": 2.640986271676301e-05, "loss": 0.9341, "step": 1334 }, { "epoch": 0.24, "learning_rate": 2.640715317919075e-05, "loss": 1.1808, "step": 1335 }, { "epoch": 0.24, "learning_rate": 2.6404443641618498e-05, "loss": 0.5941, "step": 1336 }, { "epoch": 0.24, "learning_rate": 2.6401734104046242e-05, "loss": 1.1739, "step": 1337 }, { "epoch": 0.24, "learning_rate": 2.639902456647399e-05, "loss": 0.9894, "step": 1338 }, { "epoch": 0.24, "learning_rate": 2.6396315028901738e-05, "loss": 1.4494, "step": 1339 }, { "epoch": 0.24, "learning_rate": 2.639360549132948e-05, "loss": 0.9762, "step": 1340 }, { "epoch": 0.24, "learning_rate": 2.6390895953757226e-05, "loss": 0.5174, "step": 1341 }, { "epoch": 0.24, "learning_rate": 2.638818641618497e-05, "loss": 1.4539, "step": 1342 }, { "epoch": 0.24, "learning_rate": 2.638547687861272e-05, "loss": 0.4314, "step": 1343 }, { "epoch": 0.24, "learning_rate": 2.6382767341040466e-05, "loss": 1.1492, "step": 1344 }, { "epoch": 0.24, "learning_rate": 2.6380057803468207e-05, "loss": 0.8672, "step": 1345 }, { "epoch": 0.24, "learning_rate": 2.6377348265895955e-05, "loss": 1.1623, "step": 1346 }, { "epoch": 0.24, "learning_rate": 2.63746387283237e-05, "loss": 1.2147, "step": 1347 }, { "epoch": 0.24, "learning_rate": 2.6371929190751447e-05, "loss": 1.1942, "step": 1348 }, { "epoch": 0.24, "learning_rate": 2.636921965317919e-05, "loss": 1.6288, "step": 1349 }, { "epoch": 0.24, "learning_rate": 2.6366510115606936e-05, "loss": 1.0414, "step": 1350 }, { "epoch": 0.24, "learning_rate": 2.6363800578034684e-05, "loss": 1.6644, "step": 1351 }, { "epoch": 0.24, "learning_rate": 2.6361091040462428e-05, "loss": 0.8228, "step": 1352 }, { "epoch": 0.24, "learning_rate": 2.6358381502890176e-05, "loss": 0.6925, "step": 1353 }, { "epoch": 0.24, "learning_rate": 2.635567196531792e-05, "loss": 1.0552, "step": 1354 }, { "epoch": 0.24, "learning_rate": 2.6352962427745664e-05, "loss": 1.1203, "step": 1355 }, { "epoch": 0.24, "learning_rate": 2.6350252890173412e-05, "loss": 0.4864, "step": 1356 }, { "epoch": 0.25, "learning_rate": 2.6347543352601157e-05, "loss": 0.86, "step": 1357 }, { "epoch": 0.25, "learning_rate": 2.63448338150289e-05, "loss": 0.549, "step": 1358 }, { "epoch": 0.25, "learning_rate": 2.634212427745665e-05, "loss": 1.5003, "step": 1359 }, { "epoch": 0.25, "learning_rate": 2.6339414739884393e-05, "loss": 1.4069, "step": 1360 }, { "epoch": 0.25, "learning_rate": 2.633670520231214e-05, "loss": 1.4997, "step": 1361 }, { "epoch": 0.25, "learning_rate": 2.6333995664739885e-05, "loss": 3.3634, "step": 1362 }, { "epoch": 0.25, "learning_rate": 2.633128612716763e-05, "loss": 0.9573, "step": 1363 }, { "epoch": 0.25, "learning_rate": 2.6328576589595377e-05, "loss": 1.0309, "step": 1364 }, { "epoch": 0.25, "learning_rate": 2.632586705202312e-05, "loss": 1.1407, "step": 1365 }, { "epoch": 0.25, "learning_rate": 2.632315751445087e-05, "loss": 0.6027, "step": 1366 }, { "epoch": 0.25, "learning_rate": 2.6320447976878614e-05, "loss": 1.1946, "step": 1367 }, { "epoch": 0.25, "learning_rate": 2.6317738439306358e-05, "loss": 0.7671, "step": 1368 }, { "epoch": 0.25, "learning_rate": 2.6315028901734106e-05, "loss": 1.1571, "step": 1369 }, { "epoch": 0.25, "learning_rate": 2.631231936416185e-05, "loss": 0.427, "step": 1370 }, { "epoch": 0.25, "learning_rate": 2.6309609826589598e-05, "loss": 0.9422, "step": 1371 }, { "epoch": 0.25, "learning_rate": 2.630690028901734e-05, "loss": 0.8094, "step": 1372 }, { "epoch": 0.25, "learning_rate": 2.6304190751445087e-05, "loss": 1.1791, "step": 1373 }, { "epoch": 0.25, "learning_rate": 2.6301481213872834e-05, "loss": 0.8637, "step": 1374 }, { "epoch": 0.25, "learning_rate": 2.629877167630058e-05, "loss": 0.9712, "step": 1375 }, { "epoch": 0.25, "learning_rate": 2.6296062138728327e-05, "loss": 0.6964, "step": 1376 }, { "epoch": 0.25, "learning_rate": 2.6293352601156068e-05, "loss": 1.0747, "step": 1377 }, { "epoch": 0.25, "learning_rate": 2.6290643063583815e-05, "loss": 1.0852, "step": 1378 }, { "epoch": 0.25, "learning_rate": 2.6287933526011563e-05, "loss": 1.6542, "step": 1379 }, { "epoch": 0.25, "learning_rate": 2.6285223988439307e-05, "loss": 1.2979, "step": 1380 }, { "epoch": 0.25, "learning_rate": 2.6282514450867052e-05, "loss": 1.1139, "step": 1381 }, { "epoch": 0.25, "learning_rate": 2.6279804913294796e-05, "loss": 1.2625, "step": 1382 }, { "epoch": 0.25, "learning_rate": 2.6277095375722544e-05, "loss": 2.0187, "step": 1383 }, { "epoch": 0.25, "learning_rate": 2.627438583815029e-05, "loss": 0.9115, "step": 1384 }, { "epoch": 0.25, "learning_rate": 2.6271676300578036e-05, "loss": 0.8651, "step": 1385 }, { "epoch": 0.25, "learning_rate": 2.626896676300578e-05, "loss": 1.4088, "step": 1386 }, { "epoch": 0.25, "learning_rate": 2.6266257225433525e-05, "loss": 1.2536, "step": 1387 }, { "epoch": 0.25, "learning_rate": 2.6263547687861272e-05, "loss": 1.2002, "step": 1388 }, { "epoch": 0.25, "learning_rate": 2.626083815028902e-05, "loss": 0.6648, "step": 1389 }, { "epoch": 0.25, "learning_rate": 2.6258128612716765e-05, "loss": 0.8098, "step": 1390 }, { "epoch": 0.25, "learning_rate": 2.625541907514451e-05, "loss": 0.5688, "step": 1391 }, { "epoch": 0.25, "learning_rate": 2.6252709537572253e-05, "loss": 0.4949, "step": 1392 }, { "epoch": 0.25, "learning_rate": 2.625e-05, "loss": 0.9906, "step": 1393 }, { "epoch": 0.25, "learning_rate": 2.624729046242775e-05, "loss": 1.2494, "step": 1394 }, { "epoch": 0.25, "learning_rate": 2.624458092485549e-05, "loss": 0.609, "step": 1395 }, { "epoch": 0.25, "learning_rate": 2.6241871387283238e-05, "loss": 1.0099, "step": 1396 }, { "epoch": 0.25, "learning_rate": 2.6239161849710982e-05, "loss": 0.9381, "step": 1397 }, { "epoch": 0.25, "learning_rate": 2.623645231213873e-05, "loss": 0.7957, "step": 1398 }, { "epoch": 0.25, "learning_rate": 2.6233742774566477e-05, "loss": 0.5085, "step": 1399 }, { "epoch": 0.25, "learning_rate": 2.623103323699422e-05, "loss": 1.8746, "step": 1400 }, { "epoch": 0.25, "learning_rate": 2.6228323699421966e-05, "loss": 0.4362, "step": 1401 }, { "epoch": 0.25, "learning_rate": 2.622561416184971e-05, "loss": 0.9429, "step": 1402 }, { "epoch": 0.25, "learning_rate": 2.6222904624277458e-05, "loss": 1.1311, "step": 1403 }, { "epoch": 0.25, "learning_rate": 2.6220195086705203e-05, "loss": 0.8104, "step": 1404 }, { "epoch": 0.25, "learning_rate": 2.6217485549132947e-05, "loss": 0.767, "step": 1405 }, { "epoch": 0.25, "learning_rate": 2.6214776011560695e-05, "loss": 0.7684, "step": 1406 }, { "epoch": 0.25, "learning_rate": 2.621206647398844e-05, "loss": 0.5949, "step": 1407 }, { "epoch": 0.25, "learning_rate": 2.6209356936416187e-05, "loss": 0.5036, "step": 1408 }, { "epoch": 0.25, "learning_rate": 2.620664739884393e-05, "loss": 0.5503, "step": 1409 }, { "epoch": 0.25, "learning_rate": 2.6203937861271676e-05, "loss": 0.8493, "step": 1410 }, { "epoch": 0.25, "learning_rate": 2.6201228323699423e-05, "loss": 0.902, "step": 1411 }, { "epoch": 0.26, "learning_rate": 2.6198518786127168e-05, "loss": 0.9036, "step": 1412 }, { "epoch": 0.26, "learning_rate": 2.6195809248554915e-05, "loss": 0.929, "step": 1413 }, { "epoch": 0.26, "learning_rate": 2.619309971098266e-05, "loss": 0.3423, "step": 1414 }, { "epoch": 0.26, "learning_rate": 2.6190390173410404e-05, "loss": 0.6567, "step": 1415 }, { "epoch": 0.26, "learning_rate": 2.6187680635838152e-05, "loss": 0.504, "step": 1416 }, { "epoch": 0.26, "learning_rate": 2.6184971098265896e-05, "loss": 0.9208, "step": 1417 }, { "epoch": 0.26, "learning_rate": 2.618226156069364e-05, "loss": 0.8953, "step": 1418 }, { "epoch": 0.26, "learning_rate": 2.617955202312139e-05, "loss": 0.7952, "step": 1419 }, { "epoch": 0.26, "learning_rate": 2.6176842485549133e-05, "loss": 0.8473, "step": 1420 }, { "epoch": 0.26, "learning_rate": 2.617413294797688e-05, "loss": 0.4736, "step": 1421 }, { "epoch": 0.26, "learning_rate": 2.6171423410404625e-05, "loss": 0.9256, "step": 1422 }, { "epoch": 0.26, "learning_rate": 2.616871387283237e-05, "loss": 0.9119, "step": 1423 }, { "epoch": 0.26, "learning_rate": 2.6166004335260117e-05, "loss": 0.9251, "step": 1424 }, { "epoch": 0.26, "learning_rate": 2.616329479768786e-05, "loss": 1.4945, "step": 1425 }, { "epoch": 0.26, "learning_rate": 2.616058526011561e-05, "loss": 0.2797, "step": 1426 }, { "epoch": 0.26, "learning_rate": 2.615787572254335e-05, "loss": 1.1034, "step": 1427 }, { "epoch": 0.26, "learning_rate": 2.6155166184971098e-05, "loss": 1.5137, "step": 1428 }, { "epoch": 0.26, "learning_rate": 2.6152456647398846e-05, "loss": 1.1637, "step": 1429 }, { "epoch": 0.26, "learning_rate": 2.614974710982659e-05, "loss": 0.9663, "step": 1430 }, { "epoch": 0.26, "learning_rate": 2.6147037572254338e-05, "loss": 0.5452, "step": 1431 }, { "epoch": 0.26, "learning_rate": 2.614432803468208e-05, "loss": 0.869, "step": 1432 }, { "epoch": 0.26, "learning_rate": 2.6141618497109827e-05, "loss": 0.82, "step": 1433 }, { "epoch": 0.26, "learning_rate": 2.6138908959537574e-05, "loss": 0.543, "step": 1434 }, { "epoch": 0.26, "learning_rate": 2.613619942196532e-05, "loss": 1.7872, "step": 1435 }, { "epoch": 0.26, "learning_rate": 2.6133489884393066e-05, "loss": 0.6923, "step": 1436 }, { "epoch": 0.26, "learning_rate": 2.6130780346820807e-05, "loss": 1.1661, "step": 1437 }, { "epoch": 0.26, "learning_rate": 2.6128070809248555e-05, "loss": 0.8759, "step": 1438 }, { "epoch": 0.26, "learning_rate": 2.6125361271676303e-05, "loss": 0.7559, "step": 1439 }, { "epoch": 0.26, "learning_rate": 2.6122651734104047e-05, "loss": 0.8416, "step": 1440 }, { "epoch": 0.26, "learning_rate": 2.611994219653179e-05, "loss": 1.138, "step": 1441 }, { "epoch": 0.26, "learning_rate": 2.6117232658959536e-05, "loss": 0.6207, "step": 1442 }, { "epoch": 0.26, "learning_rate": 2.6114523121387284e-05, "loss": 0.9178, "step": 1443 }, { "epoch": 0.26, "learning_rate": 2.611181358381503e-05, "loss": 1.1773, "step": 1444 }, { "epoch": 0.26, "learning_rate": 2.6109104046242776e-05, "loss": 0.5223, "step": 1445 }, { "epoch": 0.26, "learning_rate": 2.610639450867052e-05, "loss": 0.6863, "step": 1446 }, { "epoch": 0.26, "learning_rate": 2.6103684971098265e-05, "loss": 0.5889, "step": 1447 }, { "epoch": 0.26, "learning_rate": 2.6100975433526012e-05, "loss": 1.0511, "step": 1448 }, { "epoch": 0.26, "learning_rate": 2.609826589595376e-05, "loss": 1.06, "step": 1449 }, { "epoch": 0.26, "learning_rate": 2.60955563583815e-05, "loss": 1.1709, "step": 1450 }, { "epoch": 0.26, "learning_rate": 2.609284682080925e-05, "loss": 0.9679, "step": 1451 }, { "epoch": 0.26, "learning_rate": 2.6090137283236993e-05, "loss": 1.5555, "step": 1452 }, { "epoch": 0.26, "learning_rate": 2.608742774566474e-05, "loss": 1.3521, "step": 1453 }, { "epoch": 0.26, "learning_rate": 2.608471820809249e-05, "loss": 0.8549, "step": 1454 }, { "epoch": 0.26, "learning_rate": 2.608200867052023e-05, "loss": 1.1017, "step": 1455 }, { "epoch": 0.26, "learning_rate": 2.6079299132947977e-05, "loss": 0.5229, "step": 1456 }, { "epoch": 0.26, "learning_rate": 2.6076589595375722e-05, "loss": 1.1665, "step": 1457 }, { "epoch": 0.26, "learning_rate": 2.607388005780347e-05, "loss": 1.08, "step": 1458 }, { "epoch": 0.26, "learning_rate": 2.6071170520231217e-05, "loss": 0.8632, "step": 1459 }, { "epoch": 0.26, "learning_rate": 2.6068460982658958e-05, "loss": 0.9291, "step": 1460 }, { "epoch": 0.26, "learning_rate": 2.6065751445086706e-05, "loss": 0.6593, "step": 1461 }, { "epoch": 0.26, "learning_rate": 2.606304190751445e-05, "loss": 1.5122, "step": 1462 }, { "epoch": 0.26, "learning_rate": 2.6060332369942198e-05, "loss": 0.9604, "step": 1463 }, { "epoch": 0.26, "learning_rate": 2.6057622832369942e-05, "loss": 0.6797, "step": 1464 }, { "epoch": 0.26, "learning_rate": 2.6054913294797687e-05, "loss": 0.2634, "step": 1465 }, { "epoch": 0.26, "learning_rate": 2.6052203757225435e-05, "loss": 0.8834, "step": 1466 }, { "epoch": 0.26, "learning_rate": 2.604949421965318e-05, "loss": 0.3435, "step": 1467 }, { "epoch": 0.27, "learning_rate": 2.6046784682080927e-05, "loss": 1.5496, "step": 1468 }, { "epoch": 0.27, "learning_rate": 2.604407514450867e-05, "loss": 0.382, "step": 1469 }, { "epoch": 0.27, "learning_rate": 2.6041365606936415e-05, "loss": 1.296, "step": 1470 }, { "epoch": 0.27, "learning_rate": 2.6038656069364163e-05, "loss": 0.5302, "step": 1471 }, { "epoch": 0.27, "learning_rate": 2.6035946531791908e-05, "loss": 0.7629, "step": 1472 }, { "epoch": 0.27, "learning_rate": 2.6033236994219652e-05, "loss": 0.8224, "step": 1473 }, { "epoch": 0.27, "learning_rate": 2.60305274566474e-05, "loss": 1.6322, "step": 1474 }, { "epoch": 0.27, "learning_rate": 2.6027817919075144e-05, "loss": 1.0083, "step": 1475 }, { "epoch": 0.27, "learning_rate": 2.6025108381502892e-05, "loss": 0.5088, "step": 1476 }, { "epoch": 0.27, "learning_rate": 2.6022398843930636e-05, "loss": 0.1195, "step": 1477 }, { "epoch": 0.27, "learning_rate": 2.601968930635838e-05, "loss": 0.5545, "step": 1478 }, { "epoch": 0.27, "learning_rate": 2.6016979768786128e-05, "loss": 0.6059, "step": 1479 }, { "epoch": 0.27, "learning_rate": 2.6014270231213873e-05, "loss": 0.8888, "step": 1480 }, { "epoch": 0.27, "learning_rate": 2.601156069364162e-05, "loss": 1.1684, "step": 1481 }, { "epoch": 0.27, "learning_rate": 2.6008851156069368e-05, "loss": 1.2017, "step": 1482 }, { "epoch": 0.27, "learning_rate": 2.600614161849711e-05, "loss": 0.2582, "step": 1483 }, { "epoch": 0.27, "learning_rate": 2.6003432080924857e-05, "loss": 0.3746, "step": 1484 }, { "epoch": 0.27, "learning_rate": 2.60007225433526e-05, "loss": 1.3511, "step": 1485 }, { "epoch": 0.27, "learning_rate": 2.599801300578035e-05, "loss": 0.607, "step": 1486 }, { "epoch": 0.27, "learning_rate": 2.5995303468208093e-05, "loss": 1.5401, "step": 1487 }, { "epoch": 0.27, "learning_rate": 2.5992593930635838e-05, "loss": 1.6969, "step": 1488 }, { "epoch": 0.27, "learning_rate": 2.5989884393063585e-05, "loss": 0.9093, "step": 1489 }, { "epoch": 0.27, "learning_rate": 2.598717485549133e-05, "loss": 1.5972, "step": 1490 }, { "epoch": 0.27, "learning_rate": 2.5984465317919078e-05, "loss": 1.7964, "step": 1491 }, { "epoch": 0.27, "learning_rate": 2.5981755780346822e-05, "loss": 1.1792, "step": 1492 }, { "epoch": 0.27, "learning_rate": 2.5979046242774566e-05, "loss": 1.7072, "step": 1493 }, { "epoch": 0.27, "learning_rate": 2.5976336705202314e-05, "loss": 0.8347, "step": 1494 }, { "epoch": 0.27, "learning_rate": 2.597362716763006e-05, "loss": 1.0479, "step": 1495 }, { "epoch": 0.27, "learning_rate": 2.5970917630057803e-05, "loss": 0.6774, "step": 1496 }, { "epoch": 0.27, "learning_rate": 2.596820809248555e-05, "loss": 1.5472, "step": 1497 }, { "epoch": 0.27, "learning_rate": 2.5965498554913295e-05, "loss": 1.3615, "step": 1498 }, { "epoch": 0.27, "learning_rate": 2.5962789017341043e-05, "loss": 0.683, "step": 1499 }, { "epoch": 0.27, "learning_rate": 2.5960079479768787e-05, "loss": 1.1996, "step": 1500 }, { "epoch": 0.27, "eval_exact_match": 84.3519394512772, "eval_f1": 91.38884373749661, "step": 1500 }, { "epoch": 0.27, "learning_rate": 2.595736994219653e-05, "loss": 1.5886, "step": 1501 }, { "epoch": 0.27, "learning_rate": 2.595466040462428e-05, "loss": 0.7546, "step": 1502 }, { "epoch": 0.27, "learning_rate": 2.5951950867052024e-05, "loss": 1.0591, "step": 1503 }, { "epoch": 0.27, "learning_rate": 2.594924132947977e-05, "loss": 1.0326, "step": 1504 }, { "epoch": 0.27, "learning_rate": 2.5946531791907516e-05, "loss": 0.5941, "step": 1505 }, { "epoch": 0.27, "learning_rate": 2.594382225433526e-05, "loss": 0.8692, "step": 1506 }, { "epoch": 0.27, "learning_rate": 2.5941112716763008e-05, "loss": 0.6305, "step": 1507 }, { "epoch": 0.27, "learning_rate": 2.5938403179190752e-05, "loss": 1.1531, "step": 1508 }, { "epoch": 0.27, "learning_rate": 2.59356936416185e-05, "loss": 0.6323, "step": 1509 }, { "epoch": 0.27, "learning_rate": 2.593298410404624e-05, "loss": 0.8718, "step": 1510 }, { "epoch": 0.27, "learning_rate": 2.593027456647399e-05, "loss": 2.1961, "step": 1511 }, { "epoch": 0.27, "learning_rate": 2.5927565028901736e-05, "loss": 0.725, "step": 1512 }, { "epoch": 0.27, "learning_rate": 2.592485549132948e-05, "loss": 1.1774, "step": 1513 }, { "epoch": 0.27, "learning_rate": 2.592214595375723e-05, "loss": 0.6496, "step": 1514 }, { "epoch": 0.27, "learning_rate": 2.591943641618497e-05, "loss": 1.1008, "step": 1515 }, { "epoch": 0.27, "learning_rate": 2.5916726878612717e-05, "loss": 1.2172, "step": 1516 }, { "epoch": 0.27, "learning_rate": 2.5914017341040465e-05, "loss": 0.9118, "step": 1517 }, { "epoch": 0.27, "learning_rate": 2.591130780346821e-05, "loss": 1.0667, "step": 1518 }, { "epoch": 0.27, "learning_rate": 2.5908598265895954e-05, "loss": 1.3266, "step": 1519 }, { "epoch": 0.27, "learning_rate": 2.5905888728323698e-05, "loss": 1.3323, "step": 1520 }, { "epoch": 0.27, "learning_rate": 2.5903179190751446e-05, "loss": 0.7745, "step": 1521 }, { "epoch": 0.27, "learning_rate": 2.5900469653179194e-05, "loss": 1.0808, "step": 1522 }, { "epoch": 0.28, "learning_rate": 2.5897760115606938e-05, "loss": 0.9691, "step": 1523 }, { "epoch": 0.28, "learning_rate": 2.5895050578034682e-05, "loss": 0.7157, "step": 1524 }, { "epoch": 0.28, "learning_rate": 2.5892341040462427e-05, "loss": 0.7784, "step": 1525 }, { "epoch": 0.28, "learning_rate": 2.5889631502890174e-05, "loss": 1.5282, "step": 1526 }, { "epoch": 0.28, "learning_rate": 2.5886921965317922e-05, "loss": 0.4764, "step": 1527 }, { "epoch": 0.28, "learning_rate": 2.5884212427745667e-05, "loss": 0.9945, "step": 1528 }, { "epoch": 0.28, "learning_rate": 2.588150289017341e-05, "loss": 0.9979, "step": 1529 }, { "epoch": 0.28, "learning_rate": 2.5878793352601155e-05, "loss": 1.5212, "step": 1530 }, { "epoch": 0.28, "learning_rate": 2.5876083815028903e-05, "loss": 1.1389, "step": 1531 }, { "epoch": 0.28, "learning_rate": 2.587337427745665e-05, "loss": 1.1682, "step": 1532 }, { "epoch": 0.28, "learning_rate": 2.5870664739884392e-05, "loss": 0.8128, "step": 1533 }, { "epoch": 0.28, "learning_rate": 2.586795520231214e-05, "loss": 0.9211, "step": 1534 }, { "epoch": 0.28, "learning_rate": 2.5865245664739884e-05, "loss": 0.7828, "step": 1535 }, { "epoch": 0.28, "learning_rate": 2.586253612716763e-05, "loss": 1.0935, "step": 1536 }, { "epoch": 0.28, "learning_rate": 2.585982658959538e-05, "loss": 0.7813, "step": 1537 }, { "epoch": 0.28, "learning_rate": 2.585711705202312e-05, "loss": 0.7553, "step": 1538 }, { "epoch": 0.28, "learning_rate": 2.5854407514450868e-05, "loss": 0.6299, "step": 1539 }, { "epoch": 0.28, "learning_rate": 2.5851697976878612e-05, "loss": 0.9467, "step": 1540 }, { "epoch": 0.28, "learning_rate": 2.584898843930636e-05, "loss": 1.5844, "step": 1541 }, { "epoch": 0.28, "learning_rate": 2.5846278901734105e-05, "loss": 0.7902, "step": 1542 }, { "epoch": 0.28, "learning_rate": 2.584356936416185e-05, "loss": 0.8209, "step": 1543 }, { "epoch": 0.28, "learning_rate": 2.5840859826589597e-05, "loss": 1.0972, "step": 1544 }, { "epoch": 0.28, "learning_rate": 2.583815028901734e-05, "loss": 1.2799, "step": 1545 }, { "epoch": 0.28, "learning_rate": 2.583544075144509e-05, "loss": 0.4534, "step": 1546 }, { "epoch": 0.28, "learning_rate": 2.5832731213872833e-05, "loss": 0.9615, "step": 1547 }, { "epoch": 0.28, "learning_rate": 2.5830021676300578e-05, "loss": 0.5891, "step": 1548 }, { "epoch": 0.28, "learning_rate": 2.5827312138728325e-05, "loss": 1.0776, "step": 1549 }, { "epoch": 0.28, "learning_rate": 2.582460260115607e-05, "loss": 0.5069, "step": 1550 }, { "epoch": 0.28, "learning_rate": 2.5821893063583814e-05, "loss": 0.7456, "step": 1551 }, { "epoch": 0.28, "learning_rate": 2.5819183526011562e-05, "loss": 1.1116, "step": 1552 }, { "epoch": 0.28, "learning_rate": 2.5816473988439306e-05, "loss": 1.0525, "step": 1553 }, { "epoch": 0.28, "learning_rate": 2.5813764450867054e-05, "loss": 1.094, "step": 1554 }, { "epoch": 0.28, "learning_rate": 2.5811054913294798e-05, "loss": 0.9129, "step": 1555 }, { "epoch": 0.28, "learning_rate": 2.5808345375722543e-05, "loss": 0.5199, "step": 1556 }, { "epoch": 0.28, "learning_rate": 2.580563583815029e-05, "loss": 0.7345, "step": 1557 }, { "epoch": 0.28, "learning_rate": 2.5802926300578035e-05, "loss": 0.4054, "step": 1558 }, { "epoch": 0.28, "learning_rate": 2.5800216763005783e-05, "loss": 0.492, "step": 1559 }, { "epoch": 0.28, "learning_rate": 2.5797507225433527e-05, "loss": 0.615, "step": 1560 }, { "epoch": 0.28, "learning_rate": 2.579479768786127e-05, "loss": 1.2106, "step": 1561 }, { "epoch": 0.28, "learning_rate": 2.579208815028902e-05, "loss": 0.4828, "step": 1562 }, { "epoch": 0.28, "learning_rate": 2.5789378612716763e-05, "loss": 0.8247, "step": 1563 }, { "epoch": 0.28, "learning_rate": 2.578666907514451e-05, "loss": 0.8532, "step": 1564 }, { "epoch": 0.28, "learning_rate": 2.5783959537572252e-05, "loss": 0.5219, "step": 1565 }, { "epoch": 0.28, "learning_rate": 2.578125e-05, "loss": 0.9545, "step": 1566 }, { "epoch": 0.28, "learning_rate": 2.5778540462427748e-05, "loss": 1.1975, "step": 1567 }, { "epoch": 0.28, "learning_rate": 2.5775830924855492e-05, "loss": 0.5329, "step": 1568 }, { "epoch": 0.28, "learning_rate": 2.577312138728324e-05, "loss": 1.051, "step": 1569 }, { "epoch": 0.28, "learning_rate": 2.577041184971098e-05, "loss": 1.0263, "step": 1570 }, { "epoch": 0.28, "learning_rate": 2.576770231213873e-05, "loss": 0.7783, "step": 1571 }, { "epoch": 0.28, "learning_rate": 2.5764992774566476e-05, "loss": 1.5008, "step": 1572 }, { "epoch": 0.28, "learning_rate": 2.576228323699422e-05, "loss": 0.5438, "step": 1573 }, { "epoch": 0.28, "learning_rate": 2.5759573699421965e-05, "loss": 1.1147, "step": 1574 }, { "epoch": 0.28, "learning_rate": 2.575686416184971e-05, "loss": 0.466, "step": 1575 }, { "epoch": 0.28, "learning_rate": 2.5754154624277457e-05, "loss": 1.032, "step": 1576 }, { "epoch": 0.28, "learning_rate": 2.5751445086705205e-05, "loss": 0.8319, "step": 1577 }, { "epoch": 0.29, "learning_rate": 2.574873554913295e-05, "loss": 0.9247, "step": 1578 }, { "epoch": 0.29, "learning_rate": 2.5746026011560694e-05, "loss": 0.5902, "step": 1579 }, { "epoch": 0.29, "learning_rate": 2.5743316473988438e-05, "loss": 0.7605, "step": 1580 }, { "epoch": 0.29, "learning_rate": 2.5740606936416186e-05, "loss": 0.6673, "step": 1581 }, { "epoch": 0.29, "learning_rate": 2.5737897398843933e-05, "loss": 0.3508, "step": 1582 }, { "epoch": 0.29, "learning_rate": 2.5735187861271678e-05, "loss": 1.1823, "step": 1583 }, { "epoch": 0.29, "learning_rate": 2.5732478323699422e-05, "loss": 0.5071, "step": 1584 }, { "epoch": 0.29, "learning_rate": 2.5729768786127167e-05, "loss": 0.6551, "step": 1585 }, { "epoch": 0.29, "learning_rate": 2.5727059248554914e-05, "loss": 0.6218, "step": 1586 }, { "epoch": 0.29, "learning_rate": 2.5724349710982662e-05, "loss": 0.743, "step": 1587 }, { "epoch": 0.29, "learning_rate": 2.5721640173410403e-05, "loss": 1.032, "step": 1588 }, { "epoch": 0.29, "learning_rate": 2.571893063583815e-05, "loss": 0.8584, "step": 1589 }, { "epoch": 0.29, "learning_rate": 2.5716221098265895e-05, "loss": 0.814, "step": 1590 }, { "epoch": 0.29, "learning_rate": 2.5713511560693643e-05, "loss": 0.7675, "step": 1591 }, { "epoch": 0.29, "learning_rate": 2.571080202312139e-05, "loss": 0.6249, "step": 1592 }, { "epoch": 0.29, "learning_rate": 2.570809248554913e-05, "loss": 1.316, "step": 1593 }, { "epoch": 0.29, "learning_rate": 2.570538294797688e-05, "loss": 1.0772, "step": 1594 }, { "epoch": 0.29, "learning_rate": 2.5702673410404624e-05, "loss": 0.5582, "step": 1595 }, { "epoch": 0.29, "learning_rate": 2.569996387283237e-05, "loss": 1.4983, "step": 1596 }, { "epoch": 0.29, "learning_rate": 2.5697254335260116e-05, "loss": 0.5865, "step": 1597 }, { "epoch": 0.29, "learning_rate": 2.569454479768786e-05, "loss": 1.3862, "step": 1598 }, { "epoch": 0.29, "learning_rate": 2.5691835260115608e-05, "loss": 0.9536, "step": 1599 }, { "epoch": 0.29, "learning_rate": 2.5689125722543352e-05, "loss": 1.1291, "step": 1600 }, { "epoch": 0.29, "learning_rate": 2.56864161849711e-05, "loss": 0.6261, "step": 1601 }, { "epoch": 0.29, "learning_rate": 2.5683706647398844e-05, "loss": 0.9438, "step": 1602 }, { "epoch": 0.29, "learning_rate": 2.568099710982659e-05, "loss": 0.6, "step": 1603 }, { "epoch": 0.29, "learning_rate": 2.5678287572254337e-05, "loss": 0.8041, "step": 1604 }, { "epoch": 0.29, "learning_rate": 2.567557803468208e-05, "loss": 1.2921, "step": 1605 }, { "epoch": 0.29, "learning_rate": 2.567286849710983e-05, "loss": 1.5233, "step": 1606 }, { "epoch": 0.29, "learning_rate": 2.5670158959537573e-05, "loss": 0.844, "step": 1607 }, { "epoch": 0.29, "learning_rate": 2.5667449421965317e-05, "loss": 0.9963, "step": 1608 }, { "epoch": 0.29, "learning_rate": 2.5664739884393065e-05, "loss": 1.0524, "step": 1609 }, { "epoch": 0.29, "learning_rate": 2.566203034682081e-05, "loss": 0.8537, "step": 1610 }, { "epoch": 0.29, "learning_rate": 2.5659320809248554e-05, "loss": 0.5943, "step": 1611 }, { "epoch": 0.29, "learning_rate": 2.56566112716763e-05, "loss": 0.6229, "step": 1612 }, { "epoch": 0.29, "learning_rate": 2.5653901734104046e-05, "loss": 0.894, "step": 1613 }, { "epoch": 0.29, "learning_rate": 2.5651192196531794e-05, "loss": 0.945, "step": 1614 }, { "epoch": 0.29, "learning_rate": 2.5648482658959538e-05, "loss": 0.473, "step": 1615 }, { "epoch": 0.29, "learning_rate": 2.5645773121387282e-05, "loss": 1.4753, "step": 1616 }, { "epoch": 0.29, "learning_rate": 2.564306358381503e-05, "loss": 1.0055, "step": 1617 }, { "epoch": 0.29, "learning_rate": 2.5640354046242775e-05, "loss": 1.3081, "step": 1618 }, { "epoch": 0.29, "learning_rate": 2.5637644508670522e-05, "loss": 0.9411, "step": 1619 }, { "epoch": 0.29, "learning_rate": 2.5634934971098263e-05, "loss": 1.1829, "step": 1620 }, { "epoch": 0.29, "learning_rate": 2.563222543352601e-05, "loss": 0.6084, "step": 1621 }, { "epoch": 0.29, "learning_rate": 2.562951589595376e-05, "loss": 0.9137, "step": 1622 }, { "epoch": 0.29, "learning_rate": 2.5626806358381503e-05, "loss": 0.5089, "step": 1623 }, { "epoch": 0.29, "learning_rate": 2.562409682080925e-05, "loss": 1.4884, "step": 1624 }, { "epoch": 0.29, "learning_rate": 2.5621387283236992e-05, "loss": 1.1209, "step": 1625 }, { "epoch": 0.29, "learning_rate": 2.561867774566474e-05, "loss": 0.8705, "step": 1626 }, { "epoch": 0.29, "learning_rate": 2.5615968208092487e-05, "loss": 0.9153, "step": 1627 }, { "epoch": 0.29, "learning_rate": 2.5613258670520232e-05, "loss": 0.644, "step": 1628 }, { "epoch": 0.29, "learning_rate": 2.561054913294798e-05, "loss": 0.2667, "step": 1629 }, { "epoch": 0.29, "learning_rate": 2.560783959537572e-05, "loss": 1.0106, "step": 1630 }, { "epoch": 0.29, "learning_rate": 2.5605130057803468e-05, "loss": 0.7233, "step": 1631 }, { "epoch": 0.29, "learning_rate": 2.5602420520231216e-05, "loss": 1.3148, "step": 1632 }, { "epoch": 0.29, "learning_rate": 2.559971098265896e-05, "loss": 0.8345, "step": 1633 }, { "epoch": 0.3, "learning_rate": 2.5597001445086705e-05, "loss": 0.8094, "step": 1634 }, { "epoch": 0.3, "learning_rate": 2.559429190751445e-05, "loss": 1.3355, "step": 1635 }, { "epoch": 0.3, "learning_rate": 2.5591582369942197e-05, "loss": 0.4018, "step": 1636 }, { "epoch": 0.3, "learning_rate": 2.5588872832369945e-05, "loss": 0.77, "step": 1637 }, { "epoch": 0.3, "learning_rate": 2.558616329479769e-05, "loss": 1.0837, "step": 1638 }, { "epoch": 0.3, "learning_rate": 2.5583453757225433e-05, "loss": 0.8772, "step": 1639 }, { "epoch": 0.3, "learning_rate": 2.5580744219653178e-05, "loss": 0.9097, "step": 1640 }, { "epoch": 0.3, "learning_rate": 2.5578034682080925e-05, "loss": 0.7195, "step": 1641 }, { "epoch": 0.3, "learning_rate": 2.5575325144508673e-05, "loss": 0.6587, "step": 1642 }, { "epoch": 0.3, "learning_rate": 2.5572615606936414e-05, "loss": 1.6794, "step": 1643 }, { "epoch": 0.3, "learning_rate": 2.5569906069364162e-05, "loss": 0.9867, "step": 1644 }, { "epoch": 0.3, "learning_rate": 2.5567196531791906e-05, "loss": 0.9739, "step": 1645 }, { "epoch": 0.3, "learning_rate": 2.5564486994219654e-05, "loss": 1.0873, "step": 1646 }, { "epoch": 0.3, "learning_rate": 2.5561777456647402e-05, "loss": 0.9671, "step": 1647 }, { "epoch": 0.3, "learning_rate": 2.5559067919075143e-05, "loss": 0.7831, "step": 1648 }, { "epoch": 0.3, "learning_rate": 2.555635838150289e-05, "loss": 1.018, "step": 1649 }, { "epoch": 0.3, "learning_rate": 2.5553648843930635e-05, "loss": 0.8518, "step": 1650 }, { "epoch": 0.3, "learning_rate": 2.5550939306358383e-05, "loss": 2.2729, "step": 1651 }, { "epoch": 0.3, "learning_rate": 2.554822976878613e-05, "loss": 1.3185, "step": 1652 }, { "epoch": 0.3, "learning_rate": 2.554552023121387e-05, "loss": 1.2404, "step": 1653 }, { "epoch": 0.3, "learning_rate": 2.554281069364162e-05, "loss": 0.9912, "step": 1654 }, { "epoch": 0.3, "learning_rate": 2.5540101156069367e-05, "loss": 1.0984, "step": 1655 }, { "epoch": 0.3, "learning_rate": 2.553739161849711e-05, "loss": 0.8987, "step": 1656 }, { "epoch": 0.3, "learning_rate": 2.5534682080924856e-05, "loss": 1.173, "step": 1657 }, { "epoch": 0.3, "learning_rate": 2.55319725433526e-05, "loss": 0.9376, "step": 1658 }, { "epoch": 0.3, "learning_rate": 2.5529263005780348e-05, "loss": 1.4943, "step": 1659 }, { "epoch": 0.3, "learning_rate": 2.5526553468208096e-05, "loss": 0.9508, "step": 1660 }, { "epoch": 0.3, "learning_rate": 2.552384393063584e-05, "loss": 1.1618, "step": 1661 }, { "epoch": 0.3, "learning_rate": 2.5521134393063584e-05, "loss": 1.117, "step": 1662 }, { "epoch": 0.3, "learning_rate": 2.551842485549133e-05, "loss": 0.8097, "step": 1663 }, { "epoch": 0.3, "learning_rate": 2.5515715317919076e-05, "loss": 1.2796, "step": 1664 }, { "epoch": 0.3, "learning_rate": 2.5513005780346824e-05, "loss": 1.028, "step": 1665 }, { "epoch": 0.3, "learning_rate": 2.5510296242774565e-05, "loss": 0.6747, "step": 1666 }, { "epoch": 0.3, "learning_rate": 2.5507586705202313e-05, "loss": 0.9964, "step": 1667 }, { "epoch": 0.3, "learning_rate": 2.5504877167630057e-05, "loss": 0.7336, "step": 1668 }, { "epoch": 0.3, "learning_rate": 2.5502167630057805e-05, "loss": 1.4052, "step": 1669 }, { "epoch": 0.3, "learning_rate": 2.5499458092485553e-05, "loss": 1.2481, "step": 1670 }, { "epoch": 0.3, "learning_rate": 2.5496748554913294e-05, "loss": 1.0176, "step": 1671 }, { "epoch": 0.3, "learning_rate": 2.549403901734104e-05, "loss": 1.1141, "step": 1672 }, { "epoch": 0.3, "learning_rate": 2.5491329479768786e-05, "loss": 0.9113, "step": 1673 }, { "epoch": 0.3, "learning_rate": 2.5488619942196534e-05, "loss": 1.6674, "step": 1674 }, { "epoch": 0.3, "learning_rate": 2.548591040462428e-05, "loss": 1.1593, "step": 1675 }, { "epoch": 0.3, "learning_rate": 2.5483200867052022e-05, "loss": 1.0834, "step": 1676 }, { "epoch": 0.3, "learning_rate": 2.548049132947977e-05, "loss": 1.8366, "step": 1677 }, { "epoch": 0.3, "learning_rate": 2.5477781791907514e-05, "loss": 1.2904, "step": 1678 }, { "epoch": 0.3, "learning_rate": 2.5475072254335262e-05, "loss": 1.6193, "step": 1679 }, { "epoch": 0.3, "learning_rate": 2.5472362716763007e-05, "loss": 0.7125, "step": 1680 }, { "epoch": 0.3, "learning_rate": 2.546965317919075e-05, "loss": 0.7112, "step": 1681 }, { "epoch": 0.3, "learning_rate": 2.54669436416185e-05, "loss": 1.1268, "step": 1682 }, { "epoch": 0.3, "learning_rate": 2.5464234104046243e-05, "loss": 0.8394, "step": 1683 }, { "epoch": 0.3, "learning_rate": 2.546152456647399e-05, "loss": 1.5626, "step": 1684 }, { "epoch": 0.3, "learning_rate": 2.5458815028901735e-05, "loss": 0.8658, "step": 1685 }, { "epoch": 0.3, "learning_rate": 2.545610549132948e-05, "loss": 0.7071, "step": 1686 }, { "epoch": 0.3, "learning_rate": 2.5453395953757227e-05, "loss": 1.1713, "step": 1687 }, { "epoch": 0.3, "learning_rate": 2.545068641618497e-05, "loss": 1.6697, "step": 1688 }, { "epoch": 0.31, "learning_rate": 2.5447976878612716e-05, "loss": 1.2199, "step": 1689 }, { "epoch": 0.31, "learning_rate": 2.5445267341040464e-05, "loss": 0.8835, "step": 1690 }, { "epoch": 0.31, "learning_rate": 2.5442557803468208e-05, "loss": 1.0125, "step": 1691 }, { "epoch": 0.31, "learning_rate": 2.5439848265895956e-05, "loss": 0.5965, "step": 1692 }, { "epoch": 0.31, "learning_rate": 2.54371387283237e-05, "loss": 1.0226, "step": 1693 }, { "epoch": 0.31, "learning_rate": 2.5434429190751445e-05, "loss": 0.7148, "step": 1694 }, { "epoch": 0.31, "learning_rate": 2.5431719653179192e-05, "loss": 0.3856, "step": 1695 }, { "epoch": 0.31, "learning_rate": 2.5429010115606937e-05, "loss": 1.223, "step": 1696 }, { "epoch": 0.31, "learning_rate": 2.5426300578034684e-05, "loss": 0.8405, "step": 1697 }, { "epoch": 0.31, "learning_rate": 2.542359104046243e-05, "loss": 0.8446, "step": 1698 }, { "epoch": 0.31, "learning_rate": 2.5420881502890173e-05, "loss": 0.7792, "step": 1699 }, { "epoch": 0.31, "learning_rate": 2.541817196531792e-05, "loss": 1.953, "step": 1700 }, { "epoch": 0.31, "learning_rate": 2.5415462427745665e-05, "loss": 1.4125, "step": 1701 }, { "epoch": 0.31, "learning_rate": 2.5412752890173413e-05, "loss": 1.1378, "step": 1702 }, { "epoch": 0.31, "learning_rate": 2.5410043352601154e-05, "loss": 1.3215, "step": 1703 }, { "epoch": 0.31, "learning_rate": 2.5407333815028902e-05, "loss": 0.9891, "step": 1704 }, { "epoch": 0.31, "learning_rate": 2.540462427745665e-05, "loss": 0.9062, "step": 1705 }, { "epoch": 0.31, "learning_rate": 2.5401914739884394e-05, "loss": 0.3139, "step": 1706 }, { "epoch": 0.31, "learning_rate": 2.539920520231214e-05, "loss": 0.7585, "step": 1707 }, { "epoch": 0.31, "learning_rate": 2.5396495664739883e-05, "loss": 1.0942, "step": 1708 }, { "epoch": 0.31, "learning_rate": 2.539378612716763e-05, "loss": 0.6702, "step": 1709 }, { "epoch": 0.31, "learning_rate": 2.5391076589595378e-05, "loss": 0.4661, "step": 1710 }, { "epoch": 0.31, "learning_rate": 2.5388367052023123e-05, "loss": 1.3588, "step": 1711 }, { "epoch": 0.31, "learning_rate": 2.5385657514450867e-05, "loss": 1.0766, "step": 1712 }, { "epoch": 0.31, "learning_rate": 2.538294797687861e-05, "loss": 0.391, "step": 1713 }, { "epoch": 0.31, "learning_rate": 2.538023843930636e-05, "loss": 0.8808, "step": 1714 }, { "epoch": 0.31, "learning_rate": 2.5377528901734107e-05, "loss": 0.8626, "step": 1715 }, { "epoch": 0.31, "learning_rate": 2.537481936416185e-05, "loss": 2.9776, "step": 1716 }, { "epoch": 0.31, "learning_rate": 2.5372109826589595e-05, "loss": 0.7439, "step": 1717 }, { "epoch": 0.31, "learning_rate": 2.536940028901734e-05, "loss": 1.6246, "step": 1718 }, { "epoch": 0.31, "learning_rate": 2.5366690751445088e-05, "loss": 1.5824, "step": 1719 }, { "epoch": 0.31, "learning_rate": 2.5363981213872835e-05, "loss": 1.2441, "step": 1720 }, { "epoch": 0.31, "learning_rate": 2.536127167630058e-05, "loss": 0.6781, "step": 1721 }, { "epoch": 0.31, "learning_rate": 2.5358562138728324e-05, "loss": 0.7517, "step": 1722 }, { "epoch": 0.31, "learning_rate": 2.535585260115607e-05, "loss": 1.0688, "step": 1723 }, { "epoch": 0.31, "learning_rate": 2.5353143063583816e-05, "loss": 1.2419, "step": 1724 }, { "epoch": 0.31, "learning_rate": 2.5350433526011564e-05, "loss": 0.6976, "step": 1725 }, { "epoch": 0.31, "learning_rate": 2.5347723988439305e-05, "loss": 0.906, "step": 1726 }, { "epoch": 0.31, "learning_rate": 2.5345014450867053e-05, "loss": 0.9105, "step": 1727 }, { "epoch": 0.31, "learning_rate": 2.5342304913294797e-05, "loss": 0.5918, "step": 1728 }, { "epoch": 0.31, "learning_rate": 2.5339595375722545e-05, "loss": 0.6728, "step": 1729 }, { "epoch": 0.31, "learning_rate": 2.5336885838150293e-05, "loss": 0.7088, "step": 1730 }, { "epoch": 0.31, "learning_rate": 2.5334176300578034e-05, "loss": 0.9832, "step": 1731 }, { "epoch": 0.31, "learning_rate": 2.533146676300578e-05, "loss": 1.1839, "step": 1732 }, { "epoch": 0.31, "learning_rate": 2.5328757225433526e-05, "loss": 1.8682, "step": 1733 }, { "epoch": 0.31, "learning_rate": 2.5326047687861273e-05, "loss": 0.8678, "step": 1734 }, { "epoch": 0.31, "learning_rate": 2.5323338150289018e-05, "loss": 0.9038, "step": 1735 }, { "epoch": 0.31, "learning_rate": 2.5320628612716762e-05, "loss": 0.6609, "step": 1736 }, { "epoch": 0.31, "learning_rate": 2.531791907514451e-05, "loss": 0.8324, "step": 1737 }, { "epoch": 0.31, "learning_rate": 2.5315209537572254e-05, "loss": 0.3567, "step": 1738 }, { "epoch": 0.31, "learning_rate": 2.5312500000000002e-05, "loss": 1.4116, "step": 1739 }, { "epoch": 0.31, "learning_rate": 2.5309790462427746e-05, "loss": 0.3896, "step": 1740 }, { "epoch": 0.31, "learning_rate": 2.530708092485549e-05, "loss": 1.1619, "step": 1741 }, { "epoch": 0.31, "learning_rate": 2.530437138728324e-05, "loss": 0.8941, "step": 1742 }, { "epoch": 0.31, "learning_rate": 2.5301661849710983e-05, "loss": 0.9, "step": 1743 }, { "epoch": 0.32, "learning_rate": 2.529895231213873e-05, "loss": 1.4044, "step": 1744 }, { "epoch": 0.32, "learning_rate": 2.5296242774566475e-05, "loss": 0.7731, "step": 1745 }, { "epoch": 0.32, "learning_rate": 2.529353323699422e-05, "loss": 1.0917, "step": 1746 }, { "epoch": 0.32, "learning_rate": 2.5290823699421967e-05, "loss": 0.8274, "step": 1747 }, { "epoch": 0.32, "learning_rate": 2.528811416184971e-05, "loss": 1.6519, "step": 1748 }, { "epoch": 0.32, "learning_rate": 2.5285404624277456e-05, "loss": 1.9755, "step": 1749 }, { "epoch": 0.32, "learning_rate": 2.5282695086705204e-05, "loss": 2.5234, "step": 1750 }, { "epoch": 0.32, "learning_rate": 2.5279985549132948e-05, "loss": 0.7479, "step": 1751 }, { "epoch": 0.32, "learning_rate": 2.5277276011560696e-05, "loss": 0.9436, "step": 1752 }, { "epoch": 0.32, "learning_rate": 2.527456647398844e-05, "loss": 0.3779, "step": 1753 }, { "epoch": 0.32, "learning_rate": 2.5271856936416184e-05, "loss": 0.9242, "step": 1754 }, { "epoch": 0.32, "learning_rate": 2.5269147398843932e-05, "loss": 1.1046, "step": 1755 }, { "epoch": 0.32, "learning_rate": 2.5266437861271677e-05, "loss": 1.075, "step": 1756 }, { "epoch": 0.32, "learning_rate": 2.5263728323699424e-05, "loss": 1.1012, "step": 1757 }, { "epoch": 0.32, "learning_rate": 2.5261018786127165e-05, "loss": 0.5023, "step": 1758 }, { "epoch": 0.32, "learning_rate": 2.5258309248554913e-05, "loss": 0.9845, "step": 1759 }, { "epoch": 0.32, "learning_rate": 2.525559971098266e-05, "loss": 1.2351, "step": 1760 }, { "epoch": 0.32, "learning_rate": 2.5252890173410405e-05, "loss": 0.5771, "step": 1761 }, { "epoch": 0.32, "learning_rate": 2.5250180635838153e-05, "loss": 0.4309, "step": 1762 }, { "epoch": 0.32, "learning_rate": 2.5247471098265894e-05, "loss": 0.8601, "step": 1763 }, { "epoch": 0.32, "learning_rate": 2.524476156069364e-05, "loss": 1.2585, "step": 1764 }, { "epoch": 0.32, "learning_rate": 2.524205202312139e-05, "loss": 1.1483, "step": 1765 }, { "epoch": 0.32, "learning_rate": 2.5239342485549134e-05, "loss": 0.705, "step": 1766 }, { "epoch": 0.32, "learning_rate": 2.5236632947976878e-05, "loss": 0.9208, "step": 1767 }, { "epoch": 0.32, "learning_rate": 2.5233923410404622e-05, "loss": 0.3608, "step": 1768 }, { "epoch": 0.32, "learning_rate": 2.523121387283237e-05, "loss": 0.7528, "step": 1769 }, { "epoch": 0.32, "learning_rate": 2.5228504335260118e-05, "loss": 1.5556, "step": 1770 }, { "epoch": 0.32, "learning_rate": 2.5225794797687862e-05, "loss": 0.4129, "step": 1771 }, { "epoch": 0.32, "learning_rate": 2.5223085260115607e-05, "loss": 0.9866, "step": 1772 }, { "epoch": 0.32, "learning_rate": 2.522037572254335e-05, "loss": 0.9126, "step": 1773 }, { "epoch": 0.32, "learning_rate": 2.52176661849711e-05, "loss": 1.1288, "step": 1774 }, { "epoch": 0.32, "learning_rate": 2.5214956647398847e-05, "loss": 1.5398, "step": 1775 }, { "epoch": 0.32, "learning_rate": 2.521224710982659e-05, "loss": 1.2568, "step": 1776 }, { "epoch": 0.32, "learning_rate": 2.5209537572254335e-05, "loss": 1.0054, "step": 1777 }, { "epoch": 0.32, "learning_rate": 2.520682803468208e-05, "loss": 0.2927, "step": 1778 }, { "epoch": 0.32, "learning_rate": 2.5204118497109827e-05, "loss": 1.1095, "step": 1779 }, { "epoch": 0.32, "learning_rate": 2.5201408959537575e-05, "loss": 0.8467, "step": 1780 }, { "epoch": 0.32, "learning_rate": 2.5198699421965316e-05, "loss": 0.8125, "step": 1781 }, { "epoch": 0.32, "learning_rate": 2.5195989884393064e-05, "loss": 0.5343, "step": 1782 }, { "epoch": 0.32, "learning_rate": 2.5193280346820808e-05, "loss": 0.666, "step": 1783 }, { "epoch": 0.32, "learning_rate": 2.5190570809248556e-05, "loss": 0.9208, "step": 1784 }, { "epoch": 0.32, "learning_rate": 2.5187861271676304e-05, "loss": 1.0305, "step": 1785 }, { "epoch": 0.32, "learning_rate": 2.5185151734104045e-05, "loss": 0.9456, "step": 1786 }, { "epoch": 0.32, "learning_rate": 2.5182442196531793e-05, "loss": 0.6781, "step": 1787 }, { "epoch": 0.32, "learning_rate": 2.5179732658959537e-05, "loss": 0.6997, "step": 1788 }, { "epoch": 0.32, "learning_rate": 2.5177023121387285e-05, "loss": 1.6123, "step": 1789 }, { "epoch": 0.32, "learning_rate": 2.517431358381503e-05, "loss": 1.1617, "step": 1790 }, { "epoch": 0.32, "learning_rate": 2.5171604046242773e-05, "loss": 1.0518, "step": 1791 }, { "epoch": 0.32, "learning_rate": 2.516889450867052e-05, "loss": 0.633, "step": 1792 }, { "epoch": 0.32, "learning_rate": 2.5166184971098265e-05, "loss": 0.5054, "step": 1793 }, { "epoch": 0.32, "learning_rate": 2.5163475433526013e-05, "loss": 0.8344, "step": 1794 }, { "epoch": 0.32, "learning_rate": 2.5160765895953758e-05, "loss": 0.9465, "step": 1795 }, { "epoch": 0.32, "learning_rate": 2.5158056358381502e-05, "loss": 0.869, "step": 1796 }, { "epoch": 0.32, "learning_rate": 2.515534682080925e-05, "loss": 0.4884, "step": 1797 }, { "epoch": 0.32, "learning_rate": 2.5152637283236994e-05, "loss": 0.8409, "step": 1798 }, { "epoch": 0.32, "learning_rate": 2.5149927745664742e-05, "loss": 0.782, "step": 1799 }, { "epoch": 0.33, "learning_rate": 2.5147218208092486e-05, "loss": 0.7318, "step": 1800 }, { "epoch": 0.33, "learning_rate": 2.514450867052023e-05, "loss": 1.735, "step": 1801 }, { "epoch": 0.33, "learning_rate": 2.514179913294798e-05, "loss": 0.6589, "step": 1802 }, { "epoch": 0.33, "learning_rate": 2.5139089595375723e-05, "loss": 0.4785, "step": 1803 }, { "epoch": 0.33, "learning_rate": 2.5136380057803467e-05, "loss": 0.5776, "step": 1804 }, { "epoch": 0.33, "learning_rate": 2.5133670520231215e-05, "loss": 0.4075, "step": 1805 }, { "epoch": 0.33, "learning_rate": 2.513096098265896e-05, "loss": 0.8872, "step": 1806 }, { "epoch": 0.33, "learning_rate": 2.5128251445086707e-05, "loss": 0.5663, "step": 1807 }, { "epoch": 0.33, "learning_rate": 2.512554190751445e-05, "loss": 0.9077, "step": 1808 }, { "epoch": 0.33, "learning_rate": 2.5122832369942196e-05, "loss": 0.8385, "step": 1809 }, { "epoch": 0.33, "learning_rate": 2.5120122832369943e-05, "loss": 0.6392, "step": 1810 }, { "epoch": 0.33, "learning_rate": 2.5117413294797688e-05, "loss": 0.9629, "step": 1811 }, { "epoch": 0.33, "learning_rate": 2.5114703757225436e-05, "loss": 0.6958, "step": 1812 }, { "epoch": 0.33, "learning_rate": 2.511199421965318e-05, "loss": 0.9993, "step": 1813 }, { "epoch": 0.33, "learning_rate": 2.5109284682080924e-05, "loss": 0.6317, "step": 1814 }, { "epoch": 0.33, "learning_rate": 2.5106575144508672e-05, "loss": 0.8776, "step": 1815 }, { "epoch": 0.33, "learning_rate": 2.5103865606936416e-05, "loss": 0.8512, "step": 1816 }, { "epoch": 0.33, "learning_rate": 2.5101156069364164e-05, "loss": 0.4037, "step": 1817 }, { "epoch": 0.33, "learning_rate": 2.5098446531791905e-05, "loss": 0.9574, "step": 1818 }, { "epoch": 0.33, "learning_rate": 2.5095736994219653e-05, "loss": 0.8745, "step": 1819 }, { "epoch": 0.33, "learning_rate": 2.50930274566474e-05, "loss": 1.3432, "step": 1820 }, { "epoch": 0.33, "learning_rate": 2.5090317919075145e-05, "loss": 0.4528, "step": 1821 }, { "epoch": 0.33, "learning_rate": 2.5087608381502893e-05, "loss": 0.5211, "step": 1822 }, { "epoch": 0.33, "learning_rate": 2.5084898843930634e-05, "loss": 0.846, "step": 1823 }, { "epoch": 0.33, "learning_rate": 2.508218930635838e-05, "loss": 0.7349, "step": 1824 }, { "epoch": 0.33, "learning_rate": 2.507947976878613e-05, "loss": 0.4327, "step": 1825 }, { "epoch": 0.33, "learning_rate": 2.5076770231213874e-05, "loss": 0.7209, "step": 1826 }, { "epoch": 0.33, "learning_rate": 2.5074060693641618e-05, "loss": 0.5209, "step": 1827 }, { "epoch": 0.33, "learning_rate": 2.5071351156069366e-05, "loss": 1.3101, "step": 1828 }, { "epoch": 0.33, "learning_rate": 2.506864161849711e-05, "loss": 0.4154, "step": 1829 }, { "epoch": 0.33, "learning_rate": 2.5065932080924858e-05, "loss": 0.7968, "step": 1830 }, { "epoch": 0.33, "learning_rate": 2.5063222543352602e-05, "loss": 0.8852, "step": 1831 }, { "epoch": 0.33, "learning_rate": 2.5060513005780347e-05, "loss": 0.6026, "step": 1832 }, { "epoch": 0.33, "learning_rate": 2.5057803468208094e-05, "loss": 0.3166, "step": 1833 }, { "epoch": 0.33, "learning_rate": 2.505509393063584e-05, "loss": 0.4594, "step": 1834 }, { "epoch": 0.33, "learning_rate": 2.5052384393063586e-05, "loss": 1.3807, "step": 1835 }, { "epoch": 0.33, "learning_rate": 2.5049674855491327e-05, "loss": 1.2642, "step": 1836 }, { "epoch": 0.33, "learning_rate": 2.5046965317919075e-05, "loss": 0.7671, "step": 1837 }, { "epoch": 0.33, "learning_rate": 2.5044255780346823e-05, "loss": 0.6037, "step": 1838 }, { "epoch": 0.33, "learning_rate": 2.5041546242774567e-05, "loss": 0.8398, "step": 1839 }, { "epoch": 0.33, "learning_rate": 2.5038836705202315e-05, "loss": 0.6046, "step": 1840 }, { "epoch": 0.33, "learning_rate": 2.5036127167630056e-05, "loss": 0.5274, "step": 1841 }, { "epoch": 0.33, "learning_rate": 2.5033417630057804e-05, "loss": 1.3402, "step": 1842 }, { "epoch": 0.33, "learning_rate": 2.503070809248555e-05, "loss": 0.6941, "step": 1843 }, { "epoch": 0.33, "learning_rate": 2.5027998554913296e-05, "loss": 0.6615, "step": 1844 }, { "epoch": 0.33, "learning_rate": 2.5025289017341044e-05, "loss": 1.0914, "step": 1845 }, { "epoch": 0.33, "learning_rate": 2.5022579479768785e-05, "loss": 1.0214, "step": 1846 }, { "epoch": 0.33, "learning_rate": 2.5019869942196532e-05, "loss": 1.2389, "step": 1847 }, { "epoch": 0.33, "learning_rate": 2.501716040462428e-05, "loss": 1.1106, "step": 1848 }, { "epoch": 0.33, "learning_rate": 2.5014450867052024e-05, "loss": 0.472, "step": 1849 }, { "epoch": 0.33, "learning_rate": 2.501174132947977e-05, "loss": 0.9695, "step": 1850 }, { "epoch": 0.33, "learning_rate": 2.5009031791907513e-05, "loss": 1.2307, "step": 1851 }, { "epoch": 0.33, "learning_rate": 2.500632225433526e-05, "loss": 0.5099, "step": 1852 }, { "epoch": 0.33, "learning_rate": 2.500361271676301e-05, "loss": 0.6609, "step": 1853 }, { "epoch": 0.33, "learning_rate": 2.5000903179190753e-05, "loss": 0.9412, "step": 1854 }, { "epoch": 0.34, "learning_rate": 2.4998193641618497e-05, "loss": 0.7383, "step": 1855 }, { "epoch": 0.34, "learning_rate": 2.4995484104046242e-05, "loss": 0.9187, "step": 1856 }, { "epoch": 0.34, "learning_rate": 2.499277456647399e-05, "loss": 0.5572, "step": 1857 }, { "epoch": 0.34, "learning_rate": 2.4990065028901737e-05, "loss": 0.6279, "step": 1858 }, { "epoch": 0.34, "learning_rate": 2.4987355491329478e-05, "loss": 0.4745, "step": 1859 }, { "epoch": 0.34, "learning_rate": 2.4984645953757226e-05, "loss": 0.5138, "step": 1860 }, { "epoch": 0.34, "learning_rate": 2.498193641618497e-05, "loss": 1.6547, "step": 1861 }, { "epoch": 0.34, "learning_rate": 2.4979226878612718e-05, "loss": 1.9944, "step": 1862 }, { "epoch": 0.34, "learning_rate": 2.4976517341040466e-05, "loss": 0.5965, "step": 1863 }, { "epoch": 0.34, "learning_rate": 2.4973807803468207e-05, "loss": 1.4568, "step": 1864 }, { "epoch": 0.34, "learning_rate": 2.4971098265895955e-05, "loss": 0.695, "step": 1865 }, { "epoch": 0.34, "learning_rate": 2.49683887283237e-05, "loss": 0.4475, "step": 1866 }, { "epoch": 0.34, "learning_rate": 2.4965679190751447e-05, "loss": 0.4985, "step": 1867 }, { "epoch": 0.34, "learning_rate": 2.4962969653179195e-05, "loss": 0.9074, "step": 1868 }, { "epoch": 0.34, "learning_rate": 2.4960260115606935e-05, "loss": 0.836, "step": 1869 }, { "epoch": 0.34, "learning_rate": 2.4957550578034683e-05, "loss": 0.6654, "step": 1870 }, { "epoch": 0.34, "learning_rate": 2.4954841040462428e-05, "loss": 0.4133, "step": 1871 }, { "epoch": 0.34, "learning_rate": 2.4952131502890175e-05, "loss": 0.4735, "step": 1872 }, { "epoch": 0.34, "learning_rate": 2.494942196531792e-05, "loss": 0.7083, "step": 1873 }, { "epoch": 0.34, "learning_rate": 2.4946712427745664e-05, "loss": 1.7712, "step": 1874 }, { "epoch": 0.34, "learning_rate": 2.4944002890173412e-05, "loss": 0.482, "step": 1875 }, { "epoch": 0.34, "learning_rate": 2.4941293352601156e-05, "loss": 0.9262, "step": 1876 }, { "epoch": 0.34, "learning_rate": 2.4938583815028904e-05, "loss": 0.4187, "step": 1877 }, { "epoch": 0.34, "learning_rate": 2.493587427745665e-05, "loss": 0.9708, "step": 1878 }, { "epoch": 0.34, "learning_rate": 2.4933164739884393e-05, "loss": 0.7081, "step": 1879 }, { "epoch": 0.34, "learning_rate": 2.493045520231214e-05, "loss": 1.0943, "step": 1880 }, { "epoch": 0.34, "learning_rate": 2.4927745664739885e-05, "loss": 1.1898, "step": 1881 }, { "epoch": 0.34, "learning_rate": 2.492503612716763e-05, "loss": 1.4532, "step": 1882 }, { "epoch": 0.34, "learning_rate": 2.4922326589595377e-05, "loss": 1.3716, "step": 1883 }, { "epoch": 0.34, "learning_rate": 2.491961705202312e-05, "loss": 0.8498, "step": 1884 }, { "epoch": 0.34, "learning_rate": 2.491690751445087e-05, "loss": 1.0498, "step": 1885 }, { "epoch": 0.34, "learning_rate": 2.4914197976878613e-05, "loss": 0.8763, "step": 1886 }, { "epoch": 0.34, "learning_rate": 2.4911488439306358e-05, "loss": 0.9886, "step": 1887 }, { "epoch": 0.34, "learning_rate": 2.4908778901734106e-05, "loss": 1.6926, "step": 1888 }, { "epoch": 0.34, "learning_rate": 2.490606936416185e-05, "loss": 0.8534, "step": 1889 }, { "epoch": 0.34, "learning_rate": 2.4903359826589598e-05, "loss": 0.9358, "step": 1890 }, { "epoch": 0.34, "learning_rate": 2.4900650289017342e-05, "loss": 1.2855, "step": 1891 }, { "epoch": 0.34, "learning_rate": 2.4897940751445086e-05, "loss": 0.6748, "step": 1892 }, { "epoch": 0.34, "learning_rate": 2.4895231213872834e-05, "loss": 0.5376, "step": 1893 }, { "epoch": 0.34, "learning_rate": 2.489252167630058e-05, "loss": 1.0395, "step": 1894 }, { "epoch": 0.34, "learning_rate": 2.4889812138728326e-05, "loss": 1.042, "step": 1895 }, { "epoch": 0.34, "learning_rate": 2.4887102601156067e-05, "loss": 0.854, "step": 1896 }, { "epoch": 0.34, "learning_rate": 2.4884393063583815e-05, "loss": 0.9974, "step": 1897 }, { "epoch": 0.34, "learning_rate": 2.4881683526011563e-05, "loss": 1.4824, "step": 1898 }, { "epoch": 0.34, "learning_rate": 2.4878973988439307e-05, "loss": 1.5458, "step": 1899 }, { "epoch": 0.34, "learning_rate": 2.4876264450867055e-05, "loss": 0.6983, "step": 1900 }, { "epoch": 0.34, "learning_rate": 2.4873554913294796e-05, "loss": 1.3099, "step": 1901 }, { "epoch": 0.34, "learning_rate": 2.4870845375722544e-05, "loss": 0.9074, "step": 1902 }, { "epoch": 0.34, "learning_rate": 2.486813583815029e-05, "loss": 0.8625, "step": 1903 }, { "epoch": 0.34, "learning_rate": 2.4865426300578036e-05, "loss": 0.8754, "step": 1904 }, { "epoch": 0.34, "learning_rate": 2.486271676300578e-05, "loss": 0.686, "step": 1905 }, { "epoch": 0.34, "learning_rate": 2.4860007225433524e-05, "loss": 0.9185, "step": 1906 }, { "epoch": 0.34, "learning_rate": 2.4857297687861272e-05, "loss": 0.7217, "step": 1907 }, { "epoch": 0.34, "learning_rate": 2.485458815028902e-05, "loss": 1.0671, "step": 1908 }, { "epoch": 0.34, "learning_rate": 2.4851878612716764e-05, "loss": 1.2165, "step": 1909 }, { "epoch": 0.35, "learning_rate": 2.484916907514451e-05, "loss": 0.5603, "step": 1910 }, { "epoch": 0.35, "learning_rate": 2.4846459537572253e-05, "loss": 0.5881, "step": 1911 }, { "epoch": 0.35, "learning_rate": 2.484375e-05, "loss": 0.5333, "step": 1912 }, { "epoch": 0.35, "learning_rate": 2.484104046242775e-05, "loss": 0.9149, "step": 1913 }, { "epoch": 0.35, "learning_rate": 2.4838330924855493e-05, "loss": 0.9876, "step": 1914 }, { "epoch": 0.35, "learning_rate": 2.4835621387283237e-05, "loss": 0.7409, "step": 1915 }, { "epoch": 0.35, "learning_rate": 2.483291184971098e-05, "loss": 0.5736, "step": 1916 }, { "epoch": 0.35, "learning_rate": 2.483020231213873e-05, "loss": 1.1605, "step": 1917 }, { "epoch": 0.35, "learning_rate": 2.4827492774566477e-05, "loss": 1.2376, "step": 1918 }, { "epoch": 0.35, "learning_rate": 2.4824783236994218e-05, "loss": 0.7161, "step": 1919 }, { "epoch": 0.35, "learning_rate": 2.4822073699421966e-05, "loss": 0.999, "step": 1920 }, { "epoch": 0.35, "learning_rate": 2.481936416184971e-05, "loss": 0.8649, "step": 1921 }, { "epoch": 0.35, "learning_rate": 2.4816654624277458e-05, "loss": 0.3997, "step": 1922 }, { "epoch": 0.35, "learning_rate": 2.4813945086705206e-05, "loss": 0.1854, "step": 1923 }, { "epoch": 0.35, "learning_rate": 2.4811235549132947e-05, "loss": 1.5502, "step": 1924 }, { "epoch": 0.35, "learning_rate": 2.4808526011560694e-05, "loss": 0.9373, "step": 1925 }, { "epoch": 0.35, "learning_rate": 2.480581647398844e-05, "loss": 0.6361, "step": 1926 }, { "epoch": 0.35, "learning_rate": 2.4803106936416187e-05, "loss": 0.7694, "step": 1927 }, { "epoch": 0.35, "learning_rate": 2.480039739884393e-05, "loss": 0.8195, "step": 1928 }, { "epoch": 0.35, "learning_rate": 2.4797687861271675e-05, "loss": 1.7553, "step": 1929 }, { "epoch": 0.35, "learning_rate": 2.4794978323699423e-05, "loss": 1.1729, "step": 1930 }, { "epoch": 0.35, "learning_rate": 2.4792268786127167e-05, "loss": 1.4993, "step": 1931 }, { "epoch": 0.35, "learning_rate": 2.4789559248554915e-05, "loss": 1.1992, "step": 1932 }, { "epoch": 0.35, "learning_rate": 2.478684971098266e-05, "loss": 0.8957, "step": 1933 }, { "epoch": 0.35, "learning_rate": 2.4784140173410404e-05, "loss": 0.6772, "step": 1934 }, { "epoch": 0.35, "learning_rate": 2.478143063583815e-05, "loss": 1.0595, "step": 1935 }, { "epoch": 0.35, "learning_rate": 2.4778721098265896e-05, "loss": 0.9244, "step": 1936 }, { "epoch": 0.35, "learning_rate": 2.4776011560693644e-05, "loss": 0.9851, "step": 1937 }, { "epoch": 0.35, "learning_rate": 2.4773302023121388e-05, "loss": 0.9687, "step": 1938 }, { "epoch": 0.35, "learning_rate": 2.4770592485549133e-05, "loss": 0.8151, "step": 1939 }, { "epoch": 0.35, "learning_rate": 2.476788294797688e-05, "loss": 1.0805, "step": 1940 }, { "epoch": 0.35, "learning_rate": 2.4765173410404625e-05, "loss": 0.7996, "step": 1941 }, { "epoch": 0.35, "learning_rate": 2.476246387283237e-05, "loss": 1.3262, "step": 1942 }, { "epoch": 0.35, "learning_rate": 2.4759754335260117e-05, "loss": 0.46, "step": 1943 }, { "epoch": 0.35, "learning_rate": 2.475704479768786e-05, "loss": 0.8947, "step": 1944 }, { "epoch": 0.35, "learning_rate": 2.475433526011561e-05, "loss": 0.7693, "step": 1945 }, { "epoch": 0.35, "learning_rate": 2.4751625722543353e-05, "loss": 0.8737, "step": 1946 }, { "epoch": 0.35, "learning_rate": 2.4748916184971098e-05, "loss": 0.964, "step": 1947 }, { "epoch": 0.35, "learning_rate": 2.4746206647398845e-05, "loss": 1.4441, "step": 1948 }, { "epoch": 0.35, "learning_rate": 2.474349710982659e-05, "loss": 0.8245, "step": 1949 }, { "epoch": 0.35, "learning_rate": 2.4740787572254337e-05, "loss": 0.8611, "step": 1950 }, { "epoch": 0.35, "learning_rate": 2.473807803468208e-05, "loss": 1.2812, "step": 1951 }, { "epoch": 0.35, "learning_rate": 2.4735368497109826e-05, "loss": 1.2574, "step": 1952 }, { "epoch": 0.35, "learning_rate": 2.4732658959537574e-05, "loss": 1.3229, "step": 1953 }, { "epoch": 0.35, "learning_rate": 2.472994942196532e-05, "loss": 0.7459, "step": 1954 }, { "epoch": 0.35, "learning_rate": 2.4727239884393066e-05, "loss": 1.9448, "step": 1955 }, { "epoch": 0.35, "learning_rate": 2.4724530346820807e-05, "loss": 1.4812, "step": 1956 }, { "epoch": 0.35, "learning_rate": 2.4721820809248555e-05, "loss": 0.8376, "step": 1957 }, { "epoch": 0.35, "learning_rate": 2.4719111271676303e-05, "loss": 0.9656, "step": 1958 }, { "epoch": 0.35, "learning_rate": 2.4716401734104047e-05, "loss": 1.0563, "step": 1959 }, { "epoch": 0.35, "learning_rate": 2.4713692196531795e-05, "loss": 1.3686, "step": 1960 }, { "epoch": 0.35, "learning_rate": 2.4710982658959536e-05, "loss": 0.9975, "step": 1961 }, { "epoch": 0.35, "learning_rate": 2.4708273121387283e-05, "loss": 1.0205, "step": 1962 }, { "epoch": 0.35, "learning_rate": 2.470556358381503e-05, "loss": 1.6999, "step": 1963 }, { "epoch": 0.35, "learning_rate": 2.4702854046242776e-05, "loss": 0.7134, "step": 1964 }, { "epoch": 0.35, "learning_rate": 2.470014450867052e-05, "loss": 0.8739, "step": 1965 }, { "epoch": 0.36, "learning_rate": 2.4697434971098264e-05, "loss": 0.9729, "step": 1966 }, { "epoch": 0.36, "learning_rate": 2.4694725433526012e-05, "loss": 1.8493, "step": 1967 }, { "epoch": 0.36, "learning_rate": 2.469201589595376e-05, "loss": 0.8395, "step": 1968 }, { "epoch": 0.36, "learning_rate": 2.4689306358381504e-05, "loss": 1.0887, "step": 1969 }, { "epoch": 0.36, "learning_rate": 2.468659682080925e-05, "loss": 0.9229, "step": 1970 }, { "epoch": 0.36, "learning_rate": 2.4683887283236993e-05, "loss": 0.6536, "step": 1971 }, { "epoch": 0.36, "learning_rate": 2.468117774566474e-05, "loss": 0.8078, "step": 1972 }, { "epoch": 0.36, "learning_rate": 2.467846820809249e-05, "loss": 0.7657, "step": 1973 }, { "epoch": 0.36, "learning_rate": 2.467575867052023e-05, "loss": 1.3238, "step": 1974 }, { "epoch": 0.36, "learning_rate": 2.4673049132947977e-05, "loss": 1.3133, "step": 1975 }, { "epoch": 0.36, "learning_rate": 2.467033959537572e-05, "loss": 0.5039, "step": 1976 }, { "epoch": 0.36, "learning_rate": 2.466763005780347e-05, "loss": 1.5244, "step": 1977 }, { "epoch": 0.36, "learning_rate": 2.4664920520231217e-05, "loss": 0.6084, "step": 1978 }, { "epoch": 0.36, "learning_rate": 2.4662210982658958e-05, "loss": 0.6371, "step": 1979 }, { "epoch": 0.36, "learning_rate": 2.4659501445086706e-05, "loss": 0.8115, "step": 1980 }, { "epoch": 0.36, "learning_rate": 2.465679190751445e-05, "loss": 1.0754, "step": 1981 }, { "epoch": 0.36, "learning_rate": 2.4654082369942198e-05, "loss": 1.0676, "step": 1982 }, { "epoch": 0.36, "learning_rate": 2.4651372832369942e-05, "loss": 0.4255, "step": 1983 }, { "epoch": 0.36, "learning_rate": 2.4648663294797687e-05, "loss": 1.0435, "step": 1984 }, { "epoch": 0.36, "learning_rate": 2.4645953757225434e-05, "loss": 1.6551, "step": 1985 }, { "epoch": 0.36, "learning_rate": 2.464324421965318e-05, "loss": 0.6671, "step": 1986 }, { "epoch": 0.36, "learning_rate": 2.4640534682080926e-05, "loss": 0.6761, "step": 1987 }, { "epoch": 0.36, "learning_rate": 2.463782514450867e-05, "loss": 0.8475, "step": 1988 }, { "epoch": 0.36, "learning_rate": 2.4635115606936415e-05, "loss": 1.4835, "step": 1989 }, { "epoch": 0.36, "learning_rate": 2.4632406069364163e-05, "loss": 0.8658, "step": 1990 }, { "epoch": 0.36, "learning_rate": 2.4629696531791907e-05, "loss": 0.4999, "step": 1991 }, { "epoch": 0.36, "learning_rate": 2.4626986994219655e-05, "loss": 1.2997, "step": 1992 }, { "epoch": 0.36, "learning_rate": 2.46242774566474e-05, "loss": 1.4127, "step": 1993 }, { "epoch": 0.36, "learning_rate": 2.4621567919075144e-05, "loss": 0.9217, "step": 1994 }, { "epoch": 0.36, "learning_rate": 2.461885838150289e-05, "loss": 0.8587, "step": 1995 }, { "epoch": 0.36, "learning_rate": 2.4616148843930636e-05, "loss": 0.6398, "step": 1996 }, { "epoch": 0.36, "learning_rate": 2.461343930635838e-05, "loss": 0.4802, "step": 1997 }, { "epoch": 0.36, "learning_rate": 2.4610729768786128e-05, "loss": 0.4509, "step": 1998 }, { "epoch": 0.36, "learning_rate": 2.4608020231213872e-05, "loss": 0.854, "step": 1999 }, { "epoch": 0.36, "learning_rate": 2.460531069364162e-05, "loss": 1.0031, "step": 2000 }, { "epoch": 0.36, "eval_exact_match": 85.08041627246925, "eval_f1": 91.76915105179167, "step": 2000 }, { "epoch": 0.36, "learning_rate": 2.4602601156069368e-05, "loss": 0.3123, "step": 2001 }, { "epoch": 0.36, "learning_rate": 2.459989161849711e-05, "loss": 1.0401, "step": 2002 }, { "epoch": 0.36, "learning_rate": 2.4597182080924857e-05, "loss": 0.6503, "step": 2003 }, { "epoch": 0.36, "learning_rate": 2.45944725433526e-05, "loss": 0.6173, "step": 2004 }, { "epoch": 0.36, "learning_rate": 2.459176300578035e-05, "loss": 0.9166, "step": 2005 }, { "epoch": 0.36, "learning_rate": 2.4589053468208093e-05, "loss": 1.1677, "step": 2006 }, { "epoch": 0.36, "learning_rate": 2.4586343930635837e-05, "loss": 0.4389, "step": 2007 }, { "epoch": 0.36, "learning_rate": 2.4583634393063585e-05, "loss": 0.8062, "step": 2008 }, { "epoch": 0.36, "learning_rate": 2.458092485549133e-05, "loss": 0.8008, "step": 2009 }, { "epoch": 0.36, "learning_rate": 2.4578215317919077e-05, "loss": 0.6143, "step": 2010 }, { "epoch": 0.36, "learning_rate": 2.457550578034682e-05, "loss": 0.3943, "step": 2011 }, { "epoch": 0.36, "learning_rate": 2.4572796242774566e-05, "loss": 1.2278, "step": 2012 }, { "epoch": 0.36, "learning_rate": 2.4570086705202314e-05, "loss": 0.7256, "step": 2013 }, { "epoch": 0.36, "learning_rate": 2.4567377167630058e-05, "loss": 1.0478, "step": 2014 }, { "epoch": 0.36, "learning_rate": 2.4564667630057806e-05, "loss": 0.7413, "step": 2015 }, { "epoch": 0.36, "learning_rate": 2.456195809248555e-05, "loss": 1.6595, "step": 2016 }, { "epoch": 0.36, "learning_rate": 2.4559248554913295e-05, "loss": 0.7765, "step": 2017 }, { "epoch": 0.36, "learning_rate": 2.4556539017341042e-05, "loss": 0.9836, "step": 2018 }, { "epoch": 0.36, "learning_rate": 2.4553829479768787e-05, "loss": 0.7908, "step": 2019 }, { "epoch": 0.36, "learning_rate": 2.455111994219653e-05, "loss": 1.6788, "step": 2020 }, { "epoch": 0.37, "learning_rate": 2.454841040462428e-05, "loss": 1.2013, "step": 2021 }, { "epoch": 0.37, "learning_rate": 2.4545700867052023e-05, "loss": 0.8964, "step": 2022 }, { "epoch": 0.37, "learning_rate": 2.454299132947977e-05, "loss": 0.6704, "step": 2023 }, { "epoch": 0.37, "learning_rate": 2.4540281791907515e-05, "loss": 1.4036, "step": 2024 }, { "epoch": 0.37, "learning_rate": 2.453757225433526e-05, "loss": 1.0041, "step": 2025 }, { "epoch": 0.37, "learning_rate": 2.4534862716763007e-05, "loss": 0.7592, "step": 2026 }, { "epoch": 0.37, "learning_rate": 2.4532153179190752e-05, "loss": 0.6789, "step": 2027 }, { "epoch": 0.37, "learning_rate": 2.45294436416185e-05, "loss": 0.9736, "step": 2028 }, { "epoch": 0.37, "learning_rate": 2.4526734104046244e-05, "loss": 1.473, "step": 2029 }, { "epoch": 0.37, "learning_rate": 2.452402456647399e-05, "loss": 0.5146, "step": 2030 }, { "epoch": 0.37, "learning_rate": 2.4521315028901736e-05, "loss": 0.3648, "step": 2031 }, { "epoch": 0.37, "learning_rate": 2.451860549132948e-05, "loss": 0.5322, "step": 2032 }, { "epoch": 0.37, "learning_rate": 2.4515895953757228e-05, "loss": 1.1948, "step": 2033 }, { "epoch": 0.37, "learning_rate": 2.451318641618497e-05, "loss": 0.6099, "step": 2034 }, { "epoch": 0.37, "learning_rate": 2.4510476878612717e-05, "loss": 1.1675, "step": 2035 }, { "epoch": 0.37, "learning_rate": 2.4507767341040465e-05, "loss": 1.0169, "step": 2036 }, { "epoch": 0.37, "learning_rate": 2.450505780346821e-05, "loss": 1.1133, "step": 2037 }, { "epoch": 0.37, "learning_rate": 2.4502348265895957e-05, "loss": 0.845, "step": 2038 }, { "epoch": 0.37, "learning_rate": 2.4499638728323698e-05, "loss": 1.1049, "step": 2039 }, { "epoch": 0.37, "learning_rate": 2.4496929190751446e-05, "loss": 0.2133, "step": 2040 }, { "epoch": 0.37, "learning_rate": 2.4494219653179193e-05, "loss": 1.2823, "step": 2041 }, { "epoch": 0.37, "learning_rate": 2.4491510115606938e-05, "loss": 0.2183, "step": 2042 }, { "epoch": 0.37, "learning_rate": 2.4488800578034682e-05, "loss": 1.5034, "step": 2043 }, { "epoch": 0.37, "learning_rate": 2.4486091040462426e-05, "loss": 1.291, "step": 2044 }, { "epoch": 0.37, "learning_rate": 2.4483381502890174e-05, "loss": 0.7353, "step": 2045 }, { "epoch": 0.37, "learning_rate": 2.4480671965317922e-05, "loss": 1.6314, "step": 2046 }, { "epoch": 0.37, "learning_rate": 2.4477962427745666e-05, "loss": 0.5558, "step": 2047 }, { "epoch": 0.37, "learning_rate": 2.447525289017341e-05, "loss": 1.9861, "step": 2048 }, { "epoch": 0.37, "learning_rate": 2.4472543352601155e-05, "loss": 0.7905, "step": 2049 }, { "epoch": 0.37, "learning_rate": 2.4469833815028903e-05, "loss": 1.6157, "step": 2050 }, { "epoch": 0.37, "learning_rate": 2.446712427745665e-05, "loss": 0.6512, "step": 2051 }, { "epoch": 0.37, "learning_rate": 2.446441473988439e-05, "loss": 1.3429, "step": 2052 }, { "epoch": 0.37, "learning_rate": 2.446170520231214e-05, "loss": 1.2704, "step": 2053 }, { "epoch": 0.37, "learning_rate": 2.4458995664739884e-05, "loss": 1.1745, "step": 2054 }, { "epoch": 0.37, "learning_rate": 2.445628612716763e-05, "loss": 0.793, "step": 2055 }, { "epoch": 0.37, "learning_rate": 2.445357658959538e-05, "loss": 0.6421, "step": 2056 }, { "epoch": 0.37, "learning_rate": 2.445086705202312e-05, "loss": 1.4013, "step": 2057 }, { "epoch": 0.37, "learning_rate": 2.4448157514450868e-05, "loss": 1.3231, "step": 2058 }, { "epoch": 0.37, "learning_rate": 2.4445447976878612e-05, "loss": 0.4297, "step": 2059 }, { "epoch": 0.37, "learning_rate": 2.444273843930636e-05, "loss": 0.6096, "step": 2060 }, { "epoch": 0.37, "learning_rate": 2.4440028901734108e-05, "loss": 1.2101, "step": 2061 }, { "epoch": 0.37, "learning_rate": 2.443731936416185e-05, "loss": 0.6504, "step": 2062 }, { "epoch": 0.37, "learning_rate": 2.4434609826589596e-05, "loss": 0.9447, "step": 2063 }, { "epoch": 0.37, "learning_rate": 2.443190028901734e-05, "loss": 1.4093, "step": 2064 }, { "epoch": 0.37, "learning_rate": 2.442919075144509e-05, "loss": 1.5111, "step": 2065 }, { "epoch": 0.37, "learning_rate": 2.4426481213872833e-05, "loss": 0.4627, "step": 2066 }, { "epoch": 0.37, "learning_rate": 2.4423771676300577e-05, "loss": 0.7184, "step": 2067 }, { "epoch": 0.37, "learning_rate": 2.4421062138728325e-05, "loss": 0.9554, "step": 2068 }, { "epoch": 0.37, "learning_rate": 2.441835260115607e-05, "loss": 1.0063, "step": 2069 }, { "epoch": 0.37, "learning_rate": 2.4415643063583817e-05, "loss": 0.3453, "step": 2070 }, { "epoch": 0.37, "learning_rate": 2.441293352601156e-05, "loss": 0.8835, "step": 2071 }, { "epoch": 0.37, "learning_rate": 2.4410223988439306e-05, "loss": 1.0891, "step": 2072 }, { "epoch": 0.37, "learning_rate": 2.4407514450867054e-05, "loss": 0.6011, "step": 2073 }, { "epoch": 0.37, "learning_rate": 2.4404804913294798e-05, "loss": 0.941, "step": 2074 }, { "epoch": 0.37, "learning_rate": 2.4402095375722542e-05, "loss": 1.5638, "step": 2075 }, { "epoch": 0.38, "learning_rate": 2.439938583815029e-05, "loss": 1.0932, "step": 2076 }, { "epoch": 0.38, "learning_rate": 2.4396676300578034e-05, "loss": 0.5231, "step": 2077 }, { "epoch": 0.38, "learning_rate": 2.4393966763005782e-05, "loss": 1.48, "step": 2078 }, { "epoch": 0.38, "learning_rate": 2.4391257225433527e-05, "loss": 0.805, "step": 2079 }, { "epoch": 0.38, "learning_rate": 2.438854768786127e-05, "loss": 0.8545, "step": 2080 }, { "epoch": 0.38, "learning_rate": 2.438583815028902e-05, "loss": 1.1326, "step": 2081 }, { "epoch": 0.38, "learning_rate": 2.4383128612716763e-05, "loss": 0.6323, "step": 2082 }, { "epoch": 0.38, "learning_rate": 2.438041907514451e-05, "loss": 1.4259, "step": 2083 }, { "epoch": 0.38, "learning_rate": 2.4377709537572255e-05, "loss": 0.7326, "step": 2084 }, { "epoch": 0.38, "learning_rate": 2.4375e-05, "loss": 1.1086, "step": 2085 }, { "epoch": 0.38, "learning_rate": 2.4372290462427747e-05, "loss": 0.8031, "step": 2086 }, { "epoch": 0.38, "learning_rate": 2.436958092485549e-05, "loss": 0.5449, "step": 2087 }, { "epoch": 0.38, "learning_rate": 2.436687138728324e-05, "loss": 0.3419, "step": 2088 }, { "epoch": 0.38, "learning_rate": 2.436416184971098e-05, "loss": 1.1579, "step": 2089 }, { "epoch": 0.38, "learning_rate": 2.4361452312138728e-05, "loss": 0.9605, "step": 2090 }, { "epoch": 0.38, "learning_rate": 2.4358742774566476e-05, "loss": 1.6988, "step": 2091 }, { "epoch": 0.38, "learning_rate": 2.435603323699422e-05, "loss": 1.1566, "step": 2092 }, { "epoch": 0.38, "learning_rate": 2.4353323699421968e-05, "loss": 1.1716, "step": 2093 }, { "epoch": 0.38, "learning_rate": 2.435061416184971e-05, "loss": 0.5915, "step": 2094 }, { "epoch": 0.38, "learning_rate": 2.4347904624277457e-05, "loss": 0.6387, "step": 2095 }, { "epoch": 0.38, "learning_rate": 2.4345195086705205e-05, "loss": 1.0115, "step": 2096 }, { "epoch": 0.38, "learning_rate": 2.434248554913295e-05, "loss": 0.573, "step": 2097 }, { "epoch": 0.38, "learning_rate": 2.4339776011560693e-05, "loss": 0.9463, "step": 2098 }, { "epoch": 0.38, "learning_rate": 2.4337066473988438e-05, "loss": 0.785, "step": 2099 }, { "epoch": 0.38, "learning_rate": 2.4334356936416185e-05, "loss": 1.172, "step": 2100 }, { "epoch": 0.38, "learning_rate": 2.4331647398843933e-05, "loss": 0.6146, "step": 2101 }, { "epoch": 0.38, "learning_rate": 2.4328937861271677e-05, "loss": 0.9124, "step": 2102 }, { "epoch": 0.38, "learning_rate": 2.4326228323699422e-05, "loss": 0.4828, "step": 2103 }, { "epoch": 0.38, "learning_rate": 2.4323518786127166e-05, "loss": 0.6057, "step": 2104 }, { "epoch": 0.38, "learning_rate": 2.4320809248554914e-05, "loss": 1.2012, "step": 2105 }, { "epoch": 0.38, "learning_rate": 2.4318099710982662e-05, "loss": 0.7735, "step": 2106 }, { "epoch": 0.38, "learning_rate": 2.4315390173410406e-05, "loss": 0.4558, "step": 2107 }, { "epoch": 0.38, "learning_rate": 2.431268063583815e-05, "loss": 1.1098, "step": 2108 }, { "epoch": 0.38, "learning_rate": 2.4309971098265895e-05, "loss": 0.9146, "step": 2109 }, { "epoch": 0.38, "learning_rate": 2.4307261560693643e-05, "loss": 0.8114, "step": 2110 }, { "epoch": 0.38, "learning_rate": 2.430455202312139e-05, "loss": 0.4064, "step": 2111 }, { "epoch": 0.38, "learning_rate": 2.430184248554913e-05, "loss": 0.9092, "step": 2112 }, { "epoch": 0.38, "learning_rate": 2.429913294797688e-05, "loss": 0.8224, "step": 2113 }, { "epoch": 0.38, "learning_rate": 2.4296423410404623e-05, "loss": 1.795, "step": 2114 }, { "epoch": 0.38, "learning_rate": 2.429371387283237e-05, "loss": 0.4604, "step": 2115 }, { "epoch": 0.38, "learning_rate": 2.429100433526012e-05, "loss": 1.0319, "step": 2116 }, { "epoch": 0.38, "learning_rate": 2.428829479768786e-05, "loss": 0.946, "step": 2117 }, { "epoch": 0.38, "learning_rate": 2.4285585260115608e-05, "loss": 0.465, "step": 2118 }, { "epoch": 0.38, "learning_rate": 2.4282875722543352e-05, "loss": 0.6135, "step": 2119 }, { "epoch": 0.38, "learning_rate": 2.42801661849711e-05, "loss": 0.97, "step": 2120 }, { "epoch": 0.38, "learning_rate": 2.4277456647398844e-05, "loss": 1.3979, "step": 2121 }, { "epoch": 0.38, "learning_rate": 2.427474710982659e-05, "loss": 0.9976, "step": 2122 }, { "epoch": 0.38, "learning_rate": 2.4272037572254336e-05, "loss": 0.6445, "step": 2123 }, { "epoch": 0.38, "learning_rate": 2.426932803468208e-05, "loss": 1.2015, "step": 2124 }, { "epoch": 0.38, "learning_rate": 2.426661849710983e-05, "loss": 1.319, "step": 2125 }, { "epoch": 0.38, "learning_rate": 2.4263908959537573e-05, "loss": 0.9892, "step": 2126 }, { "epoch": 0.38, "learning_rate": 2.4261199421965317e-05, "loss": 1.0978, "step": 2127 }, { "epoch": 0.38, "learning_rate": 2.4258489884393065e-05, "loss": 1.0504, "step": 2128 }, { "epoch": 0.38, "learning_rate": 2.425578034682081e-05, "loss": 0.8773, "step": 2129 }, { "epoch": 0.38, "learning_rate": 2.4253070809248557e-05, "loss": 0.8752, "step": 2130 }, { "epoch": 0.38, "learning_rate": 2.42503612716763e-05, "loss": 1.0243, "step": 2131 }, { "epoch": 0.39, "learning_rate": 2.4247651734104046e-05, "loss": 1.063, "step": 2132 }, { "epoch": 0.39, "learning_rate": 2.4244942196531793e-05, "loss": 0.9936, "step": 2133 }, { "epoch": 0.39, "learning_rate": 2.4242232658959538e-05, "loss": 1.0553, "step": 2134 }, { "epoch": 0.39, "learning_rate": 2.4239523121387282e-05, "loss": 1.2361, "step": 2135 }, { "epoch": 0.39, "learning_rate": 2.423681358381503e-05, "loss": 0.9079, "step": 2136 }, { "epoch": 0.39, "learning_rate": 2.4234104046242774e-05, "loss": 0.948, "step": 2137 }, { "epoch": 0.39, "learning_rate": 2.4231394508670522e-05, "loss": 0.5012, "step": 2138 }, { "epoch": 0.39, "learning_rate": 2.4228684971098266e-05, "loss": 0.7597, "step": 2139 }, { "epoch": 0.39, "learning_rate": 2.422597543352601e-05, "loss": 0.9243, "step": 2140 }, { "epoch": 0.39, "learning_rate": 2.422326589595376e-05, "loss": 0.4128, "step": 2141 }, { "epoch": 0.39, "learning_rate": 2.4220556358381503e-05, "loss": 1.1445, "step": 2142 }, { "epoch": 0.39, "learning_rate": 2.421784682080925e-05, "loss": 0.4904, "step": 2143 }, { "epoch": 0.39, "learning_rate": 2.421513728323699e-05, "loss": 1.0459, "step": 2144 }, { "epoch": 0.39, "learning_rate": 2.421242774566474e-05, "loss": 1.1408, "step": 2145 }, { "epoch": 0.39, "learning_rate": 2.4209718208092487e-05, "loss": 0.9902, "step": 2146 }, { "epoch": 0.39, "learning_rate": 2.420700867052023e-05, "loss": 1.0591, "step": 2147 }, { "epoch": 0.39, "learning_rate": 2.420429913294798e-05, "loss": 0.8135, "step": 2148 }, { "epoch": 0.39, "learning_rate": 2.420158959537572e-05, "loss": 1.9239, "step": 2149 }, { "epoch": 0.39, "learning_rate": 2.4198880057803468e-05, "loss": 0.4619, "step": 2150 }, { "epoch": 0.39, "learning_rate": 2.4196170520231216e-05, "loss": 1.2352, "step": 2151 }, { "epoch": 0.39, "learning_rate": 2.419346098265896e-05, "loss": 0.9298, "step": 2152 }, { "epoch": 0.39, "learning_rate": 2.4190751445086708e-05, "loss": 0.9256, "step": 2153 }, { "epoch": 0.39, "learning_rate": 2.418804190751445e-05, "loss": 1.3799, "step": 2154 }, { "epoch": 0.39, "learning_rate": 2.4185332369942197e-05, "loss": 0.4484, "step": 2155 }, { "epoch": 0.39, "learning_rate": 2.4182622832369944e-05, "loss": 0.5521, "step": 2156 }, { "epoch": 0.39, "learning_rate": 2.417991329479769e-05, "loss": 0.844, "step": 2157 }, { "epoch": 0.39, "learning_rate": 2.4177203757225433e-05, "loss": 0.9112, "step": 2158 }, { "epoch": 0.39, "learning_rate": 2.4174494219653177e-05, "loss": 1.1769, "step": 2159 }, { "epoch": 0.39, "learning_rate": 2.4171784682080925e-05, "loss": 1.0662, "step": 2160 }, { "epoch": 0.39, "learning_rate": 2.4169075144508673e-05, "loss": 1.4241, "step": 2161 }, { "epoch": 0.39, "learning_rate": 2.4166365606936417e-05, "loss": 0.6717, "step": 2162 }, { "epoch": 0.39, "learning_rate": 2.416365606936416e-05, "loss": 0.7051, "step": 2163 }, { "epoch": 0.39, "learning_rate": 2.4160946531791906e-05, "loss": 1.203, "step": 2164 }, { "epoch": 0.39, "learning_rate": 2.4158236994219654e-05, "loss": 1.1558, "step": 2165 }, { "epoch": 0.39, "learning_rate": 2.41555274566474e-05, "loss": 0.9307, "step": 2166 }, { "epoch": 0.39, "learning_rate": 2.4152817919075143e-05, "loss": 1.2971, "step": 2167 }, { "epoch": 0.39, "learning_rate": 2.415010838150289e-05, "loss": 1.4759, "step": 2168 }, { "epoch": 0.39, "learning_rate": 2.4147398843930635e-05, "loss": 0.6742, "step": 2169 }, { "epoch": 0.39, "learning_rate": 2.4144689306358382e-05, "loss": 0.7801, "step": 2170 }, { "epoch": 0.39, "learning_rate": 2.414197976878613e-05, "loss": 0.4742, "step": 2171 }, { "epoch": 0.39, "learning_rate": 2.413927023121387e-05, "loss": 0.4187, "step": 2172 }, { "epoch": 0.39, "learning_rate": 2.413656069364162e-05, "loss": 0.7735, "step": 2173 }, { "epoch": 0.39, "learning_rate": 2.4133851156069367e-05, "loss": 0.9267, "step": 2174 }, { "epoch": 0.39, "learning_rate": 2.413114161849711e-05, "loss": 0.7838, "step": 2175 }, { "epoch": 0.39, "learning_rate": 2.412843208092486e-05, "loss": 0.6535, "step": 2176 }, { "epoch": 0.39, "learning_rate": 2.41257225433526e-05, "loss": 0.7771, "step": 2177 }, { "epoch": 0.39, "learning_rate": 2.4123013005780347e-05, "loss": 1.091, "step": 2178 }, { "epoch": 0.39, "learning_rate": 2.4120303468208095e-05, "loss": 0.6613, "step": 2179 }, { "epoch": 0.39, "learning_rate": 2.411759393063584e-05, "loss": 1.6389, "step": 2180 }, { "epoch": 0.39, "learning_rate": 2.4114884393063584e-05, "loss": 0.6896, "step": 2181 }, { "epoch": 0.39, "learning_rate": 2.411217485549133e-05, "loss": 0.7863, "step": 2182 }, { "epoch": 0.39, "learning_rate": 2.4109465317919076e-05, "loss": 0.4612, "step": 2183 }, { "epoch": 0.39, "learning_rate": 2.4106755780346824e-05, "loss": 1.7122, "step": 2184 }, { "epoch": 0.39, "learning_rate": 2.4104046242774568e-05, "loss": 0.9463, "step": 2185 }, { "epoch": 0.39, "learning_rate": 2.4101336705202313e-05, "loss": 0.4634, "step": 2186 }, { "epoch": 0.4, "learning_rate": 2.4098627167630057e-05, "loss": 0.9706, "step": 2187 }, { "epoch": 0.4, "learning_rate": 2.4095917630057805e-05, "loss": 0.5678, "step": 2188 }, { "epoch": 0.4, "learning_rate": 2.4093208092485552e-05, "loss": 0.9599, "step": 2189 }, { "epoch": 0.4, "learning_rate": 2.4090498554913293e-05, "loss": 1.1868, "step": 2190 }, { "epoch": 0.4, "learning_rate": 2.408778901734104e-05, "loss": 1.0537, "step": 2191 }, { "epoch": 0.4, "learning_rate": 2.4085079479768786e-05, "loss": 0.9366, "step": 2192 }, { "epoch": 0.4, "learning_rate": 2.4082369942196533e-05, "loss": 0.9168, "step": 2193 }, { "epoch": 0.4, "learning_rate": 2.407966040462428e-05, "loss": 0.798, "step": 2194 }, { "epoch": 0.4, "learning_rate": 2.4076950867052022e-05, "loss": 1.0124, "step": 2195 }, { "epoch": 0.4, "learning_rate": 2.407424132947977e-05, "loss": 1.042, "step": 2196 }, { "epoch": 0.4, "learning_rate": 2.4071531791907514e-05, "loss": 0.9173, "step": 2197 }, { "epoch": 0.4, "learning_rate": 2.4068822254335262e-05, "loss": 0.4778, "step": 2198 }, { "epoch": 0.4, "learning_rate": 2.406611271676301e-05, "loss": 0.3393, "step": 2199 }, { "epoch": 0.4, "learning_rate": 2.406340317919075e-05, "loss": 1.1578, "step": 2200 }, { "epoch": 0.4, "learning_rate": 2.40606936416185e-05, "loss": 0.8478, "step": 2201 }, { "epoch": 0.4, "learning_rate": 2.4057984104046243e-05, "loss": 0.8845, "step": 2202 }, { "epoch": 0.4, "learning_rate": 2.405527456647399e-05, "loss": 1.0315, "step": 2203 }, { "epoch": 0.4, "learning_rate": 2.4052565028901735e-05, "loss": 0.6088, "step": 2204 }, { "epoch": 0.4, "learning_rate": 2.404985549132948e-05, "loss": 2.0378, "step": 2205 }, { "epoch": 0.4, "learning_rate": 2.4047145953757227e-05, "loss": 0.3914, "step": 2206 }, { "epoch": 0.4, "learning_rate": 2.404443641618497e-05, "loss": 0.7876, "step": 2207 }, { "epoch": 0.4, "learning_rate": 2.404172687861272e-05, "loss": 0.5949, "step": 2208 }, { "epoch": 0.4, "learning_rate": 2.4039017341040463e-05, "loss": 1.2263, "step": 2209 }, { "epoch": 0.4, "learning_rate": 2.4036307803468208e-05, "loss": 0.6923, "step": 2210 }, { "epoch": 0.4, "learning_rate": 2.4033598265895956e-05, "loss": 1.1182, "step": 2211 }, { "epoch": 0.4, "learning_rate": 2.40308887283237e-05, "loss": 1.4171, "step": 2212 }, { "epoch": 0.4, "learning_rate": 2.4028179190751444e-05, "loss": 0.6755, "step": 2213 }, { "epoch": 0.4, "learning_rate": 2.4025469653179192e-05, "loss": 0.3283, "step": 2214 }, { "epoch": 0.4, "learning_rate": 2.4022760115606936e-05, "loss": 0.3809, "step": 2215 }, { "epoch": 0.4, "learning_rate": 2.4020050578034684e-05, "loss": 1.2211, "step": 2216 }, { "epoch": 0.4, "learning_rate": 2.401734104046243e-05, "loss": 1.0165, "step": 2217 }, { "epoch": 0.4, "learning_rate": 2.4014631502890173e-05, "loss": 0.1487, "step": 2218 }, { "epoch": 0.4, "learning_rate": 2.401192196531792e-05, "loss": 0.7797, "step": 2219 }, { "epoch": 0.4, "learning_rate": 2.4009212427745665e-05, "loss": 1.3475, "step": 2220 }, { "epoch": 0.4, "learning_rate": 2.4006502890173413e-05, "loss": 0.8372, "step": 2221 }, { "epoch": 0.4, "learning_rate": 2.4003793352601157e-05, "loss": 0.6801, "step": 2222 }, { "epoch": 0.4, "learning_rate": 2.40010838150289e-05, "loss": 0.6254, "step": 2223 }, { "epoch": 0.4, "learning_rate": 2.399837427745665e-05, "loss": 0.8192, "step": 2224 }, { "epoch": 0.4, "learning_rate": 2.3995664739884394e-05, "loss": 0.5986, "step": 2225 }, { "epoch": 0.4, "learning_rate": 2.399295520231214e-05, "loss": 0.6879, "step": 2226 }, { "epoch": 0.4, "learning_rate": 2.3990245664739882e-05, "loss": 1.0363, "step": 2227 }, { "epoch": 0.4, "learning_rate": 2.398753612716763e-05, "loss": 0.4677, "step": 2228 }, { "epoch": 0.4, "learning_rate": 2.3984826589595378e-05, "loss": 0.8528, "step": 2229 }, { "epoch": 0.4, "learning_rate": 2.3982117052023122e-05, "loss": 1.3407, "step": 2230 }, { "epoch": 0.4, "learning_rate": 2.397940751445087e-05, "loss": 1.3909, "step": 2231 }, { "epoch": 0.4, "learning_rate": 2.397669797687861e-05, "loss": 0.7763, "step": 2232 }, { "epoch": 0.4, "learning_rate": 2.397398843930636e-05, "loss": 1.5203, "step": 2233 }, { "epoch": 0.4, "learning_rate": 2.3971278901734106e-05, "loss": 0.2861, "step": 2234 }, { "epoch": 0.4, "learning_rate": 2.396856936416185e-05, "loss": 0.6663, "step": 2235 }, { "epoch": 0.4, "learning_rate": 2.3965859826589595e-05, "loss": 0.5137, "step": 2236 }, { "epoch": 0.4, "learning_rate": 2.396315028901734e-05, "loss": 0.4466, "step": 2237 }, { "epoch": 0.4, "learning_rate": 2.3960440751445087e-05, "loss": 1.0527, "step": 2238 }, { "epoch": 0.4, "learning_rate": 2.3957731213872835e-05, "loss": 0.8825, "step": 2239 }, { "epoch": 0.4, "learning_rate": 2.395502167630058e-05, "loss": 1.1466, "step": 2240 }, { "epoch": 0.4, "learning_rate": 2.3952312138728324e-05, "loss": 0.774, "step": 2241 }, { "epoch": 0.4, "learning_rate": 2.3949602601156068e-05, "loss": 0.6695, "step": 2242 }, { "epoch": 0.41, "learning_rate": 2.3946893063583816e-05, "loss": 0.4393, "step": 2243 }, { "epoch": 0.41, "learning_rate": 2.3944183526011564e-05, "loss": 1.4559, "step": 2244 }, { "epoch": 0.41, "learning_rate": 2.3941473988439308e-05, "loss": 1.3434, "step": 2245 }, { "epoch": 0.41, "learning_rate": 2.3938764450867052e-05, "loss": 1.5152, "step": 2246 }, { "epoch": 0.41, "learning_rate": 2.3936054913294797e-05, "loss": 0.6253, "step": 2247 }, { "epoch": 0.41, "learning_rate": 2.3933345375722545e-05, "loss": 1.0568, "step": 2248 }, { "epoch": 0.41, "learning_rate": 2.3930635838150292e-05, "loss": 1.0749, "step": 2249 }, { "epoch": 0.41, "learning_rate": 2.3927926300578033e-05, "loss": 0.3769, "step": 2250 }, { "epoch": 0.41, "learning_rate": 2.392521676300578e-05, "loss": 1.1188, "step": 2251 }, { "epoch": 0.41, "learning_rate": 2.3922507225433525e-05, "loss": 0.8118, "step": 2252 }, { "epoch": 0.41, "learning_rate": 2.3919797687861273e-05, "loss": 1.1149, "step": 2253 }, { "epoch": 0.41, "learning_rate": 2.391708815028902e-05, "loss": 1.6488, "step": 2254 }, { "epoch": 0.41, "learning_rate": 2.3914378612716762e-05, "loss": 0.7773, "step": 2255 }, { "epoch": 0.41, "learning_rate": 2.391166907514451e-05, "loss": 0.9267, "step": 2256 }, { "epoch": 0.41, "learning_rate": 2.3908959537572254e-05, "loss": 0.74, "step": 2257 }, { "epoch": 0.41, "learning_rate": 2.3906250000000002e-05, "loss": 0.8853, "step": 2258 }, { "epoch": 0.41, "learning_rate": 2.3903540462427746e-05, "loss": 0.9863, "step": 2259 }, { "epoch": 0.41, "learning_rate": 2.390083092485549e-05, "loss": 1.4407, "step": 2260 }, { "epoch": 0.41, "learning_rate": 2.3898121387283238e-05, "loss": 1.1277, "step": 2261 }, { "epoch": 0.41, "learning_rate": 2.3895411849710983e-05, "loss": 1.2692, "step": 2262 }, { "epoch": 0.41, "learning_rate": 2.389270231213873e-05, "loss": 1.0589, "step": 2263 }, { "epoch": 0.41, "learning_rate": 2.3889992774566475e-05, "loss": 0.8531, "step": 2264 }, { "epoch": 0.41, "learning_rate": 2.388728323699422e-05, "loss": 0.5184, "step": 2265 }, { "epoch": 0.41, "learning_rate": 2.3884573699421967e-05, "loss": 0.7704, "step": 2266 }, { "epoch": 0.41, "learning_rate": 2.388186416184971e-05, "loss": 0.7615, "step": 2267 }, { "epoch": 0.41, "learning_rate": 2.3879154624277456e-05, "loss": 0.7893, "step": 2268 }, { "epoch": 0.41, "learning_rate": 2.3876445086705203e-05, "loss": 0.9983, "step": 2269 }, { "epoch": 0.41, "learning_rate": 2.3873735549132948e-05, "loss": 0.8566, "step": 2270 }, { "epoch": 0.41, "learning_rate": 2.3871026011560695e-05, "loss": 0.8427, "step": 2271 }, { "epoch": 0.41, "learning_rate": 2.386831647398844e-05, "loss": 1.0154, "step": 2272 }, { "epoch": 0.41, "learning_rate": 2.3865606936416184e-05, "loss": 0.7591, "step": 2273 }, { "epoch": 0.41, "learning_rate": 2.3862897398843932e-05, "loss": 0.8443, "step": 2274 }, { "epoch": 0.41, "learning_rate": 2.3860187861271676e-05, "loss": 0.8125, "step": 2275 }, { "epoch": 0.41, "learning_rate": 2.3857478323699424e-05, "loss": 0.7411, "step": 2276 }, { "epoch": 0.41, "learning_rate": 2.385476878612717e-05, "loss": 0.515, "step": 2277 }, { "epoch": 0.41, "learning_rate": 2.3852059248554913e-05, "loss": 0.7851, "step": 2278 }, { "epoch": 0.41, "learning_rate": 2.384934971098266e-05, "loss": 1.3559, "step": 2279 }, { "epoch": 0.41, "learning_rate": 2.3846640173410405e-05, "loss": 1.0678, "step": 2280 }, { "epoch": 0.41, "learning_rate": 2.3843930635838153e-05, "loss": 0.6283, "step": 2281 }, { "epoch": 0.41, "learning_rate": 2.3841221098265894e-05, "loss": 1.0405, "step": 2282 }, { "epoch": 0.41, "learning_rate": 2.383851156069364e-05, "loss": 0.6624, "step": 2283 }, { "epoch": 0.41, "learning_rate": 2.383580202312139e-05, "loss": 1.2553, "step": 2284 }, { "epoch": 0.41, "learning_rate": 2.3833092485549133e-05, "loss": 0.6769, "step": 2285 }, { "epoch": 0.41, "learning_rate": 2.383038294797688e-05, "loss": 0.6424, "step": 2286 }, { "epoch": 0.41, "learning_rate": 2.3827673410404622e-05, "loss": 0.4977, "step": 2287 }, { "epoch": 0.41, "learning_rate": 2.382496387283237e-05, "loss": 0.6904, "step": 2288 }, { "epoch": 0.41, "learning_rate": 2.3822254335260118e-05, "loss": 1.0417, "step": 2289 }, { "epoch": 0.41, "learning_rate": 2.3819544797687862e-05, "loss": 0.6518, "step": 2290 }, { "epoch": 0.41, "learning_rate": 2.3816835260115606e-05, "loss": 0.4924, "step": 2291 }, { "epoch": 0.41, "learning_rate": 2.381412572254335e-05, "loss": 0.6299, "step": 2292 }, { "epoch": 0.41, "learning_rate": 2.38114161849711e-05, "loss": 0.4887, "step": 2293 }, { "epoch": 0.41, "learning_rate": 2.3808706647398846e-05, "loss": 1.0712, "step": 2294 }, { "epoch": 0.41, "learning_rate": 2.380599710982659e-05, "loss": 1.6863, "step": 2295 }, { "epoch": 0.41, "learning_rate": 2.3803287572254335e-05, "loss": 0.8985, "step": 2296 }, { "epoch": 0.41, "learning_rate": 2.380057803468208e-05, "loss": 0.8948, "step": 2297 }, { "epoch": 0.42, "learning_rate": 2.3797868497109827e-05, "loss": 1.478, "step": 2298 }, { "epoch": 0.42, "learning_rate": 2.3795158959537575e-05, "loss": 0.494, "step": 2299 }, { "epoch": 0.42, "learning_rate": 2.379244942196532e-05, "loss": 1.2252, "step": 2300 }, { "epoch": 0.42, "learning_rate": 2.3789739884393064e-05, "loss": 0.7106, "step": 2301 }, { "epoch": 0.42, "learning_rate": 2.3787030346820808e-05, "loss": 0.81, "step": 2302 }, { "epoch": 0.42, "learning_rate": 2.3784320809248556e-05, "loss": 0.3517, "step": 2303 }, { "epoch": 0.42, "learning_rate": 2.3781611271676303e-05, "loss": 0.8057, "step": 2304 }, { "epoch": 0.42, "learning_rate": 2.3778901734104044e-05, "loss": 1.1562, "step": 2305 }, { "epoch": 0.42, "learning_rate": 2.3776192196531792e-05, "loss": 0.8414, "step": 2306 }, { "epoch": 0.42, "learning_rate": 2.3773482658959537e-05, "loss": 0.6391, "step": 2307 }, { "epoch": 0.42, "learning_rate": 2.3770773121387284e-05, "loss": 0.6547, "step": 2308 }, { "epoch": 0.42, "learning_rate": 2.3768063583815032e-05, "loss": 0.965, "step": 2309 }, { "epoch": 0.42, "learning_rate": 2.3765354046242773e-05, "loss": 0.7541, "step": 2310 }, { "epoch": 0.42, "learning_rate": 2.376264450867052e-05, "loss": 0.4476, "step": 2311 }, { "epoch": 0.42, "learning_rate": 2.3759934971098265e-05, "loss": 0.699, "step": 2312 }, { "epoch": 0.42, "learning_rate": 2.3757225433526013e-05, "loss": 0.5458, "step": 2313 }, { "epoch": 0.42, "learning_rate": 2.3754515895953757e-05, "loss": 1.3223, "step": 2314 }, { "epoch": 0.42, "learning_rate": 2.37518063583815e-05, "loss": 0.6745, "step": 2315 }, { "epoch": 0.42, "learning_rate": 2.374909682080925e-05, "loss": 0.8549, "step": 2316 }, { "epoch": 0.42, "learning_rate": 2.3746387283236994e-05, "loss": 0.698, "step": 2317 }, { "epoch": 0.42, "learning_rate": 2.374367774566474e-05, "loss": 0.4399, "step": 2318 }, { "epoch": 0.42, "learning_rate": 2.3740968208092486e-05, "loss": 0.4084, "step": 2319 }, { "epoch": 0.42, "learning_rate": 2.373825867052023e-05, "loss": 0.5776, "step": 2320 }, { "epoch": 0.42, "learning_rate": 2.3735549132947978e-05, "loss": 1.3151, "step": 2321 }, { "epoch": 0.42, "learning_rate": 2.3732839595375722e-05, "loss": 1.4962, "step": 2322 }, { "epoch": 0.42, "learning_rate": 2.373013005780347e-05, "loss": 1.0671, "step": 2323 }, { "epoch": 0.42, "learning_rate": 2.3727420520231215e-05, "loss": 0.9718, "step": 2324 }, { "epoch": 0.42, "learning_rate": 2.372471098265896e-05, "loss": 0.9381, "step": 2325 }, { "epoch": 0.42, "learning_rate": 2.3722001445086707e-05, "loss": 0.6626, "step": 2326 }, { "epoch": 0.42, "learning_rate": 2.371929190751445e-05, "loss": 0.6582, "step": 2327 }, { "epoch": 0.42, "learning_rate": 2.3716582369942195e-05, "loss": 1.0879, "step": 2328 }, { "epoch": 0.42, "learning_rate": 2.3713872832369943e-05, "loss": 0.5553, "step": 2329 }, { "epoch": 0.42, "learning_rate": 2.3711163294797687e-05, "loss": 0.5163, "step": 2330 }, { "epoch": 0.42, "learning_rate": 2.3708453757225435e-05, "loss": 0.7533, "step": 2331 }, { "epoch": 0.42, "learning_rate": 2.370574421965318e-05, "loss": 0.67, "step": 2332 }, { "epoch": 0.42, "learning_rate": 2.3703034682080924e-05, "loss": 0.4876, "step": 2333 }, { "epoch": 0.42, "learning_rate": 2.3700325144508672e-05, "loss": 0.7012, "step": 2334 }, { "epoch": 0.42, "learning_rate": 2.3697615606936416e-05, "loss": 0.5958, "step": 2335 }, { "epoch": 0.42, "learning_rate": 2.3694906069364164e-05, "loss": 0.922, "step": 2336 }, { "epoch": 0.42, "learning_rate": 2.3692196531791905e-05, "loss": 0.4124, "step": 2337 }, { "epoch": 0.42, "learning_rate": 2.3689486994219653e-05, "loss": 1.5968, "step": 2338 }, { "epoch": 0.42, "learning_rate": 2.36867774566474e-05, "loss": 0.4457, "step": 2339 }, { "epoch": 0.42, "learning_rate": 2.3684067919075145e-05, "loss": 0.8543, "step": 2340 }, { "epoch": 0.42, "learning_rate": 2.3681358381502892e-05, "loss": 0.6407, "step": 2341 }, { "epoch": 0.42, "learning_rate": 2.3678648843930633e-05, "loss": 0.3085, "step": 2342 }, { "epoch": 0.42, "learning_rate": 2.367593930635838e-05, "loss": 1.0511, "step": 2343 }, { "epoch": 0.42, "learning_rate": 2.367322976878613e-05, "loss": 1.1915, "step": 2344 }, { "epoch": 0.42, "learning_rate": 2.3670520231213873e-05, "loss": 0.8717, "step": 2345 }, { "epoch": 0.42, "learning_rate": 2.366781069364162e-05, "loss": 0.9863, "step": 2346 }, { "epoch": 0.42, "learning_rate": 2.3665101156069365e-05, "loss": 1.7131, "step": 2347 }, { "epoch": 0.42, "learning_rate": 2.366239161849711e-05, "loss": 0.6866, "step": 2348 }, { "epoch": 0.42, "learning_rate": 2.3659682080924858e-05, "loss": 1.3835, "step": 2349 }, { "epoch": 0.42, "learning_rate": 2.3656972543352602e-05, "loss": 0.7095, "step": 2350 }, { "epoch": 0.42, "learning_rate": 2.3654263005780346e-05, "loss": 1.0297, "step": 2351 }, { "epoch": 0.42, "learning_rate": 2.3651553468208094e-05, "loss": 0.4993, "step": 2352 }, { "epoch": 0.43, "learning_rate": 2.364884393063584e-05, "loss": 1.4262, "step": 2353 }, { "epoch": 0.43, "learning_rate": 2.3646134393063586e-05, "loss": 0.9255, "step": 2354 }, { "epoch": 0.43, "learning_rate": 2.364342485549133e-05, "loss": 0.6302, "step": 2355 }, { "epoch": 0.43, "learning_rate": 2.3640715317919075e-05, "loss": 0.9321, "step": 2356 }, { "epoch": 0.43, "learning_rate": 2.3638005780346823e-05, "loss": 0.6278, "step": 2357 }, { "epoch": 0.43, "learning_rate": 2.3635296242774567e-05, "loss": 0.5954, "step": 2358 }, { "epoch": 0.43, "learning_rate": 2.3632586705202315e-05, "loss": 1.227, "step": 2359 }, { "epoch": 0.43, "learning_rate": 2.3629877167630056e-05, "loss": 1.2472, "step": 2360 }, { "epoch": 0.43, "learning_rate": 2.3627167630057803e-05, "loss": 0.6629, "step": 2361 }, { "epoch": 0.43, "learning_rate": 2.362445809248555e-05, "loss": 1.07, "step": 2362 }, { "epoch": 0.43, "learning_rate": 2.3621748554913296e-05, "loss": 0.9078, "step": 2363 }, { "epoch": 0.43, "learning_rate": 2.3619039017341043e-05, "loss": 0.8414, "step": 2364 }, { "epoch": 0.43, "learning_rate": 2.3616329479768784e-05, "loss": 0.6535, "step": 2365 }, { "epoch": 0.43, "learning_rate": 2.3613619942196532e-05, "loss": 0.81, "step": 2366 }, { "epoch": 0.43, "learning_rate": 2.361091040462428e-05, "loss": 0.9607, "step": 2367 }, { "epoch": 0.43, "learning_rate": 2.3608200867052024e-05, "loss": 1.0141, "step": 2368 }, { "epoch": 0.43, "learning_rate": 2.3605491329479772e-05, "loss": 1.223, "step": 2369 }, { "epoch": 0.43, "learning_rate": 2.3602781791907513e-05, "loss": 0.5488, "step": 2370 }, { "epoch": 0.43, "learning_rate": 2.360007225433526e-05, "loss": 0.9656, "step": 2371 }, { "epoch": 0.43, "learning_rate": 2.359736271676301e-05, "loss": 1.3574, "step": 2372 }, { "epoch": 0.43, "learning_rate": 2.3594653179190753e-05, "loss": 0.4694, "step": 2373 }, { "epoch": 0.43, "learning_rate": 2.3591943641618497e-05, "loss": 1.2159, "step": 2374 }, { "epoch": 0.43, "learning_rate": 2.358923410404624e-05, "loss": 0.5014, "step": 2375 }, { "epoch": 0.43, "learning_rate": 2.358652456647399e-05, "loss": 0.7752, "step": 2376 }, { "epoch": 0.43, "learning_rate": 2.3583815028901737e-05, "loss": 0.6136, "step": 2377 }, { "epoch": 0.43, "learning_rate": 2.358110549132948e-05, "loss": 0.7696, "step": 2378 }, { "epoch": 0.43, "learning_rate": 2.3578395953757226e-05, "loss": 1.3975, "step": 2379 }, { "epoch": 0.43, "learning_rate": 2.357568641618497e-05, "loss": 0.8659, "step": 2380 }, { "epoch": 0.43, "learning_rate": 2.3572976878612718e-05, "loss": 1.1994, "step": 2381 }, { "epoch": 0.43, "learning_rate": 2.3570267341040466e-05, "loss": 1.0539, "step": 2382 }, { "epoch": 0.43, "learning_rate": 2.3567557803468207e-05, "loss": 1.0488, "step": 2383 }, { "epoch": 0.43, "learning_rate": 2.3564848265895954e-05, "loss": 0.6945, "step": 2384 }, { "epoch": 0.43, "learning_rate": 2.35621387283237e-05, "loss": 1.0175, "step": 2385 }, { "epoch": 0.43, "learning_rate": 2.3559429190751446e-05, "loss": 0.8483, "step": 2386 }, { "epoch": 0.43, "learning_rate": 2.3556719653179194e-05, "loss": 0.5737, "step": 2387 }, { "epoch": 0.43, "learning_rate": 2.3554010115606935e-05, "loss": 0.8048, "step": 2388 }, { "epoch": 0.43, "learning_rate": 2.3551300578034683e-05, "loss": 0.8118, "step": 2389 }, { "epoch": 0.43, "learning_rate": 2.3548591040462427e-05, "loss": 1.157, "step": 2390 }, { "epoch": 0.43, "learning_rate": 2.3545881502890175e-05, "loss": 0.8057, "step": 2391 }, { "epoch": 0.43, "learning_rate": 2.3543171965317923e-05, "loss": 0.7212, "step": 2392 }, { "epoch": 0.43, "learning_rate": 2.3540462427745664e-05, "loss": 1.2324, "step": 2393 }, { "epoch": 0.43, "learning_rate": 2.353775289017341e-05, "loss": 0.9386, "step": 2394 }, { "epoch": 0.43, "learning_rate": 2.3535043352601156e-05, "loss": 0.4559, "step": 2395 }, { "epoch": 0.43, "learning_rate": 2.3532333815028904e-05, "loss": 1.1608, "step": 2396 }, { "epoch": 0.43, "learning_rate": 2.3529624277456648e-05, "loss": 0.6469, "step": 2397 }, { "epoch": 0.43, "learning_rate": 2.3526914739884392e-05, "loss": 1.1948, "step": 2398 }, { "epoch": 0.43, "learning_rate": 2.352420520231214e-05, "loss": 1.5434, "step": 2399 }, { "epoch": 0.43, "learning_rate": 2.3521495664739885e-05, "loss": 0.9487, "step": 2400 }, { "epoch": 0.43, "learning_rate": 2.3518786127167632e-05, "loss": 1.462, "step": 2401 }, { "epoch": 0.43, "learning_rate": 2.3516076589595377e-05, "loss": 0.6634, "step": 2402 }, { "epoch": 0.43, "learning_rate": 2.351336705202312e-05, "loss": 0.7179, "step": 2403 }, { "epoch": 0.43, "learning_rate": 2.351065751445087e-05, "loss": 0.6108, "step": 2404 }, { "epoch": 0.43, "learning_rate": 2.3507947976878613e-05, "loss": 0.9558, "step": 2405 }, { "epoch": 0.43, "learning_rate": 2.3505238439306357e-05, "loss": 1.4024, "step": 2406 }, { "epoch": 0.43, "learning_rate": 2.3502528901734105e-05, "loss": 0.9678, "step": 2407 }, { "epoch": 0.43, "learning_rate": 2.349981936416185e-05, "loss": 0.4765, "step": 2408 }, { "epoch": 0.44, "learning_rate": 2.3497109826589597e-05, "loss": 0.9297, "step": 2409 }, { "epoch": 0.44, "learning_rate": 2.3494400289017342e-05, "loss": 0.4281, "step": 2410 }, { "epoch": 0.44, "learning_rate": 2.3491690751445086e-05, "loss": 0.9161, "step": 2411 }, { "epoch": 0.44, "learning_rate": 2.3488981213872834e-05, "loss": 0.7081, "step": 2412 }, { "epoch": 0.44, "learning_rate": 2.3486271676300578e-05, "loss": 0.8026, "step": 2413 }, { "epoch": 0.44, "learning_rate": 2.3483562138728326e-05, "loss": 0.5926, "step": 2414 }, { "epoch": 0.44, "learning_rate": 2.348085260115607e-05, "loss": 1.4427, "step": 2415 }, { "epoch": 0.44, "learning_rate": 2.3478143063583815e-05, "loss": 1.0346, "step": 2416 }, { "epoch": 0.44, "learning_rate": 2.3475433526011562e-05, "loss": 1.1705, "step": 2417 }, { "epoch": 0.44, "learning_rate": 2.3472723988439307e-05, "loss": 1.4388, "step": 2418 }, { "epoch": 0.44, "learning_rate": 2.3470014450867055e-05, "loss": 0.4176, "step": 2419 }, { "epoch": 0.44, "learning_rate": 2.3467304913294796e-05, "loss": 0.9048, "step": 2420 }, { "epoch": 0.44, "learning_rate": 2.3464595375722543e-05, "loss": 0.8327, "step": 2421 }, { "epoch": 0.44, "learning_rate": 2.346188583815029e-05, "loss": 0.6488, "step": 2422 }, { "epoch": 0.44, "learning_rate": 2.3459176300578035e-05, "loss": 0.6456, "step": 2423 }, { "epoch": 0.44, "learning_rate": 2.3456466763005783e-05, "loss": 0.8756, "step": 2424 }, { "epoch": 0.44, "learning_rate": 2.3453757225433524e-05, "loss": 1.4454, "step": 2425 }, { "epoch": 0.44, "learning_rate": 2.3451047687861272e-05, "loss": 1.0663, "step": 2426 }, { "epoch": 0.44, "learning_rate": 2.344833815028902e-05, "loss": 0.8531, "step": 2427 }, { "epoch": 0.44, "learning_rate": 2.3445628612716764e-05, "loss": 1.0233, "step": 2428 }, { "epoch": 0.44, "learning_rate": 2.344291907514451e-05, "loss": 1.464, "step": 2429 }, { "epoch": 0.44, "learning_rate": 2.3440209537572253e-05, "loss": 0.9402, "step": 2430 }, { "epoch": 0.44, "learning_rate": 2.34375e-05, "loss": 0.4884, "step": 2431 }, { "epoch": 0.44, "learning_rate": 2.3434790462427748e-05, "loss": 0.7241, "step": 2432 }, { "epoch": 0.44, "learning_rate": 2.3432080924855493e-05, "loss": 0.4456, "step": 2433 }, { "epoch": 0.44, "learning_rate": 2.3429371387283237e-05, "loss": 1.4244, "step": 2434 }, { "epoch": 0.44, "learning_rate": 2.342666184971098e-05, "loss": 1.4202, "step": 2435 }, { "epoch": 0.44, "learning_rate": 2.342395231213873e-05, "loss": 0.4657, "step": 2436 }, { "epoch": 0.44, "learning_rate": 2.3421242774566477e-05, "loss": 0.6979, "step": 2437 }, { "epoch": 0.44, "learning_rate": 2.341853323699422e-05, "loss": 0.9787, "step": 2438 }, { "epoch": 0.44, "learning_rate": 2.3415823699421966e-05, "loss": 0.984, "step": 2439 }, { "epoch": 0.44, "learning_rate": 2.341311416184971e-05, "loss": 0.8948, "step": 2440 }, { "epoch": 0.44, "learning_rate": 2.3410404624277458e-05, "loss": 0.9703, "step": 2441 }, { "epoch": 0.44, "learning_rate": 2.3407695086705205e-05, "loss": 0.4961, "step": 2442 }, { "epoch": 0.44, "learning_rate": 2.3404985549132946e-05, "loss": 0.7847, "step": 2443 }, { "epoch": 0.44, "learning_rate": 2.3402276011560694e-05, "loss": 0.6185, "step": 2444 }, { "epoch": 0.44, "learning_rate": 2.339956647398844e-05, "loss": 0.9681, "step": 2445 }, { "epoch": 0.44, "learning_rate": 2.3396856936416186e-05, "loss": 0.5755, "step": 2446 }, { "epoch": 0.44, "learning_rate": 2.3394147398843934e-05, "loss": 0.4063, "step": 2447 }, { "epoch": 0.44, "learning_rate": 2.3391437861271675e-05, "loss": 0.6898, "step": 2448 }, { "epoch": 0.44, "learning_rate": 2.3388728323699423e-05, "loss": 1.0302, "step": 2449 }, { "epoch": 0.44, "learning_rate": 2.3386018786127167e-05, "loss": 1.2452, "step": 2450 }, { "epoch": 0.44, "learning_rate": 2.3383309248554915e-05, "loss": 0.8525, "step": 2451 }, { "epoch": 0.44, "learning_rate": 2.338059971098266e-05, "loss": 1.1648, "step": 2452 }, { "epoch": 0.44, "learning_rate": 2.3377890173410404e-05, "loss": 0.3564, "step": 2453 }, { "epoch": 0.44, "learning_rate": 2.337518063583815e-05, "loss": 1.3695, "step": 2454 }, { "epoch": 0.44, "learning_rate": 2.3372471098265896e-05, "loss": 1.3467, "step": 2455 }, { "epoch": 0.44, "learning_rate": 2.3369761560693643e-05, "loss": 0.8432, "step": 2456 }, { "epoch": 0.44, "learning_rate": 2.3367052023121388e-05, "loss": 0.7, "step": 2457 }, { "epoch": 0.44, "learning_rate": 2.3364342485549132e-05, "loss": 0.9137, "step": 2458 }, { "epoch": 0.44, "learning_rate": 2.336163294797688e-05, "loss": 1.1732, "step": 2459 }, { "epoch": 0.44, "learning_rate": 2.3358923410404624e-05, "loss": 0.7324, "step": 2460 }, { "epoch": 0.44, "learning_rate": 2.3356213872832372e-05, "loss": 0.7109, "step": 2461 }, { "epoch": 0.44, "learning_rate": 2.3353504335260116e-05, "loss": 1.8007, "step": 2462 }, { "epoch": 0.44, "learning_rate": 2.335079479768786e-05, "loss": 0.5448, "step": 2463 }, { "epoch": 0.45, "learning_rate": 2.334808526011561e-05, "loss": 0.7493, "step": 2464 }, { "epoch": 0.45, "learning_rate": 2.3345375722543353e-05, "loss": 1.9571, "step": 2465 }, { "epoch": 0.45, "learning_rate": 2.3342666184971097e-05, "loss": 1.0316, "step": 2466 }, { "epoch": 0.45, "learning_rate": 2.3339956647398845e-05, "loss": 1.0472, "step": 2467 }, { "epoch": 0.45, "learning_rate": 2.333724710982659e-05, "loss": 0.4828, "step": 2468 }, { "epoch": 0.45, "learning_rate": 2.3334537572254337e-05, "loss": 0.9694, "step": 2469 }, { "epoch": 0.45, "learning_rate": 2.333182803468208e-05, "loss": 0.7117, "step": 2470 }, { "epoch": 0.45, "learning_rate": 2.3329118497109826e-05, "loss": 0.6235, "step": 2471 }, { "epoch": 0.45, "learning_rate": 2.3326408959537574e-05, "loss": 1.3115, "step": 2472 }, { "epoch": 0.45, "learning_rate": 2.3323699421965318e-05, "loss": 0.7326, "step": 2473 }, { "epoch": 0.45, "learning_rate": 2.3320989884393066e-05, "loss": 0.8077, "step": 2474 }, { "epoch": 0.45, "learning_rate": 2.3318280346820807e-05, "loss": 0.9419, "step": 2475 }, { "epoch": 0.45, "learning_rate": 2.3315570809248555e-05, "loss": 1.5196, "step": 2476 }, { "epoch": 0.45, "learning_rate": 2.3312861271676302e-05, "loss": 1.0314, "step": 2477 }, { "epoch": 0.45, "learning_rate": 2.3310151734104047e-05, "loss": 0.9204, "step": 2478 }, { "epoch": 0.45, "learning_rate": 2.3307442196531794e-05, "loss": 0.5548, "step": 2479 }, { "epoch": 0.45, "learning_rate": 2.3304732658959535e-05, "loss": 0.4587, "step": 2480 }, { "epoch": 0.45, "learning_rate": 2.3302023121387283e-05, "loss": 0.9014, "step": 2481 }, { "epoch": 0.45, "learning_rate": 2.329931358381503e-05, "loss": 0.4563, "step": 2482 }, { "epoch": 0.45, "learning_rate": 2.3296604046242775e-05, "loss": 1.3411, "step": 2483 }, { "epoch": 0.45, "learning_rate": 2.329389450867052e-05, "loss": 0.7672, "step": 2484 }, { "epoch": 0.45, "learning_rate": 2.3291184971098264e-05, "loss": 1.0714, "step": 2485 }, { "epoch": 0.45, "learning_rate": 2.3288475433526012e-05, "loss": 0.8904, "step": 2486 }, { "epoch": 0.45, "learning_rate": 2.328576589595376e-05, "loss": 0.6602, "step": 2487 }, { "epoch": 0.45, "learning_rate": 2.3283056358381504e-05, "loss": 1.0119, "step": 2488 }, { "epoch": 0.45, "learning_rate": 2.3280346820809248e-05, "loss": 1.5387, "step": 2489 }, { "epoch": 0.45, "learning_rate": 2.3277637283236993e-05, "loss": 0.9492, "step": 2490 }, { "epoch": 0.45, "learning_rate": 2.327492774566474e-05, "loss": 1.2846, "step": 2491 }, { "epoch": 0.45, "learning_rate": 2.3272218208092488e-05, "loss": 0.7206, "step": 2492 }, { "epoch": 0.45, "learning_rate": 2.3269508670520232e-05, "loss": 0.8129, "step": 2493 }, { "epoch": 0.45, "learning_rate": 2.3266799132947977e-05, "loss": 1.1883, "step": 2494 }, { "epoch": 0.45, "learning_rate": 2.326408959537572e-05, "loss": 0.7221, "step": 2495 }, { "epoch": 0.45, "learning_rate": 2.326138005780347e-05, "loss": 1.2838, "step": 2496 }, { "epoch": 0.45, "learning_rate": 2.3258670520231217e-05, "loss": 1.312, "step": 2497 }, { "epoch": 0.45, "learning_rate": 2.3255960982658958e-05, "loss": 0.8487, "step": 2498 }, { "epoch": 0.45, "learning_rate": 2.3253251445086705e-05, "loss": 1.0324, "step": 2499 }, { "epoch": 0.45, "learning_rate": 2.325054190751445e-05, "loss": 0.8299, "step": 2500 }, { "epoch": 0.45, "eval_exact_match": 85.61021759697256, "eval_f1": 92.20706739316813, "step": 2500 }, { "epoch": 0.45, "learning_rate": 2.3247832369942198e-05, "loss": 0.6599, "step": 2501 }, { "epoch": 0.45, "learning_rate": 2.3245122832369945e-05, "loss": 1.2588, "step": 2502 }, { "epoch": 0.45, "learning_rate": 2.3242413294797686e-05, "loss": 1.1297, "step": 2503 }, { "epoch": 0.45, "learning_rate": 2.3239703757225434e-05, "loss": 1.4214, "step": 2504 }, { "epoch": 0.45, "learning_rate": 2.323699421965318e-05, "loss": 1.0886, "step": 2505 }, { "epoch": 0.45, "learning_rate": 2.3234284682080926e-05, "loss": 0.6612, "step": 2506 }, { "epoch": 0.45, "learning_rate": 2.323157514450867e-05, "loss": 0.9316, "step": 2507 }, { "epoch": 0.45, "learning_rate": 2.3228865606936415e-05, "loss": 1.0068, "step": 2508 }, { "epoch": 0.45, "learning_rate": 2.3226156069364163e-05, "loss": 1.2385, "step": 2509 }, { "epoch": 0.45, "learning_rate": 2.3223446531791907e-05, "loss": 0.6797, "step": 2510 }, { "epoch": 0.45, "learning_rate": 2.3220736994219655e-05, "loss": 1.1805, "step": 2511 }, { "epoch": 0.45, "learning_rate": 2.32180274566474e-05, "loss": 0.622, "step": 2512 }, { "epoch": 0.45, "learning_rate": 2.3215317919075143e-05, "loss": 0.7723, "step": 2513 }, { "epoch": 0.45, "learning_rate": 2.321260838150289e-05, "loss": 1.0333, "step": 2514 }, { "epoch": 0.45, "learning_rate": 2.3209898843930636e-05, "loss": 0.7795, "step": 2515 }, { "epoch": 0.45, "learning_rate": 2.3207189306358383e-05, "loss": 1.1058, "step": 2516 }, { "epoch": 0.45, "learning_rate": 2.3204479768786128e-05, "loss": 0.8148, "step": 2517 }, { "epoch": 0.45, "learning_rate": 2.3201770231213872e-05, "loss": 1.0708, "step": 2518 }, { "epoch": 0.46, "learning_rate": 2.319906069364162e-05, "loss": 0.6862, "step": 2519 }, { "epoch": 0.46, "learning_rate": 2.3196351156069368e-05, "loss": 0.6865, "step": 2520 }, { "epoch": 0.46, "learning_rate": 2.319364161849711e-05, "loss": 0.6866, "step": 2521 }, { "epoch": 0.46, "learning_rate": 2.3190932080924856e-05, "loss": 0.9166, "step": 2522 }, { "epoch": 0.46, "learning_rate": 2.31882225433526e-05, "loss": 1.1275, "step": 2523 }, { "epoch": 0.46, "learning_rate": 2.318551300578035e-05, "loss": 0.6565, "step": 2524 }, { "epoch": 0.46, "learning_rate": 2.3182803468208096e-05, "loss": 1.4827, "step": 2525 }, { "epoch": 0.46, "learning_rate": 2.3180093930635837e-05, "loss": 0.8482, "step": 2526 }, { "epoch": 0.46, "learning_rate": 2.3177384393063585e-05, "loss": 0.3265, "step": 2527 }, { "epoch": 0.46, "learning_rate": 2.317467485549133e-05, "loss": 1.2924, "step": 2528 }, { "epoch": 0.46, "learning_rate": 2.3171965317919077e-05, "loss": 0.945, "step": 2529 }, { "epoch": 0.46, "learning_rate": 2.316925578034682e-05, "loss": 0.9158, "step": 2530 }, { "epoch": 0.46, "learning_rate": 2.3166546242774566e-05, "loss": 1.1355, "step": 2531 }, { "epoch": 0.46, "learning_rate": 2.3163836705202313e-05, "loss": 1.2017, "step": 2532 }, { "epoch": 0.46, "learning_rate": 2.3161127167630058e-05, "loss": 0.3384, "step": 2533 }, { "epoch": 0.46, "learning_rate": 2.3158417630057806e-05, "loss": 0.9288, "step": 2534 }, { "epoch": 0.46, "learning_rate": 2.315570809248555e-05, "loss": 1.5087, "step": 2535 }, { "epoch": 0.46, "learning_rate": 2.3152998554913294e-05, "loss": 0.6407, "step": 2536 }, { "epoch": 0.46, "learning_rate": 2.3150289017341042e-05, "loss": 0.5439, "step": 2537 }, { "epoch": 0.46, "learning_rate": 2.3147579479768786e-05, "loss": 0.948, "step": 2538 }, { "epoch": 0.46, "learning_rate": 2.3144869942196534e-05, "loss": 0.7795, "step": 2539 }, { "epoch": 0.46, "learning_rate": 2.314216040462428e-05, "loss": 0.6617, "step": 2540 }, { "epoch": 0.46, "learning_rate": 2.3139450867052023e-05, "loss": 0.7971, "step": 2541 }, { "epoch": 0.46, "learning_rate": 2.313674132947977e-05, "loss": 0.378, "step": 2542 }, { "epoch": 0.46, "learning_rate": 2.3134031791907515e-05, "loss": 0.8849, "step": 2543 }, { "epoch": 0.46, "learning_rate": 2.313132225433526e-05, "loss": 0.954, "step": 2544 }, { "epoch": 0.46, "learning_rate": 2.3128612716763007e-05, "loss": 0.8756, "step": 2545 }, { "epoch": 0.46, "learning_rate": 2.312590317919075e-05, "loss": 0.9095, "step": 2546 }, { "epoch": 0.46, "learning_rate": 2.31231936416185e-05, "loss": 1.2684, "step": 2547 }, { "epoch": 0.46, "learning_rate": 2.3120484104046244e-05, "loss": 0.7743, "step": 2548 }, { "epoch": 0.46, "learning_rate": 2.3117774566473988e-05, "loss": 0.5241, "step": 2549 }, { "epoch": 0.46, "learning_rate": 2.3115065028901736e-05, "loss": 