{ "best_metric": null, "best_model_checkpoint": null, "epoch": 4.826492323321699, "eval_steps": 1000000, "global_step": 294556, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, "learning_rate": 5.000000000000001e-07, "loss": 10.1463, "step": 500 }, { "epoch": 0.02, "learning_rate": 1.0000000000000002e-06, "loss": 9.5605, "step": 1000 }, { "epoch": 0.02, "learning_rate": 1.5e-06, "loss": 9.1984, "step": 1500 }, { "epoch": 0.03, "learning_rate": 2.0000000000000003e-06, "loss": 8.7843, "step": 2000 }, { "epoch": 0.04, "learning_rate": 2.5e-06, "loss": 8.3139, "step": 2500 }, { "epoch": 0.05, "learning_rate": 3e-06, "loss": 7.8513, "step": 3000 }, { "epoch": 0.06, "learning_rate": 3.5e-06, "loss": 7.4722, "step": 3500 }, { "epoch": 0.07, "learning_rate": 4.000000000000001e-06, "loss": 7.2158, "step": 4000 }, { "epoch": 0.07, "learning_rate": 4.5e-06, "loss": 7.0488, "step": 4500 }, { "epoch": 0.08, "learning_rate": 5e-06, "loss": 6.9522, "step": 5000 }, { "epoch": 0.09, "learning_rate": 5.500000000000001e-06, "loss": 6.8768, "step": 5500 }, { "epoch": 0.1, "learning_rate": 6e-06, "loss": 6.8192, "step": 6000 }, { "epoch": 0.11, "learning_rate": 6.5000000000000004e-06, "loss": 6.7769, "step": 6500 }, { "epoch": 0.11, "learning_rate": 7e-06, "loss": 6.7388, "step": 7000 }, { "epoch": 0.12, "learning_rate": 7.500000000000001e-06, "loss": 6.7003, "step": 7500 }, { "epoch": 0.13, "learning_rate": 8.000000000000001e-06, "loss": 6.6686, "step": 8000 }, { "epoch": 0.14, "learning_rate": 8.5e-06, "loss": 6.6411, "step": 8500 }, { "epoch": 0.15, "learning_rate": 9e-06, "loss": 6.6134, "step": 9000 }, { "epoch": 0.16, "learning_rate": 9.5e-06, "loss": 6.5826, "step": 9500 }, { "epoch": 0.16, "learning_rate": 1e-05, "loss": 6.5578, "step": 10000 }, { "epoch": 0.17, "learning_rate": 9.999179372712501e-06, "loss": 6.5369, "step": 10500 }, { "epoch": 0.18, "learning_rate": 9.998358745425003e-06, "loss": 6.5062, "step": 11000 }, { "epoch": 0.19, "learning_rate": 9.997538118137506e-06, "loss": 6.4922, "step": 11500 }, { "epoch": 0.2, "learning_rate": 9.996717490850006e-06, "loss": 6.476, "step": 12000 }, { "epoch": 0.2, "learning_rate": 9.995896863562508e-06, "loss": 6.456, "step": 12500 }, { "epoch": 0.21, "learning_rate": 9.99507623627501e-06, "loss": 6.4453, "step": 13000 }, { "epoch": 0.22, "learning_rate": 9.994255608987511e-06, "loss": 6.4269, "step": 13500 }, { "epoch": 0.23, "learning_rate": 9.993434981700011e-06, "loss": 6.4121, "step": 14000 }, { "epoch": 0.24, "learning_rate": 9.992614354412514e-06, "loss": 6.4032, "step": 14500 }, { "epoch": 0.25, "learning_rate": 9.991793727125016e-06, "loss": 6.3908, "step": 15000 }, { "epoch": 0.25, "learning_rate": 9.990973099837516e-06, "loss": 6.3785, "step": 15500 }, { "epoch": 0.26, "learning_rate": 9.990152472550018e-06, "loss": 6.3714, "step": 16000 }, { "epoch": 0.27, "learning_rate": 9.98933184526252e-06, "loss": 6.3586, "step": 16500 }, { "epoch": 0.28, "learning_rate": 9.988511217975021e-06, "loss": 6.3413, "step": 17000 }, { "epoch": 0.29, "learning_rate": 9.987690590687521e-06, "loss": 6.3394, "step": 17500 }, { "epoch": 0.29, "learning_rate": 9.986869963400024e-06, "loss": 6.335, "step": 18000 }, { "epoch": 0.3, "learning_rate": 9.986049336112526e-06, "loss": 6.3176, "step": 18500 }, { "epoch": 0.31, "learning_rate": 9.985228708825026e-06, "loss": 6.3145, "step": 19000 }, { "epoch": 0.32, "learning_rate": 9.984408081537528e-06, "loss": 6.3076, "step": 19500 }, { "epoch": 0.33, "learning_rate": 9.98358745425003e-06, "loss": 6.2961, "step": 20000 }, { "epoch": 0.34, "learning_rate": 9.982766826962531e-06, "loss": 6.2932, "step": 20500 }, { "epoch": 0.34, "learning_rate": 9.981946199675032e-06, "loss": 6.2859, "step": 21000 }, { "epoch": 0.35, "learning_rate": 9.981125572387534e-06, "loss": 6.2771, "step": 21500 }, { "epoch": 0.36, "learning_rate": 9.980304945100036e-06, "loss": 6.2758, "step": 22000 }, { "epoch": 0.37, "learning_rate": 9.979484317812536e-06, "loss": 6.2702, "step": 22500 }, { "epoch": 0.38, "learning_rate": 9.978663690525039e-06, "loss": 6.26, "step": 23000 }, { "epoch": 0.39, "learning_rate": 9.97784306323754e-06, "loss": 6.2528, "step": 23500 }, { "epoch": 0.39, "learning_rate": 9.977022435950041e-06, "loss": 6.2556, "step": 24000 }, { "epoch": 0.4, "learning_rate": 9.976201808662542e-06, "loss": 6.2413, "step": 24500 }, { "epoch": 0.41, "learning_rate": 9.975381181375044e-06, "loss": 6.2464, "step": 25000 }, { "epoch": 0.42, "learning_rate": 9.974560554087546e-06, "loss": 6.2394, "step": 25500 }, { "epoch": 0.43, "learning_rate": 9.973739926800046e-06, "loss": 6.2295, "step": 26000 }, { "epoch": 0.43, "learning_rate": 9.972919299512549e-06, "loss": 6.2244, "step": 26500 }, { "epoch": 0.44, "learning_rate": 9.97209867222505e-06, "loss": 6.2233, "step": 27000 }, { "epoch": 0.45, "learning_rate": 9.971278044937551e-06, "loss": 6.2174, "step": 27500 }, { "epoch": 0.46, "learning_rate": 9.970457417650052e-06, "loss": 6.2133, "step": 28000 }, { "epoch": 0.47, "learning_rate": 9.969636790362554e-06, "loss": 6.2082, "step": 28500 }, { "epoch": 0.48, "learning_rate": 9.968816163075056e-06, "loss": 6.2042, "step": 29000 }, { "epoch": 0.48, "learning_rate": 9.967995535787557e-06, "loss": 6.2017, "step": 29500 }, { "epoch": 0.49, "learning_rate": 9.967174908500059e-06, "loss": 6.1967, "step": 30000 }, { "epoch": 0.5, "learning_rate": 9.966354281212561e-06, "loss": 6.1969, "step": 30500 }, { "epoch": 0.51, "learning_rate": 9.965533653925061e-06, "loss": 6.1936, "step": 31000 }, { "epoch": 0.52, "learning_rate": 9.964713026637562e-06, "loss": 6.1844, "step": 31500 }, { "epoch": 0.52, "learning_rate": 9.963892399350064e-06, "loss": 6.1813, "step": 32000 }, { "epoch": 0.53, "learning_rate": 9.963071772062566e-06, "loss": 6.1808, "step": 32500 }, { "epoch": 0.54, "learning_rate": 9.962251144775067e-06, "loss": 6.1866, "step": 33000 }, { "epoch": 0.55, "learning_rate": 9.961430517487569e-06, "loss": 6.1789, "step": 33500 }, { "epoch": 0.56, "learning_rate": 9.960609890200071e-06, "loss": 6.1698, "step": 34000 }, { "epoch": 0.57, "learning_rate": 9.959789262912571e-06, "loss": 6.1712, "step": 34500 }, { "epoch": 0.57, "learning_rate": 9.958968635625072e-06, "loss": 6.1635, "step": 35000 }, { "epoch": 0.58, "learning_rate": 9.958148008337574e-06, "loss": 6.1675, "step": 35500 }, { "epoch": 0.59, "learning_rate": 9.957327381050076e-06, "loss": 6.1635, "step": 36000 }, { "epoch": 0.6, "learning_rate": 9.956506753762577e-06, "loss": 6.1572, "step": 36500 }, { "epoch": 0.61, "learning_rate": 9.955686126475079e-06, "loss": 6.1541, "step": 37000 }, { "epoch": 0.61, "learning_rate": 9.95486549918758e-06, "loss": 6.1541, "step": 