{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.3784409682775496, "eval_steps": 1000000, "global_step": 309276, "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": 10.0966, "step": 500 }, { "epoch": 0.01, "learning_rate": 1.0000000000000002e-06, "loss": 9.5491, "step": 1000 }, { "epoch": 0.02, "learning_rate": 1.5e-06, "loss": 9.2342, "step": 1500 }, { "epoch": 0.02, "learning_rate": 2.0000000000000003e-06, "loss": 8.8573, "step": 2000 }, { "epoch": 0.03, "learning_rate": 2.5e-06, "loss": 8.4075, "step": 2500 }, { "epoch": 0.03, "learning_rate": 3e-06, "loss": 7.9381, "step": 3000 }, { "epoch": 0.04, "learning_rate": 3.5e-06, "loss": 7.5441, "step": 3500 }, { "epoch": 0.04, "learning_rate": 4.000000000000001e-06, "loss": 7.2621, "step": 4000 }, { "epoch": 0.05, "learning_rate": 4.5e-06, "loss": 7.0993, "step": 4500 }, { "epoch": 0.05, "learning_rate": 5e-06, "loss": 6.997, "step": 5000 }, { "epoch": 0.06, "learning_rate": 5.500000000000001e-06, "loss": 6.9298, "step": 5500 }, { "epoch": 0.07, "learning_rate": 6e-06, "loss": 6.871, "step": 6000 }, { "epoch": 0.07, "learning_rate": 6.5000000000000004e-06, "loss": 6.8274, "step": 6500 }, { "epoch": 0.08, "learning_rate": 7e-06, "loss": 6.7871, "step": 7000 }, { "epoch": 0.08, "learning_rate": 7.500000000000001e-06, "loss": 6.7561, "step": 7500 }, { "epoch": 0.09, "learning_rate": 8.000000000000001e-06, "loss": 6.7246, "step": 8000 }, { "epoch": 0.09, "learning_rate": 8.5e-06, "loss": 6.6881, "step": 8500 }, { "epoch": 0.1, "learning_rate": 9e-06, "loss": 6.6725, "step": 9000 }, { "epoch": 0.1, "learning_rate": 9.5e-06, "loss": 6.6444, "step": 9500 }, { "epoch": 0.11, "learning_rate": 1e-05, "loss": 6.6208, "step": 10000 }, { "epoch": 0.11, "learning_rate": 9.999453217269587e-06, "loss": 6.6056, "step": 10500 }, { "epoch": 0.12, "learning_rate": 9.998906434539172e-06, "loss": 6.5775, "step": 11000 }, { "epoch": 0.13, "learning_rate": 9.998359651808758e-06, "loss": 6.5631, "step": 11500 }, { "epoch": 0.13, "learning_rate": 9.997812869078344e-06, "loss": 6.5452, "step": 12000 }, { "epoch": 0.14, "learning_rate": 9.99726608634793e-06, "loss": 6.5293, "step": 12500 }, { "epoch": 0.14, "learning_rate": 9.996719303617516e-06, "loss": 6.5102, "step": 13000 }, { "epoch": 0.15, "learning_rate": 9.996172520887101e-06, "loss": 6.5003, "step": 13500 }, { "epoch": 0.15, "learning_rate": 9.995625738156687e-06, "loss": 6.4782, "step": 14000 }, { "epoch": 0.16, "learning_rate": 9.995078955426273e-06, "loss": 6.4742, "step": 14500 }, { "epoch": 0.16, "learning_rate": 9.994532172695859e-06, "loss": 6.4532, "step": 15000 }, { "epoch": 0.17, "learning_rate": 9.993985389965445e-06, "loss": 6.4421, "step": 15500 }, { "epoch": 0.17, "learning_rate": 9.99343860723503e-06, "loss": 6.4348, "step": 16000 }, { "epoch": 0.18, "learning_rate": 9.992891824504616e-06, "loss": 6.4234, "step": 16500 }, { "epoch": 0.19, "learning_rate": 9.992345041774202e-06, "loss": 