0.4007, "step": 2550 }, { "epoch": 0.46, "learning_rate": 2.311235549132948e-05, "loss": 1.2782, "step": 2551 }, { "epoch": 0.46, "learning_rate": 2.3109645953757228e-05, "loss": 0.629, "step": 2552 }, { "epoch": 0.46, "learning_rate": 2.310693641618497e-05, "loss": 0.6624, "step": 2553 }, { "epoch": 0.46, "learning_rate": 2.3104226878612717e-05, "loss": 1.1006, "step": 2554 }, { "epoch": 0.46, "learning_rate": 2.3101517341040464e-05, "loss": 0.8676, "step": 2555 }, { "epoch": 0.46, "learning_rate": 2.309880780346821e-05, "loss": 0.6845, "step": 2556 }, { "epoch": 0.46, "learning_rate": 2.3096098265895957e-05, "loss": 0.7093, "step": 2557 }, { "epoch": 0.46, "learning_rate": 2.3093388728323697e-05, "loss": 0.6327, "step": 2558 }, { "epoch": 0.46, "learning_rate": 2.3090679190751445e-05, "loss": 0.3499, "step": 2559 }, { "epoch": 0.46, "learning_rate": 2.3087969653179193e-05, "loss": 0.5956, "step": 2560 }, { "epoch": 0.46, "learning_rate": 2.3085260115606937e-05, "loss": 0.5709, "step": 2561 }, { "epoch": 0.46, "learning_rate": 2.3082550578034685e-05, "loss": 0.8265, "step": 2562 }, { "epoch": 0.46, "learning_rate": 2.3079841040462426e-05, "loss": 0.2804, "step": 2563 }, { "epoch": 0.46, "learning_rate": 2.3077131502890174e-05, "loss": 1.2984, "step": 2564 }, { "epoch": 0.46, "learning_rate": 2.307442196531792e-05, "loss": 0.8131, "step": 2565 }, { "epoch": 0.46, "learning_rate": 2.3071712427745666e-05, "loss": 0.8591, "step": 2566 }, { "epoch": 0.46, "learning_rate": 2.306900289017341e-05, "loss": 0.9674, "step": 2567 }, { "epoch": 0.46, "learning_rate": 2.3066293352601155e-05, "loss": 1.1199, "step": 2568 }, { "epoch": 0.46, "learning_rate": 2.3063583815028902e-05, "loss": 0.762, "step": 2569 }, { "epoch": 0.46, "learning_rate": 2.306087427745665e-05, "loss": 0.563, "step": 2570 }, { "epoch": 0.46, "learning_rate": 2.3058164739884395e-05, "loss": 0.5749, "step": 2571 }, { "epoch": 0.46, "learning_rate": 2.305545520231214e-05, "loss": 0.8643, "step": 2572 }, { "epoch": 0.46, "learning_rate": 2.3052745664739883e-05, "loss": 1.241, "step": 2573 }, { "epoch": 0.46, "learning_rate": 2.305003612716763e-05, "loss": 1.0022, "step": 2574 }, { "epoch": 0.47, "learning_rate": 2.304732658959538e-05, "loss": 0.9609, "step": 2575 }, { "epoch": 0.47, "learning_rate": 2.304461705202312e-05, "loss": 0.3318, "step": 2576 }, { "epoch": 0.47, "learning_rate": 2.3041907514450868e-05, "loss": 0.647, "step": 2577 }, { "epoch": 0.47, "learning_rate": 2.3039197976878612e-05, "loss": 0.8416, "step": 2578 }, { "epoch": 0.47, "learning_rate": 2.303648843930636e-05, "loss": 1.7066, "step": 2579 }, { "epoch": 0.47, "learning_rate": 2.3033778901734107e-05, "loss": 1.4847, "step": 2580 }, { "epoch": 0.47, "learning_rate": 2.303106936416185e-05, "loss": 0.6874, "step": 2581 }, { "epoch": 0.47, "learning_rate": 2.3028359826589596e-05, "loss": 1.4114, "step": 2582 }, { "epoch": 0.47, "learning_rate": 2.302565028901734e-05, "loss": 1.2664, "step": 2583 }, { "epoch": 0.47, "learning_rate": 2.3022940751445088e-05, "loss": 0.4838, "step": 2584 }, { "epoch": 0.47, "learning_rate": 2.3020231213872836e-05, "loss": 1.1857, "step": 2585 }, { "epoch": 0.47, "learning_rate": 2.3017521676300577e-05, "loss": 0.8523, "step": 2586 }, { "epoch": 0.47, "learning_rate": 2.3014812138728325e-05, "loss": 0.4801, "step": 2587 }, { "epoch": 0.47, "learning_rate": 2.301210260115607e-05, "loss": 0.5523, "step": 2588 }, { "epoch": 0.47, "learning_rate": 2.3009393063583817e-05, "loss": 0.5531, "step": 2589 }, { "epoch": 0.47, "learning_rate": 2.300668352601156e-05, "loss": 0.6501, "step": 2590 }, { "epoch": 0.47, "learning_rate": 2.3003973988439306e-05, "loss": 0.6912, "step": 2591 }, { "epoch": 0.47, "learning_rate": 2.3001264450867053e-05, "loss": 1.2384, "step": 2592 }, { "epoch": 0.47, "learning_rate": 2.2998554913294798e-05, "loss": 0.9413, "step": 2593 }, { "epoch": 0.47, "learning_rate": 2.2995845375722545e-05, "loss": 1.2739, "step": 2594 }, { "epoch": 0.47, "learning_rate": 2.299313583815029e-05, "loss": 0.5922, "step": 2595 }, { "epoch": 0.47, "learning_rate": 2.2990426300578034e-05, "loss": 0.7125, "step": 2596 }, { "epoch": 0.47, "learning_rate": 2.2987716763005782e-05, "loss": 0.612, "step": 2597 }, { "epoch": 0.47, "learning_rate": 2.2985007225433526e-05, "loss": 0.9231, "step": 2598 }, { "epoch": 0.47, "learning_rate": 2.298229768786127e-05, "loss": 1.2842, "step": 2599 }, { "epoch": 0.47, "learning_rate": 2.297958815028902e-05, "loss": 1.1956, "step": 2600 }, { "epoch": 0.47, "learning_rate": 2.2976878612716763e-05, "loss": 0.8935, "step": 2601 }, { "epoch": 0.47, "learning_rate": 2.297416907514451e-05, "loss": 2.4609, "step": 2602 }, { "epoch": 0.47, "learning_rate": 2.2971459537572255e-05, "loss": 0.4969, "step": 2603 }, { "epoch": 0.47, "learning_rate": 2.296875e-05, "loss": 1.1137, "step": 2604 }, { "epoch": 0.47, "learning_rate": 2.2966040462427747e-05, "loss": 0.8202, "step": 2605 }, { "epoch": 0.47, "learning_rate": 2.296333092485549e-05, "loss": 1.4998, "step": 2606 }, { "epoch": 0.47, "learning_rate": 2.296062138728324e-05, "loss": 0.5011, "step": 2607 }, { "epoch": 0.47, "learning_rate": 2.2957911849710983e-05, "loss": 1.1175, "step": 2608 }, { "epoch": 0.47, "learning_rate": 2.2955202312138728e-05, "loss": 1.2693, "step": 2609 }, { "epoch": 0.47, "learning_rate": 2.2952492774566476e-05, "loss": 0.6809, "step": 2610 }, { "epoch": 0.47, "learning_rate": 2.294978323699422e-05, "loss": 0.8584, "step": 2611 }, { "epoch": 0.47, "learning_rate": 2.2947073699421968e-05, "loss": 0.4834, "step": 2612 }, { "epoch": 0.47, "learning_rate": 2.294436416184971e-05, "loss": 0.5237, "step": 2613 }, { "epoch": 0.47, "learning_rate": 2.2941654624277456e-05, "loss": 0.4043, "step": 2614 }, { "epoch": 0.47, "learning_rate": 2.2938945086705204e-05, "loss": 0.7908, "step": 2615 }, { "epoch": 0.47, "learning_rate": 2.293623554913295e-05, "loss": 0.7198, "step": 2616 }, { "epoch": 0.47, "learning_rate": 2.2933526011560696e-05, "loss": 1.0059, "step": 2617 }, { "epoch": 0.47, "learning_rate": 2.2930816473988437e-05, "loss": 0.7562, "step": 2618 }, { "epoch": 0.47, "learning_rate": 2.2928106936416185e-05, "loss": 1.1125, "step": 2619 }, { "epoch": 0.47, "learning_rate": 2.2925397398843933e-05, "loss": 0.3011, "step": 2620 }, { "epoch": 0.47, "learning_rate": 2.2922687861271677e-05, "loss": 0.6656, "step": 2621 }, { "epoch": 0.47, "learning_rate": 2.291997832369942e-05, "loss": 0.8796, "step": 2622 }, { "epoch": 0.47, "learning_rate": 2.2917268786127166e-05, "loss": 0.3852, "step": 2623 }, { "epoch": 0.47, "learning_rate": 2.2914559248554914e-05, "loss": 0.7869, "step": 2624 }, { "epoch": 0.47, "learning_rate": 2.291184971098266e-05, "loss": 1.2857, "step": 2625 }, { "epoch": 0.47, "learning_rate": 2.2909140173410406e-05, "loss": 1.1269, "step": 2626 }, { "epoch": 0.47, "learning_rate": 2.290643063583815e-05, "loss": 0.9345, "step": 2627 }, { "epoch": 0.47, "learning_rate": 2.2903721098265895e-05, "loss": 0.9562, "step": 2628 }, { "epoch": 0.47, "learning_rate": 2.2901011560693642e-05, "loss": 0.8192, "step": 2629 }, { "epoch": 0.48, "learning_rate": 2.289830202312139e-05, "loss": 1.5817, "step": 2630 }, { "epoch": 0.48, "learning_rate": 2.2895592485549134e-05, "loss": 0.6925, "step": 2631 }, { "epoch": 0.48, "learning_rate": 2.289288294797688e-05, "loss": 0.8562, "step": 2632 }, { "epoch": 0.48, "learning_rate": 2.2890173410404623e-05, "loss": 0.6817, "step": 2633 }, { "epoch": 0.48, "learning_rate": 2.288746387283237e-05, "loss": 1.2072, "step": 2634 }, { "epoch": 0.48, "learning_rate": 2.288475433526012e-05, "loss": 0.4608, "step": 2635 }, { "epoch": 0.48, "learning_rate": 2.288204479768786e-05, "loss": 1.451, "step": 2636 }, { "epoch": 0.48, "learning_rate": 2.2879335260115607e-05, "loss": 0.824, "step": 2637 }, { "epoch": 0.48, "learning_rate": 2.2876625722543352e-05, "loss": 1.0843, "step": 2638 }, { "epoch": 0.48, "learning_rate": 2.28739161849711e-05, "loss": 0.4078, "step": 2639 }, { "epoch": 0.48, "learning_rate": 2.2871206647398847e-05, "loss": 1.5304, "step": 2640 }, { "epoch": 0.48, "learning_rate": 2.2868497109826588e-05, "loss": 0.9709, "step": 2641 }, { "epoch": 0.48, "learning_rate": 2.2865787572254336e-05, "loss": 0.647, "step": 2642 }, { "epoch": 0.48, "learning_rate": 2.286307803468208e-05, "loss": 1.033, "step": 2643 }, { "epoch": 0.48, "learning_rate": 2.2860368497109828e-05, "loss": 0.7421, "step": 2644 }, { "epoch": 0.48, "learning_rate": 2.2857658959537572e-05, "loss": 0.6725, "step": 2645 }, { "epoch": 0.48, "learning_rate": 2.2854949421965317e-05, "loss": 0.6805, "step": 2646 }, { "epoch": 0.48, "learning_rate": 2.2852239884393065e-05, "loss": 0.6625, "step": 2647 }, { "epoch": 0.48, "learning_rate": 2.284953034682081e-05, "loss": 0.8458, "step": 2648 }, { "epoch": 0.48, "learning_rate": 2.2846820809248557e-05, "loss": 0.27, "step": 2649 }, { "epoch": 0.48, "learning_rate": 2.28441112716763e-05, "loss": 0.2184, "step": 2650 }, { "epoch": 0.48, "learning_rate": 2.2841401734104045e-05, "loss": 0.4222, "step": 2651 }, { "epoch": 0.48, "learning_rate": 2.2838692196531793e-05, "loss": 0.5148, "step": 2652 }, { "epoch": 0.48, "learning_rate": 2.2835982658959538e-05, "loss": 0.7191, "step": 2653 }, { "epoch": 0.48, "learning_rate": 2.2833273121387285e-05, "loss": 0.356, "step": 2654 }, { "epoch": 0.48, "learning_rate": 2.283056358381503e-05, "loss": 1.2867, "step": 2655 }, { "epoch": 0.48, "learning_rate": 2.2827854046242774e-05, "loss": 0.9746, "step": 2656 }, { "epoch": 0.48, "learning_rate": 2.2825144508670522e-05, "loss": 1.2452, "step": 2657 }, { "epoch": 0.48, "learning_rate": 2.2822434971098266e-05, "loss": 1.5075, "step": 2658 }, { "epoch": 0.48, "learning_rate": 2.281972543352601e-05, "loss": 0.6444, "step": 2659 }, { "epoch": 0.48, "learning_rate": 2.2817015895953758e-05, "loss": 0.3812, "step": 2660 }, { "epoch": 0.48, "learning_rate": 2.2814306358381503e-05, "loss": 1.0775, "step": 2661 }, { "epoch": 0.48, "learning_rate": 2.281159682080925e-05, "loss": 0.7098, "step": 2662 }, { "epoch": 0.48, "learning_rate": 2.2808887283236995e-05, "loss": 0.2673, "step": 2663 }, { "epoch": 0.48, "learning_rate": 2.280617774566474e-05, "loss": 0.9027, "step": 2664 }, { "epoch": 0.48, "learning_rate": 2.2803468208092487e-05, "loss": 0.8298, "step": 2665 }, { "epoch": 0.48, "learning_rate": 2.280075867052023e-05, "loss": 1.1854, "step": 2666 }, { "epoch": 0.48, "learning_rate": 2.279804913294798e-05, "loss": 0.3196, "step": 2667 }, { "epoch": 0.48, "learning_rate": 2.279533959537572e-05, "loss": 0.6767, "step": 2668 }, { "epoch": 0.48, "learning_rate": 2.2792630057803468e-05, "loss": 1.0552, "step": 2669 }, { "epoch": 0.48, "learning_rate": 2.2789920520231215e-05, "loss": 0.6249, "step": 2670 }, { "epoch": 0.48, "learning_rate": 2.278721098265896e-05, "loss": 0.3928, "step": 2671 }, { "epoch": 0.48, "learning_rate": 2.2784501445086708e-05, "loss": 0.5419, "step": 2672 }, { "epoch": 0.48, "learning_rate": 2.278179190751445e-05, "loss": 0.8058, "step": 2673 }, { "epoch": 0.48, "learning_rate": 2.2779082369942196e-05, "loss": 1.0703, "step": 2674 }, { "epoch": 0.48, "learning_rate": 2.2776372832369944e-05, "loss": 1.0819, "step": 2675 }, { "epoch": 0.48, "learning_rate": 2.277366329479769e-05, "loss": 1.2859, "step": 2676 }, { "epoch": 0.48, "learning_rate": 2.2770953757225436e-05, "loss": 0.845, "step": 2677 }, { "epoch": 0.48, "learning_rate": 2.2768244219653177e-05, "loss": 0.7799, "step": 2678 }, { "epoch": 0.48, "learning_rate": 2.2765534682080925e-05, "loss": 0.6234, "step": 2679 }, { "epoch": 0.48, "learning_rate": 2.2762825144508673e-05, "loss": 0.846, "step": 2680 }, { "epoch": 0.48, "learning_rate": 2.2760115606936417e-05, "loss": 0.4248, "step": 2681 }, { "epoch": 0.48, "learning_rate": 2.275740606936416e-05, "loss": 1.365, "step": 2682 }, { "epoch": 0.48, "learning_rate": 2.2754696531791906e-05, "loss": 0.5903, "step": 2683 }, { "epoch": 0.48, "learning_rate": 2.2751986994219653e-05, "loss": 1.0203, "step": 2684 }, { "epoch": 0.49, "learning_rate": 2.27492774566474e-05, "loss": 1.6309, "step": 2685 }, { "epoch": 0.49, "learning_rate": 2.2746567919075146e-05, "loss": 0.8469, "step": 2686 }, { "epoch": 0.49, "learning_rate": 2.274385838150289e-05, "loss": 0.8977, "step": 2687 }, { "epoch": 0.49, "learning_rate": 2.2741148843930634e-05, "loss": 1.5951, "step": 2688 }, { "epoch": 0.49, "learning_rate": 2.2738439306358382e-05, "loss": 1.347, "step": 2689 }, { "epoch": 0.49, "learning_rate": 2.273572976878613e-05, "loss": 0.6539, "step": 2690 }, { "epoch": 0.49, "learning_rate": 2.273302023121387e-05, "loss": 0.6904, "step": 2691 }, { "epoch": 0.49, "learning_rate": 2.273031069364162e-05, "loss": 1.0008, "step": 2692 }, { "epoch": 0.49, "learning_rate": 2.2727601156069366e-05, "loss": 0.6485, "step": 2693 }, { "epoch": 0.49, "learning_rate": 2.272489161849711e-05, "loss": 0.419, "step": 2694 }, { "epoch": 0.49, "learning_rate": 2.272218208092486e-05, "loss": 1.5438, "step": 2695 }, { "epoch": 0.49, "learning_rate": 2.27194725433526e-05, "loss": 0.9759, "step": 2696 }, { "epoch": 0.49, "learning_rate": 2.2716763005780347e-05, "loss": 1.0196, "step": 2697 }, { "epoch": 0.49, "learning_rate": 2.2714053468208095e-05, "loss": 0.8597, "step": 2698 }, { "epoch": 0.49, "learning_rate": 2.271134393063584e-05, "loss": 0.7759, "step": 2699 }, { "epoch": 0.49, "learning_rate": 2.2708634393063584e-05, "loss": 0.6523, "step": 2700 }, { "epoch": 0.49, "learning_rate": 2.2705924855491328e-05, "loss": 0.6232, "step": 2701 }, { "epoch": 0.49, "learning_rate": 2.2703215317919076e-05, "loss": 0.9554, "step": 2702 }, { "epoch": 0.49, "learning_rate": 2.2700505780346824e-05, "loss": 1.6838, "step": 2703 }, { "epoch": 0.49, "learning_rate": 2.2697796242774568e-05, "loss": 0.6896, "step": 2704 }, { "epoch": 0.49, "learning_rate": 2.2695086705202312e-05, "loss": 0.98, "step": 2705 }, { "epoch": 0.49, "learning_rate": 2.2692377167630057e-05, "loss": 1.4931, "step": 2706 }, { "epoch": 0.49, "learning_rate": 2.2689667630057804e-05, "loss": 0.7701, "step": 2707 }, { "epoch": 0.49, "learning_rate": 2.2686958092485552e-05, "loss": 0.6042, "step": 2708 }, { "epoch": 0.49, "learning_rate": 2.2684248554913297e-05, "loss": 0.6961, "step": 2709 }, { "epoch": 0.49, "learning_rate": 2.268153901734104e-05, "loss": 1.1884, "step": 2710 }, { "epoch": 0.49, "learning_rate": 2.2678829479768785e-05, "loss": 0.9452, "step": 2711 }, { "epoch": 0.49, "learning_rate": 2.2676119942196533e-05, "loss": 0.7795, "step": 2712 }, { "epoch": 0.49, "learning_rate": 2.267341040462428e-05, "loss": 0.5166, "step": 2713 }, { "epoch": 0.49, "learning_rate": 2.2670700867052022e-05, "loss": 0.8842, "step": 2714 }, { "epoch": 0.49, "learning_rate": 2.266799132947977e-05, "loss": 0.5891, "step": 2715 }, { "epoch": 0.49, "learning_rate": 2.2665281791907514e-05, "loss": 0.2816, "step": 2716 }, { "epoch": 0.49, "learning_rate": 2.266257225433526e-05, "loss": 1.831, "step": 2717 }, { "epoch": 0.49, "learning_rate": 2.265986271676301e-05, "loss": 0.9724, "step": 2718 }, { "epoch": 0.49, "learning_rate": 2.265715317919075e-05, "loss": 0.9089, "step": 2719 }, { "epoch": 0.49, "learning_rate": 2.2654443641618498e-05, "loss": 0.8026, "step": 2720 }, { "epoch": 0.49, "learning_rate": 2.2651734104046242e-05, "loss": 0.5119, "step": 2721 }, { "epoch": 0.49, "learning_rate": 2.264902456647399e-05, "loss": 0.4175, "step": 2722 }, { "epoch": 0.49, "learning_rate": 2.2646315028901735e-05, "loss": 0.8354, "step": 2723 }, { "epoch": 0.49, "learning_rate": 2.264360549132948e-05, "loss": 1.2797, "step": 2724 }, { "epoch": 0.49, "learning_rate": 2.2640895953757227e-05, "loss": 0.6323, "step": 2725 }, { "epoch": 0.49, "learning_rate": 2.263818641618497e-05, "loss": 0.8577, "step": 2726 }, { "epoch": 0.49, "learning_rate": 2.263547687861272e-05, "loss": 0.922, "step": 2727 }, { "epoch": 0.49, "learning_rate": 2.2632767341040463e-05, "loss": 1.0287, "step": 2728 }, { "epoch": 0.49, "learning_rate": 2.2630057803468208e-05, "loss": 0.5038, "step": 2729 }, { "epoch": 0.49, "learning_rate": 2.2627348265895955e-05, "loss": 0.4155, "step": 2730 }, { "epoch": 0.49, "learning_rate": 2.26246387283237e-05, "loss": 0.7745, "step": 2731 }, { "epoch": 0.49, "learning_rate": 2.2621929190751447e-05, "loss": 0.7944, "step": 2732 }, { "epoch": 0.49, "learning_rate": 2.2619219653179192e-05, "loss": 1.2661, "step": 2733 }, { "epoch": 0.49, "learning_rate": 2.2616510115606936e-05, "loss": 0.7651, "step": 2734 }, { "epoch": 0.49, "learning_rate": 2.2613800578034684e-05, "loss": 0.722, "step": 2735 }, { "epoch": 0.49, "learning_rate": 2.2611091040462428e-05, "loss": 0.4925, "step": 2736 }, { "epoch": 0.49, "learning_rate": 2.2608381502890173e-05, "loss": 0.5818, "step": 2737 }, { "epoch": 0.49, "learning_rate": 2.260567196531792e-05, "loss": 0.7349, "step": 2738 }, { "epoch": 0.49, "learning_rate": 2.2602962427745665e-05, "loss": 1.0602, "step": 2739 }, { "epoch": 0.49, "learning_rate": 2.2600252890173412e-05, "loss": 1.0459, "step": 2740 }, { "epoch": 0.5, "learning_rate": 2.2597543352601157e-05, "loss": 0.9185, "step": 2741 }, { "epoch": 0.5, "learning_rate": 2.25948338150289e-05, "loss": 0.2984, "step": 2742 }, { "epoch": 0.5, "learning_rate": 2.259212427745665e-05, "loss": 0.9971, "step": 2743 }, { "epoch": 0.5, "learning_rate": 2.2589414739884393e-05, "loss": 0.6341, "step": 2744 }, { "epoch": 0.5, "learning_rate": 2.258670520231214e-05, "loss": 1.7271, "step": 2745 }, { "epoch": 0.5, "learning_rate": 2.2583995664739885e-05, "loss": 0.7944, "step": 2746 }, { "epoch": 0.5, "learning_rate": 2.258128612716763e-05, "loss": 1.7808, "step": 2747 }, { "epoch": 0.5, "learning_rate": 2.2578576589595378e-05, "loss": 0.5226, "step": 2748 }, { "epoch": 0.5, "learning_rate": 2.2575867052023122e-05, "loss": 0.4172, "step": 2749 }, { "epoch": 0.5, "learning_rate": 2.257315751445087e-05, "loss": 0.7784, "step": 2750 }, { "epoch": 0.5, "learning_rate": 2.257044797687861e-05, "loss": 0.4822, "step": 2751 }, { "epoch": 0.5, "learning_rate": 2.256773843930636e-05, "loss": 0.6071, "step": 2752 }, { "epoch": 0.5, "learning_rate": 2.2565028901734106e-05, "loss": 0.9352, "step": 2753 }, { "epoch": 0.5, "learning_rate": 2.256231936416185e-05, "loss": 1.7653, "step": 2754 }, { "epoch": 0.5, "learning_rate": 2.2559609826589598e-05, "loss": 0.5615, "step": 2755 }, { "epoch": 0.5, "learning_rate": 2.255690028901734e-05, "loss": 0.6022, "step": 2756 }, { "epoch": 0.5, "learning_rate": 2.2554190751445087e-05, "loss": 0.5966, "step": 2757 }, { "epoch": 0.5, "learning_rate": 2.2551481213872835e-05, "loss": 1.1683, "step": 2758 }, { "epoch": 0.5, "learning_rate": 2.254877167630058e-05, "loss": 0.9243, "step": 2759 }, { "epoch": 0.5, "learning_rate": 2.2546062138728323e-05, "loss": 0.7786, "step": 2760 }, { "epoch": 0.5, "learning_rate": 2.2543352601156068e-05, "loss": 0.753, "step": 2761 }, { "epoch": 0.5, "learning_rate": 2.2540643063583816e-05, "loss": 1.0364, "step": 2762 }, { "epoch": 0.5, "learning_rate": 2.2537933526011563e-05, "loss": 0.7142, "step": 2763 }, { "epoch": 0.5, "learning_rate": 2.2535223988439308e-05, "loss": 0.8166, "step": 2764 }, { "epoch": 0.5, "learning_rate": 2.2532514450867052e-05, "loss": 0.5732, "step": 2765 }, { "epoch": 0.5, "learning_rate": 2.2529804913294796e-05, "loss": 1.0765, "step": 2766 }, { "epoch": 0.5, "learning_rate": 2.2527095375722544e-05, "loss": 0.951, "step": 2767 }, { "epoch": 0.5, "learning_rate": 2.2524385838150292e-05, "loss": 0.8646, "step": 2768 }, { "epoch": 0.5, "learning_rate": 2.2521676300578033e-05, "loss": 0.7569, "step": 2769 }, { "epoch": 0.5, "learning_rate": 2.251896676300578e-05, "loss": 0.8728, "step": 2770 }, { "epoch": 0.5, "learning_rate": 2.2516257225433525e-05, "loss": 0.6577, "step": 2771 }, { "epoch": 0.5, "learning_rate": 2.2513547687861273e-05, "loss": 0.9886, "step": 2772 }, { "epoch": 0.5, "learning_rate": 2.251083815028902e-05, "loss": 1.1577, "step": 2773 }, { "epoch": 0.5, "learning_rate": 2.250812861271676e-05, "loss": 1.0864, "step": 2774 }, { "epoch": 0.5, "learning_rate": 2.250541907514451e-05, "loss": 0.8141, "step": 2775 }, { "epoch": 0.5, "learning_rate": 2.2502709537572254e-05, "loss": 1.0294, "step": 2776 }, { "epoch": 0.5, "learning_rate": 2.25e-05, "loss": 1.5711, "step": 2777 }, { "epoch": 0.5, "learning_rate": 2.249729046242775e-05, "loss": 1.5856, "step": 2778 }, { "epoch": 0.5, "learning_rate": 2.249458092485549e-05, "loss": 0.7996, "step": 2779 }, { "epoch": 0.5, "learning_rate": 2.2491871387283238e-05, "loss": 0.5059, "step": 2780 }, { "epoch": 0.5, "learning_rate": 2.2489161849710982e-05, "loss": 0.9744, "step": 2781 }, { "epoch": 0.5, "learning_rate": 2.248645231213873e-05, "loss": 0.6491, "step": 2782 }, { "epoch": 0.5, "learning_rate": 2.2483742774566474e-05, "loss": 0.8039, "step": 2783 }, { "epoch": 0.5, "learning_rate": 2.248103323699422e-05, "loss": 0.5834, "step": 2784 }, { "epoch": 0.5, "learning_rate": 2.2478323699421967e-05, "loss": 0.756, "step": 2785 }, { "epoch": 0.5, "learning_rate": 2.247561416184971e-05, "loss": 0.4785, "step": 2786 }, { "epoch": 0.5, "learning_rate": 2.247290462427746e-05, "loss": 0.7074, "step": 2787 }, { "epoch": 0.5, "learning_rate": 2.2470195086705203e-05, "loss": 0.9755, "step": 2788 }, { "epoch": 0.5, "learning_rate": 2.2467485549132947e-05, "loss": 0.7293, "step": 2789 }, { "epoch": 0.5, "learning_rate": 2.2464776011560695e-05, "loss": 1.2322, "step": 2790 }, { "epoch": 0.5, "learning_rate": 2.246206647398844e-05, "loss": 0.841, "step": 2791 }, { "epoch": 0.5, "learning_rate": 2.2459356936416184e-05, "loss": 0.8418, "step": 2792 }, { "epoch": 0.5, "learning_rate": 2.245664739884393e-05, "loss": 1.1518, "step": 2793 }, { "epoch": 0.5, "learning_rate": 2.2453937861271676e-05, "loss": 0.6869, "step": 2794 }, { "epoch": 0.5, "learning_rate": 2.2451228323699424e-05, "loss": 1.4196, "step": 2795 }, { "epoch": 0.51, "learning_rate": 2.2448518786127168e-05, "loss": 1.0186, "step": 2796 }, { "epoch": 0.51, "learning_rate": 2.2445809248554912e-05, "loss": 0.5968, "step": 2797 }, { "epoch": 0.51, "learning_rate": 2.244309971098266e-05, "loss": 0.5787, "step": 2798 }, { "epoch": 0.51, "learning_rate": 2.2440390173410405e-05, "loss": 0.9839, "step": 2799 }, { "epoch": 0.51, "learning_rate": 2.2437680635838152e-05, "loss": 0.2887, "step": 2800 }, { "epoch": 0.51, "learning_rate": 2.2434971098265897e-05, "loss": 1.0004, "step": 2801 }, { "epoch": 0.51, "learning_rate": 2.243226156069364e-05, "loss": 1.1456, "step": 2802 }, { "epoch": 0.51, "learning_rate": 2.242955202312139e-05, "loss": 1.8025, "step": 2803 }, { "epoch": 0.51, "learning_rate": 2.2426842485549133e-05, "loss": 1.3463, "step": 2804 }, { "epoch": 0.51, "learning_rate": 2.242413294797688e-05, "loss": 0.7066, "step": 2805 }, { "epoch": 0.51, "learning_rate": 2.2421423410404622e-05, "loss": 1.2628, "step": 2806 }, { "epoch": 0.51, "learning_rate": 2.241871387283237e-05, "loss": 0.7891, "step": 2807 }, { "epoch": 0.51, "learning_rate": 2.2416004335260117e-05, "loss": 1.0771, "step": 2808 }, { "epoch": 0.51, "learning_rate": 2.2413294797687862e-05, "loss": 0.9302, "step": 2809 }, { "epoch": 0.51, "learning_rate": 2.241058526011561e-05, "loss": 0.7307, "step": 2810 }, { "epoch": 0.51, "learning_rate": 2.240787572254335e-05, "loss": 0.3593, "step": 2811 }, { "epoch": 0.51, "learning_rate": 2.2405166184971098e-05, "loss": 0.8456, "step": 2812 }, { "epoch": 0.51, "learning_rate": 2.2402456647398846e-05, "loss": 0.7794, "step": 2813 }, { "epoch": 0.51, "learning_rate": 2.239974710982659e-05, "loss": 0.8919, "step": 2814 }, { "epoch": 0.51, "learning_rate": 2.2397037572254335e-05, "loss": 1.0812, "step": 2815 }, { "epoch": 0.51, "learning_rate": 2.239432803468208e-05, "loss": 0.8074, "step": 2816 }, { "epoch": 0.51, "learning_rate": 2.2391618497109827e-05, "loss": 0.8095, "step": 2817 }, { "epoch": 0.51, "learning_rate": 2.2388908959537575e-05, "loss": 0.451, "step": 2818 }, { "epoch": 0.51, "learning_rate": 2.238619942196532e-05, "loss": 1.0234, "step": 2819 }, { "epoch": 0.51, "learning_rate": 2.2383489884393063e-05, "loss": 0.9842, "step": 2820 }, { "epoch": 0.51, "learning_rate": 2.2380780346820808e-05, "loss": 0.829, "step": 2821 }, { "epoch": 0.51, "learning_rate": 2.2378070809248555e-05, "loss": 0.5974, "step": 2822 }, { "epoch": 0.51, "learning_rate": 2.2375361271676303e-05, "loss": 0.9214, "step": 2823 }, { "epoch": 0.51, "learning_rate": 2.2372651734104048e-05, "loss": 0.6713, "step": 2824 }, { "epoch": 0.51, "learning_rate": 2.2369942196531792e-05, "loss": 1.3539, "step": 2825 }, { "epoch": 0.51, "learning_rate": 2.2367232658959536e-05, "loss": 1.1489, "step": 2826 }, { "epoch": 0.51, "learning_rate": 2.2364523121387284e-05, "loss": 0.8593, "step": 2827 }, { "epoch": 0.51, "learning_rate": 2.2361813583815032e-05, "loss": 0.9649, "step": 2828 }, { "epoch": 0.51, "learning_rate": 2.2359104046242773e-05, "loss": 1.0033, "step": 2829 }, { "epoch": 0.51, "learning_rate": 2.235639450867052e-05, "loss": 0.389, "step": 2830 }, { "epoch": 0.51, "learning_rate": 2.2353684971098265e-05, "loss": 0.3858, "step": 2831 }, { "epoch": 0.51, "learning_rate": 2.2350975433526013e-05, "loss": 1.0276, "step": 2832 }, { "epoch": 0.51, "learning_rate": 2.234826589595376e-05, "loss": 0.8259, "step": 2833 }, { "epoch": 0.51, "learning_rate": 2.23455563583815e-05, "loss": 0.4381, "step": 2834 }, { "epoch": 0.51, "learning_rate": 2.234284682080925e-05, "loss": 0.7914, "step": 2835 }, { "epoch": 0.51, "learning_rate": 2.2340137283236993e-05, "loss": 1.2397, "step": 2836 }, { "epoch": 0.51, "learning_rate": 2.233742774566474e-05, "loss": 1.1257, "step": 2837 }, { "epoch": 0.51, "learning_rate": 2.2334718208092486e-05, "loss": 0.3901, "step": 2838 }, { "epoch": 0.51, "learning_rate": 2.233200867052023e-05, "loss": 1.1259, "step": 2839 }, { "epoch": 0.51, "learning_rate": 2.2329299132947978e-05, "loss": 0.5737, "step": 2840 }, { "epoch": 0.51, "learning_rate": 2.2326589595375722e-05, "loss": 0.743, "step": 2841 }, { "epoch": 0.51, "learning_rate": 2.232388005780347e-05, "loss": 1.2178, "step": 2842 }, { "epoch": 0.51, "learning_rate": 2.2321170520231214e-05, "loss": 0.4411, "step": 2843 }, { "epoch": 0.51, "learning_rate": 2.231846098265896e-05, "loss": 0.3717, "step": 2844 }, { "epoch": 0.51, "learning_rate": 2.2315751445086706e-05, "loss": 0.4413, "step": 2845 }, { "epoch": 0.51, "learning_rate": 2.231304190751445e-05, "loss": 0.815, "step": 2846 }, { "epoch": 0.51, "learning_rate": 2.23103323699422e-05, "loss": 0.6052, "step": 2847 }, { "epoch": 0.51, "learning_rate": 2.2307622832369943e-05, "loss": 0.7973, "step": 2848 }, { "epoch": 0.51, "learning_rate": 2.2304913294797687e-05, "loss": 0.6862, "step": 2849 }, { "epoch": 0.51, "learning_rate": 2.2302203757225435e-05, "loss": 0.974, "step": 2850 }, { "epoch": 0.51, "learning_rate": 2.229949421965318e-05, "loss": 0.9374, "step": 2851 }, { "epoch": 0.52, "learning_rate": 2.2296784682080924e-05, "loss": 0.5063, "step": 2852 }, { "epoch": 0.52, "learning_rate": 2.229407514450867e-05, "loss": 0.6647, "step": 2853 }, { "epoch": 0.52, "learning_rate": 2.2291365606936416e-05, "loss": 0.503, "step": 2854 }, { "epoch": 0.52, "learning_rate": 2.2288656069364164e-05, "loss": 1.2865, "step": 2855 }, { "epoch": 0.52, "learning_rate": 2.2285946531791908e-05, "loss": 0.7177, "step": 2856 }, { "epoch": 0.52, "learning_rate": 2.2283236994219652e-05, "loss": 1.2403, "step": 2857 }, { "epoch": 0.52, "learning_rate": 2.22805274566474e-05, "loss": 0.675, "step": 2858 }, { "epoch": 0.52, "learning_rate": 2.2277817919075144e-05, "loss": 0.3915, "step": 2859 }, { "epoch": 0.52, "learning_rate": 2.2275108381502892e-05, "loss": 0.4725, "step": 2860 }, { "epoch": 0.52, "learning_rate": 2.2272398843930633e-05, "loss": 0.7109, "step": 2861 }, { "epoch": 0.52, "learning_rate": 2.226968930635838e-05, "loss": 1.4261, "step": 2862 }, { "epoch": 0.52, "learning_rate": 2.226697976878613e-05, "loss": 1.0254, "step": 2863 }, { "epoch": 0.52, "learning_rate": 2.2264270231213873e-05, "loss": 1.2512, "step": 2864 }, { "epoch": 0.52, "learning_rate": 2.226156069364162e-05, "loss": 0.7492, "step": 2865 }, { "epoch": 0.52, "learning_rate": 2.2258851156069365e-05, "loss": 0.4629, "step": 2866 }, { "epoch": 0.52, "learning_rate": 2.225614161849711e-05, "loss": 0.9109, "step": 2867 }, { "epoch": 0.52, "learning_rate": 2.2253432080924857e-05, "loss": 0.8108, "step": 2868 }, { "epoch": 0.52, "learning_rate": 2.22507225433526e-05, "loss": 0.4853, "step": 2869 }, { "epoch": 0.52, "learning_rate": 2.224801300578035e-05, "loss": 0.9885, "step": 2870 }, { "epoch": 0.52, "learning_rate": 2.2245303468208094e-05, "loss": 0.6457, "step": 2871 }, { "epoch": 0.52, "learning_rate": 2.2242593930635838e-05, "loss": 0.7158, "step": 2872 }, { "epoch": 0.52, "learning_rate": 2.2239884393063586e-05, "loss": 0.7348, "step": 2873 }, { "epoch": 0.52, "learning_rate": 2.223717485549133e-05, "loss": 0.8457, "step": 2874 }, { "epoch": 0.52, "learning_rate": 2.2234465317919075e-05, "loss": 0.2895, "step": 2875 }, { "epoch": 0.52, "learning_rate": 2.2231755780346822e-05, "loss": 0.5215, "step": 2876 }, { "epoch": 0.52, "learning_rate": 2.2229046242774567e-05, "loss": 0.5341, "step": 2877 }, { "epoch": 0.52, "learning_rate": 2.2226336705202314e-05, "loss": 0.5989, "step": 2878 }, { "epoch": 0.52, "learning_rate": 2.222362716763006e-05, "loss": 0.447, "step": 2879 }, { "epoch": 0.52, "learning_rate": 2.2220917630057803e-05, "loss": 1.1964, "step": 2880 }, { "epoch": 0.52, "learning_rate": 2.221820809248555e-05, "loss": 0.7467, "step": 2881 }, { "epoch": 0.52, "learning_rate": 2.2215498554913295e-05, "loss": 0.5576, "step": 2882 }, { "epoch": 0.52, "learning_rate": 2.2212789017341043e-05, "loss": 0.6211, "step": 2883 }, { "epoch": 0.52, "learning_rate": 2.2210079479768784e-05, "loss": 1.4259, "step": 2884 }, { "epoch": 0.52, "learning_rate": 2.2207369942196532e-05, "loss": 0.5298, "step": 2885 }, { "epoch": 0.52, "learning_rate": 2.220466040462428e-05, "loss": 0.7697, "step": 2886 }, { "epoch": 0.52, "learning_rate": 2.2201950867052024e-05, "loss": 0.6216, "step": 2887 }, { "epoch": 0.52, "learning_rate": 2.219924132947977e-05, "loss": 1.1633, "step": 2888 }, { "epoch": 0.52, "learning_rate": 2.2196531791907513e-05, "loss": 0.7238, "step": 2889 }, { "epoch": 0.52, "learning_rate": 2.219382225433526e-05, "loss": 1.4544, "step": 2890 }, { "epoch": 0.52, "learning_rate": 2.2191112716763008e-05, "loss": 0.796, "step": 2891 }, { "epoch": 0.52, "learning_rate": 2.2188403179190752e-05, "loss": 0.3094, "step": 2892 }, { "epoch": 0.52, "learning_rate": 2.21856936416185e-05, "loss": 0.6522, "step": 2893 }, { "epoch": 0.52, "learning_rate": 2.218298410404624e-05, "loss": 1.408, "step": 2894 }, { "epoch": 0.52, "learning_rate": 2.218027456647399e-05, "loss": 0.1137, "step": 2895 }, { "epoch": 0.52, "learning_rate": 2.2177565028901737e-05, "loss": 0.5339, "step": 2896 }, { "epoch": 0.52, "learning_rate": 2.217485549132948e-05, "loss": 0.614, "step": 2897 }, { "epoch": 0.52, "learning_rate": 2.2172145953757225e-05, "loss": 1.3693, "step": 2898 }, { "epoch": 0.52, "learning_rate": 2.216943641618497e-05, "loss": 1.0459, "step": 2899 }, { "epoch": 0.52, "learning_rate": 2.2166726878612718e-05, "loss": 0.6336, "step": 2900 }, { "epoch": 0.52, "learning_rate": 2.2164017341040465e-05, "loss": 0.6, "step": 2901 }, { "epoch": 0.52, "learning_rate": 2.216130780346821e-05, "loss": 0.709, "step": 2902 }, { "epoch": 0.52, "learning_rate": 2.2158598265895954e-05, "loss": 1.1458, "step": 2903 }, { "epoch": 0.52, "learning_rate": 2.21558887283237e-05, "loss": 0.843, "step": 2904 }, { "epoch": 0.52, "learning_rate": 2.2153179190751446e-05, "loss": 0.9094, "step": 2905 }, { "epoch": 0.52, "learning_rate": 2.2150469653179194e-05, "loss": 1.2102, "step": 2906 }, { "epoch": 0.53, "learning_rate": 2.2147760115606935e-05, "loss": 0.5075, "step": 2907 }, { "epoch": 0.53, "learning_rate": 2.2145050578034683e-05, "loss": 0.2341, "step": 2908 }, { "epoch": 0.53, "learning_rate": 2.2142341040462427e-05, "loss": 0.8811, "step": 2909 }, { "epoch": 0.53, "learning_rate": 2.2139631502890175e-05, "loss": 0.8166, "step": 2910 }, { "epoch": 0.53, "learning_rate": 2.2136921965317923e-05, "loss": 0.7561, "step": 2911 }, { "epoch": 0.53, "learning_rate": 2.2134212427745663e-05, "loss": 0.4842, "step": 2912 }, { "epoch": 0.53, "learning_rate": 2.213150289017341e-05, "loss": 0.6156, "step": 2913 }, { "epoch": 0.53, "learning_rate": 2.2128793352601156e-05, "loss": 1.6126, "step": 2914 }, { "epoch": 0.53, "learning_rate": 2.2126083815028903e-05, "loss": 0.4018, "step": 2915 }, { "epoch": 0.53, "learning_rate": 2.2123374277456648e-05, "loss": 0.9584, "step": 2916 }, { "epoch": 0.53, "learning_rate": 2.2120664739884392e-05, "loss": 1.3753, "step": 2917 }, { "epoch": 0.53, "learning_rate": 2.211795520231214e-05, "loss": 1.14, "step": 2918 }, { "epoch": 0.53, "learning_rate": 2.2115245664739884e-05, "loss": 0.3075, "step": 2919 }, { "epoch": 0.53, "learning_rate": 2.2112536127167632e-05, "loss": 0.8145, "step": 2920 }, { "epoch": 0.53, "learning_rate": 2.2109826589595376e-05, "loss": 1.1149, "step": 2921 }, { "epoch": 0.53, "learning_rate": 2.210711705202312e-05, "loss": 0.8091, "step": 2922 }, { "epoch": 0.53, "learning_rate": 2.210440751445087e-05, "loss": 0.6763, "step": 2923 }, { "epoch": 0.53, "learning_rate": 2.2101697976878613e-05, "loss": 0.9574, "step": 2924 }, { "epoch": 0.53, "learning_rate": 2.209898843930636e-05, "loss": 1.297, "step": 2925 }, { "epoch": 0.53, "learning_rate": 2.2096278901734105e-05, "loss": 0.837, "step": 2926 }, { "epoch": 0.53, "learning_rate": 2.209356936416185e-05, "loss": 0.4484, "step": 2927 }, { "epoch": 0.53, "learning_rate": 2.2090859826589597e-05, "loss": 0.4587, "step": 2928 }, { "epoch": 0.53, "learning_rate": 2.208815028901734e-05, "loss": 0.4129, "step": 2929 }, { "epoch": 0.53, "learning_rate": 2.2085440751445086e-05, "loss": 0.4197, "step": 2930 }, { "epoch": 0.53, "learning_rate": 2.2082731213872834e-05, "loss": 0.6157, "step": 2931 }, { "epoch": 0.53, "learning_rate": 2.2080021676300578e-05, "loss": 0.5875, "step": 2932 }, { "epoch": 0.53, "learning_rate": 2.2077312138728326e-05, "loss": 0.491, "step": 2933 }, { "epoch": 0.53, "learning_rate": 2.207460260115607e-05, "loss": 1.4142, "step": 2934 }, { "epoch": 0.53, "learning_rate": 2.2071893063583814e-05, "loss": 0.3684, "step": 2935 }, { "epoch": 0.53, "learning_rate": 2.2069183526011562e-05, "loss": 0.5679, "step": 2936 }, { "epoch": 0.53, "learning_rate": 2.2066473988439307e-05, "loss": 1.4468, "step": 2937 }, { "epoch": 0.53, "learning_rate": 2.2063764450867054e-05, "loss": 1.1721, "step": 2938 }, { "epoch": 0.53, "learning_rate": 2.20610549132948e-05, "loss": 0.8687, "step": 2939 }, { "epoch": 0.53, "learning_rate": 2.2058345375722543e-05, "loss": 0.8608, "step": 2940 }, { "epoch": 0.53, "learning_rate": 2.205563583815029e-05, "loss": 0.7581, "step": 2941 }, { "epoch": 0.53, "learning_rate": 2.2052926300578035e-05, "loss": 0.6581, "step": 2942 }, { "epoch": 0.53, "learning_rate": 2.2050216763005783e-05, "loss": 0.8403, "step": 2943 }, { "epoch": 0.53, "learning_rate": 2.2047507225433524e-05, "loss": 0.4463, "step": 2944 }, { "epoch": 0.53, "learning_rate": 2.204479768786127e-05, "loss": 1.311, "step": 2945 }, { "epoch": 0.53, "learning_rate": 2.204208815028902e-05, "loss": 0.9874, "step": 2946 }, { "epoch": 0.53, "learning_rate": 2.2039378612716764e-05, "loss": 0.4346, "step": 2947 }, { "epoch": 0.53, "learning_rate": 2.203666907514451e-05, "loss": 1.1499, "step": 2948 }, { "epoch": 0.53, "learning_rate": 2.2033959537572252e-05, "loss": 0.4789, "step": 2949 }, { "epoch": 0.53, "learning_rate": 2.203125e-05, "loss": 0.6583, "step": 2950 }, { "epoch": 0.53, "learning_rate": 2.2028540462427748e-05, "loss": 0.4204, "step": 2951 }, { "epoch": 0.53, "learning_rate": 2.2025830924855492e-05, "loss": 0.5936, "step": 2952 }, { "epoch": 0.53, "learning_rate": 2.2023121387283237e-05, "loss": 0.7746, "step": 2953 }, { "epoch": 0.53, "learning_rate": 2.202041184971098e-05, "loss": 0.7789, "step": 2954 }, { "epoch": 0.53, "learning_rate": 2.201770231213873e-05, "loss": 0.8515, "step": 2955 }, { "epoch": 0.53, "learning_rate": 2.2014992774566477e-05, "loss": 0.4228, "step": 2956 }, { "epoch": 0.53, "learning_rate": 2.201228323699422e-05, "loss": 0.6289, "step": 2957 }, { "epoch": 0.53, "learning_rate": 2.2009573699421965e-05, "loss": 0.3992, "step": 2958 }, { "epoch": 0.53, "learning_rate": 2.200686416184971e-05, "loss": 0.9168, "step": 2959 }, { "epoch": 0.53, "learning_rate": 2.2004154624277457e-05, "loss": 1.1757, "step": 2960 }, { "epoch": 0.53, "learning_rate": 2.2001445086705205e-05, "loss": 0.3193, "step": 2961 }, { "epoch": 0.54, "learning_rate": 2.199873554913295e-05, "loss": 1.0237, "step": 2962 }, { "epoch": 0.54, "learning_rate": 2.1996026011560694e-05, "loss": 1.2573, "step": 2963 }, { "epoch": 0.54, "learning_rate": 2.1993316473988438e-05, "loss": 0.8236, "step": 2964 }, { "epoch": 0.54, "learning_rate": 2.1990606936416186e-05, "loss": 0.2359, "step": 2965 }, { "epoch": 0.54, "learning_rate": 2.1987897398843934e-05, "loss": 0.403, "step": 2966 }, { "epoch": 0.54, "learning_rate": 2.1985187861271675e-05, "loss": 0.5888, "step": 2967 }, { "epoch": 0.54, "learning_rate": 2.1982478323699422e-05, "loss": 0.8502, "step": 2968 }, { "epoch": 0.54, "learning_rate": 2.1979768786127167e-05, "loss": 1.2031, "step": 2969 }, { "epoch": 0.54, "learning_rate": 2.1977059248554915e-05, "loss": 1.2386, "step": 2970 }, { "epoch": 0.54, "learning_rate": 2.1974349710982662e-05, "loss": 1.1235, "step": 2971 }, { "epoch": 0.54, "learning_rate": 2.1971640173410403e-05, "loss": 0.5896, "step": 2972 }, { "epoch": 0.54, "learning_rate": 2.196893063583815e-05, "loss": 0.4997, "step": 2973 }, { "epoch": 0.54, "learning_rate": 2.1966221098265895e-05, "loss": 0.8192, "step": 2974 }, { "epoch": 0.54, "learning_rate": 2.1963511560693643e-05, "loss": 1.1974, "step": 2975 }, { "epoch": 0.54, "learning_rate": 2.1960802023121388e-05, "loss": 0.595, "step": 2976 }, { "epoch": 0.54, "learning_rate": 2.1958092485549132e-05, "loss": 0.803, "step": 2977 }, { "epoch": 0.54, "learning_rate": 2.195538294797688e-05, "loss": 1.0959, "step": 2978 }, { "epoch": 0.54, "learning_rate": 2.1952673410404624e-05, "loss": 0.4698, "step": 2979 }, { "epoch": 0.54, "learning_rate": 2.1949963872832372e-05, "loss": 0.8392, "step": 2980 }, { "epoch": 0.54, "learning_rate": 2.1947254335260116e-05, "loss": 0.4788, "step": 2981 }, { "epoch": 0.54, "learning_rate": 2.194454479768786e-05, "loss": 0.9439, "step": 2982 }, { "epoch": 0.54, "learning_rate": 2.1941835260115608e-05, "loss": 1.058, "step": 2983 }, { "epoch": 0.54, "learning_rate": 2.1939125722543353e-05, "loss": 0.7725, "step": 2984 }, { "epoch": 0.54, "learning_rate": 2.1936416184971097e-05, "loss": 1.0808, "step": 2985 }, { "epoch": 0.54, "learning_rate": 2.1933706647398845e-05, "loss": 0.7958, "step": 2986 }, { "epoch": 0.54, "learning_rate": 2.193099710982659e-05, "loss": 0.8548, "step": 2987 }, { "epoch": 0.54, "learning_rate": 2.1928287572254337e-05, "loss": 0.3896, "step": 2988 }, { "epoch": 0.54, "learning_rate": 2.192557803468208e-05, "loss": 0.6984, "step": 2989 }, { "epoch": 0.54, "learning_rate": 2.1922868497109826e-05, "loss": 0.9724, "step": 2990 }, { "epoch": 0.54, "learning_rate": 2.1920158959537573e-05, "loss": 0.8677, "step": 2991 }, { "epoch": 0.54, "learning_rate": 2.1917449421965318e-05, "loss": 0.6705, "step": 2992 }, { "epoch": 0.54, "learning_rate": 2.1914739884393065e-05, "loss": 0.8809, "step": 2993 }, { "epoch": 0.54, "learning_rate": 2.191203034682081e-05, "loss": 0.7468, "step": 2994 }, { "epoch": 0.54, "learning_rate": 2.1909320809248554e-05, "loss": 1.2179, "step": 2995 }, { "epoch": 0.54, "learning_rate": 2.1906611271676302e-05, "loss": 1.0312, "step": 2996 }, { "epoch": 0.54, "learning_rate": 2.1903901734104046e-05, "loss": 0.6698, "step": 2997 }, { "epoch": 0.54, "learning_rate": 2.1901192196531794e-05, "loss": 1.3392, "step": 2998 }, { "epoch": 0.54, "learning_rate": 2.1898482658959535e-05, "loss": 0.6703, "step": 2999 }, { "epoch": 0.54, "learning_rate": 2.1895773121387283e-05, "loss": 0.5835, "step": 3000 }, { "epoch": 0.54, "eval_exact_match": 85.71428571428571, "eval_f1": 92.08135563546679, "step": 3000 }, { "epoch": 0.54, "learning_rate": 2.189306358381503e-05, "loss": 1.0672, "step": 3001 }, { "epoch": 0.54, "learning_rate": 2.1890354046242775e-05, "loss": 1.7069, "step": 3002 }, { "epoch": 0.54, "learning_rate": 2.1887644508670523e-05, "loss": 0.9459, "step": 3003 }, { "epoch": 0.54, "learning_rate": 2.1884934971098264e-05, "loss": 1.0072, "step": 3004 }, { "epoch": 0.54, "learning_rate": 2.188222543352601e-05, "loss": 0.398, "step": 3005 }, { "epoch": 0.54, "learning_rate": 2.187951589595376e-05, "loss": 0.4407, "step": 3006 }, { "epoch": 0.54, "learning_rate": 2.1876806358381504e-05, "loss": 0.6804, "step": 3007 }, { "epoch": 0.54, "learning_rate": 2.1874096820809248e-05, "loss": 0.6006, "step": 3008 }, { "epoch": 0.54, "learning_rate": 2.1871387283236992e-05, "loss": 1.4903, "step": 3009 }, { "epoch": 0.54, "learning_rate": 2.186867774566474e-05, "loss": 0.6487, "step": 3010 }, { "epoch": 0.54, "learning_rate": 2.1865968208092488e-05, "loss": 0.6022, "step": 3011 }, { "epoch": 0.54, "learning_rate": 2.1863258670520232e-05, "loss": 0.9952, "step": 3012 }, { "epoch": 0.54, "learning_rate": 2.1860549132947977e-05, "loss": 1.2452, "step": 3013 }, { "epoch": 0.54, "learning_rate": 2.185783959537572e-05, "loss": 0.8078, "step": 3014 }, { "epoch": 0.54, "learning_rate": 2.185513005780347e-05, "loss": 0.4992, "step": 3015 }, { "epoch": 0.54, "learning_rate": 2.1852420520231216e-05, "loss": 1.1835, "step": 3016 }, { "epoch": 0.54, "learning_rate": 2.184971098265896e-05, "loss": 0.7958, "step": 3017 }, { "epoch": 0.55, "learning_rate": 2.1847001445086705e-05, "loss": 0.9164, "step": 3018 }, { "epoch": 0.55, "learning_rate": 2.184429190751445e-05, "loss": 0.7721, "step": 3019 }, { "epoch": 0.55, "learning_rate": 2.1841582369942197e-05, "loss": 0.4952, "step": 3020 }, { "epoch": 0.55, "learning_rate": 2.1838872832369945e-05, "loss": 0.6879, "step": 3021 }, { "epoch": 0.55, "learning_rate": 2.1836163294797686e-05, "loss": 0.7535, "step": 3022 }, { "epoch": 0.55, "learning_rate": 2.1833453757225434e-05, "loss": 0.6406, "step": 3023 }, { "epoch": 0.55, "learning_rate": 2.1830744219653178e-05, "loss": 0.7186, "step": 3024 }, { "epoch": 0.55, "learning_rate": 2.1828034682080926e-05, "loss": 0.9136, "step": 3025 }, { "epoch": 0.55, "learning_rate": 2.1825325144508674e-05, "loss": 0.7876, "step": 3026 }, { "epoch": 0.55, "learning_rate": 2.1822615606936415e-05, "loss": 0.5221, "step": 3027 }, { "epoch": 0.55, "learning_rate": 2.1819906069364162e-05, "loss": 0.8083, "step": 3028 }, { "epoch": 0.55, "learning_rate": 2.1817196531791907e-05, "loss": 0.9517, "step": 3029 }, { "epoch": 0.55, "learning_rate": 2.1814486994219654e-05, "loss": 0.6924, "step": 3030 }, { "epoch": 0.55, "learning_rate": 2.18117774566474e-05, "loss": 0.8476, "step": 3031 }, { "epoch": 0.55, "learning_rate": 2.1809067919075143e-05, "loss": 0.7538, "step": 3032 }, { "epoch": 0.55, "learning_rate": 2.180635838150289e-05, "loss": 0.9335, "step": 3033 }, { "epoch": 0.55, "learning_rate": 2.1803648843930635e-05, "loss": 0.4966, "step": 3034 }, { "epoch": 0.55, "learning_rate": 2.1800939306358383e-05, "loss": 0.7655, "step": 3035 }, { "epoch": 0.55, "learning_rate": 2.1798229768786127e-05, "loss": 0.4386, "step": 3036 }, { "epoch": 0.55, "learning_rate": 2.1795520231213872e-05, "loss": 0.7006, "step": 3037 }, { "epoch": 0.55, "learning_rate": 2.179281069364162e-05, "loss": 1.158, "step": 3038 }, { "epoch": 0.55, "learning_rate": 2.1790101156069367e-05, "loss": 0.934, "step": 3039 }, { "epoch": 0.55, "learning_rate": 2.178739161849711e-05, "loss": 0.9069, "step": 3040 }, { "epoch": 0.55, "learning_rate": 2.1784682080924856e-05, "loss": 1.3131, "step": 3041 }, { "epoch": 0.55, "learning_rate": 2.17819725433526e-05, "loss": 0.8766, "step": 3042 }, { "epoch": 0.55, "learning_rate": 2.1779263005780348e-05, "loss": 0.7318, "step": 3043 }, { "epoch": 0.55, "learning_rate": 2.1776553468208096e-05, "loss": 1.943, "step": 3044 }, { "epoch": 0.55, "learning_rate": 2.1773843930635837e-05, "loss": 1.3327, "step": 3045 }, { "epoch": 0.55, "learning_rate": 2.1771134393063585e-05, "loss": 0.7417, "step": 3046 }, { "epoch": 0.55, "learning_rate": 2.176842485549133e-05, "loss": 0.7493, "step": 3047 }, { "epoch": 0.55, "learning_rate": 2.1765715317919077e-05, "loss": 0.791, "step": 3048 }, { "epoch": 0.55, "learning_rate": 2.1763005780346824e-05, "loss": 1.0875, "step": 3049 }, { "epoch": 0.55, "learning_rate": 2.1760296242774565e-05, "loss": 0.9855, "step": 3050 }, { "epoch": 0.55, "learning_rate": 2.1757586705202313e-05, "loss": 0.9673, "step": 3051 }, { "epoch": 0.55, "learning_rate": 2.1754877167630058e-05, "loss": 0.2947, "step": 3052 }, { "epoch": 0.55, "learning_rate": 2.1752167630057805e-05, "loss": 0.775, "step": 3053 }, { "epoch": 0.55, "learning_rate": 2.174945809248555e-05, "loss": 0.8208, "step": 3054 }, { "epoch": 0.55, "learning_rate": 2.1746748554913294e-05, "loss": 0.6068, "step": 3055 }, { "epoch": 0.55, "learning_rate": 2.1744039017341042e-05, "loss": 1.2534, "step": 3056 }, { "epoch": 0.55, "learning_rate": 2.1741329479768786e-05, "loss": 0.7936, "step": 3057 }, { "epoch": 0.55, "learning_rate": 2.1738619942196534e-05, "loss": 1.2413, "step": 3058 }, { "epoch": 0.55, "learning_rate": 2.1735910404624278e-05, "loss": 0.6828, "step": 3059 }, { "epoch": 0.55, "learning_rate": 2.1733200867052023e-05, "loss": 0.8441, "step": 3060 }, { "epoch": 0.55, "learning_rate": 2.173049132947977e-05, "loss": 0.8858, "step": 3061 }, { "epoch": 0.55, "learning_rate": 2.1727781791907515e-05, "loss": 1.5508, "step": 3062 }, { "epoch": 0.55, "learning_rate": 2.1725072254335263e-05, "loss": 0.5825, "step": 3063 }, { "epoch": 0.55, "learning_rate": 2.1722362716763007e-05, "loss": 0.2554, "step": 3064 }, { "epoch": 0.55, "learning_rate": 2.171965317919075e-05, "loss": 0.9209, "step": 3065 }, { "epoch": 0.55, "learning_rate": 2.17169436416185e-05, "loss": 0.7346, "step": 3066 }, { "epoch": 0.55, "learning_rate": 2.1714234104046243e-05, "loss": 0.8166, "step": 3067 }, { "epoch": 0.55, "learning_rate": 2.1711524566473988e-05, "loss": 0.3396, "step": 3068 }, { "epoch": 0.55, "learning_rate": 2.1708815028901735e-05, "loss": 0.6872, "step": 3069 }, { "epoch": 0.55, "learning_rate": 2.170610549132948e-05, "loss": 0.73, "step": 3070 }, { "epoch": 0.55, "learning_rate": 2.1703395953757228e-05, "loss": 1.182, "step": 3071 }, { "epoch": 0.55, "learning_rate": 2.1700686416184972e-05, "loss": 0.6067, "step": 3072 }, { "epoch": 0.56, "learning_rate": 2.1697976878612716e-05, "loss": 0.7613, "step": 3073 }, { "epoch": 0.56, "learning_rate": 2.1695267341040464e-05, "loss": 1.4713, "step": 3074 }, { "epoch": 0.56, "learning_rate": 2.169255780346821e-05, "loss": 1.5323, "step": 3075 }, { "epoch": 0.56, "learning_rate": 2.1689848265895956e-05, "loss": 1.0138, "step": 3076 }, { "epoch": 0.56, "learning_rate": 2.1687138728323697e-05, "loss": 0.693, "step": 3077 }, { "epoch": 0.56, "learning_rate": 2.1684429190751445e-05, "loss": 0.9905, "step": 3078 }, { "epoch": 0.56, "learning_rate": 2.1681719653179193e-05, "loss": 1.1899, "step": 3079 }, { "epoch": 0.56, "learning_rate": 2.1679010115606937e-05, "loss": 0.4932, "step": 3080 }, { "epoch": 0.56, "learning_rate": 2.1676300578034685e-05, "loss": 0.8528, "step": 3081 }, { "epoch": 0.56, "learning_rate": 2.1673591040462426e-05, "loss": 0.8346, "step": 3082 }, { "epoch": 0.56, "learning_rate": 2.1670881502890174e-05, "loss": 0.6459, "step": 3083 }, { "epoch": 0.56, "learning_rate": 2.166817196531792e-05, "loss": 1.1557, "step": 3084 }, { "epoch": 0.56, "learning_rate": 2.1665462427745666e-05, "loss": 0.7812, "step": 3085 }, { "epoch": 0.56, "learning_rate": 2.1662752890173413e-05, "loss": 0.3497, "step": 3086 }, { "epoch": 0.56, "learning_rate": 2.1660043352601154e-05, "loss": 1.1342, "step": 3087 }, { "epoch": 0.56, "learning_rate": 2.1657333815028902e-05, "loss": 0.8211, "step": 3088 }, { "epoch": 0.56, "learning_rate": 2.165462427745665e-05, "loss": 1.3219, "step": 3089 }, { "epoch": 0.56, "learning_rate": 2.1651914739884394e-05, "loss": 0.5876, "step": 3090 }, { "epoch": 0.56, "learning_rate": 2.164920520231214e-05, "loss": 1.2181, "step": 3091 }, { "epoch": 0.56, "learning_rate": 2.1646495664739883e-05, "loss": 0.6881, "step": 3092 }, { "epoch": 0.56, "learning_rate": 2.164378612716763e-05, "loss": 0.3858, "step": 3093 }, { "epoch": 0.56, "learning_rate": 2.164107658959538e-05, "loss": 0.7849, "step": 3094 }, { "epoch": 0.56, "learning_rate": 2.1638367052023123e-05, "loss": 0.764, "step": 3095 }, { "epoch": 0.56, "learning_rate": 2.1635657514450867e-05, "loss": 1.6672, "step": 3096 }, { "epoch": 0.56, "learning_rate": 2.163294797687861e-05, "loss": 1.0461, "step": 3097 }, { "epoch": 0.56, "learning_rate": 2.163023843930636e-05, "loss": 0.9395, "step": 3098 }, { "epoch": 0.56, "learning_rate": 2.1627528901734107e-05, "loss": 1.6884, "step": 3099 }, { "epoch": 0.56, "learning_rate": 2.1624819364161848e-05, "loss": 0.4377, "step": 3100 }, { "epoch": 0.56, "learning_rate": 2.1622109826589596e-05, "loss": 1.0672, "step": 3101 }, { "epoch": 0.56, "learning_rate": 2.161940028901734e-05, "loss": 0.4559, "step": 3102 }, { "epoch": 0.56, "learning_rate": 2.1616690751445088e-05, "loss": 0.5955, "step": 3103 }, { "epoch": 0.56, "learning_rate": 2.1613981213872836e-05, "loss": 0.6201, "step": 3104 }, { "epoch": 0.56, "learning_rate": 2.1611271676300577e-05, "loss": 0.652, "step": 3105 }, { "epoch": 0.56, "learning_rate": 2.1608562138728324e-05, "loss": 0.7101, "step": 3106 }, { "epoch": 0.56, "learning_rate": 2.160585260115607e-05, "loss": 0.5116, "step": 3107 }, { "epoch": 0.56, "learning_rate": 2.1603143063583817e-05, "loss": 0.6634, "step": 3108 }, { "epoch": 0.56, "learning_rate": 2.1600433526011564e-05, "loss": 0.6975, "step": 3109 }, { "epoch": 0.56, "learning_rate": 2.1597723988439305e-05, "loss": 1.0014, "step": 3110 }, { "epoch": 0.56, "learning_rate": 2.1595014450867053e-05, "loss": 0.565, "step": 3111 }, { "epoch": 0.56, "learning_rate": 2.1592304913294797e-05, "loss": 0.8997, "step": 3112 }, { "epoch": 0.56, "learning_rate": 2.1589595375722545e-05, "loss": 0.6122, "step": 3113 }, { "epoch": 0.56, "learning_rate": 2.158688583815029e-05, "loss": 0.2757, "step": 3114 }, { "epoch": 0.56, "learning_rate": 2.1584176300578034e-05, "loss": 0.5653, "step": 3115 }, { "epoch": 0.56, "learning_rate": 2.158146676300578e-05, "loss": 1.1694, "step": 3116 }, { "epoch": 0.56, "learning_rate": 2.1578757225433526e-05, "loss": 0.5857, "step": 3117 }, { "epoch": 0.56, "learning_rate": 2.1576047687861274e-05, "loss": 0.8024, "step": 3118 }, { "epoch": 0.56, "learning_rate": 2.1573338150289018e-05, "loss": 0.82, "step": 3119 }, { "epoch": 0.56, "learning_rate": 2.1570628612716762e-05, "loss": 1.5383, "step": 3120 }, { "epoch": 0.56, "learning_rate": 2.156791907514451e-05, "loss": 1.0384, "step": 3121 }, { "epoch": 0.56, "learning_rate": 2.1565209537572255e-05, "loss": 1.1389, "step": 3122 }, { "epoch": 0.56, "learning_rate": 2.15625e-05, "loss": 0.9854, "step": 3123 }, { "epoch": 0.56, "learning_rate": 2.1559790462427747e-05, "loss": 1.8485, "step": 3124 }, { "epoch": 0.56, "learning_rate": 2.155708092485549e-05, "loss": 1.3074, "step": 3125 }, { "epoch": 0.56, "learning_rate": 2.155437138728324e-05, "loss": 0.2869, "step": 3126 }, { "epoch": 0.56, "learning_rate": 2.1551661849710983e-05, "loss": 1.1044, "step": 3127 }, { "epoch": 0.57, "learning_rate": 2.1548952312138728e-05, "loss": 0.5986, "step": 3128 }, { "epoch": 0.57, "learning_rate": 2.1546242774566475e-05, "loss": 1.0621, "step": 3129 }, { "epoch": 0.57, "learning_rate": 2.154353323699422e-05, "loss": 1.5978, "step": 3130 }, { "epoch": 0.57, "learning_rate": 2.1540823699421967e-05, "loss": 0.5998, "step": 3131 }, { "epoch": 0.57, "learning_rate": 2.1538114161849712e-05, "loss": 0.3882, "step": 3132 }, { "epoch": 0.57, "learning_rate": 2.1535404624277456e-05, "loss": 0.8277, "step": 3133 }, { "epoch": 0.57, "learning_rate": 2.1532695086705204e-05, "loss": 0.6431, "step": 3134 }, { "epoch": 0.57, "learning_rate": 2.1529985549132948e-05, "loss": 1.4651, "step": 3135 }, { "epoch": 0.57, "learning_rate": 2.1527276011560696e-05, "loss": 0.6816, "step": 3136 }, { "epoch": 0.57, "learning_rate": 2.1524566473988437e-05, "loss": 1.0815, "step": 3137 }, { "epoch": 0.57, "learning_rate": 2.1521856936416185e-05, "loss": 0.7612, "step": 3138 }, { "epoch": 0.57, "learning_rate": 2.1519147398843933e-05, "loss": 1.128, "step": 3139 }, { "epoch": 0.57, "learning_rate": 2.1516437861271677e-05, "loss": 0.6284, "step": 3140 }, { "epoch": 0.57, "learning_rate": 2.1513728323699425e-05, "loss": 0.6408, "step": 3141 }, { "epoch": 0.57, "learning_rate": 2.1511018786127166e-05, "loss": 0.8299, "step": 3142 }, { "epoch": 0.57, "learning_rate": 2.1508309248554913e-05, "loss": 0.4095, "step": 3143 }, { "epoch": 0.57, "learning_rate": 2.150559971098266e-05, "loss": 0.9572, "step": 3144 }, { "epoch": 0.57, "learning_rate": 2.1502890173410405e-05, "loss": 0.4953, "step": 3145 }, { "epoch": 0.57, "learning_rate": 2.150018063583815e-05, "loss": 0.9145, "step": 3146 }, { "epoch": 0.57, "learning_rate": 2.1497471098265894e-05, "loss": 0.6608, "step": 3147 }, { "epoch": 0.57, "learning_rate": 2.1494761560693642e-05, "loss": 0.8764, "step": 3148 }, { "epoch": 0.57, "learning_rate": 2.149205202312139e-05, "loss": 0.5719, "step": 3149 }, { "epoch": 0.57, "learning_rate": 2.1489342485549134e-05, "loss": 1.2188, "step": 3150 }, { "epoch": 0.57, "learning_rate": 2.148663294797688e-05, "loss": 0.8257, "step": 3151 }, { "epoch": 0.57, "learning_rate": 2.1483923410404623e-05, "loss": 1.772, "step": 3152 }, { "epoch": 0.57, "learning_rate": 2.148121387283237e-05, "loss": 0.6303, "step": 3153 }, { "epoch": 0.57, "learning_rate": 2.147850433526012e-05, "loss": 0.7691, "step": 3154 }, { "epoch": 0.57, "learning_rate": 2.1475794797687863e-05, "loss": 0.5151, "step": 3155 }, { "epoch": 0.57, "learning_rate": 2.1473085260115607e-05, "loss": 0.672, "step": 3156 }, { "epoch": 0.57, "learning_rate": 2.147037572254335e-05, "loss": 1.436, "step": 3157 }, { "epoch": 0.57, "learning_rate": 2.14676661849711e-05, "loss": 0.4333, "step": 3158 }, { "epoch": 0.57, "learning_rate": 2.1464956647398847e-05, "loss": 0.6994, "step": 3159 }, { "epoch": 0.57, "learning_rate": 2.1462247109826588e-05, "loss": 1.0319, "step": 3160 }, { "epoch": 0.57, "learning_rate": 2.1459537572254336e-05, "loss": 0.8697, "step": 3161 }, { "epoch": 0.57, "learning_rate": 2.145682803468208e-05, "loss": 1.3997, "step": 3162 }, { "epoch": 0.57, "learning_rate": 2.1454118497109828e-05, "loss": 0.7674, "step": 3163 }, { "epoch": 0.57, "learning_rate": 2.1451408959537576e-05, "loss": 0.4313, "step": 3164 }, { "epoch": 0.57, "learning_rate": 2.1448699421965317e-05, "loss": 1.3982, "step": 3165 }, { "epoch": 0.57, "learning_rate": 2.1445989884393064e-05, "loss": 1.2112, "step": 3166 }, { "epoch": 0.57, "learning_rate": 2.144328034682081e-05, "loss": 0.664, "step": 3167 }, { "epoch": 0.57, "learning_rate": 2.1440570809248556e-05, "loss": 0.6995, "step": 3168 }, { "epoch": 0.57, "learning_rate": 2.14378612716763e-05, "loss": 0.5756, "step": 3169 }, { "epoch": 0.57, "learning_rate": 2.1435151734104045e-05, "loss": 0.9293, "step": 3170 }, { "epoch": 0.57, "learning_rate": 2.1432442196531793e-05, "loss": 0.8616, "step": 3171 }, { "epoch": 0.57, "learning_rate": 2.1429732658959537e-05, "loss": 1.6356, "step": 3172 }, { "epoch": 0.57, "learning_rate": 2.1427023121387285e-05, "loss": 0.4932, "step": 3173 }, { "epoch": 0.57, "learning_rate": 2.142431358381503e-05, "loss": 0.8239, "step": 3174 }, { "epoch": 0.57, "learning_rate": 2.1421604046242774e-05, "loss": 0.5364, "step": 3175 }, { "epoch": 0.57, "learning_rate": 2.141889450867052e-05, "loss": 0.8248, "step": 3176 }, { "epoch": 0.57, "learning_rate": 2.1416184971098266e-05, "loss": 0.4547, "step": 3177 }, { "epoch": 0.57, "learning_rate": 2.1413475433526014e-05, "loss": 0.4442, "step": 3178 }, { "epoch": 0.57, "learning_rate": 2.1410765895953758e-05, "loss": 0.4576, "step": 3179 }, { "epoch": 0.57, "learning_rate": 2.1408056358381502e-05, "loss": 0.6111, "step": 3180 }, { "epoch": 0.57, "learning_rate": 2.140534682080925e-05, "loss": 1.3223, "step": 3181 }, { "epoch": 0.57, "learning_rate": 2.1402637283236994e-05, "loss": 1.1982, "step": 3182 }, { "epoch": 0.57, "learning_rate": 2.139992774566474e-05, "loss": 0.5145, "step": 3183 }, { "epoch": 0.58, "learning_rate": 2.1397218208092487e-05, "loss": 0.3892, "step": 3184 }, { "epoch": 0.58, "learning_rate": 2.139450867052023e-05, "loss": 0.7509, "step": 3185 }, { "epoch": 0.58, "learning_rate": 2.139179913294798e-05, "loss": 0.2253, "step": 3186 }, { "epoch": 0.58, "learning_rate": 2.1389089595375723e-05, "loss": 0.8304, "step": 3187 }, { "epoch": 0.58, "learning_rate": 2.1386380057803467e-05, "loss": 1.5142, "step": 3188 }, { "epoch": 0.58, "learning_rate": 2.1383670520231215e-05, "loss": 0.7615, "step": 3189 }, { "epoch": 0.58, "learning_rate": 2.138096098265896e-05, "loss": 1.1176, "step": 3190 }, { "epoch": 0.58, "learning_rate": 2.1378251445086707e-05, "loss": 1.0705, "step": 3191 }, { "epoch": 0.58, "learning_rate": 2.1375541907514448e-05, "loss": 0.8628, "step": 3192 }, { "epoch": 0.58, "learning_rate": 2.1372832369942196e-05, "loss": 1.8068, "step": 3193 }, { "epoch": 0.58, "learning_rate": 2.1370122832369944e-05, "loss": 0.8208, "step": 3194 }, { "epoch": 0.58, "learning_rate": 2.1367413294797688e-05, "loss": 2.2599, "step": 3195 }, { "epoch": 0.58, "learning_rate": 2.1364703757225436e-05, "loss": 1.394, "step": 3196 }, { "epoch": 0.58, "learning_rate": 2.1361994219653177e-05, "loss": 0.6084, "step": 3197 }, { "epoch": 0.58, "learning_rate": 2.1359284682080925e-05, "loss": 1.0699, "step": 3198 }, { "epoch": 0.58, "learning_rate": 2.1356575144508672e-05, "loss": 0.8512, "step": 3199 }, { "epoch": 0.58, "learning_rate": 2.1353865606936417e-05, "loss": 0.8059, "step": 3200 }, { "epoch": 0.58, "learning_rate": 2.135115606936416e-05, "loss": 0.9395, "step": 3201 }, { "epoch": 0.58, "learning_rate": 2.1348446531791905e-05, "loss": 1.1725, "step": 3202 }, { "epoch": 0.58, "learning_rate": 2.1345736994219653e-05, "loss": 0.5417, "step": 3203 }, { "epoch": 0.58, "learning_rate": 2.13430274566474e-05, "loss": 0.7869, "step": 3204 }, { "epoch": 0.58, "learning_rate": 2.1340317919075145e-05, "loss": 0.4165, "step": 3205 }, { "epoch": 0.58, "learning_rate": 2.133760838150289e-05, "loss": 0.9491, "step": 3206 }, { "epoch": 0.58, "learning_rate": 2.1334898843930634e-05, "loss": 1.3131, "step": 3207 }, { "epoch": 0.58, "learning_rate": 2.1332189306358382e-05, "loss": 1.3351, "step": 3208 }, { "epoch": 0.58, "learning_rate": 2.132947976878613e-05, "loss": 0.684, "step": 3209 }, { "epoch": 0.58, "learning_rate": 2.1326770231213874e-05, "loss": 1.122, "step": 3210 }, { "epoch": 0.58, "learning_rate": 2.1324060693641618e-05, "loss": 0.9345, "step": 3211 }, { "epoch": 0.58, "learning_rate": 2.1321351156069366e-05, "loss": 0.951, "step": 3212 }, { "epoch": 0.58, "learning_rate": 2.131864161849711e-05, "loss": 0.7729, "step": 3213 }, { "epoch": 0.58, "learning_rate": 2.1315932080924858e-05, "loss": 0.9613, "step": 3214 }, { "epoch": 0.58, "learning_rate": 2.13132225433526e-05, "loss": 1.4033, "step": 3215 }, { "epoch": 0.58, "learning_rate": 2.1310513005780347e-05, "loss": 0.7867, "step": 3216 }, { "epoch": 0.58, "learning_rate": 2.1307803468208095e-05, "loss": 1.2851, "step": 3217 }, { "epoch": 0.58, "learning_rate": 2.130509393063584e-05, "loss": 1.3483, "step": 3218 }, { "epoch": 0.58, "learning_rate": 2.1302384393063587e-05, "loss": 0.6644, "step": 3219 }, { "epoch": 0.58, "learning_rate": 2.1299674855491328e-05, "loss": 0.4983, "step": 3220 }, { "epoch": 0.58, "learning_rate": 2.1296965317919075e-05, "loss": 0.4237, "step": 3221 }, { "epoch": 0.58, "learning_rate": 2.1294255780346823e-05, "loss": 0.6656, "step": 3222 }, { "epoch": 0.58, "learning_rate": 2.1291546242774568e-05, "loss": 0.6405, "step": 3223 }, { "epoch": 0.58, "learning_rate": 2.1288836705202312e-05, "loss": 0.9094, "step": 3224 }, { "epoch": 0.58, "learning_rate": 2.1286127167630056e-05, "loss": 0.3949, "step": 3225 }, { "epoch": 0.58, "learning_rate": 2.1283417630057804e-05, "loss": 0.9697, "step": 3226 }, { "epoch": 0.58, "learning_rate": 2.1280708092485552e-05, "loss": 1.2291, "step": 3227 }, { "epoch": 0.58, "learning_rate": 2.1277998554913296e-05, "loss": 0.7403, "step": 3228 }, { "epoch": 0.58, "learning_rate": 2.127528901734104e-05, "loss": 0.9347, "step": 3229 }, { "epoch": 0.58, "learning_rate": 2.1272579479768785e-05, "loss": 0.5009, "step": 3230 }, { "epoch": 0.58, "learning_rate": 2.1269869942196533e-05, "loss": 0.5044, "step": 3231 }, { "epoch": 0.58, "learning_rate": 2.126716040462428e-05, "loss": 0.4772, "step": 3232 }, { "epoch": 0.58, "learning_rate": 2.1264450867052025e-05, "loss": 1.1203, "step": 3233 }, { "epoch": 0.58, "learning_rate": 2.126174132947977e-05, "loss": 0.6899, "step": 3234 }, { "epoch": 0.58, "learning_rate": 2.1259031791907514e-05, "loss": 0.8563, "step": 3235 }, { "epoch": 0.58, "learning_rate": 2.125632225433526e-05, "loss": 1.1446, "step": 3236 }, { "epoch": 0.58, "learning_rate": 2.125361271676301e-05, "loss": 1.1238, "step": 3237 }, { "epoch": 0.58, "learning_rate": 2.125090317919075e-05, "loss": 0.414, "step": 3238 }, { "epoch": 0.59, "learning_rate": 2.1248193641618498e-05, "loss": 0.3525, "step": 3239 }, { "epoch": 0.59, "learning_rate": 2.1245484104046242e-05, "loss": 1.1919, "step": 3240 }, { "epoch": 0.59, "learning_rate": 2.124277456647399e-05, "loss": 0.8968, "step": 3241 }, { "epoch": 0.59, "learning_rate": 2.1240065028901738e-05, "loss": 0.5821, "step": 3242 }, { "epoch": 0.59, "learning_rate": 2.123735549132948e-05, "loss": 0.5038, "step": 3243 }, { "epoch": 0.59, "learning_rate": 2.1234645953757226e-05, "loss": 0.8744, "step": 3244 }, { "epoch": 0.59, "learning_rate": 2.123193641618497e-05, "loss": 0.271, "step": 3245 }, { "epoch": 0.59, "learning_rate": 2.122922687861272e-05, "loss": 0.69, "step": 3246 }, { "epoch": 0.59, "learning_rate": 2.1226517341040463e-05, "loss": 1.6383, "step": 3247 }, { "epoch": 0.59, "learning_rate": 2.1223807803468207e-05, "loss": 1.2599, "step": 3248 }, { "epoch": 0.59, "learning_rate": 2.1221098265895955e-05, "loss": 0.8696, "step": 3249 }, { "epoch": 0.59, "learning_rate": 2.12183887283237e-05, "loss": 1.05, "step": 3250 }, { "epoch": 0.59, "learning_rate": 2.1215679190751447e-05, "loss": 0.2266, "step": 3251 }, { "epoch": 0.59, "learning_rate": 2.121296965317919e-05, "loss": 0.7851, "step": 3252 }, { "epoch": 0.59, "learning_rate": 2.1210260115606936e-05, "loss": 0.4638, "step": 3253 }, { "epoch": 0.59, "learning_rate": 2.1207550578034684e-05, "loss": 1.0902, "step": 3254 }, { "epoch": 0.59, "learning_rate": 2.1204841040462428e-05, "loss": 0.4284, "step": 3255 }, { "epoch": 0.59, "learning_rate": 2.1202131502890176e-05, "loss": 1.5547, "step": 3256 }, { "epoch": 0.59, "learning_rate": 2.119942196531792e-05, "loss": 1.0809, "step": 3257 }, { "epoch": 0.59, "learning_rate": 2.1196712427745664e-05, "loss": 0.835, "step": 3258 }, { "epoch": 0.59, "learning_rate": 2.1194002890173412e-05, "loss": 0.7419, "step": 3259 }, { "epoch": 0.59, "learning_rate": 2.1191293352601157e-05, "loss": 0.6398, "step": 3260 }, { "epoch": 0.59, "learning_rate": 2.11885838150289e-05, "loss": 1.0624, "step": 3261 }, { "epoch": 0.59, "learning_rate": 2.118587427745665e-05, "loss": 0.8476, "step": 3262 }, { "epoch": 0.59, "learning_rate": 2.1183164739884393e-05, "loss": 0.9236, "step": 3263 }, { "epoch": 0.59, "learning_rate": 2.118045520231214e-05, "loss": 0.7368, "step": 3264 }, { "epoch": 0.59, "learning_rate": 2.1177745664739885e-05, "loss": 1.3699, "step": 3265 }, { "epoch": 0.59, "learning_rate": 2.117503612716763e-05, "loss": 0.4144, "step": 3266 }, { "epoch": 0.59, "learning_rate": 2.1172326589595377e-05, "loss": 0.6381, "step": 3267 }, { "epoch": 0.59, "learning_rate": 2.116961705202312e-05, "loss": 1.4598, "step": 3268 }, { "epoch": 0.59, "learning_rate": 2.116690751445087e-05, "loss": 0.4784, "step": 3269 }, { "epoch": 0.59, "learning_rate": 2.116419797687861e-05, "loss": 0.5017, "step": 3270 }, { "epoch": 0.59, "learning_rate": 2.1161488439306358e-05, "loss": 1.3265, "step": 3271 }, { "epoch": 0.59, "learning_rate": 2.1158778901734106e-05, "loss": 0.8943, "step": 3272 }, { "epoch": 0.59, "learning_rate": 2.115606936416185e-05, "loss": 1.3581, "step": 3273 }, { "epoch": 0.59, "learning_rate": 2.1153359826589598e-05, "loss": 0.971, "step": 3274 }, { "epoch": 0.59, "learning_rate": 2.115065028901734e-05, "loss": 0.8173, "step": 3275 }, { "epoch": 0.59, "learning_rate": 2.1147940751445087e-05, "loss": 0.634, "step": 3276 }, { "epoch": 0.59, "learning_rate": 2.1145231213872834e-05, "loss": 1.5085, "step": 3277 }, { "epoch": 0.59, "learning_rate": 2.114252167630058e-05, "loss": 0.4898, "step": 3278 }, { "epoch": 0.59, "learning_rate": 2.1139812138728327e-05, "loss": 0.9526, "step": 3279 }, { "epoch": 0.59, "learning_rate": 2.1137102601156068e-05, "loss": 0.6453, "step": 3280 }, { "epoch": 0.59, "learning_rate": 2.1134393063583815e-05, "loss": 0.4233, "step": 3281 }, { "epoch": 0.59, "learning_rate": 2.1131683526011563e-05, "loss": 0.9951, "step": 3282 }, { "epoch": 0.59, "learning_rate": 2.1128973988439307e-05, "loss": 1.0679, "step": 3283 }, { "epoch": 0.59, "learning_rate": 2.1126264450867052e-05, "loss": 1.3468, "step": 3284 }, { "epoch": 0.59, "learning_rate": 2.1123554913294796e-05, "loss": 1.3632, "step": 3285 }, { "epoch": 0.59, "learning_rate": 2.1120845375722544e-05, "loss": 1.1084, "step": 3286 }, { "epoch": 0.59, "learning_rate": 2.111813583815029e-05, "loss": 1.0467, "step": 3287 }, { "epoch": 0.59, "learning_rate": 2.1115426300578036e-05, "loss": 0.7623, "step": 3288 }, { "epoch": 0.59, "learning_rate": 2.111271676300578e-05, "loss": 1.4464, "step": 3289 }, { "epoch": 0.59, "learning_rate": 2.1110007225433525e-05, "loss": 1.6201, "step": 3290 }, { "epoch": 0.59, "learning_rate": 2.1107297687861273e-05, "loss": 0.8281, "step": 3291 }, { "epoch": 0.59, "learning_rate": 2.110458815028902e-05, "loss": 1.5354, "step": 3292 }, { "epoch": 0.59, "learning_rate": 2.110187861271676e-05, "loss": 1.1261, "step": 3293 }, { "epoch": 0.6, "learning_rate": 2.109916907514451e-05, "loss": 1.3538, "step": 3294 }, { "epoch": 0.6, "learning_rate": 2.1096459537572253e-05, "loss": 0.9916, "step": 3295 }, { "epoch": 0.6, "learning_rate": 2.109375e-05, "loss": 1.171, "step": 3296 }, { "epoch": 0.6, "learning_rate": 2.109104046242775e-05, "loss": 0.6087, "step": 3297 }, { "epoch": 0.6, "learning_rate": 2.108833092485549e-05, "loss": 0.8662, "step": 3298 }, { "epoch": 0.6, "learning_rate": 2.1085621387283238e-05, "loss": 1.1374, "step": 3299 }, { "epoch": 0.6, "learning_rate": 2.1082911849710982e-05, "loss": 0.5731, "step": 3300 }, { "epoch": 0.6, "learning_rate": 2.108020231213873e-05, "loss": 0.8187, "step": 3301 }, { "epoch": 0.6, "learning_rate": 2.1077492774566477e-05, "loss": 0.5672, "step": 3302 }, { "epoch": 0.6, "learning_rate": 2.107478323699422e-05, "loss": 1.1373, "step": 3303 }, { "epoch": 0.6, "learning_rate": 2.1072073699421966e-05, "loss": 0.7806, "step": 3304 }, { "epoch": 0.6, "learning_rate": 2.106936416184971e-05, "loss": 0.9503, "step": 3305 }, { "epoch": 0.6, "learning_rate": 2.106665462427746e-05, "loss": 0.8627, "step": 3306 }, { "epoch": 0.6, "learning_rate": 2.1063945086705203e-05, "loss": 0.5975, "step": 3307 }, { "epoch": 0.6, "learning_rate": 2.1061235549132947e-05, "loss": 0.7266, "step": 3308 }, { "epoch": 0.6, "learning_rate": 2.1058526011560695e-05, "loss": 0.8919, "step": 3309 }, { "epoch": 0.6, "learning_rate": 2.105581647398844e-05, "loss": 0.5119, "step": 3310 }, { "epoch": 0.6, "learning_rate": 2.1053106936416187e-05, "loss": 0.3681, "step": 3311 }, { "epoch": 0.6, "learning_rate": 2.105039739884393e-05, "loss": 0.6784, "step": 3312 }, { "epoch": 0.6, "learning_rate": 2.1047687861271676e-05, "loss": 1.2086, "step": 3313 }, { "epoch": 0.6, "learning_rate": 2.1044978323699423e-05, "loss": 0.9783, "step": 3314 }, { "epoch": 0.6, "learning_rate": 2.1042268786127168e-05, "loss": 0.4279, "step": 3315 }, { "epoch": 0.6, "learning_rate": 2.1039559248554912e-05, "loss": 1.0525, "step": 3316 }, { "epoch": 0.6, "learning_rate": 2.103684971098266e-05, "loss": 0.6834, "step": 3317 }, { "epoch": 0.6, "learning_rate": 2.1034140173410404e-05, "loss": 0.503, "step": 3318 }, { "epoch": 0.6, "learning_rate": 2.1031430635838152e-05, "loss": 1.2241, "step": 3319 }, { "epoch": 0.6, "learning_rate": 2.1028721098265896e-05, "loss": 0.6794, "step": 3320 }, { "epoch": 0.6, "learning_rate": 2.102601156069364e-05, "loss": 0.8125, "step": 3321 }, { "epoch": 0.6, "learning_rate": 2.102330202312139e-05, "loss": 0.4623, "step": 3322 }, { "epoch": 0.6, "learning_rate": 2.1020592485549133e-05, "loss": 1.0587, "step": 3323 }, { "epoch": 0.6, "learning_rate": 2.101788294797688e-05, "loss": 0.4994, "step": 3324 }, { "epoch": 0.6, "learning_rate": 2.1015173410404625e-05, "loss": 0.9835, "step": 3325 }, { "epoch": 0.6, "learning_rate": 2.101246387283237e-05, "loss": 1.0258, "step": 3326 }, { "epoch": 0.6, "learning_rate": 2.1009754335260117e-05, "loss": 1.0565, "step": 3327 }, { "epoch": 0.6, "learning_rate": 2.100704479768786e-05, "loss": 0.9826, "step": 3328 }, { "epoch": 0.6, "learning_rate": 2.100433526011561e-05, "loss": 0.5846, "step": 3329 }, { "epoch": 0.6, "learning_rate": 2.100162572254335e-05, "loss": 1.0053, "step": 3330 }, { "epoch": 0.6, "learning_rate": 2.0998916184971098e-05, "loss": 1.851, "step": 3331 }, { "epoch": 0.6, "learning_rate": 2.0996206647398846e-05, "loss": 0.7546, "step": 3332 }, { "epoch": 0.6, "learning_rate": 2.099349710982659e-05, "loss": 1.2027, "step": 3333 }, { "epoch": 0.6, "learning_rate": 2.0990787572254338e-05, "loss": 0.757, "step": 3334 }, { "epoch": 0.6, "learning_rate": 2.098807803468208e-05, "loss": 0.7171, "step": 3335 }, { "epoch": 0.6, "learning_rate": 2.0985368497109827e-05, "loss": 1.2744, "step": 3336 }, { "epoch": 0.6, "learning_rate": 2.0982658959537574e-05, "loss": 1.6111, "step": 3337 }, { "epoch": 0.6, "learning_rate": 2.097994942196532e-05, "loss": 0.7388, "step": 3338 }, { "epoch": 0.6, "learning_rate": 2.0977239884393063e-05, "loss": 0.9436, "step": 3339 }, { "epoch": 0.6, "learning_rate": 2.0974530346820807e-05, "loss": 0.7448, "step": 3340 }, { "epoch": 0.6, "learning_rate": 2.0971820809248555e-05, "loss": 0.7302, "step": 3341 }, { "epoch": 0.6, "learning_rate": 2.0969111271676303e-05, "loss": 0.3752, "step": 3342 }, { "epoch": 0.6, "learning_rate": 2.0966401734104047e-05, "loss": 0.4414, "step": 3343 }, { "epoch": 0.6, "learning_rate": 2.096369219653179e-05, "loss": 0.5818, "step": 3344 }, { "epoch": 0.6, "learning_rate": 2.0960982658959536e-05, "loss": 0.3105, "step": 3345 }, { "epoch": 0.6, "learning_rate": 2.0958273121387284e-05, "loss": 0.7342, "step": 3346 }, { "epoch": 0.6, "learning_rate": 2.095556358381503e-05, "loss": 0.8893, "step": 3347 }, { "epoch": 0.6, "learning_rate": 2.0952854046242776e-05, "loss": 0.8764, "step": 3348 }, { "epoch": 0.6, "learning_rate": 2.095014450867052e-05, "loss": 0.8873, "step": 3349 }, { "epoch": 0.61, "learning_rate": 2.0947434971098265e-05, "loss": 0.7036, "step": 3350 }, { "epoch": 0.61, "learning_rate": 2.0944725433526012e-05, "loss": 0.951, "step": 3351 }, { "epoch": 0.61, "learning_rate": 2.094201589595376e-05, "loss": 1.1543, "step": 3352 }, { "epoch": 0.61, "learning_rate": 2.09393063583815e-05, "loss": 0.8824, "step": 3353 }, { "epoch": 0.61, "learning_rate": 2.093659682080925e-05, "loss": 0.7772, "step": 3354 }, { "epoch": 0.61, "learning_rate": 2.0933887283236993e-05, "loss": 1.0093, "step": 3355 }, { "epoch": 0.61, "learning_rate": 2.093117774566474e-05, "loss": 0.6257, "step": 3356 }, { "epoch": 0.61, "learning_rate": 2.092846820809249e-05, "loss": 0.9903, "step": 3357 }, { "epoch": 0.61, "learning_rate": 2.092575867052023e-05, "loss": 1.235, "step": 3358 }, { "epoch": 0.61, "learning_rate": 2.0923049132947977e-05, "loss": 0.337, "step": 3359 }, { "epoch": 0.61, "learning_rate": 2.0920339595375722e-05, "loss": 2.0038, "step": 3360 }, { "epoch": 0.61, "learning_rate": 2.091763005780347e-05, "loss": 0.6988, "step": 3361 }, { "epoch": 0.61, "learning_rate": 2.0914920520231214e-05, "loss": 0.5839, "step": 3362 }, { "epoch": 0.61, "learning_rate": 2.0912210982658958e-05, "loss": 1.1135, "step": 3363 }, { "epoch": 0.61, "learning_rate": 2.0909501445086706e-05, "loss": 0.5698, "step": 3364 }, { "epoch": 0.61, "learning_rate": 2.090679190751445e-05, "loss": 1.4454, "step": 3365 }, { "epoch": 0.61, "learning_rate": 2.0904082369942198e-05, "loss": 1.0574, "step": 3366 }, { "epoch": 0.61, "learning_rate": 2.0901372832369943e-05, "loss": 0.4931, "step": 3367 }, { "epoch": 0.61, "learning_rate": 2.0898663294797687e-05, "loss": 0.5744, "step": 3368 }, { "epoch": 0.61, "learning_rate": 2.0895953757225435e-05, "loss": 1.2175, "step": 3369 }, { "epoch": 0.61, "learning_rate": 2.089324421965318e-05, "loss": 0.9562, "step": 3370 }, { "epoch": 0.61, "learning_rate": 2.0890534682080927e-05, "loss": 1.2148, "step": 3371 }, { "epoch": 0.61, "learning_rate": 2.088782514450867e-05, "loss": 0.4641, "step": 3372 }, { "epoch": 0.61, "learning_rate": 2.0885115606936415e-05, "loss": 0.5793, "step": 3373 }, { "epoch": 0.61, "learning_rate": 2.0882406069364163e-05, "loss": 1.1007, "step": 3374 }, { "epoch": 0.61, "learning_rate": 2.0879696531791908e-05, "loss": 1.1971, "step": 3375 }, { "epoch": 0.61, "learning_rate": 2.0876986994219652e-05, "loss": 1.0025, "step": 3376 }, { "epoch": 0.61, "learning_rate": 2.08742774566474e-05, "loss": 1.3836, "step": 3377 }, { "epoch": 0.61, "learning_rate": 2.0871567919075144e-05, "loss": 0.768, "step": 3378 }, { "epoch": 0.61, "learning_rate": 2.0868858381502892e-05, "loss": 0.9656, "step": 3379 }, { "epoch": 0.61, "learning_rate": 2.0866148843930636e-05, "loss": 0.6972, "step": 3380 }, { "epoch": 0.61, "learning_rate": 2.086343930635838e-05, "loss": 0.9518, "step": 3381 }, { "epoch": 0.61, "learning_rate": 2.086072976878613e-05, "loss": 0.8719, "step": 3382 }, { "epoch": 0.61, "learning_rate": 2.0858020231213873e-05, "loss": 1.0145, "step": 3383 }, { "epoch": 0.61, "learning_rate": 2.085531069364162e-05, "loss": 0.399, "step": 3384 }, { "epoch": 0.61, "learning_rate": 2.0852601156069365e-05, "loss": 0.8319, "step": 3385 }, { "epoch": 0.61, "learning_rate": 2.084989161849711e-05, "loss": 0.6719, "step": 3386 }, { "epoch": 0.61, "learning_rate": 2.0847182080924857e-05, "loss": 0.7237, "step": 3387 }, { "epoch": 0.61, "learning_rate": 2.08444725433526e-05, "loss": 0.4788, "step": 3388 }, { "epoch": 0.61, "learning_rate": 2.084176300578035e-05, "loss": 0.5432, "step": 3389 }, { "epoch": 0.61, "learning_rate": 2.0839053468208093e-05, "loss": 0.8288, "step": 3390 }, { "epoch": 0.61, "learning_rate": 2.0836343930635838e-05, "loss": 0.5991, "step": 3391 }, { "epoch": 0.61, "learning_rate": 2.0833634393063586e-05, "loss": 0.6448, "step": 3392 }, { "epoch": 0.61, "learning_rate": 2.083092485549133e-05, "loss": 1.4215, "step": 3393 }, { "epoch": 0.61, "learning_rate": 2.0828215317919078e-05, "loss": 0.616, "step": 3394 }, { "epoch": 0.61, "learning_rate": 2.0825505780346822e-05, "loss": 0.6918, "step": 3395 }, { "epoch": 0.61, "learning_rate": 2.0822796242774566e-05, "loss": 0.6356, "step": 3396 }, { "epoch": 0.61, "learning_rate": 2.0820086705202314e-05, "loss": 0.8133, "step": 3397 }, { "epoch": 0.61, "learning_rate": 2.081737716763006e-05, "loss": 0.5187, "step": 3398 }, { "epoch": 0.61, "learning_rate": 2.0814667630057803e-05, "loss": 0.8348, "step": 3399 }, { "epoch": 0.61, "learning_rate": 2.081195809248555e-05, "loss": 1.7667, "step": 3400 }, { "epoch": 0.61, "learning_rate": 2.0809248554913295e-05, "loss": 0.5001, "step": 3401 }, { "epoch": 0.61, "learning_rate": 2.0806539017341043e-05, "loss": 0.9344, "step": 3402 }, { "epoch": 0.61, "learning_rate": 2.0803829479768787e-05, "loss": 0.9814, "step": 3403 }, { "epoch": 0.61, "learning_rate": 2.080111994219653e-05, "loss": 0.5543, "step": 3404 }, { "epoch": 0.62, "learning_rate": 2.079841040462428e-05, "loss": 0.383, "step": 3405 }, { "epoch": 0.62, "learning_rate": 2.0795700867052024e-05, "loss": 1.2322, "step": 3406 }, { "epoch": 0.62, "learning_rate": 2.079299132947977e-05, "loss": 1.2088, "step": 3407 }, { "epoch": 0.62, "learning_rate": 2.0790281791907512e-05, "loss": 1.0498, "step": 3408 }, { "epoch": 0.62, "learning_rate": 2.078757225433526e-05, "loss": 0.549, "step": 3409 }, { "epoch": 0.62, "learning_rate": 2.0784862716763008e-05, "loss": 0.8983, "step": 3410 }, { "epoch": 0.62, "learning_rate": 2.0782153179190752e-05, "loss": 0.8658, "step": 3411 }, { "epoch": 0.62, "learning_rate": 2.07794436416185e-05, "loss": 0.8512, "step": 3412 }, { "epoch": 0.62, "learning_rate": 2.077673410404624e-05, "loss": 0.8281, "step": 3413 }, { "epoch": 0.62, "learning_rate": 2.077402456647399e-05, "loss": 0.2129, "step": 3414 }, { "epoch": 0.62, "learning_rate": 2.0771315028901736e-05, "loss": 0.4965, "step": 3415 }, { "epoch": 0.62, "learning_rate": 2.076860549132948e-05, "loss": 0.2744, "step": 3416 }, { "epoch": 0.62, "learning_rate": 2.0765895953757225e-05, "loss": 0.8786, "step": 3417 }, { "epoch": 0.62, "learning_rate": 2.076318641618497e-05, "loss": 0.5723, "step": 3418 }, { "epoch": 0.62, "learning_rate": 2.0760476878612717e-05, "loss": 0.869, "step": 3419 }, { "epoch": 0.62, "learning_rate": 2.0757767341040465e-05, "loss": 0.742, "step": 3420 }, { "epoch": 0.62, "learning_rate": 2.075505780346821e-05, "loss": 0.6821, "step": 3421 }, { "epoch": 0.62, "learning_rate": 2.0752348265895954e-05, "loss": 1.5295, "step": 3422 }, { "epoch": 0.62, "learning_rate": 2.0749638728323698e-05, "loss": 0.5864, "step": 3423 }, { "epoch": 0.62, "learning_rate": 2.0746929190751446e-05, "loss": 0.3802, "step": 3424 }, { "epoch": 0.62, "learning_rate": 2.0744219653179194e-05, "loss": 1.1826, "step": 3425 }, { "epoch": 0.62, "learning_rate": 2.0741510115606938e-05, "loss": 0.9389, "step": 3426 }, { "epoch": 0.62, "learning_rate": 2.0738800578034682e-05, "loss": 0.8194, "step": 3427 }, { "epoch": 0.62, "learning_rate": 2.0736091040462427e-05, "loss": 1.6821, "step": 3428 }, { "epoch": 0.62, "learning_rate": 2.0733381502890174e-05, "loss": 0.7908, "step": 3429 }, { "epoch": 0.62, "learning_rate": 2.0730671965317922e-05, "loss": 0.6758, "step": 3430 }, { "epoch": 0.62, "learning_rate": 2.0727962427745663e-05, "loss": 1.1111, "step": 3431 }, { "epoch": 0.62, "learning_rate": 2.072525289017341e-05, "loss": 0.9068, "step": 3432 }, { "epoch": 0.62, "learning_rate": 2.0722543352601155e-05, "loss": 0.9783, "step": 3433 }, { "epoch": 0.62, "learning_rate": 2.0719833815028903e-05, "loss": 1.3714, "step": 3434 }, { "epoch": 0.62, "learning_rate": 2.071712427745665e-05, "loss": 0.9512, "step": 3435 }, { "epoch": 0.62, "learning_rate": 2.0714414739884392e-05, "loss": 0.4611, "step": 3436 }, { "epoch": 0.62, "learning_rate": 2.071170520231214e-05, "loss": 0.6178, "step": 3437 }, { "epoch": 0.62, "learning_rate": 2.0708995664739884e-05, "loss": 0.411, "step": 3438 }, { "epoch": 0.62, "learning_rate": 2.070628612716763e-05, "loss": 1.341, "step": 3439 }, { "epoch": 0.62, "learning_rate": 2.0703576589595376e-05, "loss": 0.7225, "step": 3440 }, { "epoch": 0.62, "learning_rate": 2.070086705202312e-05, "loss": 0.8242, "step": 3441 }, { "epoch": 0.62, "learning_rate": 2.0698157514450868e-05, "loss": 0.3163, "step": 3442 }, { "epoch": 0.62, "learning_rate": 2.0695447976878613e-05, "loss": 0.967, "step": 3443 }, { "epoch": 0.62, "learning_rate": 2.069273843930636e-05, "loss": 0.6757, "step": 3444 }, { "epoch": 0.62, "learning_rate": 2.0690028901734105e-05, "loss": 1.0251, "step": 3445 }, { "epoch": 0.62, "learning_rate": 2.068731936416185e-05, "loss": 0.7716, "step": 3446 }, { "epoch": 0.62, "learning_rate": 2.0684609826589597e-05, "loss": 0.3723, "step": 3447 }, { "epoch": 0.62, "learning_rate": 2.068190028901734e-05, "loss": 0.8182, "step": 3448 }, { "epoch": 0.62, "learning_rate": 2.067919075144509e-05, "loss": 0.7006, "step": 3449 }, { "epoch": 0.62, "learning_rate": 2.0676481213872833e-05, "loss": 0.5615, "step": 3450 }, { "epoch": 0.62, "learning_rate": 2.0673771676300578e-05, "loss": 0.8977, "step": 3451 }, { "epoch": 0.62, "learning_rate": 2.0671062138728325e-05, "loss": 1.1196, "step": 3452 }, { "epoch": 0.62, "learning_rate": 2.066835260115607e-05, "loss": 1.1605, "step": 3453 }, { "epoch": 0.62, "learning_rate": 2.0665643063583814e-05, "loss": 0.719, "step": 3454 }, { "epoch": 0.62, "learning_rate": 2.0662933526011562e-05, "loss": 1.6224, "step": 3455 }, { "epoch": 0.62, "learning_rate": 2.0660223988439306e-05, "loss": 0.744, "step": 3456 }, { "epoch": 0.62, "learning_rate": 2.0657514450867054e-05, "loss": 0.8692, "step": 3457 }, { "epoch": 0.62, "learning_rate": 2.06548049132948e-05, "loss": 1.1539, "step": 3458 }, { "epoch": 0.62, "learning_rate": 2.0652095375722543e-05, "loss": 0.5766, "step": 3459 }, { "epoch": 0.62, "learning_rate": 2.064938583815029e-05, "loss": 0.7041, "step": 3460 }, { "epoch": 0.63, "learning_rate": 2.0646676300578035e-05, "loss": 0.3304, "step": 3461 }, { "epoch": 0.63, "learning_rate": 2.0643966763005783e-05, "loss": 0.6541, "step": 3462 }, { "epoch": 0.63, "learning_rate": 2.0641257225433524e-05, "loss": 1.2081, "step": 3463 }, { "epoch": 0.63, "learning_rate": 2.063854768786127e-05, "loss": 0.7992, "step": 3464 }, { "epoch": 0.63, "learning_rate": 2.063583815028902e-05, "loss": 0.7478, "step": 3465 }, { "epoch": 0.63, "learning_rate": 2.0633128612716763e-05, "loss": 0.5797, "step": 3466 }, { "epoch": 0.63, "learning_rate": 2.063041907514451e-05, "loss": 0.5048, "step": 3467 }, { "epoch": 0.63, "learning_rate": 2.0627709537572252e-05, "loss": 0.5202, "step": 3468 }, { "epoch": 0.63, "learning_rate": 2.0625e-05, "loss": 0.6371, "step": 3469 }, { "epoch": 0.63, "learning_rate": 2.0622290462427748e-05, "loss": 1.7961, "step": 3470 }, { "epoch": 0.63, "learning_rate": 2.0619580924855492e-05, "loss": 0.5276, "step": 3471 }, { "epoch": 0.63, "learning_rate": 2.061687138728324e-05, "loss": 1.3309, "step": 3472 }, { "epoch": 0.63, "learning_rate": 2.061416184971098e-05, "loss": 0.7184, "step": 3473 }, { "epoch": 0.63, "learning_rate": 2.061145231213873e-05, "loss": 1.1433, "step": 3474 }, { "epoch": 0.63, "learning_rate": 2.0608742774566476e-05, "loss": 0.7049, "step": 3475 }, { "epoch": 0.63, "learning_rate": 2.060603323699422e-05, "loss": 0.9931, "step": 3476 }, { "epoch": 0.63, "learning_rate": 2.0603323699421965e-05, "loss": 0.5891, "step": 3477 }, { "epoch": 0.63, "learning_rate": 2.060061416184971e-05, "loss": 1.0913, "step": 3478 }, { "epoch": 0.63, "learning_rate": 2.0597904624277457e-05, "loss": 0.7436, "step": 3479 }, { "epoch": 0.63, "learning_rate": 2.0595195086705205e-05, "loss": 0.6945, "step": 3480 }, { "epoch": 0.63, "learning_rate": 2.059248554913295e-05, "loss": 1.1955, "step": 3481 }, { "epoch": 0.63, "learning_rate": 2.0589776011560694e-05, "loss": 0.6357, "step": 3482 }, { "epoch": 0.63, "learning_rate": 2.0587066473988438e-05, "loss": 1.0851, "step": 3483 }, { "epoch": 0.63, "learning_rate": 2.0584356936416186e-05, "loss": 0.3873, "step": 3484 }, { "epoch": 0.63, "learning_rate": 2.0581647398843933e-05, "loss": 1.0605, "step": 3485 }, { "epoch": 0.63, "learning_rate": 2.0578937861271674e-05, "loss": 0.6012, "step": 3486 }, { "epoch": 0.63, "learning_rate": 2.0576228323699422e-05, "loss": 1.6549, "step": 3487 }, { "epoch": 0.63, "learning_rate": 2.0573518786127167e-05, "loss": 0.9092, "step": 3488 }, { "epoch": 0.63, "learning_rate": 2.0570809248554914e-05, "loss": 0.8556, "step": 3489 }, { "epoch": 0.63, "learning_rate": 2.0568099710982662e-05, "loss": 0.6532, "step": 3490 }, { "epoch": 0.63, "learning_rate": 2.0565390173410403e-05, "loss": 0.5708, "step": 3491 }, { "epoch": 0.63, "learning_rate": 2.056268063583815e-05, "loss": 0.7661, "step": 3492 }, { "epoch": 0.63, "learning_rate": 2.0559971098265895e-05, "loss": 0.5632, "step": 3493 }, { "epoch": 0.63, "learning_rate": 2.0557261560693643e-05, "loss": 1.0514, "step": 3494 }, { "epoch": 0.63, "learning_rate": 2.055455202312139e-05, "loss": 0.6333, "step": 3495 }, { "epoch": 0.63, "learning_rate": 2.055184248554913e-05, "loss": 0.6605, "step": 3496 }, { "epoch": 0.63, "learning_rate": 2.054913294797688e-05, "loss": 0.7292, "step": 3497 }, { "epoch": 0.63, "learning_rate": 2.0546423410404624e-05, "loss": 0.2627, "step": 3498 }, { "epoch": 0.63, "learning_rate": 2.054371387283237e-05, "loss": 0.6682, "step": 3499 }, { "epoch": 0.63, "learning_rate": 2.0541004335260116e-05, "loss": 0.6546, "step": 3500 }, { "epoch": 0.63, "eval_exact_match": 86.23462630085146, "eval_f1": 92.66903548916258, "step": 3500 }, { "epoch": 0.63, "learning_rate": 2.053829479768786e-05, "loss": 0.625, "step": 3501 }, { "epoch": 0.63, "learning_rate": 2.0535585260115608e-05, "loss": 0.6408, "step": 3502 }, { "epoch": 0.63, "learning_rate": 2.0532875722543352e-05, "loss": 0.8387, "step": 3503 }, { "epoch": 0.63, "learning_rate": 2.05301661849711e-05, "loss": 0.5074, "step": 3504 }, { "epoch": 0.63, "learning_rate": 2.0527456647398844e-05, "loss": 0.859, "step": 3505 }, { "epoch": 0.63, "learning_rate": 2.052474710982659e-05, "loss": 1.025, "step": 3506 }, { "epoch": 0.63, "learning_rate": 2.0522037572254337e-05, "loss": 1.0581, "step": 3507 }, { "epoch": 0.63, "learning_rate": 2.051932803468208e-05, "loss": 0.7076, "step": 3508 }, { "epoch": 0.63, "learning_rate": 2.0516618497109825e-05, "loss": 0.8122, "step": 3509 }, { "epoch": 0.63, "learning_rate": 2.0513908959537573e-05, "loss": 0.506, "step": 3510 }, { "epoch": 0.63, "learning_rate": 2.0511199421965317e-05, "loss": 0.7248, "step": 3511 }, { "epoch": 0.63, "learning_rate": 2.0508489884393065e-05, "loss": 0.9457, "step": 3512 }, { "epoch": 0.63, "learning_rate": 2.050578034682081e-05, "loss": 0.8587, "step": 3513 }, { "epoch": 0.63, "learning_rate": 2.0503070809248554e-05, "loss": 0.586, "step": 3514 }, { "epoch": 0.63, "learning_rate": 2.05003612716763e-05, "loss": 0.9942, "step": 3515 }, { "epoch": 0.64, "learning_rate": 2.0497651734104046e-05, "loss": 0.6988, "step": 3516 }, { "epoch": 0.64, "learning_rate": 2.0494942196531794e-05, "loss": 0.5609, "step": 3517 }, { "epoch": 0.64, "learning_rate": 2.0492232658959538e-05, "loss": 1.351, "step": 3518 }, { "epoch": 0.64, "learning_rate": 2.0489523121387283e-05, "loss": 0.6867, "step": 3519 }, { "epoch": 0.64, "learning_rate": 2.048681358381503e-05, "loss": 0.3589, "step": 3520 }, { "epoch": 0.64, "learning_rate": 2.0484104046242775e-05, "loss": 0.6814, "step": 3521 }, { "epoch": 0.64, "learning_rate": 2.0481394508670522e-05, "loss": 0.6406, "step": 3522 }, { "epoch": 0.64, "learning_rate": 2.0478684971098263e-05, "loss": 1.1904, "step": 3523 }, { "epoch": 0.64, "learning_rate": 2.047597543352601e-05, "loss": 0.8159, "step": 3524 }, { "epoch": 0.64, "learning_rate": 2.047326589595376e-05, "loss": 0.7006, "step": 3525 }, { "epoch": 0.64, "learning_rate": 2.0470556358381503e-05, "loss": 0.5916, "step": 3526 }, { "epoch": 0.64, "learning_rate": 2.046784682080925e-05, "loss": 0.9917, "step": 3527 }, { "epoch": 0.64, "learning_rate": 2.0465137283236992e-05, "loss": 0.5409, "step": 3528 }, { "epoch": 0.64, "learning_rate": 2.046242774566474e-05, "loss": 0.6678, "step": 3529 }, { "epoch": 0.64, "learning_rate": 2.0459718208092487e-05, "loss": 0.6486, "step": 3530 }, { "epoch": 0.64, "learning_rate": 2.0457008670520232e-05, "loss": 2.2024, "step": 3531 }, { "epoch": 0.64, "learning_rate": 2.0454299132947976e-05, "loss": 0.954, "step": 3532 }, { "epoch": 0.64, "learning_rate": 2.045158959537572e-05, "loss": 0.7038, "step": 3533 }, { "epoch": 0.64, "learning_rate": 2.044888005780347e-05, "loss": 0.552, "step": 3534 }, { "epoch": 0.64, "learning_rate": 2.0446170520231216e-05, "loss": 0.4555, "step": 3535 }, { "epoch": 0.64, "learning_rate": 2.044346098265896e-05, "loss": 0.4413, "step": 3536 }, { "epoch": 0.64, "learning_rate": 2.0440751445086705e-05, "loss": 0.9707, "step": 3537 }, { "epoch": 0.64, "learning_rate": 2.043804190751445e-05, "loss": 0.6793, "step": 3538 }, { "epoch": 0.64, "learning_rate": 2.0435332369942197e-05, "loss": 0.6088, "step": 3539 }, { "epoch": 0.64, "learning_rate": 2.0432622832369945e-05, "loss": 0.8683, "step": 3540 }, { "epoch": 0.64, "learning_rate": 2.042991329479769e-05, "loss": 1.3203, "step": 3541 }, { "epoch": 0.64, "learning_rate": 2.0427203757225433e-05, "loss": 1.1664, "step": 3542 }, { "epoch": 0.64, "learning_rate": 2.0424494219653178e-05, "loss": 0.5329, "step": 3543 }, { "epoch": 0.64, "learning_rate": 2.0421784682080926e-05, "loss": 0.6112, "step": 3544 }, { "epoch": 0.64, "learning_rate": 2.0419075144508673e-05, "loss": 0.7326, "step": 3545 }, { "epoch": 0.64, "learning_rate": 2.0416365606936414e-05, "loss": 1.0408, "step": 3546 }, { "epoch": 0.64, "learning_rate": 2.0413656069364162e-05, "loss": 0.5993, "step": 3547 }, { "epoch": 0.64, "learning_rate": 2.0410946531791906e-05, "loss": 0.536, "step": 3548 }, { "epoch": 0.64, "learning_rate": 2.0408236994219654e-05, "loss": 0.8526, "step": 3549 }, { "epoch": 0.64, "learning_rate": 2.0405527456647402e-05, "loss": 0.38, "step": 3550 }, { "epoch": 0.64, "learning_rate": 2.0402817919075143e-05, "loss": 0.9991, "step": 3551 }, { "epoch": 0.64, "learning_rate": 2.040010838150289e-05, "loss": 1.2193, "step": 3552 }, { "epoch": 0.64, "learning_rate": 2.0397398843930635e-05, "loss": 1.4163, "step": 3553 }, { "epoch": 0.64, "learning_rate": 2.0394689306358383e-05, "loss": 0.4305, "step": 3554 }, { "epoch": 0.64, "learning_rate": 2.0391979768786127e-05, "loss": 1.4043, "step": 3555 }, { "epoch": 0.64, "learning_rate": 2.038927023121387e-05, "loss": 1.0421, "step": 3556 }, { "epoch": 0.64, "learning_rate": 2.038656069364162e-05, "loss": 0.9576, "step": 3557 }, { "epoch": 0.64, "learning_rate": 2.0383851156069367e-05, "loss": 0.7076, "step": 3558 }, { "epoch": 0.64, "learning_rate": 2.038114161849711e-05, "loss": 1.1953, "step": 3559 }, { "epoch": 0.64, "learning_rate": 2.0378432080924856e-05, "loss": 0.713, "step": 3560 }, { "epoch": 0.64, "learning_rate": 2.03757225433526e-05, "loss": 0.533, "step": 3561 }, { "epoch": 0.64, "learning_rate": 2.0373013005780348e-05, "loss": 0.6317, "step": 3562 }, { "epoch": 0.64, "learning_rate": 2.0370303468208096e-05, "loss": 1.1986, "step": 3563 }, { "epoch": 0.64, "learning_rate": 2.036759393063584e-05, "loss": 0.8618, "step": 3564 }, { "epoch": 0.64, "learning_rate": 2.0364884393063584e-05, "loss": 1.1073, "step": 3565 }, { "epoch": 0.64, "learning_rate": 2.036217485549133e-05, "loss": 0.7024, "step": 3566 }, { "epoch": 0.64, "learning_rate": 2.0359465317919076e-05, "loss": 0.565, "step": 3567 }, { "epoch": 0.64, "learning_rate": 2.0356755780346824e-05, "loss": 0.5927, "step": 3568 }, { "epoch": 0.64, "learning_rate": 2.0354046242774565e-05, "loss": 0.8856, "step": 3569 }, { "epoch": 0.64, "learning_rate": 2.0351336705202313e-05, "loss": 1.1654, "step": 3570 }, { "epoch": 0.65, "learning_rate": 2.0348627167630057e-05, "loss": 0.8382, "step": 3571 }, { "epoch": 0.65, "learning_rate": 2.0345917630057805e-05, "loss": 0.7497, "step": 3572 }, { "epoch": 0.65, "learning_rate": 2.0343208092485553e-05, "loss": 0.9336, "step": 3573 }, { "epoch": 0.65, "learning_rate": 2.0340498554913294e-05, "loss": 0.4477, "step": 3574 }, { "epoch": 0.65, "learning_rate": 2.033778901734104e-05, "loss": 0.7963, "step": 3575 }, { "epoch": 0.65, "learning_rate": 2.0335079479768786e-05, "loss": 0.4418, "step": 3576 }, { "epoch": 0.65, "learning_rate": 2.0332369942196534e-05, "loss": 1.6068, "step": 3577 }, { "epoch": 0.65, "learning_rate": 2.0329660404624278e-05, "loss": 0.8047, "step": 3578 }, { "epoch": 0.65, "learning_rate": 2.0326950867052022e-05, "loss": 1.1095, "step": 3579 }, { "epoch": 0.65, "learning_rate": 2.032424132947977e-05, "loss": 1.2108, "step": 3580 }, { "epoch": 0.65, "learning_rate": 2.0321531791907514e-05, "loss": 0.3749, "step": 3581 }, { "epoch": 0.65, "learning_rate": 2.0318822254335262e-05, "loss": 0.5778, "step": 3582 }, { "epoch": 0.65, "learning_rate": 2.0316112716763007e-05, "loss": 0.4831, "step": 3583 }, { "epoch": 0.65, "learning_rate": 2.031340317919075e-05, "loss": 0.9398, "step": 3584 }, { "epoch": 0.65, "learning_rate": 2.03106936416185e-05, "loss": 0.2103, "step": 3585 }, { "epoch": 0.65, "learning_rate": 2.0307984104046243e-05, "loss": 1.1421, "step": 3586 }, { "epoch": 0.65, "learning_rate": 2.030527456647399e-05, "loss": 0.7299, "step": 3587 }, { "epoch": 0.65, "learning_rate": 2.0302565028901735e-05, "loss": 0.9381, "step": 3588 }, { "epoch": 0.65, "learning_rate": 2.029985549132948e-05, "loss": 0.8201, "step": 3589 }, { "epoch": 0.65, "learning_rate": 2.0297145953757227e-05, "loss": 0.8845, "step": 3590 }, { "epoch": 0.65, "learning_rate": 2.029443641618497e-05, "loss": 1.0575, "step": 3591 }, { "epoch": 0.65, "learning_rate": 2.0291726878612716e-05, "loss": 1.1922, "step": 3592 }, { "epoch": 0.65, "learning_rate": 2.0289017341040464e-05, "loss": 0.7499, "step": 3593 }, { "epoch": 0.65, "learning_rate": 2.0286307803468208e-05, "loss": 0.4435, "step": 3594 }, { "epoch": 0.65, "learning_rate": 2.0283598265895956e-05, "loss": 0.9214, "step": 3595 }, { "epoch": 0.65, "learning_rate": 2.02808887283237e-05, "loss": 0.3933, "step": 3596 }, { "epoch": 0.65, "learning_rate": 2.0278179190751445e-05, "loss": 0.7371, "step": 3597 }, { "epoch": 0.65, "learning_rate": 2.0275469653179192e-05, "loss": 1.122, "step": 3598 }, { "epoch": 0.65, "learning_rate": 2.0272760115606937e-05, "loss": 0.5788, "step": 3599 }, { "epoch": 0.65, "learning_rate": 2.0270050578034685e-05, "loss": 0.6374, "step": 3600 }, { "epoch": 0.65, "learning_rate": 2.0267341040462425e-05, "loss": 0.8359, "step": 3601 }, { "epoch": 0.65, "learning_rate": 2.0264631502890173e-05, "loss": 0.66, "step": 3602 }, { "epoch": 0.65, "learning_rate": 2.026192196531792e-05, "loss": 0.4328, "step": 3603 }, { "epoch": 0.65, "learning_rate": 2.0259212427745665e-05, "loss": 1.2325, "step": 3604 }, { "epoch": 0.65, "learning_rate": 2.0256502890173413e-05, "loss": 1.0639, "step": 3605 }, { "epoch": 0.65, "learning_rate": 2.0253793352601154e-05, "loss": 1.0161, "step": 3606 }, { "epoch": 0.65, "learning_rate": 2.0251083815028902e-05, "loss": 0.5638, "step": 3607 }, { "epoch": 0.65, "learning_rate": 2.024837427745665e-05, "loss": 1.7553, "step": 3608 }, { "epoch": 0.65, "learning_rate": 2.0245664739884394e-05, "loss": 0.6663, "step": 3609 }, { "epoch": 0.65, "learning_rate": 2.0242955202312142e-05, "loss": 0.6778, "step": 3610 }, { "epoch": 0.65, "learning_rate": 2.0240245664739883e-05, "loss": 0.4632, "step": 3611 }, { "epoch": 0.65, "learning_rate": 2.023753612716763e-05, "loss": 0.6425, "step": 3612 }, { "epoch": 0.65, "learning_rate": 2.0234826589595378e-05, "loss": 0.717, "step": 3613 }, { "epoch": 0.65, "learning_rate": 2.0232117052023123e-05, "loss": 0.6743, "step": 3614 }, { "epoch": 0.65, "learning_rate": 2.0229407514450867e-05, "loss": 0.66, "step": 3615 }, { "epoch": 0.65, "learning_rate": 2.022669797687861e-05, "loss": 0.8476, "step": 3616 }, { "epoch": 0.65, "learning_rate": 2.022398843930636e-05, "loss": 1.2865, "step": 3617 }, { "epoch": 0.65, "learning_rate": 2.0221278901734107e-05, "loss": 0.687, "step": 3618 }, { "epoch": 0.65, "learning_rate": 2.021856936416185e-05, "loss": 0.4033, "step": 3619 }, { "epoch": 0.65, "learning_rate": 2.0215859826589596e-05, "loss": 0.7269, "step": 3620 }, { "epoch": 0.65, "learning_rate": 2.021315028901734e-05, "loss": 0.5438, "step": 3621 }, { "epoch": 0.65, "learning_rate": 2.0210440751445088e-05, "loss": 0.6054, "step": 3622 }, { "epoch": 0.65, "learning_rate": 2.0207731213872835e-05, "loss": 0.7838, "step": 3623 }, { "epoch": 0.65, "learning_rate": 2.0205021676300576e-05, "loss": 1.4979, "step": 3624 }, { "epoch": 0.65, "learning_rate": 2.0202312138728324e-05, "loss": 0.4385, "step": 3625 }, { "epoch": 0.65, "learning_rate": 2.019960260115607e-05, "loss": 0.4368, "step": 3626 }, { "epoch": 0.66, "learning_rate": 2.0196893063583816e-05, "loss": 0.5755, "step": 3627 }, { "epoch": 0.66, "learning_rate": 2.0194183526011564e-05, "loss": 1.551, "step": 3628 }, { "epoch": 0.66, "learning_rate": 2.0191473988439305e-05, "loss": 0.8448, "step": 3629 }, { "epoch": 0.66, "learning_rate": 2.0188764450867053e-05, "loss": 0.711, "step": 3630 }, { "epoch": 0.66, "learning_rate": 2.0186054913294797e-05, "loss": 0.5911, "step": 3631 }, { "epoch": 0.66, "learning_rate": 2.0183345375722545e-05, "loss": 0.8479, "step": 3632 }, { "epoch": 0.66, "learning_rate": 2.018063583815029e-05, "loss": 1.6911, "step": 3633 }, { "epoch": 0.66, "learning_rate": 2.0177926300578034e-05, "loss": 1.039, "step": 3634 }, { "epoch": 0.66, "learning_rate": 2.017521676300578e-05, "loss": 0.7715, "step": 3635 }, { "epoch": 0.66, "learning_rate": 2.0172507225433526e-05, "loss": 0.4569, "step": 3636 }, { "epoch": 0.66, "learning_rate": 2.0169797687861273e-05, "loss": 0.969, "step": 3637 }, { "epoch": 0.66, "learning_rate": 2.0167088150289018e-05, "loss": 1.2694, "step": 3638 }, { "epoch": 0.66, "learning_rate": 2.0164378612716762e-05, "loss": 0.2996, "step": 3639 }, { "epoch": 0.66, "learning_rate": 2.016166907514451e-05, "loss": 0.7646, "step": 3640 }, { "epoch": 0.66, "learning_rate": 2.0158959537572254e-05, "loss": 1.3706, "step": 3641 }, { "epoch": 0.66, "learning_rate": 2.0156250000000002e-05, "loss": 0.7993, "step": 3642 }, { "epoch": 0.66, "learning_rate": 2.0153540462427746e-05, "loss": 0.3677, "step": 3643 }, { "epoch": 0.66, "learning_rate": 2.015083092485549e-05, "loss": 0.538, "step": 3644 }, { "epoch": 0.66, "learning_rate": 2.014812138728324e-05, "loss": 1.2012, "step": 3645 }, { "epoch": 0.66, "learning_rate": 2.0145411849710983e-05, "loss": 0.2964, "step": 3646 }, { "epoch": 0.66, "learning_rate": 2.0142702312138727e-05, "loss": 0.957, "step": 3647 }, { "epoch": 0.66, "learning_rate": 2.0139992774566475e-05, "loss": 0.8218, "step": 3648 }, { "epoch": 0.66, "learning_rate": 2.013728323699422e-05, "loss": 0.5323, "step": 3649 }, { "epoch": 0.66, "learning_rate": 2.0134573699421967e-05, "loss": 0.808, "step": 3650 }, { "epoch": 0.66, "learning_rate": 2.013186416184971e-05, "loss": 0.8346, "step": 3651 }, { "epoch": 0.66, "learning_rate": 2.0129154624277456e-05, "loss": 0.3876, "step": 3652 }, { "epoch": 0.66, "learning_rate": 2.0126445086705204e-05, "loss": 0.8174, "step": 3653 }, { "epoch": 0.66, "learning_rate": 2.0123735549132948e-05, "loss": 0.6647, "step": 3654 }, { "epoch": 0.66, "learning_rate": 2.0121026011560696e-05, "loss": 1.5771, "step": 3655 }, { "epoch": 0.66, "learning_rate": 2.011831647398844e-05, "loss": 0.4254, "step": 3656 }, { "epoch": 0.66, "learning_rate": 2.0115606936416184e-05, "loss": 0.8821, "step": 3657 }, { "epoch": 0.66, "learning_rate": 2.0112897398843932e-05, "loss": 0.6085, "step": 3658 }, { "epoch": 0.66, "learning_rate": 2.0110187861271677e-05, "loss": 0.8531, "step": 3659 }, { "epoch": 0.66, "learning_rate": 2.0107478323699424e-05, "loss": 1.253, "step": 3660 }, { "epoch": 0.66, "learning_rate": 2.0104768786127165e-05, "loss": 0.6925, "step": 3661 }, { "epoch": 0.66, "learning_rate": 2.0102059248554913e-05, "loss": 1.3466, "step": 3662 }, { "epoch": 0.66, "learning_rate": 2.009934971098266e-05, "loss": 1.296, "step": 3663 }, { "epoch": 0.66, "learning_rate": 2.0096640173410405e-05, "loss": 0.5981, "step": 3664 }, { "epoch": 0.66, "learning_rate": 2.0093930635838153e-05, "loss": 1.0533, "step": 3665 }, { "epoch": 0.66, "learning_rate": 2.0091221098265894e-05, "loss": 1.2, "step": 3666 }, { "epoch": 0.66, "learning_rate": 2.008851156069364e-05, "loss": 0.7461, "step": 3667 }, { "epoch": 0.66, "learning_rate": 2.008580202312139e-05, "loss": 0.8929, "step": 3668 }, { "epoch": 0.66, "learning_rate": 2.0083092485549134e-05, "loss": 0.6634, "step": 3669 }, { "epoch": 0.66, "learning_rate": 2.0080382947976878e-05, "loss": 0.5374, "step": 3670 }, { "epoch": 0.66, "learning_rate": 2.0077673410404623e-05, "loss": 0.3886, "step": 3671 }, { "epoch": 0.66, "learning_rate": 2.007496387283237e-05, "loss": 0.971, "step": 3672 }, { "epoch": 0.66, "learning_rate": 2.0072254335260118e-05, "loss": 0.3897, "step": 3673 }, { "epoch": 0.66, "learning_rate": 2.0069544797687862e-05, "loss": 0.8172, "step": 3674 }, { "epoch": 0.66, "learning_rate": 2.0066835260115607e-05, "loss": 1.2934, "step": 3675 }, { "epoch": 0.66, "learning_rate": 2.006412572254335e-05, "loss": 0.9251, "step": 3676 }, { "epoch": 0.66, "learning_rate": 2.00614161849711e-05, "loss": 1.0847, "step": 3677 }, { "epoch": 0.66, "learning_rate": 2.0058706647398847e-05, "loss": 1.3953, "step": 3678 }, { "epoch": 0.66, "learning_rate": 2.005599710982659e-05, "loss": 1.0359, "step": 3679 }, { "epoch": 0.66, "learning_rate": 2.0053287572254335e-05, "loss": 0.5236, "step": 3680 }, { "epoch": 0.66, "learning_rate": 2.005057803468208e-05, "loss": 0.4538, "step": 3681 }, { "epoch": 0.67, "learning_rate": 2.0047868497109827e-05, "loss": 0.7525, "step": 3682 }, { "epoch": 0.67, "learning_rate": 2.0045158959537575e-05, "loss": 0.8551, "step": 3683 }, { "epoch": 0.67, "learning_rate": 2.0042449421965316e-05, "loss": 1.0888, "step": 3684 }, { "epoch": 0.67, "learning_rate": 2.0039739884393064e-05, "loss": 0.7582, "step": 3685 }, { "epoch": 0.67, "learning_rate": 2.003703034682081e-05, "loss": 0.9013, "step": 3686 }, { "epoch": 0.67, "learning_rate": 2.0034320809248556e-05, "loss": 0.8602, "step": 3687 }, { "epoch": 0.67, "learning_rate": 2.0031611271676304e-05, "loss": 0.6513, "step": 3688 }, { "epoch": 0.67, "learning_rate": 2.0028901734104045e-05, "loss": 1.0996, "step": 3689 }, { "epoch": 0.67, "learning_rate": 2.0026192196531793e-05, "loss": 1.4905, "step": 3690 }, { "epoch": 0.67, "learning_rate": 2.0023482658959537e-05, "loss": 0.8297, "step": 3691 }, { "epoch": 0.67, "learning_rate": 2.0020773121387285e-05, "loss": 0.4699, "step": 3692 }, { "epoch": 0.67, "learning_rate": 2.001806358381503e-05, "loss": 0.7035, "step": 3693 }, { "epoch": 0.67, "learning_rate": 2.0015354046242773e-05, "loss": 1.563, "step": 3694 }, { "epoch": 0.67, "learning_rate": 2.001264450867052e-05, "loss": 0.7057, "step": 3695 }, { "epoch": 0.67, "learning_rate": 2.0009934971098266e-05, "loss": 0.8607, "step": 3696 }, { "epoch": 0.67, "learning_rate": 2.0007225433526013e-05, "loss": 1.0264, "step": 3697 }, { "epoch": 0.67, "learning_rate": 2.0004515895953758e-05, "loss": 0.5134, "step": 3698 }, { "epoch": 0.67, "learning_rate": 2.0001806358381502e-05, "loss": 0.5573, "step": 3699 }, { "epoch": 0.67, "learning_rate": 1.999909682080925e-05, "loss": 1.2152, "step": 3700 }, { "epoch": 0.67, "learning_rate": 1.9996387283236994e-05, "loss": 0.9603, "step": 3701 }, { "epoch": 0.67, "learning_rate": 1.999367774566474e-05, "loss": 0.5783, "step": 3702 }, { "epoch": 0.67, "learning_rate": 1.9990968208092486e-05, "loss": 0.577, "step": 3703 }, { "epoch": 0.67, "learning_rate": 1.998825867052023e-05, "loss": 0.8941, "step": 3704 }, { "epoch": 0.67, "learning_rate": 1.998554913294798e-05, "loss": 0.6489, "step": 3705 }, { "epoch": 0.67, "learning_rate": 1.9982839595375723e-05, "loss": 0.6994, "step": 3706 }, { "epoch": 0.67, "learning_rate": 1.9980130057803467e-05, "loss": 1.0646, "step": 3707 }, { "epoch": 0.67, "learning_rate": 1.9977420520231215e-05, "loss": 1.1679, "step": 3708 }, { "epoch": 0.67, "learning_rate": 1.997471098265896e-05, "loss": 0.6131, "step": 3709 }, { "epoch": 0.67, "learning_rate": 1.9972001445086707e-05, "loss": 1.2977, "step": 3710 }, { "epoch": 0.67, "learning_rate": 1.996929190751445e-05, "loss": 0.9236, "step": 3711 }, { "epoch": 0.67, "learning_rate": 1.9966582369942196e-05, "loss": 1.1431, "step": 3712 }, { "epoch": 0.67, "learning_rate": 1.9963872832369943e-05, "loss": 1.0028, "step": 3713 }, { "epoch": 0.67, "learning_rate": 1.9961163294797688e-05, "loss": 1.1402, "step": 3714 }, { "epoch": 0.67, "learning_rate": 1.9958453757225436e-05, "loss": 0.8616, "step": 3715 }, { "epoch": 0.67, "learning_rate": 1.9955744219653177e-05, "loss": 0.9023, "step": 3716 }, { "epoch": 0.67, "learning_rate": 1.9953034682080924e-05, "loss": 0.8147, "step": 3717 }, { "epoch": 0.67, "learning_rate": 1.9950325144508672e-05, "loss": 1.2828, "step": 3718 }, { "epoch": 0.67, "learning_rate": 1.9947615606936416e-05, "loss": 0.3865, "step": 3719 }, { "epoch": 0.67, "learning_rate": 1.9944906069364164e-05, "loss": 1.4698, "step": 3720 }, { "epoch": 0.67, "learning_rate": 1.9942196531791905e-05, "loss": 0.8489, "step": 3721 }, { "epoch": 0.67, "learning_rate": 1.9939486994219653e-05, "loss": 0.4081, "step": 3722 }, { "epoch": 0.67, "learning_rate": 1.99367774566474e-05, "loss": 0.6656, "step": 3723 }, { "epoch": 0.67, "learning_rate": 1.9934067919075145e-05, "loss": 0.5602, "step": 3724 }, { "epoch": 0.67, "learning_rate": 1.993135838150289e-05, "loss": 0.6578, "step": 3725 }, { "epoch": 0.67, "learning_rate": 1.9928648843930634e-05, "loss": 0.5394, "step": 3726 }, { "epoch": 0.67, "learning_rate": 1.992593930635838e-05, "loss": 0.9028, "step": 3727 }, { "epoch": 0.67, "learning_rate": 1.992322976878613e-05, "loss": 0.9297, "step": 3728 }, { "epoch": 0.67, "learning_rate": 1.9920520231213874e-05, "loss": 0.5822, "step": 3729 }, { "epoch": 0.67, "learning_rate": 1.9917810693641618e-05, "loss": 0.4605, "step": 3730 }, { "epoch": 0.67, "learning_rate": 1.9915101156069366e-05, "loss": 0.6374, "step": 3731 }, { "epoch": 0.67, "learning_rate": 1.991239161849711e-05, "loss": 0.8994, "step": 3732 }, { "epoch": 0.67, "learning_rate": 1.9909682080924858e-05, "loss": 0.2528, "step": 3733 }, { "epoch": 0.67, "learning_rate": 1.9906972543352602e-05, "loss": 0.9885, "step": 3734 }, { "epoch": 0.67, "learning_rate": 1.9904263005780347e-05, "loss": 1.0717, "step": 3735 }, { "epoch": 0.67, "learning_rate": 1.9901553468208094e-05, "loss": 0.5455, "step": 3736 }, { "epoch": 0.68, "learning_rate": 1.989884393063584e-05, "loss": 0.922, "step": 3737 }, { "epoch": 0.68, "learning_rate": 1.9896134393063586e-05, "loss": 0.8109, "step": 3738 }, { "epoch": 0.68, "learning_rate": 1.9893424855491327e-05, "loss": 0.6308, "step": 3739 }, { "epoch": 0.68, "learning_rate": 1.9890715317919075e-05, "loss": 0.9407, "step": 3740 }, { "epoch": 0.68, "learning_rate": 1.9888005780346823e-05, "loss": 1.092, "step": 3741 }, { "epoch": 0.68, "learning_rate": 1.9885296242774567e-05, "loss": 0.6298, "step": 3742 }, { "epoch": 0.68, "learning_rate": 1.9882586705202315e-05, "loss": 0.7771, "step": 3743 }, { "epoch": 0.68, "learning_rate": 1.9879877167630056e-05, "loss": 0.5712, "step": 3744 }, { "epoch": 0.68, "learning_rate": 1.9877167630057804e-05, "loss": 0.7495, "step": 3745 }, { "epoch": 0.68, "learning_rate": 1.987445809248555e-05, "loss": 0.7271, "step": 3746 }, { "epoch": 0.68, "learning_rate": 1.9871748554913296e-05, "loss": 0.736, "step": 3747 }, { "epoch": 0.68, "learning_rate": 1.986903901734104e-05, "loss": 0.6922, "step": 3748 }, { "epoch": 0.68, "learning_rate": 1.9866329479768785e-05, "loss": 0.6416, "step": 3749 }, { "epoch": 0.68, "learning_rate": 1.9863619942196532e-05, "loss": 0.571, "step": 3750 }, { "epoch": 0.68, "learning_rate": 1.986091040462428e-05, "loss": 0.6495, "step": 3751 }, { "epoch": 0.68, "learning_rate": 1.9858200867052025e-05, "loss": 1.2351, "step": 3752 }, { "epoch": 0.68, "learning_rate": 1.985549132947977e-05, "loss": 0.4154, "step": 3753 }, { "epoch": 0.68, "learning_rate": 1.9852781791907513e-05, "loss": 0.9002, "step": 3754 }, { "epoch": 0.68, "learning_rate": 1.985007225433526e-05, "loss": 1.5631, "step": 3755 }, { "epoch": 0.68, "learning_rate": 1.984736271676301e-05, "loss": 0.8094, "step": 3756 }, { "epoch": 0.68, "learning_rate": 1.9844653179190753e-05, "loss": 0.7807, "step": 3757 }, { "epoch": 0.68, "learning_rate": 1.9841943641618497e-05, "loss": 0.4978, "step": 3758 }, { "epoch": 0.68, "learning_rate": 1.9839234104046242e-05, "loss": 0.5199, "step": 3759 }, { "epoch": 0.68, "learning_rate": 1.983652456647399e-05, "loss": 0.6448, "step": 3760 }, { "epoch": 0.68, "learning_rate": 1.9833815028901737e-05, "loss": 0.262, "step": 3761 }, { "epoch": 0.68, "learning_rate": 1.983110549132948e-05, "loss": 0.937, "step": 3762 }, { "epoch": 0.68, "learning_rate": 1.9828395953757226e-05, "loss": 0.6396, "step": 3763 }, { "epoch": 0.68, "learning_rate": 1.982568641618497e-05, "loss": 1.1384, "step": 3764 }, { "epoch": 0.68, "learning_rate": 1.9822976878612718e-05, "loss": 1.5294, "step": 3765 }, { "epoch": 0.68, "learning_rate": 1.9820267341040466e-05, "loss": 1.009, "step": 3766 }, { "epoch": 0.68, "learning_rate": 1.9817557803468207e-05, "loss": 0.5323, "step": 3767 }, { "epoch": 0.68, "learning_rate": 1.9814848265895955e-05, "loss": 