37500 }, { "epoch": 0.62, "learning_rate": 9.954044871900081e-06, "loss": 6.1521, "step": 38000 }, { "epoch": 0.63, "learning_rate": 9.953224244612582e-06, "loss": 6.1501, "step": 38500 }, { "epoch": 0.64, "learning_rate": 9.952403617325084e-06, "loss": 6.1449, "step": 39000 }, { "epoch": 0.65, "learning_rate": 9.951582990037586e-06, "loss": 6.1409, "step": 39500 }, { "epoch": 0.66, "learning_rate": 9.950762362750087e-06, "loss": 6.1419, "step": 40000 }, { "epoch": 0.66, "learning_rate": 9.949941735462589e-06, "loss": 6.137, "step": 40500 }, { "epoch": 0.67, "learning_rate": 9.94912110817509e-06, "loss": 6.1341, "step": 41000 }, { "epoch": 0.68, "learning_rate": 9.948300480887592e-06, "loss": 6.1323, "step": 41500 }, { "epoch": 0.69, "learning_rate": 9.947479853600092e-06, "loss": 6.1287, "step": 42000 }, { "epoch": 0.7, "learning_rate": 9.946659226312594e-06, "loss": 6.1231, "step": 42500 }, { "epoch": 0.7, "learning_rate": 9.945838599025096e-06, "loss": 6.1244, "step": 43000 }, { "epoch": 0.71, "learning_rate": 9.945017971737597e-06, "loss": 6.1184, "step": 43500 }, { "epoch": 0.72, "learning_rate": 9.944197344450099e-06, "loss": 6.1198, "step": 44000 }, { "epoch": 0.73, "learning_rate": 9.9433767171626e-06, "loss": 6.1184, "step": 44500 }, { "epoch": 0.74, "learning_rate": 9.942556089875102e-06, "loss": 6.1178, "step": 45000 }, { "epoch": 0.75, "learning_rate": 9.941735462587602e-06, "loss": 6.1117, "step": 45500 }, { "epoch": 0.75, "learning_rate": 9.940914835300104e-06, "loss": 6.1103, "step": 46000 }, { "epoch": 0.76, "learning_rate": 9.940094208012606e-06, "loss": 6.1093, "step": 46500 }, { "epoch": 0.77, "learning_rate": 9.939273580725107e-06, "loss": 6.1076, "step": 47000 }, { "epoch": 0.78, "learning_rate": 9.938452953437609e-06, "loss": 6.1009, "step": 47500 }, { "epoch": 0.79, "learning_rate": 9.93763232615011e-06, "loss": 6.1066, "step": 48000 }, { "epoch": 0.79, "learning_rate": 9.936811698862612e-06, "loss": 6.1013, "step": 48500 }, { "epoch": 0.8, "learning_rate": 9.935991071575112e-06, "loss": 6.0985, "step": 49000 }, { "epoch": 0.81, "learning_rate": 9.935170444287614e-06, "loss": 6.1018, "step": 49500 }, { "epoch": 0.82, "learning_rate": 9.934349817000117e-06, "loss": 6.1027, "step": 50000 }, { "epoch": 0.83, "learning_rate": 9.933529189712617e-06, "loss": 6.0933, "step": 50500 }, { "epoch": 0.84, "learning_rate": 9.93270856242512e-06, "loss": 6.0946, "step": 51000 }, { "epoch": 0.84, "learning_rate": 9.93188793513762e-06, "loss": 6.095, "step": 51500 }, { "epoch": 0.85, "learning_rate": 9.931067307850122e-06, "loss": 6.094, "step": 52000 }, { "epoch": 0.86, "learning_rate": 9.930246680562622e-06, "loss": 6.0827, "step": 52500 }, { "epoch": 0.87, "learning_rate": 9.929426053275124e-06, "loss": 6.0864, "step": 53000 }, { "epoch": 0.88, "learning_rate": 9.928605425987625e-06, "loss": 6.0929, "step": 53500 }, { "epoch": 0.88, "learning_rate": 9.927784798700127e-06, "loss": 6.0843, "step": 54000 }, { "epoch": 0.89, "learning_rate": 9.92696417141263e-06, "loss": 6.0839, "step": 54500 }, { "epoch": 0.9, "learning_rate": 9.92614354412513e-06, "loss": 6.0818, "step": 55000 }, { "epoch": 0.91, "learning_rate": 9.925322916837632e-06, "loss": 6.081, "step": 55500 }, { "epoch": 0.92, "learning_rate": 9.924502289550132e-06, "loss": 6.0839, "step": 56000 }, { "epoch": 0.93, "learning_rate": 9.923681662262635e-06, "loss": 6.078, "step": 56500 }, { "epoch": 0.93, "learning_rate": 9.922861034975135e-06, "loss": 6.0811, "step": 57000 }, { "epoch": 0.94, "learning_rate": 9.922040407687637e-06, "loss": 6.0751, "step": 57500 }, { "epoch": 0.95, "learning_rate": 9.92121978040014e-06, "loss": 6.0779, "step": 58000 }, { "epoch": 0.96, "learning_rate": 9.92039915311264e-06, "loss": 6.0738, "step": 58500 }, { "epoch": 0.97, "learning_rate": 9.919578525825142e-06, "loss": 6.0667, "step": 59000 }, { "epoch": 0.97, "learning_rate": 9.918757898537642e-06, "loss": 6.0712, "step": 59500 }, { "epoch": 0.98, "learning_rate": 9.917937271250145e-06, "loss": 6.0695, "step": 60000 }, { "epoch": 0.99, "learning_rate": 9.917116643962645e-06, "loss": 6.0665, "step": 60500 }, { "epoch": 1.0, "learning_rate": 9.916296016675147e-06, "loss": 6.0679, "step": 61000 }, { "epoch": 1.01, "learning_rate": 9.91547538938765e-06, "loss": 6.0599, "step": 61500 }, { "epoch": 1.02, "learning_rate": 9.91465476210015e-06, "loss": 6.0663, "step": 62000 }, { "epoch": 1.02, "learning_rate": 9.913834134812652e-06, "loss": 6.0628, "step": 62500 }, { "epoch": 1.03, "learning_rate": 9.913013507525153e-06, "loss": 6.062, "step": 63000 }, { "epoch": 1.04, "learning_rate": 9.912192880237655e-06, "loss": 6.0602, "step": 63500 }, { "epoch": 1.05, "learning_rate": 9.911372252950155e-06, "loss": 6.0551, "step": 64000 }, { "epoch": 1.06, "learning_rate": 9.910551625662657e-06, "loss": 6.0528, "step": 64500 }, { "epoch": 1.07, "learning_rate": 9.90973099837516e-06, "loss": 6.0577, "step": 65000 }, { "epoch": 1.07, "learning_rate": 9.90891037108766e-06, "loss": 6.0564, "step": 65500 }, { "epoch": 1.08, "learning_rate": 9.908089743800162e-06, "loss": 6.0555, "step": 66000 }, { "epoch": 1.09, "learning_rate": 9.907269116512663e-06, "loss": 6.052, "step": 66500 }, { "epoch": 1.1, "learning_rate": 9.906448489225165e-06, "loss": 6.0506, "step": 67000 }, { "epoch": 1.11, "learning_rate": 9.905627861937665e-06, "loss": 6.0491, "step": 67500 }, { "epoch": 1.11, "learning_rate": 9.904807234650167e-06, "loss": 6.0482, "step": 68000 }, { "epoch": 1.12, "learning_rate": 9.90398660736267e-06, "loss": 6.0486, "step": 68500 }, { "epoch": 1.13, "learning_rate": 9.90316598007517e-06, "loss": 6.0465, "step": 69000 }, { "epoch": 1.14, "learning_rate": 9.90234535278767e-06, "loss": 6.0474, "step": 69500 }, { "epoch": 1.15, "learning_rate": 9.901524725500173e-06, "loss": 6.0471, "step": 70000 }, { "epoch": 1.16, "learning_rate": 9.900704098212675e-06, "loss": 6.0442, "step": 70500 }, { "epoch": 1.16, "learning_rate": 9.899883470925175e-06, "loss": 6.0394, "step": 71000 }, { "epoch": 1.17, "learning_rate": 9.899062843637678e-06, "loss": 6.0434, "step": 71500 }, { "epoch": 1.18, "learning_rate": 9.89824221635018e-06, "loss": 6.0407, "step": 72000 }, { "epoch": 1.19, "learning_rate": 9.89742158906268e-06, "loss": 6.0364, "step": 72500 }, { "epoch": 1.2, "learning_rate": 9.89660096177518e-06, "loss": 6.0389, "step": 73000 }, { "epoch": 1.2, "learning_rate": 9.895780334487683e-06, "loss": 6.0352, "step": 73500 }, { "epoch": 1.21, "learning_rate": 9.894959707200185e-06, "loss": 6.0338, "step": 74000 }, { "epoch": 1.22, "learning_rate": 9.894139079912685e-06, "loss": 6.0337, "step": 74500 }, { "epoch": 1.23, "learning_rate": 