6.4136, "step": 17000 }, { "epoch": 0.19, "learning_rate": 9.991798259043786e-06, "loss": 6.4036, "step": 17500 }, { "epoch": 0.2, "learning_rate": 9.991251476313374e-06, "loss": 6.3948, "step": 18000 }, { "epoch": 0.2, "learning_rate": 9.99070469358296e-06, "loss": 6.3782, "step": 18500 }, { "epoch": 0.21, "learning_rate": 9.990157910852545e-06, "loss": 6.3758, "step": 19000 }, { "epoch": 0.21, "learning_rate": 9.98961112812213e-06, "loss": 6.376, "step": 19500 }, { "epoch": 0.22, "learning_rate": 9.989064345391715e-06, "loss": 6.3608, "step": 20000 }, { "epoch": 0.22, "learning_rate": 9.988517562661302e-06, "loss": 6.3474, "step": 20500 }, { "epoch": 0.23, "learning_rate": 9.987970779930888e-06, "loss": 6.3414, "step": 21000 }, { "epoch": 0.23, "learning_rate": 9.987423997200472e-06, "loss": 6.3408, "step": 21500 }, { "epoch": 0.24, "learning_rate": 9.986877214470058e-06, "loss": 6.3331, "step": 22000 }, { "epoch": 0.25, "learning_rate": 9.986330431739644e-06, "loss": 6.3285, "step": 22500 }, { "epoch": 0.25, "learning_rate": 9.985783649009231e-06, "loss": 6.317, "step": 23000 }, { "epoch": 0.26, "learning_rate": 9.985236866278816e-06, "loss": 6.3086, "step": 23500 }, { "epoch": 0.26, "learning_rate": 9.984690083548401e-06, "loss": 6.3102, "step": 24000 }, { "epoch": 0.27, "learning_rate": 9.984143300817987e-06, "loss": 6.3038, "step": 24500 }, { "epoch": 0.27, "learning_rate": 9.983596518087575e-06, "loss": 6.2911, "step": 25000 }, { "epoch": 0.28, "learning_rate": 9.98304973535716e-06, "loss": 6.2915, "step": 25500 }, { "epoch": 0.28, "learning_rate": 9.982502952626745e-06, "loss": 6.2838, "step": 26000 }, { "epoch": 0.29, "learning_rate": 9.98195616989633e-06, "loss": 6.2864, "step": 26500 }, { "epoch": 0.29, "learning_rate": 9.981409387165916e-06, "loss": 6.2742, "step": 27000 }, { "epoch": 0.3, "learning_rate": 9.980862604435504e-06, "loss": 6.2642, "step": 27500 }, { "epoch": 0.31, "learning_rate": 9.980315821705088e-06, "loss": 6.2677, "step": 28000 }, { "epoch": 0.31, "learning_rate": 9.979769038974673e-06, "loss": 6.2578, "step": 28500 }, { "epoch": 0.32, "learning_rate": 9.97922225624426e-06, "loss": 6.2604, "step": 29000 }, { "epoch": 0.32, "learning_rate": 9.978675473513845e-06, "loss": 6.2526, "step": 29500 }, { "epoch": 0.33, "learning_rate": 9.97812869078343e-06, "loss": 6.2459, "step": 30000 }, { "epoch": 0.33, "learning_rate": 9.977581908053017e-06, "loss": 6.2466, "step": 30500 }, { "epoch": 0.34, "learning_rate": 9.977035125322602e-06, "loss": 6.2467, "step": 31000 }, { "epoch": 0.34, "learning_rate": 9.976488342592188e-06, "loss": 6.237, "step": 31500 }, { "epoch": 0.35, "learning_rate": 9.975941559861774e-06, "loss": 6.2384, "step": 32000 }, { "epoch": 0.36, "learning_rate": 9.97539477713136e-06, "loss": 6.2325, "step": 32500 }, { "epoch": 0.36, "learning_rate": 9.974847994400946e-06, "loss": 6.2279, "step": 33000 }, { "epoch": 0.37, "learning_rate": 