0.9101, "step": 3768 }, { "epoch": 0.68, "learning_rate": 1.98121387283237e-05, "loss": 1.1026, "step": 3769 }, { "epoch": 0.68, "learning_rate": 1.9809429190751447e-05, "loss": 0.8705, "step": 3770 }, { "epoch": 0.68, "learning_rate": 1.980671965317919e-05, "loss": 0.922, "step": 3771 }, { "epoch": 0.68, "learning_rate": 1.9804010115606936e-05, "loss": 0.92, "step": 3772 }, { "epoch": 0.68, "learning_rate": 1.9801300578034683e-05, "loss": 0.292, "step": 3773 }, { "epoch": 0.68, "learning_rate": 1.9798591040462428e-05, "loss": 1.1051, "step": 3774 }, { "epoch": 0.68, "learning_rate": 1.9795881502890175e-05, "loss": 1.407, "step": 3775 }, { "epoch": 0.68, "learning_rate": 1.979317196531792e-05, "loss": 0.6609, "step": 3776 }, { "epoch": 0.68, "learning_rate": 1.9790462427745664e-05, "loss": 0.7495, "step": 3777 }, { "epoch": 0.68, "learning_rate": 1.9787752890173412e-05, "loss": 0.7729, "step": 3778 }, { "epoch": 0.68, "learning_rate": 1.9785043352601156e-05, "loss": 1.2634, "step": 3779 }, { "epoch": 0.68, "learning_rate": 1.9782333815028904e-05, "loss": 0.5485, "step": 3780 }, { "epoch": 0.68, "learning_rate": 1.977962427745665e-05, "loss": 1.3694, "step": 3781 }, { "epoch": 0.68, "learning_rate": 1.9776914739884393e-05, "loss": 0.8668, "step": 3782 }, { "epoch": 0.68, "learning_rate": 1.977420520231214e-05, "loss": 0.3409, "step": 3783 }, { "epoch": 0.68, "learning_rate": 1.9771495664739885e-05, "loss": 1.4403, "step": 3784 }, { "epoch": 0.68, "learning_rate": 1.976878612716763e-05, "loss": 1.6643, "step": 3785 }, { "epoch": 0.68, "learning_rate": 1.9766076589595377e-05, "loss": 0.4874, "step": 3786 }, { "epoch": 0.68, "learning_rate": 1.976336705202312e-05, "loss": 0.8715, "step": 3787 }, { "epoch": 0.68, "learning_rate": 1.976065751445087e-05, "loss": 0.6694, "step": 3788 }, { "epoch": 0.68, "learning_rate": 1.9757947976878613e-05, "loss": 1.0454, "step": 3789 }, { "epoch": 0.68, "learning_rate": 1.9755238439306358e-05, "loss": 0.4736, "step": 3790 }, { "epoch": 0.68, "learning_rate": 1.9752528901734106e-05, "loss": 1.1158, "step": 3791 }, { "epoch": 0.68, "learning_rate": 1.974981936416185e-05, "loss": 1.0702, "step": 3792 }, { "epoch": 0.69, "learning_rate": 1.9747109826589598e-05, "loss": 1.0269, "step": 3793 }, { "epoch": 0.69, "learning_rate": 1.974440028901734e-05, "loss": 0.5246, "step": 3794 }, { "epoch": 0.69, "learning_rate": 1.9741690751445086e-05, "loss": 1.0138, "step": 3795 }, { "epoch": 0.69, "learning_rate": 1.9738981213872834e-05, "loss": 0.344, "step": 3796 }, { "epoch": 0.69, "learning_rate": 1.973627167630058e-05, "loss": 1.653, "step": 3797 }, { "epoch": 0.69, "learning_rate": 1.9733562138728326e-05, "loss": 0.6953, "step": 3798 }, { "epoch": 0.69, "learning_rate": 1.9730852601156067e-05, "loss": 1.5645, "step": 3799 }, { "epoch": 0.69, "learning_rate": 1.9728143063583815e-05, "loss": 0.4838, "step": 3800 }, { "epoch": 0.69, "learning_rate": 1.9725433526011563e-05, "loss": 0.7719, "step": 3801 }, { "epoch": 0.69, "learning_rate": 1.9722723988439307e-05, "loss": 0.4787, "step": 3802 }, { "epoch": 0.69, "learning_rate": 1.9720014450867055e-05, "loss": 0.3966, "step": 3803 }, { "epoch": 0.69, "learning_rate": 1.9717304913294796e-05, "loss": 0.2184, "step": 3804 }, { "epoch": 0.69, "learning_rate": 1.9714595375722544e-05, "loss": 0.6604, "step": 3805 }, { "epoch": 0.69, "learning_rate": 1.971188583815029e-05, "loss": 1.0727, "step": 3806 }, { "epoch": 0.69, "learning_rate": 1.9709176300578036e-05, "loss": 0.6087, "step": 3807 }, { "epoch": 0.69, "learning_rate": 1.970646676300578e-05, "loss": 1.0607, "step": 3808 }, { "epoch": 0.69, "learning_rate": 1.9703757225433524e-05, "loss": 2.0042, "step": 3809 }, { "epoch": 0.69, "learning_rate": 1.9701047687861272e-05, "loss": 0.5328, "step": 3810 }, { "epoch": 0.69, "learning_rate": 1.969833815028902e-05, "loss": 0.6628, "step": 3811 }, { "epoch": 0.69, "learning_rate": 1.9695628612716764e-05, "loss": 0.5335, "step": 3812 }, { "epoch": 0.69, "learning_rate": 1.969291907514451e-05, "loss": 1.6665, "step": 3813 }, { "epoch": 0.69, "learning_rate": 1.9690209537572253e-05, "loss": 0.9215, "step": 3814 }, { "epoch": 0.69, "learning_rate": 1.96875e-05, "loss": 0.4339, "step": 3815 }, { "epoch": 0.69, "learning_rate": 1.968479046242775e-05, "loss": 0.5902, "step": 3816 }, { "epoch": 0.69, "learning_rate": 1.968208092485549e-05, "loss": 0.2731, "step": 3817 }, { "epoch": 0.69, "learning_rate": 1.9679371387283237e-05, "loss": 1.2548, "step": 3818 }, { "epoch": 0.69, "learning_rate": 1.967666184971098e-05, "loss": 0.3599, "step": 3819 }, { "epoch": 0.69, "learning_rate": 1.967395231213873e-05, "loss": 0.3942, "step": 3820 }, { "epoch": 0.69, "learning_rate": 1.9671242774566477e-05, "loss": 0.665, "step": 3821 }, { "epoch": 0.69, "learning_rate": 1.9668533236994218e-05, "loss": 0.8249, "step": 3822 }, { "epoch": 0.69, "learning_rate": 1.9665823699421966e-05, "loss": 0.246, "step": 3823 }, { "epoch": 0.69, "learning_rate": 1.966311416184971e-05, "loss": 0.9285, "step": 3824 }, { "epoch": 0.69, "learning_rate": 1.9660404624277458e-05, "loss": 0.9584, "step": 3825 }, { "epoch": 0.69, "learning_rate": 1.9657695086705206e-05, "loss": 0.2005, "step": 3826 }, { "epoch": 0.69, "learning_rate": 1.9654985549132947e-05, "loss": 0.6959, "step": 3827 }, { "epoch": 0.69, "learning_rate": 1.9652276011560695e-05, "loss": 0.8686, "step": 3828 }, { "epoch": 0.69, "learning_rate": 1.964956647398844e-05, "loss": 0.8047, "step": 3829 }, { "epoch": 0.69, "learning_rate": 1.9646856936416187e-05, "loss": 0.8074, "step": 3830 }, { "epoch": 0.69, "learning_rate": 1.964414739884393e-05, "loss": 0.4117, "step": 3831 }, { "epoch": 0.69, "learning_rate": 1.9641437861271675e-05, "loss": 1.3204, "step": 3832 }, { "epoch": 0.69, "learning_rate": 1.9638728323699423e-05, "loss": 0.6517, "step": 3833 }, { "epoch": 0.69, "learning_rate": 1.9636018786127167e-05, "loss": 0.9226, "step": 3834 }, { "epoch": 0.69, "learning_rate": 1.9633309248554915e-05, "loss": 0.7109, "step": 3835 }, { "epoch": 0.69, "learning_rate": 1.963059971098266e-05, "loss": 0.6603, "step": 3836 }, { "epoch": 0.69, "learning_rate": 1.9627890173410404e-05, "loss": 0.5135, "step": 3837 }, { "epoch": 0.69, "learning_rate": 1.9625180635838152e-05, "loss": 1.4231, "step": 3838 }, { "epoch": 0.69, "learning_rate": 1.9622471098265896e-05, "loss": 1.1164, "step": 3839 }, { "epoch": 0.69, "learning_rate": 1.961976156069364e-05, "loss": 0.6334, "step": 3840 }, { "epoch": 0.69, "learning_rate": 1.9617052023121388e-05, "loss": 0.8405, "step": 3841 }, { "epoch": 0.69, "learning_rate": 1.9614342485549133e-05, "loss": 1.0995, "step": 3842 }, { "epoch": 0.69, "learning_rate": 1.961163294797688e-05, "loss": 0.8291, "step": 3843 }, { "epoch": 0.69, "learning_rate": 1.9608923410404625e-05, "loss": 0.3749, "step": 3844 }, { "epoch": 0.69, "learning_rate": 1.960621387283237e-05, "loss": 0.8047, "step": 3845 }, { "epoch": 0.69, "learning_rate": 1.9603504335260117e-05, "loss": 0.5975, "step": 3846 }, { "epoch": 0.69, "learning_rate": 1.960079479768786e-05, "loss": 0.6674, "step": 3847 }, { "epoch": 0.7, "learning_rate": 1.959808526011561e-05, "loss": 0.6477, "step": 3848 }, { "epoch": 0.7, "learning_rate": 1.9595375722543353e-05, "loss": 0.8109, "step": 3849 }, { "epoch": 0.7, "learning_rate": 1.9592666184971098e-05, "loss": 0.7885, "step": 3850 }, { "epoch": 0.7, "learning_rate": 1.9589956647398845e-05, "loss": 0.9225, "step": 3851 }, { "epoch": 0.7, "learning_rate": 1.958724710982659e-05, "loss": 1.1375, "step": 3852 }, { "epoch": 0.7, "learning_rate": 1.9584537572254338e-05, "loss": 0.7322, "step": 3853 }, { "epoch": 0.7, "learning_rate": 1.958182803468208e-05, "loss": 1.7624, "step": 3854 }, { "epoch": 0.7, "learning_rate": 1.9579118497109826e-05, "loss": 0.8838, "step": 3855 }, { "epoch": 0.7, "learning_rate": 1.9576408959537574e-05, "loss": 0.7286, "step": 3856 }, { "epoch": 0.7, "learning_rate": 1.957369942196532e-05, "loss": 0.9466, "step": 3857 }, { "epoch": 0.7, "learning_rate": 1.9570989884393066e-05, "loss": 0.7783, "step": 3858 }, { "epoch": 0.7, "learning_rate": 1.9568280346820807e-05, "loss": 0.8751, "step": 3859 }, { "epoch": 0.7, "learning_rate": 1.9565570809248555e-05, "loss": 0.4585, "step": 3860 }, { "epoch": 0.7, "learning_rate": 1.9562861271676303e-05, "loss": 1.1602, "step": 3861 }, { "epoch": 0.7, "learning_rate": 1.9560151734104047e-05, "loss": 0.8481, "step": 3862 }, { "epoch": 0.7, "learning_rate": 1.955744219653179e-05, "loss": 0.3203, "step": 3863 }, { "epoch": 0.7, "learning_rate": 1.9554732658959536e-05, "loss": 1.0651, "step": 3864 }, { "epoch": 0.7, "learning_rate": 1.9552023121387283e-05, "loss": 1.2132, "step": 3865 }, { "epoch": 0.7, "learning_rate": 1.954931358381503e-05, "loss": 0.5676, "step": 3866 }, { "epoch": 0.7, "learning_rate": 1.9546604046242776e-05, "loss": 0.7874, "step": 3867 }, { "epoch": 0.7, "learning_rate": 1.954389450867052e-05, "loss": 0.8549, "step": 3868 }, { "epoch": 0.7, "learning_rate": 1.9541184971098264e-05, "loss": 0.9777, "step": 3869 }, { "epoch": 0.7, "learning_rate": 1.9538475433526012e-05, "loss": 0.8356, "step": 3870 }, { "epoch": 0.7, "learning_rate": 1.953576589595376e-05, "loss": 0.5227, "step": 3871 }, { "epoch": 0.7, "learning_rate": 1.9533056358381504e-05, "loss": 0.7617, "step": 3872 }, { "epoch": 0.7, "learning_rate": 1.953034682080925e-05, "loss": 0.8394, "step": 3873 }, { "epoch": 0.7, "learning_rate": 1.9527637283236993e-05, "loss": 0.3874, "step": 3874 }, { "epoch": 0.7, "learning_rate": 1.952492774566474e-05, "loss": 1.4888, "step": 3875 }, { "epoch": 0.7, "learning_rate": 1.952221820809249e-05, "loss": 0.7781, "step": 3876 }, { "epoch": 0.7, "learning_rate": 1.951950867052023e-05, "loss": 0.5373, "step": 3877 }, { "epoch": 0.7, "learning_rate": 1.9516799132947977e-05, "loss": 0.8191, "step": 3878 }, { "epoch": 0.7, "learning_rate": 1.951408959537572e-05, "loss": 0.6896, "step": 3879 }, { "epoch": 0.7, "learning_rate": 1.951138005780347e-05, "loss": 0.8633, "step": 3880 }, { "epoch": 0.7, "learning_rate": 1.9508670520231217e-05, "loss": 0.6084, "step": 3881 }, { "epoch": 0.7, "learning_rate": 1.9505960982658958e-05, "loss": 1.3619, "step": 3882 }, { "epoch": 0.7, "learning_rate": 1.9503251445086706e-05, "loss": 0.5357, "step": 3883 }, { "epoch": 0.7, "learning_rate": 1.950054190751445e-05, "loss": 0.3547, "step": 3884 }, { "epoch": 0.7, "learning_rate": 1.9497832369942198e-05, "loss": 0.4904, "step": 3885 }, { "epoch": 0.7, "learning_rate": 1.9495122832369942e-05, "loss": 1.5832, "step": 3886 }, { "epoch": 0.7, "learning_rate": 1.9492413294797687e-05, "loss": 1.2968, "step": 3887 }, { "epoch": 0.7, "learning_rate": 1.9489703757225434e-05, "loss": 0.7273, "step": 3888 }, { "epoch": 0.7, "learning_rate": 1.948699421965318e-05, "loss": 0.3224, "step": 3889 }, { "epoch": 0.7, "learning_rate": 1.9484284682080926e-05, "loss": 1.1449, "step": 3890 }, { "epoch": 0.7, "learning_rate": 1.948157514450867e-05, "loss": 0.9552, "step": 3891 }, { "epoch": 0.7, "learning_rate": 1.9478865606936415e-05, "loss": 0.3418, "step": 3892 }, { "epoch": 0.7, "learning_rate": 1.9476156069364163e-05, "loss": 0.6161, "step": 3893 }, { "epoch": 0.7, "learning_rate": 1.9473446531791907e-05, "loss": 1.3722, "step": 3894 }, { "epoch": 0.7, "learning_rate": 1.9470736994219655e-05, "loss": 0.3531, "step": 3895 }, { "epoch": 0.7, "learning_rate": 1.94680274566474e-05, "loss": 0.9024, "step": 3896 }, { "epoch": 0.7, "learning_rate": 1.9465317919075144e-05, "loss": 0.9201, "step": 3897 }, { "epoch": 0.7, "learning_rate": 1.946260838150289e-05, "loss": 0.748, "step": 3898 }, { "epoch": 0.7, "learning_rate": 1.9459898843930636e-05, "loss": 0.7125, "step": 3899 }, { "epoch": 0.7, "learning_rate": 1.945718930635838e-05, "loss": 0.6825, "step": 3900 }, { "epoch": 0.7, "learning_rate": 1.9454479768786128e-05, "loss": 1.1752, "step": 3901 }, { "epoch": 0.7, "learning_rate": 1.9451770231213872e-05, "loss": 0.7862, "step": 3902 }, { "epoch": 0.71, "learning_rate": 1.944906069364162e-05, "loss": 0.3394, "step": 3903 }, { "epoch": 0.71, "learning_rate": 1.9446351156069368e-05, "loss": 0.3241, "step": 3904 }, { "epoch": 0.71, "learning_rate": 1.944364161849711e-05, "loss": 0.6828, "step": 3905 }, { "epoch": 0.71, "learning_rate": 1.9440932080924857e-05, "loss": 0.8243, "step": 3906 }, { "epoch": 0.71, "learning_rate": 1.94382225433526e-05, "loss": 0.4315, "step": 3907 }, { "epoch": 0.71, "learning_rate": 1.943551300578035e-05, "loss": 1.2564, "step": 3908 }, { "epoch": 0.71, "learning_rate": 1.9432803468208093e-05, "loss": 0.9519, "step": 3909 }, { "epoch": 0.71, "learning_rate": 1.9430093930635837e-05, "loss": 0.677, "step": 3910 }, { "epoch": 0.71, "learning_rate": 1.9427384393063585e-05, "loss": 1.0011, "step": 3911 }, { "epoch": 0.71, "learning_rate": 1.942467485549133e-05, "loss": 0.3251, "step": 3912 }, { "epoch": 0.71, "learning_rate": 1.9421965317919077e-05, "loss": 0.6118, "step": 3913 }, { "epoch": 0.71, "learning_rate": 1.9419255780346822e-05, "loss": 1.0877, "step": 3914 }, { "epoch": 0.71, "learning_rate": 1.9416546242774566e-05, "loss": 1.4866, "step": 3915 }, { "epoch": 0.71, "learning_rate": 1.9413836705202314e-05, "loss": 1.0494, "step": 3916 }, { "epoch": 0.71, "learning_rate": 1.9411127167630058e-05, "loss": 0.4926, "step": 3917 }, { "epoch": 0.71, "learning_rate": 1.9408417630057803e-05, "loss": 0.5353, "step": 3918 }, { "epoch": 0.71, "learning_rate": 1.940570809248555e-05, "loss": 1.2889, "step": 3919 }, { "epoch": 0.71, "learning_rate": 1.9402998554913295e-05, "loss": 0.6471, "step": 3920 }, { "epoch": 0.71, "learning_rate": 1.9400289017341042e-05, "loss": 0.7726, "step": 3921 }, { "epoch": 0.71, "learning_rate": 1.9397579479768787e-05, "loss": 0.7789, "step": 3922 }, { "epoch": 0.71, "learning_rate": 1.939486994219653e-05, "loss": 0.3377, "step": 3923 }, { "epoch": 0.71, "learning_rate": 1.939216040462428e-05, "loss": 0.686, "step": 3924 }, { "epoch": 0.71, "learning_rate": 1.9389450867052023e-05, "loss": 0.7337, "step": 3925 }, { "epoch": 0.71, "learning_rate": 1.938674132947977e-05, "loss": 0.9047, "step": 3926 }, { "epoch": 0.71, "learning_rate": 1.9384031791907515e-05, "loss": 0.5571, "step": 3927 }, { "epoch": 0.71, "learning_rate": 1.938132225433526e-05, "loss": 0.8287, "step": 3928 }, { "epoch": 0.71, "learning_rate": 1.9378612716763008e-05, "loss": 0.9458, "step": 3929 }, { "epoch": 0.71, "learning_rate": 1.9375903179190752e-05, "loss": 0.7892, "step": 3930 }, { "epoch": 0.71, "learning_rate": 1.93731936416185e-05, "loss": 0.2779, "step": 3931 }, { "epoch": 0.71, "learning_rate": 1.937048410404624e-05, "loss": 0.9916, "step": 3932 }, { "epoch": 0.71, "learning_rate": 1.936777456647399e-05, "loss": 0.4822, "step": 3933 }, { "epoch": 0.71, "learning_rate": 1.9365065028901736e-05, "loss": 0.9057, "step": 3934 }, { "epoch": 0.71, "learning_rate": 1.936235549132948e-05, "loss": 0.8427, "step": 3935 }, { "epoch": 0.71, "learning_rate": 1.9359645953757228e-05, "loss": 1.0457, "step": 3936 }, { "epoch": 0.71, "learning_rate": 1.935693641618497e-05, "loss": 1.1436, "step": 3937 }, { "epoch": 0.71, "learning_rate": 1.9354226878612717e-05, "loss": 0.3575, "step": 3938 }, { "epoch": 0.71, "learning_rate": 1.9351517341040465e-05, "loss": 0.6349, "step": 3939 }, { "epoch": 0.71, "learning_rate": 1.934880780346821e-05, "loss": 0.8904, "step": 3940 }, { "epoch": 0.71, "learning_rate": 1.9346098265895953e-05, "loss": 0.824, "step": 3941 }, { "epoch": 0.71, "learning_rate": 1.9343388728323698e-05, "loss": 0.6416, "step": 3942 }, { "epoch": 0.71, "learning_rate": 1.9340679190751446e-05, "loss": 0.7382, "step": 3943 }, { "epoch": 0.71, "learning_rate": 1.9337969653179193e-05, "loss": 0.7058, "step": 3944 }, { "epoch": 0.71, "learning_rate": 1.9335260115606938e-05, "loss": 0.534, "step": 3945 }, { "epoch": 0.71, "learning_rate": 1.9332550578034682e-05, "loss": 0.9199, "step": 3946 }, { "epoch": 0.71, "learning_rate": 1.9329841040462426e-05, "loss": 0.5542, "step": 3947 }, { "epoch": 0.71, "learning_rate": 1.9327131502890174e-05, "loss": 0.7598, "step": 3948 }, { "epoch": 0.71, "learning_rate": 1.9324421965317922e-05, "loss": 0.7731, "step": 3949 }, { "epoch": 0.71, "learning_rate": 1.9321712427745666e-05, "loss": 0.7427, "step": 3950 }, { "epoch": 0.71, "learning_rate": 1.931900289017341e-05, "loss": 0.9554, "step": 3951 }, { "epoch": 0.71, "learning_rate": 1.9316293352601155e-05, "loss": 0.9122, "step": 3952 }, { "epoch": 0.71, "learning_rate": 1.9313583815028903e-05, "loss": 0.7852, "step": 3953 }, { "epoch": 0.71, "learning_rate": 1.931087427745665e-05, "loss": 0.1553, "step": 3954 }, { "epoch": 0.71, "learning_rate": 1.930816473988439e-05, "loss": 0.5708, "step": 3955 }, { "epoch": 0.71, "learning_rate": 1.930545520231214e-05, "loss": 0.9841, "step": 3956 }, { "epoch": 0.71, "learning_rate": 1.9302745664739884e-05, "loss": 0.6593, "step": 3957 }, { "epoch": 0.71, "learning_rate": 1.930003612716763e-05, "loss": 0.3664, "step": 3958 }, { "epoch": 0.72, "learning_rate": 1.929732658959538e-05, "loss": 0.5302, "step": 3959 }, { "epoch": 0.72, "learning_rate": 1.929461705202312e-05, "loss": 0.7686, "step": 3960 }, { "epoch": 0.72, "learning_rate": 1.9291907514450868e-05, "loss": 0.4986, "step": 3961 }, { "epoch": 0.72, "learning_rate": 1.9289197976878612e-05, "loss": 0.6274, "step": 3962 }, { "epoch": 0.72, "learning_rate": 1.928648843930636e-05, "loss": 1.6834, "step": 3963 }, { "epoch": 0.72, "learning_rate": 1.9283778901734104e-05, "loss": 0.5643, "step": 3964 }, { "epoch": 0.72, "learning_rate": 1.928106936416185e-05, "loss": 0.7813, "step": 3965 }, { "epoch": 0.72, "learning_rate": 1.9278359826589596e-05, "loss": 0.5247, "step": 3966 }, { "epoch": 0.72, "learning_rate": 1.927565028901734e-05, "loss": 0.5761, "step": 3967 }, { "epoch": 0.72, "learning_rate": 1.927294075144509e-05, "loss": 0.9567, "step": 3968 }, { "epoch": 0.72, "learning_rate": 1.9270231213872833e-05, "loss": 0.9357, "step": 3969 }, { "epoch": 0.72, "learning_rate": 1.9267521676300577e-05, "loss": 0.6862, "step": 3970 }, { "epoch": 0.72, "learning_rate": 1.9264812138728325e-05, "loss": 1.4816, "step": 3971 }, { "epoch": 0.72, "learning_rate": 1.926210260115607e-05, "loss": 1.4878, "step": 3972 }, { "epoch": 0.72, "learning_rate": 1.9259393063583817e-05, "loss": 0.4472, "step": 3973 }, { "epoch": 0.72, "learning_rate": 1.925668352601156e-05, "loss": 0.8025, "step": 3974 }, { "epoch": 0.72, "learning_rate": 1.9253973988439306e-05, "loss": 1.1729, "step": 3975 }, { "epoch": 0.72, "learning_rate": 1.9251264450867054e-05, "loss": 0.59, "step": 3976 }, { "epoch": 0.72, "learning_rate": 1.9248554913294798e-05, "loss": 0.7346, "step": 3977 }, { "epoch": 0.72, "learning_rate": 1.9245845375722542e-05, "loss": 1.3387, "step": 3978 }, { "epoch": 0.72, "learning_rate": 1.924313583815029e-05, "loss": 0.9879, "step": 3979 }, { "epoch": 0.72, "learning_rate": 1.9240426300578035e-05, "loss": 0.9129, "step": 3980 }, { "epoch": 0.72, "learning_rate": 1.9237716763005782e-05, "loss": 0.4471, "step": 3981 }, { "epoch": 0.72, "learning_rate": 1.9235007225433527e-05, "loss": 0.9988, "step": 3982 }, { "epoch": 0.72, "learning_rate": 1.923229768786127e-05, "loss": 0.4274, "step": 3983 }, { "epoch": 0.72, "learning_rate": 1.922958815028902e-05, "loss": 1.1062, "step": 3984 }, { "epoch": 0.72, "learning_rate": 1.9226878612716763e-05, "loss": 0.94, "step": 3985 }, { "epoch": 0.72, "learning_rate": 1.922416907514451e-05, "loss": 1.1902, "step": 3986 }, { "epoch": 0.72, "learning_rate": 1.9221459537572252e-05, "loss": 1.1645, "step": 3987 }, { "epoch": 0.72, "learning_rate": 1.921875e-05, "loss": 0.4982, "step": 3988 }, { "epoch": 0.72, "learning_rate": 1.9216040462427747e-05, "loss": 0.6047, "step": 3989 }, { "epoch": 0.72, "learning_rate": 1.9213330924855492e-05, "loss": 0.9983, "step": 3990 }, { "epoch": 0.72, "learning_rate": 1.921062138728324e-05, "loss": 0.1987, "step": 3991 }, { "epoch": 0.72, "learning_rate": 1.920791184971098e-05, "loss": 0.9683, "step": 3992 }, { "epoch": 0.72, "learning_rate": 1.9205202312138728e-05, "loss": 0.5381, "step": 3993 }, { "epoch": 0.72, "learning_rate": 1.9202492774566476e-05, "loss": 0.9903, "step": 3994 }, { "epoch": 0.72, "learning_rate": 1.919978323699422e-05, "loss": 1.071, "step": 3995 }, { "epoch": 0.72, "learning_rate": 1.9197073699421968e-05, "loss": 0.7626, "step": 3996 }, { "epoch": 0.72, "learning_rate": 1.919436416184971e-05, "loss": 0.6008, "step": 3997 }, { "epoch": 0.72, "learning_rate": 1.9191654624277457e-05, "loss": 0.5434, "step": 3998 }, { "epoch": 0.72, "learning_rate": 1.9188945086705205e-05, "loss": 0.9622, "step": 3999 }, { "epoch": 0.72, "learning_rate": 1.918623554913295e-05, "loss": 0.6423, "step": 4000 }, { "epoch": 0.72, "eval_exact_match": 86.91579943235573, "eval_f1": 93.08639840155402, "step": 4000 }, { "epoch": 0.72, "learning_rate": 1.9183526011560693e-05, "loss": 0.3299, "step": 4001 }, { "epoch": 0.72, "learning_rate": 1.9180816473988438e-05, "loss": 0.6518, "step": 4002 }, { "epoch": 0.72, "learning_rate": 1.9178106936416185e-05, "loss": 1.6279, "step": 4003 }, { "epoch": 0.72, "learning_rate": 1.9175397398843933e-05, "loss": 0.4024, "step": 4004 }, { "epoch": 0.72, "learning_rate": 1.9172687861271678e-05, "loss": 1.5095, "step": 4005 }, { "epoch": 0.72, "learning_rate": 1.9169978323699422e-05, "loss": 1.5505, "step": 4006 }, { "epoch": 0.72, "learning_rate": 1.9167268786127166e-05, "loss": 0.8517, "step": 4007 }, { "epoch": 0.72, "learning_rate": 1.9164559248554914e-05, "loss": 0.7558, "step": 4008 }, { "epoch": 0.72, "learning_rate": 1.9161849710982662e-05, "loss": 1.4641, "step": 4009 }, { "epoch": 0.72, "learning_rate": 1.9159140173410403e-05, "loss": 0.9159, "step": 4010 }, { "epoch": 0.72, "learning_rate": 1.915643063583815e-05, "loss": 0.8663, "step": 4011 }, { "epoch": 0.72, "learning_rate": 1.9153721098265895e-05, "loss": 0.4452, "step": 4012 }, { "epoch": 0.72, "learning_rate": 1.9151011560693643e-05, "loss": 0.9606, "step": 4013 }, { "epoch": 0.73, "learning_rate": 1.914830202312139e-05, "loss": 0.8141, "step": 4014 }, { "epoch": 0.73, "learning_rate": 1.914559248554913e-05, "loss": 0.7857, "step": 4015 }, { "epoch": 0.73, "learning_rate": 1.914288294797688e-05, "loss": 0.5632, "step": 4016 }, { "epoch": 0.73, "learning_rate": 1.9140173410404623e-05, "loss": 0.7552, "step": 4017 }, { "epoch": 0.73, "learning_rate": 1.913746387283237e-05, "loss": 1.4583, "step": 4018 }, { "epoch": 0.73, "learning_rate": 1.913475433526012e-05, "loss": 0.9303, "step": 4019 }, { "epoch": 0.73, "learning_rate": 1.913204479768786e-05, "loss": 0.8846, "step": 4020 }, { "epoch": 0.73, "learning_rate": 1.9129335260115608e-05, "loss": 1.1066, "step": 4021 }, { "epoch": 0.73, "learning_rate": 1.9126625722543352e-05, "loss": 0.71, "step": 4022 }, { "epoch": 0.73, "learning_rate": 1.91239161849711e-05, "loss": 0.6425, "step": 4023 }, { "epoch": 0.73, "learning_rate": 1.9121206647398844e-05, "loss": 0.9688, "step": 4024 }, { "epoch": 0.73, "learning_rate": 1.911849710982659e-05, "loss": 0.3849, "step": 4025 }, { "epoch": 0.73, "learning_rate": 1.9115787572254336e-05, "loss": 0.8745, "step": 4026 }, { "epoch": 0.73, "learning_rate": 1.911307803468208e-05, "loss": 0.6883, "step": 4027 }, { "epoch": 0.73, "learning_rate": 1.911036849710983e-05, "loss": 1.0269, "step": 4028 }, { "epoch": 0.73, "learning_rate": 1.9107658959537573e-05, "loss": 0.8646, "step": 4029 }, { "epoch": 0.73, "learning_rate": 1.9104949421965317e-05, "loss": 0.62, "step": 4030 }, { "epoch": 0.73, "learning_rate": 1.9102239884393065e-05, "loss": 0.4909, "step": 4031 }, { "epoch": 0.73, "learning_rate": 1.909953034682081e-05, "loss": 0.7948, "step": 4032 }, { "epoch": 0.73, "learning_rate": 1.9096820809248554e-05, "loss": 0.8547, "step": 4033 }, { "epoch": 0.73, "learning_rate": 1.90941112716763e-05, "loss": 0.578, "step": 4034 }, { "epoch": 0.73, "learning_rate": 1.9091401734104046e-05, "loss": 1.4733, "step": 4035 }, { "epoch": 0.73, "learning_rate": 1.9088692196531793e-05, "loss": 0.6537, "step": 4036 }, { "epoch": 0.73, "learning_rate": 1.9085982658959538e-05, "loss": 0.9657, "step": 4037 }, { "epoch": 0.73, "learning_rate": 1.9083273121387282e-05, "loss": 0.7869, "step": 4038 }, { "epoch": 0.73, "learning_rate": 1.908056358381503e-05, "loss": 1.0672, "step": 4039 }, { "epoch": 0.73, "learning_rate": 1.9077854046242774e-05, "loss": 1.1438, "step": 4040 }, { "epoch": 0.73, "learning_rate": 1.9075144508670522e-05, "loss": 0.8065, "step": 4041 }, { "epoch": 0.73, "learning_rate": 1.9072434971098266e-05, "loss": 1.0029, "step": 4042 }, { "epoch": 0.73, "learning_rate": 1.906972543352601e-05, "loss": 0.4517, "step": 4043 }, { "epoch": 0.73, "learning_rate": 1.906701589595376e-05, "loss": 1.3693, "step": 4044 }, { "epoch": 0.73, "learning_rate": 1.9064306358381503e-05, "loss": 0.9116, "step": 4045 }, { "epoch": 0.73, "learning_rate": 1.906159682080925e-05, "loss": 0.224, "step": 4046 }, { "epoch": 0.73, "learning_rate": 1.905888728323699e-05, "loss": 0.52, "step": 4047 }, { "epoch": 0.73, "learning_rate": 1.905617774566474e-05, "loss": 0.9657, "step": 4048 }, { "epoch": 0.73, "learning_rate": 1.9053468208092487e-05, "loss": 0.8887, "step": 4049 }, { "epoch": 0.73, "learning_rate": 1.905075867052023e-05, "loss": 1.0086, "step": 4050 }, { "epoch": 0.73, "learning_rate": 1.904804913294798e-05, "loss": 0.9769, "step": 4051 }, { "epoch": 0.73, "learning_rate": 1.904533959537572e-05, "loss": 0.9813, "step": 4052 }, { "epoch": 0.73, "learning_rate": 1.9042630057803468e-05, "loss": 0.5102, "step": 4053 }, { "epoch": 0.73, "learning_rate": 1.9039920520231216e-05, "loss": 0.6098, "step": 4054 }, { "epoch": 0.73, "learning_rate": 1.903721098265896e-05, "loss": 1.5279, "step": 4055 }, { "epoch": 0.73, "learning_rate": 1.9034501445086705e-05, "loss": 0.541, "step": 4056 }, { "epoch": 0.73, "learning_rate": 1.903179190751445e-05, "loss": 0.324, "step": 4057 }, { "epoch": 0.73, "learning_rate": 1.9029082369942197e-05, "loss": 0.5553, "step": 4058 }, { "epoch": 0.73, "learning_rate": 1.9026372832369944e-05, "loss": 1.0303, "step": 4059 }, { "epoch": 0.73, "learning_rate": 1.902366329479769e-05, "loss": 0.6879, "step": 4060 }, { "epoch": 0.73, "learning_rate": 1.9020953757225433e-05, "loss": 0.534, "step": 4061 }, { "epoch": 0.73, "learning_rate": 1.9018244219653177e-05, "loss": 0.8632, "step": 4062 }, { "epoch": 0.73, "learning_rate": 1.9015534682080925e-05, "loss": 1.3539, "step": 4063 }, { "epoch": 0.73, "learning_rate": 1.9012825144508673e-05, "loss": 1.3289, "step": 4064 }, { "epoch": 0.73, "learning_rate": 1.9010115606936417e-05, "loss": 0.4264, "step": 4065 }, { "epoch": 0.73, "learning_rate": 1.9007406069364162e-05, "loss": 0.4714, "step": 4066 }, { "epoch": 0.73, "learning_rate": 1.9004696531791906e-05, "loss": 0.5382, "step": 4067 }, { "epoch": 0.73, "learning_rate": 1.9001986994219654e-05, "loss": 0.6463, "step": 4068 }, { "epoch": 0.74, "learning_rate": 1.89992774566474e-05, "loss": 0.3583, "step": 4069 }, { "epoch": 0.74, "learning_rate": 1.8996567919075143e-05, "loss": 0.517, "step": 4070 }, { "epoch": 0.74, "learning_rate": 1.899385838150289e-05, "loss": 0.5943, "step": 4071 }, { "epoch": 0.74, "learning_rate": 1.8991148843930635e-05, "loss": 1.591, "step": 4072 }, { "epoch": 0.74, "learning_rate": 1.8988439306358382e-05, "loss": 0.3914, "step": 4073 }, { "epoch": 0.74, "learning_rate": 1.898572976878613e-05, "loss": 0.6481, "step": 4074 }, { "epoch": 0.74, "learning_rate": 1.898302023121387e-05, "loss": 0.571, "step": 4075 }, { "epoch": 0.74, "learning_rate": 1.898031069364162e-05, "loss": 1.0786, "step": 4076 }, { "epoch": 0.74, "learning_rate": 1.8977601156069367e-05, "loss": 0.469, "step": 4077 }, { "epoch": 0.74, "learning_rate": 1.897489161849711e-05, "loss": 0.4791, "step": 4078 }, { "epoch": 0.74, "learning_rate": 1.8972182080924855e-05, "loss": 0.816, "step": 4079 }, { "epoch": 0.74, "learning_rate": 1.89694725433526e-05, "loss": 0.7027, "step": 4080 }, { "epoch": 0.74, "learning_rate": 1.8966763005780348e-05, "loss": 2.1599, "step": 4081 }, { "epoch": 0.74, "learning_rate": 1.8964053468208095e-05, "loss": 1.383, "step": 4082 }, { "epoch": 0.74, "learning_rate": 1.896134393063584e-05, "loss": 1.4108, "step": 4083 }, { "epoch": 0.74, "learning_rate": 1.8958634393063584e-05, "loss": 0.9818, "step": 4084 }, { "epoch": 0.74, "learning_rate": 1.895592485549133e-05, "loss": 1.1416, "step": 4085 }, { "epoch": 0.74, "learning_rate": 1.8953215317919076e-05, "loss": 1.3502, "step": 4086 }, { "epoch": 0.74, "learning_rate": 1.8950505780346824e-05, "loss": 0.9544, "step": 4087 }, { "epoch": 0.74, "learning_rate": 1.8947796242774568e-05, "loss": 1.3676, "step": 4088 }, { "epoch": 0.74, "learning_rate": 1.8945086705202313e-05, "loss": 0.8476, "step": 4089 }, { "epoch": 0.74, "learning_rate": 1.8942377167630057e-05, "loss": 1.4336, "step": 4090 }, { "epoch": 0.74, "learning_rate": 1.8939667630057805e-05, "loss": 0.7402, "step": 4091 }, { "epoch": 0.74, "learning_rate": 1.8936958092485552e-05, "loss": 0.7207, "step": 4092 }, { "epoch": 0.74, "learning_rate": 1.8934248554913293e-05, "loss": 0.8673, "step": 4093 }, { "epoch": 0.74, "learning_rate": 1.893153901734104e-05, "loss": 0.9265, "step": 4094 }, { "epoch": 0.74, "learning_rate": 1.8928829479768786e-05, "loss": 0.702, "step": 4095 }, { "epoch": 0.74, "learning_rate": 1.8926119942196533e-05, "loss": 0.7604, "step": 4096 }, { "epoch": 0.74, "learning_rate": 1.892341040462428e-05, "loss": 1.1846, "step": 4097 }, { "epoch": 0.74, "learning_rate": 1.8920700867052022e-05, "loss": 1.0293, "step": 4098 }, { "epoch": 0.74, "learning_rate": 1.891799132947977e-05, "loss": 0.8059, "step": 4099 }, { "epoch": 0.74, "learning_rate": 1.8915281791907514e-05, "loss": 0.9668, "step": 4100 }, { "epoch": 0.74, "learning_rate": 1.8912572254335262e-05, "loss": 0.8274, "step": 4101 }, { "epoch": 0.74, "learning_rate": 1.8909862716763006e-05, "loss": 0.7496, "step": 4102 }, { "epoch": 0.74, "learning_rate": 1.890715317919075e-05, "loss": 0.7773, "step": 4103 }, { "epoch": 0.74, "learning_rate": 1.89044436416185e-05, "loss": 0.4221, "step": 4104 }, { "epoch": 0.74, "learning_rate": 1.8901734104046243e-05, "loss": 1.6271, "step": 4105 }, { "epoch": 0.74, "learning_rate": 1.889902456647399e-05, "loss": 0.7703, "step": 4106 }, { "epoch": 0.74, "learning_rate": 1.8896315028901735e-05, "loss": 0.6701, "step": 4107 }, { "epoch": 0.74, "learning_rate": 1.889360549132948e-05, "loss": 1.2098, "step": 4108 }, { "epoch": 0.74, "learning_rate": 1.8890895953757227e-05, "loss": 1.1312, "step": 4109 }, { "epoch": 0.74, "learning_rate": 1.888818641618497e-05, "loss": 0.8052, "step": 4110 }, { "epoch": 0.74, "learning_rate": 1.888547687861272e-05, "loss": 0.9755, "step": 4111 }, { "epoch": 0.74, "learning_rate": 1.8882767341040463e-05, "loss": 1.1487, "step": 4112 }, { "epoch": 0.74, "learning_rate": 1.8880057803468208e-05, "loss": 0.4801, "step": 4113 }, { "epoch": 0.74, "learning_rate": 1.8877348265895956e-05, "loss": 1.0129, "step": 4114 }, { "epoch": 0.74, "learning_rate": 1.88746387283237e-05, "loss": 0.4834, "step": 4115 }, { "epoch": 0.74, "learning_rate": 1.8871929190751444e-05, "loss": 1.5982, "step": 4116 }, { "epoch": 0.74, "learning_rate": 1.8869219653179192e-05, "loss": 0.9344, "step": 4117 }, { "epoch": 0.74, "learning_rate": 1.8866510115606936e-05, "loss": 0.8633, "step": 4118 }, { "epoch": 0.74, "learning_rate": 1.8863800578034684e-05, "loss": 0.4349, "step": 4119 }, { "epoch": 0.74, "learning_rate": 1.886109104046243e-05, "loss": 0.4281, "step": 4120 }, { "epoch": 0.74, "learning_rate": 1.8858381502890173e-05, "loss": 0.9698, "step": 4121 }, { "epoch": 0.74, "learning_rate": 1.885567196531792e-05, "loss": 0.8202, "step": 4122 }, { "epoch": 0.74, "learning_rate": 1.8852962427745665e-05, "loss": 0.7031, "step": 4123 }, { "epoch": 0.74, "learning_rate": 1.8850252890173413e-05, "loss": 1.3759, "step": 4124 }, { "epoch": 0.75, "learning_rate": 1.8847543352601154e-05, "loss": 1.2684, "step": 4125 }, { "epoch": 0.75, "learning_rate": 1.88448338150289e-05, "loss": 1.3674, "step": 4126 }, { "epoch": 0.75, "learning_rate": 1.884212427745665e-05, "loss": 0.7798, "step": 4127 }, { "epoch": 0.75, "learning_rate": 1.8839414739884394e-05, "loss": 0.7712, "step": 4128 }, { "epoch": 0.75, "learning_rate": 1.883670520231214e-05, "loss": 1.1654, "step": 4129 }, { "epoch": 0.75, "learning_rate": 1.8833995664739882e-05, "loss": 0.986, "step": 4130 }, { "epoch": 0.75, "learning_rate": 1.883128612716763e-05, "loss": 0.9688, "step": 4131 }, { "epoch": 0.75, "learning_rate": 1.8828576589595378e-05, "loss": 0.4897, "step": 4132 }, { "epoch": 0.75, "learning_rate": 1.8825867052023122e-05, "loss": 0.6146, "step": 4133 }, { "epoch": 0.75, "learning_rate": 1.8823157514450867e-05, "loss": 0.7737, "step": 4134 }, { "epoch": 0.75, "learning_rate": 1.882044797687861e-05, "loss": 0.4787, "step": 4135 }, { "epoch": 0.75, "learning_rate": 1.881773843930636e-05, "loss": 1.0388, "step": 4136 }, { "epoch": 0.75, "learning_rate": 1.8815028901734106e-05, "loss": 0.4319, "step": 4137 }, { "epoch": 0.75, "learning_rate": 1.881231936416185e-05, "loss": 0.6412, "step": 4138 }, { "epoch": 0.75, "learning_rate": 1.8809609826589595e-05, "loss": 0.848, "step": 4139 }, { "epoch": 0.75, "learning_rate": 1.880690028901734e-05, "loss": 1.2591, "step": 4140 }, { "epoch": 0.75, "learning_rate": 1.8804190751445087e-05, "loss": 0.5011, "step": 4141 }, { "epoch": 0.75, "learning_rate": 1.8801481213872835e-05, "loss": 1.0324, "step": 4142 }, { "epoch": 0.75, "learning_rate": 1.879877167630058e-05, "loss": 0.3491, "step": 4143 }, { "epoch": 0.75, "learning_rate": 1.8796062138728324e-05, "loss": 0.5299, "step": 4144 }, { "epoch": 0.75, "learning_rate": 1.8793352601156068e-05, "loss": 0.7867, "step": 4145 }, { "epoch": 0.75, "learning_rate": 1.8790643063583816e-05, "loss": 0.6303, "step": 4146 }, { "epoch": 0.75, "learning_rate": 1.8787933526011564e-05, "loss": 0.9503, "step": 4147 }, { "epoch": 0.75, "learning_rate": 1.8785223988439305e-05, "loss": 0.2877, "step": 4148 }, { "epoch": 0.75, "learning_rate": 1.8782514450867052e-05, "loss": 0.5625, "step": 4149 }, { "epoch": 0.75, "learning_rate": 1.8779804913294797e-05, "loss": 0.9687, "step": 4150 }, { "epoch": 0.75, "learning_rate": 1.8777095375722545e-05, "loss": 0.7076, "step": 4151 }, { "epoch": 0.75, "learning_rate": 1.8774385838150292e-05, "loss": 1.116, "step": 4152 }, { "epoch": 0.75, "learning_rate": 1.8771676300578033e-05, "loss": 1.4053, "step": 4153 }, { "epoch": 0.75, "learning_rate": 1.876896676300578e-05, "loss": 0.7567, "step": 4154 }, { "epoch": 0.75, "learning_rate": 1.8766257225433525e-05, "loss": 0.8233, "step": 4155 }, { "epoch": 0.75, "learning_rate": 1.8763547687861273e-05, "loss": 0.8191, "step": 4156 }, { "epoch": 0.75, "learning_rate": 1.8760838150289018e-05, "loss": 0.6434, "step": 4157 }, { "epoch": 0.75, "learning_rate": 1.8758128612716762e-05, "loss": 0.9443, "step": 4158 }, { "epoch": 0.75, "learning_rate": 1.875541907514451e-05, "loss": 0.8326, "step": 4159 }, { "epoch": 0.75, "learning_rate": 1.8752709537572254e-05, "loss": 0.7386, "step": 4160 }, { "epoch": 0.75, "learning_rate": 1.8750000000000002e-05, "loss": 0.6589, "step": 4161 }, { "epoch": 0.75, "learning_rate": 1.8747290462427746e-05, "loss": 1.0409, "step": 4162 }, { "epoch": 0.75, "learning_rate": 1.874458092485549e-05, "loss": 0.6948, "step": 4163 }, { "epoch": 0.75, "learning_rate": 1.8741871387283238e-05, "loss": 1.2166, "step": 4164 }, { "epoch": 0.75, "learning_rate": 1.8739161849710983e-05, "loss": 0.7334, "step": 4165 }, { "epoch": 0.75, "learning_rate": 1.873645231213873e-05, "loss": 1.0864, "step": 4166 }, { "epoch": 0.75, "learning_rate": 1.8733742774566475e-05, "loss": 0.8165, "step": 4167 }, { "epoch": 0.75, "learning_rate": 1.873103323699422e-05, "loss": 1.9391, "step": 4168 }, { "epoch": 0.75, "learning_rate": 1.8728323699421967e-05, "loss": 0.764, "step": 4169 }, { "epoch": 0.75, "learning_rate": 1.872561416184971e-05, "loss": 1.2012, "step": 4170 }, { "epoch": 0.75, "learning_rate": 1.8722904624277456e-05, "loss": 0.8938, "step": 4171 }, { "epoch": 0.75, "learning_rate": 1.8720195086705203e-05, "loss": 0.916, "step": 4172 }, { "epoch": 0.75, "learning_rate": 1.8717485549132948e-05, "loss": 0.4686, "step": 4173 }, { "epoch": 0.75, "learning_rate": 1.8714776011560695e-05, "loss": 1.0593, "step": 4174 }, { "epoch": 0.75, "learning_rate": 1.871206647398844e-05, "loss": 0.6811, "step": 4175 }, { "epoch": 0.75, "learning_rate": 1.8709356936416184e-05, "loss": 0.5811, "step": 4176 }, { "epoch": 0.75, "learning_rate": 1.8706647398843932e-05, "loss": 0.9423, "step": 4177 }, { "epoch": 0.75, "learning_rate": 1.8703937861271676e-05, "loss": 0.3707, "step": 4178 }, { "epoch": 0.75, "learning_rate": 1.8701228323699424e-05, "loss": 0.9544, "step": 4179 }, { "epoch": 0.76, "learning_rate": 1.8698518786127165e-05, "loss": 0.3986, "step": 4180 }, { "epoch": 0.76, "learning_rate": 1.8695809248554913e-05, "loss": 0.9047, "step": 4181 }, { "epoch": 0.76, "learning_rate": 1.869309971098266e-05, "loss": 0.6173, "step": 4182 }, { "epoch": 0.76, "learning_rate": 1.8690390173410405e-05, "loss": 1.4116, "step": 4183 }, { "epoch": 0.76, "learning_rate": 1.8687680635838153e-05, "loss": 0.4645, "step": 4184 }, { "epoch": 0.76, "learning_rate": 1.8684971098265894e-05, "loss": 0.3815, "step": 4185 }, { "epoch": 0.76, "learning_rate": 1.868226156069364e-05, "loss": 0.8812, "step": 4186 }, { "epoch": 0.76, "learning_rate": 1.867955202312139e-05, "loss": 0.508, "step": 4187 }, { "epoch": 0.76, "learning_rate": 1.8676842485549133e-05, "loss": 0.3497, "step": 4188 }, { "epoch": 0.76, "learning_rate": 1.867413294797688e-05, "loss": 0.7256, "step": 4189 }, { "epoch": 0.76, "learning_rate": 1.8671423410404622e-05, "loss": 0.5832, "step": 4190 }, { "epoch": 0.76, "learning_rate": 1.866871387283237e-05, "loss": 0.7938, "step": 4191 }, { "epoch": 0.76, "learning_rate": 1.8666004335260118e-05, "loss": 0.9414, "step": 4192 }, { "epoch": 0.76, "learning_rate": 1.8663294797687862e-05, "loss": 0.6125, "step": 4193 }, { "epoch": 0.76, "learning_rate": 1.8660585260115606e-05, "loss": 0.6773, "step": 4194 }, { "epoch": 0.76, "learning_rate": 1.865787572254335e-05, "loss": 0.4446, "step": 4195 }, { "epoch": 0.76, "learning_rate": 1.86551661849711e-05, "loss": 0.8612, "step": 4196 }, { "epoch": 0.76, "learning_rate": 1.8652456647398846e-05, "loss": 0.6635, "step": 4197 }, { "epoch": 0.76, "learning_rate": 1.864974710982659e-05, "loss": 1.0273, "step": 4198 }, { "epoch": 0.76, "learning_rate": 1.8647037572254335e-05, "loss": 2.0535, "step": 4199 }, { "epoch": 0.76, "learning_rate": 1.864432803468208e-05, "loss": 0.46, "step": 4200 }, { "epoch": 0.76, "learning_rate": 1.8641618497109827e-05, "loss": 1.2826, "step": 4201 }, { "epoch": 0.76, "learning_rate": 1.8638908959537575e-05, "loss": 0.5547, "step": 4202 }, { "epoch": 0.76, "learning_rate": 1.8636199421965316e-05, "loss": 0.5909, "step": 4203 }, { "epoch": 0.76, "learning_rate": 1.8633489884393064e-05, "loss": 0.6958, "step": 4204 }, { "epoch": 0.76, "learning_rate": 1.8630780346820808e-05, "loss": 1.4733, "step": 4205 }, { "epoch": 0.76, "learning_rate": 1.8628070809248556e-05, "loss": 0.6808, "step": 4206 }, { "epoch": 0.76, "learning_rate": 1.8625361271676304e-05, "loss": 0.7142, "step": 4207 }, { "epoch": 0.76, "learning_rate": 1.8622651734104045e-05, "loss": 1.2077, "step": 4208 }, { "epoch": 0.76, "learning_rate": 1.8619942196531792e-05, "loss": 1.3005, "step": 4209 }, { "epoch": 0.76, "learning_rate": 1.8617232658959537e-05, "loss": 0.903, "step": 4210 }, { "epoch": 0.76, "learning_rate": 1.8614523121387284e-05, "loss": 0.8644, "step": 4211 }, { "epoch": 0.76, "learning_rate": 1.8611813583815032e-05, "loss": 1.0254, "step": 4212 }, { "epoch": 0.76, "learning_rate": 1.8609104046242773e-05, "loss": 0.56, "step": 4213 }, { "epoch": 0.76, "learning_rate": 1.860639450867052e-05, "loss": 0.6452, "step": 4214 }, { "epoch": 0.76, "learning_rate": 1.8603684971098265e-05, "loss": 1.3318, "step": 4215 }, { "epoch": 0.76, "learning_rate": 1.8600975433526013e-05, "loss": 1.0756, "step": 4216 }, { "epoch": 0.76, "learning_rate": 1.8598265895953757e-05, "loss": 0.4879, "step": 4217 }, { "epoch": 0.76, "learning_rate": 1.8595556358381502e-05, "loss": 0.2533, "step": 4218 }, { "epoch": 0.76, "learning_rate": 1.859284682080925e-05, "loss": 0.8518, "step": 4219 }, { "epoch": 0.76, "learning_rate": 1.8590137283236994e-05, "loss": 0.6445, "step": 4220 }, { "epoch": 0.76, "learning_rate": 1.858742774566474e-05, "loss": 0.8187, "step": 4221 }, { "epoch": 0.76, "learning_rate": 1.8584718208092486e-05, "loss": 1.3737, "step": 4222 }, { "epoch": 0.76, "learning_rate": 1.858200867052023e-05, "loss": 1.4099, "step": 4223 }, { "epoch": 0.76, "learning_rate": 1.8579299132947978e-05, "loss": 0.9348, "step": 4224 }, { "epoch": 0.76, "learning_rate": 1.8576589595375722e-05, "loss": 0.1903, "step": 4225 }, { "epoch": 0.76, "learning_rate": 1.8573880057803467e-05, "loss": 0.4917, "step": 4226 }, { "epoch": 0.76, "learning_rate": 1.8571170520231215e-05, "loss": 1.4319, "step": 4227 }, { "epoch": 0.76, "learning_rate": 1.856846098265896e-05, "loss": 0.8961, "step": 4228 }, { "epoch": 0.76, "learning_rate": 1.8565751445086707e-05, "loss": 0.7755, "step": 4229 }, { "epoch": 0.76, "learning_rate": 1.856304190751445e-05, "loss": 0.9128, "step": 4230 }, { "epoch": 0.76, "learning_rate": 1.8560332369942195e-05, "loss": 0.5471, "step": 4231 }, { "epoch": 0.76, "learning_rate": 1.8557622832369943e-05, "loss": 0.5857, "step": 4232 }, { "epoch": 0.76, "learning_rate": 1.8554913294797688e-05, "loss": 0.6862, "step": 4233 }, { "epoch": 0.76, "learning_rate": 1.8552203757225435e-05, "loss": 1.3108, "step": 4234 }, { "epoch": 0.76, "learning_rate": 1.854949421965318e-05, "loss": 0.9049, "step": 4235 }, { "epoch": 0.77, "learning_rate": 1.8546784682080924e-05, "loss": 0.339, "step": 4236 }, { "epoch": 0.77, "learning_rate": 1.8544075144508672e-05, "loss": 1.2379, "step": 4237 }, { "epoch": 0.77, "learning_rate": 1.8541365606936416e-05, "loss": 0.6839, "step": 4238 }, { "epoch": 0.77, "learning_rate": 1.8538656069364164e-05, "loss": 0.7529, "step": 4239 }, { "epoch": 0.77, "learning_rate": 1.8535946531791905e-05, "loss": 0.9136, "step": 4240 }, { "epoch": 0.77, "learning_rate": 1.8533236994219653e-05, "loss": 0.5094, "step": 4241 }, { "epoch": 0.77, "learning_rate": 1.85305274566474e-05, "loss": 0.8691, "step": 4242 }, { "epoch": 0.77, "learning_rate": 1.8527817919075145e-05, "loss": 0.3341, "step": 4243 }, { "epoch": 0.77, "learning_rate": 1.8525108381502892e-05, "loss": 0.6698, "step": 4244 }, { "epoch": 0.77, "learning_rate": 1.8522398843930633e-05, "loss": 0.4947, "step": 4245 }, { "epoch": 0.77, "learning_rate": 1.851968930635838e-05, "loss": 0.5462, "step": 4246 }, { "epoch": 0.77, "learning_rate": 1.851697976878613e-05, "loss": 0.7211, "step": 4247 }, { "epoch": 0.77, "learning_rate": 1.8514270231213873e-05, "loss": 0.7737, "step": 4248 }, { "epoch": 0.77, "learning_rate": 1.8511560693641618e-05, "loss": 0.9608, "step": 4249 }, { "epoch": 0.77, "learning_rate": 1.8508851156069365e-05, "loss": 0.8124, "step": 4250 }, { "epoch": 0.77, "learning_rate": 1.850614161849711e-05, "loss": 0.5091, "step": 4251 }, { "epoch": 0.77, "learning_rate": 1.8503432080924858e-05, "loss": 0.4745, "step": 4252 }, { "epoch": 0.77, "learning_rate": 1.8500722543352602e-05, "loss": 0.6932, "step": 4253 }, { "epoch": 0.77, "learning_rate": 1.8498013005780346e-05, "loss": 0.7364, "step": 4254 }, { "epoch": 0.77, "learning_rate": 1.8495303468208094e-05, "loss": 0.9825, "step": 4255 }, { "epoch": 0.77, "learning_rate": 1.849259393063584e-05, "loss": 0.6294, "step": 4256 }, { "epoch": 0.77, "learning_rate": 1.8489884393063586e-05, "loss": 0.6172, "step": 4257 }, { "epoch": 0.77, "learning_rate": 1.848717485549133e-05, "loss": 1.107, "step": 4258 }, { "epoch": 0.77, "learning_rate": 1.8484465317919075e-05, "loss": 0.9362, "step": 4259 }, { "epoch": 0.77, "learning_rate": 1.8481755780346823e-05, "loss": 0.987, "step": 4260 }, { "epoch": 0.77, "learning_rate": 1.8479046242774567e-05, "loss": 1.1583, "step": 4261 }, { "epoch": 0.77, "learning_rate": 1.8476336705202315e-05, "loss": 0.4498, "step": 4262 }, { "epoch": 0.77, "learning_rate": 1.8473627167630056e-05, "loss": 1.7839, "step": 4263 }, { "epoch": 0.77, "learning_rate": 1.8470917630057803e-05, "loss": 0.6637, "step": 4264 }, { "epoch": 0.77, "learning_rate": 1.846820809248555e-05, "loss": 0.7501, "step": 4265 }, { "epoch": 0.77, "learning_rate": 1.8465498554913296e-05, "loss": 1.0381, "step": 4266 }, { "epoch": 0.77, "learning_rate": 1.8462789017341043e-05, "loss": 0.6484, "step": 4267 }, { "epoch": 0.77, "learning_rate": 1.8460079479768784e-05, "loss": 0.5107, "step": 4268 }, { "epoch": 0.77, "learning_rate": 1.8457369942196532e-05, "loss": 0.6778, "step": 4269 }, { "epoch": 0.77, "learning_rate": 1.845466040462428e-05, "loss": 0.913, "step": 4270 }, { "epoch": 0.77, "learning_rate": 1.8451950867052024e-05, "loss": 1.4452, "step": 4271 }, { "epoch": 0.77, "learning_rate": 1.844924132947977e-05, "loss": 1.4425, "step": 4272 }, { "epoch": 0.77, "learning_rate": 1.8446531791907513e-05, "loss": 0.5367, "step": 4273 }, { "epoch": 0.77, "learning_rate": 1.844382225433526e-05, "loss": 0.5539, "step": 4274 }, { "epoch": 0.77, "learning_rate": 1.844111271676301e-05, "loss": 0.7625, "step": 4275 }, { "epoch": 0.77, "learning_rate": 1.8438403179190753e-05, "loss": 0.7189, "step": 4276 }, { "epoch": 0.77, "learning_rate": 1.8435693641618497e-05, "loss": 0.9858, "step": 4277 }, { "epoch": 0.77, "learning_rate": 1.843298410404624e-05, "loss": 0.9557, "step": 4278 }, { "epoch": 0.77, "learning_rate": 1.843027456647399e-05, "loss": 0.4801, "step": 4279 }, { "epoch": 0.77, "learning_rate": 1.8427565028901737e-05, "loss": 0.5826, "step": 4280 }, { "epoch": 0.77, "learning_rate": 1.842485549132948e-05, "loss": 1.5374, "step": 4281 }, { "epoch": 0.77, "learning_rate": 1.8422145953757226e-05, "loss": 0.6201, "step": 4282 }, { "epoch": 0.77, "learning_rate": 1.841943641618497e-05, "loss": 0.3775, "step": 4283 }, { "epoch": 0.77, "learning_rate": 1.8416726878612718e-05, "loss": 0.9746, "step": 4284 }, { "epoch": 0.77, "learning_rate": 1.8414017341040466e-05, "loss": 0.6783, "step": 4285 }, { "epoch": 0.77, "learning_rate": 1.8411307803468207e-05, "loss": 0.247, "step": 4286 }, { "epoch": 0.77, "learning_rate": 1.8408598265895954e-05, "loss": 0.746, "step": 4287 }, { "epoch": 0.77, "learning_rate": 1.84058887283237e-05, "loss": 0.6799, "step": 4288 }, { "epoch": 0.77, "learning_rate": 1.8403179190751446e-05, "loss": 0.2861, "step": 4289 }, { "epoch": 0.77, "learning_rate": 1.8400469653179194e-05, "loss": 1.2461, "step": 4290 }, { "epoch": 0.78, "learning_rate": 1.8397760115606935e-05, "loss": 0.398, "step": 4291 }, { "epoch": 0.78, "learning_rate": 1.8395050578034683e-05, "loss": 0.6271, "step": 4292 }, { "epoch": 0.78, "learning_rate": 1.8392341040462427e-05, "loss": 1.1628, "step": 4293 }, { "epoch": 0.78, "learning_rate": 1.8389631502890175e-05, "loss": 0.887, "step": 4294 }, { "epoch": 0.78, "learning_rate": 1.838692196531792e-05, "loss": 1.1224, "step": 4295 }, { "epoch": 0.78, "learning_rate": 1.8384212427745664e-05, "loss": 0.502, "step": 4296 }, { "epoch": 0.78, "learning_rate": 1.838150289017341e-05, "loss": 0.5901, "step": 4297 }, { "epoch": 0.78, "learning_rate": 1.8378793352601156e-05, "loss": 0.313, "step": 4298 }, { "epoch": 0.78, "learning_rate": 1.8376083815028904e-05, "loss": 0.2119, "step": 4299 }, { "epoch": 0.78, "learning_rate": 1.8373374277456648e-05, "loss": 0.6606, "step": 4300 }, { "epoch": 0.78, "learning_rate": 1.8370664739884392e-05, "loss": 1.5213, "step": 4301 }, { "epoch": 0.78, "learning_rate": 1.836795520231214e-05, "loss": 1.1044, "step": 4302 }, { "epoch": 0.78, "learning_rate": 1.8365245664739885e-05, "loss": 1.1931, "step": 4303 }, { "epoch": 0.78, "learning_rate": 1.8362536127167632e-05, "loss": 1.0591, "step": 4304 }, { "epoch": 0.78, "learning_rate": 1.8359826589595377e-05, "loss": 0.7345, "step": 4305 }, { "epoch": 0.78, "learning_rate": 1.835711705202312e-05, "loss": 0.7106, "step": 4306 }, { "epoch": 0.78, "learning_rate": 1.835440751445087e-05, "loss": 0.8943, "step": 4307 }, { "epoch": 0.78, "learning_rate": 1.8351697976878613e-05, "loss": 1.0517, "step": 4308 }, { "epoch": 0.78, "learning_rate": 1.8348988439306358e-05, "loss": 0.7805, "step": 4309 }, { "epoch": 0.78, "learning_rate": 1.8346278901734105e-05, "loss": 0.9201, "step": 4310 }, { "epoch": 0.78, "learning_rate": 1.834356936416185e-05, "loss": 1.3938, "step": 4311 }, { "epoch": 0.78, "learning_rate": 1.8340859826589597e-05, "loss": 0.4761, "step": 4312 }, { "epoch": 0.78, "learning_rate": 1.8338150289017342e-05, "loss": 0.7544, "step": 4313 }, { "epoch": 0.78, "learning_rate": 1.8335440751445086e-05, "loss": 1.3795, "step": 4314 }, { "epoch": 0.78, "learning_rate": 1.8332731213872834e-05, "loss": 0.6733, "step": 4315 }, { "epoch": 0.78, "learning_rate": 1.8330021676300578e-05, "loss": 0.637, "step": 4316 }, { "epoch": 0.78, "learning_rate": 1.8327312138728326e-05, "loss": 0.601, "step": 4317 }, { "epoch": 0.78, "learning_rate": 1.8324602601156067e-05, "loss": 0.6588, "step": 4318 }, { "epoch": 0.78, "learning_rate": 1.8321893063583815e-05, "loss": 0.6898, "step": 4319 }, { "epoch": 0.78, "learning_rate": 1.8319183526011562e-05, "loss": 1.0543, "step": 4320 }, { "epoch": 0.78, "learning_rate": 1.8316473988439307e-05, "loss": 0.5374, "step": 4321 }, { "epoch": 0.78, "learning_rate": 1.8313764450867055e-05, "loss": 0.7101, "step": 4322 }, { "epoch": 0.78, "learning_rate": 1.8311054913294796e-05, "loss": 1.0315, "step": 4323 }, { "epoch": 0.78, "learning_rate": 1.8308345375722543e-05, "loss": 0.6069, "step": 4324 }, { "epoch": 0.78, "learning_rate": 1.830563583815029e-05, "loss": 0.9829, "step": 4325 }, { "epoch": 0.78, "learning_rate": 1.8302926300578035e-05, "loss": 0.5711, "step": 4326 }, { "epoch": 0.78, "learning_rate": 1.8300216763005783e-05, "loss": 0.9223, "step": 4327 }, { "epoch": 0.78, "learning_rate": 1.8297507225433524e-05, "loss": 1.1052, "step": 4328 }, { "epoch": 0.78, "learning_rate": 1.8294797687861272e-05, "loss": 1.2209, "step": 4329 }, { "epoch": 0.78, "learning_rate": 1.829208815028902e-05, "loss": 0.6945, "step": 4330 }, { "epoch": 0.78, "learning_rate": 1.8289378612716764e-05, "loss": 0.8549, "step": 4331 }, { "epoch": 0.78, "learning_rate": 1.828666907514451e-05, "loss": 0.8047, "step": 4332 }, { "epoch": 0.78, "learning_rate": 1.8283959537572253e-05, "loss": 1.1845, "step": 4333 }, { "epoch": 0.78, "learning_rate": 1.828125e-05, "loss": 0.8833, "step": 4334 }, { "epoch": 0.78, "learning_rate": 1.8278540462427748e-05, "loss": 0.745, "step": 4335 }, { "epoch": 0.78, "learning_rate": 1.8275830924855493e-05, "loss": 1.1793, "step": 4336 }, { "epoch": 0.78, "learning_rate": 1.8273121387283237e-05, "loss": 1.7003, "step": 4337 }, { "epoch": 0.78, "learning_rate": 1.827041184971098e-05, "loss": 0.5127, "step": 4338 }, { "epoch": 0.78, "learning_rate": 1.826770231213873e-05, "loss": 0.4577, "step": 4339 }, { "epoch": 0.78, "learning_rate": 1.8264992774566477e-05, "loss": 0.6023, "step": 4340 }, { "epoch": 0.78, "learning_rate": 1.8262283236994218e-05, "loss": 0.8508, "step": 4341 }, { "epoch": 0.78, "learning_rate": 1.8259573699421966e-05, "loss": 0.8624, "step": 4342 }, { "epoch": 0.78, "learning_rate": 1.825686416184971e-05, "loss": 0.4923, "step": 4343 }, { "epoch": 0.78, "learning_rate": 1.8254154624277458e-05, "loss": 0.8661, "step": 4344 }, { "epoch": 0.78, "learning_rate": 1.8251445086705205e-05, "loss": 0.4786, "step": 4345 }, { "epoch": 0.79, "learning_rate": 1.8248735549132946e-05, "loss": 0.6409, "step": 4346 }, { "epoch": 0.79, "learning_rate": 1.8246026011560694e-05, "loss": 0.7485, "step": 4347 }, { "epoch": 0.79, "learning_rate": 1.824331647398844e-05, "loss": 0.3229, "step": 4348 }, { "epoch": 0.79, "learning_rate": 1.8240606936416186e-05, "loss": 0.6997, "step": 4349 }, { "epoch": 0.79, "learning_rate": 1.823789739884393e-05, "loss": 0.4862, "step": 4350 }, { "epoch": 0.79, "learning_rate": 1.8235187861271675e-05, "loss": 0.7345, "step": 4351 }, { "epoch": 0.79, "learning_rate": 1.8232478323699423e-05, "loss": 1.0449, "step": 4352 }, { "epoch": 0.79, "learning_rate": 1.8229768786127167e-05, "loss": 0.4953, "step": 4353 }, { "epoch": 0.79, "learning_rate": 1.8227059248554915e-05, "loss": 0.731, "step": 4354 }, { "epoch": 0.79, "learning_rate": 1.822434971098266e-05, "loss": 0.5992, "step": 4355 }, { "epoch": 0.79, "learning_rate": 1.8221640173410404e-05, "loss": 0.4139, "step": 4356 }, { "epoch": 0.79, "learning_rate": 1.821893063583815e-05, "loss": 0.6972, "step": 4357 }, { "epoch": 0.79, "learning_rate": 1.8216221098265896e-05, "loss": 1.5163, "step": 4358 }, { "epoch": 0.79, "learning_rate": 1.8213511560693644e-05, "loss": 0.9031, "step": 4359 }, { "epoch": 0.79, "learning_rate": 1.8210802023121388e-05, "loss": 0.7879, "step": 4360 }, { "epoch": 0.79, "learning_rate": 1.8208092485549132e-05, "loss": 1.1045, "step": 4361 }, { "epoch": 0.79, "learning_rate": 1.820538294797688e-05, "loss": 0.442, "step": 4362 }, { "epoch": 0.79, "learning_rate": 1.8202673410404624e-05, "loss": 0.9027, "step": 4363 }, { "epoch": 0.79, "learning_rate": 1.819996387283237e-05, "loss": 0.9524, "step": 4364 }, { "epoch": 0.79, "learning_rate": 1.8197254335260116e-05, "loss": 1.3987, "step": 4365 }, { "epoch": 0.79, "learning_rate": 1.819454479768786e-05, "loss": 0.5377, "step": 4366 }, { "epoch": 0.79, "learning_rate": 1.819183526011561e-05, "loss": 0.7463, "step": 4367 }, { "epoch": 0.79, "learning_rate": 1.8189125722543353e-05, "loss": 0.5561, "step": 4368 }, { "epoch": 0.79, "learning_rate": 1.8186416184971097e-05, "loss": 1.0127, "step": 4369 }, { "epoch": 0.79, "learning_rate": 1.8183706647398845e-05, "loss": 1.0479, "step": 4370 }, { "epoch": 0.79, "learning_rate": 1.818099710982659e-05, "loss": 0.8333, "step": 4371 }, { "epoch": 0.79, "learning_rate": 1.8178287572254337e-05, "loss": 0.8332, "step": 4372 }, { "epoch": 0.79, "learning_rate": 1.817557803468208e-05, "loss": 0.4766, "step": 4373 }, { "epoch": 0.79, "learning_rate": 1.8172868497109826e-05, "loss": 0.4636, "step": 4374 }, { "epoch": 0.79, "learning_rate": 1.8170158959537574e-05, "loss": 1.0472, "step": 4375 }, { "epoch": 0.79, "learning_rate": 1.8167449421965318e-05, "loss": 1.2347, "step": 4376 }, { "epoch": 0.79, "learning_rate": 1.8164739884393066e-05, "loss": 0.9946, "step": 4377 }, { "epoch": 0.79, "learning_rate": 1.8162030346820807e-05, "loss": 0.9946, "step": 4378 }, { "epoch": 0.79, "learning_rate": 1.8159320809248555e-05, "loss": 0.7481, "step": 4379 }, { "epoch": 0.79, "learning_rate": 1.8156611271676302e-05, "loss": 0.59, "step": 4380 }, { "epoch": 0.79, "learning_rate": 1.8153901734104047e-05, "loss": 0.3197, "step": 4381 }, { "epoch": 0.79, "learning_rate": 1.8151192196531794e-05, "loss": 1.4607, "step": 4382 }, { "epoch": 0.79, "learning_rate": 1.8148482658959535e-05, "loss": 1.7572, "step": 4383 }, { "epoch": 0.79, "learning_rate": 1.8145773121387283e-05, "loss": 0.7548, "step": 4384 }, { "epoch": 0.79, "learning_rate": 1.814306358381503e-05, "loss": 0.6458, "step": 4385 }, { "epoch": 0.79, "learning_rate": 1.8140354046242775e-05, "loss": 0.6948, "step": 4386 }, { "epoch": 0.79, "learning_rate": 1.813764450867052e-05, "loss": 0.5411, "step": 4387 }, { "epoch": 0.79, "learning_rate": 1.8134934971098264e-05, "loss": 0.4968, "step": 4388 }, { "epoch": 0.79, "learning_rate": 1.8132225433526012e-05, "loss": 1.3763, "step": 4389 }, { "epoch": 0.79, "learning_rate": 1.812951589595376e-05, "loss": 1.4576, "step": 4390 }, { "epoch": 0.79, "learning_rate": 1.8126806358381504e-05, "loss": 0.5973, "step": 4391 }, { "epoch": 0.79, "learning_rate": 1.8124096820809248e-05, "loss": 0.9523, "step": 4392 }, { "epoch": 0.79, "learning_rate": 1.8121387283236993e-05, "loss": 0.9559, "step": 4393 }, { "epoch": 0.79, "learning_rate": 1.811867774566474e-05, "loss": 0.64, "step": 4394 }, { "epoch": 0.79, "learning_rate": 1.8115968208092488e-05, "loss": 0.5951, "step": 4395 }, { "epoch": 0.79, "learning_rate": 1.811325867052023e-05, "loss": 0.5708, "step": 4396 }, { "epoch": 0.79, "learning_rate": 1.8110549132947977e-05, "loss": 0.8763, "step": 4397 }, { "epoch": 0.79, "learning_rate": 1.810783959537572e-05, "loss": 0.6476, "step": 4398 }, { "epoch": 0.79, "learning_rate": 1.810513005780347e-05, "loss": 0.5043, "step": 4399 }, { "epoch": 0.79, "learning_rate": 1.8102420520231217e-05, "loss": 0.7556, "step": 4400 }, { "epoch": 0.79, "learning_rate": 1.8099710982658958e-05, "loss": 0.5914, "step": 4401 }, { "epoch": 0.8, "learning_rate": 1.8097001445086705e-05, "loss": 0.6878, "step": 4402 }, { "epoch": 0.8, "learning_rate": 1.809429190751445e-05, "loss": 0.4667, "step": 4403 }, { "epoch": 0.8, "learning_rate": 1.8091582369942198e-05, "loss": 1.1411, "step": 4404 }, { "epoch": 0.8, "learning_rate": 1.8088872832369945e-05, "loss": 0.3145, "step": 4405 }, { "epoch": 0.8, "learning_rate": 1.8086163294797686e-05, "loss": 1.0767, "step": 4406 }, { "epoch": 0.8, "learning_rate": 1.8083453757225434e-05, "loss": 1.1158, "step": 4407 }, { "epoch": 0.8, "learning_rate": 1.808074421965318e-05, "loss": 0.5374, "step": 4408 }, { "epoch": 0.8, "learning_rate": 1.8078034682080926e-05, "loss": 0.9086, "step": 4409 }, { "epoch": 0.8, "learning_rate": 1.807532514450867e-05, "loss": 0.4988, "step": 4410 }, { "epoch": 0.8, "learning_rate": 1.8072615606936415e-05, "loss": 0.8084, "step": 4411 }, { "epoch": 0.8, "learning_rate": 1.8069906069364163e-05, "loss": 0.641, "step": 4412 }, { "epoch": 0.8, "learning_rate": 1.8067196531791907e-05, "loss": 0.4066, "step": 4413 }, { "epoch": 0.8, "learning_rate": 1.8064486994219655e-05, "loss": 1.4156, "step": 4414 }, { "epoch": 0.8, "learning_rate": 1.80617774566474e-05, "loss": 0.9754, "step": 4415 }, { "epoch": 0.8, "learning_rate": 1.8059067919075143e-05, "loss": 0.9237, "step": 4416 }, { "epoch": 0.8, "learning_rate": 1.805635838150289e-05, "loss": 0.5914, "step": 4417 }, { "epoch": 0.8, "learning_rate": 1.8053648843930636e-05, "loss": 0.8096, "step": 4418 }, { "epoch": 0.8, "learning_rate": 1.805093930635838e-05, "loss": 0.626, "step": 4419 }, { "epoch": 0.8, "learning_rate": 1.8048229768786128e-05, "loss": 0.4194, "step": 4420 }, { "epoch": 0.8, "learning_rate": 1.8045520231213872e-05, "loss": 0.4264, "step": 4421 }, { "epoch": 0.8, "learning_rate": 1.804281069364162e-05, "loss": 0.7936, "step": 4422 }, { "epoch": 0.8, "learning_rate": 1.8040101156069368e-05, "loss": 0.9425, "step": 4423 }, { "epoch": 0.8, "learning_rate": 1.803739161849711e-05, "loss": 1.3138, "step": 4424 }, { "epoch": 0.8, "learning_rate": 1.8034682080924856e-05, "loss": 0.5908, "step": 4425 }, { "epoch": 0.8, "learning_rate": 1.80319725433526e-05, "loss": 0.9842, "step": 4426 }, { "epoch": 0.8, "learning_rate": 1.802926300578035e-05, "loss": 0.8235, "step": 4427 }, { "epoch": 0.8, "learning_rate": 1.8026553468208096e-05, "loss": 1.4606, "step": 4428 }, { "epoch": 0.8, "learning_rate": 1.8023843930635837e-05, "loss": 1.115, "step": 4429 }, { "epoch": 0.8, "learning_rate": 1.8021134393063585e-05, "loss": 0.7337, "step": 4430 }, { "epoch": 0.8, "learning_rate": 1.801842485549133e-05, "loss": 0.8586, "step": 4431 }, { "epoch": 0.8, "learning_rate": 1.8015715317919077e-05, "loss": 1.3229, "step": 4432 }, { "epoch": 0.8, "learning_rate": 1.801300578034682e-05, "loss": 0.8298, "step": 4433 }, { "epoch": 0.8, "learning_rate": 1.8010296242774566e-05, "loss": 0.9115, "step": 4434 }, { "epoch": 0.8, "learning_rate": 1.8007586705202314e-05, "loss": 0.6009, "step": 4435 }, { "epoch": 0.8, "learning_rate": 1.8004877167630058e-05, "loss": 0.6002, "step": 4436 }, { "epoch": 0.8, "learning_rate": 1.8002167630057806e-05, "loss": 1.2885, "step": 4437 }, { "epoch": 0.8, "learning_rate": 1.799945809248555e-05, "loss": 0.8457, "step": 4438 }, { "epoch": 0.8, "learning_rate": 1.7996748554913294e-05, "loss": 1.1836, "step": 4439 }, { "epoch": 0.8, "learning_rate": 1.7994039017341042e-05, "loss": 0.8507, "step": 4440 }, { "epoch": 0.8, "learning_rate": 1.7991329479768786e-05, "loss": 1.5461, "step": 4441 }, { "epoch": 0.8, "learning_rate": 1.798861994219653e-05, "loss": 0.7354, "step": 4442 }, { "epoch": 0.8, "learning_rate": 1.798591040462428e-05, "loss": 1.411, "step": 4443 }, { "epoch": 0.8, "learning_rate": 1.7983200867052023e-05, "loss": 0.4017, "step": 4444 }, { "epoch": 0.8, "learning_rate": 1.798049132947977e-05, "loss": 0.7331, "step": 4445 }, { "epoch": 0.8, "learning_rate": 1.7977781791907515e-05, "loss": 1.0882, "step": 4446 }, { "epoch": 0.8, "learning_rate": 1.797507225433526e-05, "loss": 0.5716, "step": 4447 }, { "epoch": 0.8, "learning_rate": 1.7972362716763007e-05, "loss": 0.6617, "step": 4448 }, { "epoch": 0.8, "learning_rate": 1.796965317919075e-05, "loss": 1.0001, "step": 4449 }, { "epoch": 0.8, "learning_rate": 1.79669436416185e-05, "loss": 0.3954, "step": 4450 }, { "epoch": 0.8, "learning_rate": 1.7964234104046244e-05, "loss": 1.0516, "step": 4451 }, { "epoch": 0.8, "learning_rate": 1.7961524566473988e-05, "loss": 0.2379, "step": 4452 }, { "epoch": 0.8, "learning_rate": 1.7958815028901736e-05, "loss": 0.4718, "step": 4453 }, { "epoch": 0.8, "learning_rate": 1.795610549132948e-05, "loss": 0.5643, "step": 4454 }, { "epoch": 0.8, "learning_rate": 1.7953395953757228e-05, "loss": 1.0309, "step": 4455 }, { "epoch": 0.8, "learning_rate": 1.795068641618497e-05, "loss": 0.5854, "step": 4456 }, { "epoch": 0.81, "learning_rate": 1.7947976878612717e-05, "loss": 0.9982, "step": 4457 }, { "epoch": 0.81, "learning_rate": 1.7945267341040464e-05, "loss": 0.8192, "step": 4458 }, { "epoch": 0.81, "learning_rate": 1.794255780346821e-05, "loss": 0.6707, "step": 4459 }, { "epoch": 0.81, "learning_rate": 1.7939848265895957e-05, "loss": 0.7894, "step": 4460 }, { "epoch": 0.81, "learning_rate": 1.7937138728323698e-05, "loss": 0.4234, "step": 4461 }, { "epoch": 0.81, "learning_rate": 1.7934429190751445e-05, "loss": 0.5521, "step": 4462 }, { "epoch": 0.81, "learning_rate": 1.7931719653179193e-05, "loss": 0.644, "step": 4463 }, { "epoch": 0.81, "learning_rate": 1.7929010115606937e-05, "loss": 0.5313, "step": 4464 }, { "epoch": 0.81, "learning_rate": 1.7926300578034682e-05, "loss": 0.3895, "step": 4465 }, { "epoch": 0.81, "learning_rate": 1.7923591040462426e-05, "loss": 0.2171, "step": 4466 }, { "epoch": 0.81, "learning_rate": 1.7920881502890174e-05, "loss": 0.6829, "step": 4467 }, { "epoch": 0.81, "learning_rate": 1.791817196531792e-05, "loss": 0.5248, "step": 4468 }, { "epoch": 0.81, "learning_rate": 1.7915462427745666e-05, "loss": 0.8233, "step": 4469 }, { "epoch": 0.81, "learning_rate": 1.791275289017341e-05, "loss": 0.9321, "step": 4470 }, { "epoch": 0.81, "learning_rate": 1.7910043352601155e-05, "loss": 0.7996, "step": 4471 }, { "epoch": 0.81, "learning_rate": 1.7907333815028902e-05, "loss": 0.5394, "step": 4472 }, { "epoch": 0.81, "learning_rate": 1.790462427745665e-05, "loss": 2.057, "step": 4473 }, { "epoch": 0.81, "learning_rate": 1.7901914739884395e-05, "loss": 0.7619, "step": 4474 }, { "epoch": 0.81, "learning_rate": 1.789920520231214e-05, "loss": 0.9453, "step": 4475 }, { "epoch": 0.81, "learning_rate": 1.7896495664739883e-05, "loss": 1.9062, "step": 4476 }, { "epoch": 0.81, "learning_rate": 1.789378612716763e-05, "loss": 0.2685, "step": 4477 }, { "epoch": 0.81, "learning_rate": 1.789107658959538e-05, "loss": 0.7063, "step": 4478 }, { "epoch": 0.81, "learning_rate": 1.788836705202312e-05, "loss": 0.6901, "step": 4479 }, { "epoch": 0.81, "learning_rate": 1.7885657514450868e-05, "loss": 0.527, "step": 4480 }, { "epoch": 0.81, "learning_rate": 1.7882947976878612e-05, "loss": 0.4839, "step": 4481 }, { "epoch": 0.81, "learning_rate": 1.788023843930636e-05, "loss": 0.5955, "step": 4482 }, { "epoch": 0.81, "learning_rate": 1.7877528901734107e-05, "loss": 0.2451, "step": 4483 }, { "epoch": 0.81, "learning_rate": 1.787481936416185e-05, "loss": 1.2343, "step": 4484 }, { "epoch": 0.81, "learning_rate": 1.7872109826589596e-05, "loss": 1.0451, "step": 4485 }, { "epoch": 0.81, "learning_rate": 1.786940028901734e-05, "loss": 0.3262, "step": 4486 }, { "epoch": 0.81, "learning_rate": 1.7866690751445088e-05, "loss": 0.9156, "step": 4487 }, { "epoch": 0.81, "learning_rate": 1.7863981213872833e-05, "loss": 1.0332, "step": 4488 }, { "epoch": 0.81, "learning_rate": 1.7861271676300577e-05, "loss": 0.8431, "step": 4489 }, { "epoch": 0.81, "learning_rate": 1.7858562138728325e-05, "loss": 0.4277, "step": 4490 }, { "epoch": 0.81, "learning_rate": 1.785585260115607e-05, "loss": 0.6324, "step": 4491 }, { "epoch": 0.81, "learning_rate": 1.7853143063583817e-05, "loss": 0.806, "step": 4492 }, { "epoch": 0.81, "learning_rate": 1.785043352601156e-05, "loss": 0.6786, "step": 4493 }, { "epoch": 0.81, "learning_rate": 1.7847723988439306e-05, "loss": 0.5671, "step": 4494 }, { "epoch": 0.81, "learning_rate": 1.7845014450867053e-05, "loss": 0.6508, "step": 4495 }, { "epoch": 0.81, "learning_rate": 1.7842304913294798e-05, "loss": 0.3507, "step": 4496 }, { "epoch": 0.81, "learning_rate": 1.7839595375722545e-05, "loss": 0.8147, "step": 4497 }, { "epoch": 0.81, "learning_rate": 1.783688583815029e-05, "loss": 1.1842, "step": 4498 }, { "epoch": 0.81, "learning_rate": 1.7834176300578034e-05, "loss": 0.4531, "step": 4499 }, { "epoch": 0.81, "learning_rate": 1.7831466763005782e-05, "loss": 0.1697, "step": 4500 }, { "epoch": 0.81, "eval_exact_match": 86.69820245979186, "eval_f1": 93.01674312497939, "step": 4500 }, { "epoch": 0.81, "learning_rate": 1.7828757225433526e-05, "loss": 1.2585, "step": 4501 }, { "epoch": 0.81, "learning_rate": 1.782604768786127e-05, "loss": 0.973, "step": 4502 }, { "epoch": 0.81, "learning_rate": 1.782333815028902e-05, "loss": 0.8502, "step": 4503 }, { "epoch": 0.81, "learning_rate": 1.7820628612716763e-05, "loss": 0.5802, "step": 4504 }, { "epoch": 0.81, "learning_rate": 1.781791907514451e-05, "loss": 1.4606, "step": 4505 }, { "epoch": 0.81, "learning_rate": 1.7815209537572255e-05, "loss": 0.3368, "step": 4506 }, { "epoch": 0.81, "learning_rate": 1.78125e-05, "loss": 1.111, "step": 4507 }, { "epoch": 0.81, "learning_rate": 1.7809790462427747e-05, "loss": 0.4652, "step": 4508 }, { "epoch": 0.81, "learning_rate": 1.780708092485549e-05, "loss": 0.4981, "step": 4509 }, { "epoch": 0.81, "learning_rate": 1.780437138728324e-05, "loss": 0.7832, "step": 4510 }, { "epoch": 0.81, "learning_rate": 1.780166184971098e-05, "loss": 0.4695, "step": 4511 }, { "epoch": 0.82, "learning_rate": 1.7798952312138728e-05, "loss": 0.6403, "step": 4512 }, { "epoch": 0.82, "learning_rate": 1.7796242774566476e-05, "loss": 0.6963, "step": 4513 }, { "epoch": 0.82, "learning_rate": 1.779353323699422e-05, "loss": 0.5346, "step": 4514 }, { "epoch": 0.82, "learning_rate": 1.7790823699421968e-05, "loss": 0.5645, "step": 4515 }, { "epoch": 0.82, "learning_rate": 1.778811416184971e-05, "loss": 0.4495, "step": 4516 }, { "epoch": 0.82, "learning_rate": 1.7785404624277456e-05, "loss": 0.9234, "step": 4517 }, { "epoch": 0.82, "learning_rate": 1.7782695086705204e-05, "loss": 0.897, "step": 4518 }, { "epoch": 0.82, "learning_rate": 1.777998554913295e-05, "loss": 0.6404, "step": 4519 }, { "epoch": 0.82, "learning_rate": 1.7777276011560696e-05, "loss": 1.2184, "step": 4520 }, { "epoch": 0.82, "learning_rate": 1.7774566473988437e-05, "loss": 1.0413, "step": 4521 }, { "epoch": 0.82, "learning_rate": 1.7771856936416185e-05, "loss": 1.1247, "step": 4522 }, { "epoch": 0.82, "learning_rate": 1.7769147398843933e-05, "loss": 0.6093, "step": 4523 }, { "epoch": 0.82, "learning_rate": 1.7766437861271677e-05, "loss": 0.635, "step": 4524 }, { "epoch": 0.82, "learning_rate": 1.776372832369942e-05, "loss": 0.9616, "step": 4525 }, { "epoch": 0.82, "learning_rate": 1.7761018786127166e-05, "loss": 0.9356, "step": 4526 }, { "epoch": 0.82, "learning_rate": 1.7758309248554914e-05, "loss": 0.6625, "step": 4527 }, { "epoch": 0.82, "learning_rate": 1.775559971098266e-05, "loss": 0.8675, "step": 4528 }, { "epoch": 0.82, "learning_rate": 1.7752890173410406e-05, "loss": 0.4186, "step": 4529 }, { "epoch": 0.82, "learning_rate": 1.775018063583815e-05, "loss": 0.8466, "step": 4530 }, { "epoch": 0.82, "learning_rate": 1.7747471098265895e-05, "loss": 0.7728, "step": 4531 }, { "epoch": 0.82, "learning_rate": 1.7744761560693642e-05, "loss": 1.4498, "step": 4532 }, { "epoch": 0.82, "learning_rate": 1.774205202312139e-05, "loss": 0.6604, "step": 4533 }, { "epoch": 0.82, "learning_rate": 1.773934248554913e-05, "loss": 0.4824, "step": 4534 }, { "epoch": 0.82, "learning_rate": 1.773663294797688e-05, "loss": 0.4857, "step": 4535 }, { "epoch": 0.82, "learning_rate": 1.7733923410404623e-05, "loss": 0.4219, "step": 4536 }, { "epoch": 0.82, "learning_rate": 1.773121387283237e-05, "loss": 0.7591, "step": 4537 }, { "epoch": 0.82, "learning_rate": 1.772850433526012e-05, "loss": 1.0806, "step": 4538 }, { "epoch": 0.82, "learning_rate": 1.772579479768786e-05, "loss": 1.3334, "step": 4539 }, { "epoch": 0.82, "learning_rate": 1.7723085260115607e-05, "loss": 1.1724, "step": 4540 }, { "epoch": 0.82, "learning_rate": 1.7720375722543352e-05, "loss": 0.5124, "step": 4541 }, { "epoch": 0.82, "learning_rate": 1.77176661849711e-05, "loss": 0.6288, "step": 4542 }, { "epoch": 0.82, "learning_rate": 1.7714956647398847e-05, "loss": 0.6035, "step": 4543 }, { "epoch": 0.82, "learning_rate": 1.7712247109826588e-05, "loss": 1.4805, "step": 4544 }, { "epoch": 0.82, "learning_rate": 1.7709537572254336e-05, "loss": 0.3133, "step": 4545 }, { "epoch": 0.82, "learning_rate": 1.770682803468208e-05, "loss": 0.6287, "step": 4546 }, { "epoch": 0.82, "learning_rate": 1.7704118497109828e-05, "loss": 1.3269, "step": 4547 }, { "epoch": 0.82, "learning_rate": 1.7701408959537572e-05, "loss": 1.1856, "step": 4548 }, { "epoch": 0.82, "learning_rate": 1.7698699421965317e-05, "loss": 0.7849, "step": 4549 }, { "epoch": 0.82, "learning_rate": 1.7695989884393065e-05, "loss": 0.8585, "step": 4550 }, { "epoch": 0.82, "learning_rate": 1.769328034682081e-05, "loss": 0.4672, "step": 4551 }, { "epoch": 0.82, "learning_rate": 1.7690570809248557e-05, "loss": 0.9688, "step": 4552 }, { "epoch": 0.82, "learning_rate": 1.76878612716763e-05, "loss": 1.1212, "step": 4553 }, { "epoch": 0.82, "learning_rate": 1.7685151734104045e-05, "loss": 0.5614, "step": 4554 }, { "epoch": 0.82, "learning_rate": 1.7682442196531793e-05, "loss": 0.6474, "step": 4555 }, { "epoch": 0.82, "learning_rate": 1.7679732658959538e-05, "loss": 0.8085, "step": 4556 }, { "epoch": 0.82, "learning_rate": 1.7677023121387282e-05, "loss": 0.5656, "step": 4557 }, { "epoch": 0.82, "learning_rate": 1.767431358381503e-05, "loss": 0.7166, "step": 4558 }, { "epoch": 0.82, "learning_rate": 1.7671604046242774e-05, "loss": 1.2653, "step": 4559 }, { "epoch": 0.82, "learning_rate": 1.7668894508670522e-05, "loss": 0.413, "step": 4560 }, { "epoch": 0.82, "learning_rate": 1.7666184971098266e-05, "loss": 0.2181, "step": 4561 }, { "epoch": 0.82, "learning_rate": 1.766347543352601e-05, "loss": 0.5837, "step": 4562 }, { "epoch": 0.82, "learning_rate": 1.7660765895953758e-05, "loss": 0.8686, "step": 4563 }, { "epoch": 0.82, "learning_rate": 1.7658056358381503e-05, "loss": 0.8113, "step": 4564 }, { "epoch": 0.82, "learning_rate": 1.765534682080925e-05, "loss": 0.6985, "step": 4565 }, { "epoch": 0.82, "learning_rate": 1.7652637283236995e-05, "loss": 0.474, "step": 4566 }, { "epoch": 0.82, "learning_rate": 1.764992774566474e-05, "loss": 0.672, "step": 4567 }, { "epoch": 0.83, "learning_rate": 1.7647218208092487e-05, "loss": 0.895, "step": 4568 }, { "epoch": 0.83, "learning_rate": 1.764450867052023e-05, "loss": 0.6085, "step": 4569 }, { "epoch": 0.83, "learning_rate": 1.764179913294798e-05, "loss": 0.708, "step": 4570 }, { "epoch": 0.83, "learning_rate": 1.763908959537572e-05, "loss": 1.0054, "step": 4571 }, { "epoch": 0.83, "learning_rate": 1.7636380057803468e-05, "loss": 1.2151, "step": 4572 }, { "epoch": 0.83, "learning_rate": 1.7633670520231215e-05, "loss": 0.7828, "step": 4573 }, { "epoch": 0.83, "learning_rate": 1.763096098265896e-05, "loss": 0.7427, "step": 4574 }, { "epoch": 0.83, "learning_rate": 1.7628251445086708e-05, "loss": 0.847, "step": 4575 }, { "epoch": 0.83, "learning_rate": 1.762554190751445e-05, "loss": 1.1645, "step": 4576 }, { "epoch": 0.83, "learning_rate": 1.7622832369942196e-05, "loss": 0.5367, "step": 4577 }, { "epoch": 0.83, "learning_rate": 1.7620122832369944e-05, "loss": 0.5054, "step": 4578 }, { "epoch": 0.83, "learning_rate": 1.761741329479769e-05, "loss": 1.4298, "step": 4579 }, { "epoch": 0.83, "learning_rate": 1.7614703757225433e-05, "loss": 0.4459, "step": 4580 }, { "epoch": 0.83, "learning_rate": 1.7611994219653177e-05, "loss": 1.1412, "step": 4581 }, { "epoch": 0.83, "learning_rate": 1.7609284682080925e-05, "loss": 0.6028, "step": 4582 }, { "epoch": 0.83, "learning_rate": 1.7606575144508673e-05, "loss": 0.7324, "step": 4583 }, { "epoch": 0.83, "learning_rate": 1.7603865606936417e-05, "loss": 0.6763, "step": 4584 }, { "epoch": 0.83, "learning_rate": 1.760115606936416e-05, "loss": 0.7184, "step": 4585 }, { "epoch": 0.83, "learning_rate": 1.7598446531791906e-05, "loss": 0.6095, "step": 4586 }, { "epoch": 0.83, "learning_rate": 1.7595736994219654e-05, "loss": 0.6144, "step": 4587 }, { "epoch": 0.83, "learning_rate": 1.75930274566474e-05, "loss": 0.4601, "step": 4588 }, { "epoch": 0.83, "learning_rate": 1.7590317919075146e-05, "loss": 0.6137, "step": 4589 }, { "epoch": 0.83, "learning_rate": 1.758760838150289e-05, "loss": 1.8932, "step": 4590 }, { "epoch": 0.83, "learning_rate": 1.7584898843930634e-05, "loss": 0.9116, "step": 4591 }, { "epoch": 0.83, "learning_rate": 1.7582189306358382e-05, "loss": 1.3924, "step": 4592 }, { "epoch": 0.83, "learning_rate": 1.757947976878613e-05, "loss": 0.6815, "step": 4593 }, { "epoch": 0.83, "learning_rate": 1.757677023121387e-05, "loss": 0.6207, "step": 4594 }, { "epoch": 0.83, "learning_rate": 1.757406069364162e-05, "loss": 0.3504, "step": 4595 }, { "epoch": 0.83, "learning_rate": 1.7571351156069366e-05, "loss": 1.5838, "step": 4596 }, { "epoch": 0.83, "learning_rate": 1.756864161849711e-05, "loss": 0.7493, "step": 4597 }, { "epoch": 0.83, "learning_rate": 1.756593208092486e-05, "loss": 1.3433, "step": 4598 }, { "epoch": 0.83, "learning_rate": 1.75632225433526e-05, "loss": 0.9672, "step": 4599 }, { "epoch": 0.83, "learning_rate": 1.7560513005780347e-05, "loss": 0.5263, "step": 4600 }, { "epoch": 0.83, "learning_rate": 1.7557803468208095e-05, "loss": 0.7474, "step": 4601 }, { "epoch": 0.83, "learning_rate": 1.755509393063584e-05, "loss": 0.539, "step": 4602 }, { "epoch": 0.83, "learning_rate": 1.7552384393063584e-05, "loss": 0.3779, "step": 4603 }, { "epoch": 0.83, "learning_rate": 1.7549674855491328e-05, "loss": 1.0975, "step": 4604 }, { "epoch": 0.83, "learning_rate": 1.7546965317919076e-05, "loss": 0.28, "step": 4605 }, { "epoch": 0.83, "learning_rate": 1.7544255780346824e-05, "loss": 0.8168, "step": 4606 }, { "epoch": 0.83, "learning_rate": 1.7541546242774568e-05, "loss": 1.157, "step": 4607 }, { "epoch": 0.83, "learning_rate": 1.7538836705202312e-05, "loss": 0.743, "step": 4608 }, { "epoch": 0.83, "learning_rate": 1.7536127167630057e-05, "loss": 1.0161, "step": 4609 }, { "epoch": 0.83, "learning_rate": 1.7533417630057804e-05, "loss": 0.9703, "step": 4610 }, { "epoch": 0.83, "learning_rate": 1.7530708092485552e-05, "loss": 0.6348, "step": 4611 }, { "epoch": 0.83, "learning_rate": 1.7527998554913297e-05, "loss": 0.7205, "step": 4612 }, { "epoch": 0.83, "learning_rate": 1.752528901734104e-05, "loss": 1.1955, "step": 4613 }, { "epoch": 0.83, "learning_rate": 1.7522579479768785e-05, "loss": 0.415, "step": 4614 }, { "epoch": 0.83, "learning_rate": 1.7519869942196533e-05, "loss": 0.2589, "step": 4615 }, { "epoch": 0.83, "learning_rate": 1.751716040462428e-05, "loss": 1.3197, "step": 4616 }, { "epoch": 0.83, "learning_rate": 1.7514450867052022e-05, "loss": 1.0035, "step": 4617 }, { "epoch": 0.83, "learning_rate": 1.751174132947977e-05, "loss": 0.6823, "step": 4618 }, { "epoch": 0.83, "learning_rate": 1.7509031791907514e-05, "loss": 0.7779, "step": 4619 }, { "epoch": 0.83, "learning_rate": 1.750632225433526e-05, "loss": 0.4407, "step": 4620 }, { "epoch": 0.83, "learning_rate": 1.750361271676301e-05, "loss": 0.5925, "step": 4621 }, { "epoch": 0.83, "learning_rate": 1.750090317919075e-05, "loss": 1.1859, "step": 4622 }, { "epoch": 0.84, "learning_rate": 1.7498193641618498e-05, "loss": 0.3609, "step": 4623 }, { "epoch": 0.84, "learning_rate": 1.7495484104046242e-05, "loss": 0.344, "step": 4624 }, { "epoch": 0.84, "learning_rate": 1.749277456647399e-05, "loss": 0.3786, "step": 4625 }, { "epoch": 0.84, "learning_rate": 1.7490065028901735e-05, "loss": 0.6748, "step": 4626 }, { "epoch": 0.84, "learning_rate": 1.748735549132948e-05, "loss": 0.8988, "step": 4627 }, { "epoch": 0.84, "learning_rate": 1.7484645953757227e-05, "loss": 0.6844, "step": 4628 }, { "epoch": 0.84, "learning_rate": 1.748193641618497e-05, "loss": 0.8706, "step": 4629 }, { "epoch": 0.84, "learning_rate": 1.747922687861272e-05, "loss": 0.8165, "step": 4630 }, { "epoch": 0.84, "learning_rate": 1.7476517341040463e-05, "loss": 0.4651, "step": 4631 }, { "epoch": 0.84, "learning_rate": 1.7473807803468208e-05, "loss": 0.5944, "step": 4632 }, { "epoch": 0.84, "learning_rate": 1.7471098265895955e-05, "loss": 1.1339, "step": 4633 }, { "epoch": 0.84, "learning_rate": 1.74683887283237e-05, "loss": 0.9888, "step": 4634 }, { "epoch": 0.84, "learning_rate": 1.7465679190751444e-05, "loss": 1.1444, "step": 4635 }, { "epoch": 0.84, "learning_rate": 1.7462969653179192e-05, "loss": 1.3934, "step": 4636 }, { "epoch": 0.84, "learning_rate": 1.7460260115606936e-05, "loss": 0.535, "step": 4637 }, { "epoch": 0.84, "learning_rate": 1.7457550578034684e-05, "loss": 0.3039, "step": 4638 }, { "epoch": 0.84, "learning_rate": 1.7454841040462428e-05, "loss": 0.7731, "step": 4639 }, { "epoch": 0.84, "learning_rate": 1.7452131502890173e-05, "loss": 0.8195, "step": 4640 }, { "epoch": 0.84, "learning_rate": 1.744942196531792e-05, "loss": 1.0315, "step": 4641 }, { "epoch": 0.84, "learning_rate": 1.7446712427745665e-05, "loss": 0.8353, "step": 4642 }, { "epoch": 0.84, "learning_rate": 1.7444002890173413e-05, "loss": 1.0599, "step": 4643 }, { "epoch": 0.84, "learning_rate": 1.7441293352601157e-05, "loss": 0.5302, "step": 4644 }, { "epoch": 0.84, "learning_rate": 1.74385838150289e-05, "loss": 1.2301, "step": 4645 }, { "epoch": 0.84, "learning_rate": 1.743587427745665e-05, "loss": 0.4413, "step": 4646 }, { "epoch": 0.84, "learning_rate": 1.7433164739884393e-05, "loss": 0.7897, "step": 4647 }, { "epoch": 0.84, "learning_rate": 1.743045520231214e-05, "loss": 0.8767, "step": 4648 }, { "epoch": 0.84, "learning_rate": 1.7427745664739882e-05, "loss": 0.8713, "step": 4649 }, { "epoch": 0.84, "learning_rate": 1.742503612716763e-05, "loss": 0.5191, "step": 4650 }, { "epoch": 0.84, "learning_rate": 1.7422326589595378e-05, "loss": 0.9174, "step": 4651 }, { "epoch": 0.84, "learning_rate": 1.7419617052023122e-05, "loss": 0.9296, "step": 4652 }, { "epoch": 0.84, "learning_rate": 1.741690751445087e-05, "loss": 0.9812, "step": 4653 }, { "epoch": 0.84, "learning_rate": 1.741419797687861e-05, "loss": 1.2013, "step": 4654 }, { "epoch": 0.84, "learning_rate": 1.741148843930636e-05, "loss": 0.7193, "step": 4655 }, { "epoch": 0.84, "learning_rate": 1.7408778901734106e-05, "loss": 0.9163, "step": 4656 }, { "epoch": 0.84, "learning_rate": 1.740606936416185e-05, "loss": 0.3785, "step": 4657 }, { "epoch": 0.84, "learning_rate": 1.7403359826589595e-05, "loss": 0.8401, "step": 4658 }, { "epoch": 0.84, "learning_rate": 1.740065028901734e-05, "loss": 0.3112, "step": 4659 }, { "epoch": 0.84, "learning_rate": 1.7397940751445087e-05, "loss": 0.9251, "step": 4660 }, { "epoch": 0.84, "learning_rate": 1.7395231213872835e-05, "loss": 0.8279, "step": 4661 }, { "epoch": 0.84, "learning_rate": 1.739252167630058e-05, "loss": 1.1512, "step": 4662 }, { "epoch": 0.84, "learning_rate": 1.7389812138728324e-05, "loss": 0.495, "step": 4663 }, { "epoch": 0.84, "learning_rate": 1.7387102601156068e-05, "loss": 1.2501, "step": 4664 }, { "epoch": 0.84, "learning_rate": 1.7384393063583816e-05, "loss": 1.421, "step": 4665 }, { "epoch": 0.84, "learning_rate": 1.7381683526011563e-05, "loss": 1.6077, "step": 4666 }, { "epoch": 0.84, "learning_rate": 1.7378973988439308e-05, "loss": 0.4142, "step": 4667 }, { "epoch": 0.84, "learning_rate": 1.7376264450867052e-05, "loss": 0.8238, "step": 4668 }, { "epoch": 0.84, "learning_rate": 1.7373554913294796e-05, "loss": 0.8528, "step": 4669 }, { "epoch": 0.84, "learning_rate": 1.7370845375722544e-05, "loss": 0.445, "step": 4670 }, { "epoch": 0.84, "learning_rate": 1.7368135838150292e-05, "loss": 0.9976, "step": 4671 }, { "epoch": 0.84, "learning_rate": 1.7365426300578033e-05, "loss": 0.6176, "step": 4672 }, { "epoch": 0.84, "learning_rate": 1.736271676300578e-05, "loss": 1.3335, "step": 4673 }, { "epoch": 0.84, "learning_rate": 1.7360007225433525e-05, "loss": 1.094, "step": 4674 }, { "epoch": 0.84, "learning_rate": 1.7357297687861273e-05, "loss": 0.7722, "step": 4675 }, { "epoch": 0.84, "learning_rate": 1.735458815028902e-05, "loss": 0.7606, "step": 4676 }, { "epoch": 0.84, "learning_rate": 1.735187861271676e-05, "loss": 0.664, "step": 4677 }, { "epoch": 0.85, "learning_rate": 1.734916907514451e-05, "loss": 0.7536, "step": 4678 }, { "epoch": 0.85, "learning_rate": 1.7346459537572254e-05, "loss": 0.6728, "step": 4679 }, { "epoch": 0.85, "learning_rate": 1.734375e-05, "loss": 1.5236, "step": 4680 }, { "epoch": 0.85, "learning_rate": 1.7341040462427746e-05, "loss": 0.9121, "step": 4681 }, { "epoch": 0.85, "learning_rate": 1.733833092485549e-05, "loss": 0.5702, "step": 4682 }, { "epoch": 0.85, "learning_rate": 1.7335621387283238e-05, "loss": 0.449, "step": 4683 }, { "epoch": 0.85, "learning_rate": 1.7332911849710982e-05, "loss": 1.365, "step": 4684 }, { "epoch": 0.85, "learning_rate": 1.733020231213873e-05, "loss": 0.4211, "step": 4685 }, { "epoch": 0.85, "learning_rate": 1.7327492774566474e-05, "loss": 0.6721, "step": 4686 }, { "epoch": 0.85, "learning_rate": 1.732478323699422e-05, "loss": 1.0865, "step": 4687 }, { "epoch": 0.85, "learning_rate": 1.7322073699421967e-05, "loss": 0.944, "step": 4688 }, { "epoch": 0.85, "learning_rate": 1.731936416184971e-05, "loss": 0.8278, "step": 4689 }, { "epoch": 0.85, "learning_rate": 1.731665462427746e-05, "loss": 0.525, "step": 4690 }, { "epoch": 0.85, "learning_rate": 1.7313945086705203e-05, "loss": 1.0584, "step": 4691 }, { "epoch": 0.85, "learning_rate": 1.7311235549132947e-05, "loss": 0.6631, "step": 4692 }, { "epoch": 0.85, "learning_rate": 1.7308526011560695e-05, "loss": 0.6318, "step": 4693 }, { "epoch": 0.85, "learning_rate": 1.730581647398844e-05, "loss": 1.2206, "step": 4694 }, { "epoch": 0.85, "learning_rate": 1.7303106936416184e-05, "loss": 1.0031, "step": 4695 }, { "epoch": 0.85, "learning_rate": 1.730039739884393e-05, "loss": 0.5387, "step": 4696 }, { "epoch": 0.85, "learning_rate": 1.7297687861271676e-05, "loss": 1.0147, "step": 4697 }, { "epoch": 0.85, "learning_rate": 1.7294978323699424e-05, "loss": 0.5967, "step": 4698 }, { "epoch": 0.85, "learning_rate": 1.7292268786127168e-05, "loss": 0.342, "step": 4699 }, { "epoch": 0.85, "learning_rate": 1.7289559248554912e-05, "loss": 0.6836, "step": 4700 }, { "epoch": 0.85, "learning_rate": 1.728684971098266e-05, "loss": 0.6628, "step": 4701 }, { "epoch": 0.85, "learning_rate": 1.7284140173410405e-05, "loss": 0.7664, "step": 4702 }, { "epoch": 0.85, "learning_rate": 1.7281430635838152e-05, "loss": 0.8453, "step": 4703 }, { "epoch": 0.85, "learning_rate": 1.7278721098265893e-05, "loss": 0.4003, "step": 4704 }, { "epoch": 0.85, "learning_rate": 1.727601156069364e-05, "loss": 1.0653, "step": 4705 }, { "epoch": 0.85, "learning_rate": 1.727330202312139e-05, "loss": 0.4522, "step": 4706 }, { "epoch": 0.85, "learning_rate": 1.7270592485549133e-05, "loss": 0.5495, "step": 4707 }, { "epoch": 0.85, "learning_rate": 1.726788294797688e-05, "loss": 0.5471, "step": 4708 }, { "epoch": 0.85, "learning_rate": 1.7265173410404622e-05, "loss": 0.8642, "step": 4709 }, { "epoch": 0.85, "learning_rate": 1.726246387283237e-05, "loss": 0.5345, "step": 4710 }, { "epoch": 0.85, "learning_rate": 1.7259754335260117e-05, "loss": 1.2707, "step": 4711 }, { "epoch": 0.85, "learning_rate": 1.7257044797687862e-05, "loss": 0.948, "step": 4712 }, { "epoch": 0.85, "learning_rate": 1.725433526011561e-05, "loss": 1.3058, "step": 4713 }, { "epoch": 0.85, "learning_rate": 1.725162572254335e-05, "loss": 0.5288, "step": 4714 }, { "epoch": 0.85, "learning_rate": 1.7248916184971098e-05, "loss": 0.7976, "step": 4715 }, { "epoch": 0.85, "learning_rate": 1.7246206647398846e-05, "loss": 0.8256, "step": 4716 }, { "epoch": 0.85, "learning_rate": 1.724349710982659e-05, "loss": 0.6315, "step": 4717 }, { "epoch": 0.85, "learning_rate": 1.7240787572254335e-05, "loss": 1.0277, "step": 4718 }, { "epoch": 0.85, "learning_rate": 1.723807803468208e-05, "loss": 0.5314, "step": 4719 }, { "epoch": 0.85, "learning_rate": 1.7235368497109827e-05, "loss": 0.2669, "step": 4720 }, { "epoch": 0.85, "learning_rate": 1.7232658959537575e-05, "loss": 1.1023, "step": 4721 }, { "epoch": 0.85, "learning_rate": 1.722994942196532e-05, "loss": 1.4492, "step": 4722 }, { "epoch": 0.85, "learning_rate": 1.7227239884393063e-05, "loss": 1.3171, "step": 4723 }, { "epoch": 0.85, "learning_rate": 1.7224530346820808e-05, "loss": 0.4885, "step": 4724 }, { "epoch": 0.85, "learning_rate": 1.7221820809248555e-05, "loss": 0.8595, "step": 4725 }, { "epoch": 0.85, "learning_rate": 1.7219111271676303e-05, "loss": 1.3405, "step": 4726 }, { "epoch": 0.85, "learning_rate": 1.7216401734104044e-05, "loss": 0.5291, "step": 4727 }, { "epoch": 0.85, "learning_rate": 1.7213692196531792e-05, "loss": 0.8371, "step": 4728 }, { "epoch": 0.85, "learning_rate": 1.7210982658959536e-05, "loss": 0.9676, "step": 4729 }, { "epoch": 0.85, "learning_rate": 1.7208273121387284e-05, "loss": 0.4569, "step": 4730 }, { "epoch": 0.85, "learning_rate": 1.7205563583815032e-05, "loss": 1.1254, "step": 4731 }, { "epoch": 0.85, "learning_rate": 1.7202854046242773e-05, "loss": 1.0226, "step": 4732 }, { "epoch": 0.85, "learning_rate": 1.720014450867052e-05, "loss": 1.8575, "step": 4733 }, { "epoch": 0.86, "learning_rate": 1.7197434971098265e-05, "loss": 0.8742, "step": 4734 }, { "epoch": 0.86, "learning_rate": 1.7194725433526013e-05, "loss": 0.7392, "step": 4735 }, { "epoch": 0.86, "learning_rate": 1.719201589595376e-05, "loss": 0.9165, "step": 4736 }, { "epoch": 0.86, "learning_rate": 1.71893063583815e-05, "loss": 1.5393, "step": 4737 }, { "epoch": 0.86, "learning_rate": 1.718659682080925e-05, "loss": 0.8094, "step": 4738 }, { "epoch": 0.86, "learning_rate": 1.7183887283236994e-05, "loss": 0.5481, "step": 4739 }, { "epoch": 0.86, "learning_rate": 1.718117774566474e-05, "loss": 0.7796, "step": 4740 }, { "epoch": 0.86, "learning_rate": 1.7178468208092486e-05, "loss": 1.1707, "step": 4741 }, { "epoch": 0.86, "learning_rate": 1.717575867052023e-05, "loss": 0.3679, "step": 4742 }, { "epoch": 0.86, "learning_rate": 1.7173049132947978e-05, "loss": 0.6562, "step": 4743 }, { "epoch": 0.86, "learning_rate": 1.7170339595375722e-05, "loss": 0.9127, "step": 4744 }, { "epoch": 0.86, "learning_rate": 1.716763005780347e-05, "loss": 0.6197, "step": 4745 }, { "epoch": 0.86, "learning_rate": 1.7164920520231214e-05, "loss": 0.8302, "step": 4746 }, { "epoch": 0.86, "learning_rate": 1.716221098265896e-05, "loss": 0.9893, "step": 4747 }, { "epoch": 0.86, "learning_rate": 1.7159501445086706e-05, "loss": 0.3018, "step": 4748 }, { "epoch": 0.86, "learning_rate": 1.715679190751445e-05, "loss": 0.5357, "step": 4749 }, { "epoch": 0.86, "learning_rate": 1.7154082369942195e-05, "loss": 0.459, "step": 4750 }, { "epoch": 0.86, "learning_rate": 1.7151372832369943e-05, "loss": 1.3427, "step": 4751 }, { "epoch": 0.86, "learning_rate": 1.7148663294797687e-05, "loss": 0.976, "step": 4752 }, { "epoch": 0.86, "learning_rate": 1.7145953757225435e-05, "loss": 0.3464, "step": 4753 }, { "epoch": 0.86, "learning_rate": 1.714324421965318e-05, "loss": 0.7634, "step": 4754 }, { "epoch": 0.86, "learning_rate": 1.7140534682080924e-05, "loss": 0.8691, "step": 4755 }, { "epoch": 0.86, "learning_rate": 1.713782514450867e-05, "loss": 0.474, "step": 4756 }, { "epoch": 0.86, "learning_rate": 1.7135115606936416e-05, "loss": 0.9162, "step": 4757 }, { "epoch": 0.86, "learning_rate": 1.7132406069364164e-05, "loss": 0.409, "step": 4758 }, { "epoch": 0.86, "learning_rate": 1.7129696531791908e-05, "loss": 0.2569, "step": 4759 }, { "epoch": 0.86, "learning_rate": 1.7126986994219652e-05, "loss": 0.5108, "step": 4760 }, { "epoch": 0.86, "learning_rate": 1.71242774566474e-05, "loss": 0.8323, "step": 4761 }, { "epoch": 0.86, "learning_rate": 1.7121567919075144e-05, "loss": 0.8656, "step": 4762 }, { "epoch": 0.86, "learning_rate": 1.7118858381502892e-05, "loss": 1.0056, "step": 4763 }, { "epoch": 0.86, "learning_rate": 1.7116148843930633e-05, "loss": 0.6189, "step": 4764 }, { "epoch": 0.86, "learning_rate": 1.711343930635838e-05, "loss": 0.9814, "step": 4765 }, { "epoch": 0.86, "learning_rate": 1.711072976878613e-05, "loss": 0.8707, "step": 4766 }, { "epoch": 0.86, "learning_rate": 1.7108020231213873e-05, "loss": 1.0672, "step": 4767 }, { "epoch": 0.86, "learning_rate": 1.710531069364162e-05, "loss": 0.5294, "step": 4768 }, { "epoch": 0.86, "learning_rate": 1.7102601156069365e-05, "loss": 0.4374, "step": 4769 }, { "epoch": 0.86, "learning_rate": 1.709989161849711e-05, "loss": 1.4089, "step": 4770 }, { "epoch": 0.86, "learning_rate": 1.7097182080924857e-05, "loss": 1.1964, "step": 4771 }, { "epoch": 0.86, "learning_rate": 1.70944725433526e-05, "loss": 1.1379, "step": 4772 }, { "epoch": 0.86, "learning_rate": 1.7091763005780346e-05, "loss": 0.7123, "step": 4773 }, { "epoch": 0.86, "learning_rate": 1.7089053468208094e-05, "loss": 1.19, "step": 4774 }, { "epoch": 0.86, "learning_rate": 1.7086343930635838e-05, "loss": 1.0764, "step": 4775 }, { "epoch": 0.86, "learning_rate": 1.7083634393063586e-05, "loss": 0.776, "step": 4776 }, { "epoch": 0.86, "learning_rate": 1.708092485549133e-05, "loss": 1.0725, "step": 4777 }, { "epoch": 0.86, "learning_rate": 1.7078215317919075e-05, "loss": 1.015, "step": 4778 }, { "epoch": 0.86, "learning_rate": 1.7075505780346822e-05, "loss": 0.8714, "step": 4779 }, { "epoch": 0.86, "learning_rate": 1.7072796242774567e-05, "loss": 0.4361, "step": 4780 }, { "epoch": 0.86, "learning_rate": 1.7070086705202314e-05, "loss": 1.0267, "step": 4781 }, { "epoch": 0.86, "learning_rate": 1.706737716763006e-05, "loss": 0.7144, "step": 4782 }, { "epoch": 0.86, "learning_rate": 1.7064667630057803e-05, "loss": 0.584, "step": 4783 }, { "epoch": 0.86, "learning_rate": 1.706195809248555e-05, "loss": 0.6246, "step": 4784 }, { "epoch": 0.86, "learning_rate": 1.7059248554913295e-05, "loss": 1.0766, "step": 4785 }, { "epoch": 0.86, "learning_rate": 1.7056539017341043e-05, "loss": 0.9309, "step": 4786 }, { "epoch": 0.86, "learning_rate": 1.7053829479768784e-05, "loss": 1.3896, "step": 4787 }, { "epoch": 0.86, "learning_rate": 1.7051119942196532e-05, "loss": 0.802, "step": 4788 }, { "epoch": 0.87, "learning_rate": 1.704841040462428e-05, "loss": 0.9102, "step": 4789 }, { "epoch": 0.87, "learning_rate": 1.7045700867052024e-05, "loss": 1.1267, "step": 4790 }, { "epoch": 0.87, "learning_rate": 1.704299132947977e-05, "loss": 0.5873, "step": 4791 }, { "epoch": 0.87, "learning_rate": 1.7040281791907513e-05, "loss": 0.5263, "step": 4792 }, { "epoch": 0.87, "learning_rate": 1.703757225433526e-05, "loss": 0.4732, "step": 4793 }, { "epoch": 0.87, "learning_rate": 1.7034862716763008e-05, "loss": 0.906, "step": 4794 }, { "epoch": 0.87, "learning_rate": 1.7032153179190753e-05, "loss": 0.6749, "step": 4795 }, { "epoch": 0.87, "learning_rate": 1.7029443641618497e-05, "loss": 1.2295, "step": 4796 }, { "epoch": 0.87, "learning_rate": 1.702673410404624e-05, "loss": 1.1186, "step": 4797 }, { "epoch": 0.87, "learning_rate": 1.702402456647399e-05, "loss": 0.8073, "step": 4798 }, { "epoch": 0.87, "learning_rate": 1.7021315028901737e-05, "loss": 0.76, "step": 4799 }, { "epoch": 0.87, "learning_rate": 1.701860549132948e-05, "loss": 0.4676, "step": 4800 }, { "epoch": 0.87, "learning_rate": 1.7015895953757225e-05, "loss": 1.0764, "step": 4801 }, { "epoch": 0.87, "learning_rate": 1.701318641618497e-05, "loss": 0.7732, "step": 4802 }, { "epoch": 0.87, "learning_rate": 1.7010476878612718e-05, "loss": 0.4771, "step": 4803 }, { "epoch": 0.87, "learning_rate": 1.7007767341040465e-05, "loss": 0.5193, "step": 4804 }, { "epoch": 0.87, "learning_rate": 1.700505780346821e-05, "loss": 0.3229, "step": 4805 }, { "epoch": 0.87, "learning_rate": 1.7002348265895954e-05, "loss": 0.8915, "step": 4806 }, { "epoch": 0.87, "learning_rate": 1.69996387283237e-05, "loss": 0.5614, "step": 4807 }, { "epoch": 0.87, "learning_rate": 1.6996929190751446e-05, "loss": 0.6143, "step": 4808 }, { "epoch": 0.87, "learning_rate": 1.6994219653179194e-05, "loss": 0.9514, "step": 4809 }, { "epoch": 0.87, "learning_rate": 1.6991510115606935e-05, "loss": 1.0675, "step": 4810 }, { "epoch": 0.87, "learning_rate": 1.6988800578034683e-05, "loss": 0.5982, "step": 4811 }, { "epoch": 0.87, "learning_rate": 1.6986091040462427e-05, "loss": 1.2704, "step": 4812 }, { "epoch": 0.87, "learning_rate": 1.6983381502890175e-05, "loss": 0.973, "step": 4813 }, { "epoch": 0.87, "learning_rate": 1.6980671965317923e-05, "loss": 1.2758, "step": 4814 }, { "epoch": 0.87, "learning_rate": 1.6977962427745664e-05, "loss": 0.5543, "step": 4815 }, { "epoch": 0.87, "learning_rate": 1.697525289017341e-05, "loss": 0.9187, "step": 4816 }, { "epoch": 0.87, "learning_rate": 1.6972543352601156e-05, "loss": 0.5836, "step": 4817 }, { "epoch": 0.87, "learning_rate": 1.6969833815028903e-05, "loss": 0.5896, "step": 4818 }, { "epoch": 0.87, "learning_rate": 1.6967124277456648e-05, "loss": 1.3545, "step": 4819 }, { "epoch": 0.87, "learning_rate": 1.6964414739884392e-05, "loss": 1.2118, "step": 4820 }, { "epoch": 0.87, "learning_rate": 1.696170520231214e-05, "loss": 0.9147, "step": 4821 }, { "epoch": 0.87, "learning_rate": 1.6958995664739884e-05, "loss": 0.6197, "step": 4822 }, { "epoch": 0.87, "learning_rate": 1.6956286127167632e-05, "loss": 1.0045, "step": 4823 }, { "epoch": 0.87, "learning_rate": 1.6953576589595376e-05, "loss": 1.1177, "step": 4824 }, { "epoch": 0.87, "learning_rate": 1.695086705202312e-05, "loss": 0.5297, "step": 4825 }, { "epoch": 0.87, "learning_rate": 1.694815751445087e-05, "loss": 0.3561, "step": 4826 }, { "epoch": 0.87, "learning_rate": 1.6945447976878613e-05, "loss": 0.4905, "step": 4827 }, { "epoch": 0.87, "learning_rate": 1.694273843930636e-05, "loss": 1.1331, "step": 4828 }, { "epoch": 0.87, "learning_rate": 1.6940028901734105e-05, "loss": 0.5205, "step": 4829 }, { "epoch": 0.87, "learning_rate": 1.693731936416185e-05, "loss": 0.954, "step": 4830 }, { "epoch": 0.87, "learning_rate": 1.6934609826589597e-05, "loss": 0.6215, "step": 4831 }, { "epoch": 0.87, "learning_rate": 1.693190028901734e-05, "loss": 0.6777, "step": 4832 }, { "epoch": 0.87, "learning_rate": 1.6929190751445086e-05, "loss": 0.8107, "step": 4833 }, { "epoch": 0.87, "learning_rate": 1.6926481213872834e-05, "loss": 0.8858, "step": 4834 }, { "epoch": 0.87, "learning_rate": 1.6923771676300578e-05, "loss": 0.5055, "step": 4835 }, { "epoch": 0.87, "learning_rate": 1.6921062138728326e-05, "loss": 1.4314, "step": 4836 }, { "epoch": 0.87, "learning_rate": 1.691835260115607e-05, "loss": 1.0159, "step": 4837 }, { "epoch": 0.87, "learning_rate": 1.6915643063583814e-05, "loss": 0.5934, "step": 4838 }, { "epoch": 0.87, "learning_rate": 1.6912933526011562e-05, "loss": 0.65, "step": 4839 }, { "epoch": 0.87, "learning_rate": 1.6910223988439307e-05, "loss": 0.8397, "step": 4840 }, { "epoch": 0.87, "learning_rate": 1.6907514450867054e-05, "loss": 1.0552, "step": 4841 }, { "epoch": 0.87, "learning_rate": 1.6904804913294795e-05, "loss": 0.5062, "step": 4842 }, { "epoch": 0.87, "learning_rate": 1.6902095375722543e-05, "loss": 0.5278, "step": 4843 }, { "epoch": 0.88, "learning_rate": 1.689938583815029e-05, "loss": 0.957, "step": 4844 }, { "epoch": 0.88, "learning_rate": 1.6896676300578035e-05, "loss": 1.3859, "step": 4845 }, { "epoch": 0.88, "learning_rate": 1.6893966763005783e-05, "loss": 0.9264, "step": 4846 }, { "epoch": 0.88, "learning_rate": 1.6891257225433524e-05, "loss": 0.9334, "step": 4847 }, { "epoch": 0.88, "learning_rate": 1.688854768786127e-05, "loss": 0.2725, "step": 4848 }, { "epoch": 0.88, "learning_rate": 1.688583815028902e-05, "loss": 0.9143, "step": 4849 }, { "epoch": 0.88, "learning_rate": 1.6883128612716764e-05, "loss": 1.1745, "step": 4850 }, { "epoch": 0.88, "learning_rate": 1.6880419075144508e-05, "loss": 0.5884, "step": 4851 }, { "epoch": 0.88, "learning_rate": 1.6877709537572252e-05, "loss": 0.9001, "step": 4852 }, { "epoch": 0.88, "learning_rate": 1.6875e-05, "loss": 0.9238, "step": 4853 }, { "epoch": 0.88, "learning_rate": 1.6872290462427748e-05, "loss": 0.7586, "step": 4854 }, { "epoch": 0.88, "learning_rate": 1.6869580924855492e-05, "loss": 1.0658, "step": 4855 }, { "epoch": 0.88, "learning_rate": 1.6866871387283237e-05, "loss": 0.7946, "step": 4856 }, { "epoch": 0.88, "learning_rate": 1.686416184971098e-05, "loss": 1.1465, "step": 4857 }, { "epoch": 0.88, "learning_rate": 1.686145231213873e-05, "loss": 0.7081, "step": 4858 }, { "epoch": 0.88, "learning_rate": 1.6858742774566477e-05, "loss": 0.6393, "step": 4859 }, { "epoch": 0.88, "learning_rate": 1.685603323699422e-05, "loss": 1.0582, "step": 4860 }, { "epoch": 0.88, "learning_rate": 1.6853323699421965e-05, "loss": 0.9374, "step": 4861 }, { "epoch": 0.88, "learning_rate": 1.685061416184971e-05, "loss": 0.824, "step": 4862 }, { "epoch": 0.88, "learning_rate": 1.6847904624277457e-05, "loss": 0.7095, "step": 4863 }, { "epoch": 0.88, "learning_rate": 1.6845195086705205e-05, "loss": 0.8158, "step": 4864 }, { "epoch": 0.88, "learning_rate": 1.6842485549132946e-05, "loss": 0.4745, "step": 4865 }, { "epoch": 0.88, "learning_rate": 1.6839776011560694e-05, "loss": 1.3878, "step": 4866 }, { "epoch": 0.88, "learning_rate": 1.6837066473988438e-05, "loss": 1.4751, "step": 4867 }, { "epoch": 0.88, "learning_rate": 1.6834356936416186e-05, "loss": 0.5542, "step": 4868 }, { "epoch": 0.88, "learning_rate": 1.6831647398843934e-05, "loss": 0.8496, "step": 4869 }, { "epoch": 0.88, "learning_rate": 1.6828937861271675e-05, "loss": 0.3352, "step": 4870 }, { "epoch": 0.88, "learning_rate": 1.6826228323699423e-05, "loss": 1.131, "step": 4871 }, { "epoch": 0.88, "learning_rate": 1.6823518786127167e-05, "loss": 0.9676, "step": 4872 }, { "epoch": 0.88, "learning_rate": 1.6820809248554915e-05, "loss": 0.7106, "step": 4873 }, { "epoch": 0.88, "learning_rate": 1.681809971098266e-05, "loss": 1.1174, "step": 4874 }, { "epoch": 0.88, "learning_rate": 1.6815390173410403e-05, "loss": 0.6247, "step": 4875 }, { "epoch": 0.88, "learning_rate": 1.681268063583815e-05, "loss": 1.0322, "step": 4876 }, { "epoch": 0.88, "learning_rate": 1.6809971098265895e-05, "loss": 0.5091, "step": 4877 }, { "epoch": 0.88, "learning_rate": 1.6807261560693643e-05, "loss": 0.4951, "step": 4878 }, { "epoch": 0.88, "learning_rate": 1.6804552023121388e-05, "loss": 0.9496, "step": 4879 }, { "epoch": 0.88, "learning_rate": 1.6801842485549132e-05, "loss": 1.2584, "step": 4880 }, { "epoch": 0.88, "learning_rate": 1.679913294797688e-05, "loss": 0.5024, "step": 4881 }, { "epoch": 0.88, "learning_rate": 1.6796423410404624e-05, "loss": 1.1982, "step": 4882 }, { "epoch": 0.88, "learning_rate": 1.6793713872832372e-05, "loss": 0.7292, "step": 4883 }, { "epoch": 0.88, "learning_rate": 1.6791004335260116e-05, "loss": 1.4423, "step": 4884 }, { "epoch": 0.88, "learning_rate": 1.678829479768786e-05, "loss": 0.6689, "step": 4885 }, { "epoch": 0.88, "learning_rate": 1.678558526011561e-05, "loss": 0.6188, "step": 4886 }, { "epoch": 0.88, "learning_rate": 1.6782875722543353e-05, "loss": 0.2019, "step": 4887 }, { "epoch": 0.88, "learning_rate": 1.6780166184971097e-05, "loss": 0.7181, "step": 4888 }, { "epoch": 0.88, "learning_rate": 1.6777456647398845e-05, "loss": 0.5921, "step": 4889 }, { "epoch": 0.88, "learning_rate": 1.677474710982659e-05, "loss": 1.0177, "step": 4890 }, { "epoch": 0.88, "learning_rate": 1.6772037572254337e-05, "loss": 1.3238, "step": 4891 }, { "epoch": 0.88, "learning_rate": 1.676932803468208e-05, "loss": 0.6788, "step": 4892 }, { "epoch": 0.88, "learning_rate": 1.6766618497109826e-05, "loss": 0.6671, "step": 4893 }, { "epoch": 0.88, "learning_rate": 1.6763908959537573e-05, "loss": 0.867, "step": 4894 }, { "epoch": 0.88, "learning_rate": 1.6761199421965318e-05, "loss": 0.8895, "step": 4895 }, { "epoch": 0.88, "learning_rate": 1.6758489884393066e-05, "loss": 0.7416, "step": 4896 }, { "epoch": 0.88, "learning_rate": 1.6755780346820806e-05, "loss": 0.524, "step": 4897 }, { "epoch": 0.88, "learning_rate": 1.6753070809248554e-05, "loss": 0.5983, "step": 4898 }, { "epoch": 0.88, "learning_rate": 1.6750361271676302e-05, "loss": 0.698, "step": 4899 }, { "epoch": 0.89, "learning_rate": 1.6747651734104046e-05, "loss": 0.4279, "step": 4900 }, { "epoch": 0.89, "learning_rate": 1.6744942196531794e-05, "loss": 0.8826, "step": 4901 }, { "epoch": 0.89, "learning_rate": 1.6742232658959535e-05, "loss": 1.4756, "step": 4902 }, { "epoch": 0.89, "learning_rate": 1.6739523121387283e-05, "loss": 1.3574, "step": 4903 }, { "epoch": 0.89, "learning_rate": 1.673681358381503e-05, "loss": 1.0194, "step": 4904 }, { "epoch": 0.89, "learning_rate": 1.6734104046242775e-05, "loss": 0.5327, "step": 4905 }, { "epoch": 0.89, "learning_rate": 1.6731394508670523e-05, "loss": 0.4614, "step": 4906 }, { "epoch": 0.89, "learning_rate": 1.6728684971098264e-05, "loss": 1.0624, "step": 4907 }, { "epoch": 0.89, "learning_rate": 1.672597543352601e-05, "loss": 0.9373, "step": 4908 }, { "epoch": 0.89, "learning_rate": 1.672326589595376e-05, "loss": 0.4628, "step": 4909 }, { "epoch": 0.89, "learning_rate": 1.6720556358381504e-05, "loss": 1.1676, "step": 4910 }, { "epoch": 0.89, "learning_rate": 1.6717846820809248e-05, "loss": 0.7108, "step": 4911 }, { "epoch": 0.89, "learning_rate": 1.6715137283236992e-05, "loss": 0.4373, "step": 4912 }, { "epoch": 0.89, "learning_rate": 1.671242774566474e-05, "loss": 1.0157, "step": 4913 }, { "epoch": 0.89, "learning_rate": 1.6709718208092488e-05, "loss": 0.6792, "step": 4914 }, { "epoch": 0.89, "learning_rate": 1.6707008670520232e-05, "loss": 0.7588, "step": 4915 }, { "epoch": 0.89, "learning_rate": 1.6704299132947977e-05, "loss": 0.4116, "step": 4916 }, { "epoch": 0.89, "learning_rate": 1.670158959537572e-05, "loss": 1.0447, "step": 4917 }, { "epoch": 0.89, "learning_rate": 1.669888005780347e-05, "loss": 0.7269, "step": 4918 }, { "epoch": 0.89, "learning_rate": 1.6696170520231216e-05, "loss": 0.528, "step": 4919 }, { "epoch": 0.89, "learning_rate": 1.6693460982658957e-05, "loss": 0.6288, "step": 4920 }, { "epoch": 0.89, "learning_rate": 1.6690751445086705e-05, "loss": 0.6767, "step": 4921 }, { "epoch": 0.89, "learning_rate": 1.668804190751445e-05, "loss": 0.9686, "step": 4922 }, { "epoch": 0.89, "learning_rate": 1.6685332369942197e-05, "loss": 0.7914, "step": 4923 }, { "epoch": 0.89, "learning_rate": 1.6682622832369945e-05, "loss": 0.5768, "step": 4924 }, { "epoch": 0.89, "learning_rate": 1.6679913294797686e-05, "loss": 0.7503, "step": 4925 }, { "epoch": 0.89, "learning_rate": 1.6677203757225434e-05, "loss": 0.8909, "step": 4926 }, { "epoch": 0.89, "learning_rate": 1.6674494219653178e-05, "loss": 0.8285, "step": 4927 }, { "epoch": 0.89, "learning_rate": 1.6671784682080926e-05, "loss": 0.561, "step": 4928 }, { "epoch": 0.89, "learning_rate": 1.6669075144508674e-05, "loss": 1.6058, "step": 4929 }, { "epoch": 0.89, "learning_rate": 1.6666365606936415e-05, "loss": 0.8154, "step": 4930 }, { "epoch": 0.89, "learning_rate": 1.6663656069364162e-05, "loss": 0.7785, "step": 4931 }, { "epoch": 0.89, "learning_rate": 1.6660946531791907e-05, "loss": 0.1673, "step": 4932 }, { "epoch": 0.89, "learning_rate": 1.6658236994219654e-05, "loss": 0.6754, "step": 4933 }, { "epoch": 0.89, "learning_rate": 1.66555274566474e-05, "loss": 1.1544, "step": 4934 }, { "epoch": 0.89, "learning_rate": 1.6652817919075143e-05, "loss": 0.564, "step": 4935 }, { "epoch": 0.89, "learning_rate": 1.665010838150289e-05, "loss": 1.3329, "step": 4936 }, { "epoch": 0.89, "learning_rate": 1.6647398843930635e-05, "loss": 1.2488, "step": 4937 }, { "epoch": 0.89, "learning_rate": 1.6644689306358383e-05, "loss": 0.996, "step": 4938 }, { "epoch": 0.89, "learning_rate": 1.6641979768786127e-05, "loss": 0.6868, "step": 4939 }, { "epoch": 0.89, "learning_rate": 1.6639270231213872e-05, "loss": 0.4885, "step": 4940 }, { "epoch": 0.89, "learning_rate": 1.663656069364162e-05, "loss": 0.6448, "step": 4941 }, { "epoch": 0.89, "learning_rate": 1.6633851156069367e-05, "loss": 0.4493, "step": 4942 }, { "epoch": 0.89, "learning_rate": 1.6631141618497108e-05, "loss": 0.4566, "step": 4943 }, { "epoch": 0.89, "learning_rate": 1.6628432080924856e-05, "loss": 0.5533, "step": 4944 }, { "epoch": 0.89, "learning_rate": 1.66257225433526e-05, "loss": 0.5773, "step": 4945 }, { "epoch": 0.89, "learning_rate": 1.6623013005780348e-05, "loss": 0.6372, "step": 4946 }, { "epoch": 0.89, "learning_rate": 1.6620303468208096e-05, "loss": 0.5606, "step": 4947 }, { "epoch": 0.89, "learning_rate": 1.6617593930635837e-05, "loss": 0.5355, "step": 4948 }, { "epoch": 0.89, "learning_rate": 1.6614884393063585e-05, "loss": 0.6654, "step": 4949 }, { "epoch": 0.89, "learning_rate": 1.661217485549133e-05, "loss": 1.0607, "step": 4950 }, { "epoch": 0.89, "learning_rate": 1.6609465317919077e-05, "loss": 0.5134, "step": 4951 }, { "epoch": 0.89, "learning_rate": 1.6606755780346824e-05, "loss": 1.6617, "step": 4952 }, { "epoch": 0.89, "learning_rate": 1.6604046242774565e-05, "loss": 0.717, "step": 4953 }, { "epoch": 0.89, "learning_rate": 1.6601336705202313e-05, "loss": 0.4948, "step": 4954 }, { "epoch": 0.9, "learning_rate": 1.6598627167630058e-05, "loss": 0.6777, "step": 4955 }, { "epoch": 0.9, "learning_rate": 1.6595917630057805e-05, "loss": 1.7127, "step": 4956 }, { "epoch": 0.9, "learning_rate": 1.659320809248555e-05, "loss": 0.5317, "step": 4957 }, { "epoch": 0.9, "learning_rate": 1.6590498554913294e-05, "loss": 0.8803, "step": 4958 }, { "epoch": 0.9, "learning_rate": 1.6587789017341042e-05, "loss": 0.5941, "step": 4959 }, { "epoch": 0.9, "learning_rate": 1.6585079479768786e-05, "loss": 0.7971, "step": 4960 }, { "epoch": 0.9, "learning_rate": 1.6582369942196534e-05, "loss": 0.7374, "step": 4961 }, { "epoch": 0.9, "learning_rate": 1.657966040462428e-05, "loss": 0.6187, "step": 4962 }, { "epoch": 0.9, "learning_rate": 1.6576950867052023e-05, "loss": 1.3981, "step": 4963 }, { "epoch": 0.9, "learning_rate": 1.657424132947977e-05, "loss": 1.4094, "step": 4964 }, { "epoch": 0.9, "learning_rate": 1.6571531791907515e-05, "loss": 0.8806, "step": 4965 }, { "epoch": 0.9, "learning_rate": 1.656882225433526e-05, "loss": 0.4463, "step": 4966 }, { "epoch": 0.9, "learning_rate": 1.6566112716763007e-05, "loss": 1.0293, "step": 4967 }, { "epoch": 0.9, "learning_rate": 1.656340317919075e-05, "loss": 0.6438, "step": 4968 }, { "epoch": 0.9, "learning_rate": 1.65606936416185e-05, "loss": 0.71, "step": 4969 }, { "epoch": 0.9, "learning_rate": 1.6557984104046243e-05, "loss": 0.5639, "step": 4970 }, { "epoch": 0.9, "learning_rate": 1.6555274566473988e-05, "loss": 0.9218, "step": 4971 }, { "epoch": 0.9, "learning_rate": 1.6552565028901736e-05, "loss": 0.8853, "step": 4972 }, { "epoch": 0.9, "learning_rate": 1.654985549132948e-05, "loss": 1.0805, "step": 4973 }, { "epoch": 0.9, "learning_rate": 1.6547145953757228e-05, "loss": 0.9302, "step": 4974 }, { "epoch": 0.9, "learning_rate": 1.6544436416184972e-05, "loss": 0.4557, "step": 4975 }, { "epoch": 0.9, "learning_rate": 1.6541726878612716e-05, "loss": 0.7506, "step": 4976 }, { "epoch": 0.9, "learning_rate": 1.6539017341040464e-05, "loss": 1.0776, "step": 4977 }, { "epoch": 0.9, "learning_rate": 1.653630780346821e-05, "loss": 1.011, "step": 4978 }, { "epoch": 0.9, "learning_rate": 1.6533598265895956e-05, "loss": 0.967, "step": 4979 }, { "epoch": 0.9, "learning_rate": 1.6530888728323697e-05, "loss": 0.8824, "step": 4980 }, { "epoch": 0.9, "learning_rate": 1.6528179190751445e-05, "loss": 0.8525, "step": 4981 }, { "epoch": 0.9, "learning_rate": 1.6525469653179193e-05, "loss": 0.5477, "step": 4982 }, { "epoch": 0.9, "learning_rate": 1.6522760115606937e-05, "loss": 0.5392, "step": 4983 }, { "epoch": 0.9, "learning_rate": 1.6520050578034685e-05, "loss": 0.5489, "step": 4984 }, { "epoch": 0.9, "learning_rate": 1.6517341040462426e-05, "loss": 0.4908, "step": 4985 }, { "epoch": 0.9, "learning_rate": 1.6514631502890174e-05, "loss": 