9.893318452625188e-06, "loss": 6.0311, "step": 75000 }, { "epoch": 1.24, "learning_rate": 9.89249782533769e-06, "loss": 6.031, "step": 75500 }, { "epoch": 1.25, "learning_rate": 9.89167719805019e-06, "loss": 6.0319, "step": 76000 }, { "epoch": 1.25, "learning_rate": 9.89085657076269e-06, "loss": 6.0331, "step": 76500 }, { "epoch": 1.26, "learning_rate": 9.890035943475193e-06, "loss": 6.0316, "step": 77000 }, { "epoch": 1.27, "learning_rate": 9.889215316187695e-06, "loss": 6.0288, "step": 77500 }, { "epoch": 1.28, "learning_rate": 9.888394688900196e-06, "loss": 6.0305, "step": 78000 }, { "epoch": 1.29, "learning_rate": 9.887574061612698e-06, "loss": 6.0289, "step": 78500 }, { "epoch": 1.29, "learning_rate": 9.8867534343252e-06, "loss": 6.0323, "step": 79000 }, { "epoch": 1.3, "learning_rate": 9.8859328070377e-06, "loss": 6.0204, "step": 79500 }, { "epoch": 1.31, "learning_rate": 9.8851121797502e-06, "loss": 6.0275, "step": 80000 }, { "epoch": 1.32, "learning_rate": 9.884291552462703e-06, "loss": 6.0266, "step": 80500 }, { "epoch": 1.33, "learning_rate": 9.883470925175205e-06, "loss": 6.0232, "step": 81000 }, { "epoch": 1.34, "learning_rate": 9.882650297887706e-06, "loss": 6.0235, "step": 81500 }, { "epoch": 1.34, "learning_rate": 9.881829670600208e-06, "loss": 6.0178, "step": 82000 }, { "epoch": 1.35, "learning_rate": 9.88100904331271e-06, "loss": 6.0208, "step": 82500 }, { "epoch": 1.36, "learning_rate": 9.88018841602521e-06, "loss": 6.0178, "step": 83000 }, { "epoch": 1.37, "learning_rate": 9.879367788737711e-06, "loss": 6.0202, "step": 83500 }, { "epoch": 1.38, "learning_rate": 9.878547161450213e-06, "loss": 6.0183, "step": 84000 }, { "epoch": 1.38, "learning_rate": 9.877726534162715e-06, "loss": 6.0116, "step": 84500 }, { "epoch": 1.39, "learning_rate": 9.876905906875216e-06, "loss": 6.0232, "step": 85000 }, { "epoch": 1.4, "learning_rate": 9.876085279587718e-06, "loss": 6.0177, "step": 85500 }, { "epoch": 1.41, "learning_rate": 9.87526465230022e-06, "loss": 6.0135, "step": 86000 }, { "epoch": 1.42, "learning_rate": 9.87444402501272e-06, "loss": 6.0148, "step": 86500 }, { "epoch": 1.43, "learning_rate": 9.873623397725221e-06, "loss": 6.0114, "step": 87000 }, { "epoch": 1.43, "learning_rate": 9.872802770437723e-06, "loss": 6.0136, "step": 87500 }, { "epoch": 1.44, "learning_rate": 9.871982143150225e-06, "loss": 6.0177, "step": 88000 }, { "epoch": 1.45, "learning_rate": 9.871161515862726e-06, "loss": 6.0113, "step": 88500 }, { "epoch": 1.46, "learning_rate": 9.870340888575228e-06, "loss": 6.0112, "step": 89000 }, { "epoch": 1.47, "learning_rate": 9.86952026128773e-06, "loss": 6.0083, "step": 89500 }, { "epoch": 1.47, "learning_rate": 9.86869963400023e-06, "loss": 6.0093, "step": 90000 }, { "epoch": 1.48, "learning_rate": 9.867879006712731e-06, "loss": 6.0088, "step": 90500 }, { "epoch": 1.49, "learning_rate": 9.867058379425233e-06, "loss": 6.0033, "step": 91000 }, { "epoch": 1.5, "learning_rate": 9.866237752137735e-06, "loss": 6.0044, "step": 91500 }, { "epoch": 1.51, "learning_rate": 9.865417124850236e-06, "loss": 6.005, "step": 92000 }, { "epoch": 1.52, "learning_rate": 9.864596497562738e-06, "loss": 6.0039, "step": 92500 }, { "epoch": 1.52, "learning_rate": 9.86377587027524e-06, "loss": 5.9981, "step": 93000 }, { "epoch": 1.53, "learning_rate": 9.86295524298774e-06, "loss": 6.0003, "step": 93500 }, { "epoch": 1.54, "learning_rate": 9.862134615700241e-06, "loss": 6.0043, "step": 94000 }, { "epoch": 1.55, "learning_rate": 9.861313988412743e-06, "loss": 6.0055, "step": 94500 }, { "epoch": 1.56, "learning_rate": 9.860493361125245e-06, "loss": 6.0071, "step": 95000 }, { "epoch": 1.56, "learning_rate": 9.859672733837746e-06, "loss": 6.0002, "step": 95500 }, { "epoch": 1.57, "learning_rate": 9.858852106550248e-06, "loss": 5.9992, "step": 96000 }, { "epoch": 1.58, "learning_rate": 9.85803147926275e-06, "loss": 6.0001, "step": 96500 }, { "epoch": 1.59, "learning_rate": 9.85721085197525e-06, "loss": 5.9998, "step": 97000 }, { "epoch": 1.6, "learning_rate": 9.856390224687751e-06, "loss": 6.0004, "step": 97500 }, { "epoch": 1.61, "learning_rate": 9.855569597400253e-06, "loss": 5.9991, "step": 98000 }, { "epoch": 1.61, "learning_rate": 9.854748970112756e-06, "loss": 6.0037, "step": 98500 }, { "epoch": 1.62, "learning_rate": 9.853928342825256e-06, "loss": 5.9961, "step": 99000 }, { "epoch": 1.63, "learning_rate": 9.853107715537758e-06, "loss": 5.9926, "step": 99500 }, { "epoch": 1.64, "learning_rate": 9.85228708825026e-06, "loss": 5.9995, "step": 100000 }, { "epoch": 1.65, "learning_rate": 9.851466460962761e-06, "loss": 5.9944, "step": 100500 }, { "epoch": 1.65, "learning_rate": 9.850645833675261e-06, "loss": 5.9959, "step": 101000 }, { "epoch": 1.66, "learning_rate": 9.849825206387764e-06, "loss": 5.9946, "step": 101500 }, { "epoch": 1.67, "learning_rate": 9.849004579100266e-06, "loss": 5.9886, "step": 102000 }, { "epoch": 1.68, "learning_rate": 9.848183951812766e-06, "loss": 5.9938, "step": 102500 }, { "epoch": 1.69, "learning_rate": 9.847363324525268e-06, "loss": 5.9933, "step": 103000 }, { "epoch": 1.7, "learning_rate": 9.84654269723777e-06, "loss": 5.9843, "step": 103500 }, { "epoch": 1.7, "learning_rate": 9.845722069950271e-06, "loss": 5.9883, "step": 104000 }, { "epoch": 1.71, "learning_rate": 9.844901442662771e-06, "loss": 5.9915, "step": 104500 }, { "epoch": 1.72, "learning_rate": 9.844080815375274e-06, "loss": 5.9887, "step": 105000 }, { "epoch": 1.73, "learning_rate": 9.843260188087776e-06, "loss": 5.9883, "step": 105500 }, { "epoch": 1.74, "learning_rate": 9.842439560800276e-06, "loss": 5.989, "step": 106000 }, { "epoch": 1.75, "learning_rate": 9.841618933512778e-06, "loss": 5.9878, "step": 106500 }, { "epoch": 1.75, "learning_rate": 9.84079830622528e-06, "loss": 5.9891, "step": 107000 }, { "epoch": 1.76, "learning_rate": 9.839977678937781e-06, "loss": 5.9872, "step": 107500 }, { "epoch": 1.77, "learning_rate": 9.839157051650282e-06, "loss": 5.982, "step": 108000 }, { "epoch": 1.78, "learning_rate": 9.838336424362784e-06, "loss": 5.9811, "step": 108500 }, { "epoch": 1.79, "learning_rate": 9.837515797075286e-06, "loss": 5.977, "step": 109000 }, { "epoch": 1.79, "learning_rate": 9.836695169787786e-06, "loss": 5.973, "step": 109500 }, { "epoch": 1.8, "learning_rate": 9.835874542500288e-06, "loss": 5.966, "step": 110000 }, { "epoch": 1.81, "learning_rate": 9.83505391521279e-06, "loss": 5.9634, "step": 110500 }, { "epoch": 1.82, "learning_rate": 9.834233287925291e-06, "loss": 5.9536, "step": 111000 }, { "epoch": 1.83, "learning_rate": 9.833412660637792e-06, "loss": 5.9503, "step": 111500 }, { "epoch": 1.84, "learning_rate": 9.832592033350294e-06, "loss": 5.9416, "step": 112000 }, { "epoch": 1.84, "learning_rate": 9.831771406062796e-06, "loss": 5.9326, "step": 112500 }, { "epoch": 1.85, "learning_rate": 9.830950778775296e-06, "loss": 5.9203, "step": 113000 }, { "epoch": 1.86, "learning_rate": 9.830130151487799e-06, "loss": 5.9099, "step": 113500 }, { "epoch": 1.87, "learning_rate": 9.8293095242003e-06, "loss": 5.8985, "step": 114000 }, { "epoch": 1.88, "learning_rate": 9.828488896912801e-06, "loss": 5.8841, "step": 114500 }, { "epoch": 1.88, "learning_rate": 9.827668269625302e-06, "loss": 5.8754, "step": 115000 }, { "epoch": 1.89, "learning_rate": 9.826847642337804e-06, "loss": 5.8637, "step": 115500 }, { "epoch": 1.9, "learning_rate": 9.826027015050306e-06, "loss": 5.8584, "step": 116000 }, { "epoch": 1.91, "learning_rate": 9.825206387762806e-06, "loss": 5.8469, "step": 116500 }, { "epoch": 1.92, "learning_rate": 9.824385760475309e-06, "loss": 5.8445, "step": 117000 }, { "epoch": 1.93, "learning_rate": 9.823565133187809e-06, "loss": 5.8321, "step": 117500 }, { "epoch": 1.93, "learning_rate": 9.822744505900311e-06, "loss": 5.8325, "step": 118000 }, { "epoch": 1.94, "learning_rate": 9.821923878612812e-06, "loss": 5.8228, "step": 118500 }, { "epoch": 1.95, "learning_rate": 9.821103251325314e-06, "loss": 5.8209, "step": 119000 }, { "epoch": 1.96, "learning_rate": 9.820282624037816e-06, "loss": 5.8135, "step": 119500 }, { "epoch": 1.97, "learning_rate": 9.819461996750317e-06, "loss": 5.81, "step": 120000 }, { "epoch": 1.97, "learning_rate": 9.818641369462819e-06, "loss": 5.7997, "step": 120500 }, { "epoch": 1.98, "learning_rate": 9.81782074217532e-06, "loss": 5.7982, "step": 121000 }, { "epoch": 1.99, "learning_rate": 9.817000114887821e-06, "loss": 5.7946, "step": 121500 }, { "epoch": 2.0, "learning_rate": 9.816179487600322e-06, "loss": 5.79, "step": 122000 }, { "epoch": 2.01, "learning_rate": 9.815358860312824e-06, "loss": 5.7844, "step": 122500 }, { "epoch": 2.02, "learning_rate": 9.814538233025326e-06, "loss": 5.7789, "step": 123000 }, { "epoch": 2.02, "learning_rate": 9.813717605737827e-06, "loss": 5.7771, "step": 123500 }, { "epoch": 2.03, "learning_rate": 9.812896978450329e-06, "loss": 5.7736, "step": 124000 }, { "epoch": 2.04, "learning_rate": 9.81207635116283e-06, "loss": 5.7709, "step": 124500 }, { "epoch": 2.05, "learning_rate": 9.811255723875331e-06, "loss": 5.7633, "step": 125000 }, { "epoch": 2.06, "learning_rate": 9.810435096587832e-06, "loss": 5.7615, "step": 125500 }, { "epoch": 2.06, "learning_rate": 9.809614469300334e-06, "loss": 5.7567, "step": 126000 }, { "epoch": 2.07, "learning_rate": 9.808793842012836e-06, "loss": 5.7573, "step": 126500 }, { "epoch": 2.08, "learning_rate": 9.807973214725337e-06, "loss": 5.7454, "step": 127000 }, { "epoch": 2.09, "learning_rate": 9.807152587437839e-06, "loss": 5.753, "step": 127500 }, { "epoch": 2.1, "learning_rate": 9.80633196015034e-06, "loss": 5.744, "step": 128000 }, { "epoch": 2.11, "learning_rate": 9.805511332862842e-06, "loss": 5.7436, "step": 128500 }, { "epoch": 2.11, "learning_rate": 9.804690705575342e-06, "loss": 5.7393, "step": 129000 }, { "epoch": 2.12, "learning_rate": 9.803870078287844e-06, "loss": 5.7376, "step": 129500 }, { "epoch": 2.13, "learning_rate": 9.803049451000346e-06, "loss": 5.7321, "step": 130000 }, { "epoch": 2.14, "learning_rate": 9.802228823712847e-06, "loss": 5.7281, "step": 130500 }, { "epoch": 2.15, "learning_rate": 9.801408196425349e-06, "loss": 5.725, "step": 131000 }, { "epoch": 2.15, "learning_rate": 9.80058756913785e-06, "loss": 5.7259, "step": 131500 }, { "epoch": 2.16, "learning_rate": 9.799766941850352e-06, "loss": 5.7216, "step": 132000 }, { "epoch": 2.17, "learning_rate": 9.798946314562852e-06, "loss": 5.7204, "step": 132500 }, { "epoch": 2.18, "learning_rate": 9.798125687275354e-06, "loss": 5.7087, "step": 133000 }, { "epoch": 2.19, "learning_rate": 9.797305059987855e-06, "loss": 5.7121, "step": 133500 }, { "epoch": 2.2, "learning_rate": 9.796484432700357e-06, "loss": 5.7061, "step": 134000 }, { "epoch": 2.2, "learning_rate": 9.795663805412859e-06, "loss": 5.7011, "step": 134500 }, { "epoch": 2.21, "learning_rate": 9.79484317812536e-06, "loss": 5.7002, "step": 135000 }, { "epoch": 2.22, "learning_rate": 9.794022550837862e-06, "loss": 5.699, "step": 135500 }, { "epoch": 2.23, "learning_rate": 9.793201923550362e-06, "loss": 5.6941, "step": 136000 }, { "epoch": 2.24, "learning_rate": 9.792381296262864e-06, "loss": 5.6861, "step": 136500 }, { "epoch": 2.24, "learning_rate": 9.791560668975365e-06, "loss": 5.6828, "step": 137000 }, { "epoch": 2.25, "learning_rate": 9.790740041687867e-06, "loss": 5.6794, "step": 137500 }, { "epoch": 2.26, "learning_rate": 9.78991941440037e-06, "loss": 5.6766, "step": 138000 }, { "epoch": 2.27, "learning_rate": 9.78909878711287e-06, "loss": 5.6702, "step": 138500 }, { "epoch": 2.28, "learning_rate": 9.788278159825372e-06, "loss": 5.6747, "step": 139000 }, { "epoch": 2.29, "learning_rate": 9.787457532537872e-06, "loss": 5.6675, "step": 139500 }, { "epoch": 2.29, "learning_rate": 9.786636905250374e-06, "loss": 5.6633, "step": 140000 }, { "epoch": 2.3, "learning_rate": 9.785816277962875e-06, "loss": 5.6608, "step": 140500 }, { "epoch": 2.31, "learning_rate": 9.784995650675377e-06, "loss": 5.6595, "step": 141000 }, { "epoch": 2.32, "learning_rate": 9.78417502338788e-06, "loss": 5.6496, "step": 141500 }, { "epoch": 2.33, "learning_rate": 9.78335439610038e-06, "loss": 5.6459, "step": 142000 }, { "epoch": 2.33, "learning_rate": 9.782533768812882e-06, "loss": 5.6449, "step": 142500 }, { "epoch": 2.34, "learning_rate": 9.781713141525382e-06, "loss": 5.6449, "step": 143000 }, { "epoch": 2.35, "learning_rate": 9.780892514237885e-06, "loss": 5.6336, "step": 143500 }, { "epoch": 2.36, "learning_rate": 9.780071886950385e-06, "loss": 5.6296, "step": 144000 }, { "epoch": 2.37, "learning_rate": 9.779251259662887e-06, "loss": 5.6258, "step": 144500 }, { "epoch": 2.38, "learning_rate": 9.77843063237539e-06, "loss": 5.6271, "step": 145000 }, { "epoch": 2.38, "learning_rate": 9.77761000508789e-06, "loss": 5.6237, "step": 145500 }, { "epoch": 2.39, "learning_rate": 9.776789377800392e-06, "loss": 5.6156, "step": 146000 }, { "epoch": 2.4, "learning_rate": 9.775968750512892e-06, "loss": 5.6165, "step": 146500 }, { "epoch": 2.41, "learning_rate": 9.775148123225395e-06, "loss": 5.6103, "step": 147000 }, { "epoch": 2.42, "learning_rate": 9.774327495937895e-06, "loss": 5.6052, "step": 147500 }, { "epoch": 2.43, "learning_rate": 9.773506868650397e-06, "loss": 5.5967, "step": 148000 }, { "epoch": 2.43, "learning_rate": 9.7726862413629e-06, "loss": 5.6002, "step": 148500 }, { "epoch": 2.44, "learning_rate": 9.7718656140754e-06, "loss": 