9.974301211670531e-06, "loss": 6.2231, "step": 33500 }, { "epoch": 0.37, "learning_rate": 9.973754428940117e-06, "loss": 6.219, "step": 34000 }, { "epoch": 0.38, "learning_rate": 9.973207646209703e-06, "loss": 6.2156, "step": 34500 }, { "epoch": 0.38, "learning_rate": 9.972660863479289e-06, "loss": 6.2117, "step": 35000 }, { "epoch": 0.39, "learning_rate": 9.972114080748875e-06, "loss": 6.2128, "step": 35500 }, { "epoch": 0.39, "learning_rate": 9.97156729801846e-06, "loss": 6.2112, "step": 36000 }, { "epoch": 0.4, "learning_rate": 9.971020515288046e-06, "loss": 6.2014, "step": 36500 }, { "epoch": 0.4, "learning_rate": 9.970473732557632e-06, "loss": 6.205, "step": 37000 }, { "epoch": 0.41, "learning_rate": 9.969926949827218e-06, "loss": 6.2012, "step": 37500 }, { "epoch": 0.42, "learning_rate": 9.969380167096804e-06, "loss": 6.1989, "step": 38000 }, { "epoch": 0.42, "learning_rate": 9.96883338436639e-06, "loss": 6.1972, "step": 38500 }, { "epoch": 0.43, "learning_rate": 9.968286601635975e-06, "loss": 6.1839, "step": 39000 }, { "epoch": 0.43, "learning_rate": 9.967739818905561e-06, "loss": 6.1838, "step": 39500 }, { "epoch": 0.44, "learning_rate": 9.967193036175147e-06, "loss": 6.1821, "step": 40000 }, { "epoch": 0.44, "learning_rate": 9.966646253444732e-06, "loss": 6.1838, "step": 40500 }, { "epoch": 0.45, "learning_rate": 9.966099470714318e-06, "loss": 6.1757, "step": 41000 }, { "epoch": 0.45, "learning_rate": 9.965552687983904e-06, "loss": 6.1814, "step": 41500 }, { "epoch": 0.46, "learning_rate": 9.96500590525349e-06, "loss": 6.175, "step": 42000 }, { "epoch": 0.46, "learning_rate": 9.964459122523074e-06, "loss": 6.1762, "step": 42500 }, { "epoch": 0.47, "learning_rate": 9.963912339792661e-06, "loss": 6.1711, "step": 43000 }, { "epoch": 0.48, "learning_rate": 9.963365557062247e-06, "loss": 6.1588, "step": 43500 }, { "epoch": 0.48, "learning_rate": 9.962818774331833e-06, "loss": 6.1655, "step": 44000 }, { "epoch": 0.49, "learning_rate": 9.962271991601417e-06, "loss": 6.1644, "step": 44500 }, { "epoch": 0.49, "learning_rate": 9.961725208871003e-06, "loss": 6.1599, "step": 45000 }, { "epoch": 0.5, "learning_rate": 9.96117842614059e-06, "loss": 6.1616, "step": 45500 }, { "epoch": 0.5, "learning_rate": 9.960631643410176e-06, "loss": 6.1561, "step": 46000 }, { "epoch": 0.51, "learning_rate": 9.96008486067976e-06, "loss": 6.1546, "step": 46500 }, { "epoch": 0.51, "learning_rate": 9.959538077949346e-06, "loss": 6.15, "step": 47000 }, { "epoch": 0.52, "learning_rate": 9.958991295218932e-06, "loss": 6.1487, "step": 47500 }, { "epoch": 0.52, "learning_rate": 9.95844451248852e-06, "loss": 6.1457, "step": 48000 }, { "epoch": 0.53, "learning_rate": 9.957897729758103e-06, "loss": 6.145, "step": 48500 }, { "epoch": 0.54, "learning_rate": 9.95735094702769e-06, "loss": 6.1477, "step": 49000 }, { "epoch": 0.54, "learning_rate": 9.956804164297275e-06, "loss": 6.1436, "step": 49500 }, { "epoch": 0.55, "learning_rate": 9.956257381566863e-06, "loss": 6.1423, "step": 50000 }, { "epoch": 0.55, "learning_rate": 9.955710598836447e-06, "loss": 6.1369, "step": 50500 }, { "epoch": 0.56, "learning_rate": 9.955163816106032e-06, "loss": 6.1333, "step": 51000 }, { "epoch": 0.56, "learning_rate": 9.954617033375618e-06, "loss": 6.1302, "step": 51500 }, { "epoch": 0.57, "learning_rate": 9.954070250645204e-06, "loss": 6.1318, "step": 52000 }, { "epoch": 0.57, "learning_rate": 9.953523467914792e-06, "loss": 6.1276, "step": 52500 }, { "epoch": 0.58, "learning_rate": 9.952976685184376e-06, "loss": 6.1337, "step": 53000 }, { "epoch": 0.58, "learning_rate": 9.952429902453961e-06, "loss": 6.1271, "step": 53500 }, { "epoch": 0.59, "learning_rate": 9.951883119723547e-06, "loss": 6.1276, "step": 54000 }, { "epoch": 0.6, "learning_rate": 9.951336336993133e-06, "loss": 6.1248, "step": 54500 }, { "epoch": 0.6, "learning_rate": 9.950789554262719e-06, "loss": 6.1208, "step": 55000 }, { "epoch": 0.61, "learning_rate": 9.950242771532305e-06, "loss": 6.1235, "step": 55500 }, { "epoch": 0.61, "learning_rate": 9.94969598880189e-06, "loss": 6.1204, "step": 56000 }, { "epoch": 0.62, "learning_rate": 9.949149206071476e-06, "loss": 6.1173, "step": 56500 }, { "epoch": 0.62, "learning_rate": 9.948602423341062e-06, "loss": 6.1158, "step": 57000 }, { "epoch": 0.63, "learning_rate": 9.948055640610648e-06, "loss": 6.1157, "step": 57500 }, { "epoch": 0.63, "learning_rate": 9.947508857880234e-06, "loss": 6.1134, "step": 58000 }, { "epoch": 0.64, "learning_rate": 9.94696207514982e-06, "loss": 6.1098, "step": 58500 }, { "epoch": 0.64, "learning_rate": 9.946415292419405e-06, "loss": 6.1088, "step": 59000 }, { "epoch": 0.65, "learning_rate": 9.945868509688991e-06, "loss": 6.103, "step": 59500 }, { "epoch": 0.66, "learning_rate": 9.945321726958577e-06, "loss": 6.1126, "step": 60000 }, { "epoch": 0.66, "learning_rate": 9.944774944228163e-06, "loss": 6.1051, "step": 60500 }, { "epoch": 0.67, "learning_rate": 9.944228161497748e-06, "loss": 6.1033, "step": 61000 }, { "epoch": 0.67, "learning_rate": 9.943681378767334e-06, "loss": 6.1055, "step": 61500 }, { "epoch": 0.68, "learning_rate": 9.94313459603692e-06, "loss": 6.0993, "step": 62000 }, { "epoch": 0.68, "learning_rate": 9.942587813306506e-06, "loss": 6.0942, "step": 62500 }, { "epoch": 0.69, "learning_rate": 9.94204103057609e-06, "loss": 6.0978, "step": 63000 }, { "epoch": 0.69, "learning_rate": 9.941494247845677e-06, "loss": 6.0901, "step": 63500 }, { "epoch": 0.7, "learning_rate": 9.940947465115263e-06, "loss": 6.0952, "step": 64000 }, { "epoch": 0.7, "learning_rate": 9.940400682384849e-06, "loss": 6.0975, "step": 64500 }, { "epoch": 0.71, "learning_rate": 9.939853899654433e-06, "loss": 6.0861, "step": 65000 }, { "epoch": 0.72, "learning_rate": 9.93930711692402e-06, "loss": 6.0879, "step": 65500 }, { "epoch": 0.72, "learning_rate": 9.938760334193606e-06, "loss": 