0.9, "step": 4986 }, { "epoch": 0.9, "learning_rate": 1.651192196531792e-05, "loss": 0.6209, "step": 4987 }, { "epoch": 0.9, "learning_rate": 1.6509212427745666e-05, "loss": 0.6968, "step": 4988 }, { "epoch": 0.9, "learning_rate": 1.650650289017341e-05, "loss": 1.1545, "step": 4989 }, { "epoch": 0.9, "learning_rate": 1.6503793352601154e-05, "loss": 0.7339, "step": 4990 }, { "epoch": 0.9, "learning_rate": 1.6501083815028902e-05, "loss": 1.3582, "step": 4991 }, { "epoch": 0.9, "learning_rate": 1.649837427745665e-05, "loss": 2.0212, "step": 4992 }, { "epoch": 0.9, "learning_rate": 1.6495664739884394e-05, "loss": 0.4484, "step": 4993 }, { "epoch": 0.9, "learning_rate": 1.649295520231214e-05, "loss": 1.1766, "step": 4994 }, { "epoch": 0.9, "learning_rate": 1.6490245664739883e-05, "loss": 0.4466, "step": 4995 }, { "epoch": 0.9, "learning_rate": 1.648753612716763e-05, "loss": 0.7806, "step": 4996 }, { "epoch": 0.9, "learning_rate": 1.648482658959538e-05, "loss": 0.8025, "step": 4997 }, { "epoch": 0.9, "learning_rate": 1.6482117052023123e-05, "loss": 1.0434, "step": 4998 }, { "epoch": 0.9, "learning_rate": 1.6479407514450867e-05, "loss": 1.268, "step": 4999 }, { "epoch": 0.9, "learning_rate": 1.647669797687861e-05, "loss": 0.3625, "step": 5000 }, { "epoch": 0.9, "eval_exact_match": 87.19016083254493, "eval_f1": 93.31917550988122, "step": 5000 }, { "epoch": 0.9, "learning_rate": 1.647398843930636e-05, "loss": 1.0541, "step": 5001 }, { "epoch": 0.9, "learning_rate": 1.6471278901734107e-05, "loss": 0.7095, "step": 5002 }, { "epoch": 0.9, "learning_rate": 1.6468569364161848e-05, "loss": 1.3844, "step": 5003 }, { "epoch": 0.9, "learning_rate": 1.6465859826589596e-05, "loss": 0.5756, "step": 5004 }, { "epoch": 0.9, "learning_rate": 1.646315028901734e-05, "loss": 0.7488, "step": 5005 }, { "epoch": 0.9, "learning_rate": 1.6460440751445088e-05, "loss": 0.9689, "step": 5006 }, { "epoch": 0.9, "learning_rate": 1.6457731213872836e-05, "loss": 0.8164, "step": 5007 }, { "epoch": 0.9, "learning_rate": 1.6455021676300577e-05, "loss": 0.6415, "step": 5008 }, { "epoch": 0.9, "learning_rate": 1.6452312138728324e-05, "loss": 1.4286, "step": 5009 }, { "epoch": 0.9, "learning_rate": 1.644960260115607e-05, "loss": 0.8973, "step": 5010 }, { "epoch": 0.91, "learning_rate": 1.6446893063583817e-05, "loss": 0.6973, "step": 5011 }, { "epoch": 0.91, "learning_rate": 1.644418352601156e-05, "loss": 0.4891, "step": 5012 }, { "epoch": 0.91, "learning_rate": 1.6441473988439305e-05, "loss": 0.5056, "step": 5013 }, { "epoch": 0.91, "learning_rate": 1.6438764450867053e-05, "loss": 0.567, "step": 5014 }, { "epoch": 0.91, "learning_rate": 1.6436054913294797e-05, "loss": 0.7755, "step": 5015 }, { "epoch": 0.91, "learning_rate": 1.6433345375722545e-05, "loss": 0.7967, "step": 5016 }, { "epoch": 0.91, "learning_rate": 1.643063583815029e-05, "loss": 0.8778, "step": 5017 }, { "epoch": 0.91, "learning_rate": 1.6427926300578034e-05, "loss": 0.252, "step": 5018 }, { "epoch": 0.91, "learning_rate": 1.642521676300578e-05, "loss": 0.505, "step": 5019 }, { "epoch": 0.91, "learning_rate": 1.6422507225433526e-05, "loss": 1.1364, "step": 5020 }, { "epoch": 0.91, "learning_rate": 1.6419797687861274e-05, "loss": 1.3744, "step": 5021 }, { "epoch": 0.91, "learning_rate": 1.6417088150289018e-05, "loss": 0.725, "step": 5022 }, { "epoch": 0.91, "learning_rate": 1.6414378612716763e-05, "loss": 1.4764, "step": 5023 }, { "epoch": 0.91, "learning_rate": 1.641166907514451e-05, "loss": 0.678, "step": 5024 }, { "epoch": 0.91, "learning_rate": 1.6408959537572255e-05, "loss": 0.3309, "step": 5025 }, { "epoch": 0.91, "learning_rate": 1.640625e-05, "loss": 0.6574, "step": 5026 }, { "epoch": 0.91, "learning_rate": 1.6403540462427747e-05, "loss": 0.9074, "step": 5027 }, { "epoch": 0.91, "learning_rate": 1.640083092485549e-05, "loss": 0.5139, "step": 5028 }, { "epoch": 0.91, "learning_rate": 1.639812138728324e-05, "loss": 0.474, "step": 5029 }, { "epoch": 0.91, "learning_rate": 1.6395411849710983e-05, "loss": 1.0268, "step": 5030 }, { "epoch": 0.91, "learning_rate": 1.6392702312138728e-05, "loss": 0.4771, "step": 5031 }, { "epoch": 0.91, "learning_rate": 1.6389992774566475e-05, "loss": 0.4348, "step": 5032 }, { "epoch": 0.91, "learning_rate": 1.638728323699422e-05, "loss": 1.1605, "step": 5033 }, { "epoch": 0.91, "learning_rate": 1.6384573699421967e-05, "loss": 0.5924, "step": 5034 }, { "epoch": 0.91, "learning_rate": 1.638186416184971e-05, "loss": 0.9035, "step": 5035 }, { "epoch": 0.91, "learning_rate": 1.6379154624277456e-05, "loss": 0.6222, "step": 5036 }, { "epoch": 0.91, "learning_rate": 1.6376445086705204e-05, "loss": 1.077, "step": 5037 }, { "epoch": 0.91, "learning_rate": 1.637373554913295e-05, "loss": 0.8208, "step": 5038 }, { "epoch": 0.91, "learning_rate": 1.6371026011560696e-05, "loss": 1.269, "step": 5039 }, { "epoch": 0.91, "learning_rate": 1.6368316473988437e-05, "loss": 0.9312, "step": 5040 }, { "epoch": 0.91, "learning_rate": 1.6365606936416185e-05, "loss": 0.8167, "step": 5041 }, { "epoch": 0.91, "learning_rate": 1.6362897398843933e-05, "loss": 0.493, "step": 5042 }, { "epoch": 0.91, "learning_rate": 1.6360187861271677e-05, "loss": 0.8362, "step": 5043 }, { "epoch": 0.91, "learning_rate": 1.6357478323699425e-05, "loss": 0.6077, "step": 5044 }, { "epoch": 0.91, "learning_rate": 1.6354768786127166e-05, "loss": 0.6797, "step": 5045 }, { "epoch": 0.91, "learning_rate": 1.6352059248554913e-05, "loss": 0.6275, "step": 5046 }, { "epoch": 0.91, "learning_rate": 1.634934971098266e-05, "loss": 0.3253, "step": 5047 }, { "epoch": 0.91, "learning_rate": 1.6346640173410406e-05, "loss": 0.9051, "step": 5048 }, { "epoch": 0.91, "learning_rate": 1.634393063583815e-05, "loss": 1.0522, "step": 5049 }, { "epoch": 0.91, "learning_rate": 1.6341221098265894e-05, "loss": 0.5889, "step": 5050 }, { "epoch": 0.91, "learning_rate": 1.6338511560693642e-05, "loss": 0.8925, "step": 5051 }, { "epoch": 0.91, "learning_rate": 1.633580202312139e-05, "loss": 0.5902, "step": 5052 }, { "epoch": 0.91, "learning_rate": 1.6333092485549134e-05, "loss": 0.8685, "step": 5053 }, { "epoch": 0.91, "learning_rate": 1.633038294797688e-05, "loss": 0.9163, "step": 5054 }, { "epoch": 0.91, "learning_rate": 1.6327673410404623e-05, "loss": 1.774, "step": 5055 }, { "epoch": 0.91, "learning_rate": 1.632496387283237e-05, "loss": 0.7625, "step": 5056 }, { "epoch": 0.91, "learning_rate": 1.632225433526012e-05, "loss": 1.3363, "step": 5057 }, { "epoch": 0.91, "learning_rate": 1.631954479768786e-05, "loss": 0.6918, "step": 5058 }, { "epoch": 0.91, "learning_rate": 1.6316835260115607e-05, "loss": 0.7897, "step": 5059 }, { "epoch": 0.91, "learning_rate": 1.631412572254335e-05, "loss": 1.0045, "step": 5060 }, { "epoch": 0.91, "learning_rate": 1.63114161849711e-05, "loss": 0.8638, "step": 5061 }, { "epoch": 0.91, "learning_rate": 1.6308706647398847e-05, "loss": 0.5086, "step": 5062 }, { "epoch": 0.91, "learning_rate": 1.6305997109826588e-05, "loss": 0.705, "step": 5063 }, { "epoch": 0.91, "learning_rate": 1.6303287572254336e-05, "loss": 0.6256, "step": 5064 }, { "epoch": 0.91, "learning_rate": 1.630057803468208e-05, "loss": 0.5735, "step": 5065 }, { "epoch": 0.92, "learning_rate": 1.6297868497109828e-05, "loss": 0.7055, "step": 5066 }, { "epoch": 0.92, "learning_rate": 1.6295158959537572e-05, "loss": 0.7855, "step": 5067 }, { "epoch": 0.92, "learning_rate": 1.6292449421965317e-05, "loss": 1.9028, "step": 5068 }, { "epoch": 0.92, "learning_rate": 1.6289739884393064e-05, "loss": 0.5109, "step": 5069 }, { "epoch": 0.92, "learning_rate": 1.628703034682081e-05, "loss": 0.8718, "step": 5070 }, { "epoch": 0.92, "learning_rate": 1.6284320809248556e-05, "loss": 0.639, "step": 5071 }, { "epoch": 0.92, "learning_rate": 1.62816112716763e-05, "loss": 0.4587, "step": 5072 }, { "epoch": 0.92, "learning_rate": 1.6278901734104045e-05, "loss": 0.4468, "step": 5073 }, { "epoch": 0.92, "learning_rate": 1.6276192196531793e-05, "loss": 0.6942, "step": 5074 }, { "epoch": 0.92, "learning_rate": 1.6273482658959537e-05, "loss": 0.5778, "step": 5075 }, { "epoch": 0.92, "learning_rate": 1.6270773121387285e-05, "loss": 0.298, "step": 5076 }, { "epoch": 0.92, "learning_rate": 1.626806358381503e-05, "loss": 0.5583, "step": 5077 }, { "epoch": 0.92, "learning_rate": 1.6265354046242774e-05, "loss": 0.6327, "step": 5078 }, { "epoch": 0.92, "learning_rate": 1.626264450867052e-05, "loss": 1.1711, "step": 5079 }, { "epoch": 0.92, "learning_rate": 1.6259934971098266e-05, "loss": 0.6849, "step": 5080 }, { "epoch": 0.92, "learning_rate": 1.625722543352601e-05, "loss": 0.938, "step": 5081 }, { "epoch": 0.92, "learning_rate": 1.6254515895953758e-05, "loss": 1.3006, "step": 5082 }, { "epoch": 0.92, "learning_rate": 1.6251806358381502e-05, "loss": 0.3046, "step": 5083 }, { "epoch": 0.92, "learning_rate": 1.624909682080925e-05, "loss": 0.4036, "step": 5084 }, { "epoch": 0.92, "learning_rate": 1.6246387283236994e-05, "loss": 0.5737, "step": 5085 }, { "epoch": 0.92, "learning_rate": 1.624367774566474e-05, "loss": 0.576, "step": 5086 }, { "epoch": 0.92, "learning_rate": 1.6240968208092487e-05, "loss": 0.5456, "step": 5087 }, { "epoch": 0.92, "learning_rate": 1.623825867052023e-05, "loss": 0.5462, "step": 5088 }, { "epoch": 0.92, "learning_rate": 1.623554913294798e-05, "loss": 0.5104, "step": 5089 }, { "epoch": 0.92, "learning_rate": 1.6232839595375723e-05, "loss": 0.9459, "step": 5090 }, { "epoch": 0.92, "learning_rate": 1.6230130057803467e-05, "loss": 1.1941, "step": 5091 }, { "epoch": 0.92, "learning_rate": 1.6227420520231215e-05, "loss": 0.878, "step": 5092 }, { "epoch": 0.92, "learning_rate": 1.622471098265896e-05, "loss": 0.819, "step": 5093 }, { "epoch": 0.92, "learning_rate": 1.6222001445086707e-05, "loss": 0.4529, "step": 5094 }, { "epoch": 0.92, "learning_rate": 1.6219291907514448e-05, "loss": 1.0214, "step": 5095 }, { "epoch": 0.92, "learning_rate": 1.6216582369942196e-05, "loss": 1.4438, "step": 5096 }, { "epoch": 0.92, "learning_rate": 1.6213872832369944e-05, "loss": 0.7904, "step": 5097 }, { "epoch": 0.92, "learning_rate": 1.6211163294797688e-05, "loss": 0.372, "step": 5098 }, { "epoch": 0.92, "learning_rate": 1.6208453757225436e-05, "loss": 0.63, "step": 5099 }, { "epoch": 0.92, "learning_rate": 1.6205744219653177e-05, "loss": 0.8506, "step": 5100 }, { "epoch": 0.92, "learning_rate": 1.6203034682080925e-05, "loss": 1.2289, "step": 5101 }, { "epoch": 0.92, "learning_rate": 1.6200325144508672e-05, "loss": 0.9133, "step": 5102 }, { "epoch": 0.92, "learning_rate": 1.6197615606936417e-05, "loss": 1.6681, "step": 5103 }, { "epoch": 0.92, "learning_rate": 1.619490606936416e-05, "loss": 0.2606, "step": 5104 }, { "epoch": 0.92, "learning_rate": 1.6192196531791905e-05, "loss": 0.6799, "step": 5105 }, { "epoch": 0.92, "learning_rate": 1.6189486994219653e-05, "loss": 0.7221, "step": 5106 }, { "epoch": 0.92, "learning_rate": 1.61867774566474e-05, "loss": 0.6417, "step": 5107 }, { "epoch": 0.92, "learning_rate": 1.6184067919075145e-05, "loss": 0.5722, "step": 5108 }, { "epoch": 0.92, "learning_rate": 1.618135838150289e-05, "loss": 0.6595, "step": 5109 }, { "epoch": 0.92, "learning_rate": 1.6178648843930634e-05, "loss": 0.6256, "step": 5110 }, { "epoch": 0.92, "learning_rate": 1.6175939306358382e-05, "loss": 0.8041, "step": 5111 }, { "epoch": 0.92, "learning_rate": 1.617322976878613e-05, "loss": 1.0969, "step": 5112 }, { "epoch": 0.92, "learning_rate": 1.617052023121387e-05, "loss": 1.1111, "step": 5113 }, { "epoch": 0.92, "learning_rate": 1.616781069364162e-05, "loss": 0.9194, "step": 5114 }, { "epoch": 0.92, "learning_rate": 1.6165101156069366e-05, "loss": 1.0381, "step": 5115 }, { "epoch": 0.92, "learning_rate": 1.616239161849711e-05, "loss": 1.2083, "step": 5116 }, { "epoch": 0.92, "learning_rate": 1.6159682080924858e-05, "loss": 0.8388, "step": 5117 }, { "epoch": 0.92, "learning_rate": 1.61569725433526e-05, "loss": 0.5964, "step": 5118 }, { "epoch": 0.92, "learning_rate": 1.6154263005780347e-05, "loss": 0.9086, "step": 5119 }, { "epoch": 0.92, "learning_rate": 1.6151553468208095e-05, "loss": 0.8839, "step": 5120 }, { "epoch": 0.93, "learning_rate": 1.614884393063584e-05, "loss": 0.732, "step": 5121 }, { "epoch": 0.93, "learning_rate": 1.6146134393063587e-05, "loss": 0.9088, "step": 5122 }, { "epoch": 0.93, "learning_rate": 1.6143424855491328e-05, "loss": 1.6666, "step": 5123 }, { "epoch": 0.93, "learning_rate": 1.6140715317919076e-05, "loss": 1.1322, "step": 5124 }, { "epoch": 0.93, "learning_rate": 1.6138005780346823e-05, "loss": 0.4815, "step": 5125 }, { "epoch": 0.93, "learning_rate": 1.6135296242774568e-05, "loss": 0.5419, "step": 5126 }, { "epoch": 0.93, "learning_rate": 1.6132586705202312e-05, "loss": 1.3175, "step": 5127 }, { "epoch": 0.93, "learning_rate": 1.6129877167630056e-05, "loss": 0.4448, "step": 5128 }, { "epoch": 0.93, "learning_rate": 1.6127167630057804e-05, "loss": 0.7534, "step": 5129 }, { "epoch": 0.93, "learning_rate": 1.6124458092485552e-05, "loss": 0.8269, "step": 5130 }, { "epoch": 0.93, "learning_rate": 1.6121748554913296e-05, "loss": 0.3256, "step": 5131 }, { "epoch": 0.93, "learning_rate": 1.611903901734104e-05, "loss": 0.5938, "step": 5132 }, { "epoch": 0.93, "learning_rate": 1.6116329479768785e-05, "loss": 0.7734, "step": 5133 }, { "epoch": 0.93, "learning_rate": 1.6113619942196533e-05, "loss": 0.6823, "step": 5134 }, { "epoch": 0.93, "learning_rate": 1.611091040462428e-05, "loss": 0.6681, "step": 5135 }, { "epoch": 0.93, "learning_rate": 1.610820086705202e-05, "loss": 0.4652, "step": 5136 }, { "epoch": 0.93, "learning_rate": 1.610549132947977e-05, "loss": 0.4181, "step": 5137 }, { "epoch": 0.93, "learning_rate": 1.6102781791907514e-05, "loss": 1.5066, "step": 5138 }, { "epoch": 0.93, "learning_rate": 1.610007225433526e-05, "loss": 0.5497, "step": 5139 }, { "epoch": 0.93, "learning_rate": 1.609736271676301e-05, "loss": 1.0231, "step": 5140 }, { "epoch": 0.93, "learning_rate": 1.609465317919075e-05, "loss": 0.8221, "step": 5141 }, { "epoch": 0.93, "learning_rate": 1.6091943641618498e-05, "loss": 0.6135, "step": 5142 }, { "epoch": 0.93, "learning_rate": 1.6089234104046242e-05, "loss": 0.6932, "step": 5143 }, { "epoch": 0.93, "learning_rate": 1.608652456647399e-05, "loss": 0.9609, "step": 5144 }, { "epoch": 0.93, "learning_rate": 1.6083815028901738e-05, "loss": 1.1377, "step": 5145 }, { "epoch": 0.93, "learning_rate": 1.608110549132948e-05, "loss": 0.5555, "step": 5146 }, { "epoch": 0.93, "learning_rate": 1.6078395953757226e-05, "loss": 0.4116, "step": 5147 }, { "epoch": 0.93, "learning_rate": 1.607568641618497e-05, "loss": 0.8063, "step": 5148 }, { "epoch": 0.93, "learning_rate": 1.607297687861272e-05, "loss": 1.1052, "step": 5149 }, { "epoch": 0.93, "learning_rate": 1.6070267341040463e-05, "loss": 1.0674, "step": 5150 }, { "epoch": 0.93, "learning_rate": 1.6067557803468207e-05, "loss": 1.29, "step": 5151 }, { "epoch": 0.93, "learning_rate": 1.6064848265895955e-05, "loss": 1.2767, "step": 5152 }, { "epoch": 0.93, "learning_rate": 1.60621387283237e-05, "loss": 0.6648, "step": 5153 }, { "epoch": 0.93, "learning_rate": 1.6059429190751447e-05, "loss": 0.8437, "step": 5154 }, { "epoch": 0.93, "learning_rate": 1.605671965317919e-05, "loss": 0.9425, "step": 5155 }, { "epoch": 0.93, "learning_rate": 1.6054010115606936e-05, "loss": 0.7004, "step": 5156 }, { "epoch": 0.93, "learning_rate": 1.6051300578034684e-05, "loss": 0.8782, "step": 5157 }, { "epoch": 0.93, "learning_rate": 1.6048591040462428e-05, "loss": 1.0572, "step": 5158 }, { "epoch": 0.93, "learning_rate": 1.6045881502890172e-05, "loss": 0.5168, "step": 5159 }, { "epoch": 0.93, "learning_rate": 1.604317196531792e-05, "loss": 0.5073, "step": 5160 }, { "epoch": 0.93, "learning_rate": 1.6040462427745664e-05, "loss": 0.6302, "step": 5161 }, { "epoch": 0.93, "learning_rate": 1.6037752890173412e-05, "loss": 1.6092, "step": 5162 }, { "epoch": 0.93, "learning_rate": 1.6035043352601157e-05, "loss": 0.5666, "step": 5163 }, { "epoch": 0.93, "learning_rate": 1.60323338150289e-05, "loss": 1.0976, "step": 5164 }, { "epoch": 0.93, "learning_rate": 1.602962427745665e-05, "loss": 0.5217, "step": 5165 }, { "epoch": 0.93, "learning_rate": 1.6026914739884393e-05, "loss": 0.8707, "step": 5166 }, { "epoch": 0.93, "learning_rate": 1.602420520231214e-05, "loss": 1.1098, "step": 5167 }, { "epoch": 0.93, "learning_rate": 1.6021495664739885e-05, "loss": 0.3169, "step": 5168 }, { "epoch": 0.93, "learning_rate": 1.601878612716763e-05, "loss": 0.8847, "step": 5169 }, { "epoch": 0.93, "learning_rate": 1.6016076589595377e-05, "loss": 0.2863, "step": 5170 }, { "epoch": 0.93, "learning_rate": 1.601336705202312e-05, "loss": 0.8632, "step": 5171 }, { "epoch": 0.93, "learning_rate": 1.601065751445087e-05, "loss": 0.5858, "step": 5172 }, { "epoch": 0.93, "learning_rate": 1.600794797687861e-05, "loss": 0.6649, "step": 5173 }, { "epoch": 0.93, "learning_rate": 1.6005238439306358e-05, "loss": 1.06, "step": 5174 }, { "epoch": 0.93, "learning_rate": 1.6002528901734106e-05, "loss": 0.9877, "step": 5175 }, { "epoch": 0.93, "learning_rate": 1.599981936416185e-05, "loss": 1.2178, "step": 5176 }, { "epoch": 0.94, "learning_rate": 1.5997109826589598e-05, "loss": 0.958, "step": 5177 }, { "epoch": 0.94, "learning_rate": 1.599440028901734e-05, "loss": 1.2069, "step": 5178 }, { "epoch": 0.94, "learning_rate": 1.5991690751445087e-05, "loss": 0.8151, "step": 5179 }, { "epoch": 0.94, "learning_rate": 1.5988981213872834e-05, "loss": 0.6424, "step": 5180 }, { "epoch": 0.94, "learning_rate": 1.598627167630058e-05, "loss": 0.3888, "step": 5181 }, { "epoch": 0.94, "learning_rate": 1.5983562138728323e-05, "loss": 0.7839, "step": 5182 }, { "epoch": 0.94, "learning_rate": 1.5980852601156068e-05, "loss": 0.6595, "step": 5183 }, { "epoch": 0.94, "learning_rate": 1.5978143063583815e-05, "loss": 1.2716, "step": 5184 }, { "epoch": 0.94, "learning_rate": 1.5975433526011563e-05, "loss": 0.6077, "step": 5185 }, { "epoch": 0.94, "learning_rate": 1.5972723988439307e-05, "loss": 0.8732, "step": 5186 }, { "epoch": 0.94, "learning_rate": 1.5970014450867052e-05, "loss": 0.5907, "step": 5187 }, { "epoch": 0.94, "learning_rate": 1.5967304913294796e-05, "loss": 0.8867, "step": 5188 }, { "epoch": 0.94, "learning_rate": 1.5964595375722544e-05, "loss": 1.0893, "step": 5189 }, { "epoch": 0.94, "learning_rate": 1.5961885838150292e-05, "loss": 0.9211, "step": 5190 }, { "epoch": 0.94, "learning_rate": 1.5959176300578036e-05, "loss": 0.6627, "step": 5191 }, { "epoch": 0.94, "learning_rate": 1.595646676300578e-05, "loss": 0.8061, "step": 5192 }, { "epoch": 0.94, "learning_rate": 1.5953757225433525e-05, "loss": 0.6084, "step": 5193 }, { "epoch": 0.94, "learning_rate": 1.5951047687861273e-05, "loss": 1.3278, "step": 5194 }, { "epoch": 0.94, "learning_rate": 1.594833815028902e-05, "loss": 0.5241, "step": 5195 }, { "epoch": 0.94, "learning_rate": 1.594562861271676e-05, "loss": 0.7254, "step": 5196 }, { "epoch": 0.94, "learning_rate": 1.594291907514451e-05, "loss": 1.7532, "step": 5197 }, { "epoch": 0.94, "learning_rate": 1.5940209537572253e-05, "loss": 0.3887, "step": 5198 }, { "epoch": 0.94, "learning_rate": 1.59375e-05, "loss": 0.7313, "step": 5199 }, { "epoch": 0.94, "learning_rate": 1.593479046242775e-05, "loss": 0.718, "step": 5200 }, { "epoch": 0.94, "learning_rate": 1.593208092485549e-05, "loss": 0.7589, "step": 5201 }, { "epoch": 0.94, "learning_rate": 1.5929371387283238e-05, "loss": 0.7053, "step": 5202 }, { "epoch": 0.94, "learning_rate": 1.5926661849710982e-05, "loss": 1.1833, "step": 5203 }, { "epoch": 0.94, "learning_rate": 1.592395231213873e-05, "loss": 0.8391, "step": 5204 }, { "epoch": 0.94, "learning_rate": 1.5921242774566474e-05, "loss": 0.62, "step": 5205 }, { "epoch": 0.94, "learning_rate": 1.591853323699422e-05, "loss": 0.4645, "step": 5206 }, { "epoch": 0.94, "learning_rate": 1.5915823699421966e-05, "loss": 0.6193, "step": 5207 }, { "epoch": 0.94, "learning_rate": 1.591311416184971e-05, "loss": 0.4671, "step": 5208 }, { "epoch": 0.94, "learning_rate": 1.591040462427746e-05, "loss": 0.7724, "step": 5209 }, { "epoch": 0.94, "learning_rate": 1.5907695086705203e-05, "loss": 0.8971, "step": 5210 }, { "epoch": 0.94, "learning_rate": 1.5904985549132947e-05, "loss": 0.4519, "step": 5211 }, { "epoch": 0.94, "learning_rate": 1.5902276011560695e-05, "loss": 1.1252, "step": 5212 }, { "epoch": 0.94, "learning_rate": 1.589956647398844e-05, "loss": 0.3632, "step": 5213 }, { "epoch": 0.94, "learning_rate": 1.5896856936416187e-05, "loss": 1.0711, "step": 5214 }, { "epoch": 0.94, "learning_rate": 1.589414739884393e-05, "loss": 0.8366, "step": 5215 }, { "epoch": 0.94, "learning_rate": 1.5891437861271676e-05, "loss": 0.4173, "step": 5216 }, { "epoch": 0.94, "learning_rate": 1.5888728323699423e-05, "loss": 0.6928, "step": 5217 }, { "epoch": 0.94, "learning_rate": 1.5886018786127168e-05, "loss": 0.8355, "step": 5218 }, { "epoch": 0.94, "learning_rate": 1.5883309248554912e-05, "loss": 0.9639, "step": 5219 }, { "epoch": 0.94, "learning_rate": 1.588059971098266e-05, "loss": 1.0178, "step": 5220 }, { "epoch": 0.94, "learning_rate": 1.5877890173410404e-05, "loss": 0.7847, "step": 5221 }, { "epoch": 0.94, "learning_rate": 1.5875180635838152e-05, "loss": 0.7054, "step": 5222 }, { "epoch": 0.94, "learning_rate": 1.5872471098265896e-05, "loss": 0.6075, "step": 5223 }, { "epoch": 0.94, "learning_rate": 1.586976156069364e-05, "loss": 0.8051, "step": 5224 }, { "epoch": 0.94, "learning_rate": 1.586705202312139e-05, "loss": 0.5424, "step": 5225 }, { "epoch": 0.94, "learning_rate": 1.5864342485549133e-05, "loss": 1.2832, "step": 5226 }, { "epoch": 0.94, "learning_rate": 1.586163294797688e-05, "loss": 0.694, "step": 5227 }, { "epoch": 0.94, "learning_rate": 1.585892341040462e-05, "loss": 0.8357, "step": 5228 }, { "epoch": 0.94, "learning_rate": 1.585621387283237e-05, "loss": 0.1228, "step": 5229 }, { "epoch": 0.94, "learning_rate": 1.5853504335260117e-05, "loss": 0.4422, "step": 5230 }, { "epoch": 0.94, "learning_rate": 1.585079479768786e-05, "loss": 1.5193, "step": 5231 }, { "epoch": 0.95, "learning_rate": 1.584808526011561e-05, "loss": 1.3125, "step": 5232 }, { "epoch": 0.95, "learning_rate": 1.584537572254335e-05, "loss": 1.51, "step": 5233 }, { "epoch": 0.95, "learning_rate": 1.5842666184971098e-05, "loss": 0.9545, "step": 5234 }, { "epoch": 0.95, "learning_rate": 1.5839956647398846e-05, "loss": 0.3834, "step": 5235 }, { "epoch": 0.95, "learning_rate": 1.583724710982659e-05, "loss": 0.7914, "step": 5236 }, { "epoch": 0.95, "learning_rate": 1.5834537572254338e-05, "loss": 0.2755, "step": 5237 }, { "epoch": 0.95, "learning_rate": 1.583182803468208e-05, "loss": 0.8667, "step": 5238 }, { "epoch": 0.95, "learning_rate": 1.5829118497109827e-05, "loss": 0.5676, "step": 5239 }, { "epoch": 0.95, "learning_rate": 1.5826408959537574e-05, "loss": 0.9433, "step": 5240 }, { "epoch": 0.95, "learning_rate": 1.582369942196532e-05, "loss": 0.7973, "step": 5241 }, { "epoch": 0.95, "learning_rate": 1.5820989884393063e-05, "loss": 0.5739, "step": 5242 }, { "epoch": 0.95, "learning_rate": 1.5818280346820807e-05, "loss": 0.8933, "step": 5243 }, { "epoch": 0.95, "learning_rate": 1.5815570809248555e-05, "loss": 0.7895, "step": 5244 }, { "epoch": 0.95, "learning_rate": 1.5812861271676303e-05, "loss": 0.862, "step": 5245 }, { "epoch": 0.95, "learning_rate": 1.5810151734104047e-05, "loss": 0.6265, "step": 5246 }, { "epoch": 0.95, "learning_rate": 1.580744219653179e-05, "loss": 0.7978, "step": 5247 }, { "epoch": 0.95, "learning_rate": 1.5804732658959536e-05, "loss": 0.6466, "step": 5248 }, { "epoch": 0.95, "learning_rate": 1.5802023121387284e-05, "loss": 0.8262, "step": 5249 }, { "epoch": 0.95, "learning_rate": 1.579931358381503e-05, "loss": 0.5173, "step": 5250 }, { "epoch": 0.95, "learning_rate": 1.5796604046242773e-05, "loss": 1.2175, "step": 5251 }, { "epoch": 0.95, "learning_rate": 1.579389450867052e-05, "loss": 0.7191, "step": 5252 }, { "epoch": 0.95, "learning_rate": 1.5791184971098265e-05, "loss": 0.5786, "step": 5253 }, { "epoch": 0.95, "learning_rate": 1.5788475433526012e-05, "loss": 0.6567, "step": 5254 }, { "epoch": 0.95, "learning_rate": 1.578576589595376e-05, "loss": 0.8908, "step": 5255 }, { "epoch": 0.95, "learning_rate": 1.57830563583815e-05, "loss": 1.1352, "step": 5256 }, { "epoch": 0.95, "learning_rate": 1.578034682080925e-05, "loss": 1.0284, "step": 5257 }, { "epoch": 0.95, "learning_rate": 1.5777637283236993e-05, "loss": 0.5984, "step": 5258 }, { "epoch": 0.95, "learning_rate": 1.577492774566474e-05, "loss": 0.8867, "step": 5259 }, { "epoch": 0.95, "learning_rate": 1.577221820809249e-05, "loss": 0.8827, "step": 5260 }, { "epoch": 0.95, "learning_rate": 1.576950867052023e-05, "loss": 0.7959, "step": 5261 }, { "epoch": 0.95, "learning_rate": 1.5766799132947977e-05, "loss": 1.0951, "step": 5262 }, { "epoch": 0.95, "learning_rate": 1.5764089595375722e-05, "loss": 1.3095, "step": 5263 }, { "epoch": 0.95, "learning_rate": 1.576138005780347e-05, "loss": 0.3736, "step": 5264 }, { "epoch": 0.95, "learning_rate": 1.5758670520231214e-05, "loss": 0.4469, "step": 5265 }, { "epoch": 0.95, "learning_rate": 1.575596098265896e-05, "loss": 0.5477, "step": 5266 }, { "epoch": 0.95, "learning_rate": 1.5753251445086706e-05, "loss": 0.6963, "step": 5267 }, { "epoch": 0.95, "learning_rate": 1.575054190751445e-05, "loss": 0.8926, "step": 5268 }, { "epoch": 0.95, "learning_rate": 1.5747832369942198e-05, "loss": 0.6071, "step": 5269 }, { "epoch": 0.95, "learning_rate": 1.5745122832369943e-05, "loss": 0.5323, "step": 5270 }, { "epoch": 0.95, "learning_rate": 1.5742413294797687e-05, "loss": 0.7942, "step": 5271 }, { "epoch": 0.95, "learning_rate": 1.5739703757225435e-05, "loss": 0.6539, "step": 5272 }, { "epoch": 0.95, "learning_rate": 1.573699421965318e-05, "loss": 0.7354, "step": 5273 }, { "epoch": 0.95, "learning_rate": 1.5734284682080923e-05, "loss": 0.6999, "step": 5274 }, { "epoch": 0.95, "learning_rate": 1.573157514450867e-05, "loss": 0.5194, "step": 5275 }, { "epoch": 0.95, "learning_rate": 1.5728865606936416e-05, "loss": 0.582, "step": 5276 }, { "epoch": 0.95, "learning_rate": 1.5726156069364163e-05, "loss": 0.8322, "step": 5277 }, { "epoch": 0.95, "learning_rate": 1.5723446531791908e-05, "loss": 0.6551, "step": 5278 }, { "epoch": 0.95, "learning_rate": 1.5720736994219652e-05, "loss": 0.4674, "step": 5279 }, { "epoch": 0.95, "learning_rate": 1.57180274566474e-05, "loss": 1.3156, "step": 5280 }, { "epoch": 0.95, "learning_rate": 1.5715317919075144e-05, "loss": 0.633, "step": 5281 }, { "epoch": 0.95, "learning_rate": 1.5712608381502892e-05, "loss": 0.5111, "step": 5282 }, { "epoch": 0.95, "learning_rate": 1.5709898843930636e-05, "loss": 1.4344, "step": 5283 }, { "epoch": 0.95, "learning_rate": 1.570718930635838e-05, "loss": 0.9757, "step": 5284 }, { "epoch": 0.95, "learning_rate": 1.570447976878613e-05, "loss": 0.6319, "step": 5285 }, { "epoch": 0.95, "learning_rate": 1.5701770231213873e-05, "loss": 0.7054, "step": 5286 }, { "epoch": 0.96, "learning_rate": 1.569906069364162e-05, "loss": 1.1205, "step": 5287 }, { "epoch": 0.96, "learning_rate": 1.5696351156069365e-05, "loss": 0.25, "step": 5288 }, { "epoch": 0.96, "learning_rate": 1.569364161849711e-05, "loss": 1.4583, "step": 5289 }, { "epoch": 0.96, "learning_rate": 1.5690932080924857e-05, "loss": 0.5926, "step": 5290 }, { "epoch": 0.96, "learning_rate": 1.56882225433526e-05, "loss": 0.6181, "step": 5291 }, { "epoch": 0.96, "learning_rate": 1.568551300578035e-05, "loss": 1.4389, "step": 5292 }, { "epoch": 0.96, "learning_rate": 1.5682803468208093e-05, "loss": 1.1745, "step": 5293 }, { "epoch": 0.96, "learning_rate": 1.5680093930635838e-05, "loss": 1.0809, "step": 5294 }, { "epoch": 0.96, "learning_rate": 1.5677384393063586e-05, "loss": 0.6931, "step": 5295 }, { "epoch": 0.96, "learning_rate": 1.567467485549133e-05, "loss": 0.7227, "step": 5296 }, { "epoch": 0.96, "learning_rate": 1.5671965317919074e-05, "loss": 0.4205, "step": 5297 }, { "epoch": 0.96, "learning_rate": 1.5669255780346822e-05, "loss": 1.1661, "step": 5298 }, { "epoch": 0.96, "learning_rate": 1.5666546242774566e-05, "loss": 1.0308, "step": 5299 }, { "epoch": 0.96, "learning_rate": 1.5663836705202314e-05, "loss": 1.1979, "step": 5300 }, { "epoch": 0.96, "learning_rate": 1.566112716763006e-05, "loss": 0.77, "step": 5301 }, { "epoch": 0.96, "learning_rate": 1.5658417630057803e-05, "loss": 0.7174, "step": 5302 }, { "epoch": 0.96, "learning_rate": 1.565570809248555e-05, "loss": 0.361, "step": 5303 }, { "epoch": 0.96, "learning_rate": 1.5652998554913295e-05, "loss": 0.4293, "step": 5304 }, { "epoch": 0.96, "learning_rate": 1.5650289017341043e-05, "loss": 1.0113, "step": 5305 }, { "epoch": 0.96, "learning_rate": 1.5647579479768787e-05, "loss": 0.5618, "step": 5306 }, { "epoch": 0.96, "learning_rate": 1.564486994219653e-05, "loss": 1.0846, "step": 5307 }, { "epoch": 0.96, "learning_rate": 1.564216040462428e-05, "loss": 0.6749, "step": 5308 }, { "epoch": 0.96, "learning_rate": 1.5639450867052024e-05, "loss": 0.5303, "step": 5309 }, { "epoch": 0.96, "learning_rate": 1.563674132947977e-05, "loss": 1.3265, "step": 5310 }, { "epoch": 0.96, "learning_rate": 1.5634031791907512e-05, "loss": 0.8811, "step": 5311 }, { "epoch": 0.96, "learning_rate": 1.563132225433526e-05, "loss": 0.803, "step": 5312 }, { "epoch": 0.96, "learning_rate": 1.5628612716763008e-05, "loss": 0.5177, "step": 5313 }, { "epoch": 0.96, "learning_rate": 1.5625903179190752e-05, "loss": 0.2714, "step": 5314 }, { "epoch": 0.96, "learning_rate": 1.56231936416185e-05, "loss": 1.1201, "step": 5315 }, { "epoch": 0.96, "learning_rate": 1.562048410404624e-05, "loss": 0.8544, "step": 5316 }, { "epoch": 0.96, "learning_rate": 1.561777456647399e-05, "loss": 0.7235, "step": 5317 }, { "epoch": 0.96, "learning_rate": 1.5615065028901736e-05, "loss": 0.8076, "step": 5318 }, { "epoch": 0.96, "learning_rate": 1.561235549132948e-05, "loss": 0.6781, "step": 5319 }, { "epoch": 0.96, "learning_rate": 1.5609645953757225e-05, "loss": 0.8751, "step": 5320 }, { "epoch": 0.96, "learning_rate": 1.560693641618497e-05, "loss": 0.5472, "step": 5321 }, { "epoch": 0.96, "learning_rate": 1.5604226878612717e-05, "loss": 1.5037, "step": 5322 }, { "epoch": 0.96, "learning_rate": 1.5601517341040465e-05, "loss": 0.4374, "step": 5323 }, { "epoch": 0.96, "learning_rate": 1.559880780346821e-05, "loss": 0.4132, "step": 5324 }, { "epoch": 0.96, "learning_rate": 1.5596098265895954e-05, "loss": 0.6274, "step": 5325 }, { "epoch": 0.96, "learning_rate": 1.5593388728323698e-05, "loss": 0.6088, "step": 5326 }, { "epoch": 0.96, "learning_rate": 1.5590679190751446e-05, "loss": 0.4962, "step": 5327 }, { "epoch": 0.96, "learning_rate": 1.5587969653179194e-05, "loss": 0.6742, "step": 5328 }, { "epoch": 0.96, "learning_rate": 1.5585260115606935e-05, "loss": 0.9609, "step": 5329 }, { "epoch": 0.96, "learning_rate": 1.5582550578034682e-05, "loss": 1.817, "step": 5330 }, { "epoch": 0.96, "learning_rate": 1.5579841040462427e-05, "loss": 0.77, "step": 5331 }, { "epoch": 0.96, "learning_rate": 1.5577131502890174e-05, "loss": 0.9775, "step": 5332 }, { "epoch": 0.96, "learning_rate": 1.5574421965317922e-05, "loss": 1.1892, "step": 5333 }, { "epoch": 0.96, "learning_rate": 1.5571712427745663e-05, "loss": 1.1219, "step": 5334 }, { "epoch": 0.96, "learning_rate": 1.556900289017341e-05, "loss": 0.8546, "step": 5335 }, { "epoch": 0.96, "learning_rate": 1.5566293352601155e-05, "loss": 0.434, "step": 5336 }, { "epoch": 0.96, "learning_rate": 1.5563583815028903e-05, "loss": 0.7928, "step": 5337 }, { "epoch": 0.96, "learning_rate": 1.556087427745665e-05, "loss": 0.9827, "step": 5338 }, { "epoch": 0.96, "learning_rate": 1.5558164739884392e-05, "loss": 0.3533, "step": 5339 }, { "epoch": 0.96, "learning_rate": 1.555545520231214e-05, "loss": 0.6117, "step": 5340 }, { "epoch": 0.96, "learning_rate": 1.5552745664739884e-05, "loss": 0.5439, "step": 5341 }, { "epoch": 0.96, "learning_rate": 1.5550036127167632e-05, "loss": 0.7071, "step": 5342 }, { "epoch": 0.97, "learning_rate": 1.5547326589595376e-05, "loss": 0.7933, "step": 5343 }, { "epoch": 0.97, "learning_rate": 1.554461705202312e-05, "loss": 0.2663, "step": 5344 }, { "epoch": 0.97, "learning_rate": 1.5541907514450868e-05, "loss": 0.6373, "step": 5345 }, { "epoch": 0.97, "learning_rate": 1.5539197976878613e-05, "loss": 0.5378, "step": 5346 }, { "epoch": 0.97, "learning_rate": 1.553648843930636e-05, "loss": 1.0572, "step": 5347 }, { "epoch": 0.97, "learning_rate": 1.5533778901734105e-05, "loss": 0.9142, "step": 5348 }, { "epoch": 0.97, "learning_rate": 1.553106936416185e-05, "loss": 1.1894, "step": 5349 }, { "epoch": 0.97, "learning_rate": 1.5528359826589597e-05, "loss": 1.3338, "step": 5350 }, { "epoch": 0.97, "learning_rate": 1.552565028901734e-05, "loss": 0.4043, "step": 5351 }, { "epoch": 0.97, "learning_rate": 1.5522940751445086e-05, "loss": 1.0408, "step": 5352 }, { "epoch": 0.97, "learning_rate": 1.5520231213872833e-05, "loss": 1.3284, "step": 5353 }, { "epoch": 0.97, "learning_rate": 1.5517521676300578e-05, "loss": 0.646, "step": 5354 }, { "epoch": 0.97, "learning_rate": 1.5514812138728325e-05, "loss": 0.4962, "step": 5355 }, { "epoch": 0.97, "learning_rate": 1.551210260115607e-05, "loss": 1.1312, "step": 5356 }, { "epoch": 0.97, "learning_rate": 1.5509393063583814e-05, "loss": 0.555, "step": 5357 }, { "epoch": 0.97, "learning_rate": 1.5506683526011562e-05, "loss": 0.8156, "step": 5358 }, { "epoch": 0.97, "learning_rate": 1.5503973988439306e-05, "loss": 1.0393, "step": 5359 }, { "epoch": 0.97, "learning_rate": 1.5501264450867054e-05, "loss": 0.571, "step": 5360 }, { "epoch": 0.97, "learning_rate": 1.54985549132948e-05, "loss": 0.6437, "step": 5361 }, { "epoch": 0.97, "learning_rate": 1.5495845375722543e-05, "loss": 0.972, "step": 5362 }, { "epoch": 0.97, "learning_rate": 1.549313583815029e-05, "loss": 0.5641, "step": 5363 }, { "epoch": 0.97, "learning_rate": 1.5490426300578035e-05, "loss": 1.021, "step": 5364 }, { "epoch": 0.97, "learning_rate": 1.5487716763005783e-05, "loss": 0.5795, "step": 5365 }, { "epoch": 0.97, "learning_rate": 1.5485007225433524e-05, "loss": 0.4977, "step": 5366 }, { "epoch": 0.97, "learning_rate": 1.548229768786127e-05, "loss": 0.6831, "step": 5367 }, { "epoch": 0.97, "learning_rate": 1.547958815028902e-05, "loss": 0.4411, "step": 5368 }, { "epoch": 0.97, "learning_rate": 1.5476878612716763e-05, "loss": 0.4145, "step": 5369 }, { "epoch": 0.97, "learning_rate": 1.547416907514451e-05, "loss": 0.7688, "step": 5370 }, { "epoch": 0.97, "learning_rate": 1.5471459537572252e-05, "loss": 0.8258, "step": 5371 }, { "epoch": 0.97, "learning_rate": 1.546875e-05, "loss": 0.6959, "step": 5372 }, { "epoch": 0.97, "learning_rate": 1.5466040462427748e-05, "loss": 0.9247, "step": 5373 }, { "epoch": 0.97, "learning_rate": 1.5463330924855492e-05, "loss": 0.7627, "step": 5374 }, { "epoch": 0.97, "learning_rate": 1.5460621387283236e-05, "loss": 0.5654, "step": 5375 }, { "epoch": 0.97, "learning_rate": 1.545791184971098e-05, "loss": 0.5063, "step": 5376 }, { "epoch": 0.97, "learning_rate": 1.545520231213873e-05, "loss": 1.3171, "step": 5377 }, { "epoch": 0.97, "learning_rate": 1.5452492774566476e-05, "loss": 0.7852, "step": 5378 }, { "epoch": 0.97, "learning_rate": 1.544978323699422e-05, "loss": 0.67, "step": 5379 }, { "epoch": 0.97, "learning_rate": 1.5447073699421965e-05, "loss": 0.9518, "step": 5380 }, { "epoch": 0.97, "learning_rate": 1.544436416184971e-05, "loss": 0.3197, "step": 5381 }, { "epoch": 0.97, "learning_rate": 1.5441654624277457e-05, "loss": 0.5511, "step": 5382 }, { "epoch": 0.97, "learning_rate": 1.5438945086705205e-05, "loss": 0.829, "step": 5383 }, { "epoch": 0.97, "learning_rate": 1.543623554913295e-05, "loss": 0.7628, "step": 5384 }, { "epoch": 0.97, "learning_rate": 1.5433526011560694e-05, "loss": 0.674, "step": 5385 }, { "epoch": 0.97, "learning_rate": 1.5430816473988438e-05, "loss": 1.6478, "step": 5386 }, { "epoch": 0.97, "learning_rate": 1.5428106936416186e-05, "loss": 1.1389, "step": 5387 }, { "epoch": 0.97, "learning_rate": 1.5425397398843933e-05, "loss": 0.9901, "step": 5388 }, { "epoch": 0.97, "learning_rate": 1.5422687861271674e-05, "loss": 0.482, "step": 5389 }, { "epoch": 0.97, "learning_rate": 1.5419978323699422e-05, "loss": 0.5036, "step": 5390 }, { "epoch": 0.97, "learning_rate": 1.5417268786127167e-05, "loss": 0.659, "step": 5391 }, { "epoch": 0.97, "learning_rate": 1.5414559248554914e-05, "loss": 1.3318, "step": 5392 }, { "epoch": 0.97, "learning_rate": 1.5411849710982662e-05, "loss": 0.687, "step": 5393 }, { "epoch": 0.97, "learning_rate": 1.5409140173410403e-05, "loss": 0.8057, "step": 5394 }, { "epoch": 0.97, "learning_rate": 1.540643063583815e-05, "loss": 0.725, "step": 5395 }, { "epoch": 0.97, "learning_rate": 1.5403721098265895e-05, "loss": 0.5906, "step": 5396 }, { "epoch": 0.97, "learning_rate": 1.5401011560693643e-05, "loss": 1.1967, "step": 5397 }, { "epoch": 0.98, "learning_rate": 1.5398302023121387e-05, "loss": 0.9863, "step": 5398 }, { "epoch": 0.98, "learning_rate": 1.539559248554913e-05, "loss": 0.8754, "step": 5399 }, { "epoch": 0.98, "learning_rate": 1.539288294797688e-05, "loss": 0.75, "step": 5400 }, { "epoch": 0.98, "learning_rate": 1.5390173410404624e-05, "loss": 1.4566, "step": 5401 }, { "epoch": 0.98, "learning_rate": 1.538746387283237e-05, "loss": 0.6063, "step": 5402 }, { "epoch": 0.98, "learning_rate": 1.5384754335260116e-05, "loss": 1.3201, "step": 5403 }, { "epoch": 0.98, "learning_rate": 1.538204479768786e-05, "loss": 1.4215, "step": 5404 }, { "epoch": 0.98, "learning_rate": 1.5379335260115608e-05, "loss": 0.8849, "step": 5405 }, { "epoch": 0.98, "learning_rate": 1.5376625722543352e-05, "loss": 0.5732, "step": 5406 }, { "epoch": 0.98, "learning_rate": 1.53739161849711e-05, "loss": 0.6759, "step": 5407 }, { "epoch": 0.98, "learning_rate": 1.5371206647398844e-05, "loss": 0.8593, "step": 5408 }, { "epoch": 0.98, "learning_rate": 1.536849710982659e-05, "loss": 0.5013, "step": 5409 }, { "epoch": 0.98, "learning_rate": 1.5365787572254337e-05, "loss": 0.9456, "step": 5410 }, { "epoch": 0.98, "learning_rate": 1.536307803468208e-05, "loss": 0.8188, "step": 5411 }, { "epoch": 0.98, "learning_rate": 1.5360368497109825e-05, "loss": 0.5185, "step": 5412 }, { "epoch": 0.98, "learning_rate": 1.5357658959537573e-05, "loss": 0.5512, "step": 5413 }, { "epoch": 0.98, "learning_rate": 1.5354949421965317e-05, "loss": 1.0735, "step": 5414 }, { "epoch": 0.98, "learning_rate": 1.5352239884393065e-05, "loss": 1.5696, "step": 5415 }, { "epoch": 0.98, "learning_rate": 1.534953034682081e-05, "loss": 0.9923, "step": 5416 }, { "epoch": 0.98, "learning_rate": 1.5346820809248554e-05, "loss": 1.4619, "step": 5417 }, { "epoch": 0.98, "learning_rate": 1.5344111271676302e-05, "loss": 0.8622, "step": 5418 }, { "epoch": 0.98, "learning_rate": 1.5341401734104046e-05, "loss": 0.9701, "step": 5419 }, { "epoch": 0.98, "learning_rate": 1.5338692196531794e-05, "loss": 0.4867, "step": 5420 }, { "epoch": 0.98, "learning_rate": 1.5335982658959535e-05, "loss": 0.657, "step": 5421 }, { "epoch": 0.98, "learning_rate": 1.5333273121387283e-05, "loss": 0.7616, "step": 5422 }, { "epoch": 0.98, "learning_rate": 1.533056358381503e-05, "loss": 1.1357, "step": 5423 }, { "epoch": 0.98, "learning_rate": 1.5327854046242775e-05, "loss": 0.4021, "step": 5424 }, { "epoch": 0.98, "learning_rate": 1.5325144508670522e-05, "loss": 0.731, "step": 5425 }, { "epoch": 0.98, "learning_rate": 1.5322434971098263e-05, "loss": 0.9, "step": 5426 }, { "epoch": 0.98, "learning_rate": 1.531972543352601e-05, "loss": 0.6167, "step": 5427 }, { "epoch": 0.98, "learning_rate": 1.531701589595376e-05, "loss": 0.3712, "step": 5428 }, { "epoch": 0.98, "learning_rate": 1.5314306358381503e-05, "loss": 0.4718, "step": 5429 }, { "epoch": 0.98, "learning_rate": 1.531159682080925e-05, "loss": 1.1839, "step": 5430 }, { "epoch": 0.98, "learning_rate": 1.5308887283236992e-05, "loss": 0.9647, "step": 5431 }, { "epoch": 0.98, "learning_rate": 1.530617774566474e-05, "loss": 0.6645, "step": 5432 }, { "epoch": 0.98, "learning_rate": 1.5303468208092487e-05, "loss": 0.8818, "step": 5433 }, { "epoch": 0.98, "learning_rate": 1.5300758670520232e-05, "loss": 0.4282, "step": 5434 }, { "epoch": 0.98, "learning_rate": 1.5298049132947976e-05, "loss": 1.4755, "step": 5435 }, { "epoch": 0.98, "learning_rate": 1.529533959537572e-05, "loss": 0.6865, "step": 5436 }, { "epoch": 0.98, "learning_rate": 1.529263005780347e-05, "loss": 0.7167, "step": 5437 }, { "epoch": 0.98, "learning_rate": 1.5289920520231216e-05, "loss": 0.7035, "step": 5438 }, { "epoch": 0.98, "learning_rate": 1.528721098265896e-05, "loss": 1.1137, "step": 5439 }, { "epoch": 0.98, "learning_rate": 1.5284501445086705e-05, "loss": 0.8774, "step": 5440 }, { "epoch": 0.98, "learning_rate": 1.528179190751445e-05, "loss": 1.3242, "step": 5441 }, { "epoch": 0.98, "learning_rate": 1.5279082369942197e-05, "loss": 0.4288, "step": 5442 }, { "epoch": 0.98, "learning_rate": 1.5276372832369945e-05, "loss": 1.276, "step": 5443 }, { "epoch": 0.98, "learning_rate": 1.5273663294797686e-05, "loss": 0.3421, "step": 5444 }, { "epoch": 0.98, "learning_rate": 1.5270953757225433e-05, "loss": 0.8562, "step": 5445 }, { "epoch": 0.98, "learning_rate": 1.5268244219653178e-05, "loss": 0.9402, "step": 5446 }, { "epoch": 0.98, "learning_rate": 1.5265534682080926e-05, "loss": 0.8761, "step": 5447 }, { "epoch": 0.98, "learning_rate": 1.5262825144508673e-05, "loss": 0.8511, "step": 5448 }, { "epoch": 0.98, "learning_rate": 1.5260115606936414e-05, "loss": 0.7466, "step": 5449 }, { "epoch": 0.98, "learning_rate": 1.5257406069364162e-05, "loss": 0.5957, "step": 5450 }, { "epoch": 0.98, "learning_rate": 1.5254696531791906e-05, "loss": 0.7075, "step": 5451 }, { "epoch": 0.98, "learning_rate": 1.5251986994219652e-05, "loss": 0.5021, "step": 5452 }, { "epoch": 0.99, "learning_rate": 1.52492774566474e-05, "loss": 0.9094, "step": 5453 }, { "epoch": 0.99, "learning_rate": 1.5246567919075145e-05, "loss": 0.9439, "step": 5454 }, { "epoch": 0.99, "learning_rate": 1.524385838150289e-05, "loss": 0.8477, "step": 5455 }, { "epoch": 0.99, "learning_rate": 1.5241148843930635e-05, "loss": 1.0243, "step": 5456 }, { "epoch": 0.99, "learning_rate": 1.5238439306358381e-05, "loss": 1.2709, "step": 5457 }, { "epoch": 0.99, "learning_rate": 1.5235729768786129e-05, "loss": 0.5743, "step": 5458 }, { "epoch": 0.99, "learning_rate": 1.5233020231213871e-05, "loss": 0.4949, "step": 5459 }, { "epoch": 0.99, "learning_rate": 1.523031069364162e-05, "loss": 0.3424, "step": 5460 }, { "epoch": 0.99, "learning_rate": 1.5227601156069367e-05, "loss": 0.9029, "step": 5461 }, { "epoch": 0.99, "learning_rate": 1.522489161849711e-05, "loss": 0.6564, "step": 5462 }, { "epoch": 0.99, "learning_rate": 1.5222182080924857e-05, "loss": 1.1936, "step": 5463 }, { "epoch": 0.99, "learning_rate": 1.52194725433526e-05, "loss": 0.8974, "step": 5464 }, { "epoch": 0.99, "learning_rate": 1.5216763005780348e-05, "loss": 0.5226, "step": 5465 }, { "epoch": 0.99, "learning_rate": 1.5214053468208094e-05, "loss": 0.7847, "step": 5466 }, { "epoch": 0.99, "learning_rate": 1.5211343930635838e-05, "loss": 0.6212, "step": 5467 }, { "epoch": 0.99, "learning_rate": 1.5208634393063584e-05, "loss": 0.8907, "step": 5468 }, { "epoch": 0.99, "learning_rate": 1.5205924855491329e-05, "loss": 1.213, "step": 5469 }, { "epoch": 0.99, "learning_rate": 1.5203215317919076e-05, "loss": 0.2024, "step": 5470 }, { "epoch": 0.99, "learning_rate": 1.5200505780346822e-05, "loss": 1.1826, "step": 5471 }, { "epoch": 0.99, "learning_rate": 1.5197796242774567e-05, "loss": 0.3896, "step": 5472 }, { "epoch": 0.99, "learning_rate": 1.5195086705202313e-05, "loss": 0.3695, "step": 5473 }, { "epoch": 0.99, "learning_rate": 1.5192377167630057e-05, "loss": 0.8305, "step": 5474 }, { "epoch": 0.99, "learning_rate": 1.5189667630057803e-05, "loss": 1.6088, "step": 5475 }, { "epoch": 0.99, "learning_rate": 1.5186958092485551e-05, "loss": 0.4124, "step": 5476 }, { "epoch": 0.99, "learning_rate": 1.5184248554913295e-05, "loss": 0.6376, "step": 5477 }, { "epoch": 0.99, "learning_rate": 1.5181539017341042e-05, "loss": 1.1855, "step": 5478 }, { "epoch": 0.99, "learning_rate": 1.5178829479768786e-05, "loss": 0.8927, "step": 5479 }, { "epoch": 0.99, "learning_rate": 1.5176119942196532e-05, "loss": 1.1419, "step": 5480 }, { "epoch": 0.99, "learning_rate": 1.517341040462428e-05, "loss": 0.5509, "step": 5481 }, { "epoch": 0.99, "learning_rate": 1.5170700867052022e-05, "loss": 0.783, "step": 5482 }, { "epoch": 0.99, "learning_rate": 1.516799132947977e-05, "loss": 0.8683, "step": 5483 }, { "epoch": 0.99, "learning_rate": 1.5165281791907514e-05, "loss": 1.0221, "step": 5484 }, { "epoch": 0.99, "learning_rate": 1.516257225433526e-05, "loss": 0.7639, "step": 5485 }, { "epoch": 0.99, "learning_rate": 1.5159862716763008e-05, "loss": 1.0526, "step": 5486 }, { "epoch": 0.99, "learning_rate": 1.5157153179190751e-05, "loss": 0.7353, "step": 5487 }, { "epoch": 0.99, "learning_rate": 1.5154443641618499e-05, "loss": 0.4726, "step": 5488 }, { "epoch": 0.99, "learning_rate": 1.5151734104046241e-05, "loss": 0.3029, "step": 5489 }, { "epoch": 0.99, "learning_rate": 1.5149024566473989e-05, "loss": 0.7014, "step": 5490 }, { "epoch": 0.99, "learning_rate": 1.5146315028901735e-05, "loss": 0.3177, "step": 5491 }, { "epoch": 0.99, "learning_rate": 1.514360549132948e-05, "loss": 0.6065, "step": 5492 }, { "epoch": 0.99, "learning_rate": 1.5140895953757227e-05, "loss": 1.1538, "step": 5493 }, { "epoch": 0.99, "learning_rate": 1.513818641618497e-05, "loss": 1.0387, "step": 5494 }, { "epoch": 0.99, "learning_rate": 1.5135476878612718e-05, "loss": 0.4254, "step": 5495 }, { "epoch": 0.99, "learning_rate": 1.5132767341040464e-05, "loss": 0.7247, "step": 5496 }, { "epoch": 0.99, "learning_rate": 1.5130057803468208e-05, "loss": 0.5098, "step": 5497 }, { "epoch": 0.99, "learning_rate": 1.5127348265895954e-05, "loss": 0.8526, "step": 5498 }, { "epoch": 0.99, "learning_rate": 1.5124638728323699e-05, "loss": 0.3178, "step": 5499 }, { "epoch": 0.99, "learning_rate": 1.5121929190751446e-05, "loss": 0.2889, "step": 5500 }, { "epoch": 0.99, "eval_exact_match": 87.51182592242195, "eval_f1": 93.60990494898797, "step": 5500 }, { "epoch": 0.99, "learning_rate": 1.5119219653179192e-05, "loss": 0.3124, "step": 5501 }, { "epoch": 0.99, "learning_rate": 1.5116510115606937e-05, "loss": 0.587, "step": 5502 }, { "epoch": 0.99, "learning_rate": 1.5113800578034683e-05, "loss": 0.7073, "step": 5503 }, { "epoch": 0.99, "learning_rate": 1.5111091040462427e-05, "loss": 1.3425, "step": 5504 }, { "epoch": 0.99, "learning_rate": 1.5108381502890173e-05, "loss": 0.8771, "step": 5505 }, { "epoch": 0.99, "learning_rate": 1.5105671965317921e-05, "loss": 0.837, "step": 5506 }, { "epoch": 0.99, "learning_rate": 1.5102962427745665e-05, "loss": 0.3161, "step": 5507 }, { "epoch": 0.99, "learning_rate": 1.5100252890173411e-05, "loss": 0.5471, "step": 5508 }, { "epoch": 1.0, "learning_rate": 1.5097543352601156e-05, "loss": 0.8675, "step": 5509 }, { "epoch": 1.0, "learning_rate": 1.5094833815028902e-05, "loss": 0.6999, "step": 5510 }, { "epoch": 1.0, "learning_rate": 1.509212427745665e-05, "loss": 0.4374, "step": 5511 }, { "epoch": 1.0, "learning_rate": 1.5089414739884392e-05, "loss": 0.4116, "step": 5512 }, { "epoch": 1.0, "learning_rate": 1.508670520231214e-05, "loss": 0.9195, "step": 5513 }, { "epoch": 1.0, "learning_rate": 1.5083995664739884e-05, "loss": 0.3774, "step": 5514 }, { "epoch": 1.0, "learning_rate": 1.508128612716763e-05, "loss": 1.2953, "step": 5515 }, { "epoch": 1.0, "learning_rate": 1.5078576589595378e-05, "loss": 0.6327, "step": 5516 }, { "epoch": 1.0, "learning_rate": 1.5075867052023121e-05, "loss": 0.4356, "step": 5517 }, { "epoch": 1.0, "learning_rate": 1.5073157514450869e-05, "loss": 1.5651, "step": 5518 }, { "epoch": 1.0, "learning_rate": 1.5070447976878611e-05, "loss": 0.9828, "step": 5519 }, { "epoch": 1.0, "learning_rate": 1.5067738439306359e-05, "loss": 0.4813, "step": 5520 }, { "epoch": 1.0, "learning_rate": 1.5065028901734105e-05, "loss": 0.7368, "step": 5521 }, { "epoch": 1.0, "learning_rate": 1.506231936416185e-05, "loss": 0.7663, "step": 5522 }, { "epoch": 1.0, "learning_rate": 1.5059609826589597e-05, "loss": 0.6706, "step": 5523 }, { "epoch": 1.0, "learning_rate": 1.505690028901734e-05, "loss": 0.7546, "step": 5524 }, { "epoch": 1.0, "learning_rate": 1.5054190751445088e-05, "loss": 1.0694, "step": 5525 }, { "epoch": 1.0, "learning_rate": 1.5051481213872834e-05, "loss": 0.794, "step": 5526 }, { "epoch": 1.0, "learning_rate": 1.5048771676300578e-05, "loss": 0.3416, "step": 5527 }, { "epoch": 1.0, "learning_rate": 1.5046062138728324e-05, "loss": 0.5033, "step": 5528 }, { "epoch": 1.0, "learning_rate": 1.5043352601156069e-05, "loss": 0.973, "step": 5529 }, { "epoch": 1.0, "learning_rate": 1.5040643063583816e-05, "loss": 1.1651, "step": 5530 }, { "epoch": 1.0, "learning_rate": 1.5037933526011562e-05, "loss": 0.9003, "step": 5531 }, { "epoch": 1.0, "learning_rate": 1.5035223988439307e-05, "loss": 0.7087, "step": 5532 }, { "epoch": 1.0, "learning_rate": 1.5032514450867053e-05, "loss": 0.7878, "step": 5533 }, { "epoch": 1.0, "learning_rate": 1.5029804913294797e-05, "loss": 0.6833, "step": 5534 }, { "epoch": 1.0, "learning_rate": 1.5027095375722543e-05, "loss": 0.8128, "step": 5535 }, { "epoch": 1.0, "learning_rate": 1.5024385838150291e-05, "loss": 1.9372, "step": 5536 }, { "epoch": 1.0, "learning_rate": 1.5021676300578034e-05, "loss": 0.5943, "step": 5537 }, { "epoch": 1.0, "learning_rate": 1.5018966763005781e-05, "loss": 0.796, "step": 5538 }, { "epoch": 1.0, "learning_rate": 1.5016257225433526e-05, "loss": 0.2775, "step": 5539 }, { "epoch": 1.0, "learning_rate": 1.5013547687861272e-05, "loss": 0.6199, "step": 5540 }, { "epoch": 1.0, "learning_rate": 1.501083815028902e-05, "loss": 0.354, "step": 5541 }, { "epoch": 1.0, "learning_rate": 1.5008128612716762e-05, "loss": 0.3919, "step": 5542 }, { "epoch": 1.0, "learning_rate": 1.500541907514451e-05, "loss": 0.8627, "step": 5543 }, { "epoch": 1.0, "learning_rate": 1.5002709537572253e-05, "loss": 0.4599, "step": 5544 }, { "epoch": 1.0, "learning_rate": 1.5e-05, "loss": 0.6333, "step": 5545 }, { "epoch": 1.0, "learning_rate": 1.4997290462427746e-05, "loss": 0.2964, "step": 5546 }, { "epoch": 1.0, "learning_rate": 1.499458092485549e-05, "loss": 0.3659, "step": 5547 }, { "epoch": 1.0, "learning_rate": 1.4991871387283239e-05, "loss": 0.761, "step": 5548 }, { "epoch": 1.0, "learning_rate": 1.4989161849710983e-05, "loss": 0.443, "step": 5549 }, { "epoch": 1.0, "learning_rate": 1.4986452312138729e-05, "loss": 0.587, "step": 5550 }, { "epoch": 1.0, "learning_rate": 1.4983742774566473e-05, "loss": 0.4152, "step": 5551 }, { "epoch": 1.0, "learning_rate": 1.498103323699422e-05, "loss": 0.2567, "step": 5552 }, { "epoch": 1.0, "learning_rate": 1.4978323699421967e-05, "loss": 0.4222, "step": 5553 }, { "epoch": 1.0, "learning_rate": 1.4975614161849712e-05, "loss": 0.289, "step": 5554 }, { "epoch": 1.0, "learning_rate": 1.4972904624277458e-05, "loss": 0.4398, "step": 5555 }, { "epoch": 1.0, "learning_rate": 1.4970195086705202e-05, "loss": 0.7994, "step": 5556 }, { "epoch": 1.0, "learning_rate": 1.4967485549132948e-05, "loss": 0.7571, "step": 5557 }, { "epoch": 1.0, "learning_rate": 1.4964776011560694e-05, "loss": 0.6255, "step": 5558 }, { "epoch": 1.0, "learning_rate": 1.496206647398844e-05, "loss": 0.3911, "step": 5559 }, { "epoch": 1.0, "learning_rate": 1.4959356936416184e-05, "loss": 0.903, "step": 5560 }, { "epoch": 1.0, "learning_rate": 1.495664739884393e-05, "loss": 0.3668, "step": 5561 }, { "epoch": 1.0, "learning_rate": 1.4953937861271677e-05, "loss": 0.8988, "step": 5562 }, { "epoch": 1.0, "learning_rate": 1.4951228323699423e-05, "loss": 1.6669, "step": 5563 }, { "epoch": 1.01, "learning_rate": 1.4948518786127169e-05, "loss": 0.8995, "step": 5564 }, { "epoch": 1.01, "learning_rate": 1.4945809248554913e-05, "loss": 0.66, "step": 5565 }, { "epoch": 1.01, "learning_rate": 1.4943099710982659e-05, "loss": 0.6031, "step": 5566 }, { "epoch": 1.01, "learning_rate": 1.4940390173410404e-05, "loss": 0.5489, "step": 5567 }, { "epoch": 1.01, "learning_rate": 1.4937680635838151e-05, "loss": 0.9498, "step": 5568 }, { "epoch": 1.01, "learning_rate": 1.4934971098265897e-05, "loss": 0.3063, "step": 5569 }, { "epoch": 1.01, "learning_rate": 1.4932261560693642e-05, "loss": 0.25, "step": 5570 }, { "epoch": 1.01, "learning_rate": 1.4929552023121388e-05, "loss": 0.9145, "step": 5571 }, { "epoch": 1.01, "learning_rate": 1.4926842485549132e-05, "loss": 0.2842, "step": 5572 }, { "epoch": 1.01, "learning_rate": 1.492413294797688e-05, "loss": 0.5511, "step": 5573 }, { "epoch": 1.01, "learning_rate": 1.4921423410404624e-05, "loss": 0.9655, "step": 5574 }, { "epoch": 1.01, "learning_rate": 1.491871387283237e-05, "loss": 0.4008, "step": 5575 }, { "epoch": 1.01, "learning_rate": 1.4916004335260116e-05, "loss": 0.3667, "step": 5576 }, { "epoch": 1.01, "learning_rate": 1.491329479768786e-05, "loss": 0.7428, "step": 5577 }, { "epoch": 1.01, "learning_rate": 1.4910585260115608e-05, "loss": 0.3607, "step": 5578 }, { "epoch": 1.01, "learning_rate": 1.4907875722543353e-05, "loss": 0.7237, "step": 5579 }, { "epoch": 1.01, "learning_rate": 1.4905166184971099e-05, "loss": 0.7257, "step": 5580 }, { "epoch": 1.01, "learning_rate": 1.4902456647398843e-05, "loss": 0.3057, "step": 5581 }, { "epoch": 1.01, "learning_rate": 1.489974710982659e-05, "loss": 0.5207, "step": 5582 }, { "epoch": 1.01, "learning_rate": 1.4897037572254335e-05, "loss": 0.4496, "step": 5583 }, { "epoch": 1.01, "learning_rate": 1.4894328034682081e-05, "loss": 0.4444, "step": 5584 }, { "epoch": 1.01, "learning_rate": 1.4891618497109827e-05, "loss": 1.0105, "step": 5585 }, { "epoch": 1.01, "learning_rate": 1.4888908959537572e-05, "loss": 0.6479, "step": 5586 }, { "epoch": 1.01, "learning_rate": 1.4886199421965318e-05, "loss": 0.5476, "step": 5587 }, { "epoch": 1.01, "learning_rate": 1.4883489884393064e-05, "loss": 1.299, "step": 5588 }, { "epoch": 1.01, "learning_rate": 1.488078034682081e-05, "loss": 0.577, "step": 5589 }, { "epoch": 1.01, "learning_rate": 1.4878070809248554e-05, "loss": 0.6722, "step": 5590 }, { "epoch": 1.01, "learning_rate": 1.48753612716763e-05, "loss": 0.1359, "step": 5591 }, { "epoch": 1.01, "learning_rate": 1.4872651734104048e-05, "loss": 0.4482, "step": 5592 }, { "epoch": 1.01, "learning_rate": 1.4869942196531793e-05, "loss": 0.8694, "step": 5593 }, { "epoch": 1.01, "learning_rate": 1.4867232658959539e-05, "loss": 0.3036, "step": 5594 }, { "epoch": 1.01, "learning_rate": 1.4864523121387283e-05, "loss": 0.3506, "step": 5595 }, { "epoch": 1.01, "learning_rate": 1.4861813583815029e-05, "loss": 0.3146, "step": 5596 }, { "epoch": 1.01, "learning_rate": 1.4859104046242775e-05, "loss": 0.4972, "step": 5597 }, { "epoch": 1.01, "learning_rate": 1.4856394508670521e-05, "loss": 0.1788, "step": 5598 }, { "epoch": 1.01, "learning_rate": 1.4853684971098267e-05, "loss": 0.6828, "step": 5599 }, { "epoch": 1.01, "learning_rate": 1.4850975433526012e-05, "loss": 0.5555, "step": 5600 }, { "epoch": 1.01, "learning_rate": 1.4848265895953758e-05, "loss": 0.5476, "step": 5601 }, { "epoch": 1.01, "learning_rate": 1.4845556358381504e-05, "loss": 0.4324, "step": 5602 }, { "epoch": 1.01, "learning_rate": 1.484284682080925e-05, "loss": 0.4966, "step": 5603 }, { "epoch": 1.01, "learning_rate": 1.4840137283236994e-05, "loss": 0.5149, "step": 5604 }, { "epoch": 1.01, "learning_rate": 1.483742774566474e-05, "loss": 0.5224, "step": 5605 }, { "epoch": 1.01, "learning_rate": 1.4834718208092485e-05, "loss": 0.265, "step": 5606 }, { "epoch": 1.01, "learning_rate": 1.4832008670520232e-05, "loss": 0.7612, "step": 5607 }, { "epoch": 1.01, "learning_rate": 1.4829299132947978e-05, "loss": 0.6607, "step": 5608 }, { "epoch": 1.01, "learning_rate": 1.4826589595375723e-05, "loss": 0.5509, "step": 5609 }, { "epoch": 1.01, "learning_rate": 1.4823880057803469e-05, "loss": 0.4625, "step": 5610 }, { "epoch": 1.01, "learning_rate": 1.4821170520231213e-05, "loss": 0.349, "step": 5611 }, { "epoch": 1.01, "learning_rate": 1.4818460982658961e-05, "loss": 0.4823, "step": 5612 }, { "epoch": 1.01, "learning_rate": 1.4815751445086705e-05, "loss": 0.8717, "step": 5613 }, { "epoch": 1.01, "learning_rate": 1.4813041907514451e-05, "loss": 0.7324, "step": 5614 }, { "epoch": 1.01, "learning_rate": 1.4810332369942197e-05, "loss": 0.6032, "step": 5615 }, { "epoch": 1.01, "learning_rate": 1.4807622832369942e-05, "loss": 1.4953, "step": 5616 }, { "epoch": 1.01, "learning_rate": 1.480491329479769e-05, "loss": 0.2649, "step": 5617 }, { "epoch": 1.01, "learning_rate": 1.4802203757225434e-05, "loss": 0.4394, "step": 5618 }, { "epoch": 1.01, "learning_rate": 1.479949421965318e-05, "loss": 1.0144, "step": 5619 }, { "epoch": 1.02, "learning_rate": 1.4796784682080924e-05, "loss": 0.2963, "step": 5620 }, { "epoch": 1.02, "learning_rate": 1.479407514450867e-05, "loss": 0.7798, "step": 5621 }, { "epoch": 1.02, "learning_rate": 1.4791365606936416e-05, "loss": 0.6475, "step": 5622 }, { "epoch": 1.02, "learning_rate": 1.4788656069364162e-05, "loss": 0.5369, "step": 5623 }, { "epoch": 1.02, "learning_rate": 1.4785946531791909e-05, "loss": 1.3131, "step": 5624 }, { "epoch": 1.02, "learning_rate": 1.4783236994219653e-05, "loss": 0.5058, "step": 5625 }, { "epoch": 1.02, "learning_rate": 1.4780527456647399e-05, "loss": 0.2166, "step": 5626 }, { "epoch": 1.02, "learning_rate": 1.4777817919075145e-05, "loss": 0.5056, "step": 5627 }, { "epoch": 1.02, "learning_rate": 1.4775108381502891e-05, "loss": 0.4719, "step": 5628 }, { "epoch": 1.02, "learning_rate": 1.4772398843930635e-05, "loss": 0.3474, "step": 5629 }, { "epoch": 1.02, "learning_rate": 1.4769689306358382e-05, "loss": 0.587, "step": 5630 }, { "epoch": 1.02, "learning_rate": 1.4766979768786128e-05, "loss": 0.4507, "step": 5631 }, { "epoch": 1.02, "learning_rate": 1.4764270231213874e-05, "loss": 0.3868, "step": 5632 }, { "epoch": 1.02, "learning_rate": 1.476156069364162e-05, "loss": 0.7061, "step": 5633 }, { "epoch": 1.02, "learning_rate": 1.4758851156069364e-05, "loss": 0.4667, "step": 5634 }, { "epoch": 1.02, "learning_rate": 1.475614161849711e-05, "loss": 0.8543, "step": 5635 }, { "epoch": 1.02, "learning_rate": 1.4753432080924854e-05, "loss": 1.1625, "step": 5636 }, { "epoch": 1.02, "learning_rate": 1.4750722543352602e-05, "loss": 0.4383, "step": 5637 }, { "epoch": 1.02, "learning_rate": 1.4748013005780348e-05, "loss": 0.6427, "step": 5638 }, { "epoch": 1.02, "learning_rate": 1.4745303468208093e-05, "loss": 0.4659, "step": 5639 }, { "epoch": 1.02, "learning_rate": 1.4742593930635839e-05, "loss": 0.4145, "step": 5640 }, { "epoch": 1.02, "learning_rate": 1.4739884393063583e-05, "loss": 1.0544, "step": 5641 }, { "epoch": 1.02, "learning_rate": 1.473717485549133e-05, "loss": 0.3618, "step": 5642 }, { "epoch": 1.02, "learning_rate": 1.4734465317919075e-05, "loss": 0.9143, "step": 5643 }, { "epoch": 1.02, "learning_rate": 1.4731755780346821e-05, "loss": 0.3264, "step": 5644 }, { "epoch": 1.02, "learning_rate": 1.4729046242774566e-05, "loss": 0.5181, "step": 5645 }, { "epoch": 1.02, "learning_rate": 1.4726336705202312e-05, "loss": 0.3472, "step": 5646 }, { "epoch": 1.02, "learning_rate": 1.472362716763006e-05, "loss": 1.0891, "step": 5647 }, { "epoch": 1.02, "learning_rate": 1.4720917630057804e-05, "loss": 0.3418, "step": 5648 }, { "epoch": 1.02, "learning_rate": 1.471820809248555e-05, "loss": 0.3452, "step": 5649 }, { "epoch": 1.02, "learning_rate": 1.4715498554913294e-05, "loss": 0.3135, "step": 5650 }, { "epoch": 1.02, "learning_rate": 1.471278901734104e-05, "loss": 0.915, "step": 5651 }, { "epoch": 1.02, "learning_rate": 1.4710079479768786e-05, "loss": 0.6471, "step": 5652 }, { "epoch": 1.02, "learning_rate": 1.4707369942196532e-05, "loss": 0.6457, "step": 5653 }, { "epoch": 1.02, "learning_rate": 1.4704660404624278e-05, "loss": 0.2645, "step": 5654 }, { "epoch": 1.02, "learning_rate": 1.4701950867052023e-05, "loss": 0.3288, "step": 5655 }, { "epoch": 1.02, "learning_rate": 1.4699241329479769e-05, "loss": 0.2255, "step": 5656 }, { "epoch": 1.02, "learning_rate": 1.4696531791907515e-05, "loss": 0.5628, "step": 5657 }, { "epoch": 1.02, "learning_rate": 1.4693822254335261e-05, "loss": 0.3933, "step": 5658 }, { "epoch": 1.02, "learning_rate": 1.4691112716763005e-05, "loss": 0.2577, "step": 5659 }, { "epoch": 1.02, "learning_rate": 1.4688403179190751e-05, "loss": 0.7555, "step": 5660 }, { "epoch": 1.02, "learning_rate": 1.4685693641618497e-05, "loss": 0.9592, "step": 5661 }, { "epoch": 1.02, "learning_rate": 1.4682984104046244e-05, "loss": 0.333, "step": 5662 }, { "epoch": 1.02, "learning_rate": 1.468027456647399e-05, "loss": 0.8188, "step": 5663 }, { "epoch": 1.02, "learning_rate": 1.4677565028901734e-05, "loss": 0.7405, "step": 5664 }, { "epoch": 1.02, "learning_rate": 1.467485549132948e-05, "loss": 0.9991, "step": 5665 }, { "epoch": 1.02, "learning_rate": 1.4672145953757224e-05, "loss": 0.3216, "step": 5666 }, { "epoch": 1.02, "learning_rate": 1.4669436416184972e-05, "loss": 0.5056, "step": 5667 }, { "epoch": 1.02, "learning_rate": 1.4666726878612717e-05, "loss": 0.4465, "step": 5668 }, { "epoch": 1.02, "learning_rate": 1.4664017341040463e-05, "loss": 0.9668, "step": 5669 }, { "epoch": 1.02, "learning_rate": 1.4661307803468209e-05, "loss": 0.7403, "step": 5670 }, { "epoch": 1.02, "learning_rate": 1.4658598265895953e-05, "loss": 0.3133, "step": 5671 }, { "epoch": 1.02, "learning_rate": 1.46558887283237e-05, "loss": 0.5505, "step": 5672 }, { "epoch": 1.02, "learning_rate": 1.4653179190751445e-05, "loss": 0.4103, "step": 5673 }, { "epoch": 1.02, "learning_rate": 1.4650469653179191e-05, "loss": 1.0607, "step": 5674 }, { "epoch": 1.03, "learning_rate": 1.4647760115606936e-05, "loss": 0.8339, "step": 5675 }, { "epoch": 1.03, "learning_rate": 1.4645050578034683e-05, "loss": 0.4099, "step": 5676 }, { "epoch": 1.03, "learning_rate": 1.464234104046243e-05, "loss": 0.3195, "step": 5677 }, { "epoch": 1.03, "learning_rate": 1.4639631502890174e-05, "loss": 0.3527, "step": 5678 }, { "epoch": 1.03, "learning_rate": 1.463692196531792e-05, "loss": 0.9178, "step": 5679 }, { "epoch": 1.03, "learning_rate": 1.4634212427745664e-05, "loss": 0.362, "step": 5680 }, { "epoch": 1.03, "learning_rate": 1.4631502890173412e-05, "loss": 0.4409, "step": 5681 }, { "epoch": 1.03, "learning_rate": 1.4628793352601156e-05, "loss": 0.752, "step": 5682 }, { "epoch": 1.03, "learning_rate": 1.4626083815028902e-05, "loss": 0.6233, "step": 5683 }, { "epoch": 1.03, "learning_rate": 1.4623374277456648e-05, "loss": 0.8139, "step": 5684 }, { "epoch": 1.03, "learning_rate": 1.4620664739884393e-05, "loss": 0.3746, "step": 5685 }, { "epoch": 1.03, "learning_rate": 1.461795520231214e-05, "loss": 0.7902, "step": 5686 }, { "epoch": 1.03, "learning_rate": 1.4615245664739885e-05, "loss": 0.9851, "step": 5687 }, { "epoch": 1.03, "learning_rate": 1.4612536127167631e-05, "loss": 0.4083, "step": 5688 }, { "epoch": 1.03, "learning_rate": 1.4609826589595375e-05, "loss": 0.7145, "step": 5689 }, { "epoch": 1.03, "learning_rate": 1.4607117052023121e-05, "loss": 0.3204, "step": 5690 }, { "epoch": 1.03, "learning_rate": 1.4604407514450867e-05, "loss": 0.7372, "step": 5691 }, { "epoch": 1.03, "learning_rate": 1.4601697976878613e-05, "loss": 0.5539, "step": 5692 }, { "epoch": 1.03, "learning_rate": 1.459898843930636e-05, "loss": 0.6331, "step": 5693 }, { "epoch": 1.03, "learning_rate": 1.4596278901734104e-05, "loss": 0.4423, "step": 5694 }, { "epoch": 1.03, "learning_rate": 1.459356936416185e-05, "loss": 0.6148, "step": 5695 }, { "epoch": 1.03, "learning_rate": 1.4590859826589596e-05, "loss": 0.5082, "step": 5696 }, { "epoch": 1.03, "learning_rate": 1.4588150289017342e-05, "loss": 0.455, "step": 5697 }, { "epoch": 1.03, "learning_rate": 1.4585440751445086e-05, "loss": 0.2849, "step": 5698 }, { "epoch": 1.03, "learning_rate": 1.4582731213872832e-05, "loss": 0.7833, "step": 5699 }, { "epoch": 1.03, "learning_rate": 1.4580021676300579e-05, "loss": 0.7301, "step": 5700 }, { "epoch": 1.03, "learning_rate": 1.4577312138728325e-05, "loss": 0.2339, "step": 5701 }, { "epoch": 1.03, "learning_rate": 1.457460260115607e-05, "loss": 0.2725, "step": 5702 }, { "epoch": 1.03, "learning_rate": 1.4571893063583815e-05, "loss": 0.6136, "step": 5703 }, { "epoch": 1.03, "learning_rate": 1.4569183526011561e-05, "loss": 0.6626, "step": 5704 }, { "epoch": 1.03, "learning_rate": 1.4566473988439305e-05, "loss": 0.3855, "step": 5705 }, { "epoch": 1.03, "learning_rate": 1.4563764450867053e-05, "loss": 0.3858, "step": 5706 }, { "epoch": 1.03, "learning_rate": 1.45610549132948e-05, "loss": 0.8053, "step": 5707 }, { "epoch": 1.03, "learning_rate": 1.4558345375722544e-05, "loss": 0.76, "step": 5708 }, { "epoch": 1.03, "learning_rate": 1.455563583815029e-05, "loss": 0.5595, "step": 5709 }, { "epoch": 1.03, "learning_rate": 1.4552926300578034e-05, "loss": 0.4864, "step": 5710 }, { "epoch": 1.03, "learning_rate": 1.4550216763005782e-05, "loss": 0.3174, "step": 5711 }, { "epoch": 1.03, "learning_rate": 1.4547507225433526e-05, "loss": 0.4656, "step": 5712 }, { "epoch": 1.03, "learning_rate": 1.4544797687861272e-05, "loss": 0.5537, "step": 5713 }, { "epoch": 1.03, "learning_rate": 1.4542088150289017e-05, "loss": 0.32, "step": 5714 }, { "epoch": 1.03, "learning_rate": 1.4539378612716763e-05, "loss": 0.4986, "step": 5715 }, { "epoch": 1.03, "learning_rate": 1.453666907514451e-05, "loss": 0.4475, "step": 5716 }, { "epoch": 1.03, "learning_rate": 1.4533959537572255e-05, "loss": 0.4045, "step": 5717 }, { "epoch": 1.03, "learning_rate": 1.453125e-05, "loss": 0.6804, "step": 5718 }, { "epoch": 1.03, "learning_rate": 1.4528540462427745e-05, "loss": 0.3596, "step": 5719 }, { "epoch": 1.03, "learning_rate": 1.4525830924855491e-05, "loss": 0.4651, "step": 5720 }, { "epoch": 1.03, "learning_rate": 1.4523121387283237e-05, "loss": 0.8383, "step": 5721 }, { "epoch": 1.03, "learning_rate": 1.4520411849710983e-05, "loss": 0.2224, "step": 5722 }, { "epoch": 1.03, "learning_rate": 1.451770231213873e-05, "loss": 0.4493, "step": 5723 }, { "epoch": 1.03, "learning_rate": 1.4514992774566474e-05, "loss": 0.4526, "step": 5724 }, { "epoch": 1.03, "learning_rate": 1.451228323699422e-05, "loss": 0.7961, "step": 5725 }, { "epoch": 1.03, "learning_rate": 1.4509573699421966e-05, "loss": 1.1197, "step": 5726 }, { "epoch": 1.03, "learning_rate": 1.4506864161849712e-05, "loss": 0.546, "step": 5727 }, { "epoch": 1.03, "learning_rate": 1.4504154624277456e-05, "loss": 0.8723, "step": 5728 }, { "epoch": 1.03, "learning_rate": 1.4501445086705202e-05, "loss": 0.4745, "step": 5729 }, { "epoch": 1.04, "learning_rate": 1.4498735549132948e-05, "loss": 0.5917, "step": 5730 }, { "epoch": 1.04, "learning_rate": 1.4496026011560695e-05, "loss": 0.5407, "step": 5731 }, { "epoch": 1.04, "learning_rate": 1.449331647398844e-05, "loss": 0.329, "step": 5732 }, { "epoch": 1.04, "learning_rate": 1.4490606936416185e-05, "loss": 0.2867, "step": 5733 }, { "epoch": 1.04, "learning_rate": 1.4487897398843931e-05, "loss": 0.683, "step": 5734 }, { "epoch": 1.04, "learning_rate": 1.4485187861271675e-05, "loss": 0.6485, "step": 5735 }, { "epoch": 1.04, "learning_rate": 1.4482478323699423e-05, "loss": 0.3902, "step": 5736 }, { "epoch": 1.04, "learning_rate": 1.4479768786127167e-05, "loss": 0.8535, "step": 5737 }, { "epoch": 1.04, "learning_rate": 1.4477059248554914e-05, "loss": 0.5059, "step": 5738 }, { "epoch": 1.04, "learning_rate": 1.447434971098266e-05, "loss": 0.485, "step": 5739 }, { "epoch": 1.04, "learning_rate": 1.4471640173410404e-05, "loss": 1.0857, "step": 5740 }, { "epoch": 1.04, "learning_rate": 1.4468930635838152e-05, "loss": 0.4595, "step": 5741 }, { "epoch": 1.04, "learning_rate": 1.4466221098265896e-05, "loss": 0.3341, "step": 5742 }, { "epoch": 1.04, "learning_rate": 1.4463511560693642e-05, "loss": 0.738, "step": 5743 }, { "epoch": 1.04, "learning_rate": 1.4460802023121387e-05, "loss": 0.4787, "step": 5744 }, { "epoch": 1.04, "learning_rate": 1.4458092485549133e-05, "loss": 0.6072, "step": 5745 }, { "epoch": 1.04, "learning_rate": 1.445538294797688e-05, "loss": 1.2293, "step": 5746 }, { "epoch": 1.04, "learning_rate": 1.4452673410404625e-05, "loss": 0.606, "step": 5747 }, { "epoch": 1.04, "learning_rate": 1.444996387283237e-05, "loss": 0.6296, "step": 5748 }, { "epoch": 1.04, "learning_rate": 1.4447254335260115e-05, "loss": 0.3587, "step": 5749 }, { "epoch": 1.04, "learning_rate": 1.4444544797687861e-05, "loss": 0.6079, "step": 5750 }, { "epoch": 1.04, "learning_rate": 1.4441835260115607e-05, "loss": 0.6566, "step": 5751 }, { "epoch": 1.04, "learning_rate": 1.4439125722543353e-05, "loss": 0.3996, "step": 5752 }, { "epoch": 1.04, "learning_rate": 1.4436416184971098e-05, "loss": 0.6913, "step": 5753 }, { "epoch": 1.04, "learning_rate": 1.4433706647398844e-05, "loss": 0.6904, "step": 5754 }, { "epoch": 1.04, "learning_rate": 1.443099710982659e-05, "loss": 0.2909, "step": 5755 }, { "epoch": 1.04, "learning_rate": 1.4428287572254336e-05, "loss": 0.4913, "step": 5756 }, { "epoch": 1.04, "learning_rate": 1.4425578034682082e-05, "loss": 0.593, "step": 5757 }, { "epoch": 1.04, "learning_rate": 1.4422868497109826e-05, "loss": 1.0019, "step": 5758 }, { "epoch": 1.04, "learning_rate": 1.4420158959537572e-05, "loss": 0.3412, "step": 5759 }, { "epoch": 1.04, "learning_rate": 1.4417449421965317e-05, "loss": 0.5373, "step": 5760 }, { "epoch": 1.04, "learning_rate": 1.4414739884393064e-05, "loss": 0.6455, "step": 5761 }, { "epoch": 1.04, "learning_rate": 1.441203034682081e-05, "loss": 0.3986, "step": 5762 }, { "epoch": 1.04, "learning_rate": 1.4409320809248555e-05, "loss": 0.6347, "step": 5763 }, { "epoch": 1.04, "learning_rate": 1.4406611271676301e-05, "loss": 0.6686, "step": 5764 }, { "epoch": 1.04, "learning_rate": 1.4403901734104047e-05, "loss": 1.2796, "step": 5765 }, { "epoch": 1.04, "learning_rate": 1.4401192196531793e-05, "loss": 0.8891, "step": 5766 }, { "epoch": 1.04, "learning_rate": 1.4398482658959537e-05, "loss": 0.3028, "step": 5767 }, { "epoch": 1.04, "learning_rate": 1.4395773121387283e-05, "loss": 0.6025, "step": 5768 }, { "epoch": 1.04, "learning_rate": 1.439306358381503e-05, "loss": 0.8342, "step": 5769 }, { "epoch": 1.04, "learning_rate": 1.4390354046242776e-05, "loss": 0.908, "step": 5770 }, { "epoch": 1.04, "learning_rate": 1.4387644508670522e-05, "loss": 0.5504, "step": 5771 }, { "epoch": 1.04, "learning_rate": 1.4384934971098266e-05, "loss": 0.5292, "step": 5772 }, { "epoch": 1.04, "learning_rate": 1.4382225433526012e-05, "loss": 0.8486, "step": 5773 }, { "epoch": 1.04, "learning_rate": 1.4379515895953756e-05, "loss": 0.5278, "step": 5774 }, { "epoch": 1.04, "learning_rate": 1.4376806358381504e-05, "loss": 0.6223, "step": 5775 }, { "epoch": 1.04, "learning_rate": 1.4374096820809249e-05, "loss": 0.6739, "step": 5776 }, { "epoch": 1.04, "learning_rate": 1.4371387283236995e-05, "loss": 0.647, "step": 5777 }, { "epoch": 1.04, "learning_rate": 1.436867774566474e-05, "loss": 0.568, "step": 5778 }, { "epoch": 1.04, "learning_rate": 1.4365968208092485e-05, "loss": 0.7882, "step": 5779 }, { "epoch": 1.04, "learning_rate": 1.4363258670520233e-05, "loss": 0.3867, "step": 5780 }, { "epoch": 1.04, "learning_rate": 1.4360549132947977e-05, "loss": 0.4112, "step": 5781 }, { "epoch": 1.04, "learning_rate": 1.4357839595375723e-05, "loss": 0.4666, "step": 5782 }, { "epoch": 1.04, "learning_rate": 1.4355130057803468e-05, "loss": 0.6256, "step": 5783 }, { "epoch": 1.04, "learning_rate": 1.4352420520231214e-05, "loss": 0.6873, "step": 5784 }, { "epoch": 1.04, "learning_rate": 1.4349710982658961e-05, "loss": 0.4617, "step": 5785 }, { "epoch": 1.05, "learning_rate": 1.4347001445086706e-05, "loss": 0.4629, "step": 5786 }, { "epoch": 1.05, "learning_rate": 1.4344291907514452e-05, "loss": 0.8374, "step": 5787 }, { "epoch": 1.05, "learning_rate": 1.4341582369942196e-05, "loss": 0.7105, "step": 5788 }, { "epoch": 1.05, "learning_rate": 1.4338872832369942e-05, "loss": 0.9371, "step": 5789 }, { "epoch": 1.05, "learning_rate": 1.4336163294797688e-05, "loss": 0.3947, "step": 5790 }, { "epoch": 1.05, "learning_rate": 1.4333453757225434e-05, "loss": 0.3295, "step": 5791 }, { "epoch": 1.05, "learning_rate": 1.433074421965318e-05, "loss": 0.5894, "step": 5792 }, { "epoch": 1.05, "learning_rate": 1.4328034682080925e-05, "loss": 0.8971, "step": 5793 }, { "epoch": 1.05, "learning_rate": 1.432532514450867e-05, "loss": 0.612, "step": 5794 }, { "epoch": 1.05, "learning_rate": 1.4322615606936417e-05, "loss": 0.4992, "step": 5795 }, { "epoch": 1.05, "learning_rate": 1.4319906069364163e-05, "loss": 0.8839, "step": 5796 }, { "epoch": 1.05, "learning_rate": 1.4317196531791907e-05, "loss": 0.9036, "step": 5797 }, { "epoch": 1.05, "learning_rate": 1.4314486994219653e-05, "loss": 0.4505, "step": 5798 }, { "epoch": 1.05, "learning_rate": 1.4311777456647398e-05, "loss": 0.5101, "step": 5799 }, { "epoch": 1.05, "learning_rate": 1.4309067919075146e-05, "loss": 0.1599, "step": 5800 }, { "epoch": 1.05, "learning_rate": 1.4306358381502892e-05, "loss": 0.3873, "step": 5801 }, { "epoch": 1.05, "learning_rate": 1.4303648843930636e-05, "loss": 1.0187, "step": 5802 }, { "epoch": 1.05, "learning_rate": 1.4300939306358382e-05, "loss": 1.431, "step": 5803 }, { "epoch": 1.05, "learning_rate": 1.4298229768786126e-05, "loss": 0.5918, "step": 5804 }, { "epoch": 1.05, "learning_rate": 1.4295520231213874e-05, "loss": 0.7618, "step": 5805 }, { "epoch": 1.05, "learning_rate": 1.4292810693641618e-05, "loss": 0.2159, "step": 5806 }, { "epoch": 1.05, "learning_rate": 1.4290101156069365e-05, "loss": 0.9428, "step": 5807 }, { "epoch": 1.05, "learning_rate": 1.428739161849711e-05, "loss": 0.5125, "step": 5808 }, { "epoch": 1.05, "learning_rate": 1.4284682080924855e-05, "loss": 0.8312, "step": 5809 }, { "epoch": 1.05, "learning_rate": 1.4281972543352603e-05, "loss": 0.3191, "step": 5810 }, { "epoch": 1.05, "learning_rate": 1.4279263005780347e-05, "loss": 1.0491, "step": 5811 }, { "epoch": 1.05, "learning_rate": 1.4276553468208093e-05, "loss": 0.2868, "step": 5812 }, { "epoch": 1.05, "learning_rate": 1.4273843930635837e-05, "loss": 0.9251, "step": 5813 }, { "epoch": 1.05, "learning_rate": 1.4271134393063584e-05, "loss": 0.8195, "step": 5814 }, { "epoch": 1.05, "learning_rate": 1.4268424855491331e-05, "loss": 0.3371, "step": 5815 }, { "epoch": 1.05, "learning_rate": 1.4265715317919076e-05, "loss": 0.2079, "step": 5816 }, { "epoch": 1.05, "learning_rate": 1.4263005780346822e-05, "loss": 0.6987, "step": 5817 }, { "epoch": 1.05, "learning_rate": 1.4260296242774566e-05, "loss": 0.4854, "step": 5818 }, { "epoch": 1.05, "learning_rate": 1.4257586705202312e-05, "loss": 0.6513, "step": 5819 }, { "epoch": 1.05, "learning_rate": 1.4254877167630058e-05, "loss": 0.68, "step": 5820 }, { "epoch": 1.05, "learning_rate": 1.4252167630057804e-05, "loss": 0.4318, "step": 5821 }, { "epoch": 1.05, "learning_rate": 1.4249458092485549e-05, "loss": 0.9787, "step": 5822 }, { "epoch": 1.05, "learning_rate": 1.4246748554913295e-05, "loss": 0.4899, "step": 5823 }, { "epoch": 1.05, "learning_rate": 1.424403901734104e-05, "loss": 0.7879, "step": 5824 }, { "epoch": 1.05, "learning_rate": 1.4241329479768787e-05, "loss": 0.6257, "step": 5825 }, { "epoch": 1.05, "learning_rate": 1.4238619942196533e-05, "loss": 0.2664, "step": 5826 }, { "epoch": 1.05, "learning_rate": 1.4235910404624277e-05, "loss": 0.9346, "step": 5827 }, { "epoch": 1.05, "learning_rate": 1.4233200867052023e-05, "loss": 1.1361, "step": 5828 }, { "epoch": 1.05, "learning_rate": 1.4230491329479768e-05, "loss": 0.8084, "step": 5829 }, { "epoch": 1.05, "learning_rate": 1.4227781791907515e-05, "loss": 0.439, "step": 5830 }, { "epoch": 1.05, "learning_rate": 1.4225072254335261e-05, "loss": 0.376, "step": 5831 }, { "epoch": 1.05, "learning_rate": 1.4222362716763006e-05, "loss": 0.3658, "step": 5832 }, { "epoch": 1.05, "learning_rate": 1.4219653179190752e-05, "loss": 1.0384, "step": 5833 }, { "epoch": 1.05, "learning_rate": 1.4216943641618496e-05, "loss": 0.4933, "step": 5834 }, { "epoch": 1.05, "learning_rate": 1.4214234104046244e-05, "loss": 0.3256, "step": 5835 }, { "epoch": 1.05, "learning_rate": 1.4211524566473988e-05, "loss": 0.6429, "step": 5836 }, { "epoch": 1.05, "learning_rate": 1.4208815028901734e-05, "loss": 0.4504, "step": 5837 }, { "epoch": 1.05, "learning_rate": 1.420610549132948e-05, "loss": 0.2219, "step": 5838 }, { "epoch": 1.05, "learning_rate": 1.4203395953757225e-05, "loss": 0.1298, "step": 5839 }, { "epoch": 1.05, "learning_rate": 1.4200686416184973e-05, "loss": 0.2609, "step": 5840 }, { "epoch": 1.06, "learning_rate": 1.4197976878612717e-05, "loss": 0.3757, "step": 5841 }, { "epoch": 1.06, "learning_rate": 1.4195267341040463e-05, "loss": 0.4934, "step": 5842 }, { "epoch": 1.06, "learning_rate": 1.4192557803468207e-05, "loss": 0.4307, "step": 5843 }, { "epoch": 1.06, "learning_rate": 1.4189848265895953e-05, "loss": 0.9486, "step": 5844 }, { "epoch": 1.06, "learning_rate": 1.41871387283237e-05, "loss": 0.4193, "step": 5845 }, { "epoch": 1.06, "learning_rate": 1.4184429190751446e-05, "loss": 0.6103, "step": 5846 }, { "epoch": 1.06, "learning_rate": 1.4181719653179192e-05, "loss": 0.7656, "step": 5847 }, { "epoch": 1.06, "learning_rate": 1.4179010115606936e-05, "loss": 0.9984, "step": 5848 }, { "epoch": 1.06, "learning_rate": 1.4176300578034684e-05, "loss": 0.2482, "step": 5849 }, { "epoch": 1.06, "learning_rate": 1.4173591040462428e-05, "loss": 0.593, "step": 5850 }, { "epoch": 1.06, "learning_rate": 1.4170881502890174e-05, "loss": 0.4588, "step": 5851 }, { "epoch": 1.06, "learning_rate": 1.4168171965317919e-05, "loss": 0.365, "step": 5852 }, { "epoch": 1.06, "learning_rate": 1.4165462427745665e-05, "loss": 0.5417, "step": 5853 }, { "epoch": 1.06, "learning_rate": 1.4162752890173412e-05, "loss": 0.453, "step": 5854 }, { "epoch": 1.06, "learning_rate": 1.4160043352601157e-05, "loss": 0.5549, "step": 5855 }, { "epoch": 1.06, "learning_rate": 1.4157333815028903e-05, "loss": 1.219, "step": 5856 }, { "epoch": 1.06, "learning_rate": 1.4154624277456647e-05, "loss": 0.3683, "step": 5857 }, { "epoch": 1.06, "learning_rate": 1.4151914739884393e-05, "loss": 0.2119, "step": 5858 }, { "epoch": 1.06, "learning_rate": 1.414920520231214e-05, "loss": 0.5964, "step": 5859 }, { "epoch": 1.06, "learning_rate": 1.4146495664739885e-05, "loss": 0.155, "step": 5860 }, { "epoch": 1.06, "learning_rate": 1.414378612716763e-05, "loss": 0.467, "step": 5861 }, { "epoch": 1.06, "learning_rate": 1.4141076589595376e-05, "loss": 0.286, "step": 5862 }, { "epoch": 1.06, "learning_rate": 1.4138367052023122e-05, "loss": 0.797, "step": 5863 }, { "epoch": 1.06, "learning_rate": 1.4135657514450868e-05, "loss": 0.9823, "step": 5864 }, { "epoch": 1.06, "learning_rate": 1.4132947976878614e-05, "loss": 0.9674, "step": 5865 }, { "epoch": 1.06, "learning_rate": 1.4130238439306358e-05, "loss": 1.5702, "step": 5866 }, { "epoch": 1.06, "learning_rate": 1.4127528901734104e-05, "loss": 0.5755, "step": 5867 }, { "epoch": 1.06, "learning_rate": 1.4124819364161849e-05, "loss": 0.3884, "step": 5868 }, { "epoch": 1.06, "learning_rate": 1.4122109826589596e-05, "loss": 0.3425, "step": 5869 }, { "epoch": 1.06, "learning_rate": 1.4119400289017343e-05, "loss": 0.6462, "step": 5870 }, { "epoch": 1.06, "learning_rate": 1.4116690751445087e-05, "loss": 0.7526, "step": 5871 }, { "epoch": 1.06, "learning_rate": 1.4113981213872833e-05, "loss": 0.1363, "step": 5872 }, { "epoch": 1.06, "learning_rate": 1.4111271676300577e-05, "loss": 0.2296, "step": 5873 }, { "epoch": 1.06, "learning_rate": 1.4108562138728325e-05, "loss": 0.5181, "step": 5874 }, { "epoch": 1.06, "learning_rate": 1.410585260115607e-05, "loss": 0.3605, "step": 5875 }, { "epoch": 1.06, "learning_rate": 1.4103143063583816e-05, "loss": 0.4598, "step": 5876 }, { "epoch": 1.06, "learning_rate": 1.4100433526011562e-05, "loss": 0.4472, "step": 5877 }, { "epoch": 1.06, "learning_rate": 1.4097723988439306e-05, "loss": 0.7612, "step": 5878 }, { "epoch": 1.06, "learning_rate": 1.4095014450867054e-05, "loss": 0.4663, "step": 5879 }, { "epoch": 1.06, "learning_rate": 1.4092304913294798e-05, "loss": 0.7572, "step": 5880 }, { "epoch": 1.06, "learning_rate": 1.4089595375722544e-05, "loss": 0.2848, "step": 5881 }, { "epoch": 1.06, "learning_rate": 1.4086885838150288e-05, "loss": 0.5, "step": 5882 }, { "epoch": 1.06, "learning_rate": 1.4084176300578035e-05, "loss": 1.0102, "step": 5883 }, { "epoch": 1.06, "learning_rate": 1.408146676300578e-05, "loss": 0.7773, "step": 5884 }, { "epoch": 1.06, "learning_rate": 1.4078757225433527e-05, "loss": 0.2746, "step": 5885 }, { "epoch": 1.06, "learning_rate": 1.4076047687861273e-05, "loss": 0.4504, "step": 5886 }, { "epoch": 1.06, "learning_rate": 1.4073338150289017e-05, "loss": 0.5353, "step": 5887 }, { "epoch": 1.06, "learning_rate": 1.4070628612716763e-05, "loss": 1.0175, "step": 5888 }, { "epoch": 1.06, "learning_rate": 1.406791907514451e-05, "loss": 0.5235, "step": 5889 }, { "epoch": 1.06, "learning_rate": 1.4065209537572255e-05, "loss": 0.3315, "step": 5890 }, { "epoch": 1.06, "learning_rate": 1.40625e-05, "loss": 0.3435, "step": 5891 }, { "epoch": 1.06, "learning_rate": 1.4059790462427746e-05, "loss": 0.3019, "step": 5892 }, { "epoch": 1.06, "learning_rate": 1.4057080924855492e-05, "loss": 0.3495, "step": 5893 }, { "epoch": 1.06, "learning_rate": 1.4054371387283238e-05, "loss": 0.1584, "step": 5894 }, { "epoch": 1.06, "learning_rate": 1.4051661849710984e-05, "loss": 0.2276, "step": 5895 }, { "epoch": 1.07, "learning_rate": 1.4048952312138728e-05, "loss": 0.4636, "step": 5896 }, { "epoch": 1.07, "learning_rate": 1.4046242774566474e-05, "loss": 1.2449, "step": 5897 }, { "epoch": 1.07, "learning_rate": 1.4043533236994219e-05, "loss": 0.4876, "step": 5898 }, { "epoch": 1.07, "learning_rate": 1.4040823699421966e-05, "loss": 0.424, "step": 5899 }, { "epoch": 1.07, "learning_rate": 1.4038114161849712e-05, "loss": 0.6004, "step": 5900 }, { "epoch": 1.07, "learning_rate": 1.4035404624277457e-05, "loss": 0.3548, "step": 5901 }, { "epoch": 1.07, "learning_rate": 1.4032695086705203e-05, "loss": 0.5121, "step": 5902 }, { "epoch": 1.07, "learning_rate": 1.4029985549132947e-05, "loss": 0.6696, "step": 5903 }, { "epoch": 1.07, "learning_rate": 1.4027276011560695e-05, "loss": 0.6291, "step": 5904 }, { "epoch": 1.07, "learning_rate": 1.402456647398844e-05, "loss": 0.1728, "step": 5905 }, { "epoch": 1.07, "learning_rate": 1.4021856936416185e-05, "loss": 0.8308, "step": 5906 }, { "epoch": 1.07, "learning_rate": 1.401914739884393e-05, "loss": 0.7672, "step": 5907 }, { "epoch": 1.07, "learning_rate": 1.4016437861271676e-05, "loss": 0.4959, "step": 5908 }, { "epoch": 1.07, "learning_rate": 1.4013728323699424e-05, "loss": 0.6694, "step": 5909 }, { "epoch": 1.07, "learning_rate": 1.4011018786127168e-05, "loss": 0.6328, "step": 5910 }, { "epoch": 1.07, "learning_rate": 1.4008309248554914e-05, "loss": 0.5184, "step": 5911 }, { "epoch": 1.07, "learning_rate": 1.4005599710982658e-05, "loss": 0.3732, "step": 5912 }, { "epoch": 1.07, "learning_rate": 1.4002890173410404e-05, "loss": 0.8864, "step": 5913 }, { "epoch": 1.07, "learning_rate": 1.400018063583815e-05, "loss": 0.3183, "step": 5914 }, { "epoch": 1.07, "learning_rate": 1.3997471098265897e-05, "loss": 0.257, "step": 5915 }, { "epoch": 1.07, "learning_rate": 1.3994761560693643e-05, "loss": 0.5543, "step": 5916 }, { "epoch": 1.07, "learning_rate": 1.3992052023121387e-05, "loss": 0.4847, "step": 5917 }, { "epoch": 1.07, "learning_rate": 1.3989342485549133e-05, "loss": 0.3737, "step": 5918 }, { "epoch": 1.07, "learning_rate": 1.3986632947976879e-05, "loss": 0.837, "step": 5919 }, { "epoch": 1.07, "learning_rate": 1.3983923410404625e-05, "loss": 0.633, "step": 5920 }, { "epoch": 1.07, "learning_rate": 1.398121387283237e-05, "loss": 0.588, "step": 5921 }, { "epoch": 1.07, "learning_rate": 1.3978504335260116e-05, "loss": 0.3648, "step": 5922 }, { "epoch": 1.07, "learning_rate": 1.3975794797687862e-05, "loss": 0.8221, "step": 5923 }, { "epoch": 1.07, "learning_rate": 1.3973085260115608e-05, "loss": 0.7176, "step": 5924 }, { "epoch": 1.07, "learning_rate": 1.3970375722543354e-05, "loss": 1.1404, "step": 5925 }, { "epoch": 1.07, "learning_rate": 1.3967666184971098e-05, "loss": 0.1579, "step": 5926 }, { "epoch": 1.07, "learning_rate": 1.3964956647398844e-05, "loss": 0.9155, "step": 5927 }, { "epoch": 1.07, "learning_rate": 1.3962247109826589e-05, "loss": 0.6285, "step": 5928 }, { "epoch": 1.07, "learning_rate": 1.3959537572254336e-05, "loss": 0.8583, "step": 5929 }, { "epoch": 1.07, "learning_rate": 1.395682803468208e-05, "loss": 0.5666, "step": 5930 }, { "epoch": 1.07, "learning_rate": 1.3954118497109827e-05, "loss": 0.5319, "step": 5931 }, { "epoch": 1.07, "learning_rate": 1.3951408959537573e-05, "loss": 0.8158, "step": 5932 }, { "epoch": 1.07, "learning_rate": 1.3948699421965317e-05, "loss": 0.5068, "step": 5933 }, { "epoch": 1.07, "learning_rate": 1.3945989884393065e-05, "loss": 0.4546, "step": 5934 }, { "epoch": 1.07, "learning_rate": 1.394328034682081e-05, "loss": 0.9288, "step": 5935 }, { "epoch": 1.07, "learning_rate": 1.3940570809248555e-05, "loss": 0.3177, "step": 5936 }, { "epoch": 1.07, "learning_rate": 1.39378612716763e-05, "loss": 0.899, "step": 5937 }, { "epoch": 1.07, "learning_rate": 1.3935151734104047e-05, "loss": 0.382, "step": 5938 }, { "epoch": 1.07, "learning_rate": 1.3932442196531794e-05, "loss": 0.4424, "step": 5939 }, { "epoch": 1.07, "learning_rate": 1.3929732658959538e-05, "loss": 0.4848, "step": 5940 }, { "epoch": 1.07, "learning_rate": 1.3927023121387284e-05, "loss": 0.5941, "step": 5941 }, { "epoch": 1.07, "learning_rate": 1.3924313583815028e-05, "loss": 0.7844, "step": 5942 }, { "epoch": 1.07, "learning_rate": 1.3921604046242776e-05, "loss": 0.5415, "step": 5943 }, { "epoch": 1.07, "learning_rate": 1.391889450867052e-05, "loss": 0.7886, "step": 5944 }, { "epoch": 1.07, "learning_rate": 1.3916184971098266e-05, "loss": 0.8773, "step": 5945 }, { "epoch": 1.07, "learning_rate": 1.3913475433526013e-05, "loss": 0.3294, "step": 5946 }, { "epoch": 1.07, "learning_rate": 1.3910765895953757e-05, "loss": 0.5325, "step": 5947 }, { "epoch": 1.07, "learning_rate": 1.3908056358381505e-05, "loss": 0.5345, "step": 5948 }, { "epoch": 1.07, "learning_rate": 1.3905346820809249e-05, "loss": 0.388, "step": 5949 }, { "epoch": 1.07, "learning_rate": 1.3902637283236995e-05, "loss": 0.6436, "step": 5950 }, { "epoch": 1.07, "learning_rate": 1.389992774566474e-05, "loss": 0.5318, "step": 5951 }, { "epoch": 1.08, "learning_rate": 1.3897218208092486e-05, "loss": 0.4188, "step": 5952 }, { "epoch": 1.08, "learning_rate": 1.3894508670520232e-05, "loss": 0.4365, "step": 5953 }, { "epoch": 1.08, "learning_rate": 1.3891799132947978e-05, "loss": 0.1905, "step": 5954 }, { "epoch": 1.08, "learning_rate": 1.3889089595375724e-05, "loss": 0.5864, "step": 5955 }, { "epoch": 1.08, "learning_rate": 1.3886380057803468e-05, "loss": 0.8392, "step": 5956 }, { "epoch": 1.08, "learning_rate": 1.3883670520231214e-05, "loss": 0.8404, "step": 5957 }, { "epoch": 1.08, "learning_rate": 1.388096098265896e-05, "loss": 0.8878, "step": 5958 }, { "epoch": 1.08, "learning_rate": 1.3878251445086706e-05, "loss": 0.479, "step": 5959 }, { "epoch": 1.08, "learning_rate": 1.387554190751445e-05, "loss": 0.425, "step": 5960 }, { "epoch": 1.08, "learning_rate": 1.3872832369942197e-05, "loss": 0.9977, "step": 5961 }, { "epoch": 1.08, "learning_rate": 1.3870122832369943e-05, "loss": 1.0293, "step": 5962 }, { "epoch": 1.08, "learning_rate": 1.3867413294797689e-05, "loss": 0.8466, "step": 5963 }, { "epoch": 1.08, "learning_rate": 1.3864703757225435e-05, "loss": 0.4901, "step": 5964 }, { "epoch": 1.08, "learning_rate": 1.386199421965318e-05, "loss": 0.4366, "step": 5965 }, { "epoch": 1.08, "learning_rate": 1.3859284682080925e-05, "loss": 0.9567, "step": 5966 }, { "epoch": 1.08, "learning_rate": 1.385657514450867e-05, "loss": 0.6415, "step": 5967 }, { "epoch": 1.08, "learning_rate": 1.3853865606936417e-05, "loss": 0.3528, "step": 5968 }, { "epoch": 1.08, "learning_rate": 1.3851156069364162e-05, "loss": 0.8144, "step": 5969 }, { "epoch": 1.08, "learning_rate": 1.3848446531791908e-05, "loss": 0.756, "step": 5970 }, { "epoch": 1.08, "learning_rate": 1.3845736994219654e-05, "loss": 0.3503, "step": 5971 }, { "epoch": 1.08, "learning_rate": 1.3843027456647398e-05, "loss": 0.6484, "step": 5972 }, { "epoch": 1.08, "learning_rate": 1.3840317919075146e-05, "loss": 0.3209, "step": 5973 }, { "epoch": 1.08, "learning_rate": 1.383760838150289e-05, "loss": 0.4619, "step": 5974 }, { "epoch": 1.08, "learning_rate": 1.3834898843930636e-05, "loss": 0.6443, "step": 5975 }, { "epoch": 1.08, "learning_rate": 1.383218930635838e-05, "loss": 0.2464, "step": 5976 }, { "epoch": 1.08, "learning_rate": 1.3829479768786127e-05, "loss": 0.4217, "step": 5977 }, { "epoch": 1.08, "learning_rate": 1.3826770231213875e-05, "loss": 1.3111, "step": 5978 }, { "epoch": 1.08, "learning_rate": 1.3824060693641619e-05, "loss": 0.7471, "step": 5979 }, { "epoch": 1.08, "learning_rate": 1.3821351156069365e-05, "loss": 0.2368, "step": 5980 }, { "epoch": 1.08, "learning_rate": 1.381864161849711e-05, "loss": 0.7815, "step": 5981 }, { "epoch": 1.08, "learning_rate": 1.3815932080924855e-05, "loss": 0.9476, "step": 5982 }, { "epoch": 1.08, "learning_rate": 1.3813222543352601e-05, "loss": 0.6444, "step": 5983 }, { "epoch": 1.08, "learning_rate": 1.3810513005780348e-05, "loss": 0.1601, "step": 5984 }, { "epoch": 1.08, "learning_rate": 1.3807803468208094e-05, "loss": 0.6, "step": 5985 }, { "epoch": 1.08, "learning_rate": 1.3805093930635838e-05, "loss": 0.5521, "step": 5986 }, { "epoch": 1.08, "learning_rate": 1.3802384393063584e-05, "loss": 0.6757, "step": 5987 }, { "epoch": 1.08, "learning_rate": 1.379967485549133e-05, "loss": 0.9227, "step": 5988 }, { "epoch": 1.08, "learning_rate": 1.3796965317919076e-05, "loss": 0.2821, "step": 5989 }, { "epoch": 1.08, "learning_rate": 1.379425578034682e-05, "loss": 0.623, "step": 5990 }, { "epoch": 1.08, "learning_rate": 1.3791546242774567e-05, "loss": 1.2591, "step": 5991 }, { "epoch": 1.08, "learning_rate": 1.3788836705202311e-05, "loss": 0.3352, "step": 5992 }, { "epoch": 1.08, "learning_rate": 1.3786127167630059e-05, "loss": 0.7144, "step": 5993 }, { "epoch": 1.08, "learning_rate": 1.3783417630057805e-05, "loss": 0.3368, "step": 5994 }, { "epoch": 1.08, "learning_rate": 1.3780708092485549e-05, "loss": 0.5493, "step": 5995 }, { "epoch": 1.08, "learning_rate": 1.3777998554913295e-05, "loss": 0.3553, "step": 5996 }, { "epoch": 1.08, "learning_rate": 1.377528901734104e-05, "loss": 0.4067, "step": 5997 }, { "epoch": 1.08, "learning_rate": 1.3772579479768787e-05, "loss": 0.5206, "step": 5998 }, { "epoch": 1.08, "learning_rate": 1.3769869942196532e-05, "loss": 1.0084, "step": 5999 }, { "epoch": 1.08, "learning_rate": 1.3767160404624278e-05, "loss": 0.3074, "step": 6000 }, { "epoch": 1.08, "eval_exact_match": 87.360454115421, "eval_f1": 93.52817901742817, "step": 6000 }, { "epoch": 1.08, "learning_rate": 1.3764450867052024e-05, "loss": 0.6776, "step": 6001 }, { "epoch": 1.08, "learning_rate": 1.3761741329479768e-05, "loss": 0.5944, "step": 6002 }, { "epoch": 1.08, "learning_rate": 1.3759031791907516e-05, "loss": 1.0123, "step": 6003 }, { "epoch": 1.08, "learning_rate": 1.375632225433526e-05, "loss": 0.7756, "step": 6004 }, { "epoch": 1.08, "learning_rate": 1.3753612716763006e-05, "loss": 0.266, "step": 6005 }, { "epoch": 1.08, "learning_rate": 1.375090317919075e-05, "loss": 0.4734, "step": 6006 }, { "epoch": 1.09, "learning_rate": 1.3748193641618497e-05, "loss": 1.3748, "step": 6007 }, { "epoch": 1.09, "learning_rate": 1.3745484104046244e-05, "loss": 0.3405, "step": 6008 }, { "epoch": 1.09, "learning_rate": 1.3742774566473989e-05, "loss": 0.4213, "step": 6009 }, { "epoch": 1.09, "learning_rate": 1.3740065028901735e-05, "loss": 0.6018, "step": 6010 }, { "epoch": 1.09, "learning_rate": 1.373735549132948e-05, "loss": 0.7665, "step": 6011 }, { "epoch": 1.09, "learning_rate": 1.3734645953757225e-05, "loss": 0.3469, "step": 6012 }, { "epoch": 1.09, "learning_rate": 1.3731936416184971e-05, "loss": 0.2771, "step": 6013 }, { "epoch": 1.09, "learning_rate": 1.3729226878612717e-05, "loss": 0.267, "step": 6014 }, { "epoch": 1.09, "learning_rate": 1.3726517341040462e-05, "loss": 0.3292, "step": 6015 }, { "epoch": 1.09, "learning_rate": 1.3723807803468208e-05, "loss": 0.8005, "step": 6016 }, { "epoch": 1.09, "learning_rate": 1.3721098265895954e-05, "loss": 0.5473, "step": 6017 }, { "epoch": 1.09, "learning_rate": 1.37183887283237e-05, "loss": 1.2422, "step": 6018 }, { "epoch": 1.09, "learning_rate": 1.3715679190751446e-05, "loss": 0.4875, "step": 6019 }, { "epoch": 1.09, "learning_rate": 1.371296965317919e-05, "loss": 0.7158, "step": 6020 }, { "epoch": 1.09, "learning_rate": 1.3710260115606936e-05, "loss": 0.7193, "step": 6021 }, { "epoch": 1.09, "learning_rate": 1.3707550578034683e-05, "loss": 0.4762, "step": 6022 }, { "epoch": 1.09, "learning_rate": 1.3704841040462429e-05, "loss": 0.415, "step": 6023 }, { "epoch": 1.09, "learning_rate": 1.3702131502890175e-05, "loss": 0.4663, "step": 6024 }, { "epoch": 1.09, "learning_rate": 1.3699421965317919e-05, "loss": 0.5938, "step": 6025 }, { "epoch": 1.09, "learning_rate": 1.3696712427745665e-05, "loss": 0.6301, "step": 6026 }, { "epoch": 1.09, "learning_rate": 1.3694002890173411e-05, "loss": 0.7104, "step": 6027 }, { "epoch": 1.09, "learning_rate": 1.3691293352601157e-05, "loss": 0.5037, "step": 6028 }, { "epoch": 1.09, "learning_rate": 1.3688583815028902e-05, "loss": 0.5042, "step": 6029 }, { "epoch": 1.09, "learning_rate": 1.3685874277456648e-05, "loss": 0.8412, "step": 6030 }, { "epoch": 1.09, "learning_rate": 1.3683164739884394e-05, "loss": 0.563, "step": 6031 }, { "epoch": 1.09, "learning_rate": 1.368045520231214e-05, "loss": 0.2283, "step": 6032 }, { "epoch": 1.09, "learning_rate": 1.3677745664739886e-05, "loss": 0.7492, "step": 6033 }, { "epoch": 1.09, "learning_rate": 1.367503612716763e-05, "loss": 0.6956, "step": 6034 }, { "epoch": 1.09, "learning_rate": 1.3672326589595376e-05, "loss": 1.4333, "step": 6035 }, { "epoch": 1.09, "learning_rate": 1.366961705202312e-05, "loss": 0.5722, "step": 6036 }, { "epoch": 1.09, "learning_rate": 1.3666907514450868e-05, "loss": 0.4337, "step": 6037 }, { "epoch": 1.09, "learning_rate": 1.3664197976878613e-05, "loss": 0.2804, "step": 6038 }, { "epoch": 1.09, "learning_rate": 1.3661488439306359e-05, "loss": 0.7547, "step": 6039 }, { "epoch": 1.09, "learning_rate": 1.3658778901734105e-05, "loss": 0.9759, "step": 6040 }, { "epoch": 1.09, "learning_rate": 1.365606936416185e-05, "loss": 0.6139, "step": 6041 }, { "epoch": 1.09, "learning_rate": 1.3653359826589597e-05, "loss": 1.3849, "step": 6042 }, { "epoch": 1.09, "learning_rate": 1.3650650289017341e-05, "loss": 0.6475, "step": 6043 }, { "epoch": 1.09, "learning_rate": 1.3647940751445087e-05, "loss": 0.4179, "step": 6044 }, { "epoch": 1.09, "learning_rate": 1.3645231213872832e-05, "loss": 0.4247, "step": 6045 }, { "epoch": 1.09, "learning_rate": 1.3642521676300578e-05, "loss": 0.6312, "step": 6046 }, { "epoch": 1.09, "learning_rate": 1.3639812138728326e-05, "loss": 0.5564, "step": 6047 }, { "epoch": 1.09, "learning_rate": 1.363710260115607e-05, "loss": 0.4582, "step": 6048 }, { "epoch": 1.09, "learning_rate": 1.3634393063583816e-05, "loss": 0.5463, "step": 6049 }, { "epoch": 1.09, "learning_rate": 1.363168352601156e-05, "loss": 0.866, "step": 6050 }, { "epoch": 1.09, "learning_rate": 1.3628973988439306e-05, "loss": 0.4628, "step": 6051 }, { "epoch": 1.09, "learning_rate": 1.3626264450867052e-05, "loss": 0.2808, "step": 6052 }, { "epoch": 1.09, "learning_rate": 1.3623554913294799e-05, "loss": 0.6564, "step": 6053 }, { "epoch": 1.09, "learning_rate": 1.3620845375722545e-05, "loss": 0.5778, "step": 6054 }, { "epoch": 1.09, "learning_rate": 1.3618135838150289e-05, "loss": 0.5122, "step": 6055 }, { "epoch": 1.09, "learning_rate": 1.3615426300578035e-05, "loss": 0.3858, "step": 6056 }, { "epoch": 1.09, "learning_rate": 1.3612716763005781e-05, "loss": 0.3625, "step": 6057 }, { "epoch": 1.09, "learning_rate": 1.3610007225433527e-05, "loss": 0.6765, "step": 6058 }, { "epoch": 1.09, "learning_rate": 1.3607297687861271e-05, "loss": 0.9161, "step": 6059 }, { "epoch": 1.09, "learning_rate": 1.3604588150289018e-05, "loss": 0.4108, "step": 6060 }, { "epoch": 1.09, "learning_rate": 1.3601878612716762e-05, "loss": 0.6433, "step": 6061 }, { "epoch": 1.1, "learning_rate": 1.359916907514451e-05, "loss": 0.5972, "step": 6062 }, { "epoch": 1.1, "learning_rate": 1.3596459537572256e-05, "loss": 0.3923, "step": 6063 }, { "epoch": 1.1, "learning_rate": 1.359375e-05, "loss": 0.3379, "step": 6064 }, { "epoch": 1.1, "learning_rate": 1.3591040462427746e-05, "loss": 0.5392, "step": 6065 }, { "epoch": 1.1, "learning_rate": 1.358833092485549e-05, "loss": 0.2398, "step": 6066 }, { "epoch": 1.1, "learning_rate": 1.3585621387283238e-05, "loss": 0.6657, "step": 6067 }, { "epoch": 1.1, "learning_rate": 1.3582911849710983e-05, "loss": 0.6943, "step": 6068 }, { "epoch": 1.1, "learning_rate": 1.3580202312138729e-05, "loss": 0.2067, "step": 6069 }, { "epoch": 1.1, "learning_rate": 1.3577492774566475e-05, "loss": 0.5247, "step": 6070 }, { "epoch": 1.1, "learning_rate": 1.3574783236994219e-05, "loss": 0.6126, "step": 6071 }, { "epoch": 1.1, "learning_rate": 1.3572073699421967e-05, "loss": 0.5623, "step": 6072 }, { "epoch": 1.1, "learning_rate": 1.3569364161849711e-05, "loss": 0.3128, "step": 6073 }, { "epoch": 1.1, "learning_rate": 1.3566654624277457e-05, "loss": 0.5483, "step": 6074 }, { "epoch": 1.1, "learning_rate": 1.3563945086705202e-05, "loss": 0.3806, "step": 6075 }, { "epoch": 1.1, "learning_rate": 1.3561235549132948e-05, "loss": 0.4725, "step": 6076 }, { "epoch": 1.1, "learning_rate": 1.3558526011560694e-05, "loss": 0.9998, "step": 6077 }, { "epoch": 1.1, "learning_rate": 1.355581647398844e-05, "loss": 0.5427, "step": 6078 }, { "epoch": 1.1, "learning_rate": 1.3553106936416186e-05, "loss": 0.493, "step": 6079 }, { "epoch": 1.1, "learning_rate": 1.355039739884393e-05, "loss": 1.0594, "step": 6080 }, { "epoch": 1.1, "learning_rate": 1.3547687861271676e-05, "loss": 0.3499, "step": 6081 }, { "epoch": 1.1, "learning_rate": 1.3544978323699422e-05, "loss": 0.2892, "step": 6082 }, { "epoch": 1.1, "learning_rate": 1.3542268786127168e-05, "loss": 0.6065, "step": 6083 }, { "epoch": 1.1, "learning_rate": 1.3539559248554913e-05, "loss": 0.6822, "step": 6084 }, { "epoch": 1.1, "learning_rate": 1.3536849710982659e-05, "loss": 1.0427, "step": 6085 }, { "epoch": 1.1, "learning_rate": 1.3534140173410405e-05, "loss": 0.3797, "step": 6086 }, { "epoch": 1.1, "learning_rate": 1.3531430635838151e-05, "loss": 0.7254, "step": 6087 }, { "epoch": 1.1, "learning_rate": 1.3528721098265897e-05, "loss": 0.9883, "step": 6088 }, { "epoch": 1.1, "learning_rate": 1.3526011560693641e-05, "loss": 0.1398, "step": 6089 }, { "epoch": 1.1, "learning_rate": 1.3523302023121387e-05, "loss": 0.4375, "step": 6090 }, { "epoch": 1.1, "learning_rate": 1.3520592485549132e-05, "loss": 0.5625, "step": 6091 }, { "epoch": 1.1, "learning_rate": 1.351788294797688e-05, "loss": 0.7307, "step": 6092 }, { "epoch": 1.1, "learning_rate": 1.3515173410404626e-05, "loss": 0.5875, "step": 6093 }, { "epoch": 1.1, "learning_rate": 1.351246387283237e-05, "loss": 0.4521, "step": 6094 }, { "epoch": 1.1, "learning_rate": 1.3509754335260116e-05, "loss": 0.4781, "step": 6095 }, { "epoch": 1.1, "learning_rate": 1.350704479768786e-05, "loss": 0.4113, "step": 6096 }, { "epoch": 1.1, "learning_rate": 1.3504335260115608e-05, "loss": 0.298, "step": 6097 }, { "epoch": 1.1, "learning_rate": 1.3501625722543353e-05, "loss": 0.4018, "step": 6098 }, { "epoch": 1.1, "learning_rate": 1.3498916184971099e-05, "loss": 0.6277, "step": 6099 }, { "epoch": 1.1, "learning_rate": 1.3496206647398843e-05, "loss": 0.4283, "step": 6100 }, { "epoch": 1.1, "learning_rate": 1.3493497109826589e-05, "loss": 0.5149, "step": 6101 }, { "epoch": 1.1, "learning_rate": 1.3490787572254337e-05, "loss": 0.876, "step": 6102 }, { "epoch": 1.1, "learning_rate": 1.3488078034682081e-05, "loss": 0.6863, "step": 6103 }, { "epoch": 1.1, "learning_rate": 1.3485368497109827e-05, "loss": 0.9775, "step": 6104 }, { "epoch": 1.1, "learning_rate": 1.3482658959537572e-05, "loss": 0.3159, "step": 6105 }, { "epoch": 1.1, "learning_rate": 1.3479949421965318e-05, "loss": 0.7471, "step": 6106 }, { "epoch": 1.1, "learning_rate": 1.3477239884393064e-05, "loss": 0.6311, "step": 6107 }, { "epoch": 1.1, "learning_rate": 1.347453034682081e-05, "loss": 0.2768, "step": 6108 }, { "epoch": 1.1, "learning_rate": 1.3471820809248556e-05, "loss": 0.7233, "step": 6109 }, { "epoch": 1.1, "learning_rate": 1.34691112716763e-05, "loss": 0.2, "step": 6110 }, { "epoch": 1.1, "learning_rate": 1.3466401734104048e-05, "loss": 0.4747, "step": 6111 }, { "epoch": 1.1, "learning_rate": 1.3463692196531792e-05, "loss": 0.9631, "step": 6112 }, { "epoch": 1.1, "learning_rate": 1.3460982658959538e-05, "loss": 0.4627, "step": 6113 }, { "epoch": 1.1, "learning_rate": 1.3458273121387283e-05, "loss": 0.5414, "step": 6114 }, { "epoch": 1.1, "learning_rate": 1.3455563583815029e-05, "loss": 1.1298, "step": 6115 }, { "epoch": 1.1, "learning_rate": 1.3452854046242777e-05, "loss": 0.6599, "step": 6116 }, { "epoch": 1.1, "learning_rate": 1.3450144508670521e-05, "loss": 1.3482, "step": 6117 }, { "epoch": 1.11, "learning_rate": 1.3447434971098267e-05, "loss": 0.5295, "step": 6118 }, { "epoch": 1.11, "learning_rate": 1.3444725433526011e-05, "loss": 1.0182, "step": 6119 }, { "epoch": 1.11, "learning_rate": 1.3442015895953757e-05, "loss": 0.5439, "step": 6120 }, { "epoch": 1.11, "learning_rate": 1.3439306358381503e-05, "loss": 0.4288, "step": 6121 }, { "epoch": 1.11, "learning_rate": 1.343659682080925e-05, "loss": 0.5365, "step": 6122 }, { "epoch": 1.11, "learning_rate": 1.3433887283236994e-05, "loss": 0.3749, "step": 6123 }, { "epoch": 1.11, "learning_rate": 1.343117774566474e-05, "loss": 0.3974, "step": 6124 }, { "epoch": 1.11, "learning_rate": 1.3428468208092486e-05, "loss": 1.9589, "step": 6125 }, { "epoch": 1.11, "learning_rate": 1.3425758670520232e-05, "loss": 0.4985, "step": 6126 }, { "epoch": 1.11, "learning_rate": 1.3423049132947978e-05, "loss": 0.3884, "step": 6127 }, { "epoch": 1.11, "learning_rate": 1.3420339595375722e-05, "loss": 0.4468, "step": 6128 }, { "epoch": 1.11, "learning_rate": 1.3417630057803469e-05, "loss": 0.5228, "step": 6129 }, { "epoch": 1.11, "learning_rate": 1.3414920520231213e-05, "loss": 0.2786, "step": 6130 }, { "epoch": 1.11, "learning_rate": 1.341221098265896e-05, "loss": 0.3982, "step": 6131 }, { "epoch": 1.11, "learning_rate": 1.3409501445086707e-05, "loss": 0.5562, "step": 6132 }, { "epoch": 1.11, "learning_rate": 1.3406791907514451e-05, "loss": 0.3987, "step": 6133 }, { "epoch": 1.11, "learning_rate": 1.3404082369942197e-05, "loss": 0.4801, "step": 6134 }, { "epoch": 1.11, "learning_rate": 1.3401372832369941e-05, "loss": 0.5108, "step": 6135 }, { "epoch": 1.11, "learning_rate": 1.339866329479769e-05, "loss": 0.5358, "step": 6136 }, { "epoch": 1.11, "learning_rate": 1.3395953757225434e-05, "loss": 0.602, "step": 6137 }, { "epoch": 1.11, "learning_rate": 1.339324421965318e-05, "loss": 0.8456, "step": 6138 }, { "epoch": 1.11, "learning_rate": 1.3390534682080926e-05, "loss": 0.6861, "step": 6139 }, { "epoch": 1.11, "learning_rate": 1.338782514450867e-05, "loss": 0.477, "step": 6140 }, { "epoch": 1.11, "learning_rate": 1.3385115606936418e-05, "loss": 0.9812, "step": 6141 }, { "epoch": 1.11, "learning_rate": 1.3382406069364162e-05, "loss": 0.1969, "step": 6142 }, { "epoch": 1.11, "learning_rate": 1.3379696531791908e-05, "loss": 0.1931, "step": 6143 }, { "epoch": 1.11, "learning_rate": 1.3376986994219653e-05, "loss": 0.6619, "step": 6144 }, { "epoch": 1.11, "learning_rate": 1.3374277456647399e-05, "loss": 0.1356, "step": 6145 }, { "epoch": 1.11, "learning_rate": 1.3371567919075145e-05, "loss": 0.5071, "step": 6146 }, { "epoch": 1.11, "learning_rate": 1.336885838150289e-05, "loss": 0.7434, "step": 6147 }, { "epoch": 1.11, "learning_rate": 1.3366148843930637e-05, "loss": 0.5056, "step": 6148 }, { "epoch": 1.11, "learning_rate": 1.3363439306358381e-05, "loss": 0.5651, "step": 6149 }, { "epoch": 1.11, "learning_rate": 1.3360729768786127e-05, "loss": 0.6603, "step": 6150 }, { "epoch": 1.11, "learning_rate": 1.3358020231213873e-05, "loss": 0.7212, "step": 6151 }, { "epoch": 1.11, "learning_rate": 1.335531069364162e-05, "loss": 0.485, "step": 6152 }, { "epoch": 1.11, "learning_rate": 1.3352601156069364e-05, "loss": 0.2057, "step": 6153 }, { "epoch": 1.11, "learning_rate": 1.334989161849711e-05, "loss": 0.6183, "step": 6154 }, { "epoch": 1.11, "learning_rate": 1.3347182080924856e-05, "loss": 0.3188, "step": 6155 }, { "epoch": 1.11, "learning_rate": 1.3344472543352602e-05, "loss": 0.5139, "step": 6156 }, { "epoch": 1.11, "learning_rate": 1.3341763005780348e-05, "loss": 0.8339, "step": 6157 }, { "epoch": 1.11, "learning_rate": 1.3339053468208092e-05, "loss": 0.6763, "step": 6158 }, { "epoch": 1.11, "learning_rate": 1.3336343930635838e-05, "loss": 0.3426, "step": 6159 }, { "epoch": 1.11, "learning_rate": 1.3333634393063583e-05, "loss": 0.3962, "step": 6160 }, { "epoch": 1.11, "learning_rate": 1.333092485549133e-05, "loss": 0.3333, "step": 6161 }, { "epoch": 1.11, "learning_rate": 1.3328215317919077e-05, "loss": 0.4015, "step": 6162 }, { "epoch": 1.11, "learning_rate": 1.3325505780346821e-05, "loss": 0.9156, "step": 6163 }, { "epoch": 1.11, "learning_rate": 1.3322796242774567e-05, "loss": 0.4707, "step": 6164 }, { "epoch": 1.11, "learning_rate": 1.3320086705202311e-05, "loss": 0.4177, "step": 6165 }, { "epoch": 1.11, "learning_rate": 1.3317377167630059e-05, "loss": 0.4717, "step": 6166 }, { "epoch": 1.11, "learning_rate": 1.3314667630057804e-05, "loss": 0.6831, "step": 6167 }, { "epoch": 1.11, "learning_rate": 1.331195809248555e-05, "loss": 1.2558, "step": 6168 }, { "epoch": 1.11, "learning_rate": 1.3309248554913294e-05, "loss": 0.3204, "step": 6169 }, { "epoch": 1.11, "learning_rate": 1.330653901734104e-05, "loss": 0.3856, "step": 6170 }, { "epoch": 1.11, "learning_rate": 1.3303829479768788e-05, "loss": 0.4377, "step": 6171 }, { "epoch": 1.11, "learning_rate": 1.3301119942196532e-05, "loss": 0.3397, "step": 6172 }, { "epoch": 1.12, "learning_rate": 1.3298410404624278e-05, "loss": 1.0293, "step": 6173 }, { "epoch": 1.12, "learning_rate": 1.3295700867052023e-05, "loss": 0.282, "step": 6174 }, { "epoch": 1.12, "learning_rate": 1.3292991329479769e-05, "loss": 0.2383, "step": 6175 }, { "epoch": 1.12, "learning_rate": 1.3290281791907515e-05, "loss": 0.5789, "step": 6176 }, { "epoch": 1.12, "learning_rate": 1.328757225433526e-05, "loss": 0.7559, "step": 6177 }, { "epoch": 1.12, "learning_rate": 1.3284862716763007e-05, "loss": 0.3089, "step": 6178 }, { "epoch": 1.12, "learning_rate": 1.3282153179190751e-05, "loss": 1.2603, "step": 6179 }, { "epoch": 1.12, "learning_rate": 1.3279443641618497e-05, "loss": 0.4307, "step": 6180 }, { "epoch": 1.12, "learning_rate": 1.3276734104046243e-05, "loss": 0.4944, "step": 6181 }, { "epoch": 1.12, "learning_rate": 1.327402456647399e-05, "loss": 0.7115, "step": 6182 }, { "epoch": 1.12, "learning_rate": 1.3271315028901734e-05, "loss": 0.5309, "step": 6183 }, { "epoch": 1.12, "learning_rate": 1.326860549132948e-05, "loss": 0.9618, "step": 6184 }, { "epoch": 1.12, "learning_rate": 1.3265895953757226e-05, "loss": 0.5964, "step": 6185 }, { "epoch": 1.12, "learning_rate": 1.3263186416184972e-05, "loss": 0.7034, "step": 6186 }, { "epoch": 1.12, "learning_rate": 1.3260476878612718e-05, "loss": 0.2857, "step": 6187 }, { "epoch": 1.12, "learning_rate": 1.3257767341040462e-05, "loss": 0.3588, "step": 6188 }, { "epoch": 1.12, "learning_rate": 1.3255057803468208e-05, "loss": 0.611, "step": 6189 }, { "epoch": 1.12, "learning_rate": 1.3252348265895953e-05, "loss": 0.5684, "step": 6190 }, { "epoch": 1.12, "learning_rate": 1.32496387283237e-05, "loss": 0.5965, "step": 6191 }, { "epoch": 1.12, "learning_rate": 1.3246929190751445e-05, "loss": 0.2053, "step": 6192 }, { "epoch": 1.12, "learning_rate": 1.3244219653179191e-05, "loss": 0.7668, "step": 6193 }, { "epoch": 1.12, "learning_rate": 1.3241510115606937e-05, "loss": 0.2749, "step": 6194 }, { "epoch": 1.12, "learning_rate": 1.3238800578034683e-05, "loss": 0.3641, "step": 6195 }, { "epoch": 1.12, "learning_rate": 1.3236091040462429e-05, "loss": 0.7379, "step": 6196 }, { "epoch": 1.12, "learning_rate": 1.3233381502890173e-05, "loss": 0.0969, "step": 6197 }, { "epoch": 1.12, "learning_rate": 1.323067196531792e-05, "loss": 0.4739, "step": 6198 }, { "epoch": 1.12, "learning_rate": 1.3227962427745664e-05, "loss": 0.1774, "step": 6199 }, { "epoch": 1.12, "learning_rate": 1.3225252890173412e-05, "loss": 0.1935, "step": 6200 }, { "epoch": 1.12, "learning_rate": 1.3222543352601158e-05, "loss": 0.3352, "step": 6201 }, { "epoch": 1.12, "learning_rate": 