5.5893, "step": 149000 }, { "epoch": 2.45, "learning_rate": 9.7710449867879e-06, "loss": 5.5861, "step": 149500 }, { "epoch": 2.46, "learning_rate": 9.770224359500403e-06, "loss": 5.5856, "step": 150000 }, { "epoch": 2.47, "learning_rate": 9.769403732212905e-06, "loss": 5.5771, "step": 150500 }, { "epoch": 2.47, "learning_rate": 9.768583104925405e-06, "loss": 5.5788, "step": 151000 }, { "epoch": 2.48, "learning_rate": 9.767762477637907e-06, "loss": 5.5766, "step": 151500 }, { "epoch": 2.49, "learning_rate": 9.76694185035041e-06, "loss": 5.5653, "step": 152000 }, { "epoch": 2.5, "learning_rate": 9.76612122306291e-06, "loss": 5.5638, "step": 152500 }, { "epoch": 2.51, "learning_rate": 9.76530059577541e-06, "loss": 5.5577, "step": 153000 }, { "epoch": 2.52, "learning_rate": 9.764479968487913e-06, "loss": 5.5568, "step": 153500 }, { "epoch": 2.52, "learning_rate": 9.763659341200415e-06, "loss": 5.5448, "step": 154000 }, { "epoch": 2.53, "learning_rate": 9.762838713912915e-06, "loss": 5.5479, "step": 154500 }, { "epoch": 2.54, "learning_rate": 9.762018086625417e-06, "loss": 5.5445, "step": 155000 }, { "epoch": 2.55, "learning_rate": 9.76119745933792e-06, "loss": 5.5383, "step": 155500 }, { "epoch": 2.56, "learning_rate": 9.76037683205042e-06, "loss": 5.533, "step": 156000 }, { "epoch": 2.56, "learning_rate": 9.75955620476292e-06, "loss": 5.5299, "step": 156500 }, { "epoch": 2.57, "learning_rate": 9.758735577475423e-06, "loss": 5.5312, "step": 157000 }, { "epoch": 2.58, "learning_rate": 9.757914950187925e-06, "loss": 5.5251, "step": 157500 }, { "epoch": 2.59, "learning_rate": 9.757094322900425e-06, "loss": 5.5225, "step": 158000 }, { "epoch": 2.6, "learning_rate": 9.756273695612928e-06, "loss": 5.5148, "step": 158500 }, { "epoch": 2.61, "learning_rate": 9.75545306832543e-06, "loss": 5.506, "step": 159000 }, { "epoch": 2.61, "learning_rate": 9.75463244103793e-06, "loss": 5.5065, "step": 159500 }, { "epoch": 2.62, "learning_rate": 9.75381181375043e-06, "loss": 5.5011, "step": 160000 }, { "epoch": 2.63, "learning_rate": 9.752991186462933e-06, "loss": 5.4979, "step": 160500 }, { "epoch": 2.64, "learning_rate": 9.752170559175435e-06, "loss": 5.4886, "step": 161000 }, { "epoch": 2.65, "learning_rate": 9.751349931887935e-06, "loss": 5.4884, "step": 161500 }, { "epoch": 2.65, "learning_rate": 9.750529304600438e-06, "loss": 5.4852, "step": 162000 }, { "epoch": 2.66, "learning_rate": 9.74970867731294e-06, "loss": 5.4753, "step": 162500 }, { "epoch": 2.67, "learning_rate": 9.74888805002544e-06, "loss": 5.4744, "step": 163000 }, { "epoch": 2.68, "learning_rate": 9.74806742273794e-06, "loss": 5.474, "step": 163500 }, { "epoch": 2.69, "learning_rate": 9.747246795450443e-06, "loss": 5.4677, "step": 164000 }, { "epoch": 2.7, "learning_rate": 9.746426168162945e-06, "loss": 5.4615, "step": 164500 }, { "epoch": 2.7, "learning_rate": 9.745605540875446e-06, "loss": 5.4586, "step": 165000 }, { "epoch": 2.71, "learning_rate": 9.744784913587948e-06, "loss": 5.4522, "step": 165500 }, { "epoch": 2.72, "learning_rate": 9.74396428630045e-06, "loss": 5.4451, "step": 166000 }, { "epoch": 2.73, "learning_rate": 9.74314365901295e-06, "loss": 5.4447, "step": 166500 }, { "epoch": 2.74, "learning_rate": 9.74232303172545e-06, "loss": 5.4346, "step": 167000 }, { "epoch": 2.74, "learning_rate": 9.741502404437953e-06, "loss": 5.4302, "step": 167500 }, { "epoch": 2.75, "learning_rate": 9.740681777150455e-06, "loss": 5.426, "step": 168000 }, { "epoch": 2.76, "learning_rate": 9.739861149862956e-06, "loss": 5.4155, "step": 168500 }, { "epoch": 2.77, "learning_rate": 9.739040522575458e-06, "loss": 5.4115, "step": 169000 }, { "epoch": 2.78, "learning_rate": 9.73821989528796e-06, "loss": 5.4117, "step": 169500 }, { "epoch": 2.79, "learning_rate": 9.73739926800046e-06, "loss": 5.4013, "step": 170000 }, { "epoch": 2.79, "learning_rate": 9.736578640712961e-06, "loss": 5.388, "step": 170500 }, { "epoch": 2.8, "learning_rate": 9.735758013425463e-06, "loss": 5.3748, "step": 171000 }, { "epoch": 2.81, "learning_rate": 9.734937386137965e-06, "loss": 5.3563, "step": 171500 }, { "epoch": 2.82, "learning_rate": 9.734116758850466e-06, "loss": 5.335, "step": 172000 }, { "epoch": 2.83, "learning_rate": 9.733296131562968e-06, "loss": 5.3192, "step": 172500 }, { "epoch": 2.83, "learning_rate": 9.73247550427547e-06, "loss": 5.2986, "step": 173000 }, { "epoch": 2.84, "learning_rate": 9.73165487698797e-06, "loss": 5.2801, "step": 173500 }, { "epoch": 2.85, "learning_rate": 9.730834249700471e-06, "loss": 5.2638, "step": 174000 }, { "epoch": 2.86, "learning_rate": 9.730013622412973e-06, "loss": 5.2447, "step": 174500 }, { "epoch": 2.87, "learning_rate": 9.729192995125475e-06, "loss": 5.2298, "step": 175000 }, { "epoch": 2.88, "learning_rate": 9.728372367837976e-06, "loss": 5.2056, "step": 175500 }, { "epoch": 2.88, "learning_rate": 9.727551740550478e-06, "loss": 5.1865, "step": 176000 }, { "epoch": 2.89, "learning_rate": 9.72673111326298e-06, "loss": 5.1691, "step": 176500 }, { "epoch": 2.9, "learning_rate": 9.72591048597548e-06, "loss": 5.1546, "step": 177000 }, { "epoch": 2.91, "learning_rate": 9.725089858687981e-06, "loss": 5.13, "step": 177500 }, { "epoch": 2.92, "learning_rate": 9.724269231400483e-06, "loss": 5.1099, "step": 178000 }, { "epoch": 2.92, "learning_rate": 9.723448604112985e-06, "loss": 5.0996, "step": 178500 }, { "epoch": 2.93, "learning_rate": 9.722627976825486e-06, "loss": 5.0703, "step": 179000 }, { "epoch": 2.94, "learning_rate": 9.721807349537988e-06, "loss": 5.0479, "step": 179500 }, { "epoch": 2.95, "learning_rate": 9.72098672225049e-06, "loss": 5.0352, "step": 180000 }, { "epoch": 2.96, "learning_rate": 9.72016609496299e-06, "loss": 5.0138, "step": 180500 }, { "epoch": 2.97, "learning_rate": 9.719345467675491e-06, "loss": 4.9974, "step": 181000 }, { "epoch": 2.97, "learning_rate": 9.718524840387993e-06, "loss": 4.9741, "step": 181500 }, { "epoch": 2.98, "learning_rate": 9.717704213100495e-06, "loss": 4.9592, "step": 182000 }, { "epoch": 2.99, "learning_rate": 9.716883585812996e-06, "loss": 4.9418, "step": 182500 }, { "epoch": 3.0, "learning_rate": 9.716062958525498e-06, "loss": 4.9191, "step": 183000 }, { "epoch": 3.01, "learning_rate": 9.715242331238e-06, "loss": 4.9099, "step": 183500 }, { "epoch": 3.01, "learning_rate": 9.7144217039505e-06, "loss": 4.8899, "step": 184000 }, { "epoch": 3.02, "learning_rate": 9.713601076663001e-06, "loss": 4.8711, "step": 184500 }, { "epoch": 3.03, "learning_rate": 9.712780449375503e-06, "loss": 4.8609, "step": 185000 }, { "epoch": 3.04, "learning_rate": 9.711959822088006e-06, "loss": 4.8413, "step": 185500 }, { "epoch": 3.05, "learning_rate": 9.711139194800506e-06, "loss": 