6.0857, "step": 66000 }, { "epoch": 0.73, "learning_rate": 9.938213551463192e-06, "loss": 6.0885, "step": 66500 }, { "epoch": 0.73, "learning_rate": 9.937666768732778e-06, "loss": 6.0858, "step": 67000 }, { "epoch": 0.74, "learning_rate": 9.937119986002362e-06, "loss": 6.0895, "step": 67500 }, { "epoch": 0.74, "learning_rate": 9.93657320327195e-06, "loss": 6.0856, "step": 68000 }, { "epoch": 0.75, "learning_rate": 9.936026420541535e-06, "loss": 6.0852, "step": 68500 }, { "epoch": 0.75, "learning_rate": 9.935479637811121e-06, "loss": 6.0807, "step": 69000 }, { "epoch": 0.76, "learning_rate": 9.934932855080705e-06, "loss": 6.0805, "step": 69500 }, { "epoch": 0.76, "learning_rate": 9.934386072350291e-06, "loss": 6.0833, "step": 70000 }, { "epoch": 0.77, "learning_rate": 9.933839289619878e-06, "loss": 6.0801, "step": 70500 }, { "epoch": 0.78, "learning_rate": 9.933292506889464e-06, "loss": 6.0736, "step": 71000 }, { "epoch": 0.78, "learning_rate": 9.932745724159048e-06, "loss": 6.0742, "step": 71500 }, { "epoch": 0.79, "learning_rate": 9.932198941428634e-06, "loss": 6.0768, "step": 72000 }, { "epoch": 0.79, "learning_rate": 9.93165215869822e-06, "loss": 6.0713, "step": 72500 }, { "epoch": 0.8, "learning_rate": 9.931105375967807e-06, "loss": 6.0677, "step": 73000 }, { "epoch": 0.8, "learning_rate": 9.930558593237391e-06, "loss": 6.0716, "step": 73500 }, { "epoch": 0.81, "learning_rate": 9.930011810506977e-06, "loss": 6.076, "step": 74000 }, { "epoch": 0.81, "learning_rate": 9.929465027776563e-06, "loss": 6.0753, "step": 74500 }, { "epoch": 0.82, "learning_rate": 9.928918245046149e-06, "loss": 6.0729, "step": 75000 }, { "epoch": 0.82, "learning_rate": 9.928371462315735e-06, "loss": 6.0631, "step": 75500 }, { "epoch": 0.83, "learning_rate": 9.92782467958532e-06, "loss": 6.0669, "step": 76000 }, { "epoch": 0.84, "learning_rate": 9.927277896854906e-06, "loss": 6.0686, "step": 76500 }, { "epoch": 0.84, "learning_rate": 9.926731114124492e-06, "loss": 6.0659, "step": 77000 }, { "epoch": 0.85, "learning_rate": 9.926184331394078e-06, "loss": 6.0683, "step": 77500 }, { "epoch": 0.85, "learning_rate": 9.925637548663664e-06, "loss": 6.0621, "step": 78000 }, { "epoch": 0.86, "learning_rate": 9.92509076593325e-06, "loss": 6.0592, "step": 78500 }, { "epoch": 0.86, "learning_rate": 9.924543983202835e-06, "loss": 6.0609, "step": 79000 }, { "epoch": 0.87, "learning_rate": 9.923997200472421e-06, "loss": 6.0573, "step": 79500 }, { "epoch": 0.87, "learning_rate": 9.923450417742007e-06, "loss": 6.0645, "step": 80000 }, { "epoch": 0.88, "learning_rate": 9.922903635011593e-06, "loss": 6.0681, "step": 80500 }, { "epoch": 0.88, "learning_rate": 9.922356852281178e-06, "loss": 6.0576, "step": 81000 }, { "epoch": 0.89, "learning_rate": 9.921810069550764e-06, "loss": 6.0559, "step": 81500 }, { "epoch": 0.9, "learning_rate": 9.92126328682035e-06, "loss": 6.0579, "step": 82000 }, { "epoch": 0.9, "learning_rate": 