1.3219833815028902e-05, "loss": 0.6596, "step": 6202 }, { "epoch": 1.12, "learning_rate": 1.3217124277456648e-05, "loss": 0.5452, "step": 6203 }, { "epoch": 1.12, "learning_rate": 1.3214414739884392e-05, "loss": 0.6329, "step": 6204 }, { "epoch": 1.12, "learning_rate": 1.321170520231214e-05, "loss": 0.3058, "step": 6205 }, { "epoch": 1.12, "learning_rate": 1.3208995664739885e-05, "loss": 0.1373, "step": 6206 }, { "epoch": 1.12, "learning_rate": 1.320628612716763e-05, "loss": 0.9577, "step": 6207 }, { "epoch": 1.12, "learning_rate": 1.3203576589595375e-05, "loss": 0.6432, "step": 6208 }, { "epoch": 1.12, "learning_rate": 1.3200867052023121e-05, "loss": 0.4533, "step": 6209 }, { "epoch": 1.12, "learning_rate": 1.3198157514450869e-05, "loss": 0.4394, "step": 6210 }, { "epoch": 1.12, "learning_rate": 1.3195447976878613e-05, "loss": 1.7342, "step": 6211 }, { "epoch": 1.12, "learning_rate": 1.319273843930636e-05, "loss": 1.1918, "step": 6212 }, { "epoch": 1.12, "learning_rate": 1.3190028901734104e-05, "loss": 0.7242, "step": 6213 }, { "epoch": 1.12, "learning_rate": 1.318731936416185e-05, "loss": 0.6633, "step": 6214 }, { "epoch": 1.12, "learning_rate": 1.3184609826589596e-05, "loss": 0.6075, "step": 6215 }, { "epoch": 1.12, "learning_rate": 1.3181900289017342e-05, "loss": 0.7986, "step": 6216 }, { "epoch": 1.12, "learning_rate": 1.3179190751445088e-05, "loss": 1.3931, "step": 6217 }, { "epoch": 1.12, "learning_rate": 1.3176481213872832e-05, "loss": 0.3653, "step": 6218 }, { "epoch": 1.12, "learning_rate": 1.3173771676300578e-05, "loss": 0.7268, "step": 6219 }, { "epoch": 1.12, "learning_rate": 1.3171062138728324e-05, "loss": 0.4167, "step": 6220 }, { "epoch": 1.12, "learning_rate": 1.316835260115607e-05, "loss": 0.6204, "step": 6221 }, { "epoch": 1.12, "learning_rate": 1.3165643063583815e-05, "loss": 0.293, "step": 6222 }, { "epoch": 1.12, "learning_rate": 1.316293352601156e-05, "loss": 0.2739, "step": 6223 }, { "epoch": 1.12, "learning_rate": 1.3160223988439307e-05, "loss": 0.6823, "step": 6224 }, { "epoch": 1.12, "learning_rate": 1.3157514450867053e-05, "loss": 0.7801, "step": 6225 }, { "epoch": 1.12, "learning_rate": 1.3154804913294799e-05, "loss": 0.2912, "step": 6226 }, { "epoch": 1.12, "learning_rate": 1.3152095375722543e-05, "loss": 0.5045, "step": 6227 }, { "epoch": 1.12, "learning_rate": 1.314938583815029e-05, "loss": 0.3751, "step": 6228 }, { "epoch": 1.13, "learning_rate": 1.3146676300578034e-05, "loss": 0.9345, "step": 6229 }, { "epoch": 1.13, "learning_rate": 1.3143966763005782e-05, "loss": 0.7737, "step": 6230 }, { "epoch": 1.13, "learning_rate": 1.3141257225433526e-05, "loss": 1.3425, "step": 6231 }, { "epoch": 1.13, "learning_rate": 1.3138547687861272e-05, "loss": 0.2205, "step": 6232 }, { "epoch": 1.13, "learning_rate": 1.3135838150289018e-05, "loss": 0.7547, "step": 6233 }, { "epoch": 1.13, "learning_rate": 1.3133128612716762e-05, "loss": 0.4675, "step": 6234 }, { "epoch": 1.13, "learning_rate": 1.313041907514451e-05, "loss": 1.1271, "step": 6235 }, { "epoch": 1.13, "learning_rate": 1.3127709537572254e-05, "loss": 0.4482, "step": 6236 }, { "epoch": 1.13, "learning_rate": 1.3125e-05, "loss": 0.4339, "step": 6237 }, { "epoch": 1.13, "learning_rate": 1.3122290462427745e-05, "loss": 0.7178, "step": 6238 }, { "epoch": 1.13, "learning_rate": 1.3119580924855491e-05, "loss": 0.3708, "step": 6239 }, { "epoch": 1.13, "learning_rate": 1.3116871387283239e-05, "loss": 0.5, "step": 6240 }, { "epoch": 1.13, "learning_rate": 1.3114161849710983e-05, "loss": 0.212, "step": 6241 }, { "epoch": 1.13, "learning_rate": 1.3111452312138729e-05, "loss": 1.1849, "step": 6242 }, { "epoch": 1.13, "learning_rate": 1.3108742774566474e-05, "loss": 0.3411, "step": 6243 }, { "epoch": 1.13, "learning_rate": 1.310603323699422e-05, "loss": 0.5276, "step": 6244 }, { "epoch": 1.13, "learning_rate": 1.3103323699421966e-05, "loss": 0.5929, "step": 6245 }, { "epoch": 1.13, "learning_rate": 1.3100614161849712e-05, "loss": 0.2848, "step": 6246 }, { "epoch": 1.13, "learning_rate": 1.3097904624277458e-05, "loss": 0.3617, "step": 6247 }, { "epoch": 1.13, "learning_rate": 1.3095195086705202e-05, "loss": 0.7511, "step": 6248 }, { "epoch": 1.13, "learning_rate": 1.3092485549132948e-05, "loss": 0.4322, "step": 6249 }, { "epoch": 1.13, "learning_rate": 1.3089776011560694e-05, "loss": 0.6843, "step": 6250 }, { "epoch": 1.13, "learning_rate": 1.308706647398844e-05, "loss": 0.4807, "step": 6251 }, { "epoch": 1.13, "learning_rate": 1.3084356936416185e-05, "loss": 0.5621, "step": 6252 }, { "epoch": 1.13, "learning_rate": 1.308164739884393e-05, "loss": 0.564, "step": 6253 }, { "epoch": 1.13, "learning_rate": 1.3078937861271675e-05, "loss": 0.7066, "step": 6254 }, { "epoch": 1.13, "learning_rate": 1.3076228323699423e-05, "loss": 1.26, "step": 6255 }, { "epoch": 1.13, "learning_rate": 1.3073518786127169e-05, "loss": 0.6031, "step": 6256 }, { "epoch": 1.13, "learning_rate": 1.3070809248554913e-05, "loss": 0.6774, "step": 6257 }, { "epoch": 1.13, "learning_rate": 1.306809971098266e-05, "loss": 0.8194, "step": 6258 }, { "epoch": 1.13, "learning_rate": 1.3065390173410404e-05, "loss": 0.6819, "step": 6259 }, { "epoch": 1.13, "learning_rate": 1.3062680635838151e-05, "loss": 0.3607, "step": 6260 }, { "epoch": 1.13, "learning_rate": 1.3059971098265896e-05, "loss": 0.5888, "step": 6261 }, { "epoch": 1.13, "learning_rate": 1.3057261560693642e-05, "loss": 0.7719, "step": 6262 }, { "epoch": 1.13, "learning_rate": 1.3054552023121388e-05, "loss": 0.8258, "step": 6263 }, { "epoch": 1.13, "learning_rate": 1.3051842485549132e-05, "loss": 0.9066, "step": 6264 }, { "epoch": 1.13, "learning_rate": 1.304913294797688e-05, "loss": 1.6444, "step": 6265 }, { "epoch": 1.13, "learning_rate": 1.3046423410404624e-05, "loss": 0.4536, "step": 6266 }, { "epoch": 1.13, "learning_rate": 1.304371387283237e-05, "loss": 0.8201, "step": 6267 }, { "epoch": 1.13, "learning_rate": 1.3041004335260115e-05, "loss": 0.6579, "step": 6268 }, { "epoch": 1.13, "learning_rate": 1.3038294797687861e-05, "loss": 0.4096, "step": 6269 }, { "epoch": 1.13, "learning_rate": 1.3035585260115609e-05, "loss": 0.6208, "step": 6270 }, { "epoch": 1.13, "learning_rate": 1.3032875722543353e-05, "loss": 0.6713, "step": 6271 }, { "epoch": 1.13, "learning_rate": 1.3030166184971099e-05, "loss": 0.6983, "step": 6272 }, { "epoch": 1.13, "learning_rate": 1.3027456647398843e-05, "loss": 0.3539, "step": 6273 }, { "epoch": 1.13, "learning_rate": 1.302474710982659e-05, "loss": 0.7619, "step": 6274 }, { "epoch": 1.13, "learning_rate": 1.3022037572254336e-05, "loss": 0.548, "step": 6275 }, { "epoch": 1.13, "learning_rate": 1.3019328034682082e-05, "loss": 1.2535, "step": 6276 }, { "epoch": 1.13, "learning_rate": 1.3016618497109826e-05, "loss": 0.4695, "step": 6277 }, { "epoch": 1.13, "learning_rate": 1.3013908959537572e-05, "loss": 0.4739, "step": 6278 }, { "epoch": 1.13, "learning_rate": 1.3011199421965318e-05, "loss": 0.3637, "step": 6279 }, { "epoch": 1.13, "learning_rate": 1.3008489884393064e-05, "loss": 0.5952, "step": 6280 }, { "epoch": 1.13, "learning_rate": 1.300578034682081e-05, "loss": 0.3567, "step": 6281 }, { "epoch": 1.13, "learning_rate": 1.3003070809248555e-05, "loss": 0.5965, "step": 6282 }, { "epoch": 1.13, "learning_rate": 1.30003612716763e-05, "loss": 1.1151, "step": 6283 }, { "epoch": 1.14, "learning_rate": 1.2997651734104047e-05, "loss": 0.5729, "step": 6284 }, { "epoch": 1.14, "learning_rate": 1.2994942196531793e-05, "loss": 0.5309, "step": 6285 }, { "epoch": 1.14, "learning_rate": 1.2992232658959539e-05, "loss": 0.5443, "step": 6286 }, { "epoch": 1.14, "learning_rate": 1.2989523121387283e-05, "loss": 0.4032, "step": 6287 }, { "epoch": 1.14, "learning_rate": 1.298681358381503e-05, "loss": 0.5186, "step": 6288 }, { "epoch": 1.14, "learning_rate": 1.2984104046242775e-05, "loss": 0.386, "step": 6289 }, { "epoch": 1.14, "learning_rate": 1.2981394508670521e-05, "loss": 0.763, "step": 6290 }, { "epoch": 1.14, "learning_rate": 1.2978684971098266e-05, "loss": 0.4115, "step": 6291 }, { "epoch": 1.14, "learning_rate": 1.2975975433526012e-05, "loss": 0.7524, "step": 6292 }, { "epoch": 1.14, "learning_rate": 1.2973265895953758e-05, "loss": 0.3153, "step": 6293 }, { "epoch": 1.14, "learning_rate": 1.2970556358381504e-05, "loss": 0.7117, "step": 6294 }, { "epoch": 1.14, "learning_rate": 1.296784682080925e-05, "loss": 0.3736, "step": 6295 }, { "epoch": 1.14, "learning_rate": 1.2965137283236994e-05, "loss": 0.4676, "step": 6296 }, { "epoch": 1.14, "learning_rate": 1.296242774566474e-05, "loss": 0.8025, "step": 6297 }, { "epoch": 1.14, "learning_rate": 1.2959718208092485e-05, "loss": 0.7098, "step": 6298 }, { "epoch": 1.14, "learning_rate": 1.2957008670520232e-05, "loss": 0.1533, "step": 6299 }, { "epoch": 1.14, "learning_rate": 1.2954299132947977e-05, "loss": 0.5926, "step": 6300 }, { "epoch": 1.14, "learning_rate": 1.2951589595375723e-05, "loss": 0.5702, "step": 6301 }, { "epoch": 1.14, "learning_rate": 1.2948880057803469e-05, "loss": 0.7421, "step": 6302 }, { "epoch": 1.14, "learning_rate": 1.2946170520231213e-05, "loss": 1.3559, "step": 6303 }, { "epoch": 1.14, "learning_rate": 1.2943460982658961e-05, "loss": 0.9598, "step": 6304 }, { "epoch": 1.14, "learning_rate": 1.2940751445086705e-05, "loss": 0.6596, "step": 6305 }, { "epoch": 1.14, "learning_rate": 1.2938041907514452e-05, "loss": 0.6519, "step": 6306 }, { "epoch": 1.14, "learning_rate": 1.2935332369942196e-05, "loss": 0.219, "step": 6307 }, { "epoch": 1.14, "learning_rate": 1.2932622832369942e-05, "loss": 0.668, "step": 6308 }, { "epoch": 1.14, "learning_rate": 1.292991329479769e-05, "loss": 0.6372, "step": 6309 }, { "epoch": 1.14, "learning_rate": 1.2927203757225434e-05, "loss": 0.0966, "step": 6310 }, { "epoch": 1.14, "learning_rate": 1.292449421965318e-05, "loss": 0.5667, "step": 6311 }, { "epoch": 1.14, "learning_rate": 1.2921784682080924e-05, "loss": 1.1907, "step": 6312 }, { "epoch": 1.14, "learning_rate": 1.291907514450867e-05, "loss": 0.8056, "step": 6313 }, { "epoch": 1.14, "learning_rate": 1.2916365606936417e-05, "loss": 0.7525, "step": 6314 }, { "epoch": 1.14, "learning_rate": 1.2913656069364163e-05, "loss": 0.3651, "step": 6315 }, { "epoch": 1.14, "learning_rate": 1.2910946531791907e-05, "loss": 0.1962, "step": 6316 }, { "epoch": 1.14, "learning_rate": 1.2908236994219653e-05, "loss": 0.9838, "step": 6317 }, { "epoch": 1.14, "learning_rate": 1.2905527456647399e-05, "loss": 0.3821, "step": 6318 }, { "epoch": 1.14, "learning_rate": 1.2902817919075145e-05, "loss": 0.8407, "step": 6319 }, { "epoch": 1.14, "learning_rate": 1.2900108381502891e-05, "loss": 0.5219, "step": 6320 }, { "epoch": 1.14, "learning_rate": 1.2897398843930636e-05, "loss": 0.5168, "step": 6321 }, { "epoch": 1.14, "learning_rate": 1.2894689306358382e-05, "loss": 0.3072, "step": 6322 }, { "epoch": 1.14, "learning_rate": 1.2891979768786126e-05, "loss": 0.5066, "step": 6323 }, { "epoch": 1.14, "learning_rate": 1.2889270231213874e-05, "loss": 0.4768, "step": 6324 }, { "epoch": 1.14, "learning_rate": 1.288656069364162e-05, "loss": 0.402, "step": 6325 }, { "epoch": 1.14, "learning_rate": 1.2883851156069364e-05, "loss": 0.4022, "step": 6326 }, { "epoch": 1.14, "learning_rate": 1.288114161849711e-05, "loss": 0.7028, "step": 6327 }, { "epoch": 1.14, "learning_rate": 1.2878432080924855e-05, "loss": 0.5322, "step": 6328 }, { "epoch": 1.14, "learning_rate": 1.2875722543352602e-05, "loss": 0.1892, "step": 6329 }, { "epoch": 1.14, "learning_rate": 1.2873013005780347e-05, "loss": 0.1541, "step": 6330 }, { "epoch": 1.14, "learning_rate": 1.2870303468208093e-05, "loss": 0.6575, "step": 6331 }, { "epoch": 1.14, "learning_rate": 1.2867593930635839e-05, "loss": 0.2725, "step": 6332 }, { "epoch": 1.14, "learning_rate": 1.2864884393063583e-05, "loss": 0.7111, "step": 6333 }, { "epoch": 1.14, "learning_rate": 1.2862174855491331e-05, "loss": 0.1897, "step": 6334 }, { "epoch": 1.14, "learning_rate": 1.2859465317919075e-05, "loss": 0.3063, "step": 6335 }, { "epoch": 1.14, "learning_rate": 1.2856755780346821e-05, "loss": 0.396, "step": 6336 }, { "epoch": 1.14, "learning_rate": 1.2854046242774566e-05, "loss": 1.0433, "step": 6337 }, { "epoch": 1.14, "learning_rate": 1.2851336705202312e-05, "loss": 0.632, "step": 6338 }, { "epoch": 1.15, "learning_rate": 1.2848627167630058e-05, "loss": 0.7754, "step": 6339 }, { "epoch": 1.15, "learning_rate": 1.2845917630057804e-05, "loss": 0.5996, "step": 6340 }, { "epoch": 1.15, "learning_rate": 1.284320809248555e-05, "loss": 0.2671, "step": 6341 }, { "epoch": 1.15, "learning_rate": 1.2840498554913294e-05, "loss": 0.5771, "step": 6342 }, { "epoch": 1.15, "learning_rate": 1.283778901734104e-05, "loss": 0.7515, "step": 6343 }, { "epoch": 1.15, "learning_rate": 1.2835079479768787e-05, "loss": 0.6874, "step": 6344 }, { "epoch": 1.15, "learning_rate": 1.2832369942196533e-05, "loss": 0.1838, "step": 6345 }, { "epoch": 1.15, "learning_rate": 1.2829660404624277e-05, "loss": 0.6524, "step": 6346 }, { "epoch": 1.15, "learning_rate": 1.2826950867052023e-05, "loss": 0.7038, "step": 6347 }, { "epoch": 1.15, "learning_rate": 1.2824241329479769e-05, "loss": 0.3313, "step": 6348 }, { "epoch": 1.15, "learning_rate": 1.2821531791907515e-05, "loss": 1.016, "step": 6349 }, { "epoch": 1.15, "learning_rate": 1.2818822254335261e-05, "loss": 0.5927, "step": 6350 }, { "epoch": 1.15, "learning_rate": 1.2816112716763006e-05, "loss": 1.467, "step": 6351 }, { "epoch": 1.15, "learning_rate": 1.2813403179190752e-05, "loss": 0.5307, "step": 6352 }, { "epoch": 1.15, "learning_rate": 1.2810693641618496e-05, "loss": 0.4891, "step": 6353 }, { "epoch": 1.15, "learning_rate": 1.2807984104046244e-05, "loss": 0.4576, "step": 6354 }, { "epoch": 1.15, "learning_rate": 1.280527456647399e-05, "loss": 0.4208, "step": 6355 }, { "epoch": 1.15, "learning_rate": 1.2802565028901734e-05, "loss": 0.4466, "step": 6356 }, { "epoch": 1.15, "learning_rate": 1.279985549132948e-05, "loss": 1.5123, "step": 6357 }, { "epoch": 1.15, "learning_rate": 1.2797145953757225e-05, "loss": 0.6571, "step": 6358 }, { "epoch": 1.15, "learning_rate": 1.2794436416184972e-05, "loss": 0.5518, "step": 6359 }, { "epoch": 1.15, "learning_rate": 1.2791726878612717e-05, "loss": 1.0149, "step": 6360 }, { "epoch": 1.15, "learning_rate": 1.2789017341040463e-05, "loss": 0.5295, "step": 6361 }, { "epoch": 1.15, "learning_rate": 1.2786307803468207e-05, "loss": 0.4477, "step": 6362 }, { "epoch": 1.15, "learning_rate": 1.2783598265895953e-05, "loss": 0.6095, "step": 6363 }, { "epoch": 1.15, "learning_rate": 1.2780888728323701e-05, "loss": 0.2129, "step": 6364 }, { "epoch": 1.15, "learning_rate": 1.2778179190751445e-05, "loss": 0.8767, "step": 6365 }, { "epoch": 1.15, "learning_rate": 1.2775469653179191e-05, "loss": 0.4322, "step": 6366 }, { "epoch": 1.15, "learning_rate": 1.2772760115606936e-05, "loss": 0.7241, "step": 6367 }, { "epoch": 1.15, "learning_rate": 1.2770050578034683e-05, "loss": 0.9218, "step": 6368 }, { "epoch": 1.15, "learning_rate": 1.2767341040462428e-05, "loss": 0.7479, "step": 6369 }, { "epoch": 1.15, "learning_rate": 1.2764631502890174e-05, "loss": 0.3471, "step": 6370 }, { "epoch": 1.15, "learning_rate": 1.276192196531792e-05, "loss": 0.6865, "step": 6371 }, { "epoch": 1.15, "learning_rate": 1.2759212427745664e-05, "loss": 1.2523, "step": 6372 }, { "epoch": 1.15, "learning_rate": 1.2756502890173412e-05, "loss": 0.5757, "step": 6373 }, { "epoch": 1.15, "learning_rate": 1.2753793352601156e-05, "loss": 0.9993, "step": 6374 }, { "epoch": 1.15, "learning_rate": 1.2751083815028902e-05, "loss": 0.8025, "step": 6375 }, { "epoch": 1.15, "learning_rate": 1.2748374277456647e-05, "loss": 0.7171, "step": 6376 }, { "epoch": 1.15, "learning_rate": 1.2745664739884393e-05, "loss": 0.7322, "step": 6377 }, { "epoch": 1.15, "learning_rate": 1.274295520231214e-05, "loss": 0.5911, "step": 6378 }, { "epoch": 1.15, "learning_rate": 1.2740245664739885e-05, "loss": 0.489, "step": 6379 }, { "epoch": 1.15, "learning_rate": 1.2737536127167631e-05, "loss": 0.8118, "step": 6380 }, { "epoch": 1.15, "learning_rate": 1.2734826589595375e-05, "loss": 0.4944, "step": 6381 }, { "epoch": 1.15, "learning_rate": 1.2732117052023122e-05, "loss": 0.4691, "step": 6382 }, { "epoch": 1.15, "learning_rate": 1.2729407514450868e-05, "loss": 0.5504, "step": 6383 }, { "epoch": 1.15, "learning_rate": 1.2726697976878614e-05, "loss": 0.6648, "step": 6384 }, { "epoch": 1.15, "learning_rate": 1.2723988439306358e-05, "loss": 0.1991, "step": 6385 }, { "epoch": 1.15, "learning_rate": 1.2721278901734104e-05, "loss": 0.3737, "step": 6386 }, { "epoch": 1.15, "learning_rate": 1.271856936416185e-05, "loss": 0.5264, "step": 6387 }, { "epoch": 1.15, "learning_rate": 1.2715859826589596e-05, "loss": 0.3072, "step": 6388 }, { "epoch": 1.15, "learning_rate": 1.2713150289017342e-05, "loss": 0.74, "step": 6389 }, { "epoch": 1.15, "learning_rate": 1.2710440751445087e-05, "loss": 0.7728, "step": 6390 }, { "epoch": 1.15, "learning_rate": 1.2707731213872833e-05, "loss": 0.3071, "step": 6391 }, { "epoch": 1.15, "learning_rate": 1.2705021676300577e-05, "loss": 0.8933, "step": 6392 }, { "epoch": 1.15, "learning_rate": 1.2702312138728325e-05, "loss": 1.4774, "step": 6393 }, { "epoch": 1.15, "learning_rate": 1.269960260115607e-05, "loss": 0.7289, "step": 6394 }, { "epoch": 1.16, "learning_rate": 1.2696893063583815e-05, "loss": 0.7215, "step": 6395 }, { "epoch": 1.16, "learning_rate": 1.2694183526011561e-05, "loss": 0.4186, "step": 6396 }, { "epoch": 1.16, "learning_rate": 1.2691473988439306e-05, "loss": 0.2028, "step": 6397 }, { "epoch": 1.16, "learning_rate": 1.2688764450867053e-05, "loss": 1.5029, "step": 6398 }, { "epoch": 1.16, "learning_rate": 1.2686054913294798e-05, "loss": 0.5708, "step": 6399 }, { "epoch": 1.16, "learning_rate": 1.2683345375722544e-05, "loss": 0.8072, "step": 6400 }, { "epoch": 1.16, "learning_rate": 1.268063583815029e-05, "loss": 0.8599, "step": 6401 }, { "epoch": 1.16, "learning_rate": 1.2677926300578034e-05, "loss": 0.8447, "step": 6402 }, { "epoch": 1.16, "learning_rate": 1.2675216763005782e-05, "loss": 0.5209, "step": 6403 }, { "epoch": 1.16, "learning_rate": 1.2672507225433526e-05, "loss": 0.6024, "step": 6404 }, { "epoch": 1.16, "learning_rate": 1.2669797687861272e-05, "loss": 0.2038, "step": 6405 }, { "epoch": 1.16, "learning_rate": 1.2667088150289017e-05, "loss": 0.8765, "step": 6406 }, { "epoch": 1.16, "learning_rate": 1.2664378612716763e-05, "loss": 0.4065, "step": 6407 }, { "epoch": 1.16, "learning_rate": 1.2661669075144509e-05, "loss": 0.671, "step": 6408 }, { "epoch": 1.16, "learning_rate": 1.2658959537572255e-05, "loss": 0.735, "step": 6409 }, { "epoch": 1.16, "learning_rate": 1.2656250000000001e-05, "loss": 0.9719, "step": 6410 }, { "epoch": 1.16, "learning_rate": 1.2653540462427745e-05, "loss": 0.8277, "step": 6411 }, { "epoch": 1.16, "learning_rate": 1.2650830924855491e-05, "loss": 0.3782, "step": 6412 }, { "epoch": 1.16, "learning_rate": 1.2648121387283237e-05, "loss": 0.9235, "step": 6413 }, { "epoch": 1.16, "learning_rate": 1.2645411849710984e-05, "loss": 0.3481, "step": 6414 }, { "epoch": 1.16, "learning_rate": 1.2642702312138728e-05, "loss": 0.4235, "step": 6415 }, { "epoch": 1.16, "learning_rate": 1.2639992774566474e-05, "loss": 0.7178, "step": 6416 }, { "epoch": 1.16, "learning_rate": 1.263728323699422e-05, "loss": 0.9455, "step": 6417 }, { "epoch": 1.16, "learning_rate": 1.2634573699421966e-05, "loss": 0.7354, "step": 6418 }, { "epoch": 1.16, "learning_rate": 1.2631864161849712e-05, "loss": 0.9108, "step": 6419 }, { "epoch": 1.16, "learning_rate": 1.2629154624277457e-05, "loss": 0.6388, "step": 6420 }, { "epoch": 1.16, "learning_rate": 1.2626445086705203e-05, "loss": 0.6579, "step": 6421 }, { "epoch": 1.16, "learning_rate": 1.2623735549132947e-05, "loss": 0.5167, "step": 6422 }, { "epoch": 1.16, "learning_rate": 1.2621026011560695e-05, "loss": 0.7617, "step": 6423 }, { "epoch": 1.16, "learning_rate": 1.2618316473988439e-05, "loss": 0.4026, "step": 6424 }, { "epoch": 1.16, "learning_rate": 1.2615606936416185e-05, "loss": 0.3017, "step": 6425 }, { "epoch": 1.16, "learning_rate": 1.2612897398843931e-05, "loss": 0.2599, "step": 6426 }, { "epoch": 1.16, "learning_rate": 1.2610187861271676e-05, "loss": 0.5398, "step": 6427 }, { "epoch": 1.16, "learning_rate": 1.2607478323699423e-05, "loss": 0.1863, "step": 6428 }, { "epoch": 1.16, "learning_rate": 1.2604768786127168e-05, "loss": 1.1016, "step": 6429 }, { "epoch": 1.16, "learning_rate": 1.2602059248554914e-05, "loss": 0.7707, "step": 6430 }, { "epoch": 1.16, "learning_rate": 1.2599349710982658e-05, "loss": 0.2286, "step": 6431 }, { "epoch": 1.16, "learning_rate": 1.2596640173410404e-05, "loss": 0.5343, "step": 6432 }, { "epoch": 1.16, "learning_rate": 1.2593930635838152e-05, "loss": 0.5196, "step": 6433 }, { "epoch": 1.16, "learning_rate": 1.2591221098265896e-05, "loss": 0.2146, "step": 6434 }, { "epoch": 1.16, "learning_rate": 1.2588511560693642e-05, "loss": 1.3474, "step": 6435 }, { "epoch": 1.16, "learning_rate": 1.2585802023121387e-05, "loss": 0.7583, "step": 6436 }, { "epoch": 1.16, "learning_rate": 1.2583092485549133e-05, "loss": 0.0972, "step": 6437 }, { "epoch": 1.16, "learning_rate": 1.2580382947976879e-05, "loss": 0.2268, "step": 6438 }, { "epoch": 1.16, "learning_rate": 1.2577673410404625e-05, "loss": 0.8671, "step": 6439 }, { "epoch": 1.16, "learning_rate": 1.2574963872832371e-05, "loss": 0.4605, "step": 6440 }, { "epoch": 1.16, "learning_rate": 1.2572254335260115e-05, "loss": 0.6834, "step": 6441 }, { "epoch": 1.16, "learning_rate": 1.2569544797687861e-05, "loss": 0.7176, "step": 6442 }, { "epoch": 1.16, "learning_rate": 1.2566835260115607e-05, "loss": 0.4882, "step": 6443 }, { "epoch": 1.16, "learning_rate": 1.2564125722543353e-05, "loss": 0.1371, "step": 6444 }, { "epoch": 1.16, "learning_rate": 1.2561416184971098e-05, "loss": 0.9129, "step": 6445 }, { "epoch": 1.16, "learning_rate": 1.2558706647398844e-05, "loss": 0.3288, "step": 6446 }, { "epoch": 1.16, "learning_rate": 1.255599710982659e-05, "loss": 0.3899, "step": 6447 }, { "epoch": 1.16, "learning_rate": 1.2553287572254336e-05, "loss": 0.5064, "step": 6448 }, { "epoch": 1.16, "learning_rate": 1.2550578034682082e-05, "loss": 0.3273, "step": 6449 }, { "epoch": 1.17, "learning_rate": 1.2547868497109826e-05, "loss": 1.1719, "step": 6450 }, { "epoch": 1.17, "learning_rate": 1.2545158959537572e-05, "loss": 0.4435, "step": 6451 }, { "epoch": 1.17, "learning_rate": 1.2542449421965317e-05, "loss": 0.6203, "step": 6452 }, { "epoch": 1.17, "learning_rate": 1.2539739884393065e-05, "loss": 0.4173, "step": 6453 }, { "epoch": 1.17, "learning_rate": 1.2537030346820809e-05, "loss": 0.6647, "step": 6454 }, { "epoch": 1.17, "learning_rate": 1.2534320809248555e-05, "loss": 0.754, "step": 6455 }, { "epoch": 1.17, "learning_rate": 1.2531611271676301e-05, "loss": 0.2958, "step": 6456 }, { "epoch": 1.17, "learning_rate": 1.2528901734104047e-05, "loss": 0.9068, "step": 6457 }, { "epoch": 1.17, "learning_rate": 1.2526192196531793e-05, "loss": 0.2682, "step": 6458 }, { "epoch": 1.17, "learning_rate": 1.2523482658959538e-05, "loss": 0.2559, "step": 6459 }, { "epoch": 1.17, "learning_rate": 1.2520773121387284e-05, "loss": 0.9009, "step": 6460 }, { "epoch": 1.17, "learning_rate": 1.2518063583815028e-05, "loss": 0.1812, "step": 6461 }, { "epoch": 1.17, "learning_rate": 1.2515354046242776e-05, "loss": 0.5656, "step": 6462 }, { "epoch": 1.17, "learning_rate": 1.2512644508670522e-05, "loss": 0.2364, "step": 6463 }, { "epoch": 1.17, "learning_rate": 1.2509934971098266e-05, "loss": 0.2343, "step": 6464 }, { "epoch": 1.17, "learning_rate": 1.2507225433526012e-05, "loss": 0.4612, "step": 6465 }, { "epoch": 1.17, "learning_rate": 1.2504515895953757e-05, "loss": 1.001, "step": 6466 }, { "epoch": 1.17, "learning_rate": 1.2501806358381504e-05, "loss": 0.4151, "step": 6467 }, { "epoch": 1.17, "learning_rate": 1.2499096820809249e-05, "loss": 0.2412, "step": 6468 }, { "epoch": 1.17, "learning_rate": 1.2496387283236995e-05, "loss": 0.3389, "step": 6469 }, { "epoch": 1.17, "learning_rate": 1.2493677745664739e-05, "loss": 0.8177, "step": 6470 }, { "epoch": 1.17, "learning_rate": 1.2490968208092485e-05, "loss": 0.7311, "step": 6471 }, { "epoch": 1.17, "learning_rate": 1.2488258670520233e-05, "loss": 0.8926, "step": 6472 }, { "epoch": 1.17, "learning_rate": 1.2485549132947977e-05, "loss": 0.9358, "step": 6473 }, { "epoch": 1.17, "learning_rate": 1.2482839595375723e-05, "loss": 0.2282, "step": 6474 }, { "epoch": 1.17, "learning_rate": 1.2480130057803468e-05, "loss": 0.728, "step": 6475 }, { "epoch": 1.17, "learning_rate": 1.2477420520231214e-05, "loss": 0.3119, "step": 6476 }, { "epoch": 1.17, "learning_rate": 1.247471098265896e-05, "loss": 0.4569, "step": 6477 }, { "epoch": 1.17, "learning_rate": 1.2472001445086706e-05, "loss": 0.3926, "step": 6478 }, { "epoch": 1.17, "learning_rate": 1.2469291907514452e-05, "loss": 0.8898, "step": 6479 }, { "epoch": 1.17, "learning_rate": 1.2466582369942196e-05, "loss": 0.2378, "step": 6480 }, { "epoch": 1.17, "learning_rate": 1.2463872832369942e-05, "loss": 0.5518, "step": 6481 }, { "epoch": 1.17, "learning_rate": 1.2461163294797688e-05, "loss": 0.7474, "step": 6482 }, { "epoch": 1.17, "learning_rate": 1.2458453757225435e-05, "loss": 0.5395, "step": 6483 }, { "epoch": 1.17, "learning_rate": 1.2455744219653179e-05, "loss": 0.6148, "step": 6484 }, { "epoch": 1.17, "learning_rate": 1.2453034682080925e-05, "loss": 0.732, "step": 6485 }, { "epoch": 1.17, "learning_rate": 1.2450325144508671e-05, "loss": 0.5423, "step": 6486 }, { "epoch": 1.17, "learning_rate": 1.2447615606936417e-05, "loss": 0.3094, "step": 6487 }, { "epoch": 1.17, "learning_rate": 1.2444906069364163e-05, "loss": 0.3505, "step": 6488 }, { "epoch": 1.17, "learning_rate": 1.2442196531791907e-05, "loss": 0.2999, "step": 6489 }, { "epoch": 1.17, "learning_rate": 1.2439486994219654e-05, "loss": 0.7305, "step": 6490 }, { "epoch": 1.17, "learning_rate": 1.2436777456647398e-05, "loss": 0.5094, "step": 6491 }, { "epoch": 1.17, "learning_rate": 1.2434067919075146e-05, "loss": 0.9921, "step": 6492 }, { "epoch": 1.17, "learning_rate": 1.243135838150289e-05, "loss": 1.7709, "step": 6493 }, { "epoch": 1.17, "learning_rate": 1.2428648843930636e-05, "loss": 0.8958, "step": 6494 }, { "epoch": 1.17, "learning_rate": 1.2425939306358382e-05, "loss": 0.592, "step": 6495 }, { "epoch": 1.17, "learning_rate": 1.2423229768786127e-05, "loss": 0.4463, "step": 6496 }, { "epoch": 1.17, "learning_rate": 1.2420520231213874e-05, "loss": 0.3025, "step": 6497 }, { "epoch": 1.17, "learning_rate": 1.2417810693641619e-05, "loss": 0.7237, "step": 6498 }, { "epoch": 1.17, "learning_rate": 1.2415101156069365e-05, "loss": 0.9175, "step": 6499 }, { "epoch": 1.17, "learning_rate": 1.2412391618497109e-05, "loss": 0.681, "step": 6500 }, { "epoch": 1.17, "eval_exact_match": 87.23746452223273, "eval_f1": 93.44392838668749, "step": 6500 }, { "epoch": 1.17, "learning_rate": 1.2409682080924855e-05, "loss": 0.3939, "step": 6501 }, { "epoch": 1.17, "learning_rate": 1.2406972543352603e-05, "loss": 0.563, "step": 6502 }, { "epoch": 1.17, "learning_rate": 1.2404263005780347e-05, "loss": 0.6305, "step": 6503 }, { "epoch": 1.17, "learning_rate": 1.2401553468208093e-05, "loss": 0.8572, "step": 6504 }, { "epoch": 1.18, "learning_rate": 1.2398843930635838e-05, "loss": 1.0294, "step": 6505 }, { "epoch": 1.18, "learning_rate": 1.2396134393063584e-05, "loss": 0.4658, "step": 6506 }, { "epoch": 1.18, "learning_rate": 1.239342485549133e-05, "loss": 0.8344, "step": 6507 }, { "epoch": 1.18, "learning_rate": 1.2390715317919076e-05, "loss": 0.3696, "step": 6508 }, { "epoch": 1.18, "learning_rate": 1.2388005780346822e-05, "loss": 0.3756, "step": 6509 }, { "epoch": 1.18, "learning_rate": 1.2385296242774566e-05, "loss": 0.3424, "step": 6510 }, { "epoch": 1.18, "learning_rate": 1.2382586705202312e-05, "loss": 0.3924, "step": 6511 }, { "epoch": 1.18, "learning_rate": 1.2379877167630058e-05, "loss": 0.3192, "step": 6512 }, { "epoch": 1.18, "learning_rate": 1.2377167630057804e-05, "loss": 0.4065, "step": 6513 }, { "epoch": 1.18, "learning_rate": 1.2374458092485549e-05, "loss": 0.8886, "step": 6514 }, { "epoch": 1.18, "learning_rate": 1.2371748554913295e-05, "loss": 0.811, "step": 6515 }, { "epoch": 1.18, "learning_rate": 1.236903901734104e-05, "loss": 0.6212, "step": 6516 }, { "epoch": 1.18, "learning_rate": 1.2366329479768787e-05, "loss": 0.6097, "step": 6517 }, { "epoch": 1.18, "learning_rate": 1.2363619942196533e-05, "loss": 0.6482, "step": 6518 }, { "epoch": 1.18, "learning_rate": 1.2360910404624277e-05, "loss": 1.1217, "step": 6519 }, { "epoch": 1.18, "learning_rate": 1.2358200867052023e-05, "loss": 0.9448, "step": 6520 }, { "epoch": 1.18, "learning_rate": 1.2355491329479768e-05, "loss": 0.9156, "step": 6521 }, { "epoch": 1.18, "learning_rate": 1.2352781791907516e-05, "loss": 0.974, "step": 6522 }, { "epoch": 1.18, "learning_rate": 1.235007225433526e-05, "loss": 0.6507, "step": 6523 }, { "epoch": 1.18, "learning_rate": 1.2347362716763006e-05, "loss": 0.5682, "step": 6524 }, { "epoch": 1.18, "learning_rate": 1.2344653179190752e-05, "loss": 0.3975, "step": 6525 }, { "epoch": 1.18, "learning_rate": 1.2341943641618496e-05, "loss": 0.7072, "step": 6526 }, { "epoch": 1.18, "learning_rate": 1.2339234104046244e-05, "loss": 0.9142, "step": 6527 }, { "epoch": 1.18, "learning_rate": 1.2336524566473989e-05, "loss": 0.801, "step": 6528 }, { "epoch": 1.18, "learning_rate": 1.2333815028901735e-05, "loss": 0.3911, "step": 6529 }, { "epoch": 1.18, "learning_rate": 1.2331105491329479e-05, "loss": 0.9682, "step": 6530 }, { "epoch": 1.18, "learning_rate": 1.2328395953757225e-05, "loss": 0.3875, "step": 6531 }, { "epoch": 1.18, "learning_rate": 1.2325686416184971e-05, "loss": 0.4621, "step": 6532 }, { "epoch": 1.18, "learning_rate": 1.2322976878612717e-05, "loss": 1.0908, "step": 6533 }, { "epoch": 1.18, "learning_rate": 1.2320267341040463e-05, "loss": 0.4327, "step": 6534 }, { "epoch": 1.18, "learning_rate": 1.2317557803468208e-05, "loss": 0.3233, "step": 6535 }, { "epoch": 1.18, "learning_rate": 1.2314848265895954e-05, "loss": 0.2798, "step": 6536 }, { "epoch": 1.18, "learning_rate": 1.23121387283237e-05, "loss": 1.6422, "step": 6537 }, { "epoch": 1.18, "learning_rate": 1.2309429190751446e-05, "loss": 0.407, "step": 6538 }, { "epoch": 1.18, "learning_rate": 1.230671965317919e-05, "loss": 0.9572, "step": 6539 }, { "epoch": 1.18, "learning_rate": 1.2304010115606936e-05, "loss": 0.5112, "step": 6540 }, { "epoch": 1.18, "learning_rate": 1.2301300578034684e-05, "loss": 0.2979, "step": 6541 }, { "epoch": 1.18, "learning_rate": 1.2298591040462428e-05, "loss": 0.6266, "step": 6542 }, { "epoch": 1.18, "learning_rate": 1.2295881502890174e-05, "loss": 0.3154, "step": 6543 }, { "epoch": 1.18, "learning_rate": 1.2293171965317919e-05, "loss": 0.2517, "step": 6544 }, { "epoch": 1.18, "learning_rate": 1.2290462427745665e-05, "loss": 0.0694, "step": 6545 }, { "epoch": 1.18, "learning_rate": 1.228775289017341e-05, "loss": 0.3604, "step": 6546 }, { "epoch": 1.18, "learning_rate": 1.2285043352601157e-05, "loss": 0.3842, "step": 6547 }, { "epoch": 1.18, "learning_rate": 1.2282333815028903e-05, "loss": 0.8663, "step": 6548 }, { "epoch": 1.18, "learning_rate": 1.2279624277456647e-05, "loss": 0.2827, "step": 6549 }, { "epoch": 1.18, "learning_rate": 1.2276914739884393e-05, "loss": 0.2454, "step": 6550 }, { "epoch": 1.18, "learning_rate": 1.227420520231214e-05, "loss": 0.3824, "step": 6551 }, { "epoch": 1.18, "learning_rate": 1.2271495664739885e-05, "loss": 0.4753, "step": 6552 }, { "epoch": 1.18, "learning_rate": 1.226878612716763e-05, "loss": 0.9113, "step": 6553 }, { "epoch": 1.18, "learning_rate": 1.2266076589595376e-05, "loss": 0.5106, "step": 6554 }, { "epoch": 1.18, "learning_rate": 1.2263367052023122e-05, "loss": 0.4692, "step": 6555 }, { "epoch": 1.18, "learning_rate": 1.2260657514450868e-05, "loss": 1.5071, "step": 6556 }, { "epoch": 1.18, "learning_rate": 1.2257947976878614e-05, "loss": 1.2358, "step": 6557 }, { "epoch": 1.18, "learning_rate": 1.2255238439306358e-05, "loss": 0.8741, "step": 6558 }, { "epoch": 1.18, "learning_rate": 1.2252528901734105e-05, "loss": 0.5963, "step": 6559 }, { "epoch": 1.18, "learning_rate": 1.2249819364161849e-05, "loss": 0.4378, "step": 6560 }, { "epoch": 1.19, "learning_rate": 1.2247109826589597e-05, "loss": 0.4336, "step": 6561 }, { "epoch": 1.19, "learning_rate": 1.2244400289017341e-05, "loss": 0.4761, "step": 6562 }, { "epoch": 1.19, "learning_rate": 1.2241690751445087e-05, "loss": 0.1429, "step": 6563 }, { "epoch": 1.19, "learning_rate": 1.2238981213872833e-05, "loss": 0.5912, "step": 6564 }, { "epoch": 1.19, "learning_rate": 1.2236271676300577e-05, "loss": 0.346, "step": 6565 }, { "epoch": 1.19, "learning_rate": 1.2233562138728325e-05, "loss": 0.4987, "step": 6566 }, { "epoch": 1.19, "learning_rate": 1.223085260115607e-05, "loss": 0.2067, "step": 6567 }, { "epoch": 1.19, "learning_rate": 1.2228143063583816e-05, "loss": 0.3056, "step": 6568 }, { "epoch": 1.19, "learning_rate": 1.222543352601156e-05, "loss": 0.5313, "step": 6569 }, { "epoch": 1.19, "learning_rate": 1.2222723988439306e-05, "loss": 0.5089, "step": 6570 }, { "epoch": 1.19, "learning_rate": 1.2220014450867054e-05, "loss": 0.1451, "step": 6571 }, { "epoch": 1.19, "learning_rate": 1.2217304913294798e-05, "loss": 0.4293, "step": 6572 }, { "epoch": 1.19, "learning_rate": 1.2214595375722544e-05, "loss": 0.7482, "step": 6573 }, { "epoch": 1.19, "learning_rate": 1.2211885838150289e-05, "loss": 0.5123, "step": 6574 }, { "epoch": 1.19, "learning_rate": 1.2209176300578035e-05, "loss": 1.0515, "step": 6575 }, { "epoch": 1.19, "learning_rate": 1.220646676300578e-05, "loss": 0.6855, "step": 6576 }, { "epoch": 1.19, "learning_rate": 1.2203757225433527e-05, "loss": 1.1573, "step": 6577 }, { "epoch": 1.19, "learning_rate": 1.2201047687861271e-05, "loss": 0.4044, "step": 6578 }, { "epoch": 1.19, "learning_rate": 1.2198338150289017e-05, "loss": 0.4246, "step": 6579 }, { "epoch": 1.19, "learning_rate": 1.2195628612716763e-05, "loss": 0.6849, "step": 6580 }, { "epoch": 1.19, "learning_rate": 1.219291907514451e-05, "loss": 0.8859, "step": 6581 }, { "epoch": 1.19, "learning_rate": 1.2190209537572255e-05, "loss": 0.6332, "step": 6582 }, { "epoch": 1.19, "learning_rate": 1.21875e-05, "loss": 1.0848, "step": 6583 }, { "epoch": 1.19, "learning_rate": 1.2184790462427746e-05, "loss": 0.9305, "step": 6584 }, { "epoch": 1.19, "learning_rate": 1.218208092485549e-05, "loss": 0.6074, "step": 6585 }, { "epoch": 1.19, "learning_rate": 1.2179371387283238e-05, "loss": 0.4592, "step": 6586 }, { "epoch": 1.19, "learning_rate": 1.2176661849710984e-05, "loss": 0.7208, "step": 6587 }, { "epoch": 1.19, "learning_rate": 1.2173952312138728e-05, "loss": 0.2886, "step": 6588 }, { "epoch": 1.19, "learning_rate": 1.2171242774566474e-05, "loss": 0.5013, "step": 6589 }, { "epoch": 1.19, "learning_rate": 1.2168533236994219e-05, "loss": 0.5507, "step": 6590 }, { "epoch": 1.19, "learning_rate": 1.2165823699421967e-05, "loss": 0.2191, "step": 6591 }, { "epoch": 1.19, "learning_rate": 1.2163114161849711e-05, "loss": 0.2583, "step": 6592 }, { "epoch": 1.19, "learning_rate": 1.2160404624277457e-05, "loss": 0.4256, "step": 6593 }, { "epoch": 1.19, "learning_rate": 1.2157695086705203e-05, "loss": 0.8914, "step": 6594 }, { "epoch": 1.19, "learning_rate": 1.2154985549132947e-05, "loss": 0.4334, "step": 6595 }, { "epoch": 1.19, "learning_rate": 1.2152276011560695e-05, "loss": 0.7911, "step": 6596 }, { "epoch": 1.19, "learning_rate": 1.214956647398844e-05, "loss": 0.6896, "step": 6597 }, { "epoch": 1.19, "learning_rate": 1.2146856936416186e-05, "loss": 0.2308, "step": 6598 }, { "epoch": 1.19, "learning_rate": 1.214414739884393e-05, "loss": 1.074, "step": 6599 }, { "epoch": 1.19, "learning_rate": 1.2141437861271676e-05, "loss": 0.6014, "step": 6600 }, { "epoch": 1.19, "learning_rate": 1.2138728323699422e-05, "loss": 0.5895, "step": 6601 }, { "epoch": 1.19, "learning_rate": 1.2136018786127168e-05, "loss": 0.5956, "step": 6602 }, { "epoch": 1.19, "learning_rate": 1.2133309248554914e-05, "loss": 0.86, "step": 6603 }, { "epoch": 1.19, "learning_rate": 1.2130599710982659e-05, "loss": 0.282, "step": 6604 }, { "epoch": 1.19, "learning_rate": 1.2127890173410405e-05, "loss": 0.2233, "step": 6605 }, { "epoch": 1.19, "learning_rate": 1.212518063583815e-05, "loss": 0.8766, "step": 6606 }, { "epoch": 1.19, "learning_rate": 1.2122471098265897e-05, "loss": 0.5321, "step": 6607 }, { "epoch": 1.19, "learning_rate": 1.2119761560693641e-05, "loss": 0.1955, "step": 6608 }, { "epoch": 1.19, "learning_rate": 1.2117052023121387e-05, "loss": 0.9899, "step": 6609 }, { "epoch": 1.19, "learning_rate": 1.2114342485549133e-05, "loss": 0.3914, "step": 6610 }, { "epoch": 1.19, "learning_rate": 1.211163294797688e-05, "loss": 0.9092, "step": 6611 }, { "epoch": 1.19, "learning_rate": 1.2108923410404625e-05, "loss": 0.9313, "step": 6612 }, { "epoch": 1.19, "learning_rate": 1.210621387283237e-05, "loss": 0.5596, "step": 6613 }, { "epoch": 1.19, "learning_rate": 1.2103504335260116e-05, "loss": 0.9625, "step": 6614 }, { "epoch": 1.19, "learning_rate": 1.210079479768786e-05, "loss": 0.9004, "step": 6615 }, { "epoch": 1.2, "learning_rate": 1.2098085260115608e-05, "loss": 0.4416, "step": 6616 }, { "epoch": 1.2, "learning_rate": 1.2095375722543354e-05, "loss": 0.9087, "step": 6617 }, { "epoch": 1.2, "learning_rate": 1.2092666184971098e-05, "loss": 0.7872, "step": 6618 }, { "epoch": 1.2, "learning_rate": 1.2089956647398844e-05, "loss": 0.6868, "step": 6619 }, { "epoch": 1.2, "learning_rate": 1.2087247109826589e-05, "loss": 0.8656, "step": 6620 }, { "epoch": 1.2, "learning_rate": 1.2084537572254336e-05, "loss": 0.9362, "step": 6621 }, { "epoch": 1.2, "learning_rate": 1.208182803468208e-05, "loss": 0.97, "step": 6622 }, { "epoch": 1.2, "learning_rate": 1.2079118497109827e-05, "loss": 0.9571, "step": 6623 }, { "epoch": 1.2, "learning_rate": 1.2076408959537571e-05, "loss": 0.7246, "step": 6624 }, { "epoch": 1.2, "learning_rate": 1.2073699421965317e-05, "loss": 0.5149, "step": 6625 }, { "epoch": 1.2, "learning_rate": 1.2070989884393065e-05, "loss": 0.5835, "step": 6626 }, { "epoch": 1.2, "learning_rate": 1.206828034682081e-05, "loss": 0.5393, "step": 6627 }, { "epoch": 1.2, "learning_rate": 1.2065570809248555e-05, "loss": 0.3598, "step": 6628 }, { "epoch": 1.2, "learning_rate": 1.20628612716763e-05, "loss": 0.7637, "step": 6629 }, { "epoch": 1.2, "learning_rate": 1.2060151734104048e-05, "loss": 0.5272, "step": 6630 }, { "epoch": 1.2, "learning_rate": 1.2057442196531792e-05, "loss": 0.3243, "step": 6631 }, { "epoch": 1.2, "learning_rate": 1.2054732658959538e-05, "loss": 0.8102, "step": 6632 }, { "epoch": 1.2, "learning_rate": 1.2052023121387284e-05, "loss": 0.6592, "step": 6633 }, { "epoch": 1.2, "learning_rate": 1.2049313583815028e-05, "loss": 0.3414, "step": 6634 }, { "epoch": 1.2, "learning_rate": 1.2046604046242776e-05, "loss": 0.7525, "step": 6635 }, { "epoch": 1.2, "learning_rate": 1.204389450867052e-05, "loss": 0.7551, "step": 6636 }, { "epoch": 1.2, "learning_rate": 1.2041184971098267e-05, "loss": 0.6268, "step": 6637 }, { "epoch": 1.2, "learning_rate": 1.2038475433526011e-05, "loss": 0.3004, "step": 6638 }, { "epoch": 1.2, "learning_rate": 1.2035765895953757e-05, "loss": 0.4566, "step": 6639 }, { "epoch": 1.2, "learning_rate": 1.2033056358381505e-05, "loss": 0.603, "step": 6640 }, { "epoch": 1.2, "learning_rate": 1.203034682080925e-05, "loss": 1.0249, "step": 6641 }, { "epoch": 1.2, "learning_rate": 1.2027637283236995e-05, "loss": 0.3974, "step": 6642 }, { "epoch": 1.2, "learning_rate": 1.202492774566474e-05, "loss": 0.4232, "step": 6643 }, { "epoch": 1.2, "learning_rate": 1.2022218208092486e-05, "loss": 0.272, "step": 6644 }, { "epoch": 1.2, "learning_rate": 1.2019508670520232e-05, "loss": 0.4175, "step": 6645 }, { "epoch": 1.2, "learning_rate": 1.2016799132947978e-05, "loss": 0.5245, "step": 6646 }, { "epoch": 1.2, "learning_rate": 1.2014089595375722e-05, "loss": 0.5782, "step": 6647 }, { "epoch": 1.2, "learning_rate": 1.2011380057803468e-05, "loss": 0.3664, "step": 6648 }, { "epoch": 1.2, "learning_rate": 1.2008670520231214e-05, "loss": 1.0274, "step": 6649 }, { "epoch": 1.2, "learning_rate": 1.200596098265896e-05, "loss": 0.9671, "step": 6650 }, { "epoch": 1.2, "learning_rate": 1.2003251445086706e-05, "loss": 0.936, "step": 6651 }, { "epoch": 1.2, "learning_rate": 1.200054190751445e-05, "loss": 0.4715, "step": 6652 }, { "epoch": 1.2, "learning_rate": 1.1997832369942197e-05, "loss": 0.7381, "step": 6653 }, { "epoch": 1.2, "learning_rate": 1.1995122832369941e-05, "loss": 0.6868, "step": 6654 }, { "epoch": 1.2, "learning_rate": 1.1992413294797689e-05, "loss": 0.6403, "step": 6655 }, { "epoch": 1.2, "learning_rate": 1.1989703757225435e-05, "loss": 0.4293, "step": 6656 }, { "epoch": 1.2, "learning_rate": 1.198699421965318e-05, "loss": 0.7356, "step": 6657 }, { "epoch": 1.2, "learning_rate": 1.1984284682080925e-05, "loss": 0.5708, "step": 6658 }, { "epoch": 1.2, "learning_rate": 1.198157514450867e-05, "loss": 0.5373, "step": 6659 }, { "epoch": 1.2, "learning_rate": 1.1978865606936418e-05, "loss": 0.473, "step": 6660 }, { "epoch": 1.2, "learning_rate": 1.1976156069364162e-05, "loss": 0.4404, "step": 6661 }, { "epoch": 1.2, "learning_rate": 1.1973446531791908e-05, "loss": 1.0028, "step": 6662 }, { "epoch": 1.2, "learning_rate": 1.1970736994219654e-05, "loss": 0.1979, "step": 6663 }, { "epoch": 1.2, "learning_rate": 1.1968027456647398e-05, "loss": 0.8711, "step": 6664 }, { "epoch": 1.2, "learning_rate": 1.1965317919075146e-05, "loss": 0.3939, "step": 6665 }, { "epoch": 1.2, "learning_rate": 1.196260838150289e-05, "loss": 0.3801, "step": 6666 }, { "epoch": 1.2, "learning_rate": 1.1959898843930637e-05, "loss": 1.0212, "step": 6667 }, { "epoch": 1.2, "learning_rate": 1.1957189306358381e-05, "loss": 0.2072, "step": 6668 }, { "epoch": 1.2, "learning_rate": 1.1954479768786127e-05, "loss": 0.7061, "step": 6669 }, { "epoch": 1.2, "learning_rate": 1.1951770231213873e-05, "loss": 0.4849, "step": 6670 }, { "epoch": 1.21, "learning_rate": 1.1949060693641619e-05, "loss": 0.5711, "step": 6671 }, { "epoch": 1.21, "learning_rate": 1.1946351156069365e-05, "loss": 0.4798, "step": 6672 }, { "epoch": 1.21, "learning_rate": 1.194364161849711e-05, "loss": 0.4556, "step": 6673 }, { "epoch": 1.21, "learning_rate": 1.1940932080924856e-05, "loss": 0.393, "step": 6674 }, { "epoch": 1.21, "learning_rate": 1.1938222543352602e-05, "loss": 0.2792, "step": 6675 }, { "epoch": 1.21, "learning_rate": 1.1935513005780348e-05, "loss": 0.1218, "step": 6676 }, { "epoch": 1.21, "learning_rate": 1.1932803468208092e-05, "loss": 0.5657, "step": 6677 }, { "epoch": 1.21, "learning_rate": 1.1930093930635838e-05, "loss": 1.0362, "step": 6678 }, { "epoch": 1.21, "learning_rate": 1.1927384393063584e-05, "loss": 0.9408, "step": 6679 }, { "epoch": 1.21, "learning_rate": 1.192467485549133e-05, "loss": 0.9949, "step": 6680 }, { "epoch": 1.21, "learning_rate": 1.1921965317919076e-05, "loss": 0.6775, "step": 6681 }, { "epoch": 1.21, "learning_rate": 1.191925578034682e-05, "loss": 0.6088, "step": 6682 }, { "epoch": 1.21, "learning_rate": 1.1916546242774567e-05, "loss": 0.6466, "step": 6683 }, { "epoch": 1.21, "learning_rate": 1.1913836705202311e-05, "loss": 0.842, "step": 6684 }, { "epoch": 1.21, "learning_rate": 1.1911127167630059e-05, "loss": 0.2454, "step": 6685 }, { "epoch": 1.21, "learning_rate": 1.1908417630057803e-05, "loss": 0.7159, "step": 6686 }, { "epoch": 1.21, "learning_rate": 1.190570809248555e-05, "loss": 0.3256, "step": 6687 }, { "epoch": 1.21, "learning_rate": 1.1902998554913295e-05, "loss": 0.1854, "step": 6688 }, { "epoch": 1.21, "learning_rate": 1.190028901734104e-05, "loss": 0.3506, "step": 6689 }, { "epoch": 1.21, "learning_rate": 1.1897579479768787e-05, "loss": 0.6762, "step": 6690 }, { "epoch": 1.21, "learning_rate": 1.1894869942196532e-05, "loss": 0.604, "step": 6691 }, { "epoch": 1.21, "learning_rate": 1.1892160404624278e-05, "loss": 0.5642, "step": 6692 }, { "epoch": 1.21, "learning_rate": 1.1889450867052022e-05, "loss": 0.6351, "step": 6693 }, { "epoch": 1.21, "learning_rate": 1.1886741329479768e-05, "loss": 0.4297, "step": 6694 }, { "epoch": 1.21, "learning_rate": 1.1884031791907516e-05, "loss": 0.586, "step": 6695 }, { "epoch": 1.21, "learning_rate": 1.188132225433526e-05, "loss": 0.4408, "step": 6696 }, { "epoch": 1.21, "learning_rate": 1.1878612716763006e-05, "loss": 0.6014, "step": 6697 }, { "epoch": 1.21, "learning_rate": 1.187590317919075e-05, "loss": 0.4408, "step": 6698 }, { "epoch": 1.21, "learning_rate": 1.1873193641618497e-05, "loss": 0.8825, "step": 6699 }, { "epoch": 1.21, "learning_rate": 1.1870484104046243e-05, "loss": 0.352, "step": 6700 }, { "epoch": 1.21, "learning_rate": 1.1867774566473989e-05, "loss": 0.8919, "step": 6701 }, { "epoch": 1.21, "learning_rate": 1.1865065028901735e-05, "loss": 0.5341, "step": 6702 }, { "epoch": 1.21, "learning_rate": 1.186235549132948e-05, "loss": 0.5709, "step": 6703 }, { "epoch": 1.21, "learning_rate": 1.1859645953757225e-05, "loss": 0.3371, "step": 6704 }, { "epoch": 1.21, "learning_rate": 1.1856936416184972e-05, "loss": 0.3926, "step": 6705 }, { "epoch": 1.21, "learning_rate": 1.1854226878612718e-05, "loss": 0.3906, "step": 6706 }, { "epoch": 1.21, "learning_rate": 1.1851517341040462e-05, "loss": 0.4208, "step": 6707 }, { "epoch": 1.21, "learning_rate": 1.1848807803468208e-05, "loss": 0.9988, "step": 6708 }, { "epoch": 1.21, "learning_rate": 1.1846098265895952e-05, "loss": 0.9329, "step": 6709 }, { "epoch": 1.21, "learning_rate": 1.18433887283237e-05, "loss": 0.3433, "step": 6710 }, { "epoch": 1.21, "learning_rate": 1.1840679190751446e-05, "loss": 0.3896, "step": 6711 }, { "epoch": 1.21, "learning_rate": 1.183796965317919e-05, "loss": 1.0047, "step": 6712 }, { "epoch": 1.21, "learning_rate": 1.1835260115606937e-05, "loss": 0.4668, "step": 6713 }, { "epoch": 1.21, "learning_rate": 1.1832550578034683e-05, "loss": 0.6653, "step": 6714 }, { "epoch": 1.21, "learning_rate": 1.1829841040462429e-05, "loss": 0.2871, "step": 6715 }, { "epoch": 1.21, "learning_rate": 1.1827131502890173e-05, "loss": 0.6876, "step": 6716 }, { "epoch": 1.21, "learning_rate": 1.182442196531792e-05, "loss": 0.6989, "step": 6717 }, { "epoch": 1.21, "learning_rate": 1.1821712427745665e-05, "loss": 1.0294, "step": 6718 }, { "epoch": 1.21, "learning_rate": 1.1819002890173411e-05, "loss": 1.0418, "step": 6719 }, { "epoch": 1.21, "learning_rate": 1.1816293352601157e-05, "loss": 0.4938, "step": 6720 }, { "epoch": 1.21, "learning_rate": 1.1813583815028902e-05, "loss": 0.3795, "step": 6721 }, { "epoch": 1.21, "learning_rate": 1.1810874277456648e-05, "loss": 0.5859, "step": 6722 }, { "epoch": 1.21, "learning_rate": 1.1808164739884392e-05, "loss": 0.7076, "step": 6723 }, { "epoch": 1.21, "learning_rate": 1.180545520231214e-05, "loss": 0.6502, "step": 6724 }, { "epoch": 1.21, "learning_rate": 1.1802745664739886e-05, "loss": 0.3006, "step": 6725 }, { "epoch": 1.21, "learning_rate": 1.180003612716763e-05, "loss": 0.365, "step": 6726 }, { "epoch": 1.22, "learning_rate": 1.1797326589595376e-05, "loss": 0.5838, "step": 6727 }, { "epoch": 1.22, "learning_rate": 1.179461705202312e-05, "loss": 0.5068, "step": 6728 }, { "epoch": 1.22, "learning_rate": 1.1791907514450869e-05, "loss": 0.4646, "step": 6729 }, { "epoch": 1.22, "learning_rate": 1.1789197976878613e-05, "loss": 0.2191, "step": 6730 }, { "epoch": 1.22, "learning_rate": 1.1786488439306359e-05, "loss": 0.3434, "step": 6731 }, { "epoch": 1.22, "learning_rate": 1.1783778901734103e-05, "loss": 0.2554, "step": 6732 }, { "epoch": 1.22, "learning_rate": 1.178106936416185e-05, "loss": 0.7116, "step": 6733 }, { "epoch": 1.22, "learning_rate": 1.1778359826589597e-05, "loss": 0.7705, "step": 6734 }, { "epoch": 1.22, "learning_rate": 1.1775650289017341e-05, "loss": 0.5616, "step": 6735 }, { "epoch": 1.22, "learning_rate": 1.1772940751445088e-05, "loss": 0.6106, "step": 6736 }, { "epoch": 1.22, "learning_rate": 1.1770231213872832e-05, "loss": 0.4712, "step": 6737 }, { "epoch": 1.22, "learning_rate": 1.1767521676300578e-05, "loss": 1.0112, "step": 6738 }, { "epoch": 1.22, "learning_rate": 1.1764812138728324e-05, "loss": 0.3236, "step": 6739 }, { "epoch": 1.22, "learning_rate": 1.176210260115607e-05, "loss": 0.4053, "step": 6740 }, { "epoch": 1.22, "learning_rate": 1.1759393063583816e-05, "loss": 0.9995, "step": 6741 }, { "epoch": 1.22, "learning_rate": 1.175668352601156e-05, "loss": 0.4447, "step": 6742 }, { "epoch": 1.22, "learning_rate": 1.1753973988439307e-05, "loss": 0.2685, "step": 6743 }, { "epoch": 1.22, "learning_rate": 1.1751264450867053e-05, "loss": 0.8258, "step": 6744 }, { "epoch": 1.22, "learning_rate": 1.1748554913294799e-05, "loss": 0.709, "step": 6745 }, { "epoch": 1.22, "learning_rate": 1.1745845375722543e-05, "loss": 0.6431, "step": 6746 }, { "epoch": 1.22, "learning_rate": 1.1743135838150289e-05, "loss": 1.0286, "step": 6747 }, { "epoch": 1.22, "learning_rate": 1.1740426300578035e-05, "loss": 0.3851, "step": 6748 }, { "epoch": 1.22, "learning_rate": 1.1737716763005781e-05, "loss": 0.6555, "step": 6749 }, { "epoch": 1.22, "learning_rate": 1.1735007225433527e-05, "loss": 0.4879, "step": 6750 }, { "epoch": 1.22, "learning_rate": 1.1732297687861272e-05, "loss": 0.4025, "step": 6751 }, { "epoch": 1.22, "learning_rate": 1.1729588150289018e-05, "loss": 0.5988, "step": 6752 }, { "epoch": 1.22, "learning_rate": 1.1726878612716762e-05, "loss": 0.6652, "step": 6753 }, { "epoch": 1.22, "learning_rate": 1.172416907514451e-05, "loss": 0.1032, "step": 6754 }, { "epoch": 1.22, "learning_rate": 1.1721459537572254e-05, "loss": 0.4661, "step": 6755 }, { "epoch": 1.22, "learning_rate": 1.171875e-05, "loss": 0.3574, "step": 6756 }, { "epoch": 1.22, "learning_rate": 1.1716040462427746e-05, "loss": 0.5929, "step": 6757 }, { "epoch": 1.22, "learning_rate": 1.171333092485549e-05, "loss": 1.3373, "step": 6758 }, { "epoch": 1.22, "learning_rate": 1.1710621387283238e-05, "loss": 0.6143, "step": 6759 }, { "epoch": 1.22, "learning_rate": 1.1707911849710983e-05, "loss": 1.5142, "step": 6760 }, { "epoch": 1.22, "learning_rate": 1.1705202312138729e-05, "loss": 0.3608, "step": 6761 }, { "epoch": 1.22, "learning_rate": 1.1702492774566473e-05, "loss": 0.573, "step": 6762 }, { "epoch": 1.22, "learning_rate": 1.169978323699422e-05, "loss": 0.8672, "step": 6763 }, { "epoch": 1.22, "learning_rate": 1.1697073699421967e-05, "loss": 0.2726, "step": 6764 }, { "epoch": 1.22, "learning_rate": 1.1694364161849711e-05, "loss": 0.8099, "step": 6765 }, { "epoch": 1.22, "learning_rate": 1.1691654624277457e-05, "loss": 0.4263, "step": 6766 }, { "epoch": 1.22, "learning_rate": 1.1688945086705202e-05, "loss": 0.2618, "step": 6767 }, { "epoch": 1.22, "learning_rate": 1.1686235549132948e-05, "loss": 0.2802, "step": 6768 }, { "epoch": 1.22, "learning_rate": 1.1683526011560694e-05, "loss": 0.5111, "step": 6769 }, { "epoch": 1.22, "learning_rate": 1.168081647398844e-05, "loss": 0.2266, "step": 6770 }, { "epoch": 1.22, "learning_rate": 1.1678106936416186e-05, "loss": 0.8114, "step": 6771 }, { "epoch": 1.22, "learning_rate": 1.167539739884393e-05, "loss": 0.5109, "step": 6772 }, { "epoch": 1.22, "learning_rate": 1.1672687861271676e-05, "loss": 0.564, "step": 6773 }, { "epoch": 1.22, "learning_rate": 1.1669978323699423e-05, "loss": 1.4708, "step": 6774 }, { "epoch": 1.22, "learning_rate": 1.1667268786127169e-05, "loss": 0.6278, "step": 6775 }, { "epoch": 1.22, "learning_rate": 1.1664559248554913e-05, "loss": 0.5752, "step": 6776 }, { "epoch": 1.22, "learning_rate": 1.1661849710982659e-05, "loss": 0.9869, "step": 6777 }, { "epoch": 1.22, "learning_rate": 1.1659140173410403e-05, "loss": 0.6222, "step": 6778 }, { "epoch": 1.22, "learning_rate": 1.1656430635838151e-05, "loss": 0.485, "step": 6779 }, { "epoch": 1.22, "learning_rate": 1.1653721098265897e-05, "loss": 0.7101, "step": 6780 }, { "epoch": 1.22, "learning_rate": 1.1651011560693642e-05, "loss": 1.4344, "step": 6781 }, { "epoch": 1.23, "learning_rate": 1.1648302023121388e-05, "loss": 1.4023, "step": 6782 }, { "epoch": 1.23, "learning_rate": 1.1645592485549132e-05, "loss": 0.7532, "step": 6783 }, { "epoch": 1.23, "learning_rate": 1.164288294797688e-05, "loss": 0.7123, "step": 6784 }, { "epoch": 1.23, "learning_rate": 1.1640173410404624e-05, "loss": 0.1707, "step": 6785 }, { "epoch": 1.23, "learning_rate": 1.163746387283237e-05, "loss": 0.9936, "step": 6786 }, { "epoch": 1.23, "learning_rate": 1.1634754335260116e-05, "loss": 0.2466, "step": 6787 }, { "epoch": 1.23, "learning_rate": 1.163204479768786e-05, "loss": 0.8768, "step": 6788 }, { "epoch": 1.23, "learning_rate": 1.1629335260115608e-05, "loss": 0.7719, "step": 6789 }, { "epoch": 1.23, "learning_rate": 1.1626625722543353e-05, "loss": 0.7067, "step": 6790 }, { "epoch": 1.23, "learning_rate": 1.1623916184971099e-05, "loss": 1.104, "step": 6791 }, { "epoch": 1.23, "learning_rate": 1.1621206647398843e-05, "loss": 0.8383, "step": 6792 }, { "epoch": 1.23, "learning_rate": 1.161849710982659e-05, "loss": 0.6957, "step": 6793 }, { "epoch": 1.23, "learning_rate": 1.1615787572254335e-05, "loss": 0.9044, "step": 6794 }, { "epoch": 1.23, "learning_rate": 1.1613078034682081e-05, "loss": 0.454, "step": 6795 }, { "epoch": 1.23, "learning_rate": 1.1610368497109827e-05, "loss": 0.7955, "step": 6796 }, { "epoch": 1.23, "learning_rate": 1.1607658959537572e-05, "loss": 0.8177, "step": 6797 }, { "epoch": 1.23, "learning_rate": 1.1604949421965318e-05, "loss": 0.4679, "step": 6798 }, { "epoch": 1.23, "learning_rate": 1.1602239884393064e-05, "loss": 1.5208, "step": 6799 }, { "epoch": 1.23, "learning_rate": 1.159953034682081e-05, "loss": 0.5821, "step": 6800 }, { "epoch": 1.23, "learning_rate": 1.1596820809248554e-05, "loss": 0.4763, "step": 6801 }, { "epoch": 1.23, "learning_rate": 1.15941112716763e-05, "loss": 0.4471, "step": 6802 }, { "epoch": 1.23, "learning_rate": 1.1591401734104048e-05, "loss": 0.4352, "step": 6803 }, { "epoch": 1.23, "learning_rate": 1.1588692196531792e-05, "loss": 0.2418, "step": 6804 }, { "epoch": 1.23, "learning_rate": 1.1585982658959539e-05, "loss": 0.5176, "step": 6805 }, { "epoch": 1.23, "learning_rate": 1.1583273121387283e-05, "loss": 0.5557, "step": 6806 }, { "epoch": 1.23, "learning_rate": 1.1580563583815029e-05, "loss": 0.9684, "step": 6807 }, { "epoch": 1.23, "learning_rate": 1.1577854046242775e-05, "loss": 0.3926, "step": 6808 }, { "epoch": 1.23, "learning_rate": 1.1575144508670521e-05, "loss": 0.5854, "step": 6809 }, { "epoch": 1.23, "learning_rate": 1.1572434971098267e-05, "loss": 0.4384, "step": 6810 }, { "epoch": 1.23, "learning_rate": 1.1569725433526011e-05, "loss": 0.8213, "step": 6811 }, { "epoch": 1.23, "learning_rate": 1.1567015895953758e-05, "loss": 0.6689, "step": 6812 }, { "epoch": 1.23, "learning_rate": 1.1564306358381504e-05, "loss": 0.3834, "step": 6813 }, { "epoch": 1.23, "learning_rate": 1.156159682080925e-05, "loss": 0.29, "step": 6814 }, { "epoch": 1.23, "learning_rate": 1.1558887283236994e-05, "loss": 0.4046, "step": 6815 }, { "epoch": 1.23, "learning_rate": 1.155617774566474e-05, "loss": 0.82, "step": 6816 }, { "epoch": 1.23, "learning_rate": 1.1553468208092484e-05, "loss": 1.2296, "step": 6817 }, { "epoch": 1.23, "learning_rate": 1.1550758670520232e-05, "loss": 0.3631, "step": 6818 }, { "epoch": 1.23, "learning_rate": 1.1548049132947978e-05, "loss": 0.1832, "step": 6819 }, { "epoch": 1.23, "learning_rate": 1.1545339595375723e-05, "loss": 0.5795, "step": 6820 }, { "epoch": 1.23, "learning_rate": 1.1542630057803469e-05, "loss": 0.2844, "step": 6821 }, { "epoch": 1.23, "learning_rate": 1.1539920520231213e-05, "loss": 0.5873, "step": 6822 }, { "epoch": 1.23, "learning_rate": 1.153721098265896e-05, "loss": 0.9837, "step": 6823 }, { "epoch": 1.23, "learning_rate": 1.1534501445086705e-05, "loss": 0.4699, "step": 6824 }, { "epoch": 1.23, "learning_rate": 1.1531791907514451e-05, "loss": 0.783, "step": 6825 }, { "epoch": 1.23, "learning_rate": 1.1529082369942197e-05, "loss": 0.4376, "step": 6826 }, { "epoch": 1.23, "learning_rate": 1.1526372832369942e-05, "loss": 0.5192, "step": 6827 }, { "epoch": 1.23, "learning_rate": 1.152366329479769e-05, "loss": 0.5, "step": 6828 }, { "epoch": 1.23, "learning_rate": 1.1520953757225434e-05, "loss": 0.5624, "step": 6829 }, { "epoch": 1.23, "learning_rate": 1.151824421965318e-05, "loss": 0.196, "step": 6830 }, { "epoch": 1.23, "learning_rate": 1.1515534682080924e-05, "loss": 0.3539, "step": 6831 }, { "epoch": 1.23, "learning_rate": 1.151282514450867e-05, "loss": 0.9737, "step": 6832 }, { "epoch": 1.23, "learning_rate": 1.1510115606936418e-05, "loss": 0.5581, "step": 6833 }, { "epoch": 1.23, "learning_rate": 1.1507406069364162e-05, "loss": 0.9617, "step": 6834 }, { "epoch": 1.23, "learning_rate": 1.1504696531791908e-05, "loss": 0.9521, "step": 6835 }, { "epoch": 1.23, "learning_rate": 1.1501986994219653e-05, "loss": 0.718, "step": 6836 }, { "epoch": 1.24, "learning_rate": 1.1499277456647399e-05, "loss": 0.7232, "step": 6837 }, { "epoch": 1.24, "learning_rate": 1.1496567919075145e-05, "loss": 0.3675, "step": 6838 }, { "epoch": 1.24, "learning_rate": 1.1493858381502891e-05, "loss": 0.8444, "step": 6839 }, { "epoch": 1.24, "learning_rate": 1.1491148843930635e-05, "loss": 0.5016, "step": 6840 }, { "epoch": 1.24, "learning_rate": 1.1488439306358381e-05, "loss": 0.5782, "step": 6841 }, { "epoch": 1.24, "learning_rate": 1.1485729768786127e-05, "loss": 0.5066, "step": 6842 }, { "epoch": 1.24, "learning_rate": 1.1483020231213874e-05, "loss": 0.3743, "step": 6843 }, { "epoch": 1.24, "learning_rate": 1.148031069364162e-05, "loss": 0.8039, "step": 6844 }, { "epoch": 1.24, "learning_rate": 1.1477601156069364e-05, "loss": 0.3172, "step": 6845 }, { "epoch": 1.24, "learning_rate": 1.147489161849711e-05, "loss": 0.1568, "step": 6846 }, { "epoch": 1.24, "learning_rate": 1.1472182080924854e-05, "loss": 0.6804, "step": 6847 }, { "epoch": 1.24, "learning_rate": 1.1469472543352602e-05, "loss": 1.055, "step": 6848 }, { "epoch": 1.24, "learning_rate": 1.1466763005780348e-05, "loss": 0.2968, "step": 6849 }, { "epoch": 1.24, "learning_rate": 1.1464053468208093e-05, "loss": 0.4079, "step": 6850 }, { "epoch": 1.24, "learning_rate": 1.1461343930635839e-05, "loss": 0.7653, "step": 6851 }, { "epoch": 1.24, "learning_rate": 1.1458634393063583e-05, "loss": 0.8191, "step": 6852 }, { "epoch": 1.24, "learning_rate": 1.145592485549133e-05, "loss": 0.7846, "step": 6853 }, { "epoch": 1.24, "learning_rate": 1.1453215317919075e-05, "loss": 0.8683, "step": 6854 }, { "epoch": 1.24, "learning_rate": 1.1450505780346821e-05, "loss": 0.2951, "step": 6855 }, { "epoch": 1.24, "learning_rate": 1.1447796242774567e-05, "loss": 0.4205, "step": 6856 }, { "epoch": 1.24, "learning_rate": 1.1445086705202312e-05, "loss": 0.6951, "step": 6857 }, { "epoch": 1.24, "learning_rate": 1.144237716763006e-05, "loss": 0.2256, "step": 6858 }, { "epoch": 1.24, "learning_rate": 1.1439667630057804e-05, "loss": 0.5392, "step": 6859 }, { "epoch": 1.24, "learning_rate": 1.143695809248555e-05, "loss": 0.5396, "step": 6860 }, { "epoch": 1.24, "learning_rate": 1.1434248554913294e-05, "loss": 0.336, "step": 6861 }, { "epoch": 1.24, "learning_rate": 1.143153901734104e-05, "loss": 0.518, "step": 6862 }, { "epoch": 1.24, "learning_rate": 1.1428829479768786e-05, "loss": 0.2745, "step": 6863 }, { "epoch": 1.24, "learning_rate": 1.1426119942196532e-05, "loss": 0.8097, "step": 6864 }, { "epoch": 1.24, "learning_rate": 1.1423410404624278e-05, "loss": 1.4029, "step": 6865 }, { "epoch": 1.24, "learning_rate": 1.1420700867052023e-05, "loss": 0.8123, "step": 6866 }, { "epoch": 1.24, "learning_rate": 1.1417991329479769e-05, "loss": 1.3054, "step": 6867 }, { "epoch": 1.24, "learning_rate": 1.1415281791907515e-05, "loss": 0.609, "step": 6868 }, { "epoch": 1.24, "learning_rate": 1.1412572254335261e-05, "loss": 1.1205, "step": 6869 }, { "epoch": 1.24, "learning_rate": 1.1409862716763005e-05, "loss": 0.729, "step": 6870 }, { "epoch": 1.24, "learning_rate": 1.1407153179190751e-05, "loss": 0.3982, "step": 6871 }, { "epoch": 1.24, "learning_rate": 1.1404443641618497e-05, "loss": 0.7876, "step": 6872 }, { "epoch": 1.24, "learning_rate": 1.1401734104046243e-05, "loss": 0.5593, "step": 6873 }, { "epoch": 1.24, "learning_rate": 1.139902456647399e-05, "loss": 0.4248, "step": 6874 }, { "epoch": 1.24, "learning_rate": 1.1396315028901734e-05, "loss": 0.2974, "step": 6875 }, { "epoch": 1.24, "learning_rate": 1.139360549132948e-05, "loss": 0.474, "step": 6876 }, { "epoch": 1.24, "learning_rate": 1.1390895953757224e-05, "loss": 0.4514, "step": 6877 }, { "epoch": 1.24, "learning_rate": 1.1388186416184972e-05, "loss": 0.3654, "step": 6878 }, { "epoch": 1.24, "learning_rate": 1.1385476878612718e-05, "loss": 0.3286, "step": 6879 }, { "epoch": 1.24, "learning_rate": 1.1382767341040462e-05, "loss": 0.5801, "step": 6880 }, { "epoch": 1.24, "learning_rate": 1.1380057803468209e-05, "loss": 0.4821, "step": 6881 }, { "epoch": 1.24, "learning_rate": 1.1377348265895953e-05, "loss": 0.2629, "step": 6882 }, { "epoch": 1.24, "learning_rate": 1.13746387283237e-05, "loss": 1.2527, "step": 6883 }, { "epoch": 1.24, "learning_rate": 1.1371929190751445e-05, "loss": 0.7122, "step": 6884 }, { "epoch": 1.24, "learning_rate": 1.1369219653179191e-05, "loss": 0.3789, "step": 6885 }, { "epoch": 1.24, "learning_rate": 1.1366510115606935e-05, "loss": 0.6891, "step": 6886 }, { "epoch": 1.24, "learning_rate": 1.1363800578034683e-05, "loss": 0.5079, "step": 6887 }, { "epoch": 1.24, "learning_rate": 1.136109104046243e-05, "loss": 0.7498, "step": 6888 }, { "epoch": 1.24, "learning_rate": 1.1358381502890174e-05, "loss": 1.6353, "step": 6889 }, { "epoch": 1.24, "learning_rate": 1.135567196531792e-05, "loss": 0.26, "step": 6890 }, { "epoch": 1.24, "learning_rate": 1.1352962427745664e-05, "loss": 0.6741, "step": 6891 }, { "epoch": 1.24, "learning_rate": 1.1350252890173412e-05, "loss": 0.2997, "step": 6892 }, { "epoch": 1.25, "learning_rate": 1.1347543352601156e-05, "loss": 0.7408, "step": 6893 }, { "epoch": 1.25, "learning_rate": 1.1344833815028902e-05, "loss": 0.5023, "step": 6894 }, { "epoch": 1.25, "learning_rate": 1.1342124277456648e-05, "loss": 0.1279, "step": 6895 }, { "epoch": 1.25, "learning_rate": 1.1339414739884393e-05, "loss": 0.4851, "step": 6896 }, { "epoch": 1.25, "learning_rate": 1.133670520231214e-05, "loss": 1.0721, "step": 6897 }, { "epoch": 1.25, "learning_rate": 1.1333995664739885e-05, "loss": 0.6544, "step": 6898 }, { "epoch": 1.25, "learning_rate": 1.133128612716763e-05, "loss": 0.501, "step": 6899 }, { "epoch": 1.25, "learning_rate": 1.1328576589595375e-05, "loss": 0.4119, "step": 6900 }, { "epoch": 1.25, "learning_rate": 1.1325867052023121e-05, "loss": 0.5403, "step": 6901 }, { "epoch": 1.25, "learning_rate": 1.1323157514450867e-05, "loss": 0.7135, "step": 6902 }, { "epoch": 1.25, "learning_rate": 1.1320447976878613e-05, "loss": 0.5341, "step": 6903 }, { "epoch": 1.25, "learning_rate": 1.131773843930636e-05, "loss": 0.7046, "step": 6904 }, { "epoch": 1.25, "learning_rate": 1.1315028901734104e-05, "loss": 1.8973, "step": 6905 }, { "epoch": 1.25, "learning_rate": 1.131231936416185e-05, "loss": 0.8393, "step": 6906 }, { "epoch": 1.25, "learning_rate": 1.1309609826589596e-05, "loss": 0.3358, "step": 6907 }, { "epoch": 1.25, "learning_rate": 1.1306900289017342e-05, "loss": 0.8817, "step": 6908 }, { "epoch": 1.25, "learning_rate": 1.1304190751445086e-05, "loss": 1.0453, "step": 6909 }, { "epoch": 1.25, "learning_rate": 1.1301481213872832e-05, "loss": 0.4782, "step": 6910 }, { "epoch": 1.25, "learning_rate": 1.1298771676300578e-05, "loss": 1.1993, "step": 6911 }, { "epoch": 1.25, "learning_rate": 1.1296062138728324e-05, "loss": 0.6886, "step": 6912 }, { "epoch": 1.25, "learning_rate": 1.129335260115607e-05, "loss": 0.2969, "step": 6913 }, { "epoch": 1.25, "learning_rate": 1.1290643063583815e-05, "loss": 0.664, "step": 6914 }, { "epoch": 1.25, "learning_rate": 1.1287933526011561e-05, "loss": 0.4537, "step": 6915 }, { "epoch": 1.25, "learning_rate": 1.1285223988439305e-05, "loss": 0.321, "step": 6916 }, { "epoch": 1.25, "learning_rate": 1.1282514450867053e-05, "loss": 0.6846, "step": 6917 }, { "epoch": 1.25, "learning_rate": 1.1279804913294799e-05, "loss": 0.9899, "step": 6918 }, { "epoch": 1.25, "learning_rate": 1.1277095375722544e-05, "loss": 0.5221, "step": 6919 }, { "epoch": 1.25, "learning_rate": 1.127438583815029e-05, "loss": 0.7169, "step": 6920 }, { "epoch": 1.25, "learning_rate": 1.1271676300578034e-05, "loss": 0.6252, "step": 6921 }, { "epoch": 1.25, "learning_rate": 1.1268966763005782e-05, "loss": 0.5788, "step": 6922 }, { "epoch": 1.25, "learning_rate": 1.1266257225433526e-05, "loss": 0.8582, "step": 6923 }, { "epoch": 1.25, "learning_rate": 1.1263547687861272e-05, "loss": 0.5621, "step": 6924 }, { "epoch": 1.25, "learning_rate": 1.1260838150289016e-05, "loss": 0.5688, "step": 6925 }, { "epoch": 1.25, "learning_rate": 1.1258128612716763e-05, "loss": 0.4852, "step": 6926 }, { "epoch": 1.25, "learning_rate": 1.125541907514451e-05, "loss": 0.1872, "step": 6927 }, { "epoch": 1.25, "learning_rate": 1.1252709537572255e-05, "loss": 0.3225, "step": 6928 }, { "epoch": 1.25, "learning_rate": 1.125e-05, "loss": 0.7831, "step": 6929 }, { "epoch": 1.25, "learning_rate": 1.1247290462427745e-05, "loss": 0.5573, "step": 6930 }, { "epoch": 1.25, "learning_rate": 1.1244580924855491e-05, "loss": 0.6062, "step": 6931 }, { "epoch": 1.25, "learning_rate": 1.1241871387283237e-05, "loss": 0.4867, "step": 6932 }, { "epoch": 1.25, "learning_rate": 1.1239161849710983e-05, "loss": 1.5621, "step": 6933 }, { "epoch": 1.25, "learning_rate": 1.123645231213873e-05, "loss": 0.5312, "step": 6934 }, { "epoch": 1.25, "learning_rate": 1.1233742774566474e-05, "loss": 0.1103, "step": 6935 }, { "epoch": 1.25, "learning_rate": 1.123103323699422e-05, "loss": 0.8935, "step": 6936 }, { "epoch": 1.25, "learning_rate": 1.1228323699421966e-05, "loss": 0.317, "step": 6937 }, { "epoch": 1.25, "learning_rate": 1.1225614161849712e-05, "loss": 0.6662, "step": 6938 }, { "epoch": 1.25, "learning_rate": 1.1222904624277456e-05, "loss": 0.4152, "step": 6939 }, { "epoch": 1.25, "learning_rate": 1.1220195086705202e-05, "loss": 0.4169, "step": 6940 }, { "epoch": 1.25, "learning_rate": 1.1217485549132948e-05, "loss": 0.6628, "step": 6941 }, { "epoch": 1.25, "learning_rate": 1.1214776011560694e-05, "loss": 0.43, "step": 6942 }, { "epoch": 1.25, "learning_rate": 1.121206647398844e-05, "loss": 0.7581, "step": 6943 }, { "epoch": 1.25, "learning_rate": 1.1209356936416185e-05, "loss": 0.7016, "step": 6944 }, { "epoch": 1.25, "learning_rate": 1.1206647398843931e-05, "loss": 0.7192, "step": 6945 }, { "epoch": 1.25, "learning_rate": 1.1203937861271675e-05, "loss": 0.5886, "step": 6946 }, { "epoch": 1.25, "learning_rate": 1.1201228323699423e-05, "loss": 0.2194, "step": 6947 }, { "epoch": 1.26, "learning_rate": 1.1198518786127167e-05, "loss": 0.5263, "step": 6948 }, { "epoch": 1.26, "learning_rate": 1.1195809248554913e-05, "loss": 0.7775, "step": 6949 }, { "epoch": 1.26, "learning_rate": 1.119309971098266e-05, "loss": 0.7055, "step": 6950 }, { "epoch": 1.26, "learning_rate": 1.1190390173410404e-05, "loss": 0.1487, "step": 6951 }, { "epoch": 1.26, "learning_rate": 1.1187680635838152e-05, "loss": 0.4724, "step": 6952 }, { "epoch": 1.26, "learning_rate": 1.1184971098265896e-05, "loss": 0.5071, "step": 6953 }, { "epoch": 1.26, "learning_rate": 1.1182261560693642e-05, "loss": 0.2591, "step": 6954 }, { "epoch": 1.26, "learning_rate": 1.1179552023121386e-05, "loss": 0.6504, "step": 6955 }, { "epoch": 1.26, "learning_rate": 1.1176842485549132e-05, "loss": 0.2711, "step": 6956 }, { "epoch": 1.26, "learning_rate": 1.117413294797688e-05, "loss": 0.6377, "step": 6957 }, { "epoch": 1.26, "learning_rate": 1.1171423410404625e-05, "loss": 0.447, "step": 6958 }, { "epoch": 1.26, "learning_rate": 1.116871387283237e-05, "loss": 0.1972, "step": 6959 }, { "epoch": 1.26, "learning_rate": 1.1166004335260115e-05, "loss": 0.4287, "step": 6960 }, { "epoch": 1.26, "learning_rate": 1.1163294797687861e-05, "loss": 1.0045, "step": 6961 }, { "epoch": 1.26, "learning_rate": 1.1160585260115607e-05, "loss": 0.3146, "step": 6962 }, { "epoch": 1.26, "learning_rate": 1.1157875722543353e-05, "loss": 0.6208, "step": 6963 }, { "epoch": 1.26, "learning_rate": 1.11551661849711e-05, "loss": 0.8503, "step": 6964 }, { "epoch": 1.26, "learning_rate": 1.1152456647398844e-05, "loss": 0.9319, "step": 6965 }, { "epoch": 1.26, "learning_rate": 1.114974710982659e-05, "loss": 0.7811, "step": 6966 }, { "epoch": 1.26, "learning_rate": 1.1147037572254336e-05, "loss": 0.4424, "step": 6967 }, { "epoch": 1.26, "learning_rate": 1.1144328034682082e-05, "loss": 0.7437, "step": 6968 }, { "epoch": 1.26, "learning_rate": 1.1141618497109826e-05, "loss": 0.6877, "step": 6969 }, { "epoch": 1.26, "learning_rate": 1.1138908959537572e-05, "loss": 0.7287, "step": 6970 }, { "epoch": 1.26, "learning_rate": 1.1136199421965317e-05, "loss": 0.2939, "step": 6971 }, { "epoch": 1.26, "learning_rate": 1.1133489884393064e-05, "loss": 0.4915, "step": 6972 }, { "epoch": 1.26, "learning_rate": 1.113078034682081e-05, "loss": 0.5691, "step": 6973 }, { "epoch": 1.26, "learning_rate": 1.1128070809248555e-05, "loss": 0.285, "step": 6974 }, { "epoch": 1.26, "learning_rate": 1.11253612716763e-05, "loss": 0.3351, "step": 6975 }, { "epoch": 1.26, "learning_rate": 1.1122651734104047e-05, "loss": 0.939, "step": 6976 }, { "epoch": 1.26, "learning_rate": 1.1119942196531793e-05, "loss": 0.3512, "step": 6977 }, { "epoch": 1.26, "learning_rate": 1.1117232658959537e-05, "loss": 0.4573, "step": 6978 }, { "epoch": 1.26, "learning_rate": 1.1114523121387283e-05, "loss": 0.372, "step": 6979 }, { "epoch": 1.26, "learning_rate": 1.111181358381503e-05, "loss": 0.8954, "step": 6980 }, { "epoch": 1.26, "learning_rate": 1.1109104046242775e-05, "loss": 0.6031, "step": 6981 }, { "epoch": 1.26, "learning_rate": 1.1106394508670522e-05, "loss": 0.3267, "step": 6982 }, { "epoch": 1.26, "learning_rate": 1.1103684971098266e-05, "loss": 0.3424, "step": 6983 }, { "epoch": 1.26, "learning_rate": 1.1100975433526012e-05, "loss": 0.5797, "step": 6984 }, { "epoch": 1.26, "learning_rate": 1.1098265895953756e-05, "loss": 0.7342, "step": 6985 }, { "epoch": 1.26, "learning_rate": 1.1095556358381504e-05, "loss": 0.227, "step": 6986 }, { "epoch": 1.26, "learning_rate": 1.109284682080925e-05, "loss": 0.6969, "step": 6987 }, { "epoch": 1.26, "learning_rate": 1.1090137283236994e-05, "loss": 0.9059, "step": 6988 }, { "epoch": 1.26, "learning_rate": 1.108742774566474e-05, "loss": 0.3053, "step": 6989 }, { "epoch": 1.26, "learning_rate": 1.1084718208092485e-05, "loss": 0.5063, "step": 6990 }, { "epoch": 1.26, "learning_rate": 1.1082008670520233e-05, "loss": 0.5768, "step": 6991 }, { "epoch": 1.26, "learning_rate": 1.1079299132947977e-05, "loss": 0.6822, "step": 6992 }, { "epoch": 1.26, "learning_rate": 1.1076589595375723e-05, "loss": 0.5952, "step": 6993 }, { "epoch": 1.26, "learning_rate": 1.1073880057803467e-05, "loss": 0.692, "step": 6994 }, { "epoch": 1.26, "learning_rate": 1.1071170520231214e-05, "loss": 0.51, "step": 6995 }, { "epoch": 1.26, "learning_rate": 1.1068460982658961e-05, "loss": 0.2806, "step": 6996 }, { "epoch": 1.26, "learning_rate": 1.1065751445086706e-05, "loss": 0.8338, "step": 6997 }, { "epoch": 1.26, "learning_rate": 1.1063041907514452e-05, "loss": 1.5222, "step": 6998 }, { "epoch": 1.26, "learning_rate": 1.1060332369942196e-05, "loss": 0.9903, "step": 6999 }, { "epoch": 1.26, "learning_rate": 1.1057622832369942e-05, "loss": 0.2389, "step": 7000 }, { "epoch": 1.26, "eval_exact_match": 87.47398297067171, "eval_f1": 93.75558095479333, "step": 7000 }, { "epoch": 1.26, "learning_rate": 1.1054913294797688e-05, "loss": 0.9395, "step": 7001 }, { "epoch": 1.26, "learning_rate": 1.1052203757225434e-05, "loss": 0.255, "step": 7002 }, { "epoch": 1.26, "learning_rate": 1.104949421965318e-05, "loss": 0.5159, "step": 7003 }, { "epoch": 1.27, "learning_rate": 1.1046784682080925e-05, "loss": 0.6903, "step": 7004 }, { "epoch": 1.27, "learning_rate": 1.104407514450867e-05, "loss": 0.5191, "step": 7005 }, { "epoch": 1.27, "learning_rate": 1.1041365606936417e-05, "loss": 0.4431, "step": 7006 }, { "epoch": 1.27, "learning_rate": 1.1038656069364163e-05, "loss": 0.5898, "step": 7007 }, { "epoch": 1.27, "learning_rate": 1.1035946531791907e-05, "loss": 0.4603, "step": 7008 }, { "epoch": 1.27, "learning_rate": 1.1033236994219653e-05, "loss": 0.6528, "step": 7009 }, { "epoch": 1.27, "learning_rate": 1.10305274566474e-05, "loss": 0.9205, "step": 7010 }, { "epoch": 1.27, "learning_rate": 1.1027817919075145e-05, "loss": 0.3656, "step": 7011 }, { "epoch": 1.27, "learning_rate": 1.1025108381502891e-05, "loss": 0.2909, "step": 7012 }, { "epoch": 1.27, "learning_rate": 1.1022398843930636e-05, "loss": 0.1928, "step": 7013 }, { "epoch": 1.27, "learning_rate": 1.1019689306358382e-05, "loss": 0.0946, "step": 7014 }, { "epoch": 1.27, "learning_rate": 1.1016979768786126e-05, "loss": 0.3771, "step": 7015 }, { "epoch": 1.27, "learning_rate": 1.1014270231213874e-05, "loss": 0.9574, "step": 7016 }, { "epoch": 1.27, "learning_rate": 1.1011560693641618e-05, "loss": 0.3288, "step": 7017 }, { "epoch": 1.27, "learning_rate": 1.1008851156069364e-05, "loss": 0.7527, "step": 7018 }, { "epoch": 1.27, "learning_rate": 1.100614161849711e-05, "loss": 0.5205, "step": 7019 }, { "epoch": 1.27, "learning_rate": 1.1003432080924855e-05, "loss": 0.4356, "step": 7020 }, { "epoch": 1.27, "learning_rate": 1.1000722543352603e-05, "loss": 0.7477, "step": 7021 }, { "epoch": 1.27, "learning_rate": 1.0998013005780347e-05, "loss": 0.4415, "step": 7022 }, { "epoch": 1.27, "learning_rate": 1.0995303468208093e-05, "loss": 0.6604, "step": 7023 }, { "epoch": 1.27, "learning_rate": 1.0992593930635837e-05, "loss": 0.709, "step": 7024 }, { "epoch": 1.27, "learning_rate": 1.0989884393063583e-05, "loss": 0.3586, "step": 7025 }, { "epoch": 1.27, "learning_rate": 1.0987174855491331e-05, "loss": 1.1732, "step": 7026 }, { "epoch": 1.27, "learning_rate": 1.0984465317919076e-05, "loss": 1.1127, "step": 7027 }, { "epoch": 1.27, "learning_rate": 1.0981755780346822e-05, "loss": 0.5435, "step": 7028 }, { "epoch": 1.27, "learning_rate": 1.0979046242774566e-05, "loss": 0.5889, "step": 7029 }, { "epoch": 1.27, "learning_rate": 1.0976336705202312e-05, "loss": 0.3299, "step": 7030 }, { "epoch": 1.27, "learning_rate": 1.0973627167630058e-05, "loss": 0.6103, "step": 7031 }, { "epoch": 1.27, "learning_rate": 1.0970917630057804e-05, "loss": 0.6015, "step": 7032 }, { "epoch": 1.27, "learning_rate": 1.0968208092485549e-05, "loss": 0.4678, "step": 7033 }, { "epoch": 1.27, "learning_rate": 1.0965498554913295e-05, "loss": 0.5185, "step": 7034 }, { "epoch": 1.27, "learning_rate": 1.096278901734104e-05, "loss": 0.5947, "step": 7035 }, { "epoch": 1.27, "learning_rate": 1.0960079479768787e-05, "loss": 0.4176, "step": 7036 }, { "epoch": 1.27, "learning_rate": 1.0957369942196533e-05, "loss": 0.413, "step": 7037 }, { "epoch": 1.27, "learning_rate": 1.0954660404624277e-05, "loss": 0.5711, "step": 7038 }, { "epoch": 1.27, "learning_rate": 1.0951950867052023e-05, "loss": 0.4628, "step": 7039 }, { "epoch": 1.27, "learning_rate": 1.0949241329479768e-05, "loss": 0.5021, "step": 7040 }, { "epoch": 1.27, "learning_rate": 1.0946531791907515e-05, "loss": 0.3333, "step": 7041 }, { "epoch": 1.27, "learning_rate": 1.0943822254335261e-05, "loss": 0.855, "step": 7042 }, { "epoch": 1.27, "learning_rate": 1.0941112716763006e-05, "loss": 0.3461, "step": 7043 }, { "epoch": 1.27, "learning_rate": 1.0938403179190752e-05, "loss": 0.6425, "step": 7044 }, { "epoch": 1.27, "learning_rate": 1.0935693641618496e-05, "loss": 0.286, "step": 7045 }, { "epoch": 1.27, "learning_rate": 1.0932984104046244e-05, "loss": 0.6414, "step": 7046 }, { "epoch": 1.27, "learning_rate": 1.0930274566473988e-05, "loss": 0.5955, "step": 7047 }, { "epoch": 1.27, "learning_rate": 1.0927565028901734e-05, "loss": 0.3961, "step": 7048 }, { "epoch": 1.27, "learning_rate": 1.092485549132948e-05, "loss": 0.298, "step": 7049 }, { "epoch": 1.27, "learning_rate": 1.0922145953757225e-05, "loss": 0.5881, "step": 7050 }, { "epoch": 1.27, "learning_rate": 1.0919436416184972e-05, "loss": 0.3336, "step": 7051 }, { "epoch": 1.27, "learning_rate": 1.0916726878612717e-05, "loss": 0.8354, "step": 7052 }, { "epoch": 1.27, "learning_rate": 1.0914017341040463e-05, "loss": 1.1364, "step": 7053 }, { "epoch": 1.27, "learning_rate": 1.0911307803468207e-05, "loss": 0.4328, "step": 7054 }, { "epoch": 1.27, "learning_rate": 1.0908598265895953e-05, "loss": 0.7513, "step": 7055 }, { "epoch": 1.27, "learning_rate": 1.09058887283237e-05, "loss": 0.4519, "step": 7056 }, { "epoch": 1.27, "learning_rate": 1.0903179190751445e-05, "loss": 0.8295, "step": 7057 }, { "epoch": 1.27, "learning_rate": 1.0900469653179192e-05, "loss": 0.461, "step": 7058 }, { "epoch": 1.28, "learning_rate": 1.0897760115606936e-05, "loss": 0.643, "step": 7059 }, { "epoch": 1.28, "learning_rate": 1.0895050578034684e-05, "loss": 0.4972, "step": 7060 }, { "epoch": 1.28, "learning_rate": 1.0892341040462428e-05, "loss": 0.7265, "step": 7061 }, { "epoch": 1.28, "learning_rate": 1.0889631502890174e-05, "loss": 0.498, "step": 7062 }, { "epoch": 1.28, "learning_rate": 1.0886921965317918e-05, "loss": 0.2286, "step": 7063 }, { "epoch": 1.28, "learning_rate": 1.0884212427745664e-05, "loss": 0.4301, "step": 7064 }, { "epoch": 1.28, "learning_rate": 1.0881502890173412e-05, "loss": 0.1769, "step": 7065 }, { "epoch": 1.28, "learning_rate": 1.0878793352601157e-05, "loss": 0.3336, "step": 7066 }, { "epoch": 1.28, "learning_rate": 1.0876083815028903e-05, "loss": 0.5527, "step": 7067 }, { "epoch": 1.28, "learning_rate": 1.0873374277456647e-05, "loss": 0.4729, "step": 7068 }, { "epoch": 1.28, "learning_rate": 1.0870664739884393e-05, "loss": 0.4564, "step": 7069 }, { "epoch": 1.28, "learning_rate": 1.0867955202312139e-05, "loss": 0.2955, "step": 7070 }, { "epoch": 1.28, "learning_rate": 1.0865245664739885e-05, "loss": 0.3573, "step": 7071 }, { "epoch": 1.28, "learning_rate": 1.0862536127167631e-05, "loss": 0.2946, "step": 7072 }, { "epoch": 1.28, "learning_rate": 1.0859826589595376e-05, "loss": 0.3453, "step": 7073 }, { "epoch": 1.28, "learning_rate": 1.0857117052023122e-05, "loss": 0.7735, "step": 7074 }, { "epoch": 1.28, "learning_rate": 1.0854407514450868e-05, "loss": 1.0054, "step": 7075 }, { "epoch": 1.28, "learning_rate": 1.0851697976878614e-05, "loss": 0.377, "step": 7076 }, { "epoch": 1.28, "learning_rate": 1.0848988439306358e-05, "loss": 0.5633, "step": 7077 }, { "epoch": 1.28, "learning_rate": 1.0846278901734104e-05, "loss": 1.4772, "step": 7078 }, { "epoch": 1.28, "learning_rate": 1.0843569364161849e-05, "loss": 1.2963, "step": 7079 }, { "epoch": 1.28, "learning_rate": 1.0840859826589596e-05, "loss": 0.3662, "step": 7080 }, { "epoch": 1.28, "learning_rate": 1.0838150289017342e-05, "loss": 0.7992, "step": 7081 }, { "epoch": 1.28, "learning_rate": 1.0835440751445087e-05, "loss": 1.1435, "step": 7082 }, { "epoch": 1.28, "learning_rate": 1.0832731213872833e-05, "loss": 0.444, "step": 7083 }, { "epoch": 1.28, "learning_rate": 1.0830021676300577e-05, "loss": 0.526, "step": 7084 }, { "epoch": 1.28, "learning_rate": 1.0827312138728325e-05, "loss": 1.156, "step": 7085 }, { "epoch": 1.28, "learning_rate": 1.082460260115607e-05, "loss": 0.4338, "step": 7086 }, { "epoch": 1.28, "learning_rate": 1.0821893063583815e-05, "loss": 0.3668, "step": 7087 }, { "epoch": 1.28, "learning_rate": 1.0819183526011561e-05, "loss": 0.7707, "step": 7088 }, { "epoch": 1.28, "learning_rate": 1.0816473988439306e-05, "loss": 1.1335, "step": 7089 }, { "epoch": 1.28, "learning_rate": 1.0813764450867054e-05, "loss": 0.3377, "step": 7090 }, { "epoch": 1.28, "learning_rate": 1.0811054913294798e-05, "loss": 0.7111, "step": 7091 }, { "epoch": 1.28, "learning_rate": 1.0808345375722544e-05, "loss": 0.275, "step": 7092 }, { "epoch": 1.28, "learning_rate": 1.0805635838150288e-05, "loss": 0.3494, "step": 7093 }, { "epoch": 1.28, "learning_rate": 1.0802926300578034e-05, "loss": 1.0575, "step": 7094 }, { "epoch": 1.28, "learning_rate": 1.0800216763005782e-05, "loss": 0.5376, "step": 7095 }, { "epoch": 1.28, "learning_rate": 1.0797507225433527e-05, "loss": 0.4321, "step": 7096 }, { "epoch": 1.28, "learning_rate": 1.0794797687861273e-05, "loss": 0.3838, "step": 7097 }, { "epoch": 1.28, "learning_rate": 1.0792088150289017e-05, "loss": 0.9599, "step": 7098 }, { "epoch": 1.28, "learning_rate": 1.0789378612716763e-05, "loss": 0.6814, "step": 7099 }, { "epoch": 1.28, "learning_rate": 1.0786669075144509e-05, "loss": 0.3332, "step": 7100 }, { "epoch": 1.28, "learning_rate": 1.0783959537572255e-05, "loss": 0.504, "step": 7101 }, { "epoch": 1.28, "learning_rate": 1.078125e-05, "loss": 0.338, "step": 7102 }, { "epoch": 1.28, "learning_rate": 1.0778540462427746e-05, "loss": 0.6517, "step": 7103 }, { "epoch": 1.28, "learning_rate": 1.0775830924855492e-05, "loss": 0.5989, "step": 7104 }, { "epoch": 1.28, "learning_rate": 1.0773121387283238e-05, "loss": 0.288, "step": 7105 }, { "epoch": 1.28, "learning_rate": 1.0770411849710984e-05, "loss": 0.4053, "step": 7106 }, { "epoch": 1.28, "learning_rate": 1.0767702312138728e-05, "loss": 0.1592, "step": 7107 }, { "epoch": 1.28, "learning_rate": 1.0764992774566474e-05, "loss": 0.6791, "step": 7108 }, { "epoch": 1.28, "learning_rate": 1.0762283236994219e-05, "loss": 0.8831, "step": 7109 }, { "epoch": 1.28, "learning_rate": 1.0759573699421966e-05, "loss": 0.4223, "step": 7110 }, { "epoch": 1.28, "learning_rate": 1.0756864161849712e-05, "loss": 0.7575, "step": 7111 }, { "epoch": 1.28, "learning_rate": 1.0754154624277457e-05, "loss": 0.2689, "step": 7112 }, { "epoch": 1.28, "learning_rate": 1.0751445086705203e-05, "loss": 0.7674, "step": 7113 }, { "epoch": 1.29, "learning_rate": 1.0748735549132947e-05, "loss": 0.6455, "step": 7114 }, { "epoch": 1.29, "learning_rate": 1.0746026011560695e-05, "loss": 0.5964, "step": 7115 }, { "epoch": 1.29, "learning_rate": 1.074331647398844e-05, "loss": 0.2463, "step": 7116 }, { "epoch": 1.29, "learning_rate": 1.0740606936416185e-05, "loss": 0.4728, "step": 7117 }, { "epoch": 1.29, "learning_rate": 1.0737897398843931e-05, "loss": 0.5841, "step": 7118 }, { "epoch": 1.29, "learning_rate": 1.0735187861271676e-05, "loss": 0.5075, "step": 7119 }, { "epoch": 1.29, "learning_rate": 1.0732478323699423e-05, "loss": 0.5685, "step": 7120 }, { "epoch": 1.29, "learning_rate": 1.0729768786127168e-05, "loss": 0.4542, "step": 7121 }, { "epoch": 1.29, "learning_rate": 1.0727059248554914e-05, "loss": 0.2215, "step": 7122 }, { "epoch": 1.29, "learning_rate": 1.0724349710982658e-05, "loss": 0.3717, "step": 7123 }, { "epoch": 1.29, "learning_rate": 1.0721640173410404e-05, "loss": 0.2634, "step": 7124 }, { "epoch": 1.29, "learning_rate": 1.071893063583815e-05, "loss": 0.4544, "step": 7125 }, { "epoch": 1.29, "learning_rate": 1.0716221098265896e-05, "loss": 0.3564, "step": 7126 }, { "epoch": 1.29, "learning_rate": 1.0713511560693642e-05, "loss": 0.7377, "step": 7127 }, { "epoch": 1.29, "learning_rate": 1.0710802023121387e-05, "loss": 0.497, "step": 7128 }, { "epoch": 1.29, "learning_rate": 1.0708092485549133e-05, "loss": 0.3853, "step": 7129 }, { "epoch": 1.29, "learning_rate": 1.0705382947976879e-05, "loss": 0.392, "step": 7130 }, { "epoch": 1.29, "learning_rate": 1.0702673410404625e-05, "loss": 0.6257, "step": 7131 }, { "epoch": 1.29, "learning_rate": 1.069996387283237e-05, "loss": 0.7735, "step": 7132 }, { "epoch": 1.29, "learning_rate": 1.0697254335260115e-05, "loss": 0.6199, "step": 7133 }, { "epoch": 1.29, "learning_rate": 1.0694544797687862e-05, "loss": 0.7042, "step": 7134 }, { "epoch": 1.29, "learning_rate": 1.0691835260115608e-05, "loss": 0.5526, "step": 7135 }, { "epoch": 1.29, "learning_rate": 1.0689125722543354e-05, "loss": 0.6113, "step": 7136 }, { "epoch": 1.29, "learning_rate": 1.0686416184971098e-05, "loss": 0.711, "step": 7137 }, { "epoch": 1.29, "learning_rate": 1.0683706647398844e-05, "loss": 0.6974, "step": 7138 }, { "epoch": 1.29, "learning_rate": 1.0680997109826588e-05, "loss": 0.2755, "step": 7139 }, { "epoch": 1.29, "learning_rate": 1.0678287572254336e-05, "loss": 0.8587, "step": 7140 }, { "epoch": 1.29, "learning_rate": 1.067557803468208e-05, "loss": 0.3846, "step": 7141 }, { "epoch": 1.29, "learning_rate": 1.0672868497109827e-05, "loss": 1.1505, "step": 7142 }, { "epoch": 1.29, "learning_rate": 1.0670158959537573e-05, "loss": 0.4522, "step": 7143 }, { "epoch": 1.29, "learning_rate": 1.0667449421965317e-05, "loss": 0.4659, "step": 7144 }, { "epoch": 1.29, "learning_rate": 1.0664739884393065e-05, "loss": 0.6188, "step": 7145 }, { "epoch": 1.29, "learning_rate": 1.0662030346820809e-05, "loss": 0.7852, "step": 7146 }, { "epoch": 1.29, "learning_rate": 1.0659320809248555e-05, "loss": 0.444, "step": 7147 }, { "epoch": 1.29, "learning_rate": 1.06566112716763e-05, "loss": 0.719, "step": 7148 }, { "epoch": 1.29, "learning_rate": 1.0653901734104047e-05, "loss": 0.7207, "step": 7149 }, { "epoch": 1.29, "learning_rate": 1.0651192196531793e-05, "loss": 0.5563, "step": 7150 }, { "epoch": 1.29, "learning_rate": 1.0648482658959538e-05, "loss": 0.8858, "step": 7151 }, { "epoch": 1.29, "learning_rate": 1.0645773121387284e-05, "loss": 0.4029, "step": 7152 }, { "epoch": 1.29, "learning_rate": 1.0643063583815028e-05, "loss": 0.6157, "step": 7153 }, { "epoch": 1.29, "learning_rate": 1.0640354046242776e-05, "loss": 0.5268, "step": 7154 }, { "epoch": 1.29, "learning_rate": 1.063764450867052e-05, "loss": 0.1832, "step": 7155 }, { "epoch": 1.29, "learning_rate": 1.0634934971098266e-05, "loss": 0.7259, "step": 7156 }, { "epoch": 1.29, "learning_rate": 1.0632225433526012e-05, "loss": 0.8023, "step": 7157 }, { "epoch": 1.29, "learning_rate": 1.0629515895953757e-05, "loss": 0.8156, "step": 7158 }, { "epoch": 1.29, "learning_rate": 1.0626806358381505e-05, "loss": 0.642, "step": 7159 }, { "epoch": 1.29, "learning_rate": 1.0624096820809249e-05, "loss": 0.5202, "step": 7160 }, { "epoch": 1.29, "learning_rate": 1.0621387283236995e-05, "loss": 0.479, "step": 7161 }, { "epoch": 1.29, "learning_rate": 1.061867774566474e-05, "loss": 0.6392, "step": 7162 }, { "epoch": 1.29, "learning_rate": 1.0615968208092485e-05, "loss": 0.5438, "step": 7163 }, { "epoch": 1.29, "learning_rate": 1.0613258670520231e-05, "loss": 0.6594, "step": 7164 }, { "epoch": 1.29, "learning_rate": 1.0610549132947977e-05, "loss": 0.3297, "step": 7165 }, { "epoch": 1.29, "learning_rate": 1.0607839595375724e-05, "loss": 1.2319, "step": 7166 }, { "epoch": 1.29, "learning_rate": 1.0605130057803468e-05, "loss": 0.9793, "step": 7167 }, { "epoch": 1.29, "learning_rate": 1.0602420520231214e-05, "loss": 0.4814, "step": 7168 }, { "epoch": 1.29, "learning_rate": 1.059971098265896e-05, "loss": 0.4009, "step": 7169 }, { "epoch": 1.3, "learning_rate": 1.0597001445086706e-05, "loss": 0.4113, "step": 7170 }, { "epoch": 1.3, "learning_rate": 1.059429190751445e-05, "loss": 0.4756, "step": 7171 }, { "epoch": 1.3, "learning_rate": 1.0591582369942197e-05, "loss": 0.653, "step": 7172 }, { "epoch": 1.3, "learning_rate": 1.0588872832369943e-05, "loss": 0.8045, "step": 7173 }, { "epoch": 1.3, "learning_rate": 1.0586163294797689e-05, "loss": 0.5788, "step": 7174 }, { "epoch": 1.3, "learning_rate": 1.0583453757225435e-05, "loss": 0.4281, "step": 7175 }, { "epoch": 1.3, "learning_rate": 1.0580744219653179e-05, "loss": 0.5694, "step": 7176 }, { "epoch": 1.3, "learning_rate": 1.0578034682080925e-05, "loss": 0.8733, "step": 7177 }, { "epoch": 1.3, "learning_rate": 1.057532514450867e-05, "loss": 0.7013, "step": 7178 }, { "epoch": 1.3, "learning_rate": 1.0572615606936417e-05, "loss": 0.3206, "step": 7179 }, { "epoch": 1.3, "learning_rate": 1.0569906069364163e-05, "loss": 0.666, "step": 7180 }, { "epoch": 1.3, "learning_rate": 1.0567196531791908e-05, "loss": 0.7197, "step": 7181 }, { "epoch": 1.3, "learning_rate": 1.0564486994219654e-05, "loss": 0.3404, "step": 7182 }, { "epoch": 1.3, "learning_rate": 1.0561777456647398e-05, "loss": 0.3021, "step": 7183 }, { "epoch": 1.3, "learning_rate": 1.0559067919075146e-05, "loss": 0.3426, "step": 7184 }, { "epoch": 1.3, "learning_rate": 1.055635838150289e-05, "loss": 0.4696, "step": 7185 }, { "epoch": 1.3, "learning_rate": 1.0553648843930636e-05, "loss": 0.7254, "step": 7186 }, { "epoch": 1.3, "learning_rate": 1.055093930635838e-05, "loss": 0.5144, "step": 7187 }, { "epoch": 1.3, "learning_rate": 1.0548229768786127e-05, "loss": 0.7479, "step": 7188 }, { "epoch": 1.3, "learning_rate": 1.0545520231213874e-05, "loss": 0.3339, "step": 7189 }, { "epoch": 1.3, "learning_rate": 1.0542810693641619e-05, "loss": 0.5362, "step": 7190 }, { "epoch": 1.3, "learning_rate": 1.0540101156069365e-05, "loss": 0.7913, "step": 7191 }, { "epoch": 1.3, "learning_rate": 1.053739161849711e-05, "loss": 0.391, "step": 7192 }, { "epoch": 1.3, "learning_rate": 1.0534682080924855e-05, "loss": 0.4517, "step": 7193 }, { "epoch": 1.3, "learning_rate": 1.0531972543352601e-05, "loss": 0.8825, "step": 7194 }, { "epoch": 1.3, "learning_rate": 1.0529263005780347e-05, "loss": 0.2555, "step": 7195 }, { "epoch": 1.3, "learning_rate": 1.0526553468208093e-05, "loss": 0.8247, "step": 7196 }, { "epoch": 1.3, "learning_rate": 1.0523843930635838e-05, "loss": 0.8807, "step": 7197 }, { "epoch": 1.3, "learning_rate": 1.0521134393063584e-05, "loss": 0.2373, "step": 7198 }, { "epoch": 1.3, "learning_rate": 1.051842485549133e-05, "loss": 0.3301, "step": 7199 }, { "epoch": 1.3, "learning_rate": 1.0515715317919076e-05, "loss": 0.9645, "step": 7200 }, { "epoch": 1.3, "learning_rate": 1.051300578034682e-05, "loss": 0.2056, "step": 7201 }, { "epoch": 1.3, "learning_rate": 1.0510296242774566e-05, "loss": 0.705, "step": 7202 }, { "epoch": 1.3, "learning_rate": 1.0507586705202312e-05, "loss": 0.331, "step": 7203 }, { "epoch": 1.3, "learning_rate": 1.0504877167630059e-05, "loss": 0.5465, "step": 7204 }, { "epoch": 1.3, "learning_rate": 1.0502167630057805e-05, "loss": 0.8059, "step": 7205 }, { "epoch": 1.3, "learning_rate": 1.0499458092485549e-05, "loss": 0.6165, "step": 7206 }, { "epoch": 1.3, "learning_rate": 1.0496748554913295e-05, "loss": 0.5106, "step": 7207 }, { "epoch": 1.3, "learning_rate": 1.049403901734104e-05, "loss": 0.9916, "step": 7208 }, { "epoch": 1.3, "learning_rate": 1.0491329479768787e-05, "loss": 0.5036, "step": 7209 }, { "epoch": 1.3, "learning_rate": 1.0488619942196532e-05, "loss": 1.4736, "step": 7210 }, { "epoch": 1.3, "learning_rate": 1.0485910404624278e-05, "loss": 0.8732, "step": 7211 }, { "epoch": 1.3, "learning_rate": 1.0483200867052024e-05, "loss": 0.4071, "step": 7212 }, { "epoch": 1.3, "learning_rate": 1.0480491329479768e-05, "loss": 0.5742, "step": 7213 }, { "epoch": 1.3, "learning_rate": 1.0477781791907516e-05, "loss": 0.4533, "step": 7214 }, { "epoch": 1.3, "learning_rate": 1.047507225433526e-05, "loss": 0.8027, "step": 7215 }, { "epoch": 1.3, "learning_rate": 1.0472362716763006e-05, "loss": 0.5848, "step": 7216 }, { "epoch": 1.3, "learning_rate": 1.046965317919075e-05, "loss": 1.0821, "step": 7217 }, { "epoch": 1.3, "learning_rate": 1.0466943641618497e-05, "loss": 0.8659, "step": 7218 }, { "epoch": 1.3, "learning_rate": 1.0464234104046244e-05, "loss": 0.4367, "step": 7219 }, { "epoch": 1.3, "learning_rate": 1.0461524566473989e-05, "loss": 1.0466, "step": 7220 }, { "epoch": 1.3, "learning_rate": 1.0458815028901735e-05, "loss": 0.4387, "step": 7221 }, { "epoch": 1.3, "learning_rate": 1.0456105491329479e-05, "loss": 0.8663, "step": 7222 }, { "epoch": 1.3, "learning_rate": 1.0453395953757225e-05, "loss": 0.5304, "step": 7223 }, { "epoch": 1.3, "learning_rate": 1.0450686416184971e-05, "loss": 0.3113, "step": 7224 }, { "epoch": 1.31, "learning_rate": 1.0447976878612717e-05, "loss": 0.2092, "step": 7225 }, { "epoch": 1.31, "learning_rate": 1.0445267341040463e-05, "loss": 0.5941, "step": 7226 }, { "epoch": 1.31, "learning_rate": 1.0442557803468208e-05, "loss": 0.2989, "step": 7227 }, { "epoch": 1.31, "learning_rate": 1.0439848265895954e-05, "loss": 0.4074, "step": 7228 }, { "epoch": 1.31, "learning_rate": 1.04371387283237e-05, "loss": 0.3265, "step": 7229 }, { "epoch": 1.31, "learning_rate": 1.0434429190751446e-05, "loss": 0.5837, "step": 7230 }, { "epoch": 1.31, "learning_rate": 1.043171965317919e-05, "loss": 0.5524, "step": 7231 }, { "epoch": 1.31, "learning_rate": 1.0429010115606936e-05, "loss": 0.436, "step": 7232 }, { "epoch": 1.31, "learning_rate": 1.0426300578034682e-05, "loss": 0.4589, "step": 7233 }, { "epoch": 1.31, "learning_rate": 1.0423591040462428e-05, "loss": 0.7897, "step": 7234 }, { "epoch": 1.31, "learning_rate": 1.0420881502890175e-05, "loss": 0.7716, "step": 7235 }, { "epoch": 1.31, "learning_rate": 1.0418171965317919e-05, "loss": 0.5874, "step": 7236 }, { "epoch": 1.31, "learning_rate": 1.0415462427745665e-05, "loss": 0.5465, "step": 7237 }, { "epoch": 1.31, "learning_rate": 1.0412752890173411e-05, "loss": 0.4124, "step": 7238 }, { "epoch": 1.31, "learning_rate": 1.0410043352601157e-05, "loss": 0.7474, "step": 7239 }, { "epoch": 1.31, "learning_rate": 1.0407333815028901e-05, "loss": 0.5297, "step": 7240 }, { "epoch": 1.31, "learning_rate": 1.0404624277456647e-05, "loss": 1.2567, "step": 7241 }, { "epoch": 1.31, "learning_rate": 1.0401914739884394e-05, "loss": 0.7122, "step": 7242 }, { "epoch": 1.31, "learning_rate": 1.039920520231214e-05, "loss": 0.5957, "step": 7243 }, { "epoch": 1.31, "learning_rate": 1.0396495664739886e-05, "loss": 0.6951, "step": 7244 }, { "epoch": 1.31, "learning_rate": 1.039378612716763e-05, "loss": 0.6099, "step": 7245 }, { "epoch": 1.31, "learning_rate": 1.0391076589595376e-05, "loss": 1.0898, "step": 7246 }, { "epoch": 1.31, "learning_rate": 1.038836705202312e-05, "loss": 0.7881, "step": 7247 }, { "epoch": 1.31, "learning_rate": 1.0385657514450868e-05, "loss": 0.4568, "step": 7248 }, { "epoch": 1.31, "learning_rate": 1.0382947976878613e-05, "loss": 0.8954, "step": 7249 }, { "epoch": 1.31, "learning_rate": 1.0380238439306359e-05, "loss": 0.4122, "step": 7250 }, { "epoch": 1.31, "learning_rate": 1.0377528901734105e-05, "loss": 0.3589, "step": 7251 }, { "epoch": 1.31, "learning_rate": 1.0374819364161849e-05, "loss": 0.5383, "step": 7252 }, { "epoch": 1.31, "learning_rate": 1.0372109826589597e-05, "loss": 0.416, "step": 7253 }, { "epoch": 1.31, "learning_rate": 1.0369400289017341e-05, "loss": 0.5936, "step": 7254 }, { "epoch": 1.31, "learning_rate": 1.0366690751445087e-05, "loss": 0.4647, "step": 7255 }, { "epoch": 1.31, "learning_rate": 1.0363981213872832e-05, "loss": 0.4894, "step": 7256 }, { "epoch": 1.31, "learning_rate": 1.0361271676300578e-05, "loss": 0.5096, "step": 7257 }, { "epoch": 1.31, "learning_rate": 1.0358562138728325e-05, "loss": 0.5912, "step": 7258 }, { "epoch": 1.31, "learning_rate": 1.035585260115607e-05, "loss": 0.3869, "step": 7259 }, { "epoch": 1.31, "learning_rate": 1.0353143063583816e-05, "loss": 0.4086, "step": 7260 }, { "epoch": 1.31, "learning_rate": 1.035043352601156e-05, "loss": 0.5861, "step": 7261 }, { "epoch": 1.31, "learning_rate": 1.0347723988439306e-05, "loss": 0.8734, "step": 7262 }, { "epoch": 1.31, "learning_rate": 1.0345014450867052e-05, "loss": 0.5089, "step": 7263 }, { "epoch": 1.31, "learning_rate": 1.0342304913294798e-05, "loss": 1.2481, "step": 7264 }, { "epoch": 1.31, "learning_rate": 1.0339595375722544e-05, "loss": 0.5083, "step": 7265 }, { "epoch": 1.31, "learning_rate": 1.0336885838150289e-05, "loss": 0.7479, "step": 7266 }, { "epoch": 1.31, "learning_rate": 1.0334176300578035e-05, "loss": 0.6539, "step": 7267 }, { "epoch": 1.31, "learning_rate": 1.0331466763005781e-05, "loss": 0.1936, "step": 7268 }, { "epoch": 1.31, "learning_rate": 1.0328757225433527e-05, "loss": 0.4348, "step": 7269 }, { "epoch": 1.31, "learning_rate": 1.0326047687861271e-05, "loss": 0.6248, "step": 7270 }, { "epoch": 1.31, "learning_rate": 1.0323338150289017e-05, "loss": 0.7164, "step": 7271 }, { "epoch": 1.31, "learning_rate": 1.0320628612716762e-05, "loss": 0.5522, "step": 7272 }, { "epoch": 1.31, "learning_rate": 1.031791907514451e-05, "loss": 0.6614, "step": 7273 }, { "epoch": 1.31, "learning_rate": 1.0315209537572256e-05, "loss": 0.5617, "step": 7274 }, { "epoch": 1.31, "learning_rate": 1.03125e-05, "loss": 0.4088, "step": 7275 }, { "epoch": 1.31, "learning_rate": 1.0309790462427746e-05, "loss": 0.9736, "step": 7276 }, { "epoch": 1.31, "learning_rate": 1.030708092485549e-05, "loss": 0.1996, "step": 7277 }, { "epoch": 1.31, "learning_rate": 1.0304371387283238e-05, "loss": 0.9858, "step": 7278 }, { "epoch": 1.31, "learning_rate": 1.0301661849710982e-05, "loss": 0.5894, "step": 7279 }, { "epoch": 1.32, "learning_rate": 1.0298952312138729e-05, "loss": 0.7282, "step": 7280 }, { "epoch": 1.32, "learning_rate": 1.0296242774566475e-05, "loss": 0.1494, "step": 7281 }, { "epoch": 1.32, "learning_rate": 1.0293533236994219e-05, "loss": 0.7229, "step": 7282 }, { "epoch": 1.32, "learning_rate": 1.0290823699421967e-05, "loss": 1.0557, "step": 7283 }, { "epoch": 1.32, "learning_rate": 1.0288114161849711e-05, "loss": 0.5238, "step": 7284 }, { "epoch": 1.32, "learning_rate": 1.0285404624277457e-05, "loss": 0.2464, "step": 7285 }, { "epoch": 1.32, "learning_rate": 1.0282695086705202e-05, "loss": 0.8988, "step": 7286 }, { "epoch": 1.32, "learning_rate": 1.0279985549132948e-05, "loss": 0.9172, "step": 7287 }, { "epoch": 1.32, "learning_rate": 1.0277276011560695e-05, "loss": 0.734, "step": 7288 }, { "epoch": 1.32, "learning_rate": 1.027456647398844e-05, "loss": 0.625, "step": 7289 }, { "epoch": 1.32, "learning_rate": 1.0271856936416186e-05, "loss": 0.6274, "step": 7290 }, { "epoch": 1.32, "learning_rate": 1.026914739884393e-05, "loss": 0.4653, "step": 7291 }, { "epoch": 1.32, "learning_rate": 1.0266437861271676e-05, "loss": 0.3489, "step": 7292 }, { "epoch": 1.32, "learning_rate": 1.0263728323699422e-05, "loss": 0.5269, "step": 7293 }, { "epoch": 1.32, "learning_rate": 1.0261018786127168e-05, "loss": 0.6781, "step": 7294 }, { "epoch": 1.32, "learning_rate": 1.0258309248554913e-05, "loss": 0.1886, "step": 7295 }, { "epoch": 1.32, "learning_rate": 1.0255599710982659e-05, "loss": 0.6322, "step": 7296 }, { "epoch": 1.32, "learning_rate": 1.0252890173410405e-05, "loss": 1.0671, "step": 7297 }, { "epoch": 1.32, "learning_rate": 1.025018063583815e-05, "loss": 0.4158, "step": 7298 }, { "epoch": 1.32, "learning_rate": 1.0247471098265897e-05, "loss": 0.5586, "step": 7299 }, { "epoch": 1.32, "learning_rate": 1.0244761560693641e-05, "loss": 0.5876, "step": 7300 }, { "epoch": 1.32, "learning_rate": 1.0242052023121387e-05, "loss": 0.6585, "step": 7301 }, { "epoch": 1.32, "learning_rate": 1.0239342485549132e-05, "loss": 0.5224, "step": 7302 }, { "epoch": 1.32, "learning_rate": 1.023663294797688e-05, "loss": 0.2069, "step": 7303 }, { "epoch": 1.32, "learning_rate": 1.0233923410404625e-05, "loss": 0.3885, "step": 7304 }, { "epoch": 1.32, "learning_rate": 1.023121387283237e-05, "loss": 0.6616, "step": 7305 }, { "epoch": 1.32, "learning_rate": 1.0228504335260116e-05, "loss": 0.4069, "step": 7306 }, { "epoch": 1.32, "learning_rate": 1.022579479768786e-05, "loss": 0.4563, "step": 7307 }, { "epoch": 1.32, "learning_rate": 1.0223085260115608e-05, "loss": 0.5481, "step": 7308 }, { "epoch": 1.32, "learning_rate": 1.0220375722543352e-05, "loss": 0.5187, "step": 7309 }, { "epoch": 1.32, "learning_rate": 1.0217666184971098e-05, "loss": 0.7699, "step": 7310 }, { "epoch": 1.32, "learning_rate": 1.0214956647398845e-05, "loss": 0.3289, "step": 7311 }, { "epoch": 1.32, "learning_rate": 1.0212247109826589e-05, "loss": 0.4321, "step": 7312 }, { "epoch": 1.32, "learning_rate": 1.0209537572254337e-05, "loss": 0.6266, "step": 7313 }, { "epoch": 1.32, "learning_rate": 1.0206828034682081e-05, "loss": 0.5817, "step": 7314 }, { "epoch": 1.32, "learning_rate": 1.0204118497109827e-05, "loss": 0.775, "step": 7315 }, { "epoch": 1.32, "learning_rate": 1.0201408959537571e-05, "loss": 0.4049, "step": 7316 }, { "epoch": 1.32, "learning_rate": 1.0198699421965317e-05, "loss": 0.2569, "step": 7317 }, { "epoch": 1.32, "learning_rate": 1.0195989884393064e-05, "loss": 0.6597, "step": 7318 }, { "epoch": 1.32, "learning_rate": 1.019328034682081e-05, "loss": 0.552, "step": 7319 }, { "epoch": 1.32, "learning_rate": 1.0190570809248556e-05, "loss": 0.3201, "step": 7320 }, { "epoch": 1.32, "learning_rate": 1.01878612716763e-05, "loss": 0.3398, "step": 7321 }, { "epoch": 1.32, "learning_rate": 1.0185151734104048e-05, "loss": 1.0401, "step": 7322 }, { "epoch": 1.32, "learning_rate": 1.0182442196531792e-05, "loss": 0.3606, "step": 7323 }, { "epoch": 1.32, "learning_rate": 1.0179732658959538e-05, "loss": 1.4276, "step": 7324 }, { "epoch": 1.32, "learning_rate": 1.0177023121387283e-05, "loss": 0.7001, "step": 7325 }, { "epoch": 1.32, "learning_rate": 1.0174313583815029e-05, "loss": 0.5396, "step": 7326 }, { "epoch": 1.32, "learning_rate": 1.0171604046242776e-05, "loss": 0.712, "step": 7327 }, { "epoch": 1.32, "learning_rate": 1.016889450867052e-05, "loss": 1.1456, "step": 7328 }, { "epoch": 1.32, "learning_rate": 1.0166184971098267e-05, "loss": 0.517, "step": 7329 }, { "epoch": 1.32, "learning_rate": 1.0163475433526011e-05, "loss": 0.6546, "step": 7330 }, { "epoch": 1.32, "learning_rate": 1.0160765895953757e-05, "loss": 0.167, "step": 7331 }, { "epoch": 1.32, "learning_rate": 1.0158056358381503e-05, "loss": 0.5892, "step": 7332 }, { "epoch": 1.32, "learning_rate": 1.015534682080925e-05, "loss": 0.3504, "step": 7333 }, { "epoch": 1.32, "learning_rate": 1.0152637283236995e-05, "loss": 0.3164, "step": 7334 }, { "epoch": 1.32, "learning_rate": 1.014992774566474e-05, "loss": 0.6752, "step": 7335 }, { "epoch": 1.33, "learning_rate": 1.0147218208092486e-05, "loss": 0.3583, "step": 7336 }, { "epoch": 1.33, "learning_rate": 1.0144508670520232e-05, "loss": 0.3709, "step": 7337 }, { "epoch": 1.33, "learning_rate": 1.0141799132947978e-05, "loss": 0.7628, "step": 7338 }, { "epoch": 1.33, "learning_rate": 1.0139089595375722e-05, "loss": 0.3309, "step": 7339 }, { "epoch": 1.33, "learning_rate": 1.0136380057803468e-05, "loss": 1.123, "step": 7340 }, { "epoch": 1.33, "learning_rate": 1.0133670520231213e-05, "loss": 2.2863, "step": 7341 }, { "epoch": 1.33, "learning_rate": 1.013096098265896e-05, "loss": 0.4539, "step": 7342 }, { "epoch": 1.33, "learning_rate": 1.0128251445086707e-05, "loss": 0.2875, "step": 7343 }, { "epoch": 1.33, "learning_rate": 1.0125541907514451e-05, "loss": 0.2803, "step": 7344 }, { "epoch": 1.33, "learning_rate": 1.0122832369942197e-05, "loss": 0.854, "step": 7345 }, { "epoch": 1.33, "learning_rate": 1.0120122832369941e-05, "loss": 0.4889, "step": 7346 }, { "epoch": 1.33, "learning_rate": 1.0117413294797689e-05, "loss": 0.2866, "step": 7347 }, { "epoch": 1.33, "learning_rate": 1.0114703757225433e-05, "loss": 0.5685, "step": 7348 }, { "epoch": 1.33, "learning_rate": 1.011199421965318e-05, "loss": 0.5333, "step": 7349 }, { "epoch": 1.33, "learning_rate": 1.0109284682080926e-05, "loss": 0.3869, "step": 7350 }, { "epoch": 1.33, "learning_rate": 1.010657514450867e-05, "loss": 0.5744, "step": 7351 }, { "epoch": 1.33, "learning_rate": 1.0103865606936418e-05, "loss": 0.6633, "step": 7352 }, { "epoch": 1.33, "learning_rate": 1.0101156069364162e-05, "loss": 0.65, "step": 7353 }, { "epoch": 1.33, "learning_rate": 1.0098446531791908e-05, "loss": 0.4751, "step": 7354 }, { "epoch": 1.33, "learning_rate": 1.0095736994219652e-05, "loss": 0.211, "step": 7355 }, { "epoch": 1.33, "learning_rate": 1.0093027456647399e-05, "loss": 0.2049, "step": 7356 }, { "epoch": 1.33, "learning_rate": 1.0090317919075145e-05, "loss": 0.3655, "step": 7357 }, { "epoch": 1.33, "learning_rate": 1.008760838150289e-05, "loss": 0.4796, "step": 7358 }, { "epoch": 1.33, "learning_rate": 1.0084898843930637e-05, "loss": 1.0328, "step": 7359 }, { "epoch": 1.33, "learning_rate": 1.0082189306358381e-05, "loss": 0.2947, "step": 7360 }, { "epoch": 1.33, "learning_rate": 1.0079479768786127e-05, "loss": 0.8932, "step": 7361 }, { "epoch": 1.33, "learning_rate": 1.0076770231213873e-05, "loss": 0.3704, "step": 7362 }, { "epoch": 1.33, "learning_rate": 1.007406069364162e-05, "loss": 0.6001, "step": 7363 }, { "epoch": 1.33, "learning_rate": 1.0071351156069364e-05, "loss": 0.3832, "step": 7364 }, { "epoch": 1.33, "learning_rate": 1.006864161849711e-05, "loss": 0.6024, "step": 7365 }, { "epoch": 1.33, "learning_rate": 1.0065932080924856e-05, "loss": 0.235, "step": 7366 }, { "epoch": 1.33, "learning_rate": 1.0063222543352602e-05, "loss": 0.3736, "step": 7367 }, { "epoch": 1.33, "learning_rate": 1.0060513005780348e-05, "loss": 0.6149, "step": 7368 }, { "epoch": 1.33, "learning_rate": 1.0057803468208092e-05, "loss": 0.3352, "step": 7369 }, { "epoch": 1.33, "learning_rate": 1.0055093930635838e-05, "loss": 0.7189, "step": 7370 }, { "epoch": 1.33, "learning_rate": 1.0052384393063583e-05, "loss": 0.6351, "step": 7371 }, { "epoch": 1.33, "learning_rate": 1.004967485549133e-05, "loss": 0.5414, "step": 7372 }, { "epoch": 1.33, "learning_rate": 1.0046965317919076e-05, "loss": 0.4098, "step": 7373 }, { "epoch": 1.33, "learning_rate": 1.004425578034682e-05, "loss": 0.4811, "step": 7374 }, { "epoch": 1.33, "learning_rate": 1.0041546242774567e-05, "loss": 0.9021, "step": 7375 }, { "epoch": 1.33, "learning_rate": 1.0038836705202311e-05, "loss": 0.4123, "step": 7376 }, { "epoch": 1.33, "learning_rate": 1.0036127167630059e-05, "loss": 0.5917, "step": 7377 }, { "epoch": 1.33, "learning_rate": 1.0033417630057803e-05, "loss": 1.0304, "step": 7378 }, { "epoch": 1.33, "learning_rate": 1.003070809248555e-05, "loss": 0.4027, "step": 7379 }, { "epoch": 1.33, "learning_rate": 1.0027998554913295e-05, "loss": 0.602, "step": 7380 }, { "epoch": 1.33, "learning_rate": 1.002528901734104e-05, "loss": 0.5847, "step": 7381 }, { "epoch": 1.33, "learning_rate": 1.0022579479768788e-05, "loss": 0.2661, "step": 7382 }, { "epoch": 1.33, "learning_rate": 1.0019869942196532e-05, "loss": 1.2804, "step": 7383 }, { "epoch": 1.33, "learning_rate": 1.0017160404624278e-05, "loss": 0.5837, "step": 7384 }, { "epoch": 1.33, "learning_rate": 1.0014450867052022e-05, "loss": 0.7158, "step": 7385 }, { "epoch": 1.33, "learning_rate": 1.0011741329479768e-05, "loss": 0.9338, "step": 7386 }, { "epoch": 1.33, "learning_rate": 1.0009031791907515e-05, "loss": 0.6617, "step": 7387 }, { "epoch": 1.33, "learning_rate": 1.000632225433526e-05, "loss": 0.5214, "step": 7388 }, { "epoch": 1.33, "learning_rate": 1.0003612716763007e-05, "loss": 0.4452, "step": 7389 }, { "epoch": 1.33, "learning_rate": 1.0000903179190751e-05, "loss": 0.666, "step": 7390 }, { "epoch": 1.34, "learning_rate": 9.998193641618497e-06, "loss": 1.5624, "step": 7391 }, { "epoch": 1.34, "learning_rate": 9.995484104046243e-06, "loss": 0.5795, "step": 7392 }, { "epoch": 1.34, "learning_rate": 9.99277456647399e-06, "loss": 0.4833, "step": 7393 }, { "epoch": 1.34, "learning_rate": 9.990065028901734e-06, "loss": 0.3325, "step": 7394 }, { "epoch": 1.34, "learning_rate": 9.98735549132948e-06, "loss": 1.1192, "step": 7395 }, { "epoch": 1.34, "learning_rate": 9.984645953757226e-06, "loss": 0.9915, "step": 7396 }, { "epoch": 1.34, "learning_rate": 9.981936416184972e-06, "loss": 0.6508, "step": 7397 }, { "epoch": 1.34, "learning_rate": 9.979226878612718e-06, "loss": 0.5566, "step": 7398 }, { "epoch": 1.34, "learning_rate": 9.976517341040462e-06, "loss": 0.4845, "step": 7399 }, { "epoch": 1.34, "learning_rate": 9.973807803468208e-06, "loss": 0.3531, "step": 7400 }, { "epoch": 1.34, "learning_rate": 9.971098265895953e-06, "loss": 0.4968, "step": 7401 }, { "epoch": 1.34, "learning_rate": 9.9683887283237e-06, "loss": 0.2769, "step": 7402 }, { "epoch": 1.34, "learning_rate": 9.965679190751445e-06, "loss": 0.5709, "step": 7403 }, { "epoch": 1.34, "learning_rate": 9.96296965317919e-06, "loss": 0.2436, "step": 7404 }, { "epoch": 1.34, "learning_rate": 9.960260115606937e-06, "loss": 0.3364, "step": 7405 }, { "epoch": 1.34, "learning_rate": 9.957550578034683e-06, "loss": 0.5169, "step": 7406 }, { "epoch": 1.34, "learning_rate": 9.954841040462429e-06, "loss": 0.2294, "step": 7407 }, { "epoch": 1.34, "learning_rate": 9.952131502890173e-06, "loss": 0.6423, "step": 7408 }, { "epoch": 1.34, "learning_rate": 9.94942196531792e-06, "loss": 0.3848, "step": 7409 }, { "epoch": 1.34, "learning_rate": 9.946712427745664e-06, "loss": 0.6674, "step": 7410 }, { "epoch": 1.34, "learning_rate": 9.944002890173411e-06, "loss": 0.398, "step": 7411 }, { "epoch": 1.34, "learning_rate": 9.941293352601158e-06, "loss": 0.3882, "step": 7412 }, { "epoch": 1.34, "learning_rate": 9.938583815028902e-06, "loss": 0.4218, "step": 7413 }, { "epoch": 1.34, "learning_rate": 9.935874277456648e-06, "loss": 1.381, "step": 7414 }, { "epoch": 1.34, "learning_rate": 9.933164739884392e-06, "loss": 0.8645, "step": 7415 }, { "epoch": 1.34, "learning_rate": 9.93045520231214e-06, "loss": 0.8429, "step": 7416 }, { "epoch": 1.34, "learning_rate": 9.927745664739884e-06, "loss": 0.3718, "step": 7417 }, { "epoch": 1.34, "learning_rate": 9.92503612716763e-06, "loss": 1.2412, "step": 7418 }, { "epoch": 1.34, "learning_rate": 9.922326589595377e-06, "loss": 0.6896, "step": 7419 }, { "epoch": 1.34, "learning_rate": 9.919617052023121e-06, "loss": 0.5278, "step": 7420 }, { "epoch": 1.34, "learning_rate": 9.916907514450869e-06, "loss": 0.7389, "step": 7421 }, { "epoch": 1.34, "learning_rate": 9.914197976878613e-06, "loss": 0.6397, "step": 7422 }, { "epoch": 1.34, "learning_rate": 9.911488439306359e-06, "loss": 0.3452, "step": 7423 }, { "epoch": 1.34, "learning_rate": 9.908778901734103e-06, "loss": 0.5773, "step": 7424 }, { "epoch": 1.34, "learning_rate": 9.90606936416185e-06, "loss": 0.5093, "step": 7425 }, { "epoch": 1.34, "learning_rate": 9.903359826589596e-06, "loss": 0.2047, "step": 7426 }, { "epoch": 1.34, "learning_rate": 9.900650289017342e-06, "loss": 0.5655, "step": 7427 }, { "epoch": 1.34, "learning_rate": 9.897940751445088e-06, "loss": 0.451, "step": 7428 }, { "epoch": 1.34, "learning_rate": 9.895231213872832e-06, "loss": 0.1369, "step": 7429 }, { "epoch": 1.34, "learning_rate": 9.892521676300578e-06, "loss": 1.0187, "step": 7430 }, { "epoch": 1.34, "learning_rate": 9.889812138728324e-06, "loss": 0.8503, "step": 7431 }, { "epoch": 1.34, "learning_rate": 9.88710260115607e-06, "loss": 0.2692, "step": 7432 }, { "epoch": 1.34, "learning_rate": 9.884393063583815e-06, "loss": 0.6737, "step": 7433 }, { "epoch": 1.34, "learning_rate": 9.88168352601156e-06, "loss": 0.4422, "step": 7434 }, { "epoch": 1.34, "learning_rate": 9.878973988439307e-06, "loss": 0.5947, "step": 7435 }, { "epoch": 1.34, "learning_rate": 9.876264450867053e-06, "loss": 0.706, "step": 7436 }, { "epoch": 1.34, "learning_rate": 9.873554913294799e-06, "loss": 0.684, "step": 7437 }, { "epoch": 1.34, "learning_rate": 9.870845375722543e-06, "loss": 0.7013, "step": 7438 }, { "epoch": 1.34, "learning_rate": 9.86813583815029e-06, "loss": 0.2602, "step": 7439 }, { "epoch": 1.34, "learning_rate": 9.865426300578034e-06, "loss": 0.5235, "step": 7440 }, { "epoch": 1.34, "learning_rate": 9.862716763005781e-06, "loss": 1.025, "step": 7441 }, { "epoch": 1.34, "learning_rate": 9.860007225433527e-06, "loss": 0.7564, "step": 7442 }, { "epoch": 1.34, "learning_rate": 9.857297687861272e-06, "loss": 0.3052, "step": 7443 }, { "epoch": 1.34, "learning_rate": 9.854588150289018e-06, "loss": 0.365, "step": 7444 }, { "epoch": 1.34, "learning_rate": 9.851878612716762e-06, "loss": 0.5653, "step": 7445 }, { "epoch": 1.35, "learning_rate": 9.84916907514451e-06, "loss": 0.4525, "step": 7446 }, { "epoch": 1.35, "learning_rate": 9.846459537572254e-06, "loss": 0.2651, "step": 7447 }, { "epoch": 1.35, "learning_rate": 9.84375e-06, "loss": 0.212, "step": 7448 }, { "epoch": 1.35, "learning_rate": 9.841040462427745e-06, "loss": 0.3893, "step": 7449 }, { "epoch": 1.35, "learning_rate": 9.83833092485549e-06, "loss": 0.6077, "step": 7450 }, { "epoch": 1.35, "learning_rate": 9.835621387283239e-06, "loss": 0.5582, "step": 7451 }, { "epoch": 1.35, "learning_rate": 9.832911849710983e-06, "loss": 0.2513, "step": 7452 }, { "epoch": 1.35, "learning_rate": 9.830202312138729e-06, "loss": 0.2656, "step": 7453 }, { "epoch": 1.35, "learning_rate": 9.827492774566473e-06, "loss": 0.5515, "step": 7454 }, { "epoch": 1.35, "learning_rate": 9.82478323699422e-06, "loss": 0.3289, "step": 7455 }, { "epoch": 1.35, "learning_rate": 9.822073699421965e-06, "loss": 0.6907, "step": 7456 }, { "epoch": 1.35, "learning_rate": 9.819364161849712e-06, "loss": 0.8873, "step": 7457 }, { "epoch": 1.35, "learning_rate": 9.816654624277458e-06, "loss": 0.4816, "step": 7458 }, { "epoch": 1.35, "learning_rate": 9.813945086705202e-06, "loss": 0.2638, "step": 7459 }, { "epoch": 1.35, "learning_rate": 9.811235549132948e-06, "loss": 0.5984, "step": 7460 }, { "epoch": 1.35, "learning_rate": 9.808526011560694e-06, "loss": 0.8825, "step": 7461 }, { "epoch": 1.35, "learning_rate": 9.80581647398844e-06, "loss": 0.5383, "step": 7462 }, { "epoch": 1.35, "learning_rate": 9.803106936416185e-06, "loss": 1.1782, "step": 7463 }, { "epoch": 1.35, "learning_rate": 9.80039739884393e-06, "loss": 0.1857, "step": 7464 }, { "epoch": 1.35, "learning_rate": 9.797687861271677e-06, "loss": 0.3473, "step": 7465 }, { "epoch": 1.35, "learning_rate": 9.794978323699423e-06, "loss": 0.2453, "step": 7466 }, { "epoch": 1.35, "learning_rate": 9.792268786127169e-06, "loss": 0.8928, "step": 7467 }, { "epoch": 1.35, "learning_rate": 9.789559248554913e-06, "loss": 0.9363, "step": 7468 }, { "epoch": 1.35, "learning_rate": 9.78684971098266e-06, "loss": 0.6349, "step": 7469 }, { "epoch": 1.35, "learning_rate": 9.784140173410404e-06, "loss": 0.4407, "step": 7470 }, { "epoch": 1.35, "learning_rate": 9.781430635838151e-06, "loss": 0.469, "step": 7471 }, { "epoch": 1.35, "learning_rate": 9.778721098265896e-06, "loss": 1.251, "step": 7472 }, { "epoch": 1.35, "learning_rate": 9.776011560693642e-06, "loss": 1.2035, "step": 7473 }, { "epoch": 1.35, "learning_rate": 9.773302023121388e-06, "loss": 0.6776, "step": 7474 }, { "epoch": 1.35, "learning_rate": 9.770592485549132e-06, "loss": 0.3481, "step": 7475 }, { "epoch": 1.35, "learning_rate": 9.76788294797688e-06, "loss": 0.6964, "step": 7476 }, { "epoch": 1.35, "learning_rate": 9.765173410404624e-06, "loss": 0.3926, "step": 7477 }, { "epoch": 1.35, "learning_rate": 9.76246387283237e-06, "loss": 0.3428, "step": 7478 }, { "epoch": 1.35, "learning_rate": 9.759754335260115e-06, "loss": 0.3605, "step": 7479 }, { "epoch": 1.35, "learning_rate": 9.75704479768786e-06, "loss": 0.3684, "step": 7480 }, { "epoch": 1.35, "learning_rate": 9.754335260115609e-06, "loss": 0.7502, "step": 7481 }, { "epoch": 1.35, "learning_rate": 9.751625722543353e-06, "loss": 0.3297, "step": 7482 }, { "epoch": 1.35, "learning_rate": 9.748916184971099e-06, "loss": 0.7076, "step": 7483 }, { "epoch": 1.35, "learning_rate": 9.746206647398843e-06, "loss": 0.594, "step": 7484 }, { "epoch": 1.35, "learning_rate": 9.74349710982659e-06, "loss": 0.5003, "step": 7485 }, { "epoch": 1.35, "learning_rate": 9.740787572254335e-06, "loss": 1.0704, "step": 7486 }, { "epoch": 1.35, "learning_rate": 9.738078034682081e-06, "loss": 0.5311, "step": 7487 }, { "epoch": 1.35, "learning_rate": 9.735368497109828e-06, "loss": 1.7345, "step": 7488 }, { "epoch": 1.35, "learning_rate": 9.732658959537572e-06, "loss": 0.3114, "step": 7489 }, { "epoch": 1.35, "learning_rate": 9.729949421965318e-06, "loss": 0.4184, "step": 7490 }, { "epoch": 1.35, "learning_rate": 9.727239884393064e-06, "loss": 0.7857, "step": 7491 }, { "epoch": 1.35, "learning_rate": 9.72453034682081e-06, "loss": 0.3152, "step": 7492 }, { "epoch": 1.35, "learning_rate": 9.721820809248554e-06, "loss": 1.0162, "step": 7493 }, { "epoch": 1.35, "learning_rate": 9.7191112716763e-06, "loss": 0.6179, "step": 7494 }, { "epoch": 1.35, "learning_rate": 9.716401734104047e-06, "loss": 0.317, "step": 7495 }, { "epoch": 1.35, "learning_rate": 9.713692196531793e-06, "loss": 0.9313, "step": 7496 }, { "epoch": 1.35, "learning_rate": 9.710982658959539e-06, "loss": 0.4097, "step": 7497 }, { "epoch": 1.35, "learning_rate": 9.708273121387283e-06, "loss": 0.2151, "step": 7498 }, { "epoch": 1.35, "learning_rate": 9.705563583815029e-06, "loss": 0.4176, "step": 7499 }, { "epoch": 1.35, "learning_rate": 9.702854046242775e-06, "loss": 0.437, "step": 7500 }, { "epoch": 1.35, "eval_exact_match": 86.93472090823084, "eval_f1": 93.29362691249123, "step": 7500 }, { "epoch": 1.35, "learning_rate": 9.700144508670521e-06, "loss": 0.4348, "step": 7501 }, { "epoch": 1.36, "learning_rate": 9.697434971098266e-06, "loss": 0.7956, "step": 7502 }, { "epoch": 1.36, "learning_rate": 9.694725433526012e-06, "loss": 0.6351, "step": 7503 }, { "epoch": 1.36, "learning_rate": 9.692015895953758e-06, "loss": 0.6047, "step": 7504 }, { "epoch": 1.36, "learning_rate": 9.689306358381504e-06, "loss": 0.4296, "step": 7505 }, { "epoch": 1.36, "learning_rate": 9.68659682080925e-06, "loss": 0.5474, "step": 7506 }, { "epoch": 1.36, "learning_rate": 9.683887283236994e-06, "loss": 0.5319, "step": 7507 }, { "epoch": 1.36, "learning_rate": 9.68117774566474e-06, "loss": 0.8318, "step": 7508 }, { "epoch": 1.36, "learning_rate": 9.678468208092485e-06, "loss": 0.2435, "step": 7509 }, { "epoch": 1.36, "learning_rate": 9.675758670520232e-06, "loss": 0.3461, "step": 7510 }, { "epoch": 1.36, "learning_rate": 9.673049132947977e-06, "loss": 0.5298, "step": 7511 }, { "epoch": 1.36, "learning_rate": 9.670339595375723e-06, "loss": 0.6875, "step": 7512 }, { "epoch": 1.36, "learning_rate": 9.667630057803469e-06, "loss": 0.4512, "step": 7513 }, { "epoch": 1.36, "learning_rate": 9.664920520231213e-06, "loss": 0.6546, "step": 7514 }, { "epoch": 1.36, "learning_rate": 9.662210982658961e-06, "loss": 0.6492, "step": 7515 }, { "epoch": 1.36, "learning_rate": 9.659501445086705e-06, "loss": 1.0373, "step": 7516 }, { "epoch": 1.36, "learning_rate": 9.656791907514451e-06, "loss": 0.7277, "step": 7517 }, { "epoch": 1.36, "learning_rate": 9.654082369942196e-06, "loss": 0.5304, "step": 7518 }, { "epoch": 1.36, "learning_rate": 9.651372832369942e-06, "loss": 0.6151, "step": 7519 }, { "epoch": 1.36, "learning_rate": 9.64866329479769e-06, "loss": 0.3653, "step": 7520 }, { "epoch": 1.36, "learning_rate": 9.645953757225434e-06, "loss": 1.0789, "step": 7521 }, { "epoch": 1.36, "learning_rate": 9.64324421965318e-06, "loss": 0.8136, "step": 7522 }, { "epoch": 1.36, "learning_rate": 9.640534682080924e-06, "loss": 0.4893, "step": 7523 }, { "epoch": 1.36, "learning_rate": 9.63782514450867e-06, "loss": 0.798, "step": 7524 }, { "epoch": 1.36, "learning_rate": 9.635115606936416e-06, "loss": 0.5613, "step": 7525 }, { "epoch": 1.36, "learning_rate": 9.632406069364163e-06, "loss": 1.1816, "step": 7526 }, { "epoch": 1.36, "learning_rate": 9.629696531791909e-06, "loss": 0.5892, "step": 7527 }, { "epoch": 1.36, "learning_rate": 9.626986994219653e-06, "loss": 0.3361, "step": 7528 }, { "epoch": 1.36, "learning_rate": 9.624277456647399e-06, "loss": 0.9428, "step": 7529 }, { "epoch": 1.36, "learning_rate": 9.621567919075145e-06, "loss": 0.8623, "step": 7530 }, { "epoch": 1.36, "learning_rate": 9.618858381502891e-06, "loss": 0.7623, "step": 7531 }, { "epoch": 1.36, "learning_rate": 9.616148843930635e-06, "loss": 0.7496, "step": 7532 }, { "epoch": 1.36, "learning_rate": 9.616148843930635e-06, "loss": 0.6815, "step": 7533 }, { "epoch": 1.36, "learning_rate": 9.613439306358382e-06, "loss": 0.6283, "step": 7534 }, { "epoch": 1.36, "learning_rate": 9.610729768786126e-06, "loss": 0.5962, "step": 7535 }, { "epoch": 1.36, "learning_rate": 9.608020231213874e-06, "loss": 0.2843, "step": 7536 }, { "epoch": 1.36, "learning_rate": 9.60531069364162e-06, "loss": 0.6381, "step": 7537 }, { "epoch": 1.36, "learning_rate": 9.602601156069364e-06, "loss": 0.5582, "step": 7538 }, { "epoch": 1.36, "learning_rate": 9.59989161849711e-06, "loss": 0.8296, "step": 7539 }, { "epoch": 1.36, "learning_rate": 9.597182080924855e-06, "loss": 0.4332, "step": 7540 }, { "epoch": 1.36, "learning_rate": 9.594472543352602e-06, "loss": 0.5347, "step": 7541 }, { "epoch": 1.36, "learning_rate": 9.591763005780347e-06, "loss": 0.958, "step": 7542 }, { "epoch": 1.36, "learning_rate": 9.589053468208093e-06, "loss": 0.344, "step": 7543 }, { "epoch": 1.36, "learning_rate": 9.586343930635839e-06, "loss": 0.7021, "step": 7544 }, { "epoch": 1.36, "learning_rate": 9.583634393063583e-06, "loss": 0.5896, "step": 7545 }, { "epoch": 1.36, "learning_rate": 9.580924855491331e-06, "loss": 0.4747, "step": 7546 }, { "epoch": 1.36, "learning_rate": 9.578215317919075e-06, "loss": 1.2829, "step": 7547 }, { "epoch": 1.36, "learning_rate": 9.575505780346821e-06, "loss": 0.4828, "step": 7548 }, { "epoch": 1.36, "learning_rate": 9.572796242774566e-06, "loss": 0.3184, "step": 7549 }, { "epoch": 1.36, "learning_rate": 9.570086705202312e-06, "loss": 0.3027, "step": 7550 }, { "epoch": 1.36, "learning_rate": 9.56737716763006e-06, "loss": 0.5419, "step": 7551 }, { "epoch": 1.36, "learning_rate": 9.564667630057804e-06, "loss": 0.41, "step": 7552 }, { "epoch": 1.36, "learning_rate": 9.56195809248555e-06, "loss": 0.5312, "step": 7553 }, { "epoch": 1.36, "learning_rate": 9.559248554913294e-06, "loss": 0.1978, "step": 7554 }, { "epoch": 1.36, "learning_rate": 9.55653901734104e-06, "loss": 0.8312, "step": 7555 }, { "epoch": 1.36, "learning_rate": 9.553829479768786e-06, "loss": 0.6604, "step": 7556 }, { "epoch": 1.37, "learning_rate": 9.551119942196532e-06, "loss": 0.6597, "step": 7557 }, { "epoch": 1.37, "learning_rate": 9.548410404624277e-06, "loss": 1.3875, "step": 7558 }, { "epoch": 1.37, "learning_rate": 9.545700867052023e-06, "loss": 0.4611, "step": 7559 }, { "epoch": 1.37, "learning_rate": 9.542991329479769e-06, "loss": 0.564, "step": 7560 }, { "epoch": 1.37, "learning_rate": 9.540281791907515e-06, "loss": 0.9556, "step": 7561 }, { "epoch": 1.37, "learning_rate": 9.537572254335261e-06, "loss": 0.5815, "step": 7562 }, { "epoch": 1.37, "learning_rate": 9.534862716763005e-06, "loss": 0.5084, "step": 7563 }, { "epoch": 1.37, "learning_rate": 9.532153179190751e-06, "loss": 0.569, "step": 7564 }, { "epoch": 1.37, "learning_rate": 9.529443641618496e-06, "loss": 0.5421, "step": 7565 }, { "epoch": 1.37, "learning_rate": 9.526734104046244e-06, "loss": 0.9123, "step": 7566 }, { "epoch": 1.37, "learning_rate": 9.52402456647399e-06, "loss": 0.7862, "step": 7567 }, { "epoch": 1.37, "learning_rate": 9.521315028901734e-06, "loss": 0.7966, "step": 7568 }, { "epoch": 1.37, "learning_rate": 9.51860549132948e-06, "loss": 0.1969, "step": 7569 }, { "epoch": 1.37, "learning_rate": 9.515895953757224e-06, "loss": 0.4892, "step": 7570 }, { "epoch": 1.37, "learning_rate": 9.513186416184972e-06, "loss": 1.2264, "step": 7571 }, { "epoch": 1.37, "learning_rate": 9.510476878612717e-06, "loss": 0.4991, "step": 7572 }, { "epoch": 1.37, "learning_rate": 9.507767341040463e-06, "loss": 0.5748, "step": 7573 }, { "epoch": 1.37, "learning_rate": 9.505057803468209e-06, "loss": 0.8738, "step": 7574 }, { "epoch": 1.37, "learning_rate": 9.502348265895953e-06, "loss": 0.8316, "step": 7575 }, { "epoch": 1.37, "learning_rate": 9.4996387283237e-06, "loss": 0.9021, "step": 7576 }, { "epoch": 1.37, "learning_rate": 9.496929190751445e-06, "loss": 1.2033, "step": 7577 }, { "epoch": 1.37, "learning_rate": 9.494219653179191e-06, "loss": 0.6772, "step": 7578 }, { "epoch": 1.37, "learning_rate": 9.491510115606936e-06, "loss": 0.4813, "step": 7579 }, { "epoch": 1.37, "learning_rate": 9.488800578034683e-06, "loss": 0.9446, "step": 7580 }, { "epoch": 1.37, "learning_rate": 9.486091040462428e-06, "loss": 0.1767, "step": 7581 }, { "epoch": 1.37, "learning_rate": 9.483381502890174e-06, "loss": 0.583, "step": 7582 }, { "epoch": 1.37, "learning_rate": 9.48067196531792e-06, "loss": 0.5729, "step": 7583 }, { "epoch": 1.37, "learning_rate": 9.477962427745664e-06, "loss": 0.9109, "step": 7584 }, { "epoch": 1.37, "learning_rate": 9.475252890173412e-06, "loss": 0.5168, "step": 7585 }, { "epoch": 1.37, "learning_rate": 9.472543352601156e-06, "loss": 0.3949, "step": 7586 }, { "epoch": 1.37, "learning_rate": 9.469833815028902e-06, "loss": 0.5877, "step": 7587 }, { "epoch": 1.37, "learning_rate": 9.467124277456647e-06, "loss": 0.7869, "step": 7588 }, { "epoch": 1.37, "learning_rate": 9.464414739884393e-06, "loss": 0.2563, "step": 7589 }, { "epoch": 1.37, "learning_rate": 9.46170520231214e-06, "loss": 0.4655, "step": 7590 }, { "epoch": 1.37, "learning_rate": 9.458995664739885e-06, "loss": 1.0336, "step": 7591 }, { "epoch": 1.37, "learning_rate": 9.456286127167631e-06, "loss": 0.2176, "step": 7592 }, { "epoch": 1.37, "learning_rate": 9.453576589595375e-06, "loss": 0.9469, "step": 7593 }, { "epoch": 1.37, "learning_rate": 9.450867052023121e-06, "loss": 0.4065, "step": 7594 }, { "epoch": 1.37, "learning_rate": 9.448157514450867e-06, "loss": 0.5648, "step": 7595 }, { "epoch": 1.37, "learning_rate": 9.445447976878614e-06, "loss": 0.633, "step": 7596 }, { "epoch": 1.37, "learning_rate": 9.44273843930636e-06, "loss": 0.5894, "step": 7597 }, { "epoch": 1.37, "learning_rate": 9.440028901734104e-06, "loss": 0.4154, "step": 7598 }, { "epoch": 1.37, "learning_rate": 9.43731936416185e-06, "loss": 1.4736, "step": 7599 }, { "epoch": 1.37, "learning_rate": 9.434609826589596e-06, "loss": 0.3731, "step": 7600 }, { "epoch": 1.37, "learning_rate": 9.431900289017342e-06, "loss": 0.5163, "step": 7601 }, { "epoch": 1.37, "learning_rate": 9.429190751445086e-06, "loss": 1.0966, "step": 7602 }, { "epoch": 1.37, "learning_rate": 9.426481213872833e-06, "loss": 0.9263, "step": 7603 }, { "epoch": 1.37, "learning_rate": 9.423771676300577e-06, "loss": 0.5723, "step": 7604 }, { "epoch": 1.37, "learning_rate": 9.421062138728325e-06, "loss": 0.7422, "step": 7605 }, { "epoch": 1.37, "learning_rate": 9.41835260115607e-06, "loss": 0.6527, "step": 7606 }, { "epoch": 1.37, "learning_rate": 9.415643063583815e-06, "loss": 0.5489, "step": 7607 }, { "epoch": 1.37, "learning_rate": 9.412933526011561e-06, "loss": 1.0158, "step": 7608 }, { "epoch": 1.37, "learning_rate": 9.410223988439305e-06, "loss": 0.3498, "step": 7609 }, { "epoch": 1.37, "learning_rate": 9.407514450867053e-06, "loss": 0.762, "step": 7610 }, { "epoch": 1.37, "learning_rate": 9.404804913294798e-06, "loss": 0.348, "step": 7611 }, { "epoch": 1.38, "learning_rate": 9.402095375722544e-06, "loss": 0.475, "step": 7612 }, { "epoch": 1.38, "learning_rate": 9.39938583815029e-06, "loss": 0.4283, "step": 7613 }, { "epoch": 1.38, "learning_rate": 9.396676300578034e-06, "loss": 0.8008, "step": 7614 }, { "epoch": 1.38, "learning_rate": 9.393966763005782e-06, "loss": 0.2272, "step": 7615 }, { "epoch": 1.38, "learning_rate": 9.391257225433526e-06, "loss": 0.7487, "step": 7616 }, { "epoch": 1.38, "learning_rate": 9.388547687861272e-06, "loss": 1.4016, "step": 7617 }, { "epoch": 1.38, "learning_rate": 9.385838150289017e-06, "loss": 1.0347, "step": 7618 }, { "epoch": 1.38, "learning_rate": 9.383128612716763e-06, "loss": 0.3523, "step": 7619 }, { "epoch": 1.38, "learning_rate": 9.380419075144509e-06, "loss": 0.5463, "step": 7620 }, { "epoch": 1.38, "learning_rate": 9.377709537572255e-06, "loss": 0.6074, "step": 7621 }, { "epoch": 1.38, "learning_rate": 9.375000000000001e-06, "loss": 0.8037, "step": 7622 }, { "epoch": 1.38, "learning_rate": 9.372290462427745e-06, "loss": 0.3836, "step": 7623 }, { "epoch": 1.38, "learning_rate": 9.369580924855491e-06, "loss": 0.3929, "step": 7624 }, { "epoch": 1.38, "learning_rate": 9.366871387283237e-06, "loss": 0.5124, "step": 7625 }, { "epoch": 1.38, "learning_rate": 9.364161849710983e-06, "loss": 0.5349, "step": 7626 }, { "epoch": 1.38, "learning_rate": 9.361452312138728e-06, "loss": 0.9226, "step": 7627 }, { "epoch": 1.38, "learning_rate": 9.358742774566474e-06, "loss": 0.7704, "step": 7628 }, { "epoch": 1.38, "learning_rate": 9.35603323699422e-06, "loss": 0.6585, "step": 7629 }, { "epoch": 1.38, "learning_rate": 9.353323699421966e-06, "loss": 0.3801, "step": 7630 }, { "epoch": 1.38, "learning_rate": 9.350614161849712e-06, "loss": 0.3498, "step": 7631 }, { "epoch": 1.38, "learning_rate": 9.347904624277456e-06, "loss": 0.8465, "step": 7632 }, { "epoch": 1.38, "learning_rate": 9.345195086705202e-06, "loss": 0.5654, "step": 7633 }, { "epoch": 1.38, "learning_rate": 9.342485549132947e-06, "loss": 0.6757, "step": 7634 }, { "epoch": 1.38, "learning_rate": 9.339776011560695e-06, "loss": 0.6025, "step": 7635 }, { "epoch": 1.38, "learning_rate": 9.33706647398844e-06, "loss": 0.8342, "step": 7636 }, { "epoch": 1.38, "learning_rate": 9.334356936416185e-06, "loss": 0.6573, "step": 7637 }, { "epoch": 1.38, "learning_rate": 9.331647398843931e-06, "loss": 0.4427, "step": 7638 }, { "epoch": 1.38, "learning_rate": 9.328937861271675e-06, "loss": 0.4264, "step": 7639 }, { "epoch": 1.38, "learning_rate": 9.326228323699423e-06, "loss": 0.3725, "step": 7640 }, { "epoch": 1.38, "learning_rate": 9.323518786127168e-06, "loss": 0.3689, "step": 7641 }, { "epoch": 1.38, "learning_rate": 9.320809248554914e-06, "loss": 0.892, "step": 7642 }, { "epoch": 1.38, "learning_rate": 9.318099710982658e-06, "loss": 0.6002, "step": 7643 }, { "epoch": 1.38, "learning_rate": 9.315390173410404e-06, "loss": 0.4063, "step": 7644 }, { "epoch": 1.38, "learning_rate": 9.312680635838152e-06, "loss": 0.9503, "step": 7645 }, { "epoch": 1.38, "learning_rate": 9.309971098265896e-06, "loss": 0.3596, "step": 7646 }, { "epoch": 1.38, "learning_rate": 9.307261560693642e-06, "loss": 0.805, "step": 7647 }, { "epoch": 1.38, "learning_rate": 9.304552023121387e-06, "loss": 0.3784, "step": 7648 }, { "epoch": 1.38, "learning_rate": 9.301842485549133e-06, "loss": 0.573, "step": 7649 }, { "epoch": 1.38, "learning_rate": 9.299132947976879e-06, "loss": 0.5606, "step": 7650 }, { "epoch": 1.38, "learning_rate": 9.296423410404625e-06, "loss": 0.9858, "step": 7651 }, { "epoch": 1.38, "learning_rate": 9.29371387283237e-06, "loss": 1.5971, "step": 7652 }, { "epoch": 1.38, "learning_rate": 9.291004335260115e-06, "loss": 0.3858, "step": 7653 }, { "epoch": 1.38, "learning_rate": 9.288294797687861e-06, "loss": 0.5664, "step": 7654 }, { "epoch": 1.38, "learning_rate": 9.285585260115607e-06, "loss": 0.6594, "step": 7655 }, { "epoch": 1.38, "learning_rate": 9.282875722543353e-06, "loss": 0.4487, "step": 7656 }, { "epoch": 1.38, "learning_rate": 9.280166184971098e-06, "loss": 0.363, "step": 7657 }, { "epoch": 1.38, "learning_rate": 9.277456647398844e-06, "loss": 0.4814, "step": 7658 }, { "epoch": 1.38, "learning_rate": 9.27474710982659e-06, "loss": 0.4229, "step": 7659 }, { "epoch": 1.38, "learning_rate": 9.272037572254336e-06, "loss": 0.6303, "step": 7660 }, { "epoch": 1.38, "learning_rate": 9.269328034682082e-06, "loss": 0.6838, "step": 7661 }, { "epoch": 1.38, "learning_rate": 9.266618497109826e-06, "loss": 0.7373, "step": 7662 }, { "epoch": 1.38, "learning_rate": 9.263908959537572e-06, "loss": 0.9715, "step": 7663 }, { "epoch": 1.38, "learning_rate": 9.261199421965317e-06, "loss": 0.2905, "step": 7664 }, { "epoch": 1.38, "learning_rate": 9.258489884393064e-06, "loss": 1.6251, "step": 7665 }, { "epoch": 1.38, "learning_rate": 9.255780346820809e-06, "loss": 0.3114, "step": 7666 }, { "epoch": 1.38, "learning_rate": 9.253070809248555e-06, "loss": 0.3206, "step": 7667 }, { "epoch": 1.39, "learning_rate": 9.250361271676301e-06, "loss": 0.5922, "step": 7668 }, { "epoch": 1.39, "learning_rate": 9.247651734104047e-06, "loss": 0.388, "step": 7669 }, { "epoch": 1.39, "learning_rate": 9.244942196531793e-06, "loss": 0.4043, "step": 7670 }, { "epoch": 1.39, "learning_rate": 9.242232658959537e-06, "loss": 0.683, "step": 7671 }, { "epoch": 1.39, "learning_rate": 9.239523121387283e-06, "loss": 0.8306, "step": 7672 }, { "epoch": 1.39, "learning_rate": 9.236813583815028e-06, "loss": 0.5347, "step": 7673 }, { "epoch": 1.39, "learning_rate": 9.234104046242776e-06, "loss": 0.8999, "step": 7674 }, { "epoch": 1.39, "learning_rate": 9.231394508670522e-06, "loss": 0.5627, "step": 7675 }, { "epoch": 1.39, "learning_rate": 9.228684971098266e-06, "loss": 1.3705, "step": 7676 }, { "epoch": 1.39, "learning_rate": 9.225975433526012e-06, "loss": 0.6655, "step": 7677 }, { "epoch": 1.39, "learning_rate": 9.223265895953756e-06, "loss": 0.6957, "step": 7678 }, { "epoch": 1.39, "learning_rate": 9.220556358381504e-06, "loss": 0.2487, "step": 7679 }, { "epoch": 1.39, "learning_rate": 9.217846820809249e-06, "loss": 0.8858, "step": 7680 }, { "epoch": 1.39, "learning_rate": 9.215137283236995e-06, "loss": 0.8133, "step": 7681 }, { "epoch": 1.39, "learning_rate": 9.21242774566474e-06, "loss": 0.5805, "step": 7682 }, { "epoch": 1.39, "learning_rate": 9.209718208092485e-06, "loss": 0.351, "step": 7683 }, { "epoch": 1.39, "learning_rate": 9.207008670520233e-06, "loss": 0.2575, "step": 7684 }, { "epoch": 1.39, "learning_rate": 9.204299132947977e-06, "loss": 1.17, "step": 7685 }, { "epoch": 1.39, "learning_rate": 9.201589595375723e-06, "loss": 0.519, "step": 7686 }, { "epoch": 1.39, "learning_rate": 9.198880057803468e-06, "loss": 0.5814, "step": 7687 }, { "epoch": 1.39, "learning_rate": 9.196170520231214e-06, "loss": 0.4694, "step": 7688 }, { "epoch": 1.39, "learning_rate": 9.19346098265896e-06, "loss": 0.7262, "step": 7689 }, { "epoch": 1.39, "learning_rate": 9.190751445086706e-06, "loss": 0.4623, "step": 7690 }, { "epoch": 1.39, "learning_rate": 9.188041907514452e-06, "loss": 0.6999, "step": 7691 }, { "epoch": 1.39, "learning_rate": 9.185332369942196e-06, "loss": 0.2399, "step": 7692 }, { "epoch": 1.39, "learning_rate": 9.182622832369942e-06, "loss": 0.7217, "step": 7693 }, { "epoch": 1.39, "learning_rate": 9.179913294797688e-06, "loss": 0.3354, "step": 7694 }, { "epoch": 1.39, "learning_rate": 9.177203757225434e-06, "loss": 0.6773, "step": 7695 }, { "epoch": 1.39, "learning_rate": 9.174494219653179e-06, "loss": 0.3773, "step": 7696 }, { "epoch": 1.39, "learning_rate": 9.171784682080925e-06, "loss": 0.9352, "step": 7697 }, { "epoch": 1.39, "learning_rate": 9.169075144508671e-06, "loss": 0.3181, "step": 7698 }, { "epoch": 1.39, "learning_rate": 9.166365606936417e-06, "loss": 0.8147, "step": 7699 }, { "epoch": 1.39, "learning_rate": 9.163656069364163e-06, "loss": 0.5619, "step": 7700 }, { "epoch": 1.39, "learning_rate": 9.160946531791907e-06, "loss": 0.3481, "step": 7701 }, { "epoch": 1.39, "learning_rate": 9.158236994219653e-06, "loss": 0.5701, "step": 7702 }, { "epoch": 1.39, "learning_rate": 9.155527456647398e-06, "loss": 0.3507, "step": 7703 }, { "epoch": 1.39, "learning_rate": 9.152817919075146e-06, "loss": 1.2041, "step": 7704 }, { "epoch": 1.39, "learning_rate": 9.150108381502892e-06, "loss": 0.5645, "step": 7705 }, { "epoch": 1.39, "learning_rate": 9.147398843930636e-06, "loss": 0.8253, "step": 7706 }, { "epoch": 1.39, "learning_rate": 9.144689306358382e-06, "loss": 0.8618, "step": 7707 }, { "epoch": 1.39, "learning_rate": 9.141979768786126e-06, "loss": 0.5577, "step": 7708 }, { "epoch": 1.39, "learning_rate": 9.139270231213874e-06, "loss": 0.4456, "step": 7709 }, { "epoch": 1.39, "learning_rate": 9.136560693641618e-06, "loss": 0.5685, "step": 7710 }, { "epoch": 1.39, "learning_rate": 9.133851156069365e-06, "loss": 0.8845, "step": 7711 }, { "epoch": 1.39, "learning_rate": 9.131141618497109e-06, "loss": 0.4667, "step": 7712 }, { "epoch": 1.39, "learning_rate": 9.128432080924855e-06, "loss": 0.3859, "step": 7713 }, { "epoch": 1.39, "learning_rate": 9.125722543352603e-06, "loss": 0.619, "step": 7714 }, { "epoch": 1.39, "learning_rate": 9.123013005780347e-06, "loss": 0.6109, "step": 7715 }, { "epoch": 1.39, "learning_rate": 9.120303468208093e-06, "loss": 0.4598, "step": 7716 }, { "epoch": 1.39, "learning_rate": 9.117593930635838e-06, "loss": 0.506, "step": 7717 }, { "epoch": 1.39, "learning_rate": 9.114884393063584e-06, "loss": 0.2388, "step": 7718 }, { "epoch": 1.39, "learning_rate": 9.11217485549133e-06, "loss": 0.4511, "step": 7719 }, { "epoch": 1.39, "learning_rate": 9.109465317919076e-06, "loss": 0.5266, "step": 7720 }, { "epoch": 1.39, "learning_rate": 9.106755780346822e-06, "loss": 0.5586, "step": 7721 }, { "epoch": 1.39, "learning_rate": 9.104046242774566e-06, "loss": 0.5486, "step": 7722 }, { "epoch": 1.4, "learning_rate": 9.101336705202312e-06, "loss": 0.5013, "step": 7723 }, { "epoch": 1.4, "learning_rate": 9.098627167630058e-06, "loss": 0.7655, "step": 7724 }, { "epoch": 1.4, "learning_rate": 9.095917630057804e-06, "loss": 0.5327, "step": 7725 }, { "epoch": 1.4, "learning_rate": 9.093208092485549e-06, "loss": 0.6248, "step": 7726 }, { "epoch": 1.4, "learning_rate": 9.090498554913295e-06, "loss": 0.3104, "step": 7727 }, { "epoch": 1.4, "learning_rate": 9.08778901734104e-06, "loss": 0.4241, "step": 7728 }, { "epoch": 1.4, "learning_rate": 9.085079479768787e-06, "loss": 0.8858, "step": 7729 }, { "epoch": 1.4, "learning_rate": 9.082369942196533e-06, "loss": 0.298, "step": 7730 }, { "epoch": 1.4, "learning_rate": 9.079660404624277e-06, "loss": 1.1225, "step": 7731 }, { "epoch": 1.4, "learning_rate": 9.076950867052023e-06, "loss": 0.5906, "step": 7732 }, { "epoch": 1.4, "learning_rate": 9.074241329479768e-06, "loss": 0.8658, "step": 7733 }, { "epoch": 1.4, "learning_rate": 9.071531791907515e-06, "loss": 0.5526, "step": 7734 }, { "epoch": 1.4, "learning_rate": 9.06882225433526e-06, "loss": 0.6507, "step": 7735 }, { "epoch": 1.4, "learning_rate": 9.066112716763006e-06, "loss": 0.8283, "step": 7736 }, { "epoch": 1.4, "learning_rate": 9.063403179190752e-06, "loss": 0.8432, "step": 7737 }, { "epoch": 1.4, "learning_rate": 9.060693641618496e-06, "loss": 0.4893, "step": 7738 }, { "epoch": 1.4, "learning_rate": 9.057984104046244e-06, "loss": 0.209, "step": 7739 }, { "epoch": 1.4, "learning_rate": 9.055274566473988e-06, "loss": 0.2541, "step": 7740 }, { "epoch": 1.4, "learning_rate": 9.052565028901734e-06, "loss": 0.7888, "step": 7741 }, { "epoch": 1.4, "learning_rate": 9.049855491329479e-06, "loss": 0.5529, "step": 7742 }, { "epoch": 1.4, "learning_rate": 9.047145953757225e-06, "loss": 0.7771, "step": 7743 }, { "epoch": 1.4, "learning_rate": 9.044436416184973e-06, "loss": 0.821, "step": 7744 }, { "epoch": 1.4, "learning_rate": 9.041726878612717e-06, "loss": 0.4926, "step": 7745 }, { "epoch": 1.4, "learning_rate": 9.039017341040463e-06, "loss": 0.2997, "step": 7746 }, { "epoch": 1.4, "learning_rate": 9.036307803468207e-06, "loss": 0.8484, "step": 7747 }, { "epoch": 1.4, "learning_rate": 9.033598265895953e-06, "loss": 0.5352, "step": 7748 }, { "epoch": 1.4, "learning_rate": 9.0308887283237e-06, "loss": 0.6861, "step": 7749 }, { "epoch": 1.4, "learning_rate": 9.028179190751446e-06, "loss": 0.4841, "step": 7750 }, { "epoch": 1.4, "learning_rate": 9.02546965317919e-06, "loss": 0.9719, "step": 7751 }, { "epoch": 1.4, "learning_rate": 9.022760115606936e-06, "loss": 0.5961, "step": 7752 }, { "epoch": 1.4, "learning_rate": 9.020050578034684e-06, "loss": 0.419, "step": 7753 }, { "epoch": 1.4, "learning_rate": 9.017341040462428e-06, "loss": 0.546, "step": 7754 }, { "epoch": 1.4, "learning_rate": 9.014631502890174e-06, "loss": 0.4425, "step": 7755 }, { "epoch": 1.4, "learning_rate": 9.011921965317919e-06, "loss": 0.2528, "step": 7756 }, { "epoch": 1.4, "learning_rate": 9.009212427745665e-06, "loss": 0.2579, "step": 7757 }, { "epoch": 1.4, "learning_rate": 9.00650289017341e-06, "loss": 0.3494, "step": 7758 }, { "epoch": 1.4, "learning_rate": 9.003793352601157e-06, "loss": 0.6959, "step": 7759 }, { "epoch": 1.4, "learning_rate": 9.001083815028903e-06, "loss": 0.515, "step": 7760 }, { "epoch": 1.4, "learning_rate": 8.998374277456647e-06, "loss": 0.4461, "step": 7761 }, { "epoch": 1.4, "learning_rate": 8.995664739884393e-06, "loss": 0.2368, "step": 7762 }, { "epoch": 1.4, "learning_rate": 8.99295520231214e-06, "loss": 0.8365, "step": 7763 }, { "epoch": 1.4, "learning_rate": 8.990245664739885e-06, "loss": 0.3465, "step": 7764 }, { "epoch": 1.4, "learning_rate": 8.98753612716763e-06, "loss": 0.518, "step": 7765 }, { "epoch": 1.4, "learning_rate": 8.984826589595376e-06, "loss": 0.5375, "step": 7766 }, { "epoch": 1.4, "learning_rate": 8.982117052023122e-06, "loss": 0.9528, "step": 7767 }, { "epoch": 1.4, "learning_rate": 8.979407514450868e-06, "loss": 0.6836, "step": 7768 }, { "epoch": 1.4, "learning_rate": 8.976697976878614e-06, "loss": 0.4856, "step": 7769 }, { "epoch": 1.4, "learning_rate": 8.973988439306358e-06, "loss": 0.9094, "step": 7770 }, { "epoch": 1.4, "learning_rate": 8.971278901734104e-06, "loss": 0.4239, "step": 7771 }, { "epoch": 1.4, "learning_rate": 8.968569364161849e-06, "loss": 0.5591, "step": 7772 }, { "epoch": 1.4, "learning_rate": 8.965859826589597e-06, "loss": 0.5576, "step": 7773 }, { "epoch": 1.4, "learning_rate": 8.963150289017341e-06, "loss": 0.3835, "step": 7774 }, { "epoch": 1.4, "learning_rate": 8.960440751445087e-06, "loss": 0.61, "step": 7775 }, { "epoch": 1.4, "learning_rate": 8.957731213872833e-06, "loss": 0.5817, "step": 7776 }, { "epoch": 1.4, "learning_rate": 8.955021676300577e-06, "loss": 0.6469, "step": 7777 }, { "epoch": 1.4, "learning_rate": 8.952312138728325e-06, "loss": 0.507, "step": 7778 }, { "epoch": 1.41, "learning_rate": 8.94960260115607e-06, "loss": 0.2981, "step": 7779 }, { "epoch": 1.41, "learning_rate": 8.946893063583816e-06, "loss": 0.5418, "step": 7780 }, { "epoch": 1.41, "learning_rate": 8.94418352601156e-06, "loss": 0.1844, "step": 7781 }, { "epoch": 1.41, "learning_rate": 8.941473988439306e-06, "loss": 0.5183, "step": 7782 }, { "epoch": 1.41, "learning_rate": 8.938764450867054e-06, "loss": 0.9123, "step": 7783 }, { "epoch": 1.41, "learning_rate": 8.936054913294798e-06, "loss": 0.5484, "step": 7784 }, { "epoch": 1.41, "learning_rate": 8.933345375722544e-06, "loss": 0.3316, "step": 7785 }, { "epoch": 1.41, "learning_rate": 8.930635838150288e-06, "loss": 0.9663, "step": 7786 }, { "epoch": 1.41, "learning_rate": 8.927926300578035e-06, "loss": 0.4956, "step": 7787 }, { "epoch": 1.41, "learning_rate": 8.92521676300578e-06, "loss": 0.5561, "step": 7788 }, { "epoch": 1.41, "learning_rate": 8.922507225433527e-06, "loss": 0.46, "step": 7789 }, { "epoch": 1.41, "learning_rate": 8.919797687861273e-06, "loss": 0.2646, "step": 7790 }, { "epoch": 1.41, "learning_rate": 8.917088150289017e-06, "loss": 0.507, "step": 7791 }, { "epoch": 1.41, "learning_rate": 8.914378612716763e-06, "loss": 0.6985, "step": 7792 }, { "epoch": 1.41, "learning_rate": 8.91166907514451e-06, "loss": 0.5156, "step": 7793 }, { "epoch": 1.41, "learning_rate": 8.908959537572255e-06, "loss": 0.4958, "step": 7794 }, { "epoch": 1.41, "learning_rate": 8.90625e-06, "loss": 0.5703, "step": 7795 }, { "epoch": 1.41, "learning_rate": 8.903540462427746e-06, "loss": 0.5006, "step": 7796 }, { "epoch": 1.41, "learning_rate": 8.90083092485549e-06, "loss": 0.4029, "step": 7797 }, { "epoch": 1.41, "learning_rate": 8.898121387283238e-06, "loss": 0.8736, "step": 7798 }, { "epoch": 1.41, "learning_rate": 8.895411849710984e-06, "loss": 0.389, "step": 7799 }, { "epoch": 1.41, "learning_rate": 8.892702312138728e-06, "loss": 0.7934, "step": 7800 }, { "epoch": 1.41, "learning_rate": 8.889992774566474e-06, "loss": 0.9023, "step": 7801 }, { "epoch": 1.41, "learning_rate": 8.887283236994219e-06, "loss": 0.3685, "step": 7802 }, { "epoch": 1.41, "learning_rate": 8.884573699421966e-06, "loss": 1.3866, "step": 7803 }, { "epoch": 1.41, "learning_rate": 8.88186416184971e-06, "loss": 0.7624, "step": 7804 }, { "epoch": 1.41, "learning_rate": 8.879154624277457e-06, "loss": 0.3562, "step": 7805 }, { "epoch": 1.41, "learning_rate": 8.876445086705203e-06, "loss": 0.395, "step": 7806 }, { "epoch": 1.41, "learning_rate": 8.873735549132947e-06, "loss": 0.608, "step": 7807 }, { "epoch": 1.41, "learning_rate": 8.871026011560695e-06, "loss": 0.8682, "step": 7808 }, { "epoch": 1.41, "learning_rate": 8.86831647398844e-06, "loss": 0.3997, "step": 7809 }, { "epoch": 1.41, "learning_rate": 8.865606936416185e-06, "loss": 0.2746, "step": 7810 }, { "epoch": 1.41, "learning_rate": 8.86289739884393e-06, "loss": 0.2351, "step": 7811 }, { "epoch": 1.41, "learning_rate": 8.860187861271676e-06, "loss": 0.4712, "step": 7812 }, { "epoch": 1.41, "learning_rate": 8.857478323699424e-06, "loss": 0.5861, "step": 7813 }, { "epoch": 1.41, "learning_rate": 8.854768786127168e-06, "loss": 0.6546, "step": 7814 }, { "epoch": 1.41, "learning_rate": 8.852059248554914e-06, "loss": 0.6721, "step": 7815 }, { "epoch": 1.41, "learning_rate": 8.849349710982658e-06, "loss": 0.4196, "step": 7816 }, { "epoch": 1.41, "learning_rate": 8.846640173410404e-06, "loss": 0.5061, "step": 7817 }, { "epoch": 1.41, "learning_rate": 8.84393063583815e-06, "loss": 0.7959, "step": 7818 }, { "epoch": 1.41, "learning_rate": 8.841221098265897e-06, "loss": 0.4981, "step": 7819 }, { "epoch": 1.41, "learning_rate": 8.838511560693641e-06, "loss": 0.5606, "step": 7820 }, { "epoch": 1.41, "learning_rate": 8.835802023121387e-06, "loss": 0.5856, "step": 7821 }, { "epoch": 1.41, "learning_rate": 8.833092485549133e-06, "loss": 0.5268, "step": 7822 }, { "epoch": 1.41, "learning_rate": 8.830382947976879e-06, "loss": 0.3239, "step": 7823 }, { "epoch": 1.41, "learning_rate": 8.827673410404625e-06, "loss": 0.6984, "step": 7824 }, { "epoch": 1.41, "learning_rate": 8.82496387283237e-06, "loss": 0.8739, "step": 7825 }, { "epoch": 1.41, "learning_rate": 8.822254335260116e-06, "loss": 0.6437, "step": 7826 }, { "epoch": 1.41, "learning_rate": 8.81954479768786e-06, "loss": 0.4455, "step": 7827 }, { "epoch": 1.41, "learning_rate": 8.816835260115608e-06, "loss": 0.7791, "step": 7828 }, { "epoch": 1.41, "learning_rate": 8.814125722543354e-06, "loss": 0.3928, "step": 7829 }, { "epoch": 1.41, "learning_rate": 8.811416184971098e-06, "loss": 0.9452, "step": 7830 }, { "epoch": 1.41, "learning_rate": 8.808706647398844e-06, "loss": 0.5994, "step": 7831 }, { "epoch": 1.41, "learning_rate": 8.805997109826589e-06, "loss": 0.4101, "step": 7832 }, { "epoch": 1.41, "learning_rate": 8.803287572254336e-06, "loss": 0.9261, "step": 7833 }, { "epoch": 1.42, "learning_rate": 8.80057803468208e-06, "loss": 0.8221, "step": 7834 }, { "epoch": 1.42, "learning_rate": 8.797868497109827e-06, "loss": 0.1687, "step": 7835 }, { "epoch": 1.42, "learning_rate": 8.795158959537573e-06, "loss": 0.3747, "step": 7836 }, { "epoch": 1.42, "learning_rate": 8.792449421965317e-06, "loss": 0.4419, "step": 7837 }, { "epoch": 1.42, "learning_rate": 8.789739884393065e-06, "loss": 0.4933, "step": 7838 }, { "epoch": 1.42, "learning_rate": 8.78703034682081e-06, "loss": 0.5825, "step": 7839 }, { "epoch": 1.42, "learning_rate": 8.784320809248555e-06, "loss": 0.6185, "step": 7840 }, { "epoch": 1.42, "learning_rate": 8.7816112716763e-06, "loss": 0.3943, "step": 7841 }, { "epoch": 1.42, "learning_rate": 8.778901734104047e-06, "loss": 0.5624, "step": 7842 }, { "epoch": 1.42, "learning_rate": 8.776192196531792e-06, "loss": 0.5396, "step": 7843 }, { "epoch": 1.42, "learning_rate": 8.773482658959538e-06, "loss": 0.6763, "step": 7844 }, { "epoch": 1.42, "learning_rate": 8.770773121387284e-06, "loss": 0.4874, "step": 7845 }, { "epoch": 1.42, "learning_rate": 8.768063583815028e-06, "loss": 0.2902, "step": 7846 }, { "epoch": 1.42, "learning_rate": 8.765354046242776e-06, "loss": 0.7643, "step": 7847 }, { "epoch": 1.42, "learning_rate": 8.76264450867052e-06, "loss": 0.4378, "step": 7848 }, { "epoch": 1.42, "learning_rate": 8.759934971098267e-06, "loss": 0.2679, "step": 7849 }, { "epoch": 1.42, "learning_rate": 8.757225433526011e-06, "loss": 0.524, "step": 7850 }, { "epoch": 1.42, "learning_rate": 8.754515895953757e-06, "loss": 0.8947, "step": 7851 }, { "epoch": 1.42, "learning_rate": 8.751806358381505e-06, "loss": 0.4771, "step": 7852 }, { "epoch": 1.42, "learning_rate": 8.749096820809249e-06, "loss": 0.6535, "step": 7853 }, { "epoch": 1.42, "learning_rate": 8.746387283236995e-06, "loss": 0.7322, "step": 7854 }, { "epoch": 1.42, "learning_rate": 8.74367774566474e-06, "loss": 0.4327, "step": 7855 }, { "epoch": 1.42, "learning_rate": 8.740968208092486e-06, "loss": 0.8055, "step": 7856 }, { "epoch": 1.42, "learning_rate": 8.738258670520232e-06, "loss": 0.7542, "step": 7857 }, { "epoch": 1.42, "learning_rate": 8.735549132947978e-06, "loss": 2.4352, "step": 7858 }, { "epoch": 1.42, "learning_rate": 8.732839595375722e-06, "loss": 0.4144, "step": 7859 }, { "epoch": 1.42, "learning_rate": 8.730130057803468e-06, "loss": 0.5638, "step": 7860 }, { "epoch": 1.42, "learning_rate": 8.727420520231214e-06, "loss": 0.5712, "step": 7861 }, { "epoch": 1.42, "learning_rate": 8.72471098265896e-06, "loss": 0.4228, "step": 7862 }, { "epoch": 1.42, "learning_rate": 8.722001445086706e-06, "loss": 0.5349, "step": 7863 }, { "epoch": 1.42, "learning_rate": 8.71929190751445e-06, "loss": 0.664, "step": 7864 }, { "epoch": 1.42, "learning_rate": 8.716582369942197e-06, "loss": 0.4654, "step": 7865 }, { "epoch": 1.42, "learning_rate": 8.713872832369941e-06, "loss": 0.3365, "step": 7866 }, { "epoch": 1.42, "learning_rate": 8.711163294797689e-06, "loss": 0.6947, "step": 7867 }, { "epoch": 1.42, "learning_rate": 8.708453757225435e-06, "loss": 1.0965, "step": 7868 }, { "epoch": 1.42, "learning_rate": 8.70574421965318e-06, "loss": 0.753, "step": 7869 }, { "epoch": 1.42, "learning_rate": 8.703034682080925e-06, "loss": 0.3322, "step": 7870 }, { "epoch": 1.42, "learning_rate": 8.70032514450867e-06, "loss": 0.9318, "step": 7871 }, { "epoch": 1.42, "learning_rate": 8.697615606936417e-06, "loss": 1.0673, "step": 7872 }, { "epoch": 1.42, "learning_rate": 8.694906069364162e-06, "loss": 0.4309, "step": 7873 }, { "epoch": 1.42, "learning_rate": 8.692196531791908e-06, "loss": 0.8269, "step": 7874 }, { "epoch": 1.42, "learning_rate": 8.689486994219654e-06, "loss": 1.0229, "step": 7875 }, { "epoch": 1.42, "learning_rate": 8.686777456647398e-06, "loss": 0.8569, "step": 7876 }, { "epoch": 1.42, "learning_rate": 8.684067919075146e-06, "loss": 1.1359, "step": 7877 }, { "epoch": 1.42, "learning_rate": 8.68135838150289e-06, "loss": 0.4533, "step": 7878 }, { "epoch": 1.42, "learning_rate": 8.678648843930636e-06, "loss": 0.3169, "step": 7879 }, { "epoch": 1.42, "learning_rate": 8.67593930635838e-06, "loss": 0.5389, "step": 7880 }, { "epoch": 1.42, "learning_rate": 8.673229768786127e-06, "loss": 0.4276, "step": 7881 }, { "epoch": 1.42, "learning_rate": 8.670520231213873e-06, "loss": 0.3728, "step": 7882 }, { "epoch": 1.42, "learning_rate": 8.667810693641619e-06, "loss": 0.6317, "step": 7883 }, { "epoch": 1.42, "learning_rate": 8.665101156069365e-06, "loss": 0.6062, "step": 7884 }, { "epoch": 1.42, "learning_rate": 8.66239161849711e-06, "loss": 0.5493, "step": 7885 }, { "epoch": 1.42, "learning_rate": 8.659682080924855e-06, "loss": 0.5331, "step": 7886 }, { "epoch": 1.42, "learning_rate": 8.656972543352602e-06, "loss": 0.3761, "step": 7887 }, { "epoch": 1.42, "learning_rate": 8.654263005780348e-06, "loss": 0.605, "step": 7888 }, { "epoch": 1.43, "learning_rate": 8.651553468208092e-06, "loss": 0.5469, "step": 7889 }, { "epoch": 1.43, "learning_rate": 8.648843930635838e-06, "loss": 1.2199, "step": 7890 }, { "epoch": 1.43, "learning_rate": 8.646134393063584e-06, "loss": 1.0067, "step": 7891 }, { "epoch": 1.43, "learning_rate": 8.64342485549133e-06, "loss": 0.4524, "step": 7892 }, { "epoch": 1.43, "learning_rate": 8.640715317919076e-06, "loss": 0.4888, "step": 7893 }, { "epoch": 1.43, "learning_rate": 8.63800578034682e-06, "loss": 0.7933, "step": 7894 }, { "epoch": 1.43, "learning_rate": 8.635296242774567e-06, "loss": 0.3761, "step": 7895 }, { "epoch": 1.43, "learning_rate": 8.632586705202311e-06, "loss": 0.6637, "step": 7896 }, { "epoch": 1.43, "learning_rate": 8.629877167630059e-06, "loss": 0.7187, "step": 7897 }, { "epoch": 1.43, "learning_rate": 8.627167630057805e-06, "loss": 0.6528, "step": 7898 }, { "epoch": 1.43, "learning_rate": 8.624458092485549e-06, "loss": 0.9251, "step": 7899 }, { "epoch": 1.43, "learning_rate": 8.621748554913295e-06, "loss": 0.428, "step": 7900 }, { "epoch": 1.43, "learning_rate": 8.61903901734104e-06, "loss": 0.8851, "step": 7901 }, { "epoch": 1.43, "learning_rate": 8.616329479768787e-06, "loss": 0.7858, "step": 7902 }, { "epoch": 1.43, "learning_rate": 8.613619942196532e-06, "loss": 0.5564, "step": 7903 }, { "epoch": 1.43, "learning_rate": 8.610910404624278e-06, "loss": 0.7623, "step": 7904 }, { "epoch": 1.43, "learning_rate": 8.608200867052022e-06, "loss": 0.7317, "step": 7905 }, { "epoch": 1.43, "learning_rate": 8.605491329479768e-06, "loss": 0.8685, "step": 7906 }, { "epoch": 1.43, "learning_rate": 8.602781791907516e-06, "loss": 0.4417, "step": 7907 }, { "epoch": 1.43, "learning_rate": 8.60007225433526e-06, "loss": 0.9611, "step": 7908 }, { "epoch": 1.43, "learning_rate": 8.597362716763006e-06, "loss": 0.4466, "step": 7909 }, { "epoch": 1.43, "learning_rate": 8.59465317919075e-06, "loss": 1.0151, "step": 7910 }, { "epoch": 1.43, "learning_rate": 8.591943641618497e-06, "loss": 0.4966, "step": 7911 }, { "epoch": 1.43, "learning_rate": 8.589234104046243e-06, "loss": 0.6078, "step": 7912 }, { "epoch": 1.43, "learning_rate": 8.586524566473989e-06, "loss": 0.3406, "step": 7913 }, { "epoch": 1.43, "learning_rate": 8.583815028901735e-06, "loss": 0.6053, "step": 7914 }, { "epoch": 1.43, "learning_rate": 8.58110549132948e-06, "loss": 0.4595, "step": 7915 }, { "epoch": 1.43, "learning_rate": 8.578395953757225e-06, "loss": 0.3993, "step": 7916 }, { "epoch": 1.43, "learning_rate": 8.575686416184971e-06, "loss": 0.4446, "step": 7917 }, { "epoch": 1.43, "learning_rate": 8.572976878612717e-06, "loss": 0.6723, "step": 7918 }, { "epoch": 1.43, "learning_rate": 8.570267341040462e-06, "loss": 0.735, "step": 7919 }, { "epoch": 1.43, "learning_rate": 8.567557803468208e-06, "loss": 0.4636, "step": 7920 }, { "epoch": 1.43, "learning_rate": 8.564848265895954e-06, "loss": 0.3944, "step": 7921 }, { "epoch": 1.43, "learning_rate": 8.5621387283237e-06, "loss": 0.4678, "step": 7922 }, { "epoch": 1.43, "learning_rate": 8.559429190751446e-06, "loss": 0.4939, "step": 7923 }, { "epoch": 1.43, "learning_rate": 8.55671965317919e-06, "loss": 0.3338, "step": 7924 }, { "epoch": 1.43, "learning_rate": 8.554010115606937e-06, "loss": 0.3309, "step": 7925 }, { "epoch": 1.43, "learning_rate": 8.551300578034683e-06, "loss": 0.4341, "step": 7926 }, { "epoch": 1.43, "learning_rate": 8.548591040462429e-06, "loss": 0.3683, "step": 7927 }, { "epoch": 1.43, "learning_rate": 8.545881502890173e-06, "loss": 0.6618, "step": 7928 }, { "epoch": 1.43, "learning_rate": 8.543171965317919e-06, "loss": 0.7722, "step": 7929 }, { "epoch": 1.43, "learning_rate": 8.540462427745665e-06, "loss": 0.6561, "step": 7930 }, { "epoch": 1.43, "learning_rate": 8.537752890173411e-06, "loss": 0.6399, "step": 7931 }, { "epoch": 1.43, "learning_rate": 8.535043352601157e-06, "loss": 0.3976, "step": 7932 }, { "epoch": 1.43, "learning_rate": 8.532333815028902e-06, "loss": 0.3567, "step": 7933 }, { "epoch": 1.43, "learning_rate": 8.529624277456648e-06, "loss": 0.5281, "step": 7934 }, { "epoch": 1.43, "learning_rate": 8.526914739884392e-06, "loss": 1.6066, "step": 7935 }, { "epoch": 1.43, "learning_rate": 8.52420520231214e-06, "loss": 0.7834, "step": 7936 }, { "epoch": 1.43, "learning_rate": 8.521495664739886e-06, "loss": 1.1442, "step": 7937 }, { "epoch": 1.43, "learning_rate": 8.51878612716763e-06, "loss": 0.4468, "step": 7938 }, { "epoch": 1.43, "learning_rate": 8.516076589595376e-06, "loss": 0.3216, "step": 7939 }, { "epoch": 1.43, "learning_rate": 8.51336705202312e-06, "loss": 0.6437, "step": 7940 }, { "epoch": 1.43, "learning_rate": 8.510657514450868e-06, "loss": 0.9515, "step": 7941 }, { "epoch": 1.43, "learning_rate": 8.507947976878613e-06, "loss": 0.5418, "step": 7942 }, { "epoch": 1.43, "learning_rate": 8.505238439306359e-06, "loss": 0.3644, "step": 7943 }, { "epoch": 1.43, "learning_rate": 8.502528901734105e-06, "loss": 0.4905, "step": 7944 }, { "epoch": 1.44, "learning_rate": 8.49981936416185e-06, "loss": 1.1591, "step": 7945 }, { "epoch": 1.44, "learning_rate": 8.497109826589597e-06, "loss": 0.8178, "step": 7946 }, { "epoch": 1.44, "learning_rate": 8.494400289017341e-06, "loss": 0.446, "step": 7947 }, { "epoch": 1.44, "learning_rate": 8.491690751445087e-06, "loss": 0.6017, "step": 7948 }, { "epoch": 1.44, "learning_rate": 8.488981213872832e-06, "loss": 0.2566, "step": 7949 }, { "epoch": 1.44, "learning_rate": 8.486271676300578e-06, "loss": 0.2244, "step": 7950 }, { "epoch": 1.44, "learning_rate": 8.483562138728324e-06, "loss": 0.4846, "step": 7951 }, { "epoch": 1.44, "learning_rate": 8.48085260115607e-06, "loss": 0.9304, "step": 7952 }, { "epoch": 1.44, "learning_rate": 8.478143063583816e-06, "loss": 0.5733, "step": 7953 }, { "epoch": 1.44, "learning_rate": 8.47543352601156e-06, "loss": 0.2385, "step": 7954 }, { "epoch": 1.44, "learning_rate": 8.472723988439306e-06, "loss": 0.5635, "step": 7955 }, { "epoch": 1.44, "learning_rate": 8.470014450867052e-06, "loss": 0.6084, "step": 7956 }, { "epoch": 1.44, "learning_rate": 8.467304913294799e-06, "loss": 0.5538, "step": 7957 }, { "epoch": 1.44, "learning_rate": 8.464595375722543e-06, "loss": 0.4575, "step": 7958 }, { "epoch": 1.44, "learning_rate": 8.461885838150289e-06, "loss": 0.6586, "step": 7959 }, { "epoch": 1.44, "learning_rate": 8.459176300578035e-06, "loss": 0.4522, "step": 7960 }, { "epoch": 1.44, "learning_rate": 8.456466763005781e-06, "loss": 0.2957, "step": 7961 }, { "epoch": 1.44, "learning_rate": 8.453757225433527e-06, "loss": 0.4096, "step": 7962 }, { "epoch": 1.44, "learning_rate": 8.451047687861272e-06, "loss": 0.7928, "step": 7963 }, { "epoch": 1.44, "learning_rate": 8.448338150289018e-06, "loss": 0.4099, "step": 7964 }, { "epoch": 1.44, "learning_rate": 8.445628612716762e-06, "loss": 0.3601, "step": 7965 }, { "epoch": 1.44, "learning_rate": 8.44291907514451e-06, "loss": 0.3945, "step": 7966 }, { "epoch": 1.44, "learning_rate": 8.440209537572254e-06, "loss": 0.6728, "step": 7967 }, { "epoch": 1.44, "learning_rate": 8.4375e-06, "loss": 1.1175, "step": 7968 }, { "epoch": 1.44, "learning_rate": 8.434790462427746e-06, "loss": 0.8888, "step": 7969 }, { "epoch": 1.44, "learning_rate": 8.43208092485549e-06, "loss": 1.1823, "step": 7970 }, { "epoch": 1.44, "learning_rate": 8.429371387283238e-06, "loss": 0.3897, "step": 7971 }, { "epoch": 1.44, "learning_rate": 8.426661849710983e-06, "loss": 0.6649, "step": 7972 }, { "epoch": 1.44, "learning_rate": 8.423952312138729e-06, "loss": 0.8312, "step": 7973 }, { "epoch": 1.44, "learning_rate": 8.421242774566473e-06, "loss": 0.8684, "step": 7974 }, { "epoch": 1.44, "learning_rate": 8.418533236994219e-06, "loss": 0.3104, "step": 7975 }, { "epoch": 1.44, "learning_rate": 8.415823699421967e-06, "loss": 0.4998, "step": 7976 }, { "epoch": 1.44, "learning_rate": 8.413114161849711e-06, "loss": 0.7055, "step": 7977 }, { "epoch": 1.44, "learning_rate": 8.410404624277457e-06, "loss": 0.493, "step": 7978 }, { "epoch": 1.44, "learning_rate": 8.407695086705202e-06, "loss": 0.3221, "step": 7979 }, { "epoch": 1.44, "learning_rate": 8.404985549132948e-06, "loss": 0.4284, "step": 7980 }, { "epoch": 1.44, "learning_rate": 8.402276011560694e-06, "loss": 0.3303, "step": 7981 }, { "epoch": 1.44, "learning_rate": 8.39956647398844e-06, "loss": 0.5214, "step": 7982 }, { "epoch": 1.44, "learning_rate": 8.396856936416186e-06, "loss": 0.338, "step": 7983 }, { "epoch": 1.44, "learning_rate": 8.39414739884393e-06, "loss": 0.6403, "step": 7984 }, { "epoch": 1.44, "learning_rate": 8.391437861271676e-06, "loss": 0.5401, "step": 7985 }, { "epoch": 1.44, "learning_rate": 8.388728323699422e-06, "loss": 0.7882, "step": 7986 }, { "epoch": 1.44, "learning_rate": 8.386018786127168e-06, "loss": 1.2839, "step": 7987 }, { "epoch": 1.44, "learning_rate": 8.383309248554913e-06, "loss": 0.8245, "step": 7988 }, { "epoch": 1.44, "learning_rate": 8.380599710982659e-06, "loss": 0.6163, "step": 7989 }, { "epoch": 1.44, "learning_rate": 8.377890173410403e-06, "loss": 0.7206, "step": 7990 }, { "epoch": 1.44, "learning_rate": 8.375180635838151e-06, "loss": 0.529, "step": 7991 }, { "epoch": 1.44, "learning_rate": 8.372471098265897e-06, "loss": 0.4262, "step": 7992 }, { "epoch": 1.44, "learning_rate": 8.369761560693641e-06, "loss": 0.7582, "step": 7993 }, { "epoch": 1.44, "learning_rate": 8.367052023121387e-06, "loss": 0.4643, "step": 7994 }, { "epoch": 1.44, "learning_rate": 8.364342485549132e-06, "loss": 0.4374, "step": 7995 }, { "epoch": 1.44, "learning_rate": 8.36163294797688e-06, "loss": 0.3978, "step": 7996 }, { "epoch": 1.44, "learning_rate": 8.358923410404624e-06, "loss": 0.4811, "step": 7997 }, { "epoch": 1.44, "learning_rate": 8.35621387283237e-06, "loss": 0.2344, "step": 7998 }, { "epoch": 1.44, "learning_rate": 8.353504335260116e-06, "loss": 0.9302, "step": 7999 }, { "epoch": 1.45, "learning_rate": 8.35079479768786e-06, "loss": 0.4909, "step": 8000 }, { "epoch": 1.45, "eval_exact_match": 88.05108798486282, "eval_f1": 93.98520975393299, "step": 8000 }, { "epoch": 1.45, "learning_rate": 8.348085260115608e-06, "loss": 0.9115, "step": 8001 }, { "epoch": 1.45, "learning_rate": 8.345375722543353e-06, "loss": 1.0185, "step": 8002 }, { "epoch": 1.45, "learning_rate": 8.342666184971099e-06, "loss": 0.5026, "step": 8003 }, { "epoch": 1.45, "learning_rate": 8.339956647398843e-06, "loss": 0.7235, "step": 8004 }, { "epoch": 1.45, "learning_rate": 8.337247109826589e-06, "loss": 0.447, "step": 8005 }, { "epoch": 1.45, "learning_rate": 8.334537572254337e-06, "loss": 0.28, "step": 8006 }, { "epoch": 1.45, "learning_rate": 8.331828034682081e-06, "loss": 0.4826, "step": 8007 }, { "epoch": 1.45, "learning_rate": 8.329118497109827e-06, "loss": 0.3814, "step": 8008 }, { "epoch": 1.45, "learning_rate": 8.326408959537572e-06, "loss": 0.5316, "step": 8009 }, { "epoch": 1.45, "learning_rate": 8.323699421965318e-06, "loss": 1.1572, "step": 8010 }, { "epoch": 1.45, "learning_rate": 8.320989884393064e-06, "loss": 1.2093, "step": 8011 }, { "epoch": 1.45, "learning_rate": 8.31828034682081e-06, "loss": 0.2542, "step": 8012 }, { "epoch": 1.45, "learning_rate": 8.315570809248554e-06, "loss": 0.5626, "step": 8013 }, { "epoch": 1.45, "learning_rate": 8.3128612716763e-06, "loss": 0.2616, "step": 8014 }, { "epoch": 1.45, "learning_rate": 8.310151734104048e-06, "loss": 0.2309, "step": 8015 }, { "epoch": 1.45, "learning_rate": 8.307442196531792e-06, "loss": 1.5406, "step": 8016 }, { "epoch": 1.45, "learning_rate": 8.304732658959538e-06, "loss": 0.3782, "step": 8017 }, { "epoch": 1.45, "learning_rate": 8.302023121387283e-06, "loss": 0.2223, "step": 8018 }, { "epoch": 1.45, "learning_rate": 8.299313583815029e-06, "loss": 0.4473, "step": 8019 }, { "epoch": 1.45, "learning_rate": 8.296604046242775e-06, "loss": 0.2316, "step": 8020 }, { "epoch": 1.45, "learning_rate": 8.293894508670521e-06, "loss": 0.4465, "step": 8021 }, { "epoch": 1.45, "learning_rate": 8.291184971098267e-06, "loss": 0.8864, "step": 8022 }, { "epoch": 1.45, "learning_rate": 8.288475433526011e-06, "loss": 0.1722, "step": 8023 }, { "epoch": 1.45, "learning_rate": 8.285765895953757e-06, "loss": 0.6894, "step": 8024 }, { "epoch": 1.45, "learning_rate": 8.283056358381503e-06, "loss": 1.24, "step": 8025 }, { "epoch": 1.45, "learning_rate": 8.28034682080925e-06, "loss": 0.362, "step": 8026 }, { "epoch": 1.45, "learning_rate": 8.277637283236994e-06, "loss": 0.7019, "step": 8027 }, { "epoch": 1.45, "learning_rate": 8.27492774566474e-06, "loss": 0.3347, "step": 8028 }, { "epoch": 1.45, "learning_rate": 8.272218208092486e-06, "loss": 0.5032, "step": 8029 }, { "epoch": 1.45, "learning_rate": 8.269508670520232e-06, "loss": 0.4846, "step": 8030 }, { "epoch": 1.45, "learning_rate": 8.266799132947978e-06, "loss": 0.3144, "step": 8031 }, { "epoch": 1.45, "learning_rate": 8.264089595375722e-06, "loss": 0.4564, "step": 8032 }, { "epoch": 1.45, "learning_rate": 8.261380057803469e-06, "loss": 0.6431, "step": 8033 }, { "epoch": 1.45, "learning_rate": 8.258670520231213e-06, "loss": 0.4642, "step": 8034 }, { "epoch": 1.45, "learning_rate": 8.25596098265896e-06, "loss": 0.4312, "step": 8035 }, { "epoch": 1.45, "learning_rate": 8.253251445086705e-06, "loss": 0.4851, "step": 8036 }, { "epoch": 1.45, "learning_rate": 8.250541907514451e-06, "loss": 0.9458, "step": 8037 }, { "epoch": 1.45, "learning_rate": 8.247832369942197e-06, "loss": 0.313, "step": 8038 }, { "epoch": 1.45, "learning_rate": 8.245122832369942e-06, "loss": 0.4359, "step": 8039 }, { "epoch": 1.45, "learning_rate": 8.24241329479769e-06, "loss": 0.2823, "step": 8040 }, { "epoch": 1.45, "learning_rate": 8.239703757225434e-06, "loss": 0.3728, "step": 8041 }, { "epoch": 1.45, "learning_rate": 8.23699421965318e-06, "loss": 0.5482, "step": 8042 }, { "epoch": 1.45, "learning_rate": 8.234284682080924e-06, "loss": 0.4732, "step": 8043 }, { "epoch": 1.45, "learning_rate": 8.23157514450867e-06, "loss": 0.6148, "step": 8044 }, { "epoch": 1.45, "learning_rate": 8.228865606936418e-06, "loss": 0.6465, "step": 8045 }, { "epoch": 1.45, "learning_rate": 8.226156069364162e-06, "loss": 0.6103, "step": 8046 }, { "epoch": 1.45, "learning_rate": 8.223446531791908e-06, "loss": 1.0267, "step": 8047 }, { "epoch": 1.45, "learning_rate": 8.220736994219653e-06, "loss": 0.4947, "step": 8048 }, { "epoch": 1.45, "learning_rate": 8.218027456647399e-06, "loss": 0.6601, "step": 8049 }, { "epoch": 1.45, "learning_rate": 8.215317919075145e-06, "loss": 0.6523, "step": 8050 }, { "epoch": 1.45, "learning_rate": 8.21260838150289e-06, "loss": 0.5785, "step": 8051 }, { "epoch": 1.45, "learning_rate": 8.209898843930637e-06, "loss": 0.4139, "step": 8052 }, { "epoch": 1.45, "learning_rate": 8.207189306358381e-06, "loss": 0.5405, "step": 8053 }, { "epoch": 1.45, "learning_rate": 8.204479768786127e-06, "loss": 0.4203, "step": 8054 }, { "epoch": 1.46, "learning_rate": 8.201770231213873e-06, "loss": 0.5936, "step": 8055 }, { "epoch": 1.46, "learning_rate": 8.19906069364162e-06, "loss": 0.2637, "step": 8056 }, { "epoch": 1.46, "learning_rate": 8.196351156069364e-06, "loss": 0.604, "step": 8057 }, { "epoch": 1.46, "learning_rate": 8.19364161849711e-06, "loss": 0.6608, "step": 8058 }, { "epoch": 1.46, "learning_rate": 8.190932080924854e-06, "loss": 1.4286, "step": 8059 }, { "epoch": 1.46, "learning_rate": 8.188222543352602e-06, "loss": 0.3942, "step": 8060 }, { "epoch": 1.46, "learning_rate": 8.185513005780348e-06, "loss": 0.3305, "step": 8061 }, { "epoch": 1.46, "learning_rate": 8.182803468208092e-06, "loss": 0.5254, "step": 8062 }, { "epoch": 1.46, "learning_rate": 8.180093930635838e-06, "loss": 0.4034, "step": 8063 }, { "epoch": 1.46, "learning_rate": 8.177384393063583e-06, "loss": 0.4713, "step": 8064 }, { "epoch": 1.46, "learning_rate": 8.17467485549133e-06, "loss": 0.8554, "step": 8065 }, { "epoch": 1.46, "learning_rate": 8.171965317919075e-06, "loss": 0.6484, "step": 8066 }, { "epoch": 1.46, "learning_rate": 8.169255780346821e-06, "loss": 0.5387, "step": 8067 }, { "epoch": 1.46, "learning_rate": 8.166546242774567e-06, "loss": 0.7781, "step": 8068 }, { "epoch": 1.46, "learning_rate": 8.163836705202311e-06, "loss": 0.5838, "step": 8069 }, { "epoch": 1.46, "learning_rate": 8.16112716763006e-06, "loss": 0.4957, "step": 8070 }, { "epoch": 1.46, "learning_rate": 8.158417630057804e-06, "loss": 0.5183, "step": 8071 }, { "epoch": 1.46, "learning_rate": 8.15570809248555e-06, "loss": 0.8632, "step": 8072 }, { "epoch": 1.46, "learning_rate": 8.152998554913294e-06, "loss": 0.691, "step": 8073 }, { "epoch": 1.46, "learning_rate": 8.15028901734104e-06, "loss": 0.6237, "step": 8074 }, { "epoch": 1.46, "learning_rate": 8.147579479768786e-06, "loss": 0.848, "step": 8075 }, { "epoch": 1.46, "learning_rate": 8.144869942196532e-06, "loss": 0.4296, "step": 8076 }, { "epoch": 1.46, "learning_rate": 8.142160404624278e-06, "loss": 0.6635, "step": 8077 }, { "epoch": 1.46, "learning_rate": 8.139450867052023e-06, "loss": 0.3628, "step": 8078 }, { "epoch": 1.46, "learning_rate": 8.136741329479769e-06, "loss": 0.7297, "step": 8079 }, { "epoch": 1.46, "learning_rate": 8.134031791907515e-06, "loss": 0.2939, "step": 8080 }, { "epoch": 1.46, "learning_rate": 8.13132225433526e-06, "loss": 0.5862, "step": 8081 }, { "epoch": 1.46, "learning_rate": 8.128612716763005e-06, "loss": 0.8613, "step": 8082 }, { "epoch": 1.46, "learning_rate": 8.125903179190751e-06, "loss": 0.5328, "step": 8083 }, { "epoch": 1.46, "learning_rate": 8.123193641618497e-06, "loss": 0.2006, "step": 8084 }, { "epoch": 1.46, "learning_rate": 8.120484104046243e-06, "loss": 0.6746, "step": 8085 }, { "epoch": 1.46, "learning_rate": 8.11777456647399e-06, "loss": 0.3359, "step": 8086 }, { "epoch": 1.46, "learning_rate": 8.115065028901734e-06, "loss": 1.0375, "step": 8087 }, { "epoch": 1.46, "learning_rate": 8.11235549132948e-06, "loss": 0.6027, "step": 8088 }, { "epoch": 1.46, "learning_rate": 8.109645953757224e-06, "loss": 0.4657, "step": 8089 }, { "epoch": 1.46, "learning_rate": 8.106936416184972e-06, "loss": 0.5876, "step": 8090 }, { "epoch": 1.46, "learning_rate": 8.104226878612718e-06, "loss": 0.7408, "step": 8091 }, { "epoch": 1.46, "learning_rate": 8.101517341040462e-06, "loss": 0.5621, "step": 8092 }, { "epoch": 1.46, "learning_rate": 8.098807803468208e-06, "loss": 0.773, "step": 8093 }, { "epoch": 1.46, "learning_rate": 8.096098265895953e-06, "loss": 0.4169, "step": 8094 }, { "epoch": 1.46, "learning_rate": 8.0933887283237e-06, "loss": 0.7547, "step": 8095 }, { "epoch": 1.46, "learning_rate": 8.090679190751445e-06, "loss": 0.6938, "step": 8096 }, { "epoch": 1.46, "learning_rate": 8.087969653179191e-06, "loss": 0.7433, "step": 8097 }, { "epoch": 1.46, "learning_rate": 8.085260115606935e-06, "loss": 0.2528, "step": 8098 }, { "epoch": 1.46, "learning_rate": 8.082550578034683e-06, "loss": 0.2084, "step": 8099 }, { "epoch": 1.46, "learning_rate": 8.079841040462429e-06, "loss": 0.6243, "step": 8100 }, { "epoch": 1.46, "learning_rate": 8.077131502890173e-06, "loss": 0.4355, "step": 8101 }, { "epoch": 1.46, "learning_rate": 8.07442196531792e-06, "loss": 0.3448, "step": 8102 }, { "epoch": 1.46, "learning_rate": 8.071712427745664e-06, "loss": 0.5562, "step": 8103 }, { "epoch": 1.46, "learning_rate": 8.069002890173412e-06, "loss": 0.1305, "step": 8104 }, { "epoch": 1.46, "learning_rate": 8.066293352601156e-06, "loss": 0.3667, "step": 8105 }, { "epoch": 1.46, "learning_rate": 8.063583815028902e-06, "loss": 0.878, "step": 8106 }, { "epoch": 1.46, "learning_rate": 8.060874277456648e-06, "loss": 0.5018, "step": 8107 }, { "epoch": 1.46, "learning_rate": 8.058164739884392e-06, "loss": 0.5471, "step": 8108 }, { "epoch": 1.46, "learning_rate": 8.05545520231214e-06, "loss": 1.0342, "step": 8109 }, { "epoch": 1.46, "learning_rate": 8.052745664739885e-06, "loss": 0.4396, "step": 8110 }, { "epoch": 1.47, "learning_rate": 8.05003612716763e-06, "loss": 0.5437, "step": 8111 }, { "epoch": 1.47, "learning_rate": 8.047326589595375e-06, "loss": 0.3892, "step": 8112 }, { "epoch": 1.47, "learning_rate": 8.044617052023121e-06, "loss": 0.5541, "step": 8113 }, { "epoch": 1.47, "learning_rate": 8.041907514450869e-06, "loss": 0.4299, "step": 8114 }, { "epoch": 1.47, "learning_rate": 8.039197976878613e-06, "loss": 0.3434, "step": 8115 }, { "epoch": 1.47, "learning_rate": 8.03648843930636e-06, "loss": 0.589, "step": 8116 }, { "epoch": 1.47, "learning_rate": 8.033778901734104e-06, "loss": 0.4876, "step": 8117 }, { "epoch": 1.47, "learning_rate": 8.03106936416185e-06, "loss": 0.5263, "step": 8118 }, { "epoch": 1.47, "learning_rate": 8.028359826589596e-06, "loss": 0.5279, "step": 8119 }, { "epoch": 1.47, "learning_rate": 8.025650289017342e-06, "loss": 0.4238, "step": 8120 }, { "epoch": 1.47, "learning_rate": 8.022940751445086e-06, "loss": 0.7145, "step": 8121 }, { "epoch": 1.47, "learning_rate": 8.020231213872832e-06, "loss": 0.6801, "step": 8122 }, { "epoch": 1.47, "learning_rate": 8.017521676300578e-06, "loss": 0.1218, "step": 8123 }, { "epoch": 1.47, "learning_rate": 8.014812138728324e-06, "loss": 0.2439, "step": 8124 }, { "epoch": 1.47, "learning_rate": 8.01210260115607e-06, "loss": 0.4203, "step": 8125 }, { "epoch": 1.47, "learning_rate": 8.009393063583815e-06, "loss": 0.68, "step": 8126 }, { "epoch": 1.47, "learning_rate": 8.00668352601156e-06, "loss": 0.8173, "step": 8127 }, { "epoch": 1.47, "learning_rate": 8.003973988439305e-06, "loss": 0.8495, "step": 8128 }, { "epoch": 1.47, "learning_rate": 8.001264450867053e-06, "loss": 0.2997, "step": 8129 }, { "epoch": 1.47, "learning_rate": 7.998554913294799e-06, "loss": 1.102, "step": 8130 }, { "epoch": 1.47, "learning_rate": 7.995845375722543e-06, "loss": 0.2694, "step": 8131 }, { "epoch": 1.47, "learning_rate": 7.99313583815029e-06, "loss": 0.58, "step": 8132 }, { "epoch": 1.47, "learning_rate": 7.990426300578034e-06, "loss": 1.0503, "step": 8133 }, { "epoch": 1.47, "learning_rate": 7.987716763005782e-06, "loss": 0.3896, "step": 8134 }, { "epoch": 1.47, "learning_rate": 7.985007225433526e-06, "loss": 0.4943, "step": 8135 }, { "epoch": 1.47, "learning_rate": 7.982297687861272e-06, "loss": 0.6512, "step": 8136 }, { "epoch": 1.47, "learning_rate": 7.979588150289018e-06, "loss": 0.4284, "step": 8137 }, { "epoch": 1.47, "learning_rate": 7.976878612716762e-06, "loss": 0.674, "step": 8138 }, { "epoch": 1.47, "learning_rate": 7.97416907514451e-06, "loss": 0.3661, "step": 8139 }, { "epoch": 1.47, "learning_rate": 7.971459537572255e-06, "loss": 0.7016, "step": 8140 }, { "epoch": 1.47, "learning_rate": 7.96875e-06, "loss": 1.2758, "step": 8141 }, { "epoch": 1.47, "learning_rate": 7.966040462427745e-06, "loss": 0.7447, "step": 8142 }, { "epoch": 1.47, "learning_rate": 7.963330924855491e-06, "loss": 0.4336, "step": 8143 }, { "epoch": 1.47, "learning_rate": 7.960621387283237e-06, "loss": 0.8983, "step": 8144 }, { "epoch": 1.47, "learning_rate": 7.957911849710983e-06, "loss": 0.6285, "step": 8145 }, { "epoch": 1.47, "learning_rate": 7.95520231213873e-06, "loss": 0.3318, "step": 8146 }, { "epoch": 1.47, "learning_rate": 7.952492774566474e-06, "loss": 0.8438, "step": 8147 }, { "epoch": 1.47, "learning_rate": 7.94978323699422e-06, "loss": 0.3919, "step": 8148 }, { "epoch": 1.47, "learning_rate": 7.947073699421966e-06, "loss": 0.268, "step": 8149 }, { "epoch": 1.47, "learning_rate": 7.944364161849712e-06, "loss": 0.2255, "step": 8150 }, { "epoch": 1.47, "learning_rate": 7.941654624277456e-06, "loss": 0.7292, "step": 8151 }, { "epoch": 1.47, "learning_rate": 7.938945086705202e-06, "loss": 0.7651, "step": 8152 }, { "epoch": 1.47, "learning_rate": 7.936235549132948e-06, "loss": 0.5721, "step": 8153 }, { "epoch": 1.47, "learning_rate": 7.933526011560694e-06, "loss": 0.5958, "step": 8154 }, { "epoch": 1.47, "learning_rate": 7.93081647398844e-06, "loss": 0.5894, "step": 8155 }, { "epoch": 1.47, "learning_rate": 7.928106936416185e-06, "loss": 1.1711, "step": 8156 }, { "epoch": 1.47, "learning_rate": 7.92539739884393e-06, "loss": 0.8598, "step": 8157 }, { "epoch": 1.47, "learning_rate": 7.922687861271675e-06, "loss": 1.0245, "step": 8158 }, { "epoch": 1.47, "learning_rate": 7.919978323699423e-06, "loss": 0.6841, "step": 8159 }, { "epoch": 1.47, "learning_rate": 7.917268786127169e-06, "loss": 1.2724, "step": 8160 }, { "epoch": 1.47, "learning_rate": 7.914559248554913e-06, "loss": 0.229, "step": 8161 }, { "epoch": 1.47, "learning_rate": 7.91184971098266e-06, "loss": 0.4139, "step": 8162 }, { "epoch": 1.47, "learning_rate": 7.909140173410404e-06, "loss": 0.7784, "step": 8163 }, { "epoch": 1.47, "learning_rate": 7.906430635838151e-06, "loss": 0.3108, "step": 8164 }, { "epoch": 1.47, "learning_rate": 7.903721098265896e-06, "loss": 0.3751, "step": 8165 }, { "epoch": 1.48, "learning_rate": 7.901011560693642e-06, "loss": 0.3513, "step": 8166 }, { "epoch": 1.48, "learning_rate": 7.898302023121386e-06, "loss": 0.5589, "step": 8167 }, { "epoch": 1.48, "learning_rate": 7.895592485549132e-06, "loss": 0.6332, "step": 8168 }, { "epoch": 1.48, "learning_rate": 7.89288294797688e-06, "loss": 0.8394, "step": 8169 }, { "epoch": 1.48, "learning_rate": 7.890173410404624e-06, "loss": 0.484, "step": 8170 }, { "epoch": 1.48, "learning_rate": 7.88746387283237e-06, "loss": 0.8328, "step": 8171 }, { "epoch": 1.48, "learning_rate": 7.884754335260115e-06, "loss": 0.971, "step": 8172 }, { "epoch": 1.48, "learning_rate": 7.882044797687861e-06, "loss": 0.1685, "step": 8173 }, { "epoch": 1.48, "learning_rate": 7.879335260115607e-06, "loss": 0.6784, "step": 8174 }, { "epoch": 1.48, "learning_rate": 7.876625722543353e-06, "loss": 0.3169, "step": 8175 }, { "epoch": 1.48, "learning_rate": 7.873916184971099e-06, "loss": 0.652, "step": 8176 }, { "epoch": 1.48, "learning_rate": 7.871206647398843e-06, "loss": 0.5832, "step": 8177 }, { "epoch": 1.48, "learning_rate": 7.86849710982659e-06, "loss": 0.6221, "step": 8178 }, { "epoch": 1.48, "learning_rate": 7.865787572254336e-06, "loss": 0.7245, "step": 8179 }, { "epoch": 1.48, "learning_rate": 7.863078034682082e-06, "loss": 0.2093, "step": 8180 }, { "epoch": 1.48, "learning_rate": 7.860368497109826e-06, "loss": 0.4241, "step": 8181 }, { "epoch": 1.48, "learning_rate": 7.857658959537572e-06, "loss": 0.3504, "step": 8182 }, { "epoch": 1.48, "learning_rate": 7.854949421965318e-06, "loss": 0.2416, "step": 8183 }, { "epoch": 1.48, "learning_rate": 7.852239884393064e-06, "loss": 0.528, "step": 8184 }, { "epoch": 1.48, "learning_rate": 7.84953034682081e-06, "loss": 0.2719, "step": 8185 }, { "epoch": 1.48, "learning_rate": 7.846820809248555e-06, "loss": 0.2986, "step": 8186 }, { "epoch": 1.48, "learning_rate": 7.8441112716763e-06, "loss": 0.9331, "step": 8187 }, { "epoch": 1.48, "learning_rate": 7.841401734104047e-06, "loss": 0.5105, "step": 8188 }, { "epoch": 1.48, "learning_rate": 7.838692196531793e-06, "loss": 0.4122, "step": 8189 }, { "epoch": 1.48, "learning_rate": 7.835982658959537e-06, "loss": 0.7145, "step": 8190 }, { "epoch": 1.48, "learning_rate": 7.833273121387283e-06, "loss": 0.7005, "step": 8191 }, { "epoch": 1.48, "learning_rate": 7.83056358381503e-06, "loss": 0.6927, "step": 8192 }, { "epoch": 1.48, "learning_rate": 7.827854046242775e-06, "loss": 0.6371, "step": 8193 }, { "epoch": 1.48, "learning_rate": 7.825144508670521e-06, "loss": 0.3508, "step": 8194 }, { "epoch": 1.48, "learning_rate": 7.822434971098266e-06, "loss": 0.428, "step": 8195 }, { "epoch": 1.48, "learning_rate": 7.819725433526012e-06, "loss": 0.5721, "step": 8196 }, { "epoch": 1.48, "learning_rate": 7.817015895953756e-06, "loss": 0.4534, "step": 8197 }, { "epoch": 1.48, "learning_rate": 7.814306358381504e-06, "loss": 0.8273, "step": 8198 }, { "epoch": 1.48, "learning_rate": 7.81159682080925e-06, "loss": 0.3507, "step": 8199 }, { "epoch": 1.48, "learning_rate": 7.808887283236994e-06, "loss": 0.4255, "step": 8200 }, { "epoch": 1.48, "learning_rate": 7.80617774566474e-06, "loss": 1.3079, "step": 8201 }, { "epoch": 1.48, "learning_rate": 7.803468208092485e-06, "loss": 0.3271, "step": 8202 }, { "epoch": 1.48, "learning_rate": 7.800758670520233e-06, "loss": 0.5039, "step": 8203 }, { "epoch": 1.48, "learning_rate": 7.798049132947977e-06, "loss": 0.8682, "step": 8204 }, { "epoch": 1.48, "learning_rate": 7.795339595375723e-06, "loss": 0.6792, "step": 8205 }, { "epoch": 1.48, "learning_rate": 7.792630057803467e-06, "loss": 0.5543, "step": 8206 }, { "epoch": 1.48, "learning_rate": 7.789920520231213e-06, "loss": 0.3586, "step": 8207 }, { "epoch": 1.48, "learning_rate": 7.787210982658961e-06, "loss": 0.8093, "step": 8208 }, { "epoch": 1.48, "learning_rate": 7.784501445086705e-06, "loss": 0.7767, "step": 8209 }, { "epoch": 1.48, "learning_rate": 7.781791907514452e-06, "loss": 0.7451, "step": 8210 }, { "epoch": 1.48, "learning_rate": 7.779082369942196e-06, "loss": 0.1822, "step": 8211 }, { "epoch": 1.48, "learning_rate": 7.776372832369942e-06, "loss": 0.295, "step": 8212 }, { "epoch": 1.48, "learning_rate": 7.773663294797688e-06, "loss": 0.5331, "step": 8213 }, { "epoch": 1.48, "learning_rate": 7.770953757225434e-06, "loss": 0.4069, "step": 8214 }, { "epoch": 1.48, "learning_rate": 7.76824421965318e-06, "loss": 0.5143, "step": 8215 }, { "epoch": 1.48, "learning_rate": 7.765534682080925e-06, "loss": 0.377, "step": 8216 }, { "epoch": 1.48, "learning_rate": 7.76282514450867e-06, "loss": 0.6726, "step": 8217 }, { "epoch": 1.48, "learning_rate": 7.760115606936417e-06, "loss": 0.5396, "step": 8218 }, { "epoch": 1.48, "learning_rate": 7.757406069364163e-06, "loss": 0.8591, "step": 8219 }, { "epoch": 1.48, "learning_rate": 7.754696531791907e-06, "loss": 0.8691, "step": 8220 }, { "epoch": 1.49, "learning_rate": 7.751986994219653e-06, "loss": 0.5684, "step": 8221 }, { "epoch": 1.49, "learning_rate": 7.7492774566474e-06, "loss": 0.7598, "step": 8222 }, { "epoch": 1.49, "learning_rate": 7.746567919075145e-06, "loss": 1.4018, "step": 8223 }, { "epoch": 1.49, "learning_rate": 7.743858381502891e-06, "loss": 0.333, "step": 8224 }, { "epoch": 1.49, "learning_rate": 7.741148843930636e-06, "loss": 0.4921, "step": 8225 }, { "epoch": 1.49, "learning_rate": 7.738439306358382e-06, "loss": 0.3767, "step": 8226 }, { "epoch": 1.49, "learning_rate": 7.735729768786126e-06, "loss": 0.7668, "step": 8227 }, { "epoch": 1.49, "learning_rate": 7.733020231213874e-06, "loss": 0.3357, "step": 8228 }, { "epoch": 1.49, "learning_rate": 7.730310693641618e-06, "loss": 0.7575, "step": 8229 }, { "epoch": 1.49, "learning_rate": 7.727601156069364e-06, "loss": 1.3832, "step": 8230 }, { "epoch": 1.49, "learning_rate": 7.72489161849711e-06, "loss": 0.4298, "step": 8231 }, { "epoch": 1.49, "learning_rate": 7.722182080924855e-06, "loss": 0.2179, "step": 8232 }, { "epoch": 1.49, "learning_rate": 7.719472543352602e-06, "loss": 0.6919, "step": 8233 }, { "epoch": 1.49, "learning_rate": 7.716763005780347e-06, "loss": 0.4249, "step": 8234 }, { "epoch": 1.49, "learning_rate": 7.714053468208093e-06, "loss": 0.5291, "step": 8235 }, { "epoch": 1.49, "learning_rate": 7.711343930635837e-06, "loss": 0.4763, "step": 8236 }, { "epoch": 1.49, "learning_rate": 7.708634393063583e-06, "loss": 0.4217, "step": 8237 }, { "epoch": 1.49, "learning_rate": 7.705924855491331e-06, "loss": 0.3558, "step": 8238 }, { "epoch": 1.49, "learning_rate": 7.703215317919075e-06, "loss": 0.4748, "step": 8239 }, { "epoch": 1.49, "learning_rate": 7.700505780346821e-06, "loss": 0.8514, "step": 8240 }, { "epoch": 1.49, "learning_rate": 7.697796242774566e-06, "loss": 0.4612, "step": 8241 }, { "epoch": 1.49, "learning_rate": 7.695086705202312e-06, "loss": 0.4092, "step": 8242 }, { "epoch": 1.49, "learning_rate": 7.692377167630058e-06, "loss": 0.3934, "step": 8243 }, { "epoch": 1.49, "learning_rate": 7.689667630057804e-06, "loss": 0.8571, "step": 8244 }, { "epoch": 1.49, "learning_rate": 7.68695809248555e-06, "loss": 0.7217, "step": 8245 }, { "epoch": 1.49, "learning_rate": 7.684248554913294e-06, "loss": 1.0726, "step": 8246 }, { "epoch": 1.49, "learning_rate": 7.68153901734104e-06, "loss": 0.2846, "step": 8247 }, { "epoch": 1.49, "learning_rate": 7.678829479768787e-06, "loss": 0.556, "step": 8248 }, { "epoch": 1.49, "learning_rate": 7.676119942196533e-06, "loss": 0.4962, "step": 8249 }, { "epoch": 1.49, "learning_rate": 7.673410404624277e-06, "loss": 0.5957, "step": 8250 }, { "epoch": 1.49, "learning_rate": 7.670700867052023e-06, "loss": 0.409, "step": 8251 }, { "epoch": 1.49, "learning_rate": 7.667991329479767e-06, "loss": 0.5122, "step": 8252 }, { "epoch": 1.49, "learning_rate": 7.665281791907515e-06, "loss": 1.0306, "step": 8253 }, { "epoch": 1.49, "learning_rate": 7.662572254335261e-06, "loss": 0.648, "step": 8254 }, { "epoch": 1.49, "learning_rate": 7.659862716763006e-06, "loss": 0.8338, "step": 8255 }, { "epoch": 1.49, "learning_rate": 7.657153179190752e-06, "loss": 0.3119, "step": 8256 }, { "epoch": 1.49, "learning_rate": 7.654443641618496e-06, "loss": 0.5937, "step": 8257 }, { "epoch": 1.49, "learning_rate": 7.651734104046244e-06, "loss": 1.0033, "step": 8258 }, { "epoch": 1.49, "learning_rate": 7.649024566473988e-06, "loss": 0.4284, "step": 8259 }, { "epoch": 1.49, "learning_rate": 7.646315028901734e-06, "loss": 1.0434, "step": 8260 }, { "epoch": 1.49, "learning_rate": 7.64360549132948e-06, "loss": 0.2638, "step": 8261 }, { "epoch": 1.49, "learning_rate": 7.640895953757225e-06, "loss": 0.7983, "step": 8262 }, { "epoch": 1.49, "learning_rate": 7.638186416184972e-06, "loss": 0.2895, "step": 8263 }, { "epoch": 1.49, "learning_rate": 7.635476878612717e-06, "loss": 0.4952, "step": 8264 }, { "epoch": 1.49, "learning_rate": 7.632767341040463e-06, "loss": 0.4822, "step": 8265 }, { "epoch": 1.49, "learning_rate": 7.630057803468207e-06, "loss": 0.8083, "step": 8266 }, { "epoch": 1.49, "learning_rate": 7.627348265895953e-06, "loss": 0.9905, "step": 8267 }, { "epoch": 1.49, "learning_rate": 7.6246387283237e-06, "loss": 0.6563, "step": 8268 }, { "epoch": 1.49, "learning_rate": 7.621929190751445e-06, "loss": 0.2412, "step": 8269 }, { "epoch": 1.49, "learning_rate": 7.6192196531791905e-06, "loss": 0.7201, "step": 8270 }, { "epoch": 1.49, "learning_rate": 7.616510115606936e-06, "loss": 0.4208, "step": 8271 }, { "epoch": 1.49, "learning_rate": 7.6138005780346835e-06, "loss": 0.3922, "step": 8272 }, { "epoch": 1.49, "learning_rate": 7.611091040462429e-06, "loss": 1.0461, "step": 8273 }, { "epoch": 1.49, "learning_rate": 7.608381502890174e-06, "loss": 0.4757, "step": 8274 }, { "epoch": 1.49, "learning_rate": 7.605671965317919e-06, "loss": 0.3594, "step": 8275 }, { "epoch": 1.49, "learning_rate": 7.602962427745664e-06, "loss": 0.5305, "step": 8276 }, { "epoch": 1.5, "learning_rate": 7.600252890173411e-06, "loss": 0.3474, "step": 8277 }, { "epoch": 1.5, "learning_rate": 7.5975433526011565e-06, "loss": 0.3568, "step": 8278 }, { "epoch": 1.5, "learning_rate": 7.594833815028902e-06, "loss": 0.3469, "step": 8279 }, { "epoch": 1.5, "learning_rate": 7.592124277456648e-06, "loss": 0.4179, "step": 8280 }, { "epoch": 1.5, "learning_rate": 7.589414739884393e-06, "loss": 0.3942, "step": 8281 }, { "epoch": 1.5, "learning_rate": 7.58670520231214e-06, "loss": 0.8054, "step": 8282 }, { "epoch": 1.5, "learning_rate": 7.583995664739885e-06, "loss": 0.2522, "step": 8283 }, { "epoch": 1.5, "learning_rate": 7.58128612716763e-06, "loss": 0.5063, "step": 8284 }, { "epoch": 1.5, "learning_rate": 7.5785765895953755e-06, "loss": 0.4588, "step": 8285 }, { "epoch": 1.5, "learning_rate": 7.575867052023121e-06, "loss": 1.0102, "step": 8286 }, { "epoch": 1.5, "learning_rate": 7.573157514450868e-06, "loss": 0.3978, "step": 8287 }, { "epoch": 1.5, "learning_rate": 7.570447976878614e-06, "loss": 0.4965, "step": 8288 }, { "epoch": 1.5, "learning_rate": 7.567738439306359e-06, "loss": 0.4685, "step": 8289 }, { "epoch": 1.5, "learning_rate": 7.565028901734104e-06, "loss": 1.3388, "step": 8290 }, { "epoch": 1.5, "learning_rate": 7.562319364161849e-06, "loss": 0.6841, "step": 8291 }, { "epoch": 1.5, "learning_rate": 7.559609826589596e-06, "loss": 0.618, "step": 8292 }, { "epoch": 1.5, "learning_rate": 7.556900289017341e-06, "loss": 0.2116, "step": 8293 }, { "epoch": 1.5, "learning_rate": 7.554190751445087e-06, "loss": 0.7375, "step": 8294 }, { "epoch": 1.5, "learning_rate": 7.551481213872833e-06, "loss": 0.4412, "step": 8295 }, { "epoch": 1.5, "learning_rate": 7.548771676300578e-06, "loss": 0.4407, "step": 8296 }, { "epoch": 1.5, "learning_rate": 7.546062138728325e-06, "loss": 0.6075, "step": 8297 }, { "epoch": 1.5, "learning_rate": 7.54335260115607e-06, "loss": 0.1482, "step": 8298 }, { "epoch": 1.5, "learning_rate": 7.540643063583815e-06, "loss": 0.8651, "step": 8299 }, { "epoch": 1.5, "learning_rate": 7.5379335260115604e-06, "loss": 1.4265, "step": 8300 }, { "epoch": 1.5, "learning_rate": 7.535223988439306e-06, "loss": 0.9205, "step": 8301 }, { "epoch": 1.5, "learning_rate": 7.5325144508670526e-06, "loss": 0.2467, "step": 8302 }, { "epoch": 1.5, "learning_rate": 7.529804913294799e-06, "loss": 0.1737, "step": 8303 }, { "epoch": 1.5, "learning_rate": 7.527095375722544e-06, "loss": 0.5612, "step": 8304 }, { "epoch": 1.5, "learning_rate": 7.524385838150289e-06, "loss": 0.5957, "step": 8305 }, { "epoch": 1.5, "learning_rate": 7.521676300578034e-06, "loss": 0.6956, "step": 8306 }, { "epoch": 1.5, "learning_rate": 7.518966763005781e-06, "loss": 0.6178, "step": 8307 }, { "epoch": 1.5, "learning_rate": 7.516257225433526e-06, "loss": 0.6682, "step": 8308 }, { "epoch": 1.5, "learning_rate": 7.513547687861272e-06, "loss": 0.5085, "step": 8309 }, { "epoch": 1.5, "learning_rate": 7.510838150289017e-06, "loss": 0.3607, "step": 8310 }, { "epoch": 1.5, "learning_rate": 7.508128612716763e-06, "loss": 0.7413, "step": 8311 }, { "epoch": 1.5, "learning_rate": 7.50541907514451e-06, "loss": 0.3636, "step": 8312 }, { "epoch": 1.5, "learning_rate": 7.502709537572255e-06, "loss": 0.6184, "step": 8313 }, { "epoch": 1.5, "learning_rate": 7.5e-06, "loss": 0.3851, "step": 8314 }, { "epoch": 1.5, "learning_rate": 7.497290462427745e-06, "loss": 0.3344, "step": 8315 }, { "epoch": 1.5, "learning_rate": 7.4945809248554915e-06, "loss": 0.2902, "step": 8316 }, { "epoch": 1.5, "learning_rate": 7.491871387283237e-06, "loss": 0.6214, "step": 8317 }, { "epoch": 1.5, "learning_rate": 7.489161849710984e-06, "loss": 0.1176, "step": 8318 }, { "epoch": 1.5, "learning_rate": 7.486452312138729e-06, "loss": 0.6791, "step": 8319 }, { "epoch": 1.5, "learning_rate": 7.483742774566474e-06, "loss": 0.7186, "step": 8320 }, { "epoch": 1.5, "learning_rate": 7.48103323699422e-06, "loss": 0.8627, "step": 8321 }, { "epoch": 1.5, "learning_rate": 7.478323699421965e-06, "loss": 0.8413, "step": 8322 }, { "epoch": 1.5, "learning_rate": 7.475614161849711e-06, "loss": 0.5161, "step": 8323 }, { "epoch": 1.5, "learning_rate": 7.4729046242774565e-06, "loss": 0.6642, "step": 8324 }, { "epoch": 1.5, "learning_rate": 7.470195086705202e-06, "loss": 0.4132, "step": 8325 }, { "epoch": 1.5, "learning_rate": 7.467485549132949e-06, "loss": 0.3523, "step": 8326 }, { "epoch": 1.5, "learning_rate": 7.464776011560694e-06, "loss": 0.8895, "step": 8327 }, { "epoch": 1.5, "learning_rate": 7.46206647398844e-06, "loss": 0.2653, "step": 8328 }, { "epoch": 1.5, "learning_rate": 7.459356936416185e-06, "loss": 0.5319, "step": 8329 }, { "epoch": 1.5, "learning_rate": 7.45664739884393e-06, "loss": 0.5144, "step": 8330 }, { "epoch": 1.5, "learning_rate": 7.453937861271676e-06, "loss": 0.7582, "step": 8331 }, { "epoch": 1.51, "learning_rate": 7.451228323699422e-06, "loss": 0.34, "step": 8332 }, { "epoch": 1.51, "learning_rate": 7.448518786127168e-06, "loss": 0.392, "step": 8333 }, { "epoch": 1.51, "learning_rate": 7.445809248554914e-06, "loss": 0.4952, "step": 8334 }, { "epoch": 1.51, "learning_rate": 7.443099710982659e-06, "loss": 0.7057, "step": 8335 }, { "epoch": 1.51, "learning_rate": 7.440390173410405e-06, "loss": 0.8201, "step": 8336 }, { "epoch": 1.51, "learning_rate": 7.43768063583815e-06, "loss": 0.5518, "step": 8337 }, { "epoch": 1.51, "learning_rate": 7.434971098265896e-06, "loss": 0.6438, "step": 8338 }, { "epoch": 1.51, "learning_rate": 7.4322615606936415e-06, "loss": 0.6857, "step": 8339 }, { "epoch": 1.51, "learning_rate": 7.4295520231213876e-06, "loss": 0.5233, "step": 8340 }, { "epoch": 1.51, "learning_rate": 7.426842485549134e-06, "loss": 0.6067, "step": 8341 }, { "epoch": 1.51, "learning_rate": 7.424132947976879e-06, "loss": 0.4334, "step": 8342 }, { "epoch": 1.51, "learning_rate": 7.421423410404625e-06, "loss": 0.4316, "step": 8343 }, { "epoch": 1.51, "learning_rate": 7.41871387283237e-06, "loss": 0.5971, "step": 8344 }, { "epoch": 1.51, "learning_rate": 7.416004335260116e-06, "loss": 1.0581, "step": 8345 }, { "epoch": 1.51, "learning_rate": 7.413294797687861e-06, "loss": 0.5167, "step": 8346 }, { "epoch": 1.51, "learning_rate": 7.410585260115607e-06, "loss": 0.3937, "step": 8347 }, { "epoch": 1.51, "learning_rate": 7.407875722543353e-06, "loss": 0.4646, "step": 8348 }, { "epoch": 1.51, "learning_rate": 7.405166184971099e-06, "loss": 0.7187, "step": 8349 }, { "epoch": 1.51, "learning_rate": 7.402456647398845e-06, "loss": 0.433, "step": 8350 }, { "epoch": 1.51, "learning_rate": 7.39974710982659e-06, "loss": 0.4568, "step": 8351 }, { "epoch": 1.51, "learning_rate": 7.397037572254335e-06, "loss": 0.992, "step": 8352 }, { "epoch": 1.51, "learning_rate": 7.394328034682081e-06, "loss": 0.4132, "step": 8353 }, { "epoch": 1.51, "learning_rate": 7.3916184971098265e-06, "loss": 0.9197, "step": 8354 }, { "epoch": 1.51, "learning_rate": 7.3889089595375725e-06, "loss": 0.5303, "step": 8355 }, { "epoch": 1.51, "learning_rate": 7.386199421965318e-06, "loss": 0.3657, "step": 8356 }, { "epoch": 1.51, "learning_rate": 7.383489884393064e-06, "loss": 0.477, "step": 8357 }, { "epoch": 1.51, "learning_rate": 7.38078034682081e-06, "loss": 0.9179, "step": 8358 }, { "epoch": 1.51, "learning_rate": 7.378070809248555e-06, "loss": 0.5856, "step": 8359 }, { "epoch": 1.51, "learning_rate": 7.375361271676301e-06, "loss": 0.1363, "step": 8360 }, { "epoch": 1.51, "learning_rate": 7.372651734104046e-06, "loss": 0.3274, "step": 8361 }, { "epoch": 1.51, "learning_rate": 7.3699421965317915e-06, "loss": 1.0113, "step": 8362 }, { "epoch": 1.51, "learning_rate": 7.367232658959538e-06, "loss": 0.395, "step": 8363 }, { "epoch": 1.51, "learning_rate": 7.364523121387283e-06, "loss": 0.481, "step": 8364 }, { "epoch": 1.51, "learning_rate": 7.36181358381503e-06, "loss": 0.5759, "step": 8365 }, { "epoch": 1.51, "learning_rate": 7.359104046242775e-06, "loss": 0.8505, "step": 8366 }, { "epoch": 1.51, "learning_rate": 7.35639450867052e-06, "loss": 0.4956, "step": 8367 }, { "epoch": 1.51, "learning_rate": 7.353684971098266e-06, "loss": 0.9545, "step": 8368 }, { "epoch": 1.51, "learning_rate": 7.350975433526011e-06, "loss": 0.4995, "step": 8369 }, { "epoch": 1.51, "learning_rate": 7.3482658959537575e-06, "loss": 0.5949, "step": 8370 }, { "epoch": 1.51, "learning_rate": 7.345556358381503e-06, "loss": 0.3874, "step": 8371 }, { "epoch": 1.51, "learning_rate": 7.342846820809249e-06, "loss": 0.2883, "step": 8372 }, { "epoch": 1.51, "learning_rate": 7.340137283236995e-06, "loss": 0.4809, "step": 8373 }, { "epoch": 1.51, "learning_rate": 7.33742774566474e-06, "loss": 0.191, "step": 8374 }, { "epoch": 1.51, "learning_rate": 7.334718208092486e-06, "loss": 0.3411, "step": 8375 }, { "epoch": 1.51, "learning_rate": 7.332008670520231e-06, "loss": 0.5417, "step": 8376 }, { "epoch": 1.51, "learning_rate": 7.3292991329479765e-06, "loss": 0.704, "step": 8377 }, { "epoch": 1.51, "learning_rate": 7.3265895953757226e-06, "loss": 0.3039, "step": 8378 }, { "epoch": 1.51, "learning_rate": 7.323880057803468e-06, "loss": 0.3645, "step": 8379 }, { "epoch": 1.51, "learning_rate": 7.321170520231215e-06, "loss": 0.1745, "step": 8380 }, { "epoch": 1.51, "learning_rate": 7.31846098265896e-06, "loss": 0.4195, "step": 8381 }, { "epoch": 1.51, "learning_rate": 7.315751445086706e-06, "loss": 1.1417, "step": 8382 }, { "epoch": 1.51, "learning_rate": 7.313041907514451e-06, "loss": 0.6659, "step": 8383 }, { "epoch": 1.51, "learning_rate": 7.310332369942196e-06, "loss": 0.5716, "step": 8384 }, { "epoch": 1.51, "learning_rate": 7.3076228323699424e-06, "loss": 0.8884, "step": 8385 }, { "epoch": 1.51, "learning_rate": 7.304913294797688e-06, "loss": 0.2343, "step": 8386 }, { "epoch": 1.51, "learning_rate": 7.302203757225434e-06, "loss": 0.3431, "step": 8387 }, { "epoch": 1.52, "learning_rate": 7.29949421965318e-06, "loss": 0.6616, "step": 8388 }, { "epoch": 1.52, "learning_rate": 7.296784682080925e-06, "loss": 0.254, "step": 8389 }, { "epoch": 1.52, "learning_rate": 7.294075144508671e-06, "loss": 0.4059, "step": 8390 }, { "epoch": 1.52, "learning_rate": 7.291365606936416e-06, "loss": 0.6742, "step": 8391 }, { "epoch": 1.52, "learning_rate": 7.288656069364162e-06, "loss": 0.4488, "step": 8392 }, { "epoch": 1.52, "learning_rate": 7.2859465317919075e-06, "loss": 0.5991, "step": 8393 }, { "epoch": 1.52, "learning_rate": 7.283236994219653e-06, "loss": 0.5025, "step": 8394 }, { "epoch": 1.52, "learning_rate": 7.2805274566474e-06, "loss": 0.2295, "step": 8395 }, { "epoch": 1.52, "learning_rate": 7.277817919075145e-06, "loss": 0.6511, "step": 8396 }, { "epoch": 1.52, "learning_rate": 7.275108381502891e-06, "loss": 0.4475, "step": 8397 }, { "epoch": 1.52, "learning_rate": 7.272398843930636e-06, "loss": 1.297, "step": 8398 }, { "epoch": 1.52, "learning_rate": 7.269689306358381e-06, "loss": 0.4375, "step": 8399 }, { "epoch": 1.52, "learning_rate": 7.266979768786127e-06, "loss": 0.3334, "step": 8400 }, { "epoch": 1.52, "learning_rate": 7.264270231213873e-06, "loss": 0.5546, "step": 8401 }, { "epoch": 1.52, "learning_rate": 7.261560693641619e-06, "loss": 0.7542, "step": 8402 }, { "epoch": 1.52, "learning_rate": 7.258851156069365e-06, "loss": 0.7429, "step": 8403 }, { "epoch": 1.52, "learning_rate": 7.25614161849711e-06, "loss": 0.2853, "step": 8404 }, { "epoch": 1.52, "learning_rate": 7.253432080924856e-06, "loss": 0.7545, "step": 8405 }, { "epoch": 1.52, "learning_rate": 7.250722543352601e-06, "loss": 0.6792, "step": 8406 }, { "epoch": 1.52, "learning_rate": 7.248013005780347e-06, "loss": 0.3334, "step": 8407 }, { "epoch": 1.52, "learning_rate": 7.2453034682080925e-06, "loss": 0.2681, "step": 8408 }, { "epoch": 1.52, "learning_rate": 7.242593930635838e-06, "loss": 0.6871, "step": 8409 }, { "epoch": 1.52, "learning_rate": 7.239884393063584e-06, "loss": 0.8317, "step": 8410 }, { "epoch": 1.52, "learning_rate": 7.23717485549133e-06, "loss": 0.5807, "step": 8411 }, { "epoch": 1.52, "learning_rate": 7.234465317919076e-06, "loss": 0.8275, "step": 8412 }, { "epoch": 1.52, "learning_rate": 7.231755780346821e-06, "loss": 0.536, "step": 8413 }, { "epoch": 1.52, "learning_rate": 7.229046242774566e-06, "loss": 0.321, "step": 8414 }, { "epoch": 1.52, "learning_rate": 7.226336705202312e-06, "loss": 0.3498, "step": 8415 }, { "epoch": 1.52, "learning_rate": 7.2236271676300576e-06, "loss": 0.3467, "step": 8416 }, { "epoch": 1.52, "learning_rate": 7.220917630057804e-06, "loss": 0.3814, "step": 8417 }, { "epoch": 1.52, "learning_rate": 7.218208092485549e-06, "loss": 0.4585, "step": 8418 }, { "epoch": 1.52, "learning_rate": 7.215498554913295e-06, "loss": 0.4961, "step": 8419 }, { "epoch": 1.52, "learning_rate": 7.212789017341041e-06, "loss": 0.3606, "step": 8420 }, { "epoch": 1.52, "learning_rate": 7.210079479768786e-06, "loss": 0.3747, "step": 8421 }, { "epoch": 1.52, "learning_rate": 7.207369942196532e-06, "loss": 0.3535, "step": 8422 }, { "epoch": 1.52, "learning_rate": 7.2046604046242774e-06, "loss": 0.4103, "step": 8423 }, { "epoch": 1.52, "learning_rate": 7.2019508670520235e-06, "loss": 0.275, "step": 8424 }, { "epoch": 1.52, "learning_rate": 7.199241329479769e-06, "loss": 0.2667, "step": 8425 }, { "epoch": 1.52, "learning_rate": 7.196531791907515e-06, "loss": 0.7313, "step": 8426 }, { "epoch": 1.52, "learning_rate": 7.193822254335261e-06, "loss": 0.9706, "step": 8427 }, { "epoch": 1.52, "learning_rate": 7.191112716763006e-06, "loss": 0.2393, "step": 8428 }, { "epoch": 1.52, "learning_rate": 7.188403179190752e-06, "loss": 0.4342, "step": 8429 }, { "epoch": 1.52, "learning_rate": 7.185693641618497e-06, "loss": 0.2171, "step": 8430 }, { "epoch": 1.52, "learning_rate": 7.1829841040462425e-06, "loss": 0.9138, "step": 8431 }, { "epoch": 1.52, "learning_rate": 7.180274566473989e-06, "loss": 0.6713, "step": 8432 }, { "epoch": 1.52, "learning_rate": 7.177565028901734e-06, "loss": 0.7975, "step": 8433 }, { "epoch": 1.52, "learning_rate": 7.174855491329481e-06, "loss": 0.4319, "step": 8434 }, { "epoch": 1.52, "learning_rate": 7.172145953757226e-06, "loss": 0.7056, "step": 8435 }, { "epoch": 1.52, "learning_rate": 7.169436416184971e-06, "loss": 0.4168, "step": 8436 }, { "epoch": 1.52, "learning_rate": 7.166726878612717e-06, "loss": 0.6657, "step": 8437 }, { "epoch": 1.52, "learning_rate": 7.164017341040462e-06, "loss": 0.527, "step": 8438 }, { "epoch": 1.52, "learning_rate": 7.1613078034682085e-06, "loss": 0.5817, "step": 8439 }, { "epoch": 1.52, "learning_rate": 7.158598265895954e-06, "loss": 0.3322, "step": 8440 }, { "epoch": 1.52, "learning_rate": 7.155888728323699e-06, "loss": 0.5216, "step": 8441 }, { "epoch": 1.52, "learning_rate": 7.153179190751446e-06, "loss": 0.4643, "step": 8442 }, { "epoch": 1.53, "learning_rate": 7.150469653179191e-06, "loss": 0.8395, "step": 8443 }, { "epoch": 1.53, "learning_rate": 7.147760115606937e-06, "loss": 0.4697, "step": 8444 }, { "epoch": 1.53, "learning_rate": 7.145050578034682e-06, "loss": 0.6223, "step": 8445 }, { "epoch": 1.53, "learning_rate": 7.1423410404624275e-06, "loss": 0.551, "step": 8446 }, { "epoch": 1.53, "learning_rate": 7.1396315028901735e-06, "loss": 0.6318, "step": 8447 }, { "epoch": 1.53, "learning_rate": 7.136921965317919e-06, "loss": 1.0423, "step": 8448 }, { "epoch": 1.53, "learning_rate": 7.134212427745666e-06, "loss": 0.2116, "step": 8449 }, { "epoch": 1.53, "learning_rate": 7.131502890173411e-06, "loss": 0.4217, "step": 8450 }, { "epoch": 1.53, "learning_rate": 7.128793352601156e-06, "loss": 0.2979, "step": 8451 }, { "epoch": 1.53, "learning_rate": 7.126083815028902e-06, "loss": 0.597, "step": 8452 }, { "epoch": 1.53, "learning_rate": 7.123374277456647e-06, "loss": 0.4861, "step": 8453 }, { "epoch": 1.53, "learning_rate": 7.120664739884393e-06, "loss": 0.4596, "step": 8454 }, { "epoch": 1.53, "learning_rate": 7.117955202312139e-06, "loss": 0.2158, "step": 8455 }, { "epoch": 1.53, "learning_rate": 7.115245664739884e-06, "loss": 0.2306, "step": 8456 }, { "epoch": 1.53, "learning_rate": 7.112536127167631e-06, "loss": 0.7063, "step": 8457 }, { "epoch": 1.53, "learning_rate": 7.109826589595376e-06, "loss": 0.1347, "step": 8458 }, { "epoch": 1.53, "learning_rate": 7.107117052023122e-06, "loss": 0.7692, "step": 8459 }, { "epoch": 1.53, "learning_rate": 7.104407514450867e-06, "loss": 1.1899, "step": 8460 }, { "epoch": 1.53, "learning_rate": 7.1016979768786124e-06, "loss": 0.481, "step": 8461 }, { "epoch": 1.53, "learning_rate": 7.0989884393063585e-06, "loss": 0.4652, "step": 8462 }, { "epoch": 1.53, "learning_rate": 7.096278901734104e-06, "loss": 1.0678, "step": 8463 }, { "epoch": 1.53, "learning_rate": 7.09356936416185e-06, "loss": 0.9055, "step": 8464 }, { "epoch": 1.53, "learning_rate": 7.090859826589596e-06, "loss": 0.9421, "step": 8465 }, { "epoch": 1.53, "learning_rate": 7.088150289017342e-06, "loss": 0.6896, "step": 8466 }, { "epoch": 1.53, "learning_rate": 7.085440751445087e-06, "loss": 0.2326, "step": 8467 }, { "epoch": 1.53, "learning_rate": 7.082731213872832e-06, "loss": 0.4369, "step": 8468 }, { "epoch": 1.53, "learning_rate": 7.080021676300578e-06, "loss": 0.9191, "step": 8469 }, { "epoch": 1.53, "learning_rate": 7.077312138728324e-06, "loss": 0.7682, "step": 8470 }, { "epoch": 1.53, "learning_rate": 7.07460260115607e-06, "loss": 0.2411, "step": 8471 }, { "epoch": 1.53, "learning_rate": 7.071893063583815e-06, "loss": 0.8909, "step": 8472 }, { "epoch": 1.53, "learning_rate": 7.069183526011561e-06, "loss": 0.5615, "step": 8473 }, { "epoch": 1.53, "learning_rate": 7.066473988439307e-06, "loss": 0.4871, "step": 8474 }, { "epoch": 1.53, "learning_rate": 7.063764450867052e-06, "loss": 0.6006, "step": 8475 }, { "epoch": 1.53, "learning_rate": 7.061054913294798e-06, "loss": 0.3321, "step": 8476 }, { "epoch": 1.53, "learning_rate": 7.0583453757225435e-06, "loss": 0.6618, "step": 8477 }, { "epoch": 1.53, "learning_rate": 7.055635838150289e-06, "loss": 0.5604, "step": 8478 }, { "epoch": 1.53, "learning_rate": 7.052926300578035e-06, "loss": 0.8809, "step": 8479 }, { "epoch": 1.53, "learning_rate": 7.050216763005781e-06, "loss": 0.6313, "step": 8480 }, { "epoch": 1.53, "learning_rate": 7.047507225433527e-06, "loss": 0.4808, "step": 8481 }, { "epoch": 1.53, "learning_rate": 7.044797687861272e-06, "loss": 0.2872, "step": 8482 }, { "epoch": 1.53, "learning_rate": 7.042088150289017e-06, "loss": 0.5392, "step": 8483 }, { "epoch": 1.53, "learning_rate": 7.039378612716763e-06, "loss": 0.484, "step": 8484 }, { "epoch": 1.53, "learning_rate": 7.0366690751445085e-06, "loss": 0.6413, "step": 8485 }, { "epoch": 1.53, "learning_rate": 7.033959537572255e-06, "loss": 0.5208, "step": 8486 }, { "epoch": 1.53, "learning_rate": 7.03125e-06, "loss": 0.3987, "step": 8487 }, { "epoch": 1.53, "learning_rate": 7.028540462427746e-06, "loss": 0.3505, "step": 8488 }, { "epoch": 1.53, "learning_rate": 7.025830924855492e-06, "loss": 0.4602, "step": 8489 }, { "epoch": 1.53, "learning_rate": 7.023121387283237e-06, "loss": 0.3586, "step": 8490 }, { "epoch": 1.53, "learning_rate": 7.020411849710983e-06, "loss": 0.3745, "step": 8491 }, { "epoch": 1.53, "learning_rate": 7.017702312138728e-06, "loss": 0.6478, "step": 8492 }, { "epoch": 1.53, "learning_rate": 7.014992774566474e-06, "loss": 0.41, "step": 8493 }, { "epoch": 1.53, "learning_rate": 7.01228323699422e-06, "loss": 0.5561, "step": 8494 }, { "epoch": 1.53, "learning_rate": 7.009573699421965e-06, "loss": 0.4542, "step": 8495 }, { "epoch": 1.53, "learning_rate": 7.006864161849712e-06, "loss": 0.2566, "step": 8496 }, { "epoch": 1.53, "learning_rate": 7.004154624277457e-06, "loss": 0.3774, "step": 8497 }, { "epoch": 1.54, "learning_rate": 7.001445086705202e-06, "loss": 0.3429, "step": 8498 }, { "epoch": 1.54, "learning_rate": 6.998735549132948e-06, "loss": 0.5445, "step": 8499 }, { "epoch": 1.54, "learning_rate": 6.9960260115606935e-06, "loss": 0.5422, "step": 8500 }, { "epoch": 1.54, "eval_exact_match": 88.0794701986755, "eval_f1": 94.01284953052189, "step": 8500 }, { "epoch": 1.54, "learning_rate": 6.9933164739884396e-06, "loss": 0.3743, "step": 8501 }, { "epoch": 1.54, "learning_rate": 6.990606936416185e-06, "loss": 0.1858, "step": 8502 }, { "epoch": 1.54, "learning_rate": 6.987897398843931e-06, "loss": 0.6117, "step": 8503 }, { "epoch": 1.54, "learning_rate": 6.985187861271677e-06, "loss": 0.6155, "step": 8504 }, { "epoch": 1.54, "learning_rate": 6.982478323699422e-06, "loss": 1.0982, "step": 8505 }, { "epoch": 1.54, "learning_rate": 6.979768786127168e-06, "loss": 0.9688, "step": 8506 }, { "epoch": 1.54, "learning_rate": 6.977059248554913e-06, "loss": 0.1049, "step": 8507 }, { "epoch": 1.54, "learning_rate": 6.974349710982659e-06, "loss": 0.2755, "step": 8508 }, { "epoch": 1.54, "learning_rate": 6.971640173410405e-06, "loss": 0.4231, "step": 8509 }, { "epoch": 1.54, "learning_rate": 6.96893063583815e-06, "loss": 0.734, "step": 8510 }, { "epoch": 1.54, "learning_rate": 6.966221098265897e-06, "loss": 0.6517, "step": 8511 }, { "epoch": 1.54, "learning_rate": 6.963511560693642e-06, "loss": 0.1796, "step": 8512 }, { "epoch": 1.54, "learning_rate": 6.960802023121388e-06, "loss": 0.7014, "step": 8513 }, { "epoch": 1.54, "learning_rate": 6.958092485549133e-06, "loss": 0.6529, "step": 8514 }, { "epoch": 1.54, "learning_rate": 6.9553829479768785e-06, "loss": 0.4114, "step": 8515 }, { "epoch": 1.54, "learning_rate": 6.9526734104046245e-06, "loss": 0.497, "step": 8516 }, { "epoch": 1.54, "learning_rate": 6.94996387283237e-06, "loss": 0.3031, "step": 8517 }, { "epoch": 1.54, "learning_rate": 6.947254335260116e-06, "loss": 0.6512, "step": 8518 }, { "epoch": 1.54, "learning_rate": 6.944544797687862e-06, "loss": 0.4033, "step": 8519 }, { "epoch": 1.54, "learning_rate": 6.941835260115607e-06, "loss": 0.3937, "step": 8520 }, { "epoch": 1.54, "learning_rate": 6.939125722543353e-06, "loss": 0.5465, "step": 8521 }, { "epoch": 1.54, "learning_rate": 6.936416184971098e-06, "loss": 0.781, "step": 8522 }, { "epoch": 1.54, "learning_rate": 6.933706647398844e-06, "loss": 0.2393, "step": 8523 }, { "epoch": 1.54, "learning_rate": 6.93099710982659e-06, "loss": 0.5845, "step": 8524 }, { "epoch": 1.54, "learning_rate": 6.928287572254335e-06, "loss": 0.4496, "step": 8525 }, { "epoch": 1.54, "learning_rate": 6.925578034682081e-06, "loss": 0.4682, "step": 8526 }, { "epoch": 1.54, "learning_rate": 6.922868497109827e-06, "loss": 0.5123, "step": 8527 }, { "epoch": 1.54, "learning_rate": 6.920158959537573e-06, "loss": 0.4006, "step": 8528 }, { "epoch": 1.54, "learning_rate": 6.917449421965318e-06, "loss": 1.105, "step": 8529 }, { "epoch": 1.54, "learning_rate": 6.914739884393063e-06, "loss": 0.8452, "step": 8530 }, { "epoch": 1.54, "learning_rate": 6.9120303468208095e-06, "loss": 0.8589, "step": 8531 }, { "epoch": 1.54, "learning_rate": 6.909320809248555e-06, "loss": 0.5708, "step": 8532 }, { "epoch": 1.54, "learning_rate": 6.906611271676301e-06, "loss": 0.2112, "step": 8533 }, { "epoch": 1.54, "learning_rate": 6.903901734104047e-06, "loss": 0.2378, "step": 8534 }, { "epoch": 1.54, "learning_rate": 6.901192196531792e-06, "loss": 0.3643, "step": 8535 }, { "epoch": 1.54, "learning_rate": 6.898482658959538e-06, "loss": 0.2881, "step": 8536 }, { "epoch": 1.54, "learning_rate": 6.895773121387283e-06, "loss": 0.2697, "step": 8537 }, { "epoch": 1.54, "learning_rate": 6.893063583815029e-06, "loss": 0.4114, "step": 8538 }, { "epoch": 1.54, "learning_rate": 6.8903540462427746e-06, "loss": 1.3026, "step": 8539 }, { "epoch": 1.54, "learning_rate": 6.88764450867052e-06, "loss": 0.2267, "step": 8540 }, { "epoch": 1.54, "learning_rate": 6.884934971098266e-06, "loss": 0.696, "step": 8541 }, { "epoch": 1.54, "learning_rate": 6.882225433526012e-06, "loss": 0.2627, "step": 8542 }, { "epoch": 1.54, "learning_rate": 6.879515895953758e-06, "loss": 0.4765, "step": 8543 }, { "epoch": 1.54, "learning_rate": 6.876806358381503e-06, "loss": 0.3784, "step": 8544 }, { "epoch": 1.54, "learning_rate": 6.874096820809248e-06, "loss": 0.4544, "step": 8545 }, { "epoch": 1.54, "learning_rate": 6.8713872832369944e-06, "loss": 0.8966, "step": 8546 }, { "epoch": 1.54, "learning_rate": 6.86867774566474e-06, "loss": 0.3616, "step": 8547 }, { "epoch": 1.54, "learning_rate": 6.865968208092486e-06, "loss": 0.4271, "step": 8548 }, { "epoch": 1.54, "learning_rate": 6.863258670520231e-06, "loss": 0.4544, "step": 8549 }, { "epoch": 1.54, "learning_rate": 6.860549132947977e-06, "loss": 0.5132, "step": 8550 }, { "epoch": 1.54, "learning_rate": 6.857839595375723e-06, "loss": 0.3604, "step": 8551 }, { "epoch": 1.54, "learning_rate": 6.855130057803468e-06, "loss": 0.3369, "step": 8552 }, { "epoch": 1.54, "learning_rate": 6.852420520231214e-06, "loss": 0.4185, "step": 8553 }, { "epoch": 1.55, "learning_rate": 6.8497109826589595e-06, "loss": 0.7471, "step": 8554 }, { "epoch": 1.55, "learning_rate": 6.8470014450867056e-06, "loss": 0.832, "step": 8555 }, { "epoch": 1.55, "learning_rate": 6.844291907514451e-06, "loss": 0.9203, "step": 8556 }, { "epoch": 1.55, "learning_rate": 6.841582369942197e-06, "loss": 0.7401, "step": 8557 }, { "epoch": 1.55, "learning_rate": 6.838872832369943e-06, "loss": 0.3859, "step": 8558 }, { "epoch": 1.55, "learning_rate": 6.836163294797688e-06, "loss": 0.7949, "step": 8559 }, { "epoch": 1.55, "learning_rate": 6.833453757225434e-06, "loss": 0.6175, "step": 8560 }, { "epoch": 1.55, "learning_rate": 6.830744219653179e-06, "loss": 0.5166, "step": 8561 }, { "epoch": 1.55, "learning_rate": 6.828034682080925e-06, "loss": 0.3307, "step": 8562 }, { "epoch": 1.55, "learning_rate": 6.825325144508671e-06, "loss": 0.5209, "step": 8563 }, { "epoch": 1.55, "learning_rate": 6.822615606936416e-06, "loss": 0.5916, "step": 8564 }, { "epoch": 1.55, "learning_rate": 6.819906069364163e-06, "loss": 0.4111, "step": 8565 }, { "epoch": 1.55, "learning_rate": 6.817196531791908e-06, "loss": 0.437, "step": 8566 }, { "epoch": 1.55, "learning_rate": 6.814486994219653e-06, "loss": 0.2711, "step": 8567 }, { "epoch": 1.55, "learning_rate": 6.811777456647399e-06, "loss": 0.579, "step": 8568 }, { "epoch": 1.55, "learning_rate": 6.8090679190751445e-06, "loss": 0.4311, "step": 8569 }, { "epoch": 1.55, "learning_rate": 6.8063583815028905e-06, "loss": 0.9739, "step": 8570 }, { "epoch": 1.55, "learning_rate": 6.803648843930636e-06, "loss": 0.2473, "step": 8571 }, { "epoch": 1.55, "learning_rate": 6.800939306358381e-06, "loss": 0.8711, "step": 8572 }, { "epoch": 1.55, "learning_rate": 6.798229768786128e-06, "loss": 0.8725, "step": 8573 }, { "epoch": 1.55, "learning_rate": 6.795520231213873e-06, "loss": 0.9395, "step": 8574 }, { "epoch": 1.55, "learning_rate": 6.792810693641619e-06, "loss": 0.2684, "step": 8575 }, { "epoch": 1.55, "learning_rate": 6.790101156069364e-06, "loss": 0.6392, "step": 8576 }, { "epoch": 1.55, "learning_rate": 6.7873916184971096e-06, "loss": 0.7963, "step": 8577 }, { "epoch": 1.55, "learning_rate": 6.784682080924856e-06, "loss": 0.6548, "step": 8578 }, { "epoch": 1.55, "learning_rate": 6.781972543352601e-06, "loss": 0.4313, "step": 8579 }, { "epoch": 1.55, "learning_rate": 6.779263005780347e-06, "loss": 0.6557, "step": 8580 }, { "epoch": 1.55, "learning_rate": 6.776553468208093e-06, "loss": 0.3017, "step": 8581 }, { "epoch": 1.55, "learning_rate": 6.773843930635838e-06, "loss": 0.2249, "step": 8582 }, { "epoch": 1.55, "learning_rate": 6.771134393063584e-06, "loss": 0.1765, "step": 8583 }, { "epoch": 1.55, "learning_rate": 6.7684248554913294e-06, "loss": 0.3686, "step": 8584 }, { "epoch": 1.55, "learning_rate": 6.7657153179190755e-06, "loss": 0.3882, "step": 8585 }, { "epoch": 1.55, "learning_rate": 6.763005780346821e-06, "loss": 0.7299, "step": 8586 }, { "epoch": 1.55, "learning_rate": 6.760296242774566e-06, "loss": 0.5923, "step": 8587 }, { "epoch": 1.55, "learning_rate": 6.757586705202313e-06, "loss": 0.1976, "step": 8588 }, { "epoch": 1.55, "learning_rate": 6.754877167630058e-06, "loss": 0.4065, "step": 8589 }, { "epoch": 1.55, "learning_rate": 6.752167630057804e-06, "loss": 0.5001, "step": 8590 }, { "epoch": 1.55, "learning_rate": 6.749458092485549e-06, "loss": 0.1989, "step": 8591 }, { "epoch": 1.55, "learning_rate": 6.7467485549132945e-06, "loss": 0.2027, "step": 8592 }, { "epoch": 1.55, "learning_rate": 6.7440390173410406e-06, "loss": 0.238, "step": 8593 }, { "epoch": 1.55, "learning_rate": 6.741329479768786e-06, "loss": 0.3272, "step": 8594 }, { "epoch": 1.55, "learning_rate": 6.738619942196532e-06, "loss": 0.4595, "step": 8595 }, { "epoch": 1.55, "learning_rate": 6.735910404624278e-06, "loss": 0.7753, "step": 8596 }, { "epoch": 1.55, "learning_rate": 6.733200867052024e-06, "loss": 0.8786, "step": 8597 }, { "epoch": 1.55, "learning_rate": 6.730491329479769e-06, "loss": 0.9, "step": 8598 }, { "epoch": 1.55, "learning_rate": 6.727781791907514e-06, "loss": 0.4335, "step": 8599 }, { "epoch": 1.55, "learning_rate": 6.7250722543352604e-06, "loss": 0.3454, "step": 8600 }, { "epoch": 1.55, "learning_rate": 6.722362716763006e-06, "loss": 0.8749, "step": 8601 }, { "epoch": 1.55, "learning_rate": 6.719653179190752e-06, "loss": 0.4917, "step": 8602 }, { "epoch": 1.55, "learning_rate": 6.716943641618497e-06, "loss": 0.5186, "step": 8603 }, { "epoch": 1.55, "learning_rate": 6.714234104046243e-06, "loss": 0.4351, "step": 8604 }, { "epoch": 1.55, "learning_rate": 6.711524566473989e-06, "loss": 0.5952, "step": 8605 }, { "epoch": 1.55, "learning_rate": 6.708815028901734e-06, "loss": 0.5193, "step": 8606 }, { "epoch": 1.55, "learning_rate": 6.70610549132948e-06, "loss": 0.2637, "step": 8607 }, { "epoch": 1.55, "learning_rate": 6.7033959537572255e-06, "loss": 0.1388, "step": 8608 }, { "epoch": 1.56, "learning_rate": 6.700686416184971e-06, "loss": 0.2318, "step": 8609 }, { "epoch": 1.56, "learning_rate": 6.697976878612717e-06, "loss": 0.8043, "step": 8610 }, { "epoch": 1.56, "learning_rate": 6.695267341040463e-06, "loss": 0.2731, "step": 8611 }, { "epoch": 1.56, "learning_rate": 6.692557803468209e-06, "loss": 0.5049, "step": 8612 }, { "epoch": 1.56, "learning_rate": 6.689848265895954e-06, "loss": 1.055, "step": 8613 }, { "epoch": 1.56, "learning_rate": 6.687138728323699e-06, "loss": 0.4999, "step": 8614 }, { "epoch": 1.56, "learning_rate": 6.684429190751445e-06, "loss": 0.9606, "step": 8615 }, { "epoch": 1.56, "learning_rate": 6.681719653179191e-06, "loss": 0.4828, "step": 8616 }, { "epoch": 1.56, "learning_rate": 6.679010115606937e-06, "loss": 0.4149, "step": 8617 }, { "epoch": 1.56, "learning_rate": 6.676300578034682e-06, "loss": 0.2011, "step": 8618 }, { "epoch": 1.56, "learning_rate": 6.673591040462428e-06, "loss": 0.4988, "step": 8619 }, { "epoch": 1.56, "learning_rate": 6.670881502890174e-06, "loss": 0.4921, "step": 8620 }, { "epoch": 1.56, "learning_rate": 6.668171965317919e-06, "loss": 0.3425, "step": 8621 }, { "epoch": 1.56, "learning_rate": 6.665462427745665e-06, "loss": 0.8187, "step": 8622 }, { "epoch": 1.56, "learning_rate": 6.6627528901734105e-06, "loss": 0.7339, "step": 8623 }, { "epoch": 1.56, "learning_rate": 6.660043352601156e-06, "loss": 0.3239, "step": 8624 }, { "epoch": 1.56, "learning_rate": 6.657333815028902e-06, "loss": 0.9515, "step": 8625 }, { "epoch": 1.56, "learning_rate": 6.654624277456647e-06, "loss": 0.3845, "step": 8626 }, { "epoch": 1.56, "learning_rate": 6.651914739884394e-06, "loss": 0.4726, "step": 8627 }, { "epoch": 1.56, "learning_rate": 6.649205202312139e-06, "loss": 0.5165, "step": 8628 }, { "epoch": 1.56, "learning_rate": 6.646495664739884e-06, "loss": 0.5476, "step": 8629 }, { "epoch": 1.56, "learning_rate": 6.64378612716763e-06, "loss": 0.6092, "step": 8630 }, { "epoch": 1.56, "learning_rate": 6.6410765895953756e-06, "loss": 0.6835, "step": 8631 }, { "epoch": 1.56, "learning_rate": 6.638367052023122e-06, "loss": 0.4631, "step": 8632 }, { "epoch": 1.56, "learning_rate": 6.635657514450867e-06, "loss": 0.2539, "step": 8633 }, { "epoch": 1.56, "learning_rate": 6.632947976878613e-06, "loss": 0.297, "step": 8634 }, { "epoch": 1.56, "learning_rate": 6.630238439306359e-06, "loss": 0.3272, "step": 8635 }, { "epoch": 1.56, "learning_rate": 6.627528901734104e-06, "loss": 0.2636, "step": 8636 }, { "epoch": 1.56, "learning_rate": 6.62481936416185e-06, "loss": 0.5811, "step": 8637 }, { "epoch": 1.56, "learning_rate": 6.6221098265895954e-06, "loss": 0.7676, "step": 8638 }, { "epoch": 1.56, "learning_rate": 6.6194002890173415e-06, "loss": 0.9376, "step": 8639 }, { "epoch": 1.56, "learning_rate": 6.616690751445087e-06, "loss": 0.5734, "step": 8640 }, { "epoch": 1.56, "learning_rate": 6.613981213872832e-06, "loss": 0.4792, "step": 8641 }, { "epoch": 1.56, "learning_rate": 6.611271676300579e-06, "loss": 0.3335, "step": 8642 }, { "epoch": 1.56, "learning_rate": 6.608562138728324e-06, "loss": 0.3044, "step": 8643 }, { "epoch": 1.56, "learning_rate": 6.60585260115607e-06, "loss": 