4.8224, "step": 186000 }, { "epoch": 3.06, "learning_rate": 9.710318567513008e-06, "loss": 4.8095, "step": 186500 }, { "epoch": 3.06, "learning_rate": 9.70949794022551e-06, "loss": 4.7918, "step": 187000 }, { "epoch": 3.07, "learning_rate": 9.70867731293801e-06, "loss": 4.7821, "step": 187500 }, { "epoch": 3.08, "learning_rate": 9.707856685650511e-06, "loss": 4.7654, "step": 188000 }, { "epoch": 3.09, "learning_rate": 9.707036058363013e-06, "loss": 4.7497, "step": 188500 }, { "epoch": 3.1, "learning_rate": 9.706215431075516e-06, "loss": 4.7403, "step": 189000 }, { "epoch": 3.11, "learning_rate": 9.705394803788016e-06, "loss": 4.7226, "step": 189500 }, { "epoch": 3.11, "learning_rate": 9.704574176500518e-06, "loss": 4.7121, "step": 190000 }, { "epoch": 3.12, "learning_rate": 9.70375354921302e-06, "loss": 4.7013, "step": 190500 }, { "epoch": 3.13, "learning_rate": 9.702932921925521e-06, "loss": 4.6821, "step": 191000 }, { "epoch": 3.14, "learning_rate": 9.702112294638021e-06, "loss": 4.6672, "step": 191500 }, { "epoch": 3.15, "learning_rate": 9.701291667350524e-06, "loss": 4.6583, "step": 192000 }, { "epoch": 3.15, "learning_rate": 9.700471040063026e-06, "loss": 4.6457, "step": 192500 }, { "epoch": 3.16, "learning_rate": 9.699650412775526e-06, "loss": 4.6416, "step": 193000 }, { "epoch": 3.17, "learning_rate": 9.698829785488028e-06, "loss": 4.6263, "step": 193500 }, { "epoch": 3.18, "learning_rate": 9.69800915820053e-06, "loss": 4.6144, "step": 194000 }, { "epoch": 3.19, "learning_rate": 9.697188530913031e-06, "loss": 4.6047, "step": 194500 }, { "epoch": 3.2, "learning_rate": 9.696367903625531e-06, "loss": 4.5889, "step": 195000 }, { "epoch": 3.2, "learning_rate": 9.695547276338034e-06, "loss": 4.5833, "step": 195500 }, { "epoch": 3.21, "learning_rate": 9.694726649050536e-06, "loss": 4.5721, "step": 196000 }, { "epoch": 3.22, "learning_rate": 9.693906021763036e-06, "loss": 4.5581, "step": 196500 }, { "epoch": 3.23, "learning_rate": 9.693085394475538e-06, "loss": 4.5382, "step": 197000 }, { "epoch": 3.24, "learning_rate": 9.69226476718804e-06, "loss": 4.5359, "step": 197500 }, { "epoch": 3.24, "learning_rate": 9.691444139900541e-06, "loss": 4.5247, "step": 198000 }, { "epoch": 3.25, "learning_rate": 9.690623512613042e-06, "loss": 4.5166, "step": 198500 }, { "epoch": 3.26, "learning_rate": 9.689802885325544e-06, "loss": 4.5061, "step": 199000 }, { "epoch": 3.27, "learning_rate": 9.688982258038046e-06, "loss": 4.4909, "step": 199500 }, { "epoch": 3.28, "learning_rate": 9.688161630750546e-06, "loss": 4.4781, "step": 200000 }, { "epoch": 3.29, "learning_rate": 9.687341003463049e-06, "loss": 4.4705, "step": 200500 }, { "epoch": 3.29, "learning_rate": 9.686520376175549e-06, "loss": 4.464, "step": 201000 }, { "epoch": 3.3, "learning_rate": 9.685699748888051e-06, "loss": 4.4474, "step": 201500 }, { "epoch": 3.31, "learning_rate": 9.684879121600552e-06, "loss": 4.4406, "step": 202000 }, { "epoch": 3.32, "learning_rate": 9.684058494313054e-06, "loss": 4.4335, "step": 202500 }, { "epoch": 3.33, "learning_rate": 9.683237867025556e-06, "loss": 4.4179, "step": 203000 }, { "epoch": 3.33, "learning_rate": 9.682417239738056e-06, "loss": 4.4131, "step": 203500 }, { "epoch": 3.34, "learning_rate": 9.681596612450559e-06, "loss": 4.3885, "step": 204000 }, { "epoch": 3.35, "learning_rate": 9.680775985163059e-06, "loss": 4.3736, "step": 204500 }, { "epoch": 3.36, "learning_rate": 9.679955357875561e-06, "loss": 4.3488, "step": 205000 }, { "epoch": 3.37, "learning_rate": 9.679134730588062e-06, "loss": 4.3171, "step": 205500 }, { "epoch": 3.38, "learning_rate": 9.678314103300564e-06, "loss": 4.2963, "step": 206000 }, { "epoch": 3.38, "learning_rate": 9.677493476013066e-06, "loss": 4.2718, "step": 206500 }, { "epoch": 3.39, "learning_rate": 9.676672848725567e-06, "loss": 4.2613, "step": 207000 }, { "epoch": 3.4, "learning_rate": 9.675852221438069e-06, "loss": 4.245, "step": 207500 }, { "epoch": 3.41, "learning_rate": 9.67503159415057e-06, "loss": 4.2306, "step": 208000 }, { "epoch": 3.42, "learning_rate": 9.674210966863071e-06, "loss": 4.2092, "step": 208500 }, { "epoch": 3.42, "learning_rate": 9.673390339575572e-06, "loss": 4.2013, "step": 209000 }, { "epoch": 3.43, "learning_rate": 9.672569712288074e-06, "loss": 4.1807, "step": 209500 }, { "epoch": 3.44, "learning_rate": 9.671749085000576e-06, "loss": 4.1753, "step": 210000 }, { "epoch": 3.45, "learning_rate": 9.670928457713077e-06, "loss": 4.1627, "step": 210500 }, { "epoch": 3.46, "learning_rate": 9.670107830425579e-06, "loss": 4.1437, "step": 211000 }, { "epoch": 3.47, "learning_rate": 9.66928720313808e-06, "loss": 4.129, "step": 211500 }, { "epoch": 3.47, "learning_rate": 9.668466575850581e-06, "loss": 4.1218, "step": 212000 }, { "epoch": 3.48, "learning_rate": 9.667645948563082e-06, "loss": 4.1112, "step": 212500 }, { "epoch": 3.49, "learning_rate": 9.666825321275584e-06, "loss": 4.1003, "step": 213000 }, { "epoch": 3.5, "learning_rate": 9.666004693988086e-06, "loss": 4.0871, "step": 213500 }, { "epoch": 3.51, "learning_rate": 9.665184066700587e-06, "loss": 4.077, "step": 214000 }, { "epoch": 3.51, "learning_rate": 9.664363439413089e-06, "loss": 4.0663, "step": 214500 }, { "epoch": 3.52, "learning_rate": 9.66354281212559e-06, "loss": 4.0644, "step": 215000 }, { "epoch": 3.53, "learning_rate": 9.662722184838092e-06, "loss": 4.0471, "step": 215500 }, { "epoch": 3.54, "learning_rate": 9.661901557550592e-06, "loss": 4.0354, "step": 216000 }, { "epoch": 3.55, "learning_rate": 9.661080930263094e-06, "loss": 4.0289, "step": 216500 }, { "epoch": 3.56, "learning_rate": 9.660260302975595e-06, "loss": 4.0182, "step": 217000 }, { "epoch": 3.56, "learning_rate": 9.659439675688097e-06, "loss": 4.0152, "step": 217500 }, { "epoch": 3.57, "learning_rate": 9.658619048400599e-06, "loss": 3.9946, "step": 218000 }, { "epoch": 3.58, "learning_rate": 9.6577984211131e-06, "loss": 3.9904, "step": 218500 }, { "epoch": 3.59, "learning_rate": 9.656977793825602e-06, "loss": 3.984, "step": 219000 }, { "epoch": 3.6, "learning_rate": 9.656157166538102e-06, "loss": 3.9729, "step": 219500 }, { "epoch": 3.6, "learning_rate": 9.655336539250604e-06, "loss": 3.9676, "step": 220000 }, { "epoch": 3.61, "learning_rate": 9.654515911963105e-06, "loss": 3.9549, "step": 220500 }, { "epoch": 3.62, "learning_rate": 9.653695284675607e-06, "loss": 3.9416, "step": 221000 }, { "epoch": 3.63, "learning_rate": 9.652874657388109e-06, "loss": 3.944, "step": 221500 }, { "epoch": 3.64, "learning_rate": 9.65205403010061e-06, "loss": 3.9331, "step": 222000 }, { "epoch": 3.65, "learning_rate": 9.651233402813112e-06, "loss": 3.9273, "step": 222500 }, { "epoch": 3.65, "learning_rate": 