9.920716504089936e-06, "loss": 6.058, "step": 82500 }, { "epoch": 0.91, "learning_rate": 9.920169721359522e-06, "loss": 6.0535, "step": 83000 }, { "epoch": 0.91, "learning_rate": 9.919622938629107e-06, "loss": 6.0531, "step": 83500 }, { "epoch": 0.92, "learning_rate": 9.919076155898693e-06, "loss": 6.0586, "step": 84000 }, { "epoch": 0.92, "learning_rate": 9.918529373168279e-06, "loss": 6.0474, "step": 84500 }, { "epoch": 0.93, "learning_rate": 9.917982590437865e-06, "loss": 6.0526, "step": 85000 }, { "epoch": 0.93, "learning_rate": 9.91743580770745e-06, "loss": 6.0558, "step": 85500 }, { "epoch": 0.94, "learning_rate": 9.916889024977036e-06, "loss": 6.0482, "step": 86000 }, { "epoch": 0.94, "learning_rate": 9.916342242246622e-06, "loss": 6.0483, "step": 86500 }, { "epoch": 0.95, "learning_rate": 9.915795459516208e-06, "loss": 6.0481, "step": 87000 }, { "epoch": 0.96, "learning_rate": 9.915248676785794e-06, "loss": 6.0491, "step": 87500 }, { "epoch": 0.96, "learning_rate": 9.914701894055378e-06, "loss": 6.0415, "step": 88000 }, { "epoch": 0.97, "learning_rate": 9.914155111324965e-06, "loss": 6.0473, "step": 88500 }, { "epoch": 0.97, "learning_rate": 9.913608328594551e-06, "loss": 6.0442, "step": 89000 }, { "epoch": 0.98, "learning_rate": 9.913061545864137e-06, "loss": 6.0461, "step": 89500 }, { "epoch": 0.98, "learning_rate": 9.912514763133721e-06, "loss": 6.042, "step": 90000 }, { "epoch": 0.99, "learning_rate": 9.911967980403307e-06, "loss": 6.0383, "step": 90500 }, { "epoch": 0.99, "learning_rate": 9.911421197672894e-06, "loss": 6.0393, "step": 91000 }, { "epoch": 1.0, "learning_rate": 9.91087441494248e-06, "loss": 6.0437, "step": 91500 }, { "epoch": 1.0, "learning_rate": 9.910327632212064e-06, "loss": 6.038, "step": 92000 }, { "epoch": 1.01, "learning_rate": 9.90978084948165e-06, "loss": 6.0349, "step": 92500 }, { "epoch": 1.02, "learning_rate": 9.909234066751237e-06, "loss": 6.0353, "step": 93000 }, { "epoch": 1.02, "learning_rate": 9.908687284020823e-06, "loss": 6.0408, "step": 93500 }, { "epoch": 1.03, "learning_rate": 9.908140501290409e-06, "loss": 6.034, "step": 94000 }, { "epoch": 1.03, "learning_rate": 9.907593718559993e-06, "loss": 6.0379, "step": 94500 }, { "epoch": 1.04, "learning_rate": 9.907046935829579e-06, "loss": 6.0328, "step": 95000 }, { "epoch": 1.04, "learning_rate": 9.906500153099166e-06, "loss": 6.0319, "step": 95500 }, { "epoch": 1.05, "learning_rate": 9.905953370368752e-06, "loss": 6.0276, "step": 96000 }, { "epoch": 1.05, "learning_rate": 9.905406587638336e-06, "loss": 6.0296, "step": 96500 }, { "epoch": 1.06, "learning_rate": 9.904859804907922e-06, "loss": 6.0279, "step": 97000 }, { "epoch": 1.07, "learning_rate": 9.904313022177508e-06, "loss": 6.0268, "step": 97500 }, { "epoch": 1.07, "learning_rate": 9.903766239447095e-06, "loss": 6.0198, "step": 98000 }, { "epoch": 1.08, "learning_rate": 9.90321945671668e-06, "loss": 6.0227, "step": 98500 }, { "epoch": 1.08, "learning_rate": 9.902672673986265e-06, "loss": 6.0087, "step": 99000 }, { "epoch": 1.09, "learning_rate": 9.902125891255851e-06, "loss": 6.0001, "step": 99500 }, { "epoch": 1.09, "learning_rate": 9.901579108525437e-06, "loss": 5.9878, "step": 100000 }, { "epoch": 1.1, "learning_rate": 9.901032325795023e-06, "loss": 5.98, "step": 100500 }, { "epoch": 1.1, "learning_rate": 9.900485543064608e-06, "loss": 5.9674, "step": 101000 }, { "epoch": 1.11, "learning_rate": 9.899938760334194e-06, "loss": 5.9536, "step": 101500 }, { "epoch": 1.11, "learning_rate": 9.89939197760378e-06, "loss": 5.9448, "step": 102000 }, { "epoch": 1.12, "learning_rate": 9.898845194873366e-06, "loss": 5.9356, "step": 102500 }, { "epoch": 1.13, "learning_rate": 9.898298412142952e-06, "loss": 5.9187, "step": 103000 }, { "epoch": 1.13, "learning_rate": 9.897751629412537e-06, "loss": 5.914, "step": 103500 }, { "epoch": 1.14, "learning_rate": 9.897204846682123e-06, "loss": 5.9026, "step": 104000 }, { "epoch": 1.14, "learning_rate": 9.896658063951709e-06, "loss": 5.8975, "step": 104500 }, { "epoch": 1.15, "learning_rate": 9.896111281221295e-06, "loss": 5.8889, "step": 105000 }, { "epoch": 1.15, "learning_rate": 9.89556449849088e-06, "loss": 5.8869, "step": 105500 }, { "epoch": 1.16, "learning_rate": 9.895017715760466e-06, "loss": 5.8752, "step": 106000 }, { "epoch": 1.16, "learning_rate": 9.894470933030052e-06, "loss": 5.8721, "step": 106500 }, { "epoch": 1.17, "learning_rate": 9.893924150299638e-06, "loss": 5.8684, "step": 107000 }, { "epoch": 1.17, "learning_rate": 9.893377367569224e-06, "loss": 5.863, "step": 107500 }, { "epoch": 1.18, "learning_rate": 9.89283058483881e-06, "loss": 5.8546, "step": 108000 }, { "epoch": 1.19, "learning_rate": 9.892283802108395e-06, "loss": 5.8482, "step": 108500 }, { "epoch": 1.19, "learning_rate": 9.891737019377981e-06, "loss": 5.8479, "step": 109000 }, { "epoch": 1.2, "learning_rate": 9.891190236647567e-06, "loss": 5.8455, "step": 109500 }, { "epoch": 1.2, "learning_rate": 9.890643453917153e-06, "loss": 5.8358, "step": 110000 }, { "epoch": 1.21, "learning_rate": 9.890096671186738e-06, "loss": 5.8313, "step": 110500 }, { "epoch": 1.21, "learning_rate": 9.889549888456324e-06, "loss": 5.8262, "step": 111000 }, { "epoch": 1.22, "learning_rate": 9.88900310572591e-06, "loss": 5.8251, "step": 111500 }, { "epoch": 1.22, "learning_rate": 9.888456322995496e-06, "loss": 5.8234, "step": 112000 }, { "epoch": 1.23, "learning_rate": 9.887909540265082e-06, "loss": 5.814, "step": 112500 }, { "epoch": 1.23, "learning_rate": 9.887362757534666e-06, "loss": 5.8128, "step": 113000 }, { "epoch": 1.24, "learning_rate": 9.886815974804253e-06, "loss": 5.8091, "step": 113500 }, { "epoch": 1.25, "learning_rate": 9.886269192073839e-06, "loss": 5.8063, "step": 114000 }, { "epoch": 1.25, "learning_rate": 9.885722409343425e-06, "loss": 5.8085, "step": 114500 }, { "epoch": 1.26, "learning_rate": 