0.6428, "step": 8644 }, { "epoch": 1.56, "learning_rate": 6.603143063583815e-06, "loss": 0.3982, "step": 8645 }, { "epoch": 1.56, "learning_rate": 6.6004335260115605e-06, "loss": 0.6309, "step": 8646 }, { "epoch": 1.56, "learning_rate": 6.597723988439307e-06, "loss": 0.2798, "step": 8647 }, { "epoch": 1.56, "learning_rate": 6.595014450867052e-06, "loss": 0.6357, "step": 8648 }, { "epoch": 1.56, "learning_rate": 6.592304913294798e-06, "loss": 0.8194, "step": 8649 }, { "epoch": 1.56, "learning_rate": 6.589595375722544e-06, "loss": 0.4603, "step": 8650 }, { "epoch": 1.56, "learning_rate": 6.586885838150289e-06, "loss": 0.3104, "step": 8651 }, { "epoch": 1.56, "learning_rate": 6.584176300578035e-06, "loss": 0.7079, "step": 8652 }, { "epoch": 1.56, "learning_rate": 6.58146676300578e-06, "loss": 0.5666, "step": 8653 }, { "epoch": 1.56, "learning_rate": 6.5787572254335265e-06, "loss": 0.4603, "step": 8654 }, { "epoch": 1.56, "learning_rate": 6.576047687861272e-06, "loss": 0.2374, "step": 8655 }, { "epoch": 1.56, "learning_rate": 6.573338150289017e-06, "loss": 0.29, "step": 8656 }, { "epoch": 1.56, "learning_rate": 6.570628612716763e-06, "loss": 0.9968, "step": 8657 }, { "epoch": 1.56, "learning_rate": 6.567919075144509e-06, "loss": 0.3941, "step": 8658 }, { "epoch": 1.56, "learning_rate": 6.565209537572255e-06, "loss": 1.1785, "step": 8659 }, { "epoch": 1.56, "learning_rate": 6.5625e-06, "loss": 0.4431, "step": 8660 }, { "epoch": 1.56, "learning_rate": 6.5597904624277455e-06, "loss": 0.2686, "step": 8661 }, { "epoch": 1.56, "learning_rate": 6.5570809248554915e-06, "loss": 1.2905, "step": 8662 }, { "epoch": 1.56, "learning_rate": 6.554371387283237e-06, "loss": 0.4134, "step": 8663 }, { "epoch": 1.57, "learning_rate": 6.551661849710983e-06, "loss": 0.7873, "step": 8664 }, { "epoch": 1.57, "learning_rate": 6.548952312138729e-06, "loss": 0.3388, "step": 8665 }, { "epoch": 1.57, "learning_rate": 6.546242774566474e-06, "loss": 0.6833, "step": 8666 }, { "epoch": 1.57, "learning_rate": 6.54353323699422e-06, "loss": 0.5464, "step": 8667 }, { "epoch": 1.57, "learning_rate": 6.540823699421965e-06, "loss": 0.3758, "step": 8668 }, { "epoch": 1.57, "learning_rate": 6.538114161849711e-06, "loss": 0.6756, "step": 8669 }, { "epoch": 1.57, "learning_rate": 6.535404624277457e-06, "loss": 0.2089, "step": 8670 }, { "epoch": 1.57, "learning_rate": 6.532695086705202e-06, "loss": 0.1616, "step": 8671 }, { "epoch": 1.57, "learning_rate": 6.529985549132948e-06, "loss": 0.3938, "step": 8672 }, { "epoch": 1.57, "learning_rate": 6.527276011560694e-06, "loss": 0.4784, "step": 8673 }, { "epoch": 1.57, "learning_rate": 6.52456647398844e-06, "loss": 0.5219, "step": 8674 }, { "epoch": 1.57, "learning_rate": 6.521856936416185e-06, "loss": 0.4215, "step": 8675 }, { "epoch": 1.57, "learning_rate": 6.5191473988439304e-06, "loss": 0.2444, "step": 8676 }, { "epoch": 1.57, "learning_rate": 6.5164378612716765e-06, "loss": 0.8862, "step": 8677 }, { "epoch": 1.57, "learning_rate": 6.513728323699422e-06, "loss": 0.5545, "step": 8678 }, { "epoch": 1.57, "learning_rate": 6.511018786127168e-06, "loss": 0.164, "step": 8679 }, { "epoch": 1.57, "learning_rate": 6.508309248554913e-06, "loss": 0.3659, "step": 8680 }, { "epoch": 1.57, "learning_rate": 6.505599710982659e-06, "loss": 0.7601, "step": 8681 }, { "epoch": 1.57, "learning_rate": 6.502890173410405e-06, "loss": 0.3936, "step": 8682 }, { "epoch": 1.57, "learning_rate": 6.50018063583815e-06, "loss": 0.375, "step": 8683 }, { "epoch": 1.57, "learning_rate": 6.497471098265896e-06, "loss": 0.7878, "step": 8684 }, { "epoch": 1.57, "learning_rate": 6.494761560693642e-06, "loss": 0.4562, "step": 8685 }, { "epoch": 1.57, "learning_rate": 6.492052023121388e-06, "loss": 1.2473, "step": 8686 }, { "epoch": 1.57, "learning_rate": 6.489342485549133e-06, "loss": 0.6831, "step": 8687 }, { "epoch": 1.57, "learning_rate": 6.486632947976879e-06, "loss": 0.3182, "step": 8688 }, { "epoch": 1.57, "learning_rate": 6.483923410404625e-06, "loss": 0.357, "step": 8689 }, { "epoch": 1.57, "learning_rate": 6.48121387283237e-06, "loss": 0.8255, "step": 8690 }, { "epoch": 1.57, "learning_rate": 6.478504335260116e-06, "loss": 0.5898, "step": 8691 }, { "epoch": 1.57, "learning_rate": 6.4757947976878615e-06, "loss": 0.5571, "step": 8692 }, { "epoch": 1.57, "learning_rate": 6.473085260115607e-06, "loss": 0.5342, "step": 8693 }, { "epoch": 1.57, "learning_rate": 6.470375722543353e-06, "loss": 0.3692, "step": 8694 }, { "epoch": 1.57, "learning_rate": 6.467666184971098e-06, "loss": 0.2242, "step": 8695 }, { "epoch": 1.57, "learning_rate": 6.464956647398845e-06, "loss": 0.6305, "step": 8696 }, { "epoch": 1.57, "learning_rate": 6.46224710982659e-06, "loss": 0.2559, "step": 8697 }, { "epoch": 1.57, "learning_rate": 6.459537572254335e-06, "loss": 0.2849, "step": 8698 }, { "epoch": 1.57, "learning_rate": 6.456828034682081e-06, "loss": 0.6751, "step": 8699 }, { "epoch": 1.57, "learning_rate": 6.4541184971098265e-06, "loss": 0.4878, "step": 8700 }, { "epoch": 1.57, "learning_rate": 6.451408959537573e-06, "loss": 0.4852, "step": 8701 }, { "epoch": 1.57, "learning_rate": 6.448699421965318e-06, "loss": 0.4674, "step": 8702 }, { "epoch": 1.57, "learning_rate": 6.445989884393063e-06, "loss": 0.3967, "step": 8703 }, { "epoch": 1.57, "learning_rate": 6.44328034682081e-06, "loss": 0.7552, "step": 8704 }, { "epoch": 1.57, "learning_rate": 6.440570809248555e-06, "loss": 0.3253, "step": 8705 }, { "epoch": 1.57, "learning_rate": 6.437861271676301e-06, "loss": 0.3353, "step": 8706 }, { "epoch": 1.57, "learning_rate": 6.435151734104046e-06, "loss": 0.4248, "step": 8707 }, { "epoch": 1.57, "learning_rate": 6.432442196531792e-06, "loss": 0.2351, "step": 8708 }, { "epoch": 1.57, "learning_rate": 6.429732658959538e-06, "loss": 0.2737, "step": 8709 }, { "epoch": 1.57, "learning_rate": 6.427023121387283e-06, "loss": 0.3173, "step": 8710 }, { "epoch": 1.57, "learning_rate": 6.424313583815029e-06, "loss": 0.5722, "step": 8711 }, { "epoch": 1.57, "learning_rate": 6.421604046242775e-06, "loss": 0.6984, "step": 8712 }, { "epoch": 1.57, "learning_rate": 6.41889450867052e-06, "loss": 0.5157, "step": 8713 }, { "epoch": 1.57, "learning_rate": 6.416184971098266e-06, "loss": 0.2034, "step": 8714 }, { "epoch": 1.57, "learning_rate": 6.4134754335260115e-06, "loss": 0.6528, "step": 8715 }, { "epoch": 1.57, "learning_rate": 6.4107658959537576e-06, "loss": 0.97, "step": 8716 }, { "epoch": 1.57, "learning_rate": 6.408056358381503e-06, "loss": 0.2673, "step": 8717 }, { "epoch": 1.57, "learning_rate": 6.405346820809248e-06, "loss": 0.6093, "step": 8718 }, { "epoch": 1.57, "learning_rate": 6.402637283236995e-06, "loss": 0.5792, "step": 8719 }, { "epoch": 1.58, "learning_rate": 6.39992774566474e-06, "loss": 0.7053, "step": 8720 }, { "epoch": 1.58, "learning_rate": 6.397218208092486e-06, "loss": 0.4866, "step": 8721 }, { "epoch": 1.58, "learning_rate": 6.394508670520231e-06, "loss": 0.5547, "step": 8722 }, { "epoch": 1.58, "learning_rate": 6.391799132947977e-06, "loss": 0.4986, "step": 8723 }, { "epoch": 1.58, "learning_rate": 6.389089595375723e-06, "loss": 0.3582, "step": 8724 }, { "epoch": 1.58, "learning_rate": 6.386380057803468e-06, "loss": 0.6061, "step": 8725 }, { "epoch": 1.58, "learning_rate": 6.383670520231214e-06, "loss": 0.5852, "step": 8726 }, { "epoch": 1.58, "learning_rate": 6.38096098265896e-06, "loss": 0.4359, "step": 8727 }, { "epoch": 1.58, "learning_rate": 6.378251445086706e-06, "loss": 0.5466, "step": 8728 }, { "epoch": 1.58, "learning_rate": 6.375541907514451e-06, "loss": 0.335, "step": 8729 }, { "epoch": 1.58, "learning_rate": 6.3728323699421965e-06, "loss": 0.5588, "step": 8730 }, { "epoch": 1.58, "learning_rate": 6.3701228323699425e-06, "loss": 0.6976, "step": 8731 }, { "epoch": 1.58, "learning_rate": 6.367413294797688e-06, "loss": 0.6806, "step": 8732 }, { "epoch": 1.58, "learning_rate": 6.364703757225434e-06, "loss": 0.6256, "step": 8733 }, { "epoch": 1.58, "learning_rate": 6.361994219653179e-06, "loss": 0.1987, "step": 8734 }, { "epoch": 1.58, "learning_rate": 6.359284682080925e-06, "loss": 0.9926, "step": 8735 }, { "epoch": 1.58, "learning_rate": 6.356575144508671e-06, "loss": 0.4044, "step": 8736 }, { "epoch": 1.58, "learning_rate": 6.353865606936416e-06, "loss": 0.1861, "step": 8737 }, { "epoch": 1.58, "learning_rate": 6.351156069364162e-06, "loss": 0.1314, "step": 8738 }, { "epoch": 1.58, "learning_rate": 6.348446531791908e-06, "loss": 0.7321, "step": 8739 }, { "epoch": 1.58, "learning_rate": 6.345736994219653e-06, "loss": 0.5901, "step": 8740 }, { "epoch": 1.58, "learning_rate": 6.343027456647399e-06, "loss": 0.8791, "step": 8741 }, { "epoch": 1.58, "learning_rate": 6.340317919075145e-06, "loss": 0.3714, "step": 8742 }, { "epoch": 1.58, "learning_rate": 6.337608381502891e-06, "loss": 0.5096, "step": 8743 }, { "epoch": 1.58, "learning_rate": 6.334898843930636e-06, "loss": 0.3709, "step": 8744 }, { "epoch": 1.58, "learning_rate": 6.332189306358381e-06, "loss": 0.8016, "step": 8745 }, { "epoch": 1.58, "learning_rate": 6.3294797687861275e-06, "loss": 0.8991, "step": 8746 }, { "epoch": 1.58, "learning_rate": 6.326770231213873e-06, "loss": 0.3463, "step": 8747 }, { "epoch": 1.58, "learning_rate": 6.324060693641619e-06, "loss": 0.9068, "step": 8748 }, { "epoch": 1.58, "learning_rate": 6.321351156069364e-06, "loss": 0.181, "step": 8749 }, { "epoch": 1.58, "learning_rate": 6.31864161849711e-06, "loss": 0.8654, "step": 8750 }, { "epoch": 1.58, "learning_rate": 6.315932080924856e-06, "loss": 0.6652, "step": 8751 }, { "epoch": 1.58, "learning_rate": 6.313222543352601e-06, "loss": 0.9652, "step": 8752 }, { "epoch": 1.58, "learning_rate": 6.310513005780347e-06, "loss": 0.2961, "step": 8753 }, { "epoch": 1.58, "learning_rate": 6.3078034682080926e-06, "loss": 0.2062, "step": 8754 }, { "epoch": 1.58, "learning_rate": 6.305093930635838e-06, "loss": 0.678, "step": 8755 }, { "epoch": 1.58, "learning_rate": 6.302384393063584e-06, "loss": 0.269, "step": 8756 }, { "epoch": 1.58, "learning_rate": 6.299674855491329e-06, "loss": 0.6937, "step": 8757 }, { "epoch": 1.58, "learning_rate": 6.296965317919076e-06, "loss": 0.7387, "step": 8758 }, { "epoch": 1.58, "learning_rate": 6.294255780346821e-06, "loss": 0.5178, "step": 8759 }, { "epoch": 1.58, "learning_rate": 6.291546242774566e-06, "loss": 0.7416, "step": 8760 }, { "epoch": 1.58, "learning_rate": 6.2888367052023124e-06, "loss": 0.5869, "step": 8761 }, { "epoch": 1.58, "learning_rate": 6.286127167630058e-06, "loss": 0.6838, "step": 8762 }, { "epoch": 1.58, "learning_rate": 6.283417630057804e-06, "loss": 0.3226, "step": 8763 }, { "epoch": 1.58, "learning_rate": 6.280708092485549e-06, "loss": 0.4162, "step": 8764 }, { "epoch": 1.58, "learning_rate": 6.277998554913295e-06, "loss": 0.6068, "step": 8765 }, { "epoch": 1.58, "learning_rate": 6.275289017341041e-06, "loss": 0.552, "step": 8766 }, { "epoch": 1.58, "learning_rate": 6.272579479768786e-06, "loss": 0.8707, "step": 8767 }, { "epoch": 1.58, "learning_rate": 6.269869942196532e-06, "loss": 0.1307, "step": 8768 }, { "epoch": 1.58, "learning_rate": 6.2671604046242775e-06, "loss": 0.5137, "step": 8769 }, { "epoch": 1.58, "learning_rate": 6.2644508670520236e-06, "loss": 0.4189, "step": 8770 }, { "epoch": 1.58, "learning_rate": 6.261741329479769e-06, "loss": 0.8526, "step": 8771 }, { "epoch": 1.58, "learning_rate": 6.259031791907514e-06, "loss": 1.2229, "step": 8772 }, { "epoch": 1.58, "learning_rate": 6.256322254335261e-06, "loss": 0.6118, "step": 8773 }, { "epoch": 1.58, "learning_rate": 6.253612716763006e-06, "loss": 0.6838, "step": 8774 }, { "epoch": 1.59, "learning_rate": 6.250903179190752e-06, "loss": 0.859, "step": 8775 }, { "epoch": 1.59, "learning_rate": 6.248193641618497e-06, "loss": 0.6882, "step": 8776 }, { "epoch": 1.59, "learning_rate": 6.245484104046243e-06, "loss": 0.5253, "step": 8777 }, { "epoch": 1.59, "learning_rate": 6.242774566473989e-06, "loss": 0.2856, "step": 8778 }, { "epoch": 1.59, "learning_rate": 6.240065028901734e-06, "loss": 0.6874, "step": 8779 }, { "epoch": 1.59, "learning_rate": 6.23735549132948e-06, "loss": 0.2576, "step": 8780 }, { "epoch": 1.59, "learning_rate": 6.234645953757226e-06, "loss": 0.6701, "step": 8781 }, { "epoch": 1.59, "learning_rate": 6.231936416184971e-06, "loss": 0.6652, "step": 8782 }, { "epoch": 1.59, "learning_rate": 6.229226878612717e-06, "loss": 0.6099, "step": 8783 }, { "epoch": 1.59, "learning_rate": 6.2265173410404625e-06, "loss": 0.9514, "step": 8784 }, { "epoch": 1.59, "learning_rate": 6.2238078034682085e-06, "loss": 0.289, "step": 8785 }, { "epoch": 1.59, "learning_rate": 6.221098265895954e-06, "loss": 0.7196, "step": 8786 }, { "epoch": 1.59, "learning_rate": 6.218388728323699e-06, "loss": 0.1048, "step": 8787 }, { "epoch": 1.59, "learning_rate": 6.215679190751445e-06, "loss": 0.3994, "step": 8788 }, { "epoch": 1.59, "learning_rate": 6.212969653179191e-06, "loss": 0.4898, "step": 8789 }, { "epoch": 1.59, "learning_rate": 6.210260115606937e-06, "loss": 0.5786, "step": 8790 }, { "epoch": 1.59, "learning_rate": 6.207550578034682e-06, "loss": 0.6028, "step": 8791 }, { "epoch": 1.59, "learning_rate": 6.2048410404624276e-06, "loss": 0.2557, "step": 8792 }, { "epoch": 1.59, "learning_rate": 6.202131502890174e-06, "loss": 0.5025, "step": 8793 }, { "epoch": 1.59, "learning_rate": 6.199421965317919e-06, "loss": 0.5945, "step": 8794 }, { "epoch": 1.59, "learning_rate": 6.196712427745665e-06, "loss": 0.8613, "step": 8795 }, { "epoch": 1.59, "learning_rate": 6.194002890173411e-06, "loss": 0.3978, "step": 8796 }, { "epoch": 1.59, "learning_rate": 6.191293352601156e-06, "loss": 1.0921, "step": 8797 }, { "epoch": 1.59, "learning_rate": 6.188583815028902e-06, "loss": 0.4347, "step": 8798 }, { "epoch": 1.59, "learning_rate": 6.1858742774566474e-06, "loss": 0.5588, "step": 8799 }, { "epoch": 1.59, "learning_rate": 6.1831647398843935e-06, "loss": 0.2745, "step": 8800 }, { "epoch": 1.59, "learning_rate": 6.180455202312139e-06, "loss": 1.0213, "step": 8801 }, { "epoch": 1.59, "learning_rate": 6.177745664739884e-06, "loss": 0.409, "step": 8802 }, { "epoch": 1.59, "learning_rate": 6.17503612716763e-06, "loss": 0.4203, "step": 8803 }, { "epoch": 1.59, "learning_rate": 6.172326589595376e-06, "loss": 1.0527, "step": 8804 }, { "epoch": 1.59, "learning_rate": 6.169617052023122e-06, "loss": 0.748, "step": 8805 }, { "epoch": 1.59, "learning_rate": 6.166907514450867e-06, "loss": 0.6879, "step": 8806 }, { "epoch": 1.59, "learning_rate": 6.1641979768786125e-06, "loss": 0.2509, "step": 8807 }, { "epoch": 1.59, "learning_rate": 6.1614884393063586e-06, "loss": 0.525, "step": 8808 }, { "epoch": 1.59, "learning_rate": 6.158778901734104e-06, "loss": 0.948, "step": 8809 }, { "epoch": 1.59, "learning_rate": 6.15606936416185e-06, "loss": 0.7125, "step": 8810 }, { "epoch": 1.59, "learning_rate": 6.153359826589595e-06, "loss": 0.5383, "step": 8811 }, { "epoch": 1.59, "learning_rate": 6.150650289017342e-06, "loss": 0.4301, "step": 8812 }, { "epoch": 1.59, "learning_rate": 6.147940751445087e-06, "loss": 0.6463, "step": 8813 }, { "epoch": 1.59, "learning_rate": 6.145231213872832e-06, "loss": 0.3387, "step": 8814 }, { "epoch": 1.59, "learning_rate": 6.1425216763005784e-06, "loss": 0.3158, "step": 8815 }, { "epoch": 1.59, "learning_rate": 6.139812138728324e-06, "loss": 0.6056, "step": 8816 }, { "epoch": 1.59, "learning_rate": 6.13710260115607e-06, "loss": 0.522, "step": 8817 }, { "epoch": 1.59, "learning_rate": 6.134393063583815e-06, "loss": 0.885, "step": 8818 }, { "epoch": 1.59, "learning_rate": 6.131683526011561e-06, "loss": 0.5538, "step": 8819 }, { "epoch": 1.59, "learning_rate": 6.128973988439307e-06, "loss": 0.8083, "step": 8820 }, { "epoch": 1.59, "learning_rate": 6.126264450867052e-06, "loss": 0.3331, "step": 8821 }, { "epoch": 1.59, "learning_rate": 6.123554913294798e-06, "loss": 0.4394, "step": 8822 }, { "epoch": 1.59, "learning_rate": 6.1208453757225435e-06, "loss": 0.6431, "step": 8823 }, { "epoch": 1.59, "learning_rate": 6.118135838150289e-06, "loss": 0.233, "step": 8824 }, { "epoch": 1.59, "learning_rate": 6.115426300578035e-06, "loss": 0.9556, "step": 8825 }, { "epoch": 1.59, "learning_rate": 6.11271676300578e-06, "loss": 0.7195, "step": 8826 }, { "epoch": 1.59, "learning_rate": 6.110007225433527e-06, "loss": 0.3468, "step": 8827 }, { "epoch": 1.59, "learning_rate": 6.107297687861272e-06, "loss": 0.2745, "step": 8828 }, { "epoch": 1.59, "learning_rate": 6.104588150289017e-06, "loss": 0.7289, "step": 8829 }, { "epoch": 1.6, "learning_rate": 6.101878612716763e-06, "loss": 0.514, "step": 8830 }, { "epoch": 1.6, "learning_rate": 6.099169075144509e-06, "loss": 0.1473, "step": 8831 }, { "epoch": 1.6, "learning_rate": 6.096459537572255e-06, "loss": 0.246, "step": 8832 }, { "epoch": 1.6, "learning_rate": 6.09375e-06, "loss": 0.3633, "step": 8833 }, { "epoch": 1.6, "learning_rate": 6.091040462427745e-06, "loss": 0.5049, "step": 8834 }, { "epoch": 1.6, "learning_rate": 6.088330924855492e-06, "loss": 0.3813, "step": 8835 }, { "epoch": 1.6, "learning_rate": 6.085621387283237e-06, "loss": 0.7555, "step": 8836 }, { "epoch": 1.6, "learning_rate": 6.082911849710983e-06, "loss": 0.5528, "step": 8837 }, { "epoch": 1.6, "learning_rate": 6.0802023121387285e-06, "loss": 1.0962, "step": 8838 }, { "epoch": 1.6, "learning_rate": 6.077492774566474e-06, "loss": 1.0585, "step": 8839 }, { "epoch": 1.6, "learning_rate": 6.07478323699422e-06, "loss": 0.677, "step": 8840 }, { "epoch": 1.6, "learning_rate": 6.072073699421965e-06, "loss": 0.3595, "step": 8841 }, { "epoch": 1.6, "learning_rate": 6.069364161849711e-06, "loss": 0.3489, "step": 8842 }, { "epoch": 1.6, "learning_rate": 6.066654624277457e-06, "loss": 0.7122, "step": 8843 }, { "epoch": 1.6, "learning_rate": 6.063945086705202e-06, "loss": 0.6963, "step": 8844 }, { "epoch": 1.6, "learning_rate": 6.061235549132948e-06, "loss": 0.4179, "step": 8845 }, { "epoch": 1.6, "learning_rate": 6.0585260115606936e-06, "loss": 0.4738, "step": 8846 }, { "epoch": 1.6, "learning_rate": 6.05581647398844e-06, "loss": 0.4398, "step": 8847 }, { "epoch": 1.6, "learning_rate": 6.053106936416185e-06, "loss": 0.2349, "step": 8848 }, { "epoch": 1.6, "learning_rate": 6.05039739884393e-06, "loss": 0.5501, "step": 8849 }, { "epoch": 1.6, "learning_rate": 6.047687861271677e-06, "loss": 0.5631, "step": 8850 }, { "epoch": 1.6, "learning_rate": 6.044978323699422e-06, "loss": 0.5326, "step": 8851 }, { "epoch": 1.6, "learning_rate": 6.042268786127168e-06, "loss": 0.651, "step": 8852 }, { "epoch": 1.6, "learning_rate": 6.0395592485549134e-06, "loss": 0.5996, "step": 8853 }, { "epoch": 1.6, "learning_rate": 6.036849710982659e-06, "loss": 0.3793, "step": 8854 }, { "epoch": 1.6, "learning_rate": 6.034140173410405e-06, "loss": 0.5682, "step": 8855 }, { "epoch": 1.6, "learning_rate": 6.03143063583815e-06, "loss": 0.3387, "step": 8856 }, { "epoch": 1.6, "learning_rate": 6.028721098265896e-06, "loss": 0.6781, "step": 8857 }, { "epoch": 1.6, "learning_rate": 6.026011560693642e-06, "loss": 1.0426, "step": 8858 }, { "epoch": 1.6, "learning_rate": 6.023302023121388e-06, "loss": 0.4467, "step": 8859 }, { "epoch": 1.6, "learning_rate": 6.020592485549133e-06, "loss": 0.235, "step": 8860 }, { "epoch": 1.6, "learning_rate": 6.0178829479768785e-06, "loss": 0.3605, "step": 8861 }, { "epoch": 1.6, "learning_rate": 6.015173410404625e-06, "loss": 0.9724, "step": 8862 }, { "epoch": 1.6, "learning_rate": 6.01246387283237e-06, "loss": 0.3383, "step": 8863 }, { "epoch": 1.6, "learning_rate": 6.009754335260116e-06, "loss": 0.4431, "step": 8864 }, { "epoch": 1.6, "learning_rate": 6.007044797687861e-06, "loss": 0.1614, "step": 8865 }, { "epoch": 1.6, "learning_rate": 6.004335260115607e-06, "loss": 0.4859, "step": 8866 }, { "epoch": 1.6, "learning_rate": 6.001625722543353e-06, "loss": 0.8241, "step": 8867 }, { "epoch": 1.6, "learning_rate": 5.998916184971098e-06, "loss": 0.8368, "step": 8868 }, { "epoch": 1.6, "learning_rate": 5.9962066473988445e-06, "loss": 0.6468, "step": 8869 }, { "epoch": 1.6, "learning_rate": 5.99349710982659e-06, "loss": 0.4753, "step": 8870 }, { "epoch": 1.6, "learning_rate": 5.990787572254335e-06, "loss": 0.7008, "step": 8871 }, { "epoch": 1.6, "learning_rate": 5.988078034682081e-06, "loss": 0.5251, "step": 8872 }, { "epoch": 1.6, "learning_rate": 5.985368497109827e-06, "loss": 0.4695, "step": 8873 }, { "epoch": 1.6, "learning_rate": 5.982658959537573e-06, "loss": 0.6092, "step": 8874 }, { "epoch": 1.6, "learning_rate": 5.979949421965318e-06, "loss": 0.5485, "step": 8875 }, { "epoch": 1.6, "learning_rate": 5.9772398843930635e-06, "loss": 0.4956, "step": 8876 }, { "epoch": 1.6, "learning_rate": 5.9745303468208096e-06, "loss": 0.8307, "step": 8877 }, { "epoch": 1.6, "learning_rate": 5.971820809248555e-06, "loss": 0.3411, "step": 8878 }, { "epoch": 1.6, "learning_rate": 5.969111271676301e-06, "loss": 0.8839, "step": 8879 }, { "epoch": 1.6, "learning_rate": 5.966401734104046e-06, "loss": 0.7022, "step": 8880 }, { "epoch": 1.6, "learning_rate": 5.963692196531792e-06, "loss": 0.6419, "step": 8881 }, { "epoch": 1.6, "learning_rate": 5.960982658959538e-06, "loss": 0.4965, "step": 8882 }, { "epoch": 1.6, "learning_rate": 5.958273121387283e-06, "loss": 0.5174, "step": 8883 }, { "epoch": 1.6, "learning_rate": 5.955563583815029e-06, "loss": 0.5547, "step": 8884 }, { "epoch": 1.6, "learning_rate": 5.952854046242775e-06, "loss": 0.4403, "step": 8885 }, { "epoch": 1.61, "learning_rate": 5.95014450867052e-06, "loss": 0.2686, "step": 8886 }, { "epoch": 1.61, "learning_rate": 5.947434971098266e-06, "loss": 0.7512, "step": 8887 }, { "epoch": 1.61, "learning_rate": 5.944725433526011e-06, "loss": 0.5375, "step": 8888 }, { "epoch": 1.61, "learning_rate": 5.942015895953758e-06, "loss": 0.9567, "step": 8889 }, { "epoch": 1.61, "learning_rate": 5.939306358381503e-06, "loss": 0.687, "step": 8890 }, { "epoch": 1.61, "learning_rate": 5.9365968208092484e-06, "loss": 0.5088, "step": 8891 }, { "epoch": 1.61, "learning_rate": 5.9338872832369945e-06, "loss": 0.6548, "step": 8892 }, { "epoch": 1.61, "learning_rate": 5.93117774566474e-06, "loss": 0.6526, "step": 8893 }, { "epoch": 1.61, "learning_rate": 5.928468208092486e-06, "loss": 0.5452, "step": 8894 }, { "epoch": 1.61, "learning_rate": 5.925758670520231e-06, "loss": 0.3246, "step": 8895 }, { "epoch": 1.61, "learning_rate": 5.923049132947976e-06, "loss": 0.6332, "step": 8896 }, { "epoch": 1.61, "learning_rate": 5.920339595375723e-06, "loss": 0.9546, "step": 8897 }, { "epoch": 1.61, "learning_rate": 5.917630057803468e-06, "loss": 0.5343, "step": 8898 }, { "epoch": 1.61, "learning_rate": 5.914920520231214e-06, "loss": 0.5912, "step": 8899 }, { "epoch": 1.61, "learning_rate": 5.91221098265896e-06, "loss": 0.7191, "step": 8900 }, { "epoch": 1.61, "learning_rate": 5.909501445086706e-06, "loss": 0.7541, "step": 8901 }, { "epoch": 1.61, "learning_rate": 5.906791907514451e-06, "loss": 0.6908, "step": 8902 }, { "epoch": 1.61, "learning_rate": 5.904082369942196e-06, "loss": 0.5876, "step": 8903 }, { "epoch": 1.61, "learning_rate": 5.901372832369943e-06, "loss": 0.3301, "step": 8904 }, { "epoch": 1.61, "learning_rate": 5.898663294797688e-06, "loss": 0.3623, "step": 8905 }, { "epoch": 1.61, "learning_rate": 5.895953757225434e-06, "loss": 0.8617, "step": 8906 }, { "epoch": 1.61, "learning_rate": 5.8932442196531795e-06, "loss": 0.5094, "step": 8907 }, { "epoch": 1.61, "learning_rate": 5.890534682080925e-06, "loss": 0.5213, "step": 8908 }, { "epoch": 1.61, "learning_rate": 5.887825144508671e-06, "loss": 0.6282, "step": 8909 }, { "epoch": 1.61, "learning_rate": 5.885115606936416e-06, "loss": 0.3964, "step": 8910 }, { "epoch": 1.61, "learning_rate": 5.882406069364162e-06, "loss": 1.1436, "step": 8911 }, { "epoch": 1.61, "learning_rate": 5.879696531791908e-06, "loss": 0.4475, "step": 8912 }, { "epoch": 1.61, "learning_rate": 5.876986994219653e-06, "loss": 0.6902, "step": 8913 }, { "epoch": 1.61, "learning_rate": 5.874277456647399e-06, "loss": 1.642, "step": 8914 }, { "epoch": 1.61, "learning_rate": 5.8715679190751446e-06, "loss": 0.6908, "step": 8915 }, { "epoch": 1.61, "learning_rate": 5.868858381502891e-06, "loss": 0.5853, "step": 8916 }, { "epoch": 1.61, "learning_rate": 5.866148843930636e-06, "loss": 0.5068, "step": 8917 }, { "epoch": 1.61, "learning_rate": 5.863439306358381e-06, "loss": 0.58, "step": 8918 }, { "epoch": 1.61, "learning_rate": 5.860729768786127e-06, "loss": 0.2315, "step": 8919 }, { "epoch": 1.61, "learning_rate": 5.858020231213873e-06, "loss": 0.5639, "step": 8920 }, { "epoch": 1.61, "learning_rate": 5.855310693641619e-06, "loss": 0.4203, "step": 8921 }, { "epoch": 1.61, "learning_rate": 5.852601156069364e-06, "loss": 0.6713, "step": 8922 }, { "epoch": 1.61, "learning_rate": 5.84989161849711e-06, "loss": 0.4273, "step": 8923 }, { "epoch": 1.61, "learning_rate": 5.847182080924856e-06, "loss": 0.6721, "step": 8924 }, { "epoch": 1.61, "learning_rate": 5.844472543352601e-06, "loss": 2.2051, "step": 8925 }, { "epoch": 1.61, "learning_rate": 5.841763005780347e-06, "loss": 0.9069, "step": 8926 }, { "epoch": 1.61, "learning_rate": 5.839053468208093e-06, "loss": 0.2667, "step": 8927 }, { "epoch": 1.61, "learning_rate": 5.836343930635838e-06, "loss": 0.5759, "step": 8928 }, { "epoch": 1.61, "learning_rate": 5.833634393063584e-06, "loss": 0.4555, "step": 8929 }, { "epoch": 1.61, "learning_rate": 5.8309248554913295e-06, "loss": 0.4321, "step": 8930 }, { "epoch": 1.61, "learning_rate": 5.8282153179190756e-06, "loss": 0.3351, "step": 8931 }, { "epoch": 1.61, "learning_rate": 5.825505780346821e-06, "loss": 0.2522, "step": 8932 }, { "epoch": 1.61, "learning_rate": 5.822796242774566e-06, "loss": 0.9377, "step": 8933 }, { "epoch": 1.61, "learning_rate": 5.820086705202312e-06, "loss": 0.6714, "step": 8934 }, { "epoch": 1.61, "learning_rate": 5.817377167630058e-06, "loss": 0.7925, "step": 8935 }, { "epoch": 1.61, "learning_rate": 5.814667630057804e-06, "loss": 0.8402, "step": 8936 }, { "epoch": 1.61, "learning_rate": 5.811958092485549e-06, "loss": 0.6128, "step": 8937 }, { "epoch": 1.61, "learning_rate": 5.809248554913295e-06, "loss": 0.5394, "step": 8938 }, { "epoch": 1.61, "learning_rate": 5.806539017341041e-06, "loss": 0.6155, "step": 8939 }, { "epoch": 1.61, "learning_rate": 5.803829479768786e-06, "loss": 0.4708, "step": 8940 }, { "epoch": 1.62, "learning_rate": 5.801119942196532e-06, "loss": 0.1228, "step": 8941 }, { "epoch": 1.62, "learning_rate": 5.798410404624277e-06, "loss": 1.1542, "step": 8942 }, { "epoch": 1.62, "learning_rate": 5.795700867052024e-06, "loss": 0.4059, "step": 8943 }, { "epoch": 1.62, "learning_rate": 5.792991329479769e-06, "loss": 0.4887, "step": 8944 }, { "epoch": 1.62, "learning_rate": 5.7902817919075145e-06, "loss": 0.4524, "step": 8945 }, { "epoch": 1.62, "learning_rate": 5.7875722543352605e-06, "loss": 0.4284, "step": 8946 }, { "epoch": 1.62, "learning_rate": 5.784862716763006e-06, "loss": 0.4262, "step": 8947 }, { "epoch": 1.62, "learning_rate": 5.782153179190752e-06, "loss": 0.463, "step": 8948 }, { "epoch": 1.62, "learning_rate": 5.779443641618497e-06, "loss": 0.5262, "step": 8949 }, { "epoch": 1.62, "learning_rate": 5.776734104046242e-06, "loss": 0.3964, "step": 8950 }, { "epoch": 1.62, "learning_rate": 5.774024566473989e-06, "loss": 0.422, "step": 8951 }, { "epoch": 1.62, "learning_rate": 5.771315028901734e-06, "loss": 0.307, "step": 8952 }, { "epoch": 1.62, "learning_rate": 5.76860549132948e-06, "loss": 0.464, "step": 8953 }, { "epoch": 1.62, "learning_rate": 5.765895953757226e-06, "loss": 0.1287, "step": 8954 }, { "epoch": 1.62, "learning_rate": 5.763186416184971e-06, "loss": 0.3816, "step": 8955 }, { "epoch": 1.62, "learning_rate": 5.760476878612717e-06, "loss": 1.0333, "step": 8956 }, { "epoch": 1.62, "learning_rate": 5.757767341040462e-06, "loss": 0.664, "step": 8957 }, { "epoch": 1.62, "learning_rate": 5.755057803468209e-06, "loss": 0.6446, "step": 8958 }, { "epoch": 1.62, "learning_rate": 5.752348265895954e-06, "loss": 0.3582, "step": 8959 }, { "epoch": 1.62, "learning_rate": 5.749638728323699e-06, "loss": 0.5306, "step": 8960 }, { "epoch": 1.62, "learning_rate": 5.7469291907514455e-06, "loss": 0.2376, "step": 8961 }, { "epoch": 1.62, "learning_rate": 5.744219653179191e-06, "loss": 0.5744, "step": 8962 }, { "epoch": 1.62, "learning_rate": 5.741510115606937e-06, "loss": 1.3493, "step": 8963 }, { "epoch": 1.62, "learning_rate": 5.738800578034682e-06, "loss": 0.7028, "step": 8964 }, { "epoch": 1.62, "learning_rate": 5.736091040462427e-06, "loss": 0.2268, "step": 8965 }, { "epoch": 1.62, "learning_rate": 5.733381502890174e-06, "loss": 0.4548, "step": 8966 }, { "epoch": 1.62, "learning_rate": 5.730671965317919e-06, "loss": 0.4837, "step": 8967 }, { "epoch": 1.62, "learning_rate": 5.727962427745665e-06, "loss": 0.6094, "step": 8968 }, { "epoch": 1.62, "learning_rate": 5.7252528901734106e-06, "loss": 0.6426, "step": 8969 }, { "epoch": 1.62, "learning_rate": 5.722543352601156e-06, "loss": 0.5661, "step": 8970 }, { "epoch": 1.62, "learning_rate": 5.719833815028902e-06, "loss": 0.6166, "step": 8971 }, { "epoch": 1.62, "learning_rate": 5.717124277456647e-06, "loss": 0.4128, "step": 8972 }, { "epoch": 1.62, "learning_rate": 5.714414739884393e-06, "loss": 0.4241, "step": 8973 }, { "epoch": 1.62, "learning_rate": 5.711705202312139e-06, "loss": 0.3673, "step": 8974 }, { "epoch": 1.62, "learning_rate": 5.708995664739884e-06, "loss": 0.6217, "step": 8975 }, { "epoch": 1.62, "learning_rate": 5.7062861271676304e-06, "loss": 0.5506, "step": 8976 }, { "epoch": 1.62, "learning_rate": 5.703576589595376e-06, "loss": 0.4877, "step": 8977 }, { "epoch": 1.62, "learning_rate": 5.700867052023122e-06, "loss": 0.7044, "step": 8978 }, { "epoch": 1.62, "learning_rate": 5.698157514450867e-06, "loss": 0.344, "step": 8979 }, { "epoch": 1.62, "learning_rate": 5.695447976878612e-06, "loss": 0.5498, "step": 8980 }, { "epoch": 1.62, "learning_rate": 5.692738439306359e-06, "loss": 0.1405, "step": 8981 }, { "epoch": 1.62, "learning_rate": 5.690028901734104e-06, "loss": 0.7159, "step": 8982 }, { "epoch": 1.62, "learning_rate": 5.68731936416185e-06, "loss": 0.6267, "step": 8983 }, { "epoch": 1.62, "learning_rate": 5.6846098265895955e-06, "loss": 0.7747, "step": 8984 }, { "epoch": 1.62, "learning_rate": 5.681900289017342e-06, "loss": 0.5465, "step": 8985 }, { "epoch": 1.62, "learning_rate": 5.679190751445087e-06, "loss": 0.4116, "step": 8986 }, { "epoch": 1.62, "learning_rate": 5.676481213872832e-06, "loss": 1.3074, "step": 8987 }, { "epoch": 1.62, "learning_rate": 5.673771676300578e-06, "loss": 0.4241, "step": 8988 }, { "epoch": 1.62, "learning_rate": 5.671062138728324e-06, "loss": 0.701, "step": 8989 }, { "epoch": 1.62, "learning_rate": 5.66835260115607e-06, "loss": 0.3908, "step": 8990 }, { "epoch": 1.62, "learning_rate": 5.665643063583815e-06, "loss": 0.7569, "step": 8991 }, { "epoch": 1.62, "learning_rate": 5.662933526011561e-06, "loss": 0.5121, "step": 8992 }, { "epoch": 1.62, "learning_rate": 5.660223988439307e-06, "loss": 0.5262, "step": 8993 }, { "epoch": 1.62, "learning_rate": 5.657514450867052e-06, "loss": 0.3048, "step": 8994 }, { "epoch": 1.62, "learning_rate": 5.654804913294798e-06, "loss": 0.5804, "step": 8995 }, { "epoch": 1.62, "learning_rate": 5.652095375722543e-06, "loss": 0.7119, "step": 8996 }, { "epoch": 1.63, "learning_rate": 5.649385838150289e-06, "loss": 0.4204, "step": 8997 }, { "epoch": 1.63, "learning_rate": 5.646676300578035e-06, "loss": 1.3732, "step": 8998 }, { "epoch": 1.63, "learning_rate": 5.6439667630057805e-06, "loss": 0.505, "step": 8999 }, { "epoch": 1.63, "learning_rate": 5.6412572254335265e-06, "loss": 1.0612, "step": 9000 }, { "epoch": 1.63, "eval_exact_match": 88.48628192999054, "eval_f1": 94.19246800228838, "step": 9000 }, { "epoch": 1.63, "learning_rate": 5.638547687861272e-06, "loss": 0.2624, "step": 9001 }, { "epoch": 1.63, "learning_rate": 5.635838150289017e-06, "loss": 0.8465, "step": 9002 }, { "epoch": 1.63, "learning_rate": 5.633128612716763e-06, "loss": 0.5891, "step": 9003 }, { "epoch": 1.63, "learning_rate": 5.630419075144508e-06, "loss": 0.4968, "step": 9004 }, { "epoch": 1.63, "learning_rate": 5.627709537572255e-06, "loss": 0.4427, "step": 9005 }, { "epoch": 1.63, "learning_rate": 5.625e-06, "loss": 0.88, "step": 9006 }, { "epoch": 1.63, "learning_rate": 5.6222904624277456e-06, "loss": 0.2687, "step": 9007 }, { "epoch": 1.63, "learning_rate": 5.619580924855492e-06, "loss": 0.7045, "step": 9008 }, { "epoch": 1.63, "learning_rate": 5.616871387283237e-06, "loss": 0.463, "step": 9009 }, { "epoch": 1.63, "learning_rate": 5.614161849710983e-06, "loss": 0.5585, "step": 9010 }, { "epoch": 1.63, "learning_rate": 5.611452312138728e-06, "loss": 0.4549, "step": 9011 }, { "epoch": 1.63, "learning_rate": 5.608742774566474e-06, "loss": 0.2629, "step": 9012 }, { "epoch": 1.63, "learning_rate": 5.60603323699422e-06, "loss": 0.3401, "step": 9013 }, { "epoch": 1.63, "learning_rate": 5.6033236994219654e-06, "loss": 0.556, "step": 9014 }, { "epoch": 1.63, "learning_rate": 5.6006141618497115e-06, "loss": 0.3498, "step": 9015 }, { "epoch": 1.63, "learning_rate": 5.597904624277457e-06, "loss": 0.8498, "step": 9016 }, { "epoch": 1.63, "learning_rate": 5.595195086705202e-06, "loss": 0.4563, "step": 9017 }, { "epoch": 1.63, "learning_rate": 5.592485549132948e-06, "loss": 0.5656, "step": 9018 }, { "epoch": 1.63, "learning_rate": 5.589776011560693e-06, "loss": 0.6695, "step": 9019 }, { "epoch": 1.63, "learning_rate": 5.58706647398844e-06, "loss": 0.3379, "step": 9020 }, { "epoch": 1.63, "learning_rate": 5.584356936416185e-06, "loss": 0.3924, "step": 9021 }, { "epoch": 1.63, "learning_rate": 5.5816473988439305e-06, "loss": 0.4183, "step": 9022 }, { "epoch": 1.63, "learning_rate": 5.578937861271677e-06, "loss": 0.3099, "step": 9023 }, { "epoch": 1.63, "learning_rate": 5.576228323699422e-06, "loss": 0.4749, "step": 9024 }, { "epoch": 1.63, "learning_rate": 5.573518786127168e-06, "loss": 0.4283, "step": 9025 }, { "epoch": 1.63, "learning_rate": 5.570809248554913e-06, "loss": 0.4201, "step": 9026 }, { "epoch": 1.63, "learning_rate": 5.568099710982658e-06, "loss": 0.6709, "step": 9027 }, { "epoch": 1.63, "learning_rate": 5.565390173410405e-06, "loss": 0.6365, "step": 9028 }, { "epoch": 1.63, "learning_rate": 5.56268063583815e-06, "loss": 0.8555, "step": 9029 }, { "epoch": 1.63, "learning_rate": 5.5599710982658965e-06, "loss": 0.5232, "step": 9030 }, { "epoch": 1.63, "learning_rate": 5.557261560693642e-06, "loss": 0.5888, "step": 9031 }, { "epoch": 1.63, "learning_rate": 5.554552023121388e-06, "loss": 0.5541, "step": 9032 }, { "epoch": 1.63, "learning_rate": 5.551842485549133e-06, "loss": 0.8809, "step": 9033 }, { "epoch": 1.63, "learning_rate": 5.549132947976878e-06, "loss": 0.548, "step": 9034 }, { "epoch": 1.63, "learning_rate": 5.546423410404625e-06, "loss": 1.0472, "step": 9035 }, { "epoch": 1.63, "learning_rate": 5.54371387283237e-06, "loss": 1.0164, "step": 9036 }, { "epoch": 1.63, "learning_rate": 5.541004335260116e-06, "loss": 0.6281, "step": 9037 }, { "epoch": 1.63, "learning_rate": 5.5382947976878615e-06, "loss": 0.6613, "step": 9038 }, { "epoch": 1.63, "learning_rate": 5.535585260115607e-06, "loss": 0.7713, "step": 9039 }, { "epoch": 1.63, "learning_rate": 5.532875722543353e-06, "loss": 0.8852, "step": 9040 }, { "epoch": 1.63, "learning_rate": 5.530166184971098e-06, "loss": 0.3763, "step": 9041 }, { "epoch": 1.63, "learning_rate": 5.527456647398844e-06, "loss": 0.5431, "step": 9042 }, { "epoch": 1.63, "learning_rate": 5.52474710982659e-06, "loss": 0.509, "step": 9043 }, { "epoch": 1.63, "learning_rate": 5.522037572254335e-06, "loss": 0.3645, "step": 9044 }, { "epoch": 1.63, "learning_rate": 5.519328034682081e-06, "loss": 0.3373, "step": 9045 }, { "epoch": 1.63, "learning_rate": 5.516618497109827e-06, "loss": 0.511, "step": 9046 }, { "epoch": 1.63, "learning_rate": 5.513908959537573e-06, "loss": 0.5222, "step": 9047 }, { "epoch": 1.63, "learning_rate": 5.511199421965318e-06, "loss": 1.1617, "step": 9048 }, { "epoch": 1.63, "learning_rate": 5.508489884393063e-06, "loss": 0.3124, "step": 9049 }, { "epoch": 1.63, "learning_rate": 5.505780346820809e-06, "loss": 0.5255, "step": 9050 }, { "epoch": 1.63, "learning_rate": 5.503070809248555e-06, "loss": 0.4393, "step": 9051 }, { "epoch": 1.64, "learning_rate": 5.500361271676301e-06, "loss": 0.5735, "step": 9052 }, { "epoch": 1.64, "learning_rate": 5.4976517341040465e-06, "loss": 0.365, "step": 9053 }, { "epoch": 1.64, "learning_rate": 5.494942196531792e-06, "loss": 1.0825, "step": 9054 }, { "epoch": 1.64, "learning_rate": 5.492232658959538e-06, "loss": 0.4951, "step": 9055 }, { "epoch": 1.64, "learning_rate": 5.489523121387283e-06, "loss": 0.5253, "step": 9056 }, { "epoch": 1.64, "learning_rate": 5.486813583815029e-06, "loss": 0.8455, "step": 9057 }, { "epoch": 1.64, "learning_rate": 5.484104046242774e-06, "loss": 0.3089, "step": 9058 }, { "epoch": 1.64, "learning_rate": 5.48139450867052e-06, "loss": 1.6592, "step": 9059 }, { "epoch": 1.64, "learning_rate": 5.478684971098266e-06, "loss": 0.739, "step": 9060 }, { "epoch": 1.64, "learning_rate": 5.475975433526012e-06, "loss": 0.4154, "step": 9061 }, { "epoch": 1.64, "learning_rate": 5.473265895953758e-06, "loss": 0.3714, "step": 9062 }, { "epoch": 1.64, "learning_rate": 5.470556358381503e-06, "loss": 0.3837, "step": 9063 }, { "epoch": 1.64, "learning_rate": 5.467846820809248e-06, "loss": 1.1145, "step": 9064 }, { "epoch": 1.64, "learning_rate": 5.465137283236994e-06, "loss": 0.6127, "step": 9065 }, { "epoch": 1.64, "learning_rate": 5.46242774566474e-06, "loss": 0.2059, "step": 9066 }, { "epoch": 1.64, "learning_rate": 5.459718208092486e-06, "loss": 0.3079, "step": 9067 }, { "epoch": 1.64, "learning_rate": 5.4570086705202315e-06, "loss": 0.2383, "step": 9068 }, { "epoch": 1.64, "learning_rate": 5.454299132947977e-06, "loss": 0.6571, "step": 9069 }, { "epoch": 1.64, "learning_rate": 5.451589595375723e-06, "loss": 0.6177, "step": 9070 }, { "epoch": 1.64, "learning_rate": 5.448880057803468e-06, "loss": 0.4299, "step": 9071 }, { "epoch": 1.64, "learning_rate": 5.446170520231214e-06, "loss": 0.4432, "step": 9072 }, { "epoch": 1.64, "learning_rate": 5.443460982658959e-06, "loss": 0.6411, "step": 9073 }, { "epoch": 1.64, "learning_rate": 5.440751445086706e-06, "loss": 0.4618, "step": 9074 }, { "epoch": 1.64, "learning_rate": 5.438041907514451e-06, "loss": 1.2335, "step": 9075 }, { "epoch": 1.64, "learning_rate": 5.4353323699421965e-06, "loss": 0.5263, "step": 9076 }, { "epoch": 1.64, "learning_rate": 5.432622832369943e-06, "loss": 0.5056, "step": 9077 }, { "epoch": 1.64, "learning_rate": 5.429913294797688e-06, "loss": 0.297, "step": 9078 }, { "epoch": 1.64, "learning_rate": 5.427203757225434e-06, "loss": 0.6596, "step": 9079 }, { "epoch": 1.64, "learning_rate": 5.424494219653179e-06, "loss": 0.8744, "step": 9080 }, { "epoch": 1.64, "learning_rate": 5.421784682080924e-06, "loss": 0.292, "step": 9081 }, { "epoch": 1.64, "learning_rate": 5.419075144508671e-06, "loss": 0.1798, "step": 9082 }, { "epoch": 1.64, "learning_rate": 5.416365606936416e-06, "loss": 0.6227, "step": 9083 }, { "epoch": 1.64, "learning_rate": 5.4136560693641625e-06, "loss": 1.0993, "step": 9084 }, { "epoch": 1.64, "learning_rate": 5.410946531791908e-06, "loss": 0.2683, "step": 9085 }, { "epoch": 1.64, "learning_rate": 5.408236994219653e-06, "loss": 0.6051, "step": 9086 }, { "epoch": 1.64, "learning_rate": 5.405527456647399e-06, "loss": 0.7335, "step": 9087 }, { "epoch": 1.64, "learning_rate": 5.402817919075144e-06, "loss": 0.533, "step": 9088 }, { "epoch": 1.64, "learning_rate": 5.400108381502891e-06, "loss": 0.588, "step": 9089 }, { "epoch": 1.64, "learning_rate": 5.397398843930636e-06, "loss": 0.4779, "step": 9090 }, { "epoch": 1.64, "learning_rate": 5.3946893063583815e-06, "loss": 0.3349, "step": 9091 }, { "epoch": 1.64, "learning_rate": 5.3919797687861276e-06, "loss": 0.3102, "step": 9092 }, { "epoch": 1.64, "learning_rate": 5.389270231213873e-06, "loss": 1.1327, "step": 9093 }, { "epoch": 1.64, "learning_rate": 5.386560693641619e-06, "loss": 0.5167, "step": 9094 }, { "epoch": 1.64, "learning_rate": 5.383851156069364e-06, "loss": 0.7116, "step": 9095 }, { "epoch": 1.64, "learning_rate": 5.381141618497109e-06, "loss": 0.2558, "step": 9096 }, { "epoch": 1.64, "learning_rate": 5.378432080924856e-06, "loss": 0.7417, "step": 9097 }, { "epoch": 1.64, "learning_rate": 5.375722543352601e-06, "loss": 0.4592, "step": 9098 }, { "epoch": 1.64, "learning_rate": 5.3730130057803474e-06, "loss": 1.0637, "step": 9099 }, { "epoch": 1.64, "learning_rate": 5.370303468208093e-06, "loss": 0.5796, "step": 9100 }, { "epoch": 1.64, "learning_rate": 5.367593930635838e-06, "loss": 0.6173, "step": 9101 }, { "epoch": 1.64, "learning_rate": 5.364884393063584e-06, "loss": 1.41, "step": 9102 }, { "epoch": 1.64, "learning_rate": 5.362174855491329e-06, "loss": 0.2571, "step": 9103 }, { "epoch": 1.64, "learning_rate": 5.359465317919075e-06, "loss": 0.3123, "step": 9104 }, { "epoch": 1.64, "learning_rate": 5.356755780346821e-06, "loss": 0.4983, "step": 9105 }, { "epoch": 1.64, "learning_rate": 5.3540462427745665e-06, "loss": 0.3714, "step": 9106 }, { "epoch": 1.65, "learning_rate": 5.3513367052023125e-06, "loss": 0.7024, "step": 9107 }, { "epoch": 1.65, "learning_rate": 5.348627167630058e-06, "loss": 0.3745, "step": 9108 }, { "epoch": 1.65, "learning_rate": 5.345917630057804e-06, "loss": 0.4449, "step": 9109 }, { "epoch": 1.65, "learning_rate": 5.343208092485549e-06, "loss": 0.2432, "step": 9110 }, { "epoch": 1.65, "learning_rate": 5.340498554913294e-06, "loss": 0.2085, "step": 9111 }, { "epoch": 1.65, "learning_rate": 5.33778901734104e-06, "loss": 0.7099, "step": 9112 }, { "epoch": 1.65, "learning_rate": 5.335079479768786e-06, "loss": 1.109, "step": 9113 }, { "epoch": 1.65, "learning_rate": 5.332369942196532e-06, "loss": 0.6365, "step": 9114 }, { "epoch": 1.65, "learning_rate": 5.329660404624278e-06, "loss": 0.8397, "step": 9115 }, { "epoch": 1.65, "learning_rate": 5.326950867052024e-06, "loss": 0.8327, "step": 9116 }, { "epoch": 1.65, "learning_rate": 5.324241329479769e-06, "loss": 0.8339, "step": 9117 }, { "epoch": 1.65, "learning_rate": 5.321531791907514e-06, "loss": 0.3977, "step": 9118 }, { "epoch": 1.65, "learning_rate": 5.31882225433526e-06, "loss": 1.2971, "step": 9119 }, { "epoch": 1.65, "learning_rate": 5.316112716763006e-06, "loss": 0.8897, "step": 9120 }, { "epoch": 1.65, "learning_rate": 5.313403179190752e-06, "loss": 0.7253, "step": 9121 }, { "epoch": 1.65, "learning_rate": 5.3106936416184975e-06, "loss": 0.3621, "step": 9122 }, { "epoch": 1.65, "learning_rate": 5.307984104046243e-06, "loss": 0.5764, "step": 9123 }, { "epoch": 1.65, "learning_rate": 5.305274566473989e-06, "loss": 0.5663, "step": 9124 }, { "epoch": 1.65, "learning_rate": 5.302565028901734e-06, "loss": 0.5809, "step": 9125 }, { "epoch": 1.65, "learning_rate": 5.29985549132948e-06, "loss": 0.8145, "step": 9126 }, { "epoch": 1.65, "learning_rate": 5.297145953757225e-06, "loss": 0.8067, "step": 9127 }, { "epoch": 1.65, "learning_rate": 5.294436416184971e-06, "loss": 0.8162, "step": 9128 }, { "epoch": 1.65, "learning_rate": 5.291726878612717e-06, "loss": 0.3469, "step": 9129 }, { "epoch": 1.65, "learning_rate": 5.2890173410404626e-06, "loss": 0.3286, "step": 9130 }, { "epoch": 1.65, "learning_rate": 5.286307803468209e-06, "loss": 0.505, "step": 9131 }, { "epoch": 1.65, "learning_rate": 5.283598265895954e-06, "loss": 0.267, "step": 9132 }, { "epoch": 1.65, "learning_rate": 5.280888728323699e-06, "loss": 0.6523, "step": 9133 }, { "epoch": 1.65, "learning_rate": 5.278179190751445e-06, "loss": 0.0936, "step": 9134 }, { "epoch": 1.65, "learning_rate": 5.27546965317919e-06, "loss": 0.7845, "step": 9135 }, { "epoch": 1.65, "learning_rate": 5.272760115606937e-06, "loss": 0.6888, "step": 9136 }, { "epoch": 1.65, "learning_rate": 5.2700505780346824e-06, "loss": 0.3793, "step": 9137 }, { "epoch": 1.65, "learning_rate": 5.267341040462428e-06, "loss": 0.5864, "step": 9138 }, { "epoch": 1.65, "learning_rate": 5.264631502890174e-06, "loss": 0.853, "step": 9139 }, { "epoch": 1.65, "learning_rate": 5.261921965317919e-06, "loss": 0.7062, "step": 9140 }, { "epoch": 1.65, "learning_rate": 5.259212427745665e-06, "loss": 0.7074, "step": 9141 }, { "epoch": 1.65, "learning_rate": 5.25650289017341e-06, "loss": 0.899, "step": 9142 }, { "epoch": 1.65, "learning_rate": 5.253793352601156e-06, "loss": 0.6999, "step": 9143 }, { "epoch": 1.65, "learning_rate": 5.251083815028902e-06, "loss": 0.5738, "step": 9144 }, { "epoch": 1.65, "learning_rate": 5.2483742774566475e-06, "loss": 0.3914, "step": 9145 }, { "epoch": 1.65, "learning_rate": 5.2456647398843936e-06, "loss": 0.1974, "step": 9146 }, { "epoch": 1.65, "learning_rate": 5.242955202312139e-06, "loss": 0.5172, "step": 9147 }, { "epoch": 1.65, "learning_rate": 5.240245664739884e-06, "loss": 0.5627, "step": 9148 }, { "epoch": 1.65, "learning_rate": 5.23753612716763e-06, "loss": 0.8013, "step": 9149 }, { "epoch": 1.65, "learning_rate": 5.234826589595375e-06, "loss": 0.5831, "step": 9150 }, { "epoch": 1.65, "learning_rate": 5.232117052023122e-06, "loss": 0.2797, "step": 9151 }, { "epoch": 1.65, "learning_rate": 5.229407514450867e-06, "loss": 0.4466, "step": 9152 }, { "epoch": 1.65, "learning_rate": 5.226697976878613e-06, "loss": 0.7663, "step": 9153 }, { "epoch": 1.65, "learning_rate": 5.223988439306359e-06, "loss": 0.6566, "step": 9154 }, { "epoch": 1.65, "learning_rate": 5.221278901734104e-06, "loss": 0.1384, "step": 9155 }, { "epoch": 1.65, "learning_rate": 5.21856936416185e-06, "loss": 0.4876, "step": 9156 }, { "epoch": 1.65, "learning_rate": 5.215859826589595e-06, "loss": 0.3605, "step": 9157 }, { "epoch": 1.65, "learning_rate": 5.213150289017341e-06, "loss": 0.2486, "step": 9158 }, { "epoch": 1.65, "learning_rate": 5.210440751445087e-06, "loss": 0.4514, "step": 9159 }, { "epoch": 1.65, "learning_rate": 5.2077312138728325e-06, "loss": 0.4579, "step": 9160 }, { "epoch": 1.65, "learning_rate": 5.2050216763005785e-06, "loss": 0.2655, "step": 9161 }, { "epoch": 1.65, "learning_rate": 5.202312138728324e-06, "loss": 0.7057, "step": 9162 }, { "epoch": 1.66, "learning_rate": 5.19960260115607e-06, "loss": 0.6032, "step": 9163 }, { "epoch": 1.66, "learning_rate": 5.196893063583815e-06, "loss": 0.3205, "step": 9164 }, { "epoch": 1.66, "learning_rate": 5.19418352601156e-06, "loss": 0.9667, "step": 9165 }, { "epoch": 1.66, "learning_rate": 5.191473988439306e-06, "loss": 0.3383, "step": 9166 }, { "epoch": 1.66, "learning_rate": 5.188764450867052e-06, "loss": 0.5778, "step": 9167 }, { "epoch": 1.66, "learning_rate": 5.186054913294798e-06, "loss": 0.5721, "step": 9168 }, { "epoch": 1.66, "learning_rate": 5.183345375722544e-06, "loss": 0.9425, "step": 9169 }, { "epoch": 1.66, "learning_rate": 5.180635838150289e-06, "loss": 0.6761, "step": 9170 }, { "epoch": 1.66, "learning_rate": 5.177926300578035e-06, "loss": 0.4667, "step": 9171 }, { "epoch": 1.66, "learning_rate": 5.17521676300578e-06, "loss": 0.4445, "step": 9172 }, { "epoch": 1.66, "learning_rate": 5.172507225433526e-06, "loss": 0.8025, "step": 9173 }, { "epoch": 1.66, "learning_rate": 5.169797687861272e-06, "loss": 0.3575, "step": 9174 }, { "epoch": 1.66, "learning_rate": 5.1670881502890174e-06, "loss": 0.4621, "step": 9175 }, { "epoch": 1.66, "learning_rate": 5.1643786127167635e-06, "loss": 0.6884, "step": 9176 }, { "epoch": 1.66, "learning_rate": 5.161669075144509e-06, "loss": 0.6801, "step": 9177 }, { "epoch": 1.66, "learning_rate": 5.158959537572255e-06, "loss": 0.7518, "step": 9178 }, { "epoch": 1.66, "learning_rate": 5.15625e-06, "loss": 1.2016, "step": 9179 }, { "epoch": 1.66, "learning_rate": 5.153540462427745e-06, "loss": 0.3904, "step": 9180 }, { "epoch": 1.66, "learning_rate": 5.150830924855491e-06, "loss": 0.3378, "step": 9181 }, { "epoch": 1.66, "learning_rate": 5.148121387283237e-06, "loss": 0.5932, "step": 9182 }, { "epoch": 1.66, "learning_rate": 5.145411849710983e-06, "loss": 0.4053, "step": 9183 }, { "epoch": 1.66, "learning_rate": 5.1427023121387286e-06, "loss": 0.8683, "step": 9184 }, { "epoch": 1.66, "learning_rate": 5.139992774566474e-06, "loss": 0.6747, "step": 9185 }, { "epoch": 1.66, "learning_rate": 5.13728323699422e-06, "loss": 0.4882, "step": 9186 }, { "epoch": 1.66, "learning_rate": 5.134573699421965e-06, "loss": 0.385, "step": 9187 }, { "epoch": 1.66, "learning_rate": 5.131864161849711e-06, "loss": 0.7789, "step": 9188 }, { "epoch": 1.66, "learning_rate": 5.129154624277456e-06, "loss": 0.505, "step": 9189 }, { "epoch": 1.66, "learning_rate": 5.126445086705202e-06, "loss": 0.5198, "step": 9190 }, { "epoch": 1.66, "learning_rate": 5.1237355491329484e-06, "loss": 0.5828, "step": 9191 }, { "epoch": 1.66, "learning_rate": 5.121026011560694e-06, "loss": 0.4228, "step": 9192 }, { "epoch": 1.66, "learning_rate": 5.11831647398844e-06, "loss": 0.9287, "step": 9193 }, { "epoch": 1.66, "learning_rate": 5.115606936416185e-06, "loss": 0.3496, "step": 9194 }, { "epoch": 1.66, "learning_rate": 5.11289739884393e-06, "loss": 0.3886, "step": 9195 }, { "epoch": 1.66, "learning_rate": 5.110187861271676e-06, "loss": 0.4301, "step": 9196 }, { "epoch": 1.66, "learning_rate": 5.107478323699422e-06, "loss": 0.9108, "step": 9197 }, { "epoch": 1.66, "learning_rate": 5.104768786127168e-06, "loss": 0.5403, "step": 9198 }, { "epoch": 1.66, "learning_rate": 5.1020592485549135e-06, "loss": 0.9875, "step": 9199 }, { "epoch": 1.66, "learning_rate": 5.099349710982659e-06, "loss": 0.6237, "step": 9200 }, { "epoch": 1.66, "learning_rate": 5.096640173410405e-06, "loss": 0.6077, "step": 9201 }, { "epoch": 1.66, "learning_rate": 5.09393063583815e-06, "loss": 0.4181, "step": 9202 }, { "epoch": 1.66, "learning_rate": 5.091221098265896e-06, "loss": 0.6314, "step": 9203 }, { "epoch": 1.66, "learning_rate": 5.088511560693641e-06, "loss": 0.6587, "step": 9204 }, { "epoch": 1.66, "learning_rate": 5.085802023121388e-06, "loss": 0.6023, "step": 9205 }, { "epoch": 1.66, "learning_rate": 5.083092485549133e-06, "loss": 0.4053, "step": 9206 }, { "epoch": 1.66, "learning_rate": 5.080382947976879e-06, "loss": 0.9357, "step": 9207 }, { "epoch": 1.66, "learning_rate": 5.077673410404625e-06, "loss": 0.4336, "step": 9208 }, { "epoch": 1.66, "learning_rate": 5.07496387283237e-06, "loss": 0.263, "step": 9209 }, { "epoch": 1.66, "learning_rate": 5.072254335260116e-06, "loss": 0.3998, "step": 9210 }, { "epoch": 1.66, "learning_rate": 5.069544797687861e-06, "loss": 0.6369, "step": 9211 }, { "epoch": 1.66, "learning_rate": 5.066835260115606e-06, "loss": 0.5817, "step": 9212 }, { "epoch": 1.66, "learning_rate": 5.064125722543353e-06, "loss": 1.2219, "step": 9213 }, { "epoch": 1.66, "learning_rate": 5.0614161849710985e-06, "loss": 0.6649, "step": 9214 }, { "epoch": 1.66, "learning_rate": 5.0587066473988445e-06, "loss": 0.437, "step": 9215 }, { "epoch": 1.66, "learning_rate": 5.05599710982659e-06, "loss": 0.6139, "step": 9216 }, { "epoch": 1.66, "learning_rate": 5.053287572254335e-06, "loss": 0.4269, "step": 9217 }, { "epoch": 1.67, "learning_rate": 5.050578034682081e-06, "loss": 0.2735, "step": 9218 }, { "epoch": 1.67, "learning_rate": 5.047868497109826e-06, "loss": 0.4526, "step": 9219 }, { "epoch": 1.67, "learning_rate": 5.045158959537572e-06, "loss": 0.4229, "step": 9220 }, { "epoch": 1.67, "learning_rate": 5.042449421965318e-06, "loss": 0.2063, "step": 9221 }, { "epoch": 1.67, "learning_rate": 5.0397398843930636e-06, "loss": 0.5441, "step": 9222 }, { "epoch": 1.67, "learning_rate": 5.03703034682081e-06, "loss": 0.5145, "step": 9223 }, { "epoch": 1.67, "learning_rate": 5.034320809248555e-06, "loss": 0.5119, "step": 9224 }, { "epoch": 1.67, "learning_rate": 5.031611271676301e-06, "loss": 0.2506, "step": 9225 }, { "epoch": 1.67, "learning_rate": 5.028901734104046e-06, "loss": 1.0482, "step": 9226 }, { "epoch": 1.67, "learning_rate": 5.026192196531791e-06, "loss": 0.8375, "step": 9227 }, { "epoch": 1.67, "learning_rate": 5.023482658959538e-06, "loss": 0.4003, "step": 9228 }, { "epoch": 1.67, "learning_rate": 5.0207731213872834e-06, "loss": 0.4548, "step": 9229 }, { "epoch": 1.67, "learning_rate": 5.0180635838150295e-06, "loss": 0.5918, "step": 9230 }, { "epoch": 1.67, "learning_rate": 5.015354046242775e-06, "loss": 0.7992, "step": 9231 }, { "epoch": 1.67, "learning_rate": 5.01264450867052e-06, "loss": 0.6868, "step": 9232 }, { "epoch": 1.67, "learning_rate": 5.009934971098266e-06, "loss": 0.3399, "step": 9233 }, { "epoch": 1.67, "learning_rate": 5.007225433526011e-06, "loss": 1.3536, "step": 9234 }, { "epoch": 1.67, "learning_rate": 5.004515895953757e-06, "loss": 0.2911, "step": 9235 }, { "epoch": 1.67, "learning_rate": 5.001806358381503e-06, "loss": 0.4671, "step": 9236 }, { "epoch": 1.67, "learning_rate": 4.9990968208092485e-06, "loss": 0.6858, "step": 9237 }, { "epoch": 1.67, "learning_rate": 4.996387283236995e-06, "loss": 0.557, "step": 9238 }, { "epoch": 1.67, "learning_rate": 4.99367774566474e-06, "loss": 0.6663, "step": 9239 }, { "epoch": 1.67, "learning_rate": 4.990968208092486e-06, "loss": 0.2324, "step": 9240 }, { "epoch": 1.67, "learning_rate": 4.988258670520231e-06, "loss": 0.4011, "step": 9241 }, { "epoch": 1.67, "learning_rate": 4.985549132947976e-06, "loss": 0.3684, "step": 9242 }, { "epoch": 1.67, "learning_rate": 4.982839595375722e-06, "loss": 0.2316, "step": 9243 }, { "epoch": 1.67, "learning_rate": 4.980130057803468e-06, "loss": 0.676, "step": 9244 }, { "epoch": 1.67, "learning_rate": 4.9774205202312145e-06, "loss": 0.3133, "step": 9245 }, { "epoch": 1.67, "learning_rate": 4.97471098265896e-06, "loss": 0.6975, "step": 9246 }, { "epoch": 1.67, "learning_rate": 4.972001445086706e-06, "loss": 0.4381, "step": 9247 }, { "epoch": 1.67, "learning_rate": 4.969291907514451e-06, "loss": 0.3586, "step": 9248 }, { "epoch": 1.67, "learning_rate": 4.966582369942196e-06, "loss": 0.2688, "step": 9249 }, { "epoch": 1.67, "learning_rate": 4.963872832369942e-06, "loss": 1.352, "step": 9250 }, { "epoch": 1.67, "learning_rate": 4.961163294797688e-06, "loss": 0.9472, "step": 9251 }, { "epoch": 1.67, "learning_rate": 4.958453757225434e-06, "loss": 0.9356, "step": 9252 }, { "epoch": 1.67, "learning_rate": 4.9557442196531795e-06, "loss": 0.6431, "step": 9253 }, { "epoch": 1.67, "learning_rate": 4.953034682080925e-06, "loss": 0.7001, "step": 9254 }, { "epoch": 1.67, "learning_rate": 4.950325144508671e-06, "loss": 0.8685, "step": 9255 }, { "epoch": 1.67, "learning_rate": 4.947615606936416e-06, "loss": 0.9206, "step": 9256 }, { "epoch": 1.67, "learning_rate": 4.944906069364162e-06, "loss": 0.4354, "step": 9257 }, { "epoch": 1.67, "learning_rate": 4.942196531791907e-06, "loss": 1.0226, "step": 9258 }, { "epoch": 1.67, "learning_rate": 4.939486994219653e-06, "loss": 0.7381, "step": 9259 }, { "epoch": 1.67, "learning_rate": 4.936777456647399e-06, "loss": 0.4099, "step": 9260 }, { "epoch": 1.67, "learning_rate": 4.934067919075145e-06, "loss": 0.6015, "step": 9261 }, { "epoch": 1.67, "learning_rate": 4.931358381502891e-06, "loss": 0.2138, "step": 9262 }, { "epoch": 1.67, "learning_rate": 4.928648843930636e-06, "loss": 0.2349, "step": 9263 }, { "epoch": 1.67, "learning_rate": 4.925939306358381e-06, "loss": 0.9656, "step": 9264 }, { "epoch": 1.67, "learning_rate": 4.923229768786127e-06, "loss": 0.4026, "step": 9265 }, { "epoch": 1.67, "learning_rate": 4.920520231213872e-06, "loss": 0.9077, "step": 9266 }, { "epoch": 1.67, "learning_rate": 4.917810693641619e-06, "loss": 0.2507, "step": 9267 }, { "epoch": 1.67, "learning_rate": 4.9151011560693645e-06, "loss": 1.2604, "step": 9268 }, { "epoch": 1.67, "learning_rate": 4.91239161849711e-06, "loss": 0.4587, "step": 9269 }, { "epoch": 1.67, "learning_rate": 4.909682080924856e-06, "loss": 1.3664, "step": 9270 }, { "epoch": 1.67, "learning_rate": 4.906972543352601e-06, "loss": 0.1921, "step": 9271 }, { "epoch": 1.67, "learning_rate": 4.904263005780347e-06, "loss": 0.8365, "step": 9272 }, { "epoch": 1.68, "learning_rate": 4.901553468208092e-06, "loss": 0.5395, "step": 9273 }, { "epoch": 1.68, "learning_rate": 4.898843930635838e-06, "loss": 0.3533, "step": 9274 }, { "epoch": 1.68, "learning_rate": 4.896134393063584e-06, "loss": 0.2316, "step": 9275 }, { "epoch": 1.68, "learning_rate": 4.89342485549133e-06, "loss": 0.5237, "step": 9276 }, { "epoch": 1.68, "learning_rate": 4.890715317919076e-06, "loss": 0.4448, "step": 9277 }, { "epoch": 1.68, "learning_rate": 4.888005780346821e-06, "loss": 0.8994, "step": 9278 }, { "epoch": 1.68, "learning_rate": 4.885296242774566e-06, "loss": 0.1823, "step": 9279 }, { "epoch": 1.68, "learning_rate": 4.882586705202312e-06, "loss": 0.5617, "step": 9280 }, { "epoch": 1.68, "learning_rate": 4.879877167630057e-06, "loss": 0.7975, "step": 9281 }, { "epoch": 1.68, "learning_rate": 4.877167630057804e-06, "loss": 0.5023, "step": 9282 }, { "epoch": 1.68, "learning_rate": 4.8744580924855495e-06, "loss": 0.8418, "step": 9283 }, { "epoch": 1.68, "learning_rate": 4.871748554913295e-06, "loss": 0.2224, "step": 9284 }, { "epoch": 1.68, "learning_rate": 4.869039017341041e-06, "loss": 1.0038, "step": 9285 }, { "epoch": 1.68, "learning_rate": 4.866329479768786e-06, "loss": 0.4908, "step": 9286 }, { "epoch": 1.68, "learning_rate": 4.863619942196532e-06, "loss": 0.6549, "step": 9287 }, { "epoch": 1.68, "learning_rate": 4.860910404624277e-06, "loss": 0.2043, "step": 9288 }, { "epoch": 1.68, "learning_rate": 4.858200867052023e-06, "loss": 0.8658, "step": 9289 }, { "epoch": 1.68, "learning_rate": 4.855491329479769e-06, "loss": 0.7677, "step": 9290 }, { "epoch": 1.68, "learning_rate": 4.8527817919075145e-06, "loss": 0.27, "step": 9291 }, { "epoch": 1.68, "learning_rate": 4.850072254335261e-06, "loss": 0.5577, "step": 9292 }, { "epoch": 1.68, "learning_rate": 4.847362716763006e-06, "loss": 0.174, "step": 9293 }, { "epoch": 1.68, "learning_rate": 4.844653179190752e-06, "loss": 0.8058, "step": 9294 }, { "epoch": 1.68, "learning_rate": 4.841943641618497e-06, "loss": 1.0095, "step": 9295 }, { "epoch": 1.68, "learning_rate": 4.839234104046242e-06, "loss": 0.4156, "step": 9296 }, { "epoch": 1.68, "learning_rate": 4.836524566473988e-06, "loss": 0.515, "step": 9297 }, { "epoch": 1.68, "learning_rate": 4.833815028901734e-06, "loss": 0.8046, "step": 9298 }, { "epoch": 1.68, "learning_rate": 4.8311054913294805e-06, "loss": 0.3434, "step": 9299 }, { "epoch": 1.68, "learning_rate": 4.828395953757226e-06, "loss": 0.2342, "step": 9300 }, { "epoch": 1.68, "learning_rate": 4.825686416184971e-06, "loss": 0.3222, "step": 9301 }, { "epoch": 1.68, "learning_rate": 4.822976878612717e-06, "loss": 0.4797, "step": 9302 }, { "epoch": 1.68, "learning_rate": 4.820267341040462e-06, "loss": 0.6209, "step": 9303 }, { "epoch": 1.68, "learning_rate": 4.817557803468208e-06, "loss": 0.8082, "step": 9304 }, { "epoch": 1.68, "learning_rate": 4.814848265895954e-06, "loss": 0.6875, "step": 9305 }, { "epoch": 1.68, "learning_rate": 4.8121387283236995e-06, "loss": 0.4404, "step": 9306 }, { "epoch": 1.68, "learning_rate": 4.8094291907514456e-06, "loss": 0.3036, "step": 9307 }, { "epoch": 1.68, "learning_rate": 4.806719653179191e-06, "loss": 0.6652, "step": 9308 }, { "epoch": 1.68, "learning_rate": 4.804010115606937e-06, "loss": 0.3849, "step": 9309 }, { "epoch": 1.68, "learning_rate": 4.801300578034682e-06, "loss": 0.1972, "step": 9310 }, { "epoch": 1.68, "learning_rate": 4.798591040462427e-06, "loss": 0.8306, "step": 9311 }, { "epoch": 1.68, "learning_rate": 4.795881502890173e-06, "loss": 1.1418, "step": 9312 }, { "epoch": 1.68, "learning_rate": 4.793171965317919e-06, "loss": 0.4279, "step": 9313 }, { "epoch": 1.68, "learning_rate": 4.7904624277456654e-06, "loss": 0.1673, "step": 9314 }, { "epoch": 1.68, "learning_rate": 4.787752890173411e-06, "loss": 0.3983, "step": 9315 }, { "epoch": 1.68, "learning_rate": 4.785043352601156e-06, "loss": 0.2769, "step": 9316 }, { "epoch": 1.68, "learning_rate": 4.782333815028902e-06, "loss": 0.566, "step": 9317 }, { "epoch": 1.68, "learning_rate": 4.779624277456647e-06, "loss": 0.3502, "step": 9318 }, { "epoch": 1.68, "learning_rate": 4.776914739884393e-06, "loss": 0.5622, "step": 9319 }, { "epoch": 1.68, "learning_rate": 4.774205202312138e-06, "loss": 0.8417, "step": 9320 }, { "epoch": 1.68, "learning_rate": 4.7714956647398845e-06, "loss": 0.3252, "step": 9321 }, { "epoch": 1.68, "learning_rate": 4.7687861271676305e-06, "loss": 0.5761, "step": 9322 }, { "epoch": 1.68, "learning_rate": 4.766076589595376e-06, "loss": 0.3899, "step": 9323 }, { "epoch": 1.68, "learning_rate": 4.763367052023122e-06, "loss": 0.4095, "step": 9324 }, { "epoch": 1.68, "learning_rate": 4.760657514450867e-06, "loss": 0.9292, "step": 9325 }, { "epoch": 1.68, "learning_rate": 4.757947976878612e-06, "loss": 0.4704, "step": 9326 }, { "epoch": 1.68, "learning_rate": 4.755238439306358e-06, "loss": 0.9472, "step": 9327 }, { "epoch": 1.68, "learning_rate": 4.752528901734104e-06, "loss": 0.6571, "step": 9328 }, { "epoch": 1.69, "learning_rate": 4.74981936416185e-06, "loss": 0.7333, "step": 9329 }, { "epoch": 1.69, "learning_rate": 4.747109826589596e-06, "loss": 0.3788, "step": 9330 }, { "epoch": 1.69, "learning_rate": 4.744400289017342e-06, "loss": 0.2284, "step": 9331 }, { "epoch": 1.69, "learning_rate": 4.741690751445087e-06, "loss": 0.4179, "step": 9332 }, { "epoch": 1.69, "learning_rate": 4.738981213872832e-06, "loss": 0.991, "step": 9333 }, { "epoch": 1.69, "learning_rate": 4.736271676300578e-06, "loss": 0.2303, "step": 9334 }, { "epoch": 1.69, "learning_rate": 4.733562138728323e-06, "loss": 0.201, "step": 9335 }, { "epoch": 1.69, "learning_rate": 4.73085260115607e-06, "loss": 0.3383, "step": 9336 }, { "epoch": 1.69, "learning_rate": 4.7281430635838155e-06, "loss": 0.6164, "step": 9337 }, { "epoch": 1.69, "learning_rate": 4.725433526011561e-06, "loss": 0.2135, "step": 9338 }, { "epoch": 1.69, "learning_rate": 4.722723988439307e-06, "loss": 0.6138, "step": 9339 }, { "epoch": 1.69, "learning_rate": 4.720014450867052e-06, "loss": 0.5605, "step": 9340 }, { "epoch": 1.69, "learning_rate": 4.717304913294798e-06, "loss": 0.2602, "step": 9341 }, { "epoch": 1.69, "learning_rate": 4.714595375722543e-06, "loss": 0.3907, "step": 9342 }, { "epoch": 1.69, "learning_rate": 4.7118858381502884e-06, "loss": 0.7953, "step": 9343 }, { "epoch": 1.69, "learning_rate": 4.709176300578035e-06, "loss": 1.1917, "step": 9344 }, { "epoch": 1.69, "learning_rate": 4.7064667630057806e-06, "loss": 0.6348, "step": 9345 }, { "epoch": 1.69, "learning_rate": 4.703757225433527e-06, "loss": 0.3024, "step": 9346 }, { "epoch": 1.69, "learning_rate": 4.701047687861272e-06, "loss": 0.3935, "step": 9347 }, { "epoch": 1.69, "learning_rate": 4.698338150289017e-06, "loss": 0.4872, "step": 9348 }, { "epoch": 1.69, "learning_rate": 4.695628612716763e-06, "loss": 0.8197, "step": 9349 }, { "epoch": 1.69, "learning_rate": 4.692919075144508e-06, "loss": 0.5596, "step": 9350 }, { "epoch": 1.69, "learning_rate": 4.690209537572254e-06, "loss": 0.2568, "step": 9351 }, { "epoch": 1.69, "learning_rate": 4.6875000000000004e-06, "loss": 0.7382, "step": 9352 }, { "epoch": 1.69, "learning_rate": 4.684790462427746e-06, "loss": 0.7782, "step": 9353 }, { "epoch": 1.69, "learning_rate": 4.682080924855492e-06, "loss": 0.5172, "step": 9354 }, { "epoch": 1.69, "learning_rate": 4.679371387283237e-06, "loss": 0.4493, "step": 9355 }, { "epoch": 1.69, "learning_rate": 4.676661849710983e-06, "loss": 0.1603, "step": 9356 }, { "epoch": 1.69, "learning_rate": 4.673952312138728e-06, "loss": 0.6946, "step": 9357 }, { "epoch": 1.69, "learning_rate": 4.671242774566473e-06, "loss": 0.5717, "step": 9358 }, { "epoch": 1.69, "learning_rate": 4.66853323699422e-06, "loss": 1.2547, "step": 9359 }, { "epoch": 1.69, "learning_rate": 4.6658236994219655e-06, "loss": 0.291, "step": 9360 }, { "epoch": 1.69, "learning_rate": 4.663114161849712e-06, "loss": 0.4201, "step": 9361 }, { "epoch": 1.69, "learning_rate": 4.660404624277457e-06, "loss": 0.5737, "step": 9362 }, { "epoch": 1.69, "learning_rate": 4.657695086705202e-06, "loss": 0.389, "step": 9363 }, { "epoch": 1.69, "learning_rate": 4.654985549132948e-06, "loss": 0.8406, "step": 9364 }, { "epoch": 1.69, "learning_rate": 4.652276011560693e-06, "loss": 0.4429, "step": 9365 }, { "epoch": 1.69, "learning_rate": 4.649566473988439e-06, "loss": 0.2906, "step": 9366 }, { "epoch": 1.69, "learning_rate": 4.646856936416185e-06, "loss": 0.2859, "step": 9367 }, { "epoch": 1.69, "learning_rate": 4.644147398843931e-06, "loss": 0.4457, "step": 9368 }, { "epoch": 1.69, "learning_rate": 4.641437861271677e-06, "loss": 0.4123, "step": 9369 }, { "epoch": 1.69, "learning_rate": 4.638728323699422e-06, "loss": 0.7204, "step": 9370 }, { "epoch": 1.69, "learning_rate": 4.636018786127168e-06, "loss": 0.1841, "step": 9371 }, { "epoch": 1.69, "learning_rate": 4.633309248554913e-06, "loss": 0.5701, "step": 9372 }, { "epoch": 1.69, "learning_rate": 4.630599710982658e-06, "loss": 0.5342, "step": 9373 }, { "epoch": 1.69, "learning_rate": 4.627890173410404e-06, "loss": 0.4712, "step": 9374 }, { "epoch": 1.69, "learning_rate": 4.6251806358381505e-06, "loss": 0.2522, "step": 9375 }, { "epoch": 1.69, "learning_rate": 4.6224710982658965e-06, "loss": 0.3215, "step": 9376 }, { "epoch": 1.69, "learning_rate": 4.619761560693642e-06, "loss": 0.3837, "step": 9377 }, { "epoch": 1.69, "learning_rate": 4.617052023121388e-06, "loss": 0.6468, "step": 9378 }, { "epoch": 1.69, "learning_rate": 4.614342485549133e-06, "loss": 0.2663, "step": 9379 }, { "epoch": 1.69, "learning_rate": 4.611632947976878e-06, "loss": 0.6214, "step": 9380 }, { "epoch": 1.69, "learning_rate": 4.608923410404624e-06, "loss": 0.2044, "step": 9381 }, { "epoch": 1.69, "learning_rate": 4.60621387283237e-06, "loss": 0.7038, "step": 9382 }, { "epoch": 1.69, "learning_rate": 4.603504335260116e-06, "loss": 0.1331, "step": 9383 }, { "epoch": 1.7, "learning_rate": 4.600794797687862e-06, "loss": 0.4164, "step": 9384 }, { "epoch": 1.7, "learning_rate": 4.598085260115607e-06, "loss": 0.1774, "step": 9385 }, { "epoch": 1.7, "learning_rate": 4.595375722543353e-06, "loss": 0.8089, "step": 9386 }, { "epoch": 1.7, "learning_rate": 4.592666184971098e-06, "loss": 0.679, "step": 9387 }, { "epoch": 1.7, "learning_rate": 4.589956647398844e-06, "loss": 0.98, "step": 9388 }, { "epoch": 1.7, "learning_rate": 4.587247109826589e-06, "loss": 0.2424, "step": 9389 }, { "epoch": 1.7, "learning_rate": 4.5845375722543354e-06, "loss": 1.2049, "step": 9390 }, { "epoch": 1.7, "learning_rate": 4.5818280346820815e-06, "loss": 0.3356, "step": 9391 }, { "epoch": 1.7, "learning_rate": 4.579118497109827e-06, "loss": 0.2192, "step": 9392 }, { "epoch": 1.7, "learning_rate": 4.576408959537573e-06, "loss": 0.1433, "step": 9393 }, { "epoch": 1.7, "learning_rate": 4.573699421965318e-06, "loss": 0.5974, "step": 9394 }, { "epoch": 1.7, "learning_rate": 4.570989884393063e-06, "loss": 1.2933, "step": 9395 }, { "epoch": 1.7, "learning_rate": 4.568280346820809e-06, "loss": 0.6518, "step": 9396 }, { "epoch": 1.7, "learning_rate": 4.5655708092485545e-06, "loss": 0.5877, "step": 9397 }, { "epoch": 1.7, "learning_rate": 4.562861271676301e-06, "loss": 0.5821, "step": 9398 }, { "epoch": 1.7, "learning_rate": 4.560151734104047e-06, "loss": 0.4916, "step": 9399 }, { "epoch": 1.7, "learning_rate": 4.557442196531792e-06, "loss": 0.8187, "step": 9400 }, { "epoch": 1.7, "learning_rate": 4.554732658959538e-06, "loss": 0.2848, "step": 9401 }, { "epoch": 1.7, "learning_rate": 4.552023121387283e-06, "loss": 0.7499, "step": 9402 }, { "epoch": 1.7, "learning_rate": 4.549313583815029e-06, "loss": 0.5062, "step": 9403 }, { "epoch": 1.7, "learning_rate": 4.546604046242774e-06, "loss": 0.7087, "step": 9404 }, { "epoch": 1.7, "learning_rate": 4.54389450867052e-06, "loss": 0.9214, "step": 9405 }, { "epoch": 1.7, "learning_rate": 4.5411849710982665e-06, "loss": 0.7729, "step": 9406 }, { "epoch": 1.7, "learning_rate": 4.538475433526012e-06, "loss": 0.5136, "step": 9407 }, { "epoch": 1.7, "learning_rate": 4.535765895953758e-06, "loss": 1.0128, "step": 9408 }, { "epoch": 1.7, "learning_rate": 4.533056358381503e-06, "loss": 0.9245, "step": 9409 }, { "epoch": 1.7, "learning_rate": 4.530346820809248e-06, "loss": 0.7904, "step": 9410 }, { "epoch": 1.7, "learning_rate": 4.527637283236994e-06, "loss": 0.4788, "step": 9411 }, { "epoch": 1.7, "learning_rate": 4.524927745664739e-06, "loss": 0.5437, "step": 9412 }, { "epoch": 1.7, "learning_rate": 4.522218208092486e-06, "loss": 0.534, "step": 9413 }, { "epoch": 1.7, "learning_rate": 4.5195086705202315e-06, "loss": 0.6069, "step": 9414 }, { "epoch": 1.7, "learning_rate": 4.516799132947977e-06, "loss": 0.6357, "step": 9415 }, { "epoch": 1.7, "learning_rate": 4.514089595375723e-06, "loss": 0.3652, "step": 9416 }, { "epoch": 1.7, "learning_rate": 4.511380057803468e-06, "loss": 1.2141, "step": 9417 }, { "epoch": 1.7, "learning_rate": 4.508670520231214e-06, "loss": 0.3572, "step": 9418 }, { "epoch": 1.7, "learning_rate": 4.505960982658959e-06, "loss": 0.5816, "step": 9419 }, { "epoch": 1.7, "learning_rate": 4.503251445086705e-06, "loss": 0.9056, "step": 9420 }, { "epoch": 1.7, "learning_rate": 4.500541907514451e-06, "loss": 0.5832, "step": 9421 }, { "epoch": 1.7, "learning_rate": 4.497832369942197e-06, "loss": 0.5799, "step": 9422 }, { "epoch": 1.7, "learning_rate": 4.495122832369943e-06, "loss": 0.2816, "step": 9423 }, { "epoch": 1.7, "learning_rate": 4.492413294797688e-06, "loss": 0.7368, "step": 9424 }, { "epoch": 1.7, "learning_rate": 4.489703757225434e-06, "loss": 0.4081, "step": 9425 }, { "epoch": 1.7, "learning_rate": 4.486994219653179e-06, "loss": 0.4171, "step": 9426 }, { "epoch": 1.7, "learning_rate": 4.484284682080924e-06, "loss": 0.2208, "step": 9427 }, { "epoch": 1.7, "learning_rate": 4.4815751445086704e-06, "loss": 0.7127, "step": 9428 }, { "epoch": 1.7, "learning_rate": 4.4788656069364165e-06, "loss": 0.8965, "step": 9429 }, { "epoch": 1.7, "learning_rate": 4.4761560693641626e-06, "loss": 0.568, "step": 9430 }, { "epoch": 1.7, "learning_rate": 4.473446531791908e-06, "loss": 0.8015, "step": 9431 }, { "epoch": 1.7, "learning_rate": 4.470736994219653e-06, "loss": 0.3329, "step": 9432 }, { "epoch": 1.7, "learning_rate": 4.468027456647399e-06, "loss": 0.9051, "step": 9433 }, { "epoch": 1.7, "learning_rate": 4.465317919075144e-06, "loss": 0.7556, "step": 9434 }, { "epoch": 1.7, "learning_rate": 4.46260838150289e-06, "loss": 0.6923, "step": 9435 }, { "epoch": 1.7, "learning_rate": 4.459898843930636e-06, "loss": 0.8731, "step": 9436 }, { "epoch": 1.7, "learning_rate": 4.457189306358382e-06, "loss": 0.4741, "step": 9437 }, { "epoch": 1.7, "learning_rate": 4.454479768786128e-06, "loss": 0.3191, "step": 9438 }, { "epoch": 1.71, "learning_rate": 4.451770231213873e-06, "loss": 0.4375, "step": 9439 }, { "epoch": 1.71, "learning_rate": 4.449060693641619e-06, "loss": 0.7247, "step": 9440 }, { "epoch": 1.71, "learning_rate": 4.446351156069364e-06, "loss": 0.5471, "step": 9441 }, { "epoch": 1.71, "learning_rate": 4.443641618497109e-06, "loss": 0.2103, "step": 9442 }, { "epoch": 1.71, "learning_rate": 4.440932080924855e-06, "loss": 0.3406, "step": 9443 }, { "epoch": 1.71, "learning_rate": 4.4382225433526015e-06, "loss": 0.4113, "step": 9444 }, { "epoch": 1.71, "learning_rate": 4.4355130057803475e-06, "loss": 0.5038, "step": 9445 }, { "epoch": 1.71, "learning_rate": 4.432803468208093e-06, "loss": 0.5556, "step": 9446 }, { "epoch": 1.71, "learning_rate": 4.430093930635838e-06, "loss": 0.5603, "step": 9447 }, { "epoch": 1.71, "learning_rate": 4.427384393063584e-06, "loss": 0.3779, "step": 9448 }, { "epoch": 1.71, "learning_rate": 4.424674855491329e-06, "loss": 0.4641, "step": 9449 }, { "epoch": 1.71, "learning_rate": 4.421965317919075e-06, "loss": 0.5722, "step": 9450 }, { "epoch": 1.71, "learning_rate": 4.4192557803468205e-06, "loss": 0.3457, "step": 9451 }, { "epoch": 1.71, "learning_rate": 4.4165462427745665e-06, "loss": 1.005, "step": 9452 }, { "epoch": 1.71, "learning_rate": 4.413836705202313e-06, "loss": 0.6349, "step": 9453 }, { "epoch": 1.71, "learning_rate": 4.411127167630058e-06, "loss": 0.4881, "step": 9454 }, { "epoch": 1.71, "learning_rate": 4.408417630057804e-06, "loss": 0.5891, "step": 9455 }, { "epoch": 1.71, "learning_rate": 4.405708092485549e-06, "loss": 1.0662, "step": 9456 }, { "epoch": 1.71, "learning_rate": 4.402998554913294e-06, "loss": 0.4892, "step": 9457 }, { "epoch": 1.71, "learning_rate": 4.40028901734104e-06, "loss": 0.468, "step": 9458 }, { "epoch": 1.71, "learning_rate": 4.397579479768786e-06, "loss": 0.9169, "step": 9459 }, { "epoch": 1.71, "learning_rate": 4.3948699421965325e-06, "loss": 0.547, "step": 9460 }, { "epoch": 1.71, "learning_rate": 4.392160404624278e-06, "loss": 0.3061, "step": 9461 }, { "epoch": 1.71, "learning_rate": 4.389450867052024e-06, "loss": 1.0883, "step": 9462 }, { "epoch": 1.71, "learning_rate": 4.386741329479769e-06, "loss": 0.2913, "step": 9463 }, { "epoch": 1.71, "learning_rate": 4.384031791907514e-06, "loss": 0.6675, "step": 9464 }, { "epoch": 1.71, "learning_rate": 4.38132225433526e-06, "loss": 0.28, "step": 9465 }, { "epoch": 1.71, "learning_rate": 4.3786127167630054e-06, "loss": 0.6708, "step": 9466 }, { "epoch": 1.71, "learning_rate": 4.375903179190752e-06, "loss": 0.6534, "step": 9467 }, { "epoch": 1.71, "learning_rate": 4.3731936416184976e-06, "loss": 0.3443, "step": 9468 }, { "epoch": 1.71, "learning_rate": 4.370484104046243e-06, "loss": 0.5324, "step": 9469 }, { "epoch": 1.71, "learning_rate": 4.367774566473989e-06, "loss": 0.3428, "step": 9470 }, { "epoch": 1.71, "learning_rate": 4.365065028901734e-06, "loss": 0.5837, "step": 9471 }, { "epoch": 1.71, "learning_rate": 4.36235549132948e-06, "loss": 0.1609, "step": 9472 }, { "epoch": 1.71, "learning_rate": 4.359645953757225e-06, "loss": 0.3095, "step": 9473 }, { "epoch": 1.71, "learning_rate": 4.3569364161849705e-06, "loss": 0.7005, "step": 9474 }, { "epoch": 1.71, "learning_rate": 4.3542268786127174e-06, "loss": 0.6784, "step": 9475 }, { "epoch": 1.71, "learning_rate": 4.351517341040463e-06, "loss": 0.3657, "step": 9476 }, { "epoch": 1.71, "learning_rate": 4.348807803468209e-06, "loss": 0.5902, "step": 9477 }, { "epoch": 1.71, "learning_rate": 4.346098265895954e-06, "loss": 0.489, "step": 9478 }, { "epoch": 1.71, "learning_rate": 4.343388728323699e-06, "loss": 0.8345, "step": 9479 }, { "epoch": 1.71, "learning_rate": 4.340679190751445e-06, "loss": 0.9041, "step": 9480 }, { "epoch": 1.71, "learning_rate": 4.33796965317919e-06, "loss": 1.008, "step": 9481 }, { "epoch": 1.71, "learning_rate": 4.3352601156069365e-06, "loss": 0.346, "step": 9482 }, { "epoch": 1.71, "learning_rate": 4.3325505780346825e-06, "loss": 0.3442, "step": 9483 }, { "epoch": 1.71, "learning_rate": 4.329841040462428e-06, "loss": 0.921, "step": 9484 }, { "epoch": 1.71, "learning_rate": 4.327131502890174e-06, "loss": 0.7367, "step": 9485 }, { "epoch": 1.71, "learning_rate": 4.324421965317919e-06, "loss": 0.4537, "step": 9486 }, { "epoch": 1.71, "learning_rate": 4.321712427745665e-06, "loss": 0.2994, "step": 9487 }, { "epoch": 1.71, "learning_rate": 4.31900289017341e-06, "loss": 0.6432, "step": 9488 }, { "epoch": 1.71, "learning_rate": 4.3162933526011555e-06, "loss": 0.198, "step": 9489 }, { "epoch": 1.71, "learning_rate": 4.313583815028902e-06, "loss": 0.6024, "step": 9490 }, { "epoch": 1.71, "learning_rate": 4.310874277456648e-06, "loss": 0.3669, "step": 9491 }, { "epoch": 1.71, "learning_rate": 4.308164739884394e-06, "loss": 0.4463, "step": 9492 }, { "epoch": 1.71, "learning_rate": 4.305455202312139e-06, "loss": 0.5817, "step": 9493 }, { "epoch": 1.71, "learning_rate": 4.302745664739884e-06, "loss": 0.3467, "step": 9494 }, { "epoch": 1.72, "learning_rate": 4.30003612716763e-06, "loss": 0.6935, "step": 9495 }, { "epoch": 1.72, "learning_rate": 4.297326589595375e-06, "loss": 0.1854, "step": 9496 }, { "epoch": 1.72, "learning_rate": 4.294617052023121e-06, "loss": 0.5233, "step": 9497 }, { "epoch": 1.72, "learning_rate": 4.2919075144508675e-06, "loss": 0.6762, "step": 9498 }, { "epoch": 1.72, "learning_rate": 4.289197976878613e-06, "loss": 0.1995, "step": 9499 }, { "epoch": 1.72, "learning_rate": 4.286488439306359e-06, "loss": 0.8109, "step": 9500 }, { "epoch": 1.72, "eval_exact_match": 88.4484389782403, "eval_f1": 94.26205917357929, "step": 9500 }, { "epoch": 1.72, "learning_rate": 4.283778901734104e-06, "loss": 0.7494, "step": 9501 }, { "epoch": 1.72, "learning_rate": 4.28106936416185e-06, "loss": 0.4208, "step": 9502 }, { "epoch": 1.72, "learning_rate": 4.278359826589595e-06, "loss": 0.2514, "step": 9503 }, { "epoch": 1.72, "learning_rate": 4.275650289017341e-06, "loss": 0.4993, "step": 9504 }, { "epoch": 1.72, "learning_rate": 4.2729407514450865e-06, "loss": 0.8569, "step": 9505 }, { "epoch": 1.72, "learning_rate": 4.2702312138728326e-06, "loss": 0.5557, "step": 9506 }, { "epoch": 1.72, "learning_rate": 4.267521676300579e-06, "loss": 0.4505, "step": 9507 }, { "epoch": 1.72, "learning_rate": 4.264812138728324e-06, "loss": 0.8693, "step": 9508 }, { "epoch": 1.72, "learning_rate": 4.26210260115607e-06, "loss": 0.1873, "step": 9509 }, { "epoch": 1.72, "learning_rate": 4.259393063583815e-06, "loss": 0.933, "step": 9510 }, { "epoch": 1.72, "learning_rate": 4.25668352601156e-06, "loss": 0.6531, "step": 9511 }, { "epoch": 1.72, "learning_rate": 4.253973988439306e-06, "loss": 0.8802, "step": 9512 }, { "epoch": 1.72, "learning_rate": 4.2512644508670524e-06, "loss": 0.2321, "step": 9513 }, { "epoch": 1.72, "learning_rate": 4.2485549132947985e-06, "loss": 0.6837, "step": 9514 }, { "epoch": 1.72, "learning_rate": 4.245845375722544e-06, "loss": 0.7885, "step": 9515 }, { "epoch": 1.72, "learning_rate": 4.243135838150289e-06, "loss": 0.369, "step": 9516 }, { "epoch": 1.72, "learning_rate": 4.240426300578035e-06, "loss": 0.6403, "step": 9517 }, { "epoch": 1.72, "learning_rate": 4.23771676300578e-06, "loss": 0.4347, "step": 9518 }, { "epoch": 1.72, "learning_rate": 4.235007225433526e-06, "loss": 0.2992, "step": 9519 }, { "epoch": 1.72, "learning_rate": 4.2322976878612715e-06, "loss": 0.6696, "step": 9520 }, { "epoch": 1.72, "learning_rate": 4.2295881502890175e-06, "loss": 0.5843, "step": 9521 }, { "epoch": 1.72, "learning_rate": 4.2268786127167636e-06, "loss": 0.5029, "step": 9522 }, { "epoch": 1.72, "learning_rate": 4.224169075144509e-06, "loss": 0.9113, "step": 9523 }, { "epoch": 1.72, "learning_rate": 4.221459537572255e-06, "loss": 0.6749, "step": 9524 }, { "epoch": 1.72, "learning_rate": 4.21875e-06, "loss": 0.6958, "step": 9525 }, { "epoch": 1.72, "learning_rate": 4.216040462427745e-06, "loss": 0.7349, "step": 9526 }, { "epoch": 1.72, "learning_rate": 4.213330924855491e-06, "loss": 1.1145, "step": 9527 }, { "epoch": 1.72, "learning_rate": 4.2106213872832365e-06, "loss": 1.0312, "step": 9528 }, { "epoch": 1.72, "learning_rate": 4.2079118497109834e-06, "loss": 0.7693, "step": 9529 }, { "epoch": 1.72, "learning_rate": 4.205202312138729e-06, "loss": 0.4985, "step": 9530 }, { "epoch": 1.72, "learning_rate": 4.202492774566474e-06, "loss": 0.2895, "step": 9531 }, { "epoch": 1.72, "learning_rate": 4.19978323699422e-06, "loss": 0.9102, "step": 9532 }, { "epoch": 1.72, "learning_rate": 4.197073699421965e-06, "loss": 0.7265, "step": 9533 }, { "epoch": 1.72, "learning_rate": 4.194364161849711e-06, "loss": 0.5906, "step": 9534 }, { "epoch": 1.72, "learning_rate": 4.191654624277456e-06, "loss": 0.7557, "step": 9535 }, { "epoch": 1.72, "learning_rate": 4.188945086705202e-06, "loss": 0.3575, "step": 9536 }, { "epoch": 1.72, "learning_rate": 4.1862355491329485e-06, "loss": 0.3323, "step": 9537 }, { "epoch": 1.72, "learning_rate": 4.183526011560694e-06, "loss": 0.8854, "step": 9538 }, { "epoch": 1.72, "learning_rate": 4.18081647398844e-06, "loss": 0.5185, "step": 9539 }, { "epoch": 1.72, "learning_rate": 4.178106936416185e-06, "loss": 0.3733, "step": 9540 }, { "epoch": 1.72, "learning_rate": 4.17539739884393e-06, "loss": 0.3635, "step": 9541 }, { "epoch": 1.72, "learning_rate": 4.172687861271676e-06, "loss": 0.537, "step": 9542 }, { "epoch": 1.72, "learning_rate": 4.1699783236994215e-06, "loss": 0.2463, "step": 9543 }, { "epoch": 1.72, "learning_rate": 4.167268786127168e-06, "loss": 0.611, "step": 9544 }, { "epoch": 1.72, "learning_rate": 4.164559248554914e-06, "loss": 0.2521, "step": 9545 }, { "epoch": 1.72, "learning_rate": 4.161849710982659e-06, "loss": 0.2434, "step": 9546 }, { "epoch": 1.72, "learning_rate": 4.159140173410405e-06, "loss": 0.1461, "step": 9547 }, { "epoch": 1.72, "learning_rate": 4.15643063583815e-06, "loss": 0.6128, "step": 9548 }, { "epoch": 1.72, "learning_rate": 4.153721098265896e-06, "loss": 0.6251, "step": 9549 }, { "epoch": 1.73, "learning_rate": 4.151011560693641e-06, "loss": 0.6264, "step": 9550 }, { "epoch": 1.73, "learning_rate": 4.1483020231213874e-06, "loss": 0.8568, "step": 9551 }, { "epoch": 1.73, "learning_rate": 4.1455924855491335e-06, "loss": 0.6907, "step": 9552 }, { "epoch": 1.73, "learning_rate": 4.142882947976879e-06, "loss": 0.7992, "step": 9553 }, { "epoch": 1.73, "learning_rate": 4.140173410404625e-06, "loss": 0.9916, "step": 9554 }, { "epoch": 1.73, "learning_rate": 4.13746387283237e-06, "loss": 0.7094, "step": 9555 }, { "epoch": 1.73, "learning_rate": 4.134754335260116e-06, "loss": 0.6769, "step": 9556 }, { "epoch": 1.73, "learning_rate": 4.132044797687861e-06, "loss": 1.0117, "step": 9557 }, { "epoch": 1.73, "learning_rate": 4.1293352601156065e-06, "loss": 0.2928, "step": 9558 }, { "epoch": 1.73, "learning_rate": 4.1266257225433525e-06, "loss": 0.3565, "step": 9559 }, { "epoch": 1.73, "learning_rate": 4.1239161849710986e-06, "loss": 1.0773, "step": 9560 }, { "epoch": 1.73, "learning_rate": 4.121206647398845e-06, "loss": 0.5522, "step": 9561 }, { "epoch": 1.73, "learning_rate": 4.11849710982659e-06, "loss": 0.7041, "step": 9562 }, { "epoch": 1.73, "learning_rate": 4.115787572254335e-06, "loss": 1.13, "step": 9563 }, { "epoch": 1.73, "learning_rate": 4.113078034682081e-06, "loss": 1.395, "step": 9564 }, { "epoch": 1.73, "learning_rate": 4.110368497109826e-06, "loss": 0.5868, "step": 9565 }, { "epoch": 1.73, "learning_rate": 4.107658959537572e-06, "loss": 0.6328, "step": 9566 }, { "epoch": 1.73, "learning_rate": 4.1049494219653184e-06, "loss": 0.5245, "step": 9567 }, { "epoch": 1.73, "learning_rate": 4.102239884393064e-06, "loss": 0.5122, "step": 9568 }, { "epoch": 1.73, "learning_rate": 4.09953034682081e-06, "loss": 0.5198, "step": 9569 }, { "epoch": 1.73, "learning_rate": 4.096820809248555e-06, "loss": 0.5196, "step": 9570 }, { "epoch": 1.73, "learning_rate": 4.094111271676301e-06, "loss": 0.5817, "step": 9571 }, { "epoch": 1.73, "learning_rate": 4.091401734104046e-06, "loss": 0.9812, "step": 9572 }, { "epoch": 1.73, "learning_rate": 4.088692196531791e-06, "loss": 0.3215, "step": 9573 }, { "epoch": 1.73, "learning_rate": 4.0859826589595375e-06, "loss": 0.296, "step": 9574 }, { "epoch": 1.73, "learning_rate": 4.0832731213872835e-06, "loss": 0.2606, "step": 9575 }, { "epoch": 1.73, "learning_rate": 4.08056358381503e-06, "loss": 0.466, "step": 9576 }, { "epoch": 1.73, "learning_rate": 4.077854046242775e-06, "loss": 0.2484, "step": 9577 }, { "epoch": 1.73, "learning_rate": 4.07514450867052e-06, "loss": 0.4049, "step": 9578 }, { "epoch": 1.73, "learning_rate": 4.072434971098266e-06, "loss": 0.6258, "step": 9579 }, { "epoch": 1.73, "learning_rate": 4.069725433526011e-06, "loss": 0.4595, "step": 9580 }, { "epoch": 1.73, "learning_rate": 4.067015895953757e-06, "loss": 0.8503, "step": 9581 }, { "epoch": 1.73, "learning_rate": 4.0643063583815026e-06, "loss": 0.9681, "step": 9582 }, { "epoch": 1.73, "learning_rate": 4.061596820809249e-06, "loss": 0.6764, "step": 9583 }, { "epoch": 1.73, "learning_rate": 4.058887283236995e-06, "loss": 0.4255, "step": 9584 }, { "epoch": 1.73, "learning_rate": 4.05617774566474e-06, "loss": 0.4097, "step": 9585 }, { "epoch": 1.73, "learning_rate": 4.053468208092486e-06, "loss": 0.723, "step": 9586 }, { "epoch": 1.73, "learning_rate": 4.050758670520231e-06, "loss": 0.5104, "step": 9587 }, { "epoch": 1.73, "learning_rate": 4.048049132947976e-06, "loss": 0.6123, "step": 9588 }, { "epoch": 1.73, "learning_rate": 4.0453395953757224e-06, "loss": 0.6759, "step": 9589 }, { "epoch": 1.73, "learning_rate": 4.042630057803468e-06, "loss": 1.0452, "step": 9590 }, { "epoch": 1.73, "learning_rate": 4.0399205202312145e-06, "loss": 0.7565, "step": 9591 }, { "epoch": 1.73, "learning_rate": 4.03721098265896e-06, "loss": 0.208, "step": 9592 }, { "epoch": 1.73, "learning_rate": 4.034501445086706e-06, "loss": 0.3654, "step": 9593 }, { "epoch": 1.73, "learning_rate": 4.031791907514451e-06, "loss": 0.2977, "step": 9594 }, { "epoch": 1.73, "learning_rate": 4.029082369942196e-06, "loss": 0.3604, "step": 9595 }, { "epoch": 1.73, "learning_rate": 4.026372832369942e-06, "loss": 0.3041, "step": 9596 }, { "epoch": 1.73, "learning_rate": 4.0236632947976875e-06, "loss": 0.7587, "step": 9597 }, { "epoch": 1.73, "learning_rate": 4.020953757225434e-06, "loss": 0.3855, "step": 9598 }, { "epoch": 1.73, "learning_rate": 4.01824421965318e-06, "loss": 0.5388, "step": 9599 }, { "epoch": 1.73, "learning_rate": 4.015534682080925e-06, "loss": 0.5513, "step": 9600 }, { "epoch": 1.73, "learning_rate": 4.012825144508671e-06, "loss": 0.3918, "step": 9601 }, { "epoch": 1.73, "learning_rate": 4.010115606936416e-06, "loss": 0.6905, "step": 9602 }, { "epoch": 1.73, "learning_rate": 4.007406069364162e-06, "loss": 0.5992, "step": 9603 }, { "epoch": 1.73, "learning_rate": 4.004696531791907e-06, "loss": 0.7518, "step": 9604 }, { "epoch": 1.74, "learning_rate": 4.001986994219653e-06, "loss": 0.8133, "step": 9605 }, { "epoch": 1.74, "learning_rate": 3.9992774566473995e-06, "loss": 0.4372, "step": 9606 }, { "epoch": 1.74, "learning_rate": 3.996567919075145e-06, "loss": 1.2292, "step": 9607 }, { "epoch": 1.74, "learning_rate": 3.993858381502891e-06, "loss": 0.4049, "step": 9608 }, { "epoch": 1.74, "learning_rate": 3.991148843930636e-06, "loss": 0.6093, "step": 9609 }, { "epoch": 1.74, "learning_rate": 3.988439306358381e-06, "loss": 0.7636, "step": 9610 }, { "epoch": 1.74, "learning_rate": 3.985729768786127e-06, "loss": 0.2769, "step": 9611 }, { "epoch": 1.74, "learning_rate": 3.9830202312138725e-06, "loss": 0.7177, "step": 9612 }, { "epoch": 1.74, "learning_rate": 3.9803106936416185e-06, "loss": 0.3826, "step": 9613 }, { "epoch": 1.74, "learning_rate": 3.977601156069365e-06, "loss": 0.3683, "step": 9614 }, { "epoch": 1.74, "learning_rate": 3.97489161849711e-06, "loss": 0.9681, "step": 9615 }, { "epoch": 1.74, "learning_rate": 3.972182080924856e-06, "loss": 0.2993, "step": 9616 }, { "epoch": 1.74, "learning_rate": 3.969472543352601e-06, "loss": 0.4052, "step": 9617 }, { "epoch": 1.74, "learning_rate": 3.966763005780347e-06, "loss": 0.7297, "step": 9618 }, { "epoch": 1.74, "learning_rate": 3.964053468208092e-06, "loss": 0.797, "step": 9619 }, { "epoch": 1.74, "learning_rate": 3.9613439306358376e-06, "loss": 0.5326, "step": 9620 }, { "epoch": 1.74, "learning_rate": 3.9586343930635845e-06, "loss": 0.3554, "step": 9621 }, { "epoch": 1.74, "learning_rate": 3.95592485549133e-06, "loss": 0.5465, "step": 9622 }, { "epoch": 1.74, "learning_rate": 3.953215317919076e-06, "loss": 0.6873, "step": 9623 }, { "epoch": 1.74, "learning_rate": 3.950505780346821e-06, "loss": 0.2362, "step": 9624 }, { "epoch": 1.74, "learning_rate": 3.947796242774566e-06, "loss": 0.1927, "step": 9625 }, { "epoch": 1.74, "learning_rate": 3.945086705202312e-06, "loss": 0.2764, "step": 9626 }, { "epoch": 1.74, "learning_rate": 3.9423771676300574e-06, "loss": 0.7593, "step": 9627 }, { "epoch": 1.74, "learning_rate": 3.9396676300578035e-06, "loss": 0.3792, "step": 9628 }, { "epoch": 1.74, "learning_rate": 3.9369580924855495e-06, "loss": 0.1608, "step": 9629 }, { "epoch": 1.74, "learning_rate": 3.934248554913295e-06, "loss": 0.7462, "step": 9630 }, { "epoch": 1.74, "learning_rate": 3.931539017341041e-06, "loss": 0.5077, "step": 9631 }, { "epoch": 1.74, "learning_rate": 3.928829479768786e-06, "loss": 0.7583, "step": 9632 }, { "epoch": 1.74, "learning_rate": 3.926119942196532e-06, "loss": 0.5197, "step": 9633 }, { "epoch": 1.74, "learning_rate": 3.923410404624277e-06, "loss": 0.3882, "step": 9634 }, { "epoch": 1.74, "learning_rate": 3.920700867052023e-06, "loss": 0.5107, "step": 9635 }, { "epoch": 1.74, "learning_rate": 3.9179913294797686e-06, "loss": 0.265, "step": 9636 }, { "epoch": 1.74, "learning_rate": 3.915281791907515e-06, "loss": 0.7257, "step": 9637 }, { "epoch": 1.74, "learning_rate": 3.912572254335261e-06, "loss": 0.5084, "step": 9638 }, { "epoch": 1.74, "learning_rate": 3.909862716763006e-06, "loss": 0.5329, "step": 9639 }, { "epoch": 1.74, "learning_rate": 3.907153179190752e-06, "loss": 0.4059, "step": 9640 }, { "epoch": 1.74, "learning_rate": 3.904443641618497e-06, "loss": 1.0774, "step": 9641 }, { "epoch": 1.74, "learning_rate": 3.901734104046242e-06, "loss": 0.1556, "step": 9642 }, { "epoch": 1.74, "learning_rate": 3.8990245664739884e-06, "loss": 0.2887, "step": 9643 }, { "epoch": 1.74, "learning_rate": 3.896315028901734e-06, "loss": 0.437, "step": 9644 }, { "epoch": 1.74, "learning_rate": 3.8936054913294806e-06, "loss": 0.6955, "step": 9645 }, { "epoch": 1.74, "learning_rate": 3.890895953757226e-06, "loss": 0.4753, "step": 9646 }, { "epoch": 1.74, "learning_rate": 3.888186416184971e-06, "loss": 0.185, "step": 9647 }, { "epoch": 1.74, "learning_rate": 3.885476878612717e-06, "loss": 0.9425, "step": 9648 }, { "epoch": 1.74, "learning_rate": 3.882767341040462e-06, "loss": 0.755, "step": 9649 }, { "epoch": 1.74, "learning_rate": 3.880057803468208e-06, "loss": 0.4792, "step": 9650 }, { "epoch": 1.74, "learning_rate": 3.8773482658959535e-06, "loss": 0.9209, "step": 9651 }, { "epoch": 1.74, "learning_rate": 3.8746387283237e-06, "loss": 0.3306, "step": 9652 }, { "epoch": 1.74, "learning_rate": 3.871929190751446e-06, "loss": 0.6383, "step": 9653 }, { "epoch": 1.74, "learning_rate": 3.869219653179191e-06, "loss": 0.6588, "step": 9654 }, { "epoch": 1.74, "learning_rate": 3.866510115606937e-06, "loss": 0.7769, "step": 9655 }, { "epoch": 1.74, "learning_rate": 3.863800578034682e-06, "loss": 0.522, "step": 9656 }, { "epoch": 1.74, "learning_rate": 3.861091040462427e-06, "loss": 0.4417, "step": 9657 }, { "epoch": 1.74, "learning_rate": 3.858381502890173e-06, "loss": 0.4273, "step": 9658 }, { "epoch": 1.74, "learning_rate": 3.855671965317919e-06, "loss": 0.6823, "step": 9659 }, { "epoch": 1.74, "learning_rate": 3.8529624277456655e-06, "loss": 0.4172, "step": 9660 }, { "epoch": 1.75, "learning_rate": 3.850252890173411e-06, "loss": 0.9659, "step": 9661 }, { "epoch": 1.75, "learning_rate": 3.847543352601156e-06, "loss": 0.3593, "step": 9662 }, { "epoch": 1.75, "learning_rate": 3.844833815028902e-06, "loss": 0.2748, "step": 9663 }, { "epoch": 1.75, "learning_rate": 3.842124277456647e-06, "loss": 0.3442, "step": 9664 }, { "epoch": 1.75, "learning_rate": 3.839414739884393e-06, "loss": 0.4779, "step": 9665 }, { "epoch": 1.75, "learning_rate": 3.8367052023121385e-06, "loss": 0.5456, "step": 9666 }, { "epoch": 1.75, "learning_rate": 3.833995664739884e-06, "loss": 0.405, "step": 9667 }, { "epoch": 1.75, "learning_rate": 3.831286127167631e-06, "loss": 1.1506, "step": 9668 }, { "epoch": 1.75, "learning_rate": 3.828576589595376e-06, "loss": 0.4278, "step": 9669 }, { "epoch": 1.75, "learning_rate": 3.825867052023122e-06, "loss": 0.3955, "step": 9670 }, { "epoch": 1.75, "learning_rate": 3.823157514450867e-06, "loss": 0.5139, "step": 9671 }, { "epoch": 1.75, "learning_rate": 3.820447976878612e-06, "loss": 0.4441, "step": 9672 }, { "epoch": 1.75, "learning_rate": 3.817738439306358e-06, "loss": 0.7106, "step": 9673 }, { "epoch": 1.75, "learning_rate": 3.8150289017341036e-06, "loss": 0.3988, "step": 9674 }, { "epoch": 1.75, "learning_rate": 3.81231936416185e-06, "loss": 0.2621, "step": 9675 }, { "epoch": 1.75, "learning_rate": 3.8096098265895953e-06, "loss": 0.8485, "step": 9676 }, { "epoch": 1.75, "learning_rate": 3.8069002890173417e-06, "loss": 0.2184, "step": 9677 }, { "epoch": 1.75, "learning_rate": 3.804190751445087e-06, "loss": 0.4255, "step": 9678 }, { "epoch": 1.75, "learning_rate": 3.801481213872832e-06, "loss": 0.3243, "step": 9679 }, { "epoch": 1.75, "learning_rate": 3.7987716763005782e-06, "loss": 0.6382, "step": 9680 }, { "epoch": 1.75, "learning_rate": 3.796062138728324e-06, "loss": 0.4426, "step": 9681 }, { "epoch": 1.75, "learning_rate": 3.79335260115607e-06, "loss": 0.2411, "step": 9682 }, { "epoch": 1.75, "learning_rate": 3.790643063583815e-06, "loss": 0.4908, "step": 9683 }, { "epoch": 1.75, "learning_rate": 3.7879335260115603e-06, "loss": 0.5269, "step": 9684 }, { "epoch": 1.75, "learning_rate": 3.785223988439307e-06, "loss": 0.365, "step": 9685 }, { "epoch": 1.75, "learning_rate": 3.782514450867052e-06, "loss": 0.498, "step": 9686 }, { "epoch": 1.75, "learning_rate": 3.779804913294798e-06, "loss": 0.7867, "step": 9687 }, { "epoch": 1.75, "learning_rate": 3.7770953757225433e-06, "loss": 0.4462, "step": 9688 }, { "epoch": 1.75, "learning_rate": 3.774385838150289e-06, "loss": 0.3464, "step": 9689 }, { "epoch": 1.75, "learning_rate": 3.771676300578035e-06, "loss": 0.3561, "step": 9690 }, { "epoch": 1.75, "learning_rate": 3.7689667630057802e-06, "loss": 0.854, "step": 9691 }, { "epoch": 1.75, "learning_rate": 3.7662572254335263e-06, "loss": 0.3664, "step": 9692 }, { "epoch": 1.75, "learning_rate": 3.763547687861272e-06, "loss": 0.5543, "step": 9693 }, { "epoch": 1.75, "learning_rate": 3.760838150289017e-06, "loss": 0.3357, "step": 9694 }, { "epoch": 1.75, "learning_rate": 3.758128612716763e-06, "loss": 0.5474, "step": 9695 }, { "epoch": 1.75, "learning_rate": 3.7554190751445084e-06, "loss": 1.0905, "step": 9696 }, { "epoch": 1.75, "learning_rate": 3.752709537572255e-06, "loss": 0.3589, "step": 9697 }, { "epoch": 1.75, "learning_rate": 3.75e-06, "loss": 0.4063, "step": 9698 }, { "epoch": 1.75, "learning_rate": 3.7472904624277457e-06, "loss": 0.3, "step": 9699 }, { "epoch": 1.75, "learning_rate": 3.744580924855492e-06, "loss": 0.3636, "step": 9700 }, { "epoch": 1.75, "learning_rate": 3.741871387283237e-06, "loss": 0.8799, "step": 9701 }, { "epoch": 1.75, "learning_rate": 3.7391618497109826e-06, "loss": 0.3781, "step": 9702 }, { "epoch": 1.75, "learning_rate": 3.7364523121387283e-06, "loss": 0.3835, "step": 9703 }, { "epoch": 1.75, "learning_rate": 3.7337427745664743e-06, "loss": 0.4048, "step": 9704 }, { "epoch": 1.75, "learning_rate": 3.73103323699422e-06, "loss": 0.6067, "step": 9705 }, { "epoch": 1.75, "learning_rate": 3.728323699421965e-06, "loss": 0.6796, "step": 9706 }, { "epoch": 1.75, "learning_rate": 3.725614161849711e-06, "loss": 0.5777, "step": 9707 }, { "epoch": 1.75, "learning_rate": 3.722904624277457e-06, "loss": 0.5192, "step": 9708 }, { "epoch": 1.75, "learning_rate": 3.7201950867052025e-06, "loss": 0.5247, "step": 9709 }, { "epoch": 1.75, "learning_rate": 3.717485549132948e-06, "loss": 1.0696, "step": 9710 }, { "epoch": 1.75, "learning_rate": 3.7147760115606938e-06, "loss": 0.2598, "step": 9711 }, { "epoch": 1.75, "learning_rate": 3.7120664739884394e-06, "loss": 0.3503, "step": 9712 }, { "epoch": 1.75, "learning_rate": 3.709356936416185e-06, "loss": 0.522, "step": 9713 }, { "epoch": 1.75, "learning_rate": 3.7066473988439307e-06, "loss": 0.4743, "step": 9714 }, { "epoch": 1.75, "learning_rate": 3.7039378612716763e-06, "loss": 0.8089, "step": 9715 }, { "epoch": 1.76, "learning_rate": 3.7012283236994224e-06, "loss": 0.457, "step": 9716 }, { "epoch": 1.76, "learning_rate": 3.6985187861271676e-06, "loss": 0.4562, "step": 9717 }, { "epoch": 1.76, "learning_rate": 3.6958092485549132e-06, "loss": 0.7606, "step": 9718 }, { "epoch": 1.76, "learning_rate": 3.693099710982659e-06, "loss": 0.3213, "step": 9719 }, { "epoch": 1.76, "learning_rate": 3.690390173410405e-06, "loss": 0.7584, "step": 9720 }, { "epoch": 1.76, "learning_rate": 3.6876806358381506e-06, "loss": 0.3218, "step": 9721 }, { "epoch": 1.76, "learning_rate": 3.6849710982658958e-06, "loss": 0.2946, "step": 9722 }, { "epoch": 1.76, "learning_rate": 3.6822615606936414e-06, "loss": 1.0952, "step": 9723 }, { "epoch": 1.76, "learning_rate": 3.6795520231213875e-06, "loss": 0.4629, "step": 9724 }, { "epoch": 1.76, "learning_rate": 3.676842485549133e-06, "loss": 0.4361, "step": 9725 }, { "epoch": 1.76, "learning_rate": 3.6741329479768787e-06, "loss": 1.0054, "step": 9726 }, { "epoch": 1.76, "learning_rate": 3.6714234104046244e-06, "loss": 0.2947, "step": 9727 }, { "epoch": 1.76, "learning_rate": 3.66871387283237e-06, "loss": 0.374, "step": 9728 }, { "epoch": 1.76, "learning_rate": 3.6660043352601156e-06, "loss": 0.1589, "step": 9729 }, { "epoch": 1.76, "learning_rate": 3.6632947976878613e-06, "loss": 0.7022, "step": 9730 }, { "epoch": 1.76, "learning_rate": 3.6605852601156073e-06, "loss": 0.808, "step": 9731 }, { "epoch": 1.76, "learning_rate": 3.657875722543353e-06, "loss": 0.8556, "step": 9732 }, { "epoch": 1.76, "learning_rate": 3.655166184971098e-06, "loss": 0.3279, "step": 9733 }, { "epoch": 1.76, "learning_rate": 3.652456647398844e-06, "loss": 0.4413, "step": 9734 }, { "epoch": 1.76, "learning_rate": 3.64974710982659e-06, "loss": 0.628, "step": 9735 }, { "epoch": 1.76, "learning_rate": 3.6470375722543355e-06, "loss": 1.0902, "step": 9736 }, { "epoch": 1.76, "learning_rate": 3.644328034682081e-06, "loss": 0.4512, "step": 9737 }, { "epoch": 1.76, "learning_rate": 3.6416184971098264e-06, "loss": 0.2029, "step": 9738 }, { "epoch": 1.76, "learning_rate": 3.6389089595375724e-06, "loss": 0.8365, "step": 9739 }, { "epoch": 1.76, "learning_rate": 3.636199421965318e-06, "loss": 0.6534, "step": 9740 }, { "epoch": 1.76, "learning_rate": 3.6334898843930637e-06, "loss": 0.3023, "step": 9741 }, { "epoch": 1.76, "learning_rate": 3.6307803468208093e-06, "loss": 0.4804, "step": 9742 }, { "epoch": 1.76, "learning_rate": 3.628070809248555e-06, "loss": 0.5451, "step": 9743 }, { "epoch": 1.76, "learning_rate": 3.6253612716763006e-06, "loss": 0.415, "step": 9744 }, { "epoch": 1.76, "learning_rate": 3.6226517341040462e-06, "loss": 0.4519, "step": 9745 }, { "epoch": 1.76, "learning_rate": 3.619942196531792e-06, "loss": 0.4259, "step": 9746 }, { "epoch": 1.76, "learning_rate": 3.617232658959538e-06, "loss": 0.4089, "step": 9747 }, { "epoch": 1.76, "learning_rate": 3.614523121387283e-06, "loss": 0.6021, "step": 9748 }, { "epoch": 1.76, "learning_rate": 3.6118135838150288e-06, "loss": 0.7036, "step": 9749 }, { "epoch": 1.76, "learning_rate": 3.6091040462427744e-06, "loss": 0.9365, "step": 9750 }, { "epoch": 1.76, "learning_rate": 3.6063945086705205e-06, "loss": 0.2094, "step": 9751 }, { "epoch": 1.76, "learning_rate": 3.603684971098266e-06, "loss": 0.9589, "step": 9752 }, { "epoch": 1.76, "learning_rate": 3.6009754335260117e-06, "loss": 0.388, "step": 9753 }, { "epoch": 1.76, "learning_rate": 3.5982658959537574e-06, "loss": 0.6364, "step": 9754 }, { "epoch": 1.76, "learning_rate": 3.595556358381503e-06, "loss": 0.2852, "step": 9755 }, { "epoch": 1.76, "learning_rate": 3.5928468208092487e-06, "loss": 2.0369, "step": 9756 }, { "epoch": 1.76, "learning_rate": 3.5901372832369943e-06, "loss": 0.3698, "step": 9757 }, { "epoch": 1.76, "learning_rate": 3.5874277456647403e-06, "loss": 0.8794, "step": 9758 }, { "epoch": 1.76, "learning_rate": 3.5847182080924856e-06, "loss": 0.9295, "step": 9759 }, { "epoch": 1.76, "learning_rate": 3.582008670520231e-06, "loss": 0.6711, "step": 9760 }, { "epoch": 1.76, "learning_rate": 3.579299132947977e-06, "loss": 0.4843, "step": 9761 }, { "epoch": 1.76, "learning_rate": 3.576589595375723e-06, "loss": 0.4252, "step": 9762 }, { "epoch": 1.76, "learning_rate": 3.5738800578034685e-06, "loss": 0.6777, "step": 9763 }, { "epoch": 1.76, "learning_rate": 3.5711705202312137e-06, "loss": 0.8519, "step": 9764 }, { "epoch": 1.76, "learning_rate": 3.5684609826589594e-06, "loss": 0.4852, "step": 9765 }, { "epoch": 1.76, "learning_rate": 3.5657514450867054e-06, "loss": 0.5362, "step": 9766 }, { "epoch": 1.76, "learning_rate": 3.563041907514451e-06, "loss": 0.3871, "step": 9767 }, { "epoch": 1.76, "learning_rate": 3.5603323699421967e-06, "loss": 0.526, "step": 9768 }, { "epoch": 1.76, "learning_rate": 3.557622832369942e-06, "loss": 0.3162, "step": 9769 }, { "epoch": 1.76, "learning_rate": 3.554913294797688e-06, "loss": 0.5007, "step": 9770 }, { "epoch": 1.76, "learning_rate": 3.5522037572254336e-06, "loss": 0.5926, "step": 9771 }, { "epoch": 1.77, "learning_rate": 3.5494942196531792e-06, "loss": 0.3735, "step": 9772 }, { "epoch": 1.77, "learning_rate": 3.546784682080925e-06, "loss": 0.5403, "step": 9773 }, { "epoch": 1.77, "learning_rate": 3.544075144508671e-06, "loss": 0.5384, "step": 9774 }, { "epoch": 1.77, "learning_rate": 3.541365606936416e-06, "loss": 1.014, "step": 9775 }, { "epoch": 1.77, "learning_rate": 3.538656069364162e-06, "loss": 0.7199, "step": 9776 }, { "epoch": 1.77, "learning_rate": 3.5359465317919074e-06, "loss": 0.3415, "step": 9777 }, { "epoch": 1.77, "learning_rate": 3.5332369942196535e-06, "loss": 0.9458, "step": 9778 }, { "epoch": 1.77, "learning_rate": 3.530527456647399e-06, "loss": 0.5742, "step": 9779 }, { "epoch": 1.77, "learning_rate": 3.5278179190751443e-06, "loss": 0.4181, "step": 9780 }, { "epoch": 1.77, "learning_rate": 3.5251083815028904e-06, "loss": 0.386, "step": 9781 }, { "epoch": 1.77, "learning_rate": 3.522398843930636e-06, "loss": 0.5671, "step": 9782 }, { "epoch": 1.77, "learning_rate": 3.5196893063583817e-06, "loss": 1.0509, "step": 9783 }, { "epoch": 1.77, "learning_rate": 3.5169797687861273e-06, "loss": 0.4058, "step": 9784 }, { "epoch": 1.77, "learning_rate": 3.514270231213873e-06, "loss": 0.5384, "step": 9785 }, { "epoch": 1.77, "learning_rate": 3.5115606936416186e-06, "loss": 0.732, "step": 9786 }, { "epoch": 1.77, "learning_rate": 3.508851156069364e-06, "loss": 0.5284, "step": 9787 }, { "epoch": 1.77, "learning_rate": 3.50614161849711e-06, "loss": 0.4576, "step": 9788 }, { "epoch": 1.77, "learning_rate": 3.503432080924856e-06, "loss": 0.4373, "step": 9789 }, { "epoch": 1.77, "learning_rate": 3.500722543352601e-06, "loss": 0.6098, "step": 9790 }, { "epoch": 1.77, "learning_rate": 3.4980130057803467e-06, "loss": 0.2287, "step": 9791 }, { "epoch": 1.77, "learning_rate": 3.4953034682080924e-06, "loss": 0.6494, "step": 9792 }, { "epoch": 1.77, "learning_rate": 3.4925939306358384e-06, "loss": 0.4731, "step": 9793 }, { "epoch": 1.77, "learning_rate": 3.489884393063584e-06, "loss": 0.551, "step": 9794 }, { "epoch": 1.77, "learning_rate": 3.4871748554913293e-06, "loss": 0.569, "step": 9795 }, { "epoch": 1.77, "learning_rate": 3.484465317919075e-06, "loss": 0.409, "step": 9796 }, { "epoch": 1.77, "learning_rate": 3.481755780346821e-06, "loss": 0.6108, "step": 9797 }, { "epoch": 1.77, "learning_rate": 3.4790462427745666e-06, "loss": 0.4831, "step": 9798 }, { "epoch": 1.77, "learning_rate": 3.4763367052023123e-06, "loss": 0.8474, "step": 9799 }, { "epoch": 1.77, "learning_rate": 3.473627167630058e-06, "loss": 0.4566, "step": 9800 }, { "epoch": 1.77, "learning_rate": 3.4709176300578035e-06, "loss": 0.446, "step": 9801 }, { "epoch": 1.77, "learning_rate": 3.468208092485549e-06, "loss": 0.5208, "step": 9802 }, { "epoch": 1.77, "learning_rate": 3.465498554913295e-06, "loss": 0.4804, "step": 9803 }, { "epoch": 1.77, "learning_rate": 3.4627890173410404e-06, "loss": 0.6528, "step": 9804 }, { "epoch": 1.77, "learning_rate": 3.4600794797687865e-06, "loss": 0.7296, "step": 9805 }, { "epoch": 1.77, "learning_rate": 3.4573699421965317e-06, "loss": 0.5793, "step": 9806 }, { "epoch": 1.77, "learning_rate": 3.4546604046242773e-06, "loss": 0.3746, "step": 9807 }, { "epoch": 1.77, "learning_rate": 3.4519508670520234e-06, "loss": 0.5568, "step": 9808 }, { "epoch": 1.77, "learning_rate": 3.449241329479769e-06, "loss": 0.6485, "step": 9809 }, { "epoch": 1.77, "learning_rate": 3.4465317919075147e-06, "loss": 0.3351, "step": 9810 }, { "epoch": 1.77, "learning_rate": 3.44382225433526e-06, "loss": 0.5976, "step": 9811 }, { "epoch": 1.77, "learning_rate": 3.441112716763006e-06, "loss": 0.4219, "step": 9812 }, { "epoch": 1.77, "learning_rate": 3.4384031791907516e-06, "loss": 0.3868, "step": 9813 }, { "epoch": 1.77, "learning_rate": 3.4356936416184972e-06, "loss": 0.3395, "step": 9814 }, { "epoch": 1.77, "learning_rate": 3.432984104046243e-06, "loss": 0.3493, "step": 9815 }, { "epoch": 1.77, "learning_rate": 3.4302745664739885e-06, "loss": 0.5174, "step": 9816 }, { "epoch": 1.77, "learning_rate": 3.427565028901734e-06, "loss": 0.7301, "step": 9817 }, { "epoch": 1.77, "learning_rate": 3.4248554913294798e-06, "loss": 0.3326, "step": 9818 }, { "epoch": 1.77, "learning_rate": 3.4221459537572254e-06, "loss": 1.2086, "step": 9819 }, { "epoch": 1.77, "learning_rate": 3.4194364161849714e-06, "loss": 0.3571, "step": 9820 }, { "epoch": 1.77, "learning_rate": 3.416726878612717e-06, "loss": 0.2333, "step": 9821 }, { "epoch": 1.77, "learning_rate": 3.4140173410404623e-06, "loss": 0.4456, "step": 9822 }, { "epoch": 1.77, "learning_rate": 3.411307803468208e-06, "loss": 0.3449, "step": 9823 }, { "epoch": 1.77, "learning_rate": 3.408598265895954e-06, "loss": 0.5358, "step": 9824 }, { "epoch": 1.77, "learning_rate": 3.4058887283236996e-06, "loss": 0.7531, "step": 9825 }, { "epoch": 1.77, "learning_rate": 3.4031791907514453e-06, "loss": 0.1012, "step": 9826 }, { "epoch": 1.78, "learning_rate": 3.4004696531791905e-06, "loss": 0.5784, "step": 9827 }, { "epoch": 1.78, "learning_rate": 3.3977601156069365e-06, "loss": 1.0149, "step": 9828 }, { "epoch": 1.78, "learning_rate": 3.395050578034682e-06, "loss": 0.5137, "step": 9829 }, { "epoch": 1.78, "learning_rate": 3.392341040462428e-06, "loss": 0.5696, "step": 9830 }, { "epoch": 1.78, "learning_rate": 3.3896315028901734e-06, "loss": 0.2878, "step": 9831 }, { "epoch": 1.78, "learning_rate": 3.386921965317919e-06, "loss": 0.3066, "step": 9832 }, { "epoch": 1.78, "learning_rate": 3.3842124277456647e-06, "loss": 0.2646, "step": 9833 }, { "epoch": 1.78, "learning_rate": 3.3815028901734103e-06, "loss": 0.6319, "step": 9834 }, { "epoch": 1.78, "learning_rate": 3.3787933526011564e-06, "loss": 0.3803, "step": 9835 }, { "epoch": 1.78, "learning_rate": 3.376083815028902e-06, "loss": 0.7159, "step": 9836 }, { "epoch": 1.78, "learning_rate": 3.3733742774566473e-06, "loss": 0.3907, "step": 9837 }, { "epoch": 1.78, "learning_rate": 3.370664739884393e-06, "loss": 0.9375, "step": 9838 }, { "epoch": 1.78, "learning_rate": 3.367955202312139e-06, "loss": 0.4166, "step": 9839 }, { "epoch": 1.78, "learning_rate": 3.3652456647398846e-06, "loss": 0.5264, "step": 9840 }, { "epoch": 1.78, "learning_rate": 3.3625361271676302e-06, "loss": 0.6505, "step": 9841 }, { "epoch": 1.78, "learning_rate": 3.359826589595376e-06, "loss": 0.27, "step": 9842 }, { "epoch": 1.78, "learning_rate": 3.3571170520231215e-06, "loss": 0.3255, "step": 9843 }, { "epoch": 1.78, "learning_rate": 3.354407514450867e-06, "loss": 0.3856, "step": 9844 }, { "epoch": 1.78, "learning_rate": 3.3516979768786128e-06, "loss": 1.1744, "step": 9845 }, { "epoch": 1.78, "learning_rate": 3.3489884393063584e-06, "loss": 0.8862, "step": 9846 }, { "epoch": 1.78, "learning_rate": 3.3462789017341045e-06, "loss": 0.9625, "step": 9847 }, { "epoch": 1.78, "learning_rate": 3.3435693641618497e-06, "loss": 0.2971, "step": 9848 }, { "epoch": 1.78, "learning_rate": 3.3408598265895953e-06, "loss": 0.4978, "step": 9849 }, { "epoch": 1.78, "learning_rate": 3.338150289017341e-06, "loss": 0.6168, "step": 9850 }, { "epoch": 1.78, "learning_rate": 3.335440751445087e-06, "loss": 0.4859, "step": 9851 }, { "epoch": 1.78, "learning_rate": 3.3327312138728326e-06, "loss": 0.4418, "step": 9852 }, { "epoch": 1.78, "learning_rate": 3.330021676300578e-06, "loss": 0.7033, "step": 9853 }, { "epoch": 1.78, "learning_rate": 3.3273121387283235e-06, "loss": 0.4384, "step": 9854 }, { "epoch": 1.78, "learning_rate": 3.3246026011560695e-06, "loss": 0.2244, "step": 9855 }, { "epoch": 1.78, "learning_rate": 3.321893063583815e-06, "loss": 0.4479, "step": 9856 }, { "epoch": 1.78, "learning_rate": 3.319183526011561e-06, "loss": 0.3485, "step": 9857 }, { "epoch": 1.78, "learning_rate": 3.3164739884393064e-06, "loss": 0.5294, "step": 9858 }, { "epoch": 1.78, "learning_rate": 3.313764450867052e-06, "loss": 1.2461, "step": 9859 }, { "epoch": 1.78, "learning_rate": 3.3110549132947977e-06, "loss": 0.3354, "step": 9860 }, { "epoch": 1.78, "learning_rate": 3.3083453757225434e-06, "loss": 1.1664, "step": 9861 }, { "epoch": 1.78, "learning_rate": 3.3056358381502894e-06, "loss": 0.6709, "step": 9862 }, { "epoch": 1.78, "learning_rate": 3.302926300578035e-06, "loss": 0.445, "step": 9863 }, { "epoch": 1.78, "learning_rate": 3.3002167630057803e-06, "loss": 0.5011, "step": 9864 }, { "epoch": 1.78, "learning_rate": 3.297507225433526e-06, "loss": 0.3781, "step": 9865 }, { "epoch": 1.78, "learning_rate": 3.294797687861272e-06, "loss": 0.3936, "step": 9866 }, { "epoch": 1.78, "learning_rate": 3.2920881502890176e-06, "loss": 0.2707, "step": 9867 }, { "epoch": 1.78, "learning_rate": 3.2893786127167632e-06, "loss": 0.576, "step": 9868 }, { "epoch": 1.78, "learning_rate": 