9.650412775525612e-06, "loss": 3.9158, "step": 223000 }, { "epoch": 3.66, "learning_rate": 9.649592148238114e-06, "loss": 3.9059, "step": 223500 }, { "epoch": 3.67, "learning_rate": 9.648771520950615e-06, "loss": 3.8975, "step": 224000 }, { "epoch": 3.68, "learning_rate": 9.647950893663117e-06, "loss": 3.8899, "step": 224500 }, { "epoch": 3.69, "learning_rate": 9.647130266375619e-06, "loss": 3.8827, "step": 225000 }, { "epoch": 3.69, "learning_rate": 9.64630963908812e-06, "loss": 3.8749, "step": 225500 }, { "epoch": 3.7, "learning_rate": 9.645489011800622e-06, "loss": 3.8719, "step": 226000 }, { "epoch": 3.71, "learning_rate": 9.644668384513122e-06, "loss": 3.8606, "step": 226500 }, { "epoch": 3.72, "learning_rate": 9.643847757225624e-06, "loss": 3.8536, "step": 227000 }, { "epoch": 3.73, "learning_rate": 9.643027129938125e-06, "loss": 3.8505, "step": 227500 }, { "epoch": 3.74, "learning_rate": 9.642206502650627e-06, "loss": 3.8405, "step": 228000 }, { "epoch": 3.74, "learning_rate": 9.64138587536313e-06, "loss": 3.8298, "step": 228500 }, { "epoch": 3.75, "learning_rate": 9.64056524807563e-06, "loss": 3.8289, "step": 229000 }, { "epoch": 3.76, "learning_rate": 9.639744620788132e-06, "loss": 3.8206, "step": 229500 }, { "epoch": 3.77, "learning_rate": 9.638923993500632e-06, "loss": 3.8085, "step": 230000 }, { "epoch": 3.78, "learning_rate": 9.638103366213134e-06, "loss": 3.8026, "step": 230500 }, { "epoch": 3.79, "learning_rate": 9.637282738925635e-06, "loss": 3.7986, "step": 231000 }, { "epoch": 3.79, "learning_rate": 9.636462111638137e-06, "loss": 3.7951, "step": 231500 }, { "epoch": 3.8, "learning_rate": 9.63564148435064e-06, "loss": 3.7823, "step": 232000 }, { "epoch": 3.81, "learning_rate": 9.63482085706314e-06, "loss": 3.7798, "step": 232500 }, { "epoch": 3.82, "learning_rate": 9.63400022977564e-06, "loss": 3.7746, "step": 233000 }, { "epoch": 3.83, "learning_rate": 9.633179602488142e-06, "loss": 3.7661, "step": 233500 }, { "epoch": 3.83, "learning_rate": 9.632358975200645e-06, "loss": 3.7573, "step": 234000 }, { "epoch": 3.84, "learning_rate": 9.631538347913145e-06, "loss": 3.7505, "step": 234500 }, { "epoch": 3.85, "learning_rate": 9.630717720625647e-06, "loss": 3.7477, "step": 235000 }, { "epoch": 3.86, "learning_rate": 9.62989709333815e-06, "loss": 3.7464, "step": 235500 }, { "epoch": 3.87, "learning_rate": 9.62907646605065e-06, "loss": 3.7383, "step": 236000 }, { "epoch": 3.88, "learning_rate": 9.62825583876315e-06, "loss": 3.7322, "step": 236500 }, { "epoch": 3.88, "learning_rate": 9.627435211475652e-06, "loss": 3.7271, "step": 237000 }, { "epoch": 3.89, "learning_rate": 9.626614584188155e-06, "loss": 3.7216, "step": 237500 }, { "epoch": 3.9, "learning_rate": 9.625793956900655e-06, "loss": 3.7089, "step": 238000 }, { "epoch": 3.91, "learning_rate": 9.624973329613157e-06, "loss": 3.7098, "step": 238500 }, { "epoch": 3.92, "learning_rate": 9.62415270232566e-06, "loss": 3.7013, "step": 239000 }, { "epoch": 3.92, "learning_rate": 9.62333207503816e-06, "loss": 3.6959, "step": 239500 }, { "epoch": 3.93, "learning_rate": 9.62251144775066e-06, "loss": 3.6988, "step": 240000 }, { "epoch": 3.94, "learning_rate": 9.621690820463163e-06, "loss": 3.6832, "step": 240500 }, { "epoch": 3.95, "learning_rate": 9.620870193175665e-06, "loss": 3.6852, "step": 241000 }, { "epoch": 3.96, "learning_rate": 9.620049565888165e-06, "loss": 3.6795, "step": 241500 }, { "epoch": 3.97, "learning_rate": 9.619228938600667e-06, "loss": 3.6718, "step": 242000 }, { "epoch": 3.97, "learning_rate": 9.61840831131317e-06, "loss": 3.6708, "step": 242500 }, { "epoch": 3.98, "learning_rate": 9.61758768402567e-06, "loss": 3.6622, "step": 243000 }, { "epoch": 3.99, "learning_rate": 9.61676705673817e-06, "loss": 3.6609, "step": 243500 }, { "epoch": 4.0, "learning_rate": 9.615946429450673e-06, "loss": 3.6505, "step": 244000 }, { "epoch": 4.01, "learning_rate": 9.615125802163175e-06, "loss": 3.6503, "step": 244500 }, { "epoch": 4.01, "learning_rate": 9.614305174875675e-06, "loss": 3.6438, "step": 245000 }, { "epoch": 4.02, "learning_rate": 9.613484547588177e-06, "loss": 3.6369, "step": 245500 }, { "epoch": 4.03, "learning_rate": 9.61266392030068e-06, "loss": 3.6375, "step": 246000 }, { "epoch": 4.04, "learning_rate": 9.61184329301318e-06, "loss": 3.6329, "step": 246500 }, { "epoch": 4.05, "learning_rate": 9.61102266572568e-06, "loss": 3.6269, "step": 247000 }, { "epoch": 4.06, "learning_rate": 9.610202038438183e-06, "loss": 3.6185, "step": 247500 }, { "epoch": 4.06, "learning_rate": 9.609381411150685e-06, "loss": 3.6147, "step": 248000 }, { "epoch": 4.07, "learning_rate": 9.608560783863185e-06, "loss": 3.6167, "step": 248500 }, { "epoch": 4.08, "learning_rate": 9.607740156575688e-06, "loss": 3.6059, "step": 249000 }, { "epoch": 4.09, "learning_rate": 9.60691952928819e-06, "loss": 3.6045, "step": 249500 }, { "epoch": 4.1, "learning_rate": 9.60609890200069e-06, "loss": 3.6031, "step": 250000 }, { "epoch": 4.1, "learning_rate": 9.60527827471319e-06, "loss": 3.597, "step": 250500 }, { "epoch": 4.11, "learning_rate": 9.604457647425693e-06, "loss": 3.5894, "step": 251000 }, { "epoch": 4.12, "learning_rate": 9.603637020138195e-06, "loss": 3.5852, "step": 251500 }, { "epoch": 4.13, "learning_rate": 9.602816392850695e-06, "loss": 3.5787, "step": 252000 }, { "epoch": 4.14, "learning_rate": 9.601995765563198e-06, "loss": 3.5782, "step": 252500 }, { "epoch": 4.15, "learning_rate": 9.6011751382757e-06, "loss": 3.5725, "step": 253000 }, { "epoch": 4.15, "learning_rate": 9.6003545109882e-06, "loss": 3.5692, "step": 253500 }, { "epoch": 4.16, "learning_rate": 9.5995338837007e-06, "loss": 3.5663, "step": 254000 }, { "epoch": 4.17, "learning_rate": 9.598713256413203e-06, "loss": 3.5598, "step": 254500 }, { "epoch": 4.18, "learning_rate": 9.597892629125705e-06, "loss": 3.558, "step": 255000 }, { "epoch": 4.19, "learning_rate": 9.597072001838206e-06, "loss": 3.5507, "step": 255500 }, { "epoch": 4.19, "learning_rate": 9.596251374550708e-06, "loss": 3.5495, "step": 256000 }, { "epoch": 4.2, "learning_rate": 9.59543074726321e-06, "loss": 3.5488, "step": 256500 }, { "epoch": 4.21, "learning_rate": 9.59461011997571e-06, "loss": 3.5419, "step": 257000 }, { "epoch": 4.22, "learning_rate": 9.59378949268821e-06, "loss": 3.5431, "step": 257500 }, { "epoch": 4.23, "learning_rate": 9.592968865400713e-06, "loss": 3.5382, "step": 258000 }, { "epoch": 4.24, "learning_rate": 9.592148238113215e-06, "loss": 3.5328, "step": 258500 }, { "epoch": 4.24, "learning_rate": 9.591327610825716e-06, "loss": 3.5292, "step": 259000 }, { "epoch": 4.25, "learning_rate": 9.590506983538218e-06, "loss": 3.5264, "step": 259500 }, { "epoch": 4.26, "learning_rate": 