9.885175626613009e-06, "loss": 5.7971, "step": 115000 }, { "epoch": 1.26, "learning_rate": 9.884628843882595e-06, "loss": 5.8025, "step": 115500 }, { "epoch": 1.27, "learning_rate": 9.884082061152182e-06, "loss": 5.7942, "step": 116000 }, { "epoch": 1.27, "learning_rate": 9.883535278421768e-06, "loss": 5.7909, "step": 116500 }, { "epoch": 1.28, "learning_rate": 9.882988495691352e-06, "loss": 5.7886, "step": 117000 }, { "epoch": 1.28, "learning_rate": 9.882441712960938e-06, "loss": 5.7821, "step": 117500 }, { "epoch": 1.29, "learning_rate": 9.881894930230524e-06, "loss": 5.7776, "step": 118000 }, { "epoch": 1.29, "learning_rate": 9.881348147500111e-06, "loss": 5.7781, "step": 118500 }, { "epoch": 1.3, "learning_rate": 9.880801364769695e-06, "loss": 5.7666, "step": 119000 }, { "epoch": 1.31, "learning_rate": 9.880254582039281e-06, "loss": 5.7716, "step": 119500 }, { "epoch": 1.31, "learning_rate": 9.879707799308867e-06, "loss": 5.7703, "step": 120000 }, { "epoch": 1.32, "learning_rate": 9.879161016578454e-06, "loss": 5.763, "step": 120500 }, { "epoch": 1.32, "learning_rate": 9.878614233848038e-06, "loss": 5.7535, "step": 121000 }, { "epoch": 1.33, "learning_rate": 9.878067451117624e-06, "loss": 5.7573, "step": 121500 }, { "epoch": 1.33, "learning_rate": 9.87752066838721e-06, "loss": 5.7527, "step": 122000 }, { "epoch": 1.34, "learning_rate": 9.876973885656796e-06, "loss": 5.7461, "step": 122500 }, { "epoch": 1.34, "learning_rate": 9.876427102926383e-06, "loss": 5.744, "step": 123000 }, { "epoch": 1.35, "learning_rate": 9.875880320195967e-06, "loss": 5.7397, "step": 123500 }, { "epoch": 1.35, "learning_rate": 9.875333537465553e-06, "loss": 5.7412, "step": 124000 }, { "epoch": 1.36, "learning_rate": 9.874786754735139e-06, "loss": 5.7337, "step": 124500 }, { "epoch": 1.37, "learning_rate": 9.874239972004725e-06, "loss": 5.7257, "step": 125000 }, { "epoch": 1.37, "learning_rate": 9.87369318927431e-06, "loss": 5.7263, "step": 125500 }, { "epoch": 1.38, "learning_rate": 9.873146406543896e-06, "loss": 5.7242, "step": 126000 }, { "epoch": 1.38, "learning_rate": 9.872599623813482e-06, "loss": 5.7179, "step": 126500 }, { "epoch": 1.39, "learning_rate": 9.872052841083068e-06, "loss": 5.7139, "step": 127000 }, { "epoch": 1.39, "learning_rate": 9.871506058352654e-06, "loss": 5.7089, "step": 127500 }, { "epoch": 1.4, "learning_rate": 9.87095927562224e-06, "loss": 5.7034, "step": 128000 }, { "epoch": 1.4, "learning_rate": 9.870412492891825e-06, "loss": 5.7053, "step": 128500 }, { "epoch": 1.41, "learning_rate": 9.869865710161411e-06, "loss": 5.6986, "step": 129000 }, { "epoch": 1.41, "learning_rate": 9.869318927430997e-06, "loss": 5.6903, "step": 129500 }, { "epoch": 1.42, "learning_rate": 9.868772144700583e-06, "loss": 5.6926, "step": 130000 }, { "epoch": 1.43, "learning_rate": 9.868225361970168e-06, "loss": 5.6852, "step": 130500 }, { "epoch": 1.43, "learning_rate": 9.867678579239754e-06