3.2866690751445084e-06, "loss": 0.653, "step": 9869 }, { "epoch": 1.78, "learning_rate": 3.2839595375722545e-06, "loss": 0.4714, "step": 9870 }, { "epoch": 1.78, "learning_rate": 3.28125e-06, "loss": 0.5152, "step": 9871 }, { "epoch": 1.78, "learning_rate": 3.2785404624277458e-06, "loss": 0.3508, "step": 9872 }, { "epoch": 1.78, "learning_rate": 3.2758309248554914e-06, "loss": 0.6293, "step": 9873 }, { "epoch": 1.78, "learning_rate": 3.273121387283237e-06, "loss": 0.1834, "step": 9874 }, { "epoch": 1.78, "learning_rate": 3.2704118497109827e-06, "loss": 0.324, "step": 9875 }, { "epoch": 1.78, "learning_rate": 3.2677023121387283e-06, "loss": 0.4805, "step": 9876 }, { "epoch": 1.78, "learning_rate": 3.264992774566474e-06, "loss": 0.5054, "step": 9877 }, { "epoch": 1.78, "learning_rate": 3.26228323699422e-06, "loss": 0.7851, "step": 9878 }, { "epoch": 1.78, "learning_rate": 3.2595736994219652e-06, "loss": 0.1897, "step": 9879 }, { "epoch": 1.78, "learning_rate": 3.256864161849711e-06, "loss": 0.7842, "step": 9880 }, { "epoch": 1.78, "learning_rate": 3.2541546242774565e-06, "loss": 0.7447, "step": 9881 }, { "epoch": 1.79, "learning_rate": 3.2514450867052026e-06, "loss": 0.4451, "step": 9882 }, { "epoch": 1.79, "learning_rate": 3.248735549132948e-06, "loss": 0.4044, "step": 9883 }, { "epoch": 1.79, "learning_rate": 3.246026011560694e-06, "loss": 0.1912, "step": 9884 }, { "epoch": 1.79, "learning_rate": 3.2433164739884395e-06, "loss": 0.6113, "step": 9885 }, { "epoch": 1.79, "learning_rate": 3.240606936416185e-06, "loss": 0.2686, "step": 9886 }, { "epoch": 1.79, "learning_rate": 3.2378973988439307e-06, "loss": 0.1129, "step": 9887 }, { "epoch": 1.79, "learning_rate": 3.2351878612716764e-06, "loss": 0.4242, "step": 9888 }, { "epoch": 1.79, "learning_rate": 3.2324783236994224e-06, "loss": 0.3603, "step": 9889 }, { "epoch": 1.79, "learning_rate": 3.2297687861271676e-06, "loss": 0.7047, "step": 9890 }, { "epoch": 1.79, "learning_rate": 3.2270592485549133e-06, "loss": 0.6513, "step": 9891 }, { "epoch": 1.79, "learning_rate": 3.224349710982659e-06, "loss": 0.7026, "step": 9892 }, { "epoch": 1.79, "learning_rate": 3.221640173410405e-06, "loss": 0.5527, "step": 9893 }, { "epoch": 1.79, "learning_rate": 3.2189306358381506e-06, "loss": 0.3842, "step": 9894 }, { "epoch": 1.79, "learning_rate": 3.216221098265896e-06, "loss": 0.4419, "step": 9895 }, { "epoch": 1.79, "learning_rate": 3.2135115606936414e-06, "loss": 1.3477, "step": 9896 }, { "epoch": 1.79, "learning_rate": 3.2108020231213875e-06, "loss": 0.4421, "step": 9897 }, { "epoch": 1.79, "learning_rate": 3.208092485549133e-06, "loss": 0.4013, "step": 9898 }, { "epoch": 1.79, "learning_rate": 3.2053829479768788e-06, "loss": 0.9191, "step": 9899 }, { "epoch": 1.79, "learning_rate": 3.202673410404624e-06, "loss": 0.4927, "step": 9900 }, { "epoch": 1.79, "learning_rate": 3.19996387283237e-06, "loss": 0.574, "step": 9901 }, { "epoch": 1.79, "learning_rate": 3.1972543352601157e-06, "loss": 0.6694, "step": 9902 }, { "epoch": 1.79, "learning_rate": 3.1945447976878613e-06, "loss": 0.8717, "step": 9903 }, { "epoch": 1.79, "learning_rate": 3.191835260115607e-06, "loss": 0.6915, "step": 9904 }, { "epoch": 1.79, "learning_rate": 3.189125722543353e-06, "loss": 0.3268, "step": 9905 }, { "epoch": 1.79, "learning_rate": 3.1864161849710982e-06, "loss": 0.8088, "step": 9906 }, { "epoch": 1.79, "learning_rate": 3.183706647398844e-06, "loss": 0.5882, "step": 9907 }, { "epoch": 1.79, "learning_rate": 3.1809971098265895e-06, "loss": 0.5179, "step": 9908 }, { "epoch": 1.79, "learning_rate": 3.1782875722543356e-06, "loss": 0.3502, "step": 9909 }, { "epoch": 1.79, "learning_rate": 3.175578034682081e-06, "loss": 0.3826, "step": 9910 }, { "epoch": 1.79, "learning_rate": 3.1728684971098264e-06, "loss": 0.2361, "step": 9911 }, { "epoch": 1.79, "learning_rate": 3.1701589595375725e-06, "loss": 0.9505, "step": 9912 }, { "epoch": 1.79, "learning_rate": 3.167449421965318e-06, "loss": 0.4416, "step": 9913 }, { "epoch": 1.79, "learning_rate": 3.1647398843930637e-06, "loss": 0.8791, "step": 9914 }, { "epoch": 1.79, "learning_rate": 3.1620303468208094e-06, "loss": 0.3247, "step": 9915 }, { "epoch": 1.79, "learning_rate": 3.159320809248555e-06, "loss": 0.4159, "step": 9916 }, { "epoch": 1.79, "learning_rate": 3.1566112716763006e-06, "loss": 0.3606, "step": 9917 }, { "epoch": 1.79, "learning_rate": 3.1539017341040463e-06, "loss": 0.464, "step": 9918 }, { "epoch": 1.79, "learning_rate": 3.151192196531792e-06, "loss": 0.6573, "step": 9919 }, { "epoch": 1.79, "learning_rate": 3.148482658959538e-06, "loss": 0.8724, "step": 9920 }, { "epoch": 1.79, "learning_rate": 3.145773121387283e-06, "loss": 0.7034, "step": 9921 }, { "epoch": 1.79, "learning_rate": 3.143063583815029e-06, "loss": 0.3501, "step": 9922 }, { "epoch": 1.79, "learning_rate": 3.1403540462427745e-06, "loss": 0.519, "step": 9923 }, { "epoch": 1.79, "learning_rate": 3.1376445086705205e-06, "loss": 0.6966, "step": 9924 }, { "epoch": 1.79, "learning_rate": 3.134934971098266e-06, "loss": 0.2762, "step": 9925 }, { "epoch": 1.79, "learning_rate": 3.1322254335260118e-06, "loss": 0.9254, "step": 9926 }, { "epoch": 1.79, "learning_rate": 3.129515895953757e-06, "loss": 0.2954, "step": 9927 }, { "epoch": 1.79, "learning_rate": 3.126806358381503e-06, "loss": 0.7038, "step": 9928 }, { "epoch": 1.79, "learning_rate": 3.1240968208092487e-06, "loss": 0.4188, "step": 9929 }, { "epoch": 1.79, "learning_rate": 3.1213872832369943e-06, "loss": 0.1973, "step": 9930 }, { "epoch": 1.79, "learning_rate": 3.11867774566474e-06, "loss": 0.4815, "step": 9931 }, { "epoch": 1.79, "learning_rate": 3.1159682080924856e-06, "loss": 0.5386, "step": 9932 }, { "epoch": 1.79, "learning_rate": 3.1132586705202312e-06, "loss": 0.5671, "step": 9933 }, { "epoch": 1.79, "learning_rate": 3.110549132947977e-06, "loss": 0.465, "step": 9934 }, { "epoch": 1.79, "learning_rate": 3.1078395953757225e-06, "loss": 0.5019, "step": 9935 }, { "epoch": 1.79, "learning_rate": 3.1051300578034686e-06, "loss": 0.5151, "step": 9936 }, { "epoch": 1.79, "learning_rate": 3.1024205202312138e-06, "loss": 0.564, "step": 9937 }, { "epoch": 1.8, "learning_rate": 3.0997109826589594e-06, "loss": 0.4106, "step": 9938 }, { "epoch": 1.8, "learning_rate": 3.0970014450867055e-06, "loss": 0.5742, "step": 9939 }, { "epoch": 1.8, "learning_rate": 3.094291907514451e-06, "loss": 0.209, "step": 9940 }, { "epoch": 1.8, "learning_rate": 3.0915823699421967e-06, "loss": 0.5313, "step": 9941 }, { "epoch": 1.8, "learning_rate": 3.088872832369942e-06, "loss": 0.4816, "step": 9942 }, { "epoch": 1.8, "learning_rate": 3.086163294797688e-06, "loss": 0.3755, "step": 9943 }, { "epoch": 1.8, "learning_rate": 3.0834537572254337e-06, "loss": 0.5655, "step": 9944 }, { "epoch": 1.8, "learning_rate": 3.0807442196531793e-06, "loss": 0.4009, "step": 9945 }, { "epoch": 1.8, "learning_rate": 3.078034682080925e-06, "loss": 0.4859, "step": 9946 }, { "epoch": 1.8, "learning_rate": 3.075325144508671e-06, "loss": 0.4246, "step": 9947 }, { "epoch": 1.8, "learning_rate": 3.072615606936416e-06, "loss": 0.4926, "step": 9948 }, { "epoch": 1.8, "learning_rate": 3.069906069364162e-06, "loss": 0.5569, "step": 9949 }, { "epoch": 1.8, "learning_rate": 3.0671965317919075e-06, "loss": 0.5791, "step": 9950 }, { "epoch": 1.8, "learning_rate": 3.0644869942196535e-06, "loss": 0.3542, "step": 9951 }, { "epoch": 1.8, "learning_rate": 3.061777456647399e-06, "loss": 0.5629, "step": 9952 }, { "epoch": 1.8, "learning_rate": 3.0590679190751444e-06, "loss": 0.2411, "step": 9953 }, { "epoch": 1.8, "learning_rate": 3.05635838150289e-06, "loss": 0.2776, "step": 9954 }, { "epoch": 1.8, "learning_rate": 3.053648843930636e-06, "loss": 1.195, "step": 9955 }, { "epoch": 1.8, "learning_rate": 3.0509393063583817e-06, "loss": 0.8534, "step": 9956 }, { "epoch": 1.8, "learning_rate": 3.0482297687861273e-06, "loss": 0.4371, "step": 9957 }, { "epoch": 1.8, "learning_rate": 3.0455202312138726e-06, "loss": 1.1037, "step": 9958 }, { "epoch": 1.8, "learning_rate": 3.0428106936416186e-06, "loss": 0.4546, "step": 9959 }, { "epoch": 1.8, "learning_rate": 3.0401011560693642e-06, "loss": 0.3735, "step": 9960 }, { "epoch": 1.8, "learning_rate": 3.03739161849711e-06, "loss": 0.308, "step": 9961 }, { "epoch": 1.8, "learning_rate": 3.0346820809248555e-06, "loss": 0.516, "step": 9962 }, { "epoch": 1.8, "learning_rate": 3.031972543352601e-06, "loss": 0.8288, "step": 9963 }, { "epoch": 1.8, "learning_rate": 3.0292630057803468e-06, "loss": 0.4264, "step": 9964 }, { "epoch": 1.8, "learning_rate": 3.0265534682080924e-06, "loss": 0.8058, "step": 9965 }, { "epoch": 1.8, "learning_rate": 3.0238439306358385e-06, "loss": 0.3561, "step": 9966 }, { "epoch": 1.8, "learning_rate": 3.021134393063584e-06, "loss": 0.214, "step": 9967 }, { "epoch": 1.8, "learning_rate": 3.0184248554913293e-06, "loss": 0.4067, "step": 9968 }, { "epoch": 1.8, "learning_rate": 3.015715317919075e-06, "loss": 0.412, "step": 9969 }, { "epoch": 1.8, "learning_rate": 3.013005780346821e-06, "loss": 0.9904, "step": 9970 }, { "epoch": 1.8, "learning_rate": 3.0102962427745667e-06, "loss": 0.2413, "step": 9971 }, { "epoch": 1.8, "learning_rate": 3.0075867052023123e-06, "loss": 0.6834, "step": 9972 }, { "epoch": 1.8, "learning_rate": 3.004877167630058e-06, "loss": 1.1191, "step": 9973 }, { "epoch": 1.8, "learning_rate": 3.0021676300578036e-06, "loss": 0.4602, "step": 9974 }, { "epoch": 1.8, "learning_rate": 2.999458092485549e-06, "loss": 0.5646, "step": 9975 }, { "epoch": 1.8, "learning_rate": 2.996748554913295e-06, "loss": 0.4224, "step": 9976 }, { "epoch": 1.8, "learning_rate": 2.9940390173410405e-06, "loss": 0.8196, "step": 9977 }, { "epoch": 1.8, "learning_rate": 2.9913294797687865e-06, "loss": 0.7468, "step": 9978 }, { "epoch": 1.8, "learning_rate": 2.9886199421965317e-06, "loss": 0.9433, "step": 9979 }, { "epoch": 1.8, "learning_rate": 2.9859104046242774e-06, "loss": 0.3492, "step": 9980 }, { "epoch": 1.8, "learning_rate": 2.983200867052023e-06, "loss": 0.3581, "step": 9981 }, { "epoch": 1.8, "learning_rate": 2.980491329479769e-06, "loss": 1.2884, "step": 9982 }, { "epoch": 1.8, "learning_rate": 2.9777817919075147e-06, "loss": 0.55, "step": 9983 }, { "epoch": 1.8, "learning_rate": 2.97507225433526e-06, "loss": 0.5604, "step": 9984 }, { "epoch": 1.8, "learning_rate": 2.9723627167630056e-06, "loss": 0.4151, "step": 9985 }, { "epoch": 1.8, "learning_rate": 2.9696531791907516e-06, "loss": 0.7904, "step": 9986 }, { "epoch": 1.8, "learning_rate": 2.9669436416184973e-06, "loss": 0.3543, "step": 9987 }, { "epoch": 1.8, "learning_rate": 2.964234104046243e-06, "loss": 0.6624, "step": 9988 }, { "epoch": 1.8, "learning_rate": 2.961524566473988e-06, "loss": 0.2759, "step": 9989 }, { "epoch": 1.8, "learning_rate": 2.958815028901734e-06, "loss": 0.4312, "step": 9990 }, { "epoch": 1.8, "learning_rate": 2.95610549132948e-06, "loss": 0.5006, "step": 9991 }, { "epoch": 1.8, "learning_rate": 2.9533959537572254e-06, "loss": 0.5552, "step": 9992 }, { "epoch": 1.81, "learning_rate": 2.9506864161849715e-06, "loss": 0.5452, "step": 9993 }, { "epoch": 1.81, "learning_rate": 2.947976878612717e-06, "loss": 0.2433, "step": 9994 }, { "epoch": 1.81, "learning_rate": 2.9452673410404623e-06, "loss": 0.706, "step": 9995 }, { "epoch": 1.81, "learning_rate": 2.942557803468208e-06, "loss": 0.2937, "step": 9996 }, { "epoch": 1.81, "learning_rate": 2.939848265895954e-06, "loss": 0.7166, "step": 9997 }, { "epoch": 1.81, "learning_rate": 2.9371387283236997e-06, "loss": 0.8311, "step": 9998 }, { "epoch": 1.81, "learning_rate": 2.9344291907514453e-06, "loss": 0.5299, "step": 9999 }, { "epoch": 1.81, "learning_rate": 2.9317196531791905e-06, "loss": 0.7862, "step": 10000 }, { "epoch": 1.81, "eval_exact_match": 88.4484389782403, "eval_f1": 94.17701356891143, "step": 10000 }, { "epoch": 1.81, "learning_rate": 2.9290101156069366e-06, "loss": 0.4851, "step": 10001 }, { "epoch": 1.81, "learning_rate": 2.926300578034682e-06, "loss": 0.5107, "step": 10002 }, { "epoch": 1.81, "learning_rate": 2.923591040462428e-06, "loss": 0.315, "step": 10003 }, { "epoch": 1.81, "learning_rate": 2.9208815028901735e-06, "loss": 0.2134, "step": 10004 }, { "epoch": 1.81, "learning_rate": 2.918171965317919e-06, "loss": 0.5552, "step": 10005 }, { "epoch": 1.81, "learning_rate": 2.9154624277456648e-06, "loss": 0.6257, "step": 10006 }, { "epoch": 1.81, "learning_rate": 2.9127528901734104e-06, "loss": 0.3164, "step": 10007 }, { "epoch": 1.81, "learning_rate": 2.910043352601156e-06, "loss": 0.7179, "step": 10008 }, { "epoch": 1.81, "learning_rate": 2.907333815028902e-06, "loss": 0.9593, "step": 10009 }, { "epoch": 1.81, "learning_rate": 2.9046242774566473e-06, "loss": 0.1762, "step": 10010 }, { "epoch": 1.81, "learning_rate": 2.901914739884393e-06, "loss": 0.6361, "step": 10011 }, { "epoch": 1.81, "learning_rate": 2.8992052023121386e-06, "loss": 0.9534, "step": 10012 }, { "epoch": 1.81, "learning_rate": 2.8964956647398846e-06, "loss": 0.3478, "step": 10013 }, { "epoch": 1.81, "learning_rate": 2.8937861271676303e-06, "loss": 0.4516, "step": 10014 }, { "epoch": 1.81, "learning_rate": 2.891076589595376e-06, "loss": 0.6815, "step": 10015 }, { "epoch": 1.81, "learning_rate": 2.888367052023121e-06, "loss": 0.57, "step": 10016 }, { "epoch": 1.81, "learning_rate": 2.885657514450867e-06, "loss": 0.2497, "step": 10017 }, { "epoch": 1.81, "learning_rate": 2.882947976878613e-06, "loss": 0.4156, "step": 10018 }, { "epoch": 1.81, "learning_rate": 2.8802384393063584e-06, "loss": 1.0058, "step": 10019 }, { "epoch": 1.81, "learning_rate": 2.8775289017341045e-06, "loss": 0.6416, "step": 10020 }, { "epoch": 1.81, "learning_rate": 2.8748193641618497e-06, "loss": 0.3232, "step": 10021 }, { "epoch": 1.81, "learning_rate": 2.8721098265895953e-06, "loss": 0.4, "step": 10022 }, { "epoch": 1.81, "learning_rate": 2.869400289017341e-06, "loss": 0.4981, "step": 10023 }, { "epoch": 1.81, "learning_rate": 2.866690751445087e-06, "loss": 0.8073, "step": 10024 }, { "epoch": 1.81, "learning_rate": 2.8639812138728327e-06, "loss": 0.9757, "step": 10025 }, { "epoch": 1.81, "learning_rate": 2.861271676300578e-06, "loss": 1.2391, "step": 10026 }, { "epoch": 1.81, "learning_rate": 2.8585621387283235e-06, "loss": 0.4955, "step": 10027 }, { "epoch": 1.81, "learning_rate": 2.8558526011560696e-06, "loss": 0.399, "step": 10028 }, { "epoch": 1.81, "learning_rate": 2.8531430635838152e-06, "loss": 0.9493, "step": 10029 }, { "epoch": 1.81, "learning_rate": 2.850433526011561e-06, "loss": 0.6487, "step": 10030 }, { "epoch": 1.81, "learning_rate": 2.847723988439306e-06, "loss": 0.7716, "step": 10031 }, { "epoch": 1.81, "learning_rate": 2.845014450867052e-06, "loss": 0.5341, "step": 10032 }, { "epoch": 1.81, "learning_rate": 2.8423049132947978e-06, "loss": 0.9526, "step": 10033 }, { "epoch": 1.81, "learning_rate": 2.8395953757225434e-06, "loss": 0.5772, "step": 10034 }, { "epoch": 1.81, "learning_rate": 2.836885838150289e-06, "loss": 0.7841, "step": 10035 }, { "epoch": 1.81, "learning_rate": 2.834176300578035e-06, "loss": 0.5688, "step": 10036 }, { "epoch": 1.81, "learning_rate": 2.8314667630057803e-06, "loss": 0.4182, "step": 10037 }, { "epoch": 1.81, "learning_rate": 2.828757225433526e-06, "loss": 0.7693, "step": 10038 }, { "epoch": 1.81, "learning_rate": 2.8260476878612716e-06, "loss": 0.4056, "step": 10039 }, { "epoch": 1.81, "learning_rate": 2.8233381502890176e-06, "loss": 0.746, "step": 10040 }, { "epoch": 1.81, "learning_rate": 2.8206286127167633e-06, "loss": 0.672, "step": 10041 }, { "epoch": 1.81, "learning_rate": 2.8179190751445085e-06, "loss": 0.6975, "step": 10042 }, { "epoch": 1.81, "learning_rate": 2.815209537572254e-06, "loss": 0.6544, "step": 10043 }, { "epoch": 1.81, "learning_rate": 2.8125e-06, "loss": 0.4114, "step": 10044 }, { "epoch": 1.81, "learning_rate": 2.809790462427746e-06, "loss": 0.334, "step": 10045 }, { "epoch": 1.81, "learning_rate": 2.8070809248554914e-06, "loss": 0.4429, "step": 10046 }, { "epoch": 1.81, "learning_rate": 2.804371387283237e-06, "loss": 0.1693, "step": 10047 }, { "epoch": 1.82, "learning_rate": 2.8016618497109827e-06, "loss": 0.5634, "step": 10048 }, { "epoch": 1.82, "learning_rate": 2.7989523121387284e-06, "loss": 0.9396, "step": 10049 }, { "epoch": 1.82, "learning_rate": 2.796242774566474e-06, "loss": 0.661, "step": 10050 }, { "epoch": 1.82, "learning_rate": 2.79353323699422e-06, "loss": 0.5224, "step": 10051 }, { "epoch": 1.82, "learning_rate": 2.7908236994219653e-06, "loss": 0.695, "step": 10052 }, { "epoch": 1.82, "learning_rate": 2.788114161849711e-06, "loss": 0.52, "step": 10053 }, { "epoch": 1.82, "learning_rate": 2.7854046242774565e-06, "loss": 0.2501, "step": 10054 }, { "epoch": 1.82, "learning_rate": 2.7826950867052026e-06, "loss": 0.7376, "step": 10055 }, { "epoch": 1.82, "learning_rate": 2.7799855491329482e-06, "loss": 0.5237, "step": 10056 }, { "epoch": 1.82, "learning_rate": 2.777276011560694e-06, "loss": 0.5392, "step": 10057 }, { "epoch": 1.82, "learning_rate": 2.774566473988439e-06, "loss": 0.163, "step": 10058 }, { "epoch": 1.82, "learning_rate": 2.771856936416185e-06, "loss": 0.2884, "step": 10059 }, { "epoch": 1.82, "learning_rate": 2.7691473988439308e-06, "loss": 0.1348, "step": 10060 }, { "epoch": 1.82, "learning_rate": 2.7664378612716764e-06, "loss": 0.8669, "step": 10061 }, { "epoch": 1.82, "learning_rate": 2.763728323699422e-06, "loss": 0.7657, "step": 10062 }, { "epoch": 1.82, "learning_rate": 2.7610187861271677e-06, "loss": 0.5208, "step": 10063 }, { "epoch": 1.82, "learning_rate": 2.7583092485549133e-06, "loss": 0.9024, "step": 10064 }, { "epoch": 1.82, "learning_rate": 2.755599710982659e-06, "loss": 0.9611, "step": 10065 }, { "epoch": 1.82, "learning_rate": 2.7528901734104046e-06, "loss": 0.5605, "step": 10066 }, { "epoch": 1.82, "learning_rate": 2.7501806358381506e-06, "loss": 0.3189, "step": 10067 }, { "epoch": 1.82, "learning_rate": 2.747471098265896e-06, "loss": 0.2446, "step": 10068 }, { "epoch": 1.82, "learning_rate": 2.7447615606936415e-06, "loss": 0.5156, "step": 10069 }, { "epoch": 1.82, "learning_rate": 2.742052023121387e-06, "loss": 0.5502, "step": 10070 }, { "epoch": 1.82, "learning_rate": 2.739342485549133e-06, "loss": 0.6849, "step": 10071 }, { "epoch": 1.82, "learning_rate": 2.736632947976879e-06, "loss": 0.298, "step": 10072 }, { "epoch": 1.82, "learning_rate": 2.733923410404624e-06, "loss": 1.238, "step": 10073 }, { "epoch": 1.82, "learning_rate": 2.73121387283237e-06, "loss": 0.6923, "step": 10074 }, { "epoch": 1.82, "learning_rate": 2.7285043352601157e-06, "loss": 0.4132, "step": 10075 }, { "epoch": 1.82, "learning_rate": 2.7257947976878614e-06, "loss": 0.4552, "step": 10076 }, { "epoch": 1.82, "learning_rate": 2.723085260115607e-06, "loss": 0.4415, "step": 10077 }, { "epoch": 1.82, "learning_rate": 2.720375722543353e-06, "loss": 0.7861, "step": 10078 }, { "epoch": 1.82, "learning_rate": 2.7176661849710983e-06, "loss": 0.5424, "step": 10079 }, { "epoch": 1.82, "learning_rate": 2.714956647398844e-06, "loss": 0.6246, "step": 10080 }, { "epoch": 1.82, "learning_rate": 2.7122471098265895e-06, "loss": 0.4649, "step": 10081 }, { "epoch": 1.82, "learning_rate": 2.7095375722543356e-06, "loss": 0.8815, "step": 10082 }, { "epoch": 1.82, "learning_rate": 2.7068280346820812e-06, "loss": 0.5572, "step": 10083 }, { "epoch": 1.82, "learning_rate": 2.7041184971098264e-06, "loss": 0.4127, "step": 10084 }, { "epoch": 1.82, "learning_rate": 2.701408959537572e-06, "loss": 0.9134, "step": 10085 }, { "epoch": 1.82, "learning_rate": 2.698699421965318e-06, "loss": 0.3817, "step": 10086 }, { "epoch": 1.82, "learning_rate": 2.6959898843930638e-06, "loss": 0.4855, "step": 10087 }, { "epoch": 1.82, "learning_rate": 2.6932803468208094e-06, "loss": 0.5171, "step": 10088 }, { "epoch": 1.82, "learning_rate": 2.6905708092485546e-06, "loss": 0.446, "step": 10089 }, { "epoch": 1.82, "learning_rate": 2.6878612716763007e-06, "loss": 0.3701, "step": 10090 }, { "epoch": 1.82, "learning_rate": 2.6851517341040463e-06, "loss": 0.2805, "step": 10091 }, { "epoch": 1.82, "learning_rate": 2.682442196531792e-06, "loss": 0.3707, "step": 10092 }, { "epoch": 1.82, "learning_rate": 2.6797326589595376e-06, "loss": 0.4728, "step": 10093 }, { "epoch": 1.82, "learning_rate": 2.6770231213872832e-06, "loss": 0.7412, "step": 10094 }, { "epoch": 1.82, "learning_rate": 2.674313583815029e-06, "loss": 0.5506, "step": 10095 }, { "epoch": 1.82, "learning_rate": 2.6716040462427745e-06, "loss": 0.8216, "step": 10096 }, { "epoch": 1.82, "learning_rate": 2.66889450867052e-06, "loss": 0.3573, "step": 10097 }, { "epoch": 1.82, "learning_rate": 2.666184971098266e-06, "loss": 0.5165, "step": 10098 }, { "epoch": 1.82, "learning_rate": 2.663475433526012e-06, "loss": 0.6671, "step": 10099 }, { "epoch": 1.82, "learning_rate": 2.660765895953757e-06, "loss": 0.3544, "step": 10100 }, { "epoch": 1.82, "learning_rate": 2.658056358381503e-06, "loss": 0.5249, "step": 10101 }, { "epoch": 1.82, "learning_rate": 2.6553468208092487e-06, "loss": 0.466, "step": 10102 }, { "epoch": 1.82, "learning_rate": 2.6526372832369944e-06, "loss": 0.3527, "step": 10103 }, { "epoch": 1.83, "learning_rate": 2.64992774566474e-06, "loss": 0.6992, "step": 10104 }, { "epoch": 1.83, "learning_rate": 2.6472182080924856e-06, "loss": 0.5917, "step": 10105 }, { "epoch": 1.83, "learning_rate": 2.6445086705202313e-06, "loss": 0.4214, "step": 10106 }, { "epoch": 1.83, "learning_rate": 2.641799132947977e-06, "loss": 0.9749, "step": 10107 }, { "epoch": 1.83, "learning_rate": 2.6390895953757225e-06, "loss": 0.644, "step": 10108 }, { "epoch": 1.83, "learning_rate": 2.6363800578034686e-06, "loss": 0.3361, "step": 10109 }, { "epoch": 1.83, "learning_rate": 2.633670520231214e-06, "loss": 0.139, "step": 10110 }, { "epoch": 1.83, "learning_rate": 2.6309609826589595e-06, "loss": 0.5525, "step": 10111 }, { "epoch": 1.83, "learning_rate": 2.628251445086705e-06, "loss": 0.549, "step": 10112 }, { "epoch": 1.83, "learning_rate": 2.625541907514451e-06, "loss": 0.7052, "step": 10113 }, { "epoch": 1.83, "learning_rate": 2.6228323699421968e-06, "loss": 0.4976, "step": 10114 }, { "epoch": 1.83, "learning_rate": 2.620122832369942e-06, "loss": 0.9314, "step": 10115 }, { "epoch": 1.83, "learning_rate": 2.6174132947976876e-06, "loss": 0.5389, "step": 10116 }, { "epoch": 1.83, "learning_rate": 2.6147037572254337e-06, "loss": 0.3922, "step": 10117 }, { "epoch": 1.83, "learning_rate": 2.6119942196531793e-06, "loss": 0.6406, "step": 10118 }, { "epoch": 1.83, "learning_rate": 2.609284682080925e-06, "loss": 0.7208, "step": 10119 }, { "epoch": 1.83, "learning_rate": 2.6065751445086706e-06, "loss": 0.4944, "step": 10120 }, { "epoch": 1.83, "learning_rate": 2.6038656069364162e-06, "loss": 0.2263, "step": 10121 }, { "epoch": 1.83, "learning_rate": 2.601156069364162e-06, "loss": 0.2381, "step": 10122 }, { "epoch": 1.83, "learning_rate": 2.5984465317919075e-06, "loss": 1.233, "step": 10123 }, { "epoch": 1.83, "learning_rate": 2.595736994219653e-06, "loss": 0.3391, "step": 10124 }, { "epoch": 1.83, "learning_rate": 2.593027456647399e-06, "loss": 0.3474, "step": 10125 }, { "epoch": 1.83, "learning_rate": 2.5903179190751444e-06, "loss": 0.6172, "step": 10126 }, { "epoch": 1.83, "learning_rate": 2.58760838150289e-06, "loss": 0.541, "step": 10127 }, { "epoch": 1.83, "learning_rate": 2.584898843930636e-06, "loss": 0.5995, "step": 10128 }, { "epoch": 1.83, "learning_rate": 2.5821893063583817e-06, "loss": 0.4597, "step": 10129 }, { "epoch": 1.83, "learning_rate": 2.5794797687861274e-06, "loss": 0.4809, "step": 10130 }, { "epoch": 1.83, "learning_rate": 2.5767702312138726e-06, "loss": 0.2128, "step": 10131 }, { "epoch": 1.83, "learning_rate": 2.5740606936416187e-06, "loss": 0.5805, "step": 10132 }, { "epoch": 1.83, "learning_rate": 2.5713511560693643e-06, "loss": 0.3151, "step": 10133 }, { "epoch": 1.83, "learning_rate": 2.56864161849711e-06, "loss": 0.6704, "step": 10134 }, { "epoch": 1.83, "learning_rate": 2.5659320809248556e-06, "loss": 0.5974, "step": 10135 }, { "epoch": 1.83, "learning_rate": 2.563222543352601e-06, "loss": 0.6325, "step": 10136 }, { "epoch": 1.83, "learning_rate": 2.560513005780347e-06, "loss": 0.1959, "step": 10137 }, { "epoch": 1.83, "learning_rate": 2.5578034682080925e-06, "loss": 0.7778, "step": 10138 }, { "epoch": 1.83, "learning_rate": 2.555093930635838e-06, "loss": 0.3029, "step": 10139 }, { "epoch": 1.83, "learning_rate": 2.552384393063584e-06, "loss": 0.8074, "step": 10140 }, { "epoch": 1.83, "learning_rate": 2.5496748554913294e-06, "loss": 0.3296, "step": 10141 }, { "epoch": 1.83, "learning_rate": 2.546965317919075e-06, "loss": 0.4692, "step": 10142 }, { "epoch": 1.83, "learning_rate": 2.5442557803468206e-06, "loss": 0.3908, "step": 10143 }, { "epoch": 1.83, "learning_rate": 2.5415462427745667e-06, "loss": 0.3923, "step": 10144 }, { "epoch": 1.83, "learning_rate": 2.5388367052023123e-06, "loss": 0.9565, "step": 10145 }, { "epoch": 1.83, "learning_rate": 2.536127167630058e-06, "loss": 0.2596, "step": 10146 }, { "epoch": 1.83, "learning_rate": 2.533417630057803e-06, "loss": 0.3487, "step": 10147 }, { "epoch": 1.83, "learning_rate": 2.5307080924855492e-06, "loss": 0.6205, "step": 10148 }, { "epoch": 1.83, "learning_rate": 2.527998554913295e-06, "loss": 0.5452, "step": 10149 }, { "epoch": 1.83, "learning_rate": 2.5252890173410405e-06, "loss": 0.5676, "step": 10150 }, { "epoch": 1.83, "learning_rate": 2.522579479768786e-06, "loss": 0.2764, "step": 10151 }, { "epoch": 1.83, "learning_rate": 2.5198699421965318e-06, "loss": 0.512, "step": 10152 }, { "epoch": 1.83, "learning_rate": 2.5171604046242774e-06, "loss": 0.6193, "step": 10153 }, { "epoch": 1.83, "learning_rate": 2.514450867052023e-06, "loss": 1.1272, "step": 10154 }, { "epoch": 1.83, "learning_rate": 2.511741329479769e-06, "loss": 0.5523, "step": 10155 }, { "epoch": 1.83, "learning_rate": 2.5090317919075148e-06, "loss": 0.7195, "step": 10156 }, { "epoch": 1.83, "learning_rate": 2.50632225433526e-06, "loss": 0.2757, "step": 10157 }, { "epoch": 1.83, "learning_rate": 2.5036127167630056e-06, "loss": 0.6727, "step": 10158 }, { "epoch": 1.84, "learning_rate": 2.5009031791907517e-06, "loss": 0.3076, "step": 10159 }, { "epoch": 1.84, "learning_rate": 2.4981936416184973e-06, "loss": 0.322, "step": 10160 }, { "epoch": 1.84, "learning_rate": 2.495484104046243e-06, "loss": 0.747, "step": 10161 }, { "epoch": 1.84, "learning_rate": 2.492774566473988e-06, "loss": 0.5958, "step": 10162 }, { "epoch": 1.84, "learning_rate": 2.490065028901734e-06, "loss": 0.3213, "step": 10163 }, { "epoch": 1.84, "learning_rate": 2.48735549132948e-06, "loss": 0.5393, "step": 10164 }, { "epoch": 1.84, "learning_rate": 2.4846459537572255e-06, "loss": 0.6048, "step": 10165 }, { "epoch": 1.84, "learning_rate": 2.481936416184971e-06, "loss": 0.5907, "step": 10166 }, { "epoch": 1.84, "learning_rate": 2.479226878612717e-06, "loss": 0.6878, "step": 10167 }, { "epoch": 1.84, "learning_rate": 2.4765173410404624e-06, "loss": 0.2147, "step": 10168 }, { "epoch": 1.84, "learning_rate": 2.473807803468208e-06, "loss": 0.4185, "step": 10169 }, { "epoch": 1.84, "learning_rate": 2.4710982658959537e-06, "loss": 0.5719, "step": 10170 }, { "epoch": 1.84, "learning_rate": 2.4683887283236997e-06, "loss": 0.8127, "step": 10171 }, { "epoch": 1.84, "learning_rate": 2.4656791907514453e-06, "loss": 0.2101, "step": 10172 }, { "epoch": 1.84, "learning_rate": 2.4629696531791906e-06, "loss": 0.1988, "step": 10173 }, { "epoch": 1.84, "learning_rate": 2.460260115606936e-06, "loss": 0.6307, "step": 10174 }, { "epoch": 1.84, "learning_rate": 2.4575505780346823e-06, "loss": 0.4634, "step": 10175 }, { "epoch": 1.84, "learning_rate": 2.454841040462428e-06, "loss": 0.4847, "step": 10176 }, { "epoch": 1.84, "learning_rate": 2.4521315028901735e-06, "loss": 0.2465, "step": 10177 }, { "epoch": 1.84, "learning_rate": 2.449421965317919e-06, "loss": 0.5893, "step": 10178 }, { "epoch": 1.84, "learning_rate": 2.446712427745665e-06, "loss": 0.2013, "step": 10179 }, { "epoch": 1.84, "learning_rate": 2.4440028901734104e-06, "loss": 0.3695, "step": 10180 }, { "epoch": 1.84, "learning_rate": 2.441293352601156e-06, "loss": 0.5753, "step": 10181 }, { "epoch": 1.84, "learning_rate": 2.438583815028902e-06, "loss": 0.4372, "step": 10182 }, { "epoch": 1.84, "learning_rate": 2.4358742774566473e-06, "loss": 0.7401, "step": 10183 }, { "epoch": 1.84, "learning_rate": 2.433164739884393e-06, "loss": 0.5199, "step": 10184 }, { "epoch": 1.84, "learning_rate": 2.4304552023121386e-06, "loss": 0.2153, "step": 10185 }, { "epoch": 1.84, "learning_rate": 2.4277456647398847e-06, "loss": 0.4386, "step": 10186 }, { "epoch": 1.84, "learning_rate": 2.4250361271676303e-06, "loss": 0.3062, "step": 10187 }, { "epoch": 1.84, "learning_rate": 2.422326589595376e-06, "loss": 0.3146, "step": 10188 }, { "epoch": 1.84, "learning_rate": 2.419617052023121e-06, "loss": 0.7551, "step": 10189 }, { "epoch": 1.84, "learning_rate": 2.416907514450867e-06, "loss": 0.4609, "step": 10190 }, { "epoch": 1.84, "learning_rate": 2.414197976878613e-06, "loss": 0.2894, "step": 10191 }, { "epoch": 1.84, "learning_rate": 2.4114884393063585e-06, "loss": 0.5758, "step": 10192 }, { "epoch": 1.84, "learning_rate": 2.408778901734104e-06, "loss": 0.2849, "step": 10193 }, { "epoch": 1.84, "learning_rate": 2.4060693641618498e-06, "loss": 0.1416, "step": 10194 }, { "epoch": 1.84, "learning_rate": 2.4033598265895954e-06, "loss": 0.415, "step": 10195 }, { "epoch": 1.84, "learning_rate": 2.400650289017341e-06, "loss": 0.5971, "step": 10196 }, { "epoch": 1.84, "learning_rate": 2.3979407514450867e-06, "loss": 0.5067, "step": 10197 }, { "epoch": 1.84, "learning_rate": 2.3952312138728327e-06, "loss": 0.3424, "step": 10198 }, { "epoch": 1.84, "learning_rate": 2.392521676300578e-06, "loss": 0.7866, "step": 10199 }, { "epoch": 1.84, "learning_rate": 2.3898121387283236e-06, "loss": 0.4538, "step": 10200 }, { "epoch": 1.84, "learning_rate": 2.387102601156069e-06, "loss": 0.4206, "step": 10201 }, { "epoch": 1.84, "learning_rate": 2.3843930635838153e-06, "loss": 0.5679, "step": 10202 }, { "epoch": 1.84, "learning_rate": 2.381683526011561e-06, "loss": 0.6147, "step": 10203 }, { "epoch": 1.84, "learning_rate": 2.378973988439306e-06, "loss": 0.4003, "step": 10204 }, { "epoch": 1.84, "learning_rate": 2.376264450867052e-06, "loss": 0.6042, "step": 10205 }, { "epoch": 1.84, "learning_rate": 2.373554913294798e-06, "loss": 0.4827, "step": 10206 }, { "epoch": 1.84, "learning_rate": 2.3708453757225434e-06, "loss": 0.7474, "step": 10207 }, { "epoch": 1.84, "learning_rate": 2.368135838150289e-06, "loss": 0.7093, "step": 10208 }, { "epoch": 1.84, "learning_rate": 2.365426300578035e-06, "loss": 0.3767, "step": 10209 }, { "epoch": 1.84, "learning_rate": 2.3627167630057803e-06, "loss": 0.4245, "step": 10210 }, { "epoch": 1.84, "learning_rate": 2.360007225433526e-06, "loss": 0.45, "step": 10211 }, { "epoch": 1.84, "learning_rate": 2.3572976878612716e-06, "loss": 1.126, "step": 10212 }, { "epoch": 1.84, "learning_rate": 2.3545881502890177e-06, "loss": 1.3447, "step": 10213 }, { "epoch": 1.85, "learning_rate": 2.3518786127167633e-06, "loss": 0.5356, "step": 10214 }, { "epoch": 1.85, "learning_rate": 2.3491690751445085e-06, "loss": 0.2731, "step": 10215 }, { "epoch": 1.85, "learning_rate": 2.346459537572254e-06, "loss": 0.6297, "step": 10216 }, { "epoch": 1.85, "learning_rate": 2.3437500000000002e-06, "loss": 1.0977, "step": 10217 }, { "epoch": 1.85, "learning_rate": 2.341040462427746e-06, "loss": 0.2641, "step": 10218 }, { "epoch": 1.85, "learning_rate": 2.3383309248554915e-06, "loss": 0.3557, "step": 10219 }, { "epoch": 1.85, "learning_rate": 2.3356213872832367e-06, "loss": 0.6098, "step": 10220 }, { "epoch": 1.85, "learning_rate": 2.3329118497109828e-06, "loss": 1.1336, "step": 10221 }, { "epoch": 1.85, "learning_rate": 2.3302023121387284e-06, "loss": 0.4291, "step": 10222 }, { "epoch": 1.85, "learning_rate": 2.327492774566474e-06, "loss": 0.2628, "step": 10223 }, { "epoch": 1.85, "learning_rate": 2.3247832369942197e-06, "loss": 0.4598, "step": 10224 }, { "epoch": 1.85, "learning_rate": 2.3220736994219653e-06, "loss": 0.5367, "step": 10225 }, { "epoch": 1.85, "learning_rate": 2.319364161849711e-06, "loss": 0.3644, "step": 10226 }, { "epoch": 1.85, "learning_rate": 2.3166546242774566e-06, "loss": 1.1603, "step": 10227 }, { "epoch": 1.85, "learning_rate": 2.313945086705202e-06, "loss": 0.207, "step": 10228 }, { "epoch": 1.85, "learning_rate": 2.3112355491329483e-06, "loss": 0.2633, "step": 10229 }, { "epoch": 1.85, "learning_rate": 2.308526011560694e-06, "loss": 0.7791, "step": 10230 }, { "epoch": 1.85, "learning_rate": 2.305816473988439e-06, "loss": 0.2188, "step": 10231 }, { "epoch": 1.85, "learning_rate": 2.303106936416185e-06, "loss": 0.6627, "step": 10232 }, { "epoch": 1.85, "learning_rate": 2.300397398843931e-06, "loss": 1.3617, "step": 10233 }, { "epoch": 1.85, "learning_rate": 2.2976878612716764e-06, "loss": 0.5154, "step": 10234 }, { "epoch": 1.85, "learning_rate": 2.294978323699422e-06, "loss": 0.1942, "step": 10235 }, { "epoch": 1.85, "learning_rate": 2.2922687861271677e-06, "loss": 0.246, "step": 10236 }, { "epoch": 1.85, "learning_rate": 2.2895592485549134e-06, "loss": 0.6762, "step": 10237 }, { "epoch": 1.85, "learning_rate": 2.286849710982659e-06, "loss": 0.3222, "step": 10238 }, { "epoch": 1.85, "learning_rate": 2.2841401734104046e-06, "loss": 0.5863, "step": 10239 }, { "epoch": 1.85, "learning_rate": 2.2814306358381507e-06, "loss": 0.44, "step": 10240 }, { "epoch": 1.85, "learning_rate": 2.278721098265896e-06, "loss": 0.6453, "step": 10241 }, { "epoch": 1.85, "learning_rate": 2.2760115606936415e-06, "loss": 0.4666, "step": 10242 }, { "epoch": 1.85, "learning_rate": 2.273302023121387e-06, "loss": 0.5507, "step": 10243 }, { "epoch": 1.85, "learning_rate": 2.2705924855491332e-06, "loss": 0.5353, "step": 10244 }, { "epoch": 1.85, "learning_rate": 2.267882947976879e-06, "loss": 0.7691, "step": 10245 }, { "epoch": 1.85, "learning_rate": 2.265173410404624e-06, "loss": 0.2188, "step": 10246 }, { "epoch": 1.85, "learning_rate": 2.2624638728323697e-06, "loss": 0.3574, "step": 10247 }, { "epoch": 1.85, "learning_rate": 2.2597543352601158e-06, "loss": 0.2483, "step": 10248 }, { "epoch": 1.85, "learning_rate": 2.2570447976878614e-06, "loss": 0.3119, "step": 10249 }, { "epoch": 1.85, "learning_rate": 2.254335260115607e-06, "loss": 0.3411, "step": 10250 }, { "epoch": 1.85, "learning_rate": 2.2516257225433527e-06, "loss": 0.8842, "step": 10251 }, { "epoch": 1.85, "learning_rate": 2.2489161849710983e-06, "loss": 0.5078, "step": 10252 }, { "epoch": 1.85, "learning_rate": 2.246206647398844e-06, "loss": 0.449, "step": 10253 }, { "epoch": 1.85, "learning_rate": 2.2434971098265896e-06, "loss": 0.4648, "step": 10254 }, { "epoch": 1.85, "learning_rate": 2.2407875722543352e-06, "loss": 0.5733, "step": 10255 }, { "epoch": 1.85, "learning_rate": 2.2380780346820813e-06, "loss": 0.9418, "step": 10256 }, { "epoch": 1.85, "learning_rate": 2.2353684971098265e-06, "loss": 1.1914, "step": 10257 }, { "epoch": 1.85, "learning_rate": 2.232658959537572e-06, "loss": 0.5535, "step": 10258 }, { "epoch": 1.85, "learning_rate": 2.229949421965318e-06, "loss": 0.7732, "step": 10259 }, { "epoch": 1.85, "learning_rate": 2.227239884393064e-06, "loss": 0.2974, "step": 10260 }, { "epoch": 1.85, "learning_rate": 2.2245303468208095e-06, "loss": 0.5502, "step": 10261 }, { "epoch": 1.85, "learning_rate": 2.2218208092485547e-06, "loss": 0.3936, "step": 10262 }, { "epoch": 1.85, "learning_rate": 2.2191112716763007e-06, "loss": 0.6386, "step": 10263 }, { "epoch": 1.85, "learning_rate": 2.2164017341040464e-06, "loss": 0.783, "step": 10264 }, { "epoch": 1.85, "learning_rate": 2.213692196531792e-06, "loss": 0.5738, "step": 10265 }, { "epoch": 1.85, "learning_rate": 2.2109826589595376e-06, "loss": 0.3101, "step": 10266 }, { "epoch": 1.85, "learning_rate": 2.2082731213872833e-06, "loss": 1.2178, "step": 10267 }, { "epoch": 1.85, "learning_rate": 2.205563583815029e-06, "loss": 0.5714, "step": 10268 }, { "epoch": 1.85, "learning_rate": 2.2028540462427745e-06, "loss": 0.6463, "step": 10269 }, { "epoch": 1.86, "learning_rate": 2.20014450867052e-06, "loss": 0.3969, "step": 10270 }, { "epoch": 1.86, "learning_rate": 2.1974349710982662e-06, "loss": 0.3458, "step": 10271 }, { "epoch": 1.86, "learning_rate": 2.194725433526012e-06, "loss": 0.5674, "step": 10272 }, { "epoch": 1.86, "learning_rate": 2.192015895953757e-06, "loss": 0.1999, "step": 10273 }, { "epoch": 1.86, "learning_rate": 2.1893063583815027e-06, "loss": 0.7144, "step": 10274 }, { "epoch": 1.86, "learning_rate": 2.1865968208092488e-06, "loss": 0.3554, "step": 10275 }, { "epoch": 1.86, "learning_rate": 2.1838872832369944e-06, "loss": 0.2833, "step": 10276 }, { "epoch": 1.86, "learning_rate": 2.18117774566474e-06, "loss": 0.4283, "step": 10277 }, { "epoch": 1.86, "learning_rate": 2.1784682080924853e-06, "loss": 0.3554, "step": 10278 }, { "epoch": 1.86, "learning_rate": 2.1757586705202313e-06, "loss": 0.4549, "step": 10279 }, { "epoch": 1.86, "learning_rate": 2.173049132947977e-06, "loss": 0.4662, "step": 10280 }, { "epoch": 1.86, "learning_rate": 2.1703395953757226e-06, "loss": 0.1422, "step": 10281 }, { "epoch": 1.86, "learning_rate": 2.1676300578034682e-06, "loss": 0.2974, "step": 10282 }, { "epoch": 1.86, "learning_rate": 2.164920520231214e-06, "loss": 0.5108, "step": 10283 }, { "epoch": 1.86, "learning_rate": 2.1622109826589595e-06, "loss": 0.5042, "step": 10284 }, { "epoch": 1.86, "learning_rate": 2.159501445086705e-06, "loss": 0.3551, "step": 10285 }, { "epoch": 1.86, "learning_rate": 2.156791907514451e-06, "loss": 0.5152, "step": 10286 }, { "epoch": 1.86, "learning_rate": 2.154082369942197e-06, "loss": 0.3258, "step": 10287 }, { "epoch": 1.86, "learning_rate": 2.151372832369942e-06, "loss": 0.5963, "step": 10288 }, { "epoch": 1.86, "learning_rate": 2.1486632947976877e-06, "loss": 0.2463, "step": 10289 }, { "epoch": 1.86, "learning_rate": 2.1459537572254337e-06, "loss": 0.903, "step": 10290 }, { "epoch": 1.86, "learning_rate": 2.1432442196531794e-06, "loss": 0.4705, "step": 10291 }, { "epoch": 1.86, "learning_rate": 2.140534682080925e-06, "loss": 0.7016, "step": 10292 }, { "epoch": 1.86, "learning_rate": 2.1378251445086706e-06, "loss": 0.8027, "step": 10293 }, { "epoch": 1.86, "learning_rate": 2.1351156069364163e-06, "loss": 0.2863, "step": 10294 }, { "epoch": 1.86, "learning_rate": 2.132406069364162e-06, "loss": 0.9024, "step": 10295 }, { "epoch": 1.86, "learning_rate": 2.1296965317919075e-06, "loss": 0.3259, "step": 10296 }, { "epoch": 1.86, "learning_rate": 2.126986994219653e-06, "loss": 0.8422, "step": 10297 }, { "epoch": 1.86, "learning_rate": 2.1242774566473992e-06, "loss": 0.481, "step": 10298 }, { "epoch": 1.86, "learning_rate": 2.1215679190751445e-06, "loss": 0.56, "step": 10299 }, { "epoch": 1.86, "learning_rate": 2.11885838150289e-06, "loss": 0.7568, "step": 10300 }, { "epoch": 1.86, "learning_rate": 2.1161488439306357e-06, "loss": 0.4747, "step": 10301 }, { "epoch": 1.86, "learning_rate": 2.1134393063583818e-06, "loss": 0.4954, "step": 10302 }, { "epoch": 1.86, "learning_rate": 2.1107297687861274e-06, "loss": 0.4102, "step": 10303 }, { "epoch": 1.86, "learning_rate": 2.1080202312138726e-06, "loss": 0.5149, "step": 10304 }, { "epoch": 1.86, "learning_rate": 2.1053106936416183e-06, "loss": 0.4948, "step": 10305 }, { "epoch": 1.86, "learning_rate": 2.1026011560693643e-06, "loss": 0.3201, "step": 10306 }, { "epoch": 1.86, "learning_rate": 2.09989161849711e-06, "loss": 0.2496, "step": 10307 }, { "epoch": 1.86, "learning_rate": 2.0971820809248556e-06, "loss": 0.4798, "step": 10308 }, { "epoch": 1.86, "learning_rate": 2.094472543352601e-06, "loss": 0.3577, "step": 10309 }, { "epoch": 1.86, "learning_rate": 2.091763005780347e-06, "loss": 0.7266, "step": 10310 }, { "epoch": 1.86, "learning_rate": 2.0890534682080925e-06, "loss": 0.7332, "step": 10311 }, { "epoch": 1.86, "learning_rate": 2.086343930635838e-06, "loss": 0.2623, "step": 10312 }, { "epoch": 1.86, "learning_rate": 2.083634393063584e-06, "loss": 0.7677, "step": 10313 }, { "epoch": 1.86, "learning_rate": 2.0809248554913294e-06, "loss": 0.4451, "step": 10314 }, { "epoch": 1.86, "learning_rate": 2.078215317919075e-06, "loss": 0.3547, "step": 10315 }, { "epoch": 1.86, "learning_rate": 2.0755057803468207e-06, "loss": 0.4726, "step": 10316 }, { "epoch": 1.86, "learning_rate": 2.0727962427745667e-06, "loss": 0.5202, "step": 10317 }, { "epoch": 1.86, "learning_rate": 2.0700867052023124e-06, "loss": 0.2568, "step": 10318 }, { "epoch": 1.86, "learning_rate": 2.067377167630058e-06, "loss": 0.7421, "step": 10319 }, { "epoch": 1.86, "learning_rate": 2.0646676300578032e-06, "loss": 0.5433, "step": 10320 }, { "epoch": 1.86, "learning_rate": 2.0619580924855493e-06, "loss": 0.6245, "step": 10321 }, { "epoch": 1.86, "learning_rate": 2.059248554913295e-06, "loss": 0.706, "step": 10322 }, { "epoch": 1.86, "learning_rate": 2.0565390173410406e-06, "loss": 0.4021, "step": 10323 }, { "epoch": 1.86, "learning_rate": 2.053829479768786e-06, "loss": 0.2003, "step": 10324 }, { "epoch": 1.87, "learning_rate": 2.051119942196532e-06, "loss": 0.7031, "step": 10325 }, { "epoch": 1.87, "learning_rate": 2.0484104046242775e-06, "loss": 0.6259, "step": 10326 }, { "epoch": 1.87, "learning_rate": 2.045700867052023e-06, "loss": 0.3777, "step": 10327 }, { "epoch": 1.87, "learning_rate": 2.0429913294797687e-06, "loss": 0.685, "step": 10328 }, { "epoch": 1.87, "learning_rate": 2.040281791907515e-06, "loss": 0.6053, "step": 10329 }, { "epoch": 1.87, "learning_rate": 2.03757225433526e-06, "loss": 0.7898, "step": 10330 }, { "epoch": 1.87, "learning_rate": 2.0348627167630056e-06, "loss": 0.7347, "step": 10331 }, { "epoch": 1.87, "learning_rate": 2.0321531791907513e-06, "loss": 0.562, "step": 10332 }, { "epoch": 1.87, "learning_rate": 2.0294436416184973e-06, "loss": 0.5541, "step": 10333 }, { "epoch": 1.87, "learning_rate": 2.026734104046243e-06, "loss": 0.6899, "step": 10334 }, { "epoch": 1.87, "learning_rate": 2.024024566473988e-06, "loss": 0.4795, "step": 10335 }, { "epoch": 1.87, "learning_rate": 2.021315028901734e-06, "loss": 0.3215, "step": 10336 }, { "epoch": 1.87, "learning_rate": 2.01860549132948e-06, "loss": 0.2287, "step": 10337 }, { "epoch": 1.87, "learning_rate": 2.0158959537572255e-06, "loss": 0.2802, "step": 10338 }, { "epoch": 1.87, "learning_rate": 2.013186416184971e-06, "loss": 0.4453, "step": 10339 }, { "epoch": 1.87, "learning_rate": 2.010476878612717e-06, "loss": 0.3861, "step": 10340 }, { "epoch": 1.87, "learning_rate": 2.0077673410404624e-06, "loss": 0.6623, "step": 10341 }, { "epoch": 1.87, "learning_rate": 2.005057803468208e-06, "loss": 0.5383, "step": 10342 }, { "epoch": 1.87, "learning_rate": 2.0023482658959537e-06, "loss": 0.6103, "step": 10343 }, { "epoch": 1.87, "learning_rate": 1.9996387283236998e-06, "loss": 0.5052, "step": 10344 }, { "epoch": 1.87, "learning_rate": 1.9969291907514454e-06, "loss": 0.6047, "step": 10345 }, { "epoch": 1.87, "learning_rate": 1.9942196531791906e-06, "loss": 0.7865, "step": 10346 }, { "epoch": 1.87, "learning_rate": 1.9915101156069362e-06, "loss": 0.6903, "step": 10347 }, { "epoch": 1.87, "learning_rate": 1.9888005780346823e-06, "loss": 0.8307, "step": 10348 }, { "epoch": 1.87, "learning_rate": 1.986091040462428e-06, "loss": 0.3585, "step": 10349 }, { "epoch": 1.87, "learning_rate": 1.9833815028901736e-06, "loss": 0.8426, "step": 10350 }, { "epoch": 1.87, "learning_rate": 1.9806719653179188e-06, "loss": 0.3397, "step": 10351 }, { "epoch": 1.87, "learning_rate": 1.977962427745665e-06, "loss": 0.4903, "step": 10352 }, { "epoch": 1.87, "learning_rate": 1.9752528901734105e-06, "loss": 0.6317, "step": 10353 }, { "epoch": 1.87, "learning_rate": 1.972543352601156e-06, "loss": 0.3853, "step": 10354 }, { "epoch": 1.87, "learning_rate": 1.9698338150289017e-06, "loss": 0.6112, "step": 10355 }, { "epoch": 1.87, "learning_rate": 1.9671242774566474e-06, "loss": 0.7592, "step": 10356 }, { "epoch": 1.87, "learning_rate": 1.964414739884393e-06, "loss": 0.6031, "step": 10357 }, { "epoch": 1.87, "learning_rate": 1.9617052023121386e-06, "loss": 0.2204, "step": 10358 }, { "epoch": 1.87, "learning_rate": 1.9589956647398843e-06, "loss": 0.5745, "step": 10359 }, { "epoch": 1.87, "learning_rate": 1.9562861271676303e-06, "loss": 0.8355, "step": 10360 }, { "epoch": 1.87, "learning_rate": 1.953576589595376e-06, "loss": 0.18, "step": 10361 }, { "epoch": 1.87, "learning_rate": 1.950867052023121e-06, "loss": 0.5058, "step": 10362 }, { "epoch": 1.87, "learning_rate": 1.948157514450867e-06, "loss": 0.4191, "step": 10363 }, { "epoch": 1.87, "learning_rate": 1.945447976878613e-06, "loss": 0.3647, "step": 10364 }, { "epoch": 1.87, "learning_rate": 1.9427384393063585e-06, "loss": 1.1029, "step": 10365 }, { "epoch": 1.87, "learning_rate": 1.940028901734104e-06, "loss": 0.7024, "step": 10366 }, { "epoch": 1.87, "learning_rate": 1.93731936416185e-06, "loss": 0.5327, "step": 10367 }, { "epoch": 1.87, "learning_rate": 1.9346098265895954e-06, "loss": 0.7163, "step": 10368 }, { "epoch": 1.87, "learning_rate": 1.931900289017341e-06, "loss": 0.3805, "step": 10369 }, { "epoch": 1.87, "learning_rate": 1.9291907514450867e-06, "loss": 0.4362, "step": 10370 }, { "epoch": 1.87, "learning_rate": 1.9264812138728328e-06, "loss": 0.4291, "step": 10371 }, { "epoch": 1.87, "learning_rate": 1.923771676300578e-06, "loss": 0.3791, "step": 10372 }, { "epoch": 1.87, "learning_rate": 1.9210621387283236e-06, "loss": 0.3577, "step": 10373 }, { "epoch": 1.87, "learning_rate": 1.9183526011560692e-06, "loss": 0.2455, "step": 10374 }, { "epoch": 1.87, "learning_rate": 1.9156430635838153e-06, "loss": 0.3223, "step": 10375 }, { "epoch": 1.87, "learning_rate": 1.912933526011561e-06, "loss": 0.2528, "step": 10376 }, { "epoch": 1.87, "learning_rate": 1.910223988439306e-06, "loss": 0.6222, "step": 10377 }, { "epoch": 1.87, "learning_rate": 1.9075144508670518e-06, "loss": 0.2822, "step": 10378 }, { "epoch": 1.87, "learning_rate": 1.9048049132947976e-06, "loss": 0.4586, "step": 10379 }, { "epoch": 1.88, "learning_rate": 1.9020953757225435e-06, "loss": 0.5366, "step": 10380 }, { "epoch": 1.88, "learning_rate": 1.8993858381502891e-06, "loss": 0.3092, "step": 10381 }, { "epoch": 1.88, "learning_rate": 1.896676300578035e-06, "loss": 0.405, "step": 10382 }, { "epoch": 1.88, "learning_rate": 1.8939667630057802e-06, "loss": 0.3004, "step": 10383 }, { "epoch": 1.88, "learning_rate": 1.891257225433526e-06, "loss": 0.221, "step": 10384 }, { "epoch": 1.88, "learning_rate": 1.8885476878612717e-06, "loss": 0.9806, "step": 10385 }, { "epoch": 1.88, "learning_rate": 1.8858381502890175e-06, "loss": 0.6052, "step": 10386 }, { "epoch": 1.88, "learning_rate": 1.8831286127167631e-06, "loss": 0.3416, "step": 10387 }, { "epoch": 1.88, "learning_rate": 1.8804190751445086e-06, "loss": 0.3472, "step": 10388 }, { "epoch": 1.88, "learning_rate": 1.8777095375722542e-06, "loss": 0.2064, "step": 10389 }, { "epoch": 1.88, "learning_rate": 1.875e-06, "loss": 0.755, "step": 10390 }, { "epoch": 1.88, "learning_rate": 1.872290462427746e-06, "loss": 0.6644, "step": 10391 }, { "epoch": 1.88, "learning_rate": 1.8695809248554913e-06, "loss": 0.3012, "step": 10392 }, { "epoch": 1.88, "learning_rate": 1.8668713872832372e-06, "loss": 0.6663, "step": 10393 }, { "epoch": 1.88, "learning_rate": 1.8641618497109826e-06, "loss": 0.4354, "step": 10394 }, { "epoch": 1.88, "learning_rate": 1.8614523121387284e-06, "loss": 0.2076, "step": 10395 }, { "epoch": 1.88, "learning_rate": 1.858742774566474e-06, "loss": 0.6423, "step": 10396 }, { "epoch": 1.88, "learning_rate": 1.8560332369942197e-06, "loss": 0.556, "step": 10397 }, { "epoch": 1.88, "learning_rate": 1.8533236994219653e-06, "loss": 0.3168, "step": 10398 }, { "epoch": 1.88, "learning_rate": 1.8506141618497112e-06, "loss": 0.7368, "step": 10399 }, { "epoch": 1.88, "learning_rate": 1.8479046242774566e-06, "loss": 0.5011, "step": 10400 }, { "epoch": 1.88, "learning_rate": 1.8451950867052025e-06, "loss": 0.2947, "step": 10401 }, { "epoch": 1.88, "learning_rate": 1.8424855491329479e-06, "loss": 0.2122, "step": 10402 }, { "epoch": 1.88, "learning_rate": 1.8397760115606937e-06, "loss": 0.4152, "step": 10403 }, { "epoch": 1.88, "learning_rate": 1.8370664739884394e-06, "loss": 0.2605, "step": 10404 }, { "epoch": 1.88, "learning_rate": 1.834356936416185e-06, "loss": 0.2593, "step": 10405 }, { "epoch": 1.88, "learning_rate": 1.8316473988439306e-06, "loss": 0.5778, "step": 10406 }, { "epoch": 1.88, "learning_rate": 1.8289378612716765e-06, "loss": 0.4567, "step": 10407 }, { "epoch": 1.88, "learning_rate": 1.826228323699422e-06, "loss": 0.6639, "step": 10408 }, { "epoch": 1.88, "learning_rate": 1.8235187861271678e-06, "loss": 1.0722, "step": 10409 }, { "epoch": 1.88, "learning_rate": 1.8208092485549132e-06, "loss": 0.6407, "step": 10410 }, { "epoch": 1.88, "learning_rate": 1.818099710982659e-06, "loss": 0.5336, "step": 10411 }, { "epoch": 1.88, "learning_rate": 1.8153901734104047e-06, "loss": 1.0719, "step": 10412 }, { "epoch": 1.88, "learning_rate": 1.8126806358381503e-06, "loss": 0.7895, "step": 10413 }, { "epoch": 1.88, "learning_rate": 1.809971098265896e-06, "loss": 0.3647, "step": 10414 }, { "epoch": 1.88, "learning_rate": 1.8072615606936416e-06, "loss": 0.7091, "step": 10415 }, { "epoch": 1.88, "learning_rate": 1.8045520231213872e-06, "loss": 1.2092, "step": 10416 }, { "epoch": 1.88, "learning_rate": 1.801842485549133e-06, "loss": 0.3388, "step": 10417 }, { "epoch": 1.88, "learning_rate": 1.7991329479768787e-06, "loss": 0.6876, "step": 10418 }, { "epoch": 1.88, "learning_rate": 1.7964234104046243e-06, "loss": 0.4139, "step": 10419 }, { "epoch": 1.88, "learning_rate": 1.7937138728323702e-06, "loss": 1.2715, "step": 10420 }, { "epoch": 1.88, "learning_rate": 1.7910043352601156e-06, "loss": 0.1551, "step": 10421 }, { "epoch": 1.88, "learning_rate": 1.7882947976878614e-06, "loss": 1.2595, "step": 10422 }, { "epoch": 1.88, "learning_rate": 1.7855852601156069e-06, "loss": 0.2707, "step": 10423 }, { "epoch": 1.88, "learning_rate": 1.7828757225433527e-06, "loss": 0.74, "step": 10424 }, { "epoch": 1.88, "learning_rate": 1.7801661849710984e-06, "loss": 1.0899, "step": 10425 }, { "epoch": 1.88, "learning_rate": 1.777456647398844e-06, "loss": 0.2467, "step": 10426 }, { "epoch": 1.88, "learning_rate": 1.7747471098265896e-06, "loss": 0.8046, "step": 10427 }, { "epoch": 1.88, "learning_rate": 1.7720375722543355e-06, "loss": 0.3945, "step": 10428 }, { "epoch": 1.88, "learning_rate": 1.769328034682081e-06, "loss": 0.604, "step": 10429 }, { "epoch": 1.88, "learning_rate": 1.7666184971098267e-06, "loss": 0.5564, "step": 10430 }, { "epoch": 1.88, "learning_rate": 1.7639089595375722e-06, "loss": 0.6127, "step": 10431 }, { "epoch": 1.88, "learning_rate": 1.761199421965318e-06, "loss": 0.7835, "step": 10432 }, { "epoch": 1.88, "learning_rate": 1.7584898843930636e-06, "loss": 0.2551, "step": 10433 }, { "epoch": 1.88, "learning_rate": 1.7557803468208093e-06, "loss": 0.6662, "step": 10434 }, { "epoch": 1.88, "learning_rate": 1.753070809248555e-06, "loss": 0.2896, "step": 10435 }, { "epoch": 1.89, "learning_rate": 1.7503612716763006e-06, "loss": 0.4951, "step": 10436 }, { "epoch": 1.89, "learning_rate": 1.7476517341040462e-06, "loss": 0.1865, "step": 10437 }, { "epoch": 1.89, "learning_rate": 1.744942196531792e-06, "loss": 0.3153, "step": 10438 }, { "epoch": 1.89, "learning_rate": 1.7422326589595375e-06, "loss": 0.2552, "step": 10439 }, { "epoch": 1.89, "learning_rate": 1.7395231213872833e-06, "loss": 0.5007, "step": 10440 }, { "epoch": 1.89, "learning_rate": 1.736813583815029e-06, "loss": 0.4986, "step": 10441 }, { "epoch": 1.89, "learning_rate": 1.7341040462427746e-06, "loss": 0.6881, "step": 10442 }, { "epoch": 1.89, "learning_rate": 1.7313945086705202e-06, "loss": 1.1229, "step": 10443 }, { "epoch": 1.89, "learning_rate": 1.7286849710982659e-06, "loss": 0.4814, "step": 10444 }, { "epoch": 1.89, "learning_rate": 1.7259754335260117e-06, "loss": 0.1699, "step": 10445 }, { "epoch": 1.89, "learning_rate": 1.7232658959537573e-06, "loss": 0.4079, "step": 10446 }, { "epoch": 1.89, "learning_rate": 1.720556358381503e-06, "loss": 0.395, "step": 10447 }, { "epoch": 1.89, "learning_rate": 1.7178468208092486e-06, "loss": 0.4488, "step": 10448 }, { "epoch": 1.89, "learning_rate": 1.7151372832369942e-06, "loss": 0.5947, "step": 10449 }, { "epoch": 1.89, "learning_rate": 1.7124277456647399e-06, "loss": 0.5584, "step": 10450 }, { "epoch": 1.89, "learning_rate": 1.7097182080924857e-06, "loss": 0.4211, "step": 10451 }, { "epoch": 1.89, "learning_rate": 1.7070086705202311e-06, "loss": 0.4365, "step": 10452 }, { "epoch": 1.89, "learning_rate": 1.704299132947977e-06, "loss": 1.4627, "step": 10453 }, { "epoch": 1.89, "learning_rate": 1.7015895953757226e-06, "loss": 0.3997, "step": 10454 }, { "epoch": 1.89, "learning_rate": 1.6988800578034683e-06, "loss": 0.413, "step": 10455 }, { "epoch": 1.89, "learning_rate": 1.696170520231214e-06, "loss": 0.3108, "step": 10456 }, { "epoch": 1.89, "learning_rate": 1.6934609826589595e-06, "loss": 0.4322, "step": 10457 }, { "epoch": 1.89, "learning_rate": 1.6907514450867052e-06, "loss": 1.0875, "step": 10458 }, { "epoch": 1.89, "learning_rate": 1.688041907514451e-06, "loss": 0.264, "step": 10459 }, { "epoch": 1.89, "learning_rate": 1.6853323699421964e-06, "loss": 0.4669, "step": 10460 }, { "epoch": 1.89, "learning_rate": 1.6826228323699423e-06, "loss": 0.3926, "step": 10461 }, { "epoch": 1.89, "learning_rate": 1.679913294797688e-06, "loss": 0.9063, "step": 10462 }, { "epoch": 1.89, "learning_rate": 1.6772037572254336e-06, "loss": 0.1529, "step": 10463 }, { "epoch": 1.89, "learning_rate": 1.6744942196531792e-06, "loss": 0.7806, "step": 10464 }, { "epoch": 1.89, "learning_rate": 1.6717846820809248e-06, "loss": 0.6233, "step": 10465 }, { "epoch": 1.89, "learning_rate": 1.6690751445086705e-06, "loss": 0.4813, "step": 10466 }, { "epoch": 1.89, "learning_rate": 1.6663656069364163e-06, "loss": 0.6087, "step": 10467 }, { "epoch": 1.89, "learning_rate": 1.6636560693641617e-06, "loss": 0.2071, "step": 10468 }, { "epoch": 1.89, "learning_rate": 1.6609465317919076e-06, "loss": 0.3559, "step": 10469 }, { "epoch": 1.89, "learning_rate": 1.6582369942196532e-06, "loss": 0.2899, "step": 10470 }, { "epoch": 1.89, "learning_rate": 1.6555274566473989e-06, "loss": 0.1363, "step": 10471 }, { "epoch": 1.89, "learning_rate": 1.6528179190751447e-06, "loss": 0.3342, "step": 10472 }, { "epoch": 1.89, "learning_rate": 1.6501083815028901e-06, "loss": 0.7545, "step": 10473 }, { "epoch": 1.89, "learning_rate": 1.647398843930636e-06, "loss": 0.2185, "step": 10474 }, { "epoch": 1.89, "learning_rate": 1.6446893063583816e-06, "loss": 0.4361, "step": 10475 }, { "epoch": 1.89, "learning_rate": 1.6419797687861273e-06, "loss": 0.504, "step": 10476 }, { "epoch": 1.89, "learning_rate": 1.6392702312138729e-06, "loss": 0.8085, "step": 10477 }, { "epoch": 1.89, "learning_rate": 1.6365606936416185e-06, "loss": 0.3674, "step": 10478 }, { "epoch": 1.89, "learning_rate": 1.6338511560693642e-06, "loss": 0.3939, "step": 10479 }, { "epoch": 1.89, "learning_rate": 1.63114161849711e-06, "loss": 0.5917, "step": 10480 }, { "epoch": 1.89, "learning_rate": 1.6284320809248554e-06, "loss": 0.2907, "step": 10481 }, { "epoch": 1.89, "learning_rate": 1.6257225433526013e-06, "loss": 0.4824, "step": 10482 }, { "epoch": 1.89, "learning_rate": 1.623013005780347e-06, "loss": 1.3091, "step": 10483 }, { "epoch": 1.89, "learning_rate": 1.6203034682080925e-06, "loss": 0.3883, "step": 10484 }, { "epoch": 1.89, "learning_rate": 1.6175939306358382e-06, "loss": 0.5844, "step": 10485 }, { "epoch": 1.89, "learning_rate": 1.6148843930635838e-06, "loss": 0.5183, "step": 10486 }, { "epoch": 1.89, "learning_rate": 1.6121748554913295e-06, "loss": 0.8003, "step": 10487 }, { "epoch": 1.89, "learning_rate": 1.6094653179190753e-06, "loss": 0.4837, "step": 10488 }, { "epoch": 1.89, "learning_rate": 1.6067557803468207e-06, "loss": 0.4487, "step": 10489 }, { "epoch": 1.89, "learning_rate": 1.6040462427745666e-06, "loss": 0.3639, "step": 10490 }, { "epoch": 1.9, "learning_rate": 1.601336705202312e-06, "loss": 0.3138, "step": 10491 }, { "epoch": 1.9, "learning_rate": 1.5986271676300578e-06, "loss": 0.4893, "step": 10492 }, { "epoch": 1.9, "learning_rate": 1.5959176300578035e-06, "loss": 0.8155, "step": 10493 }, { "epoch": 1.9, "learning_rate": 1.5932080924855491e-06, "loss": 0.5619, "step": 10494 }, { "epoch": 1.9, "learning_rate": 1.5904985549132948e-06, "loss": 0.1981, "step": 10495 }, { "epoch": 1.9, "learning_rate": 1.5877890173410406e-06, "loss": 0.4485, "step": 10496 }, { "epoch": 1.9, "learning_rate": 1.5850794797687862e-06, "loss": 1.1139, "step": 10497 }, { "epoch": 1.9, "learning_rate": 1.5823699421965319e-06, "loss": 0.4921, "step": 10498 }, { "epoch": 1.9, "learning_rate": 1.5796604046242775e-06, "loss": 0.5463, "step": 10499 }, { "epoch": 1.9, "learning_rate": 1.5769508670520231e-06, "loss": 0.6889, "step": 10500 }, { "epoch": 1.9, "eval_exact_match": 88.21192052980132, "eval_f1": 94.17137634338887, "step": 10500 }, { "epoch": 1.9, "learning_rate": 1.574241329479769e-06, "loss": 0.7617, "step": 10501 }, { "epoch": 1.9, "learning_rate": 1.5715317919075144e-06, "loss": 0.6308, "step": 10502 }, { "epoch": 1.9, "learning_rate": 1.5688222543352603e-06, "loss": 0.2554, "step": 10503 }, { "epoch": 1.9, "learning_rate": 1.5661127167630059e-06, "loss": 0.6272, "step": 10504 }, { "epoch": 1.9, "learning_rate": 1.5634031791907515e-06, "loss": 0.7569, "step": 10505 }, { "epoch": 1.9, "learning_rate": 1.5606936416184972e-06, "loss": 0.8986, "step": 10506 }, { "epoch": 1.9, "learning_rate": 1.5579841040462428e-06, "loss": 0.7223, "step": 10507 }, { "epoch": 1.9, "learning_rate": 1.5552745664739884e-06, "loss": 0.2112, "step": 10508 }, { "epoch": 1.9, "learning_rate": 1.5525650289017343e-06, "loss": 0.3959, "step": 10509 }, { "epoch": 1.9, "learning_rate": 1.5498554913294797e-06, "loss": 0.2118, "step": 10510 }, { "epoch": 1.9, "learning_rate": 1.5471459537572256e-06, "loss": 0.4065, "step": 10511 }, { "epoch": 1.9, "learning_rate": 1.544436416184971e-06, "loss": 0.5613, "step": 10512 }, { "epoch": 1.9, "learning_rate": 1.5417268786127168e-06, "loss": 0.6347, "step": 10513 }, { "epoch": 1.9, "learning_rate": 1.5390173410404625e-06, "loss": 0.3351, "step": 10514 }, { "epoch": 1.9, "learning_rate": 1.536307803468208e-06, "loss": 0.6445, "step": 10515 }, { "epoch": 1.9, "learning_rate": 1.5335982658959537e-06, "loss": 0.5905, "step": 10516 }, { "epoch": 1.9, "learning_rate": 1.5308887283236996e-06, "loss": 0.7786, "step": 10517 }, { "epoch": 1.9, "learning_rate": 1.528179190751445e-06, "loss": 0.3778, "step": 10518 }, { "epoch": 1.9, "learning_rate": 1.5254696531791909e-06, "loss": 0.6042, "step": 10519 }, { "epoch": 1.9, "learning_rate": 1.5227601156069363e-06, "loss": 0.2011, "step": 10520 }, { "epoch": 1.9, "learning_rate": 1.5200505780346821e-06, "loss": 0.7171, "step": 10521 }, { "epoch": 1.9, "learning_rate": 1.5173410404624278e-06, "loss": 1.0574, "step": 10522 }, { "epoch": 1.9, "learning_rate": 1.5146315028901734e-06, "loss": 0.5232, "step": 10523 }, { "epoch": 1.9, "learning_rate": 1.5119219653179192e-06, "loss": 0.7737, "step": 10524 }, { "epoch": 1.9, "learning_rate": 1.5092124277456647e-06, "loss": 0.3644, "step": 10525 }, { "epoch": 1.9, "learning_rate": 1.5065028901734105e-06, "loss": 0.9109, "step": 10526 }, { "epoch": 1.9, "learning_rate": 1.5037933526011561e-06, "loss": 0.6338, "step": 10527 }, { "epoch": 1.9, "learning_rate": 1.5010838150289018e-06, "loss": 0.7961, "step": 10528 }, { "epoch": 1.9, "learning_rate": 1.4983742774566474e-06, "loss": 0.4346, "step": 10529 }, { "epoch": 1.9, "learning_rate": 1.4956647398843933e-06, "loss": 0.4415, "step": 10530 }, { "epoch": 1.9, "learning_rate": 1.4929552023121387e-06, "loss": 1.1167, "step": 10531 }, { "epoch": 1.9, "learning_rate": 1.4902456647398845e-06, "loss": 0.4774, "step": 10532 }, { "epoch": 1.9, "learning_rate": 1.48753612716763e-06, "loss": 0.6234, "step": 10533 }, { "epoch": 1.9, "learning_rate": 1.4848265895953758e-06, "loss": 0.8275, "step": 10534 }, { "epoch": 1.9, "learning_rate": 1.4821170520231214e-06, "loss": 0.368, "step": 10535 }, { "epoch": 1.9, "learning_rate": 1.479407514450867e-06, "loss": 0.1787, "step": 10536 }, { "epoch": 1.9, "learning_rate": 1.4766979768786127e-06, "loss": 0.7472, "step": 10537 }, { "epoch": 1.9, "learning_rate": 1.4739884393063586e-06, "loss": 0.4246, "step": 10538 }, { "epoch": 1.9, "learning_rate": 1.471278901734104e-06, "loss": 0.8589, "step": 10539 }, { "epoch": 1.9, "learning_rate": 1.4685693641618498e-06, "loss": 0.6066, "step": 10540 }, { "epoch": 1.9, "learning_rate": 1.4658598265895953e-06, "loss": 0.857, "step": 10541 }, { "epoch": 1.9, "learning_rate": 1.463150289017341e-06, "loss": 0.6725, "step": 10542 }, { "epoch": 1.9, "learning_rate": 1.4604407514450867e-06, "loss": 0.5688, "step": 10543 }, { "epoch": 1.9, "learning_rate": 1.4577312138728324e-06, "loss": 0.6148, "step": 10544 }, { "epoch": 1.9, "learning_rate": 1.455021676300578e-06, "loss": 0.2896, "step": 10545 }, { "epoch": 1.9, "learning_rate": 1.4523121387283236e-06, "loss": 0.2943, "step": 10546 }, { "epoch": 1.91, "learning_rate": 1.4496026011560693e-06, "loss": 0.6556, "step": 10547 }, { "epoch": 1.91, "learning_rate": 1.4468930635838151e-06, "loss": 0.5315, "step": 10548 }, { "epoch": 1.91, "learning_rate": 1.4441835260115606e-06, "loss": 0.6123, "step": 10549 }, { "epoch": 1.91, "learning_rate": 1.4414739884393064e-06, "loss": 0.9986, "step": 10550 }, { "epoch": 1.91, "learning_rate": 1.4387644508670522e-06, "loss": 0.4364, "step": 10551 }, { "epoch": 1.91, "learning_rate": 1.4360549132947977e-06, "loss": 0.2171, "step": 10552 }, { "epoch": 1.91, "learning_rate": 1.4333453757225435e-06, "loss": 0.2933, "step": 10553 }, { "epoch": 1.91, "learning_rate": 1.430635838150289e-06, "loss": 0.4528, "step": 10554 }, { "epoch": 1.91, "learning_rate": 1.4279263005780348e-06, "loss": 0.8571, "step": 10555 }, { "epoch": 1.91, "learning_rate": 1.4252167630057804e-06, "loss": 0.6298, "step": 10556 }, { "epoch": 1.91, "learning_rate": 1.422507225433526e-06, "loss": 1.6554, "step": 10557 }, { "epoch": 1.91, "learning_rate": 1.4197976878612717e-06, "loss": 0.1603, "step": 10558 }, { "epoch": 1.91, "learning_rate": 1.4170881502890175e-06, "loss": 0.7632, "step": 10559 }, { "epoch": 1.91, "learning_rate": 1.414378612716763e-06, "loss": 0.6916, "step": 10560 }, { "epoch": 1.91, "learning_rate": 1.4116690751445088e-06, "loss": 1.0129, "step": 10561 }, { "epoch": 1.91, "learning_rate": 1.4089595375722542e-06, "loss": 0.2289, "step": 10562 }, { "epoch": 1.91, "learning_rate": 1.40625e-06, "loss": 0.3244, "step": 10563 }, { "epoch": 1.91, "learning_rate": 1.4035404624277457e-06, "loss": 0.626, "step": 10564 }, { "epoch": 1.91, "learning_rate": 1.4008309248554914e-06, "loss": 0.6742, "step": 10565 }, { "epoch": 1.91, "learning_rate": 1.398121387283237e-06, "loss": 0.1525, "step": 10566 }, { "epoch": 1.91, "learning_rate": 1.3954118497109826e-06, "loss": 0.5856, "step": 10567 }, { "epoch": 1.91, "learning_rate": 1.3927023121387283e-06, "loss": 0.3138, "step": 10568 }, { "epoch": 1.91, "learning_rate": 1.3899927745664741e-06, "loss": 0.283, "step": 10569 }, { "epoch": 1.91, "learning_rate": 1.3872832369942195e-06, "loss": 0.8522, "step": 10570 }, { "epoch": 1.91, "learning_rate": 1.3845736994219654e-06, "loss": 0.9462, "step": 10571 }, { "epoch": 1.91, "learning_rate": 1.381864161849711e-06, "loss": 0.41, "step": 10572 }, { "epoch": 1.91, "learning_rate": 1.3791546242774567e-06, "loss": 0.5251, "step": 10573 }, { "epoch": 1.91, "learning_rate": 1.3764450867052023e-06, "loss": 0.5087, "step": 10574 }, { "epoch": 1.91, "learning_rate": 1.373735549132948e-06, "loss": 0.6233, "step": 10575 }, { "epoch": 1.91, "learning_rate": 1.3710260115606936e-06, "loss": 0.7862, "step": 10576 }, { "epoch": 1.91, "learning_rate": 1.3683164739884394e-06, "loss": 0.2591, "step": 10577 }, { "epoch": 1.91, "learning_rate": 1.365606936416185e-06, "loss": 0.8167, "step": 10578 }, { "epoch": 1.91, "learning_rate": 1.3628973988439307e-06, "loss": 0.5654, "step": 10579 }, { "epoch": 1.91, "learning_rate": 1.3601878612716765e-06, "loss": 0.9758, "step": 10580 }, { "epoch": 1.91, "learning_rate": 1.357478323699422e-06, "loss": 0.8279, "step": 10581 }, { "epoch": 1.91, "learning_rate": 1.3547687861271678e-06, "loss": 0.6167, "step": 10582 }, { "epoch": 1.91, "learning_rate": 1.3520592485549132e-06, "loss": 0.3662, "step": 10583 }, { "epoch": 1.91, "learning_rate": 1.349349710982659e-06, "loss": 0.5723, "step": 10584 }, { "epoch": 1.91, "learning_rate": 1.3466401734104047e-06, "loss": 0.3631, "step": 10585 }, { "epoch": 1.91, "learning_rate": 1.3439306358381503e-06, "loss": 0.4882, "step": 10586 }, { "epoch": 1.91, "learning_rate": 1.341221098265896e-06, "loss": 0.4754, "step": 10587 }, { "epoch": 1.91, "learning_rate": 1.3385115606936416e-06, "loss": 0.2488, "step": 10588 }, { "epoch": 1.91, "learning_rate": 1.3358020231213872e-06, "loss": 0.188, "step": 10589 }, { "epoch": 1.91, "learning_rate": 1.333092485549133e-06, "loss": 0.4658, "step": 10590 }, { "epoch": 1.91, "learning_rate": 1.3303829479768785e-06, "loss": 0.2986, "step": 10591 }, { "epoch": 1.91, "learning_rate": 1.3276734104046244e-06, "loss": 0.4428, "step": 10592 }, { "epoch": 1.91, "learning_rate": 1.32496387283237e-06, "loss": 0.5018, "step": 10593 }, { "epoch": 1.91, "learning_rate": 1.3222543352601156e-06, "loss": 0.3635, "step": 10594 }, { "epoch": 1.91, "learning_rate": 1.3195447976878613e-06, "loss": 0.5075, "step": 10595 }, { "epoch": 1.91, "learning_rate": 1.316835260115607e-06, "loss": 0.3874, "step": 10596 }, { "epoch": 1.91, "learning_rate": 1.3141257225433525e-06, "loss": 0.4661, "step": 10597 }, { "epoch": 1.91, "learning_rate": 1.3114161849710984e-06, "loss": 0.2629, "step": 10598 }, { "epoch": 1.91, "learning_rate": 1.3087066473988438e-06, "loss": 0.5384, "step": 10599 }, { "epoch": 1.91, "learning_rate": 1.3059971098265897e-06, "loss": 0.5591, "step": 10600 }, { "epoch": 1.91, "learning_rate": 1.3032875722543353e-06, "loss": 0.3763, "step": 10601 }, { "epoch": 1.92, "learning_rate": 1.300578034682081e-06, "loss": 0.3316, "step": 10602 }, { "epoch": 1.92, "learning_rate": 1.2978684971098266e-06, "loss": 0.3134, "step": 10603 }, { "epoch": 1.92, "learning_rate": 1.2951589595375722e-06, "loss": 0.9661, "step": 10604 }, { "epoch": 1.92, "learning_rate": 1.292449421965318e-06, "loss": 0.384, "step": 10605 }, { "epoch": 1.92, "learning_rate": 1.2897398843930637e-06, "loss": 0.1169, "step": 10606 }, { "epoch": 1.92, "learning_rate": 1.2870303468208093e-06, "loss": 0.2845, "step": 10607 }, { "epoch": 1.92, "learning_rate": 1.284320809248555e-06, "loss": 0.1762, "step": 10608 }, { "epoch": 1.92, "learning_rate": 1.2816112716763006e-06, "loss": 0.5676, "step": 10609 }, { "epoch": 1.92, "learning_rate": 1.2789017341040462e-06, "loss": 0.4344, "step": 10610 }, { "epoch": 1.92, "learning_rate": 1.276192196531792e-06, "loss": 0.841, "step": 10611 }, { "epoch": 1.92, "learning_rate": 1.2734826589595375e-06, "loss": 0.1901, "step": 10612 }, { "epoch": 1.92, "learning_rate": 1.2707731213872834e-06, "loss": 0.2018, "step": 10613 }, { "epoch": 1.92, "learning_rate": 1.268063583815029e-06, "loss": 0.447, "step": 10614 }, { "epoch": 1.92, "learning_rate": 1.2653540462427746e-06, "loss": 0.4254, "step": 10615 }, { "epoch": 1.92, "learning_rate": 1.2626445086705203e-06, "loss": 0.2569, "step": 10616 }, { "epoch": 1.92, "learning_rate": 1.2599349710982659e-06, "loss": 1.0906, "step": 10617 }, { "epoch": 1.92, "learning_rate": 1.2572254335260115e-06, "loss": 0.3636, "step": 10618 }, { "epoch": 1.92, "learning_rate": 1.2545158959537574e-06, "loss": 0.4685, "step": 10619 }, { "epoch": 1.92, "learning_rate": 1.2518063583815028e-06, "loss": 0.8468, "step": 10620 }, { "epoch": 1.92, "learning_rate": 1.2490968208092486e-06, "loss": 0.8938, "step": 10621 }, { "epoch": 1.92, "learning_rate": 1.246387283236994e-06, "loss": 0.1496, "step": 10622 }, { "epoch": 1.92, "learning_rate": 1.24367774566474e-06, "loss": 1.116, "step": 10623 }, { "epoch": 1.92, "learning_rate": 1.2409682080924856e-06, "loss": 0.4268, "step": 10624 }, { "epoch": 1.92, "learning_rate": 1.2382586705202312e-06, "loss": 0.3713, "step": 10625 }, { "epoch": 1.92, "learning_rate": 1.2355491329479768e-06, "loss": 0.687, "step": 10626 }, { "epoch": 1.92, "learning_rate": 1.2328395953757227e-06, "loss": 0.7468, "step": 10627 }, { "epoch": 1.92, "learning_rate": 1.230130057803468e-06, "loss": 0.3687, "step": 10628 }, { "epoch": 1.92, "learning_rate": 1.227420520231214e-06, "loss": 1.0959, "step": 10629 }, { "epoch": 1.92, "learning_rate": 1.2247109826589596e-06, "loss": 0.4118, "step": 10630 }, { "epoch": 1.92, "learning_rate": 1.2220014450867052e-06, "loss": 0.6233, "step": 10631 }, { "epoch": 1.92, "learning_rate": 1.219291907514451e-06, "loss": 0.6089, "step": 10632 }, { "epoch": 1.92, "learning_rate": 1.2165823699421965e-06, "loss": 0.6761, "step": 10633 }, { "epoch": 1.92, "learning_rate": 1.2138728323699423e-06, "loss": 0.4376, "step": 10634 }, { "epoch": 1.92, "learning_rate": 1.211163294797688e-06, "loss": 0.5738, "step": 10635 }, { "epoch": 1.92, "learning_rate": 1.2084537572254336e-06, "loss": 0.7338, "step": 10636 }, { "epoch": 1.92, "learning_rate": 1.2057442196531792e-06, "loss": 0.3553, "step": 10637 }, { "epoch": 1.92, "learning_rate": 1.2030346820809249e-06, "loss": 0.414, "step": 10638 }, { "epoch": 1.92, "learning_rate": 1.2003251445086705e-06, "loss": 0.1337, "step": 10639 }, { "epoch": 1.92, "learning_rate": 1.1976156069364164e-06, "loss": 0.391, "step": 10640 }, { "epoch": 1.92, "learning_rate": 1.1949060693641618e-06, "loss": 0.8154, "step": 10641 }, { "epoch": 1.92, "learning_rate": 1.1921965317919076e-06, "loss": 0.7892, "step": 10642 }, { "epoch": 1.92, "learning_rate": 1.189486994219653e-06, "loss": 0.5758, "step": 10643 }, { "epoch": 1.92, "learning_rate": 1.186777456647399e-06, "loss": 1.0476, "step": 10644 }, { "epoch": 1.92, "learning_rate": 1.1840679190751445e-06, "loss": 0.6818, "step": 10645 }, { "epoch": 1.92, "learning_rate": 1.1813583815028902e-06, "loss": 0.4725, "step": 10646 }, { "epoch": 1.92, "learning_rate": 1.1786488439306358e-06, "loss": 0.221, "step": 10647 }, { "epoch": 1.92, "learning_rate": 1.1759393063583817e-06, "loss": 0.8336, "step": 10648 }, { "epoch": 1.92, "learning_rate": 1.173229768786127e-06, "loss": 0.4765, "step": 10649 }, { "epoch": 1.92, "learning_rate": 1.170520231213873e-06, "loss": 0.2489, "step": 10650 }, { "epoch": 1.92, "learning_rate": 1.1678106936416184e-06, "loss": 0.2487, "step": 10651 }, { "epoch": 1.92, "learning_rate": 1.1651011560693642e-06, "loss": 0.4996, "step": 10652 }, { "epoch": 1.92, "learning_rate": 1.1623916184971098e-06, "loss": 0.81, "step": 10653 }, { "epoch": 1.92, "learning_rate": 1.1596820809248555e-06, "loss": 0.317, "step": 10654 }, { "epoch": 1.92, "learning_rate": 1.156972543352601e-06, "loss": 0.0733, "step": 10655 }, { "epoch": 1.92, "learning_rate": 1.154263005780347e-06, "loss": 0.5998, "step": 10656 }, { "epoch": 1.93, "learning_rate": 1.1515534682080926e-06, "loss": 0.953, "step": 10657 }, { "epoch": 1.93, "learning_rate": 1.1488439306358382e-06, "loss": 0.5378, "step": 10658 }, { "epoch": 1.93, "learning_rate": 1.1461343930635839e-06, "loss": 0.5983, "step": 10659 }, { "epoch": 1.93, "learning_rate": 1.1434248554913295e-06, "loss": 0.5593, "step": 10660 }, { "epoch": 1.93, "learning_rate": 1.1407153179190753e-06, "loss": 0.4835, "step": 10661 }, { "epoch": 1.93, "learning_rate": 1.1380057803468208e-06, "loss": 0.4581, "step": 10662 }, { "epoch": 1.93, "learning_rate": 1.1352962427745666e-06, "loss": 0.4173, "step": 10663 }, { "epoch": 1.93, "learning_rate": 1.132586705202312e-06, "loss": 0.2737, "step": 10664 }, { "epoch": 1.93, "learning_rate": 1.1298771676300579e-06, "loss": 0.1423, "step": 10665 }, { "epoch": 1.93, "learning_rate": 1.1271676300578035e-06, "loss": 0.5099, "step": 10666 }, { "epoch": 1.93, "learning_rate": 1.1244580924855492e-06, "loss": 0.386, "step": 10667 }, { "epoch": 1.93, "learning_rate": 1.1217485549132948e-06, "loss": 0.6754, "step": 10668 }, { "epoch": 1.93, "learning_rate": 1.1190390173410406e-06, "loss": 0.3839, "step": 10669 }, { "epoch": 1.93, "learning_rate": 1.116329479768786e-06, "loss": 0.4676, "step": 10670 }, { "epoch": 1.93, "learning_rate": 1.113619942196532e-06, "loss": 0.5478, "step": 10671 }, { "epoch": 1.93, "learning_rate": 1.1109104046242773e-06, "loss": 0.4903, "step": 10672 }, { "epoch": 1.93, "learning_rate": 1.1082008670520232e-06, "loss": 0.4108, "step": 10673 }, { "epoch": 1.93, "learning_rate": 1.1054913294797688e-06, "loss": 0.2105, "step": 10674 }, { "epoch": 1.93, "learning_rate": 1.1027817919075145e-06, "loss": 0.4088, "step": 10675 }, { "epoch": 1.93, "learning_rate": 1.10007225433526e-06, "loss": 0.3316, "step": 10676 }, { "epoch": 1.93, "learning_rate": 1.097362716763006e-06, "loss": 0.4352, "step": 10677 }, { "epoch": 1.93, "learning_rate": 1.0946531791907514e-06, "loss": 0.4778, "step": 10678 }, { "epoch": 1.93, "learning_rate": 1.0919436416184972e-06, "loss": 0.7831, "step": 10679 }, { "epoch": 1.93, "learning_rate": 1.0892341040462426e-06, "loss": 0.6484, "step": 10680 }, { "epoch": 1.93, "learning_rate": 1.0865245664739885e-06, "loss": 0.5094, "step": 10681 }, { "epoch": 1.93, "learning_rate": 1.0838150289017341e-06, "loss": 0.4491, "step": 10682 }, { "epoch": 1.93, "learning_rate": 1.0811054913294797e-06, "loss": 0.3558, "step": 10683 }, { "epoch": 1.93, "learning_rate": 1.0783959537572256e-06, "loss": 0.4805, "step": 10684 }, { "epoch": 1.93, "learning_rate": 1.075686416184971e-06, "loss": 0.2659, "step": 10685 }, { "epoch": 1.93, "learning_rate": 1.0729768786127169e-06, "loss": 0.9381, "step": 10686 }, { "epoch": 1.93, "learning_rate": 1.0702673410404625e-06, "loss": 0.4665, "step": 10687 }, { "epoch": 1.93, "learning_rate": 1.0675578034682081e-06, "loss": 0.3346, "step": 10688 }, { "epoch": 1.93, "learning_rate": 1.0648482658959538e-06, "loss": 0.2377, "step": 10689 }, { "epoch": 1.93, "learning_rate": 1.0621387283236996e-06, "loss": 1.0762, "step": 10690 }, { "epoch": 1.93, "learning_rate": 1.059429190751445e-06, "loss": 0.3064, "step": 10691 }, { "epoch": 1.93, "learning_rate": 1.0567196531791909e-06, "loss": 0.5941, "step": 10692 }, { "epoch": 1.93, "learning_rate": 1.0540101156069363e-06, "loss": 0.991, "step": 10693 }, { "epoch": 1.93, "learning_rate": 1.0513005780346822e-06, "loss": 1.0233, "step": 10694 }, { "epoch": 1.93, "learning_rate": 1.0485910404624278e-06, "loss": 0.1884, "step": 10695 }, { "epoch": 1.93, "learning_rate": 1.0458815028901734e-06, "loss": 0.1931, "step": 10696 }, { "epoch": 1.93, "learning_rate": 1.043171965317919e-06, "loss": 0.4486, "step": 10697 }, { "epoch": 1.93, "learning_rate": 1.0404624277456647e-06, "loss": 0.6149, "step": 10698 }, { "epoch": 1.93, "learning_rate": 1.0377528901734103e-06, "loss": 0.723, "step": 10699 }, { "epoch": 1.93, "learning_rate": 1.0350433526011562e-06, "loss": 0.6849, "step": 10700 }, { "epoch": 1.93, "learning_rate": 1.0323338150289016e-06, "loss": 0.1611, "step": 10701 }, { "epoch": 1.93, "learning_rate": 1.0296242774566475e-06, "loss": 0.6657, "step": 10702 }, { "epoch": 1.93, "learning_rate": 1.026914739884393e-06, "loss": 0.6836, "step": 10703 }, { "epoch": 1.93, "learning_rate": 1.0242052023121387e-06, "loss": 0.6673, "step": 10704 }, { "epoch": 1.93, "learning_rate": 1.0214956647398844e-06, "loss": 0.5923, "step": 10705 }, { "epoch": 1.93, "learning_rate": 1.01878612716763e-06, "loss": 0.3243, "step": 10706 }, { "epoch": 1.93, "learning_rate": 1.0160765895953756e-06, "loss": 0.2145, "step": 10707 }, { "epoch": 1.93, "learning_rate": 1.0133670520231215e-06, "loss": 0.366, "step": 10708 }, { "epoch": 1.93, "learning_rate": 1.010657514450867e-06, "loss": 0.5382, "step": 10709 }, { "epoch": 1.93, "learning_rate": 1.0079479768786128e-06, "loss": 0.4142, "step": 10710 }, { "epoch": 1.93, "learning_rate": 1.0052384393063586e-06, "loss": 0.452, "step": 10711 }, { "epoch": 1.93, "learning_rate": 1.002528901734104e-06, "loss": 0.718, "step": 10712 }, { "epoch": 1.94, "learning_rate": 9.998193641618499e-07, "loss": 0.7004, "step": 10713 }, { "epoch": 1.94, "learning_rate": 9.971098265895953e-07, "loss": 0.2501, "step": 10714 }, { "epoch": 1.94, "learning_rate": 9.944002890173411e-07, "loss": 0.4059, "step": 10715 }, { "epoch": 1.94, "learning_rate": 9.916907514450868e-07, "loss": 0.2334, "step": 10716 }, { "epoch": 1.94, "learning_rate": 9.889812138728324e-07, "loss": 0.8063, "step": 10717 }, { "epoch": 1.94, "learning_rate": 9.86271676300578e-07, "loss": 0.4254, "step": 10718 }, { "epoch": 1.94, "learning_rate": 9.835621387283237e-07, "loss": 0.685, "step": 10719 }, { "epoch": 1.94, "learning_rate": 9.808526011560693e-07, "loss": 0.2908, "step": 10720 }, { "epoch": 1.94, "learning_rate": 9.781430635838152e-07, "loss": 0.3461, "step": 10721 }, { "epoch": 1.94, "learning_rate": 9.754335260115606e-07, "loss": 0.4916, "step": 10722 }, { "epoch": 1.94, "learning_rate": 9.727239884393064e-07, "loss": 0.277, "step": 10723 }, { "epoch": 1.94, "learning_rate": 9.70014450867052e-07, "loss": 0.4982, "step": 10724 }, { "epoch": 1.94, "learning_rate": 9.673049132947977e-07, "loss": 0.7595, "step": 10725 }, { "epoch": 1.94, "learning_rate": 9.645953757225434e-07, "loss": 0.8431, "step": 10726 }, { "epoch": 1.94, "learning_rate": 9.61885838150289e-07, "loss": 0.4956, "step": 10727 }, { "epoch": 1.94, "learning_rate": 9.591763005780346e-07, "loss": 0.422, "step": 10728 }, { "epoch": 1.94, "learning_rate": 9.564667630057805e-07, "loss": 0.4817, "step": 10729 }, { "epoch": 1.94, "learning_rate": 9.537572254335259e-07, "loss": 0.1788, "step": 10730 }, { "epoch": 1.94, "learning_rate": 9.510476878612717e-07, "loss": 0.9086, "step": 10731 }, { "epoch": 1.94, "learning_rate": 9.483381502890175e-07, "loss": 0.1398, "step": 10732 }, { "epoch": 1.94, "learning_rate": 9.45628612716763e-07, "loss": 0.3545, "step": 10733 }, { "epoch": 1.94, "learning_rate": 9.429190751445088e-07, "loss": 0.4131, "step": 10734 }, { "epoch": 1.94, "learning_rate": 9.402095375722543e-07, "loss": 0.4959, "step": 10735 }, { "epoch": 1.94, "learning_rate": 9.375e-07, "loss": 0.3944, "step": 10736 }, { "epoch": 1.94, "learning_rate": 9.347904624277457e-07, "loss": 0.6266, "step": 10737 }, { "epoch": 1.94, "learning_rate": 9.320809248554913e-07, "loss": 1.2981, "step": 10738 }, { "epoch": 1.94, "learning_rate": 9.29371387283237e-07, "loss": 0.6932, "step": 10739 }, { "epoch": 1.94, "learning_rate": 9.266618497109827e-07, "loss": 0.3493, "step": 10740 }, { "epoch": 1.94, "learning_rate": 9.239523121387283e-07, "loss": 0.2205, "step": 10741 }, { "epoch": 1.94, "learning_rate": 9.212427745664739e-07, "loss": 1.1282, "step": 10742 }, { "epoch": 1.94, "learning_rate": 9.185332369942197e-07, "loss": 0.5921, "step": 10743 }, { "epoch": 1.94, "learning_rate": 9.158236994219653e-07, "loss": 0.5681, "step": 10744 }, { "epoch": 1.94, "learning_rate": 9.13114161849711e-07, "loss": 0.3972, "step": 10745 }, { "epoch": 1.94, "learning_rate": 9.104046242774566e-07, "loss": 0.3544, "step": 10746 }, { "epoch": 1.94, "learning_rate": 9.076950867052023e-07, "loss": 0.5783, "step": 10747 }, { "epoch": 1.94, "learning_rate": 9.04985549132948e-07, "loss": 0.5554, "step": 10748 }, { "epoch": 1.94, "learning_rate": 9.022760115606936e-07, "loss": 1.0014, "step": 10749 }, { "epoch": 1.94, "learning_rate": 8.995664739884393e-07, "loss": 0.6747, "step": 10750 }, { "epoch": 1.94, "learning_rate": 8.968569364161851e-07, "loss": 0.5451, "step": 10751 }, { "epoch": 1.94, "learning_rate": 8.941473988439307e-07, "loss": 0.2153, "step": 10752 }, { "epoch": 1.94, "learning_rate": 8.914378612716764e-07, "loss": 1.0067, "step": 10753 }, { "epoch": 1.94, "learning_rate": 8.88728323699422e-07, "loss": 0.5491, "step": 10754 }, { "epoch": 1.94, "learning_rate": 8.860187861271677e-07, "loss": 0.5766, "step": 10755 }, { "epoch": 1.94, "learning_rate": 8.833092485549134e-07, "loss": 0.6061, "step": 10756 }, { "epoch": 1.94, "learning_rate": 8.80599710982659e-07, "loss": 0.5156, "step": 10757 }, { "epoch": 1.94, "learning_rate": 8.778901734104046e-07, "loss": 0.2913, "step": 10758 }, { "epoch": 1.94, "learning_rate": 8.751806358381503e-07, "loss": 0.4589, "step": 10759 }, { "epoch": 1.94, "learning_rate": 8.72471098265896e-07, "loss": 0.553, "step": 10760 }, { "epoch": 1.94, "learning_rate": 8.697615606936417e-07, "loss": 0.2665, "step": 10761 }, { "epoch": 1.94, "learning_rate": 8.670520231213873e-07, "loss": 0.3245, "step": 10762 }, { "epoch": 1.94, "learning_rate": 8.643424855491329e-07, "loss": 0.5653, "step": 10763 }, { "epoch": 1.94, "learning_rate": 8.616329479768787e-07, "loss": 0.7005, "step": 10764 }, { "epoch": 1.94, "learning_rate": 8.589234104046243e-07, "loss": 0.2312, "step": 10765 }, { "epoch": 1.94, "learning_rate": 8.562138728323699e-07, "loss": 0.2145, "step": 10766 }, { "epoch": 1.94, "learning_rate": 8.535043352601156e-07, "loss": 0.5507, "step": 10767 }, { "epoch": 1.95, "learning_rate": 8.507947976878613e-07, "loss": 0.2793, "step": 10768 }, { "epoch": 1.95, "learning_rate": 8.48085260115607e-07, "loss": 0.5039, "step": 10769 }, { "epoch": 1.95, "learning_rate": 8.453757225433526e-07, "loss": 0.8508, "step": 10770 }, { "epoch": 1.95, "learning_rate": 8.426661849710982e-07, "loss": 1.7485, "step": 10771 }, { "epoch": 1.95, "learning_rate": 8.39956647398844e-07, "loss": 0.482, "step": 10772 }, { "epoch": 1.95, "learning_rate": 8.372471098265896e-07, "loss": 0.6943, "step": 10773 }, { "epoch": 1.95, "learning_rate": 8.345375722543352e-07, "loss": 0.3695, "step": 10774 }, { "epoch": 1.95, "learning_rate": 8.318280346820809e-07, "loss": 0.2191, "step": 10775 }, { "epoch": 1.95, "learning_rate": 8.291184971098266e-07, "loss": 0.5187, "step": 10776 }, { "epoch": 1.95, "learning_rate": 8.264089595375724e-07, "loss": 0.4321, "step": 10777 }, { "epoch": 1.95, "learning_rate": 8.23699421965318e-07, "loss": 0.3013, "step": 10778 }, { "epoch": 1.95, "learning_rate": 8.209898843930636e-07, "loss": 0.6108, "step": 10779 }, { "epoch": 1.95, "learning_rate": 8.182803468208093e-07, "loss": 0.313, "step": 10780 }, { "epoch": 1.95, "learning_rate": 8.15570809248555e-07, "loss": 0.1548, "step": 10781 }, { "epoch": 1.95, "learning_rate": 8.128612716763006e-07, "loss": 0.9614, "step": 10782 }, { "epoch": 1.95, "learning_rate": 8.101517341040463e-07, "loss": 0.9165, "step": 10783 }, { "epoch": 1.95, "learning_rate": 8.074421965317919e-07, "loss": 0.2497, "step": 10784 }, { "epoch": 1.95, "learning_rate": 8.047326589595377e-07, "loss": 0.5348, "step": 10785 }, { "epoch": 1.95, "learning_rate": 8.020231213872833e-07, "loss": 0.543, "step": 10786 }, { "epoch": 1.95, "learning_rate": 7.993135838150289e-07, "loss": 1.0371, "step": 10787 }, { "epoch": 1.95, "learning_rate": 7.966040462427746e-07, "loss": 0.5554, "step": 10788 }, { "epoch": 1.95, "learning_rate": 7.938945086705203e-07, "loss": 0.6327, "step": 10789 }, { "epoch": 1.95, "learning_rate": 7.911849710982659e-07, "loss": 0.5394, "step": 10790 }, { "epoch": 1.95, "learning_rate": 7.884754335260116e-07, "loss": 1.2459, "step": 10791 }, { "epoch": 1.95, "learning_rate": 7.857658959537572e-07, "loss": 0.8429, "step": 10792 }, { "epoch": 1.95, "learning_rate": 7.830563583815029e-07, "loss": 0.4255, "step": 10793 }, { "epoch": 1.95, "learning_rate": 7.803468208092486e-07, "loss": 0.6726, "step": 10794 }, { "epoch": 1.95, "learning_rate": 7.776372832369942e-07, "loss": 0.3302, "step": 10795 }, { "epoch": 1.95, "learning_rate": 7.749277456647399e-07, "loss": 0.2496, "step": 10796 }, { "epoch": 1.95, "learning_rate": 7.722182080924855e-07, "loss": 0.2956, "step": 10797 }, { "epoch": 1.95, "learning_rate": 7.695086705202312e-07, "loss": 0.5299, "step": 10798 }, { "epoch": 1.95, "learning_rate": 7.667991329479769e-07, "loss": 0.3806, "step": 10799 }, { "epoch": 1.95, "learning_rate": 7.640895953757225e-07, "loss": 0.3712, "step": 10800 }, { "epoch": 1.95, "learning_rate": 7.613800578034681e-07, "loss": 0.5001, "step": 10801 }, { "epoch": 1.95, "learning_rate": 7.586705202312139e-07, "loss": 0.5335, "step": 10802 }, { "epoch": 1.95, "learning_rate": 7.559609826589596e-07, "loss": 0.3601, "step": 10803 }, { "epoch": 1.95, "learning_rate": 7.532514450867053e-07, "loss": 1.274, "step": 10804 }, { "epoch": 1.95, "learning_rate": 7.505419075144509e-07, "loss": 0.8289, "step": 10805 }, { "epoch": 1.95, "learning_rate": 7.478323699421966e-07, "loss": 0.3996, "step": 10806 }, { "epoch": 1.95, "learning_rate": 7.451228323699423e-07, "loss": 0.5115, "step": 10807 }, { "epoch": 1.95, "learning_rate": 7.424132947976879e-07, "loss": 0.2641, "step": 10808 }, { "epoch": 1.95, "learning_rate": 7.397037572254335e-07, "loss": 0.6139, "step": 10809 }, { "epoch": 1.95, "learning_rate": 7.369942196531793e-07, "loss": 0.5078, "step": 10810 }, { "epoch": 1.95, "learning_rate": 7.342846820809249e-07, "loss": 0.3907, "step": 10811 }, { "epoch": 1.95, "learning_rate": 7.315751445086706e-07, "loss": 0.8083, "step": 10812 }, { "epoch": 1.95, "learning_rate": 7.288656069364162e-07, "loss": 0.5647, "step": 10813 }, { "epoch": 1.95, "learning_rate": 7.261560693641618e-07, "loss": 0.2956, "step": 10814 }, { "epoch": 1.95, "learning_rate": 7.234465317919076e-07, "loss": 0.7234, "step": 10815 }, { "epoch": 1.95, "learning_rate": 7.207369942196532e-07, "loss": 0.5757, "step": 10816 }, { "epoch": 1.95, "learning_rate": 7.180274566473988e-07, "loss": 0.6912, "step": 10817 }, { "epoch": 1.95, "learning_rate": 7.153179190751445e-07, "loss": 0.6265, "step": 10818 }, { "epoch": 1.95, "learning_rate": 7.126083815028902e-07, "loss": 0.209, "step": 10819 }, { "epoch": 1.95, "learning_rate": 7.098988439306358e-07, "loss": 0.3571, "step": 10820 }, { "epoch": 1.95, "learning_rate": 7.071893063583815e-07, "loss": 0.9804, "step": 10821 }, { "epoch": 1.95, "learning_rate": 7.044797687861271e-07, "loss": 0.4489, "step": 10822 }, { "epoch": 1.96, "learning_rate": 7.017702312138729e-07, "loss": 0.2605, "step": 10823 }, { "epoch": 1.96, "learning_rate": 6.990606936416185e-07, "loss": 0.6883, "step": 10824 }, { "epoch": 1.96, "learning_rate": 6.963511560693641e-07, "loss": 0.7367, "step": 10825 }, { "epoch": 1.96, "learning_rate": 6.936416184971098e-07, "loss": 0.1876, "step": 10826 }, { "epoch": 1.96, "learning_rate": 6.909320809248555e-07, "loss": 0.4207, "step": 10827 }, { "epoch": 1.96, "learning_rate": 6.882225433526011e-07, "loss": 0.7124, "step": 10828 }, { "epoch": 1.96, "learning_rate": 6.855130057803468e-07, "loss": 0.9985, "step": 10829 }, { "epoch": 1.96, "learning_rate": 6.828034682080925e-07, "loss": 0.7117, "step": 10830 }, { "epoch": 1.96, "learning_rate": 6.800939306358383e-07, "loss": 0.7009, "step": 10831 }, { "epoch": 1.96, "learning_rate": 6.773843930635839e-07, "loss": 0.4206, "step": 10832 }, { "epoch": 1.96, "learning_rate": 6.746748554913295e-07, "loss": 0.6433, "step": 10833 }, { "epoch": 1.96, "learning_rate": 6.719653179190752e-07, "loss": 0.4325, "step": 10834 }, { "epoch": 1.96, "learning_rate": 6.692557803468208e-07, "loss": 0.4168, "step": 10835 }, { "epoch": 1.96, "learning_rate": 6.665462427745665e-07, "loss": 1.1041, "step": 10836 }, { "epoch": 1.96, "learning_rate": 6.638367052023122e-07, "loss": 0.3184, "step": 10837 }, { "epoch": 1.96, "learning_rate": 6.611271676300578e-07, "loss": 0.2734, "step": 10838 }, { "epoch": 1.96, "learning_rate": 6.584176300578035e-07, "loss": 0.2496, "step": 10839 }, { "epoch": 1.96, "learning_rate": 6.557080924855492e-07, "loss": 0.3728, "step": 10840 }, { "epoch": 1.96, "learning_rate": 6.529985549132948e-07, "loss": 0.3021, "step": 10841 }, { "epoch": 1.96, "learning_rate": 6.502890173410405e-07, "loss": 0.3013, "step": 10842 }, { "epoch": 1.96, "learning_rate": 6.475794797687861e-07, "loss": 0.5737, "step": 10843 }, { "epoch": 1.96, "learning_rate": 6.448699421965318e-07, "loss": 0.3584, "step": 10844 }, { "epoch": 1.96, "learning_rate": 6.421604046242775e-07, "loss": 0.5248, "step": 10845 }, { "epoch": 1.96, "learning_rate": 6.394508670520231e-07, "loss": 0.882, "step": 10846 }, { "epoch": 1.96, "learning_rate": 6.367413294797688e-07, "loss": 1.3712, "step": 10847 }, { "epoch": 1.96, "learning_rate": 6.340317919075145e-07, "loss": 0.3166, "step": 10848 }, { "epoch": 1.96, "learning_rate": 6.313222543352601e-07, "loss": 0.7205, "step": 10849 }, { "epoch": 1.96, "learning_rate": 6.286127167630058e-07, "loss": 0.7985, "step": 10850 }, { "epoch": 1.96, "learning_rate": 6.259031791907514e-07, "loss": 0.5577, "step": 10851 }, { "epoch": 1.96, "learning_rate": 6.23193641618497e-07, "loss": 0.3302, "step": 10852 }, { "epoch": 1.96, "learning_rate": 6.204841040462428e-07, "loss": 0.8839, "step": 10853 }, { "epoch": 1.96, "learning_rate": 6.177745664739884e-07, "loss": 0.7027, "step": 10854 }, { "epoch": 1.96, "learning_rate": 6.15065028901734e-07, "loss": 0.3868, "step": 10855 }, { "epoch": 1.96, "learning_rate": 6.123554913294798e-07, "loss": 0.4592, "step": 10856 }, { "epoch": 1.96, "learning_rate": 6.096459537572255e-07, "loss": 0.7768, "step": 10857 }, { "epoch": 1.96, "learning_rate": 6.069364161849712e-07, "loss": 0.4714, "step": 10858 }, { "epoch": 1.96, "learning_rate": 6.042268786127168e-07, "loss": 0.7343, "step": 10859 }, { "epoch": 1.96, "learning_rate": 6.015173410404624e-07, "loss": 0.9162, "step": 10860 }, { "epoch": 1.96, "learning_rate": 5.988078034682082e-07, "loss": 0.2658, "step": 10861 }, { "epoch": 1.96, "learning_rate": 5.960982658959538e-07, "loss": 0.9481, "step": 10862 }, { "epoch": 1.96, "learning_rate": 5.933887283236995e-07, "loss": 0.4406, "step": 10863 }, { "epoch": 1.96, "learning_rate": 5.906791907514451e-07, "loss": 0.3116, "step": 10864 }, { "epoch": 1.96, "learning_rate": 5.879696531791908e-07, "loss": 0.2169, "step": 10865 }, { "epoch": 1.96, "learning_rate": 5.852601156069365e-07, "loss": 0.131, "step": 10866 }, { "epoch": 1.96, "learning_rate": 5.825505780346821e-07, "loss": 0.9328, "step": 10867 }, { "epoch": 1.96, "learning_rate": 5.798410404624277e-07, "loss": 0.8435, "step": 10868 }, { "epoch": 1.96, "learning_rate": 5.771315028901735e-07, "loss": 0.7638, "step": 10869 }, { "epoch": 1.96, "learning_rate": 5.744219653179191e-07, "loss": 0.5887, "step": 10870 }, { "epoch": 1.96, "learning_rate": 5.717124277456647e-07, "loss": 0.351, "step": 10871 }, { "epoch": 1.96, "learning_rate": 5.690028901734104e-07, "loss": 0.3546, "step": 10872 }, { "epoch": 1.96, "learning_rate": 5.66293352601156e-07, "loss": 0.2592, "step": 10873 }, { "epoch": 1.96, "learning_rate": 5.635838150289018e-07, "loss": 0.308, "step": 10874 }, { "epoch": 1.96, "learning_rate": 5.608742774566474e-07, "loss": 0.8422, "step": 10875 }, { "epoch": 1.96, "learning_rate": 5.58164739884393e-07, "loss": 0.8042, "step": 10876 }, { "epoch": 1.96, "learning_rate": 5.554552023121387e-07, "loss": 0.6357, "step": 10877 }, { "epoch": 1.96, "learning_rate": 5.527456647398844e-07, "loss": 0.5217, "step": 10878 }, { "epoch": 1.97, "learning_rate": 5.5003612716763e-07, "loss": 1.181, "step": 10879 }, { "epoch": 1.97, "learning_rate": 5.473265895953757e-07, "loss": 0.2476, "step": 10880 }, { "epoch": 1.97, "learning_rate": 5.446170520231213e-07, "loss": 0.2949, "step": 10881 }, { "epoch": 1.97, "learning_rate": 5.419075144508671e-07, "loss": 0.5605, "step": 10882 }, { "epoch": 1.97, "learning_rate": 5.391979768786128e-07, "loss": 0.3602, "step": 10883 }, { "epoch": 1.97, "learning_rate": 5.364884393063584e-07, "loss": 0.5759, "step": 10884 }, { "epoch": 1.97, "learning_rate": 5.337789017341041e-07, "loss": 0.3047, "step": 10885 }, { "epoch": 1.97, "learning_rate": 5.310693641618498e-07, "loss": 0.55, "step": 10886 }, { "epoch": 1.97, "learning_rate": 5.283598265895954e-07, "loss": 0.4973, "step": 10887 }, { "epoch": 1.97, "learning_rate": 5.256502890173411e-07, "loss": 0.3197, "step": 10888 }, { "epoch": 1.97, "learning_rate": 5.229407514450867e-07, "loss": 0.3856, "step": 10889 }, { "epoch": 1.97, "learning_rate": 5.202312138728324e-07, "loss": 0.363, "step": 10890 }, { "epoch": 1.97, "learning_rate": 5.175216763005781e-07, "loss": 0.3633, "step": 10891 }, { "epoch": 1.97, "learning_rate": 5.148121387283237e-07, "loss": 0.367, "step": 10892 }, { "epoch": 1.97, "learning_rate": 5.121026011560694e-07, "loss": 0.2409, "step": 10893 }, { "epoch": 1.97, "learning_rate": 5.09393063583815e-07, "loss": 0.2087, "step": 10894 }, { "epoch": 1.97, "learning_rate": 5.066835260115607e-07, "loss": 0.6425, "step": 10895 }, { "epoch": 1.97, "learning_rate": 5.039739884393064e-07, "loss": 0.4585, "step": 10896 }, { "epoch": 1.97, "learning_rate": 5.01264450867052e-07, "loss": 0.8704, "step": 10897 }, { "epoch": 1.97, "learning_rate": 4.985549132947976e-07, "loss": 0.8864, "step": 10898 }, { "epoch": 1.97, "learning_rate": 4.958453757225434e-07, "loss": 0.2668, "step": 10899 }, { "epoch": 1.97, "learning_rate": 4.93135838150289e-07, "loss": 0.2986, "step": 10900 }, { "epoch": 1.97, "learning_rate": 4.904263005780347e-07, "loss": 0.2338, "step": 10901 }, { "epoch": 1.97, "learning_rate": 4.877167630057803e-07, "loss": 0.3641, "step": 10902 }, { "epoch": 1.97, "learning_rate": 4.85007225433526e-07, "loss": 0.6223, "step": 10903 }, { "epoch": 1.97, "learning_rate": 4.822976878612717e-07, "loss": 0.6058, "step": 10904 }, { "epoch": 1.97, "learning_rate": 4.795881502890173e-07, "loss": 0.8279, "step": 10905 }, { "epoch": 1.97, "learning_rate": 4.768786127167629e-07, "loss": 0.5197, "step": 10906 }, { "epoch": 1.97, "learning_rate": 4.7416907514450874e-07, "loss": 0.8729, "step": 10907 }, { "epoch": 1.97, "learning_rate": 4.714595375722544e-07, "loss": 0.7484, "step": 10908 }, { "epoch": 1.97, "learning_rate": 4.6875e-07, "loss": 0.3094, "step": 10909 }, { "epoch": 1.97, "learning_rate": 4.6604046242774565e-07, "loss": 0.3062, "step": 10910 }, { "epoch": 1.97, "learning_rate": 4.6333092485549134e-07, "loss": 0.8231, "step": 10911 }, { "epoch": 1.97, "learning_rate": 4.6062138728323697e-07, "loss": 0.7316, "step": 10912 }, { "epoch": 1.97, "learning_rate": 4.5791184971098266e-07, "loss": 0.5848, "step": 10913 }, { "epoch": 1.97, "learning_rate": 4.552023121387283e-07, "loss": 0.7227, "step": 10914 }, { "epoch": 1.97, "learning_rate": 4.52492774566474e-07, "loss": 0.8298, "step": 10915 }, { "epoch": 1.97, "learning_rate": 4.4978323699421967e-07, "loss": 0.21, "step": 10916 }, { "epoch": 1.97, "learning_rate": 4.4707369942196536e-07, "loss": 1.1896, "step": 10917 }, { "epoch": 1.97, "learning_rate": 4.44364161849711e-07, "loss": 0.5316, "step": 10918 }, { "epoch": 1.97, "learning_rate": 4.416546242774567e-07, "loss": 0.8096, "step": 10919 }, { "epoch": 1.97, "learning_rate": 4.389450867052023e-07, "loss": 0.4807, "step": 10920 }, { "epoch": 1.97, "learning_rate": 4.36235549132948e-07, "loss": 0.4683, "step": 10921 }, { "epoch": 1.97, "learning_rate": 4.3352601156069365e-07, "loss": 0.2904, "step": 10922 }, { "epoch": 1.97, "learning_rate": 4.3081647398843933e-07, "loss": 0.5986, "step": 10923 }, { "epoch": 1.97, "learning_rate": 4.2810693641618497e-07, "loss": 1.0057, "step": 10924 }, { "epoch": 1.97, "learning_rate": 4.2539739884393066e-07, "loss": 0.3582, "step": 10925 }, { "epoch": 1.97, "learning_rate": 4.226878612716763e-07, "loss": 0.4881, "step": 10926 }, { "epoch": 1.97, "learning_rate": 4.19978323699422e-07, "loss": 0.3236, "step": 10927 }, { "epoch": 1.97, "learning_rate": 4.172687861271676e-07, "loss": 0.2302, "step": 10928 }, { "epoch": 1.97, "learning_rate": 4.145592485549133e-07, "loss": 0.2985, "step": 10929 }, { "epoch": 1.97, "learning_rate": 4.11849710982659e-07, "loss": 0.4307, "step": 10930 }, { "epoch": 1.97, "learning_rate": 4.0914017341040463e-07, "loss": 0.282, "step": 10931 }, { "epoch": 1.97, "learning_rate": 4.064306358381503e-07, "loss": 0.8534, "step": 10932 }, { "epoch": 1.97, "learning_rate": 4.0372109826589595e-07, "loss": 0.813, "step": 10933 }, { "epoch": 1.98, "learning_rate": 4.0101156069364164e-07, "loss": 0.2413, "step": 10934 }, { "epoch": 1.98, "learning_rate": 3.983020231213873e-07, "loss": 0.7685, "step": 10935 }, { "epoch": 1.98, "learning_rate": 3.9559248554913297e-07, "loss": 0.3827, "step": 10936 }, { "epoch": 1.98, "learning_rate": 3.928829479768786e-07, "loss": 0.3744, "step": 10937 }, { "epoch": 1.98, "learning_rate": 3.901734104046243e-07, "loss": 0.7721, "step": 10938 }, { "epoch": 1.98, "learning_rate": 3.8746387283236993e-07, "loss": 0.5407, "step": 10939 }, { "epoch": 1.98, "learning_rate": 3.847543352601156e-07, "loss": 0.4282, "step": 10940 }, { "epoch": 1.98, "learning_rate": 3.8204479768786125e-07, "loss": 0.5417, "step": 10941 }, { "epoch": 1.98, "learning_rate": 3.7933526011560694e-07, "loss": 0.389, "step": 10942 }, { "epoch": 1.98, "learning_rate": 3.7662572254335263e-07, "loss": 0.4789, "step": 10943 }, { "epoch": 1.98, "learning_rate": 3.739161849710983e-07, "loss": 0.2974, "step": 10944 }, { "epoch": 1.98, "learning_rate": 3.7120664739884395e-07, "loss": 0.3875, "step": 10945 }, { "epoch": 1.98, "learning_rate": 3.6849710982658964e-07, "loss": 0.8946, "step": 10946 }, { "epoch": 1.98, "learning_rate": 3.657875722543353e-07, "loss": 0.4619, "step": 10947 }, { "epoch": 1.98, "learning_rate": 3.630780346820809e-07, "loss": 0.5067, "step": 10948 }, { "epoch": 1.98, "learning_rate": 3.603684971098266e-07, "loss": 0.5309, "step": 10949 }, { "epoch": 1.98, "learning_rate": 3.5765895953757224e-07, "loss": 0.3689, "step": 10950 }, { "epoch": 1.98, "learning_rate": 3.549494219653179e-07, "loss": 0.442, "step": 10951 }, { "epoch": 1.98, "learning_rate": 3.5223988439306356e-07, "loss": 0.5327, "step": 10952 }, { "epoch": 1.98, "learning_rate": 3.4953034682080925e-07, "loss": 1.0726, "step": 10953 }, { "epoch": 1.98, "learning_rate": 3.468208092485549e-07, "loss": 0.5578, "step": 10954 }, { "epoch": 1.98, "learning_rate": 3.4411127167630057e-07, "loss": 1.252, "step": 10955 }, { "epoch": 1.98, "learning_rate": 3.4140173410404626e-07, "loss": 0.3769, "step": 10956 }, { "epoch": 1.98, "learning_rate": 3.3869219653179195e-07, "loss": 1.1183, "step": 10957 }, { "epoch": 1.98, "learning_rate": 3.359826589595376e-07, "loss": 0.4697, "step": 10958 }, { "epoch": 1.98, "learning_rate": 3.332731213872833e-07, "loss": 0.434, "step": 10959 }, { "epoch": 1.98, "learning_rate": 3.305635838150289e-07, "loss": 1.024, "step": 10960 }, { "epoch": 1.98, "learning_rate": 3.278540462427746e-07, "loss": 0.4944, "step": 10961 }, { "epoch": 1.98, "learning_rate": 3.2514450867052023e-07, "loss": 0.5563, "step": 10962 }, { "epoch": 1.98, "learning_rate": 3.224349710982659e-07, "loss": 0.5535, "step": 10963 }, { "epoch": 1.98, "learning_rate": 3.1972543352601156e-07, "loss": 0.2466, "step": 10964 }, { "epoch": 1.98, "learning_rate": 3.1701589595375725e-07, "loss": 0.2782, "step": 10965 }, { "epoch": 1.98, "learning_rate": 3.143063583815029e-07, "loss": 0.6737, "step": 10966 }, { "epoch": 1.98, "learning_rate": 3.115968208092485e-07, "loss": 0.2573, "step": 10967 }, { "epoch": 1.98, "learning_rate": 3.088872832369942e-07, "loss": 0.3719, "step": 10968 }, { "epoch": 1.98, "learning_rate": 3.061777456647399e-07, "loss": 0.518, "step": 10969 }, { "epoch": 1.98, "learning_rate": 3.034682080924856e-07, "loss": 0.4543, "step": 10970 }, { "epoch": 1.98, "learning_rate": 3.007586705202312e-07, "loss": 0.506, "step": 10971 }, { "epoch": 1.98, "learning_rate": 2.980491329479769e-07, "loss": 0.3921, "step": 10972 }, { "epoch": 1.98, "learning_rate": 2.9533959537572254e-07, "loss": 0.4785, "step": 10973 }, { "epoch": 1.98, "learning_rate": 2.9263005780346823e-07, "loss": 0.5335, "step": 10974 }, { "epoch": 1.98, "learning_rate": 2.8992052023121387e-07, "loss": 0.6663, "step": 10975 }, { "epoch": 1.98, "learning_rate": 2.8721098265895956e-07, "loss": 0.2546, "step": 10976 }, { "epoch": 1.98, "learning_rate": 2.845014450867052e-07, "loss": 0.4611, "step": 10977 }, { "epoch": 1.98, "learning_rate": 2.817919075144509e-07, "loss": 0.4794, "step": 10978 }, { "epoch": 1.98, "learning_rate": 2.790823699421965e-07, "loss": 0.4001, "step": 10979 }, { "epoch": 1.98, "learning_rate": 2.763728323699422e-07, "loss": 0.381, "step": 10980 }, { "epoch": 1.98, "learning_rate": 2.7366329479768784e-07, "loss": 0.5583, "step": 10981 }, { "epoch": 1.98, "learning_rate": 2.7095375722543353e-07, "loss": 0.4364, "step": 10982 }, { "epoch": 1.98, "learning_rate": 2.682442196531792e-07, "loss": 0.4241, "step": 10983 }, { "epoch": 1.98, "learning_rate": 2.655346820809249e-07, "loss": 0.2177, "step": 10984 }, { "epoch": 1.98, "learning_rate": 2.6282514450867054e-07, "loss": 0.5357, "step": 10985 }, { "epoch": 1.98, "learning_rate": 2.601156069364162e-07, "loss": 0.7809, "step": 10986 }, { "epoch": 1.98, "learning_rate": 2.5740606936416187e-07, "loss": 0.1737, "step": 10987 }, { "epoch": 1.98, "learning_rate": 2.546965317919075e-07, "loss": 1.2332, "step": 10988 }, { "epoch": 1.99, "learning_rate": 2.519869942196532e-07, "loss": 0.7249, "step": 10989 }, { "epoch": 1.99, "learning_rate": 2.492774566473988e-07, "loss": 0.4602, "step": 10990 }, { "epoch": 1.99, "learning_rate": 2.465679190751445e-07, "loss": 0.2468, "step": 10991 }, { "epoch": 1.99, "learning_rate": 2.4385838150289015e-07, "loss": 0.7332, "step": 10992 }, { "epoch": 1.99, "learning_rate": 2.4114884393063584e-07, "loss": 0.1426, "step": 10993 }, { "epoch": 1.99, "learning_rate": 2.3843930635838147e-07, "loss": 0.9876, "step": 10994 }, { "epoch": 1.99, "learning_rate": 2.357297687861272e-07, "loss": 0.7279, "step": 10995 }, { "epoch": 1.99, "learning_rate": 2.3302023121387282e-07, "loss": 0.4606, "step": 10996 }, { "epoch": 1.99, "learning_rate": 2.3031069364161849e-07, "loss": 0.4803, "step": 10997 }, { "epoch": 1.99, "learning_rate": 2.2760115606936415e-07, "loss": 0.4295, "step": 10998 }, { "epoch": 1.99, "learning_rate": 2.2489161849710984e-07, "loss": 0.2811, "step": 10999 }, { "epoch": 1.99, "learning_rate": 2.221820809248555e-07, "loss": 0.4138, "step": 11000 }, { "epoch": 1.99, "eval_exact_match": 88.45789971617786, "eval_f1": 94.3054529598198, "step": 11000 }, { "epoch": 1.99, "learning_rate": 2.1947254335260116e-07, "loss": 0.4641, "step": 11001 }, { "epoch": 1.99, "learning_rate": 2.1676300578034682e-07, "loss": 0.6234, "step": 11002 }, { "epoch": 1.99, "learning_rate": 2.1405346820809248e-07, "loss": 0.515, "step": 11003 }, { "epoch": 1.99, "learning_rate": 2.1134393063583815e-07, "loss": 1.3814, "step": 11004 }, { "epoch": 1.99, "learning_rate": 2.086343930635838e-07, "loss": 0.596, "step": 11005 }, { "epoch": 1.99, "learning_rate": 2.059248554913295e-07, "loss": 0.6783, "step": 11006 }, { "epoch": 1.99, "learning_rate": 2.0321531791907516e-07, "loss": 0.5679, "step": 11007 }, { "epoch": 1.99, "learning_rate": 2.0050578034682082e-07, "loss": 0.2745, "step": 11008 }, { "epoch": 1.99, "learning_rate": 1.9779624277456648e-07, "loss": 0.3473, "step": 11009 }, { "epoch": 1.99, "learning_rate": 1.9508670520231215e-07, "loss": 0.4332, "step": 11010 }, { "epoch": 1.99, "learning_rate": 1.923771676300578e-07, "loss": 0.4052, "step": 11011 }, { "epoch": 1.99, "learning_rate": 1.8966763005780347e-07, "loss": 0.9499, "step": 11012 }, { "epoch": 1.99, "learning_rate": 1.8695809248554916e-07, "loss": 0.6688, "step": 11013 }, { "epoch": 1.99, "learning_rate": 1.8424855491329482e-07, "loss": 0.6516, "step": 11014 }, { "epoch": 1.99, "learning_rate": 1.8153901734104046e-07, "loss": 1.0463, "step": 11015 }, { "epoch": 1.99, "learning_rate": 1.7882947976878612e-07, "loss": 0.3201, "step": 11016 }, { "epoch": 1.99, "learning_rate": 1.7611994219653178e-07, "loss": 0.5384, "step": 11017 }, { "epoch": 1.99, "learning_rate": 1.7341040462427744e-07, "loss": 0.4169, "step": 11018 }, { "epoch": 1.99, "learning_rate": 1.7070086705202313e-07, "loss": 0.5316, "step": 11019 }, { "epoch": 1.99, "learning_rate": 1.679913294797688e-07, "loss": 0.3414, "step": 11020 }, { "epoch": 1.99, "learning_rate": 1.6528179190751445e-07, "loss": 0.4853, "step": 11021 }, { "epoch": 1.99, "learning_rate": 1.6257225433526012e-07, "loss": 0.6539, "step": 11022 }, { "epoch": 1.99, "learning_rate": 1.5986271676300578e-07, "loss": 0.5202, "step": 11023 }, { "epoch": 1.99, "learning_rate": 1.5715317919075144e-07, "loss": 0.395, "step": 11024 }, { "epoch": 1.99, "learning_rate": 1.544436416184971e-07, "loss": 0.2165, "step": 11025 }, { "epoch": 1.99, "learning_rate": 1.517341040462428e-07, "loss": 0.4038, "step": 11026 }, { "epoch": 1.99, "learning_rate": 1.4902456647398845e-07, "loss": 0.5786, "step": 11027 }, { "epoch": 1.99, "learning_rate": 1.4631502890173412e-07, "loss": 0.3236, "step": 11028 }, { "epoch": 1.99, "learning_rate": 1.4360549132947978e-07, "loss": 0.6954, "step": 11029 }, { "epoch": 1.99, "learning_rate": 1.4089595375722544e-07, "loss": 0.7456, "step": 11030 }, { "epoch": 1.99, "learning_rate": 1.381864161849711e-07, "loss": 0.501, "step": 11031 }, { "epoch": 1.99, "learning_rate": 1.3547687861271676e-07, "loss": 0.2943, "step": 11032 }, { "epoch": 1.99, "learning_rate": 1.3276734104046245e-07, "loss": 0.6122, "step": 11033 }, { "epoch": 1.99, "learning_rate": 1.300578034682081e-07, "loss": 0.339, "step": 11034 }, { "epoch": 1.99, "learning_rate": 1.2734826589595375e-07, "loss": 0.6, "step": 11035 }, { "epoch": 1.99, "learning_rate": 1.246387283236994e-07, "loss": 0.6747, "step": 11036 }, { "epoch": 1.99, "learning_rate": 1.2192919075144507e-07, "loss": 0.3839, "step": 11037 }, { "epoch": 1.99, "learning_rate": 1.1921965317919074e-07, "loss": 0.4059, "step": 11038 }, { "epoch": 1.99, "learning_rate": 1.1651011560693641e-07, "loss": 0.4342, "step": 11039 }, { "epoch": 1.99, "learning_rate": 1.1380057803468207e-07, "loss": 0.7548, "step": 11040 }, { "epoch": 1.99, "learning_rate": 1.1109104046242775e-07, "loss": 0.8011, "step": 11041 }, { "epoch": 1.99, "learning_rate": 1.0838150289017341e-07, "loss": 0.3751, "step": 11042 }, { "epoch": 1.99, "learning_rate": 1.0567196531791907e-07, "loss": 0.5552, "step": 11043 }, { "epoch": 1.99, "learning_rate": 1.0296242774566475e-07, "loss": 0.6616, "step": 11044 }, { "epoch": 2.0, "learning_rate": 1.0025289017341041e-07, "loss": 0.3306, "step": 11045 }, { "epoch": 2.0, "learning_rate": 9.754335260115607e-08, "loss": 0.9774, "step": 11046 }, { "epoch": 2.0, "learning_rate": 9.483381502890173e-08, "loss": 0.3765, "step": 11047 }, { "epoch": 2.0, "learning_rate": 9.212427745664741e-08, "loss": 0.781, "step": 11048 }, { "epoch": 2.0, "learning_rate": 8.941473988439306e-08, "loss": 0.8923, "step": 11049 }, { "epoch": 2.0, "learning_rate": 8.670520231213872e-08, "loss": 0.5282, "step": 11050 }, { "epoch": 2.0, "learning_rate": 8.39956647398844e-08, "loss": 0.4723, "step": 11051 }, { "epoch": 2.0, "learning_rate": 8.128612716763006e-08, "loss": 0.6615, "step": 11052 }, { "epoch": 2.0, "learning_rate": 7.857658959537572e-08, "loss": 0.4828, "step": 11053 }, { "epoch": 2.0, "learning_rate": 7.58670520231214e-08, "loss": 0.5061, "step": 11054 }, { "epoch": 2.0, "learning_rate": 7.315751445086706e-08, "loss": 0.6917, "step": 11055 }, { "epoch": 2.0, "learning_rate": 7.044797687861272e-08, "loss": 0.6938, "step": 11056 }, { "epoch": 2.0, "learning_rate": 6.773843930635838e-08, "loss": 0.4679, "step": 11057 }, { "epoch": 2.0, "learning_rate": 6.502890173410404e-08, "loss": 0.3924, "step": 11058 }, { "epoch": 2.0, "learning_rate": 6.23193641618497e-08, "loss": 0.3257, "step": 11059 }, { "epoch": 2.0, "learning_rate": 5.960982658959537e-08, "loss": 0.3655, "step": 11060 }, { "epoch": 2.0, "learning_rate": 5.690028901734104e-08, "loss": 0.8334, "step": 11061 }, { "epoch": 2.0, "learning_rate": 5.4190751445086706e-08, "loss": 0.2207, "step": 11062 }, { "epoch": 2.0, "learning_rate": 5.1481213872832374e-08, "loss": 0.359, "step": 11063 }, { "epoch": 2.0, "learning_rate": 4.8771676300578036e-08, "loss": 0.3212, "step": 11064 }, { "epoch": 2.0, "learning_rate": 4.6062138728323705e-08, "loss": 0.4717, "step": 11065 }, { "epoch": 2.0, "learning_rate": 4.335260115606936e-08, "loss": 0.9213, "step": 11066 }, { "epoch": 2.0, "learning_rate": 4.064306358381503e-08, "loss": 0.782, "step": 11067 }, { "epoch": 2.0, "learning_rate": 3.79335260115607e-08, "loss": 0.969, "step": 11068 }, { "epoch": 2.0, "learning_rate": 3.522398843930636e-08, "loss": 0.5686, "step": 11069 }, { "epoch": 2.0, "learning_rate": 3.251445086705202e-08, "loss": 0.6288, "step": 11070 }, { "epoch": 2.0, "learning_rate": 2.9804913294797684e-08, "loss": 0.6734, "step": 11071 }, { "epoch": 2.0, "learning_rate": 2.7095375722543353e-08, "loss": 0.3599, "step": 11072 }, { "epoch": 2.0, "step": 11072, "total_flos": 1.2338058131818906e+17, "train_loss": 0.7616665850008564, "train_runtime": 4169.2181, "train_samples_per_second": 42.487, "train_steps_per_second": 2.656 } ], "max_steps": 11072, "num_train_epochs": 2, "total_flos": 1.2338058131818906e+17, "trial_name": null, "trial_params": null }