9.58968635625072e-06, "loss": 3.5243, "step": 260000 }, { "epoch": 4.27, "learning_rate": 9.58886572896322e-06, "loss": 3.519, "step": 260500 }, { "epoch": 4.28, "learning_rate": 9.588045101675721e-06, "loss": 3.5134, "step": 261000 }, { "epoch": 4.28, "learning_rate": 9.587224474388223e-06, "loss": 3.5141, "step": 261500 }, { "epoch": 4.29, "learning_rate": 9.586403847100725e-06, "loss": 3.5069, "step": 262000 }, { "epoch": 4.3, "learning_rate": 9.585583219813226e-06, "loss": 3.5053, "step": 262500 }, { "epoch": 4.31, "learning_rate": 9.584762592525728e-06, "loss": 3.5055, "step": 263000 }, { "epoch": 4.32, "learning_rate": 9.58394196523823e-06, "loss": 3.4985, "step": 263500 }, { "epoch": 4.33, "learning_rate": 9.58312133795073e-06, "loss": 3.4988, "step": 264000 }, { "epoch": 4.33, "learning_rate": 9.582300710663231e-06, "loss": 3.4906, "step": 264500 }, { "epoch": 4.34, "learning_rate": 9.581480083375733e-06, "loss": 3.487, "step": 265000 }, { "epoch": 4.35, "learning_rate": 9.580659456088235e-06, "loss": 3.4828, "step": 265500 }, { "epoch": 4.36, "learning_rate": 9.579838828800736e-06, "loss": 3.4862, "step": 266000 }, { "epoch": 4.37, "learning_rate": 9.579018201513238e-06, "loss": 3.4818, "step": 266500 }, { "epoch": 4.37, "learning_rate": 9.57819757422574e-06, "loss": 3.4765, "step": 267000 }, { "epoch": 4.38, "learning_rate": 9.57737694693824e-06, "loss": 3.4731, "step": 267500 }, { "epoch": 4.39, "learning_rate": 9.576556319650741e-06, "loss": 3.4684, "step": 268000 }, { "epoch": 4.4, "learning_rate": 9.575735692363243e-06, "loss": 3.4692, "step": 268500 }, { "epoch": 4.41, "learning_rate": 9.574915065075745e-06, "loss": 3.4632, "step": 269000 }, { "epoch": 4.42, "learning_rate": 9.574094437788246e-06, "loss": 3.4659, "step": 269500 }, { "epoch": 4.42, "learning_rate": 9.573273810500748e-06, "loss": 3.4629, "step": 270000 }, { "epoch": 4.43, "learning_rate": 9.57245318321325e-06, "loss": 3.4531, "step": 270500 }, { "epoch": 4.44, "learning_rate": 9.57163255592575e-06, "loss": 3.453, "step": 271000 }, { "epoch": 4.45, "learning_rate": 9.570811928638251e-06, "loss": 3.4515, "step": 271500 }, { "epoch": 4.46, "learning_rate": 9.569991301350753e-06, "loss": 3.4439, "step": 272000 }, { "epoch": 4.47, "learning_rate": 9.569170674063256e-06, "loss": 3.4456, "step": 272500 }, { "epoch": 4.47, "learning_rate": 9.568350046775756e-06, "loss": 3.4456, "step": 273000 }, { "epoch": 4.48, "learning_rate": 9.567529419488258e-06, "loss": 3.441, "step": 273500 }, { "epoch": 4.49, "learning_rate": 9.56670879220076e-06, "loss": 3.4312, "step": 274000 }, { "epoch": 4.5, "learning_rate": 9.56588816491326e-06, "loss": 3.4398, "step": 274500 }, { "epoch": 4.51, "learning_rate": 9.565067537625761e-06, "loss": 3.4365, "step": 275000 }, { "epoch": 4.51, "learning_rate": 9.564246910338263e-06, "loss": 3.4216, "step": 275500 }, { "epoch": 4.52, "learning_rate": 9.563426283050766e-06, "loss": 3.4264, "step": 276000 }, { "epoch": 4.53, "learning_rate": 9.562605655763266e-06, "loss": 3.4211, "step": 276500 }, { "epoch": 4.54, "learning_rate": 9.561785028475768e-06, "loss": 3.4192, "step": 277000 }, { "epoch": 4.55, "learning_rate": 9.56096440118827e-06, "loss": 3.4161, "step": 277500 }, { "epoch": 4.56, "learning_rate": 9.560143773900771e-06, "loss": 3.4142, "step": 278000 }, { "epoch": 4.56, "learning_rate": 9.559323146613271e-06, "loss": 3.4068, "step": 278500 }, { "epoch": 4.57, "learning_rate": 9.558502519325774e-06, "loss": 3.4101, "step": 279000 }, { "epoch": 4.58, "learning_rate": 9.557681892038276e-06, "loss": 3.4049, "step": 279500 }, { "epoch": 4.59, "learning_rate": 9.556861264750776e-06, "loss": 3.4054, "step": 280000 }, { "epoch": 4.6, "learning_rate": 9.556040637463278e-06, "loss": 3.4074, "step": 280500 }, { "epoch": 4.6, "learning_rate": 9.555220010175779e-06, "loss": 3.4023, "step": 281000 }, { "epoch": 4.61, "learning_rate": 9.554399382888281e-06, "loss": 3.3951, "step": 281500 }, { "epoch": 4.62, "learning_rate": 9.553578755600781e-06, "loss": 3.3857, "step": 282000 }, { "epoch": 4.63, "learning_rate": 9.552758128313284e-06, "loss": 3.387, "step": 282500 }, { "epoch": 4.64, "learning_rate": 9.551937501025786e-06, "loss": 3.388, "step": 283000 }, { "epoch": 4.65, "learning_rate": 9.551116873738286e-06, "loss": 3.3917, "step": 283500 }, { "epoch": 4.65, "learning_rate": 9.550296246450788e-06, "loss": 3.3829, "step": 284000 }, { "epoch": 4.66, "learning_rate": 9.549475619163289e-06, "loss": 3.3815, "step": 284500 }, { "epoch": 4.67, "learning_rate": 9.548654991875791e-06, "loss": 3.38, "step": 285000 }, { "epoch": 4.68, "learning_rate": 9.547834364588292e-06, "loss": 3.3668, "step": 285500 }, { "epoch": 4.69, "learning_rate": 9.547013737300794e-06, "loss": 3.3713, "step": 286000 }, { "epoch": 4.69, "learning_rate": 9.546193110013296e-06, "loss": 3.3662, "step": 286500 }, { "epoch": 4.7, "learning_rate": 9.545372482725796e-06, "loss": 3.3722, "step": 287000 }, { "epoch": 4.71, "learning_rate": 9.544551855438298e-06, "loss": 3.3696, "step": 287500 }, { "epoch": 4.72, "learning_rate": 9.543731228150799e-06, "loss": 3.3672, "step": 288000 }, { "epoch": 4.73, "learning_rate": 9.542910600863301e-06, "loss": 3.3606, "step": 288500 }, { "epoch": 4.74, "learning_rate": 9.542089973575802e-06, "loss": 3.3582, "step": 289000 }, { "epoch": 4.74, "learning_rate": 9.541269346288304e-06, "loss": 3.3576, "step": 289500 }, { "epoch": 4.75, "learning_rate": 9.540448719000806e-06, "loss": 3.3494, "step": 290000 }, { "epoch": 4.76, "learning_rate": 9.539628091713306e-06, "loss": 3.3518, "step": 290500 }, { "epoch": 4.77, "learning_rate": 9.538807464425809e-06, "loss": 3.3534, "step": 291000 }, { "epoch": 4.78, "learning_rate": 9.537986837138309e-06, "loss": 3.3495, "step": 291500 }, { "epoch": 4.78, "learning_rate": 9.537166209850811e-06, "loss": 3.3427, "step": 292000 }, { "epoch": 4.79, "learning_rate": 9.536345582563312e-06, "loss": 3.3428, "step": 292500 }, { "epoch": 4.8, "learning_rate": 9.535524955275814e-06, "loss": 3.3422, "step": 293000 }, { "epoch": 4.81, "learning_rate": 9.534704327988316e-06, "loss": 3.3437, "step": 293500 }, { "epoch": 4.82, "learning_rate": 9.533883700700816e-06, "loss": 3.3365, "step": 294000 }, { "epoch": 4.83, "learning_rate": 9.533063073413319e-06, "loss": 3.3319, "step": 294500 }, { "epoch": 4.83, "step": 294556, "total_flos": 1.8769758992036004e+18, "train_loss": 5.167583625387428, "train_runtime": 197999.0273, "train_samples_per_second": 2958.983, "train_steps_per_second": 30.823 } ], "logging_steps": 500, "max_steps": 6102900, "num_train_epochs": 100, "save_steps": 1000000, "total_flos": 1.8769758992036004e+18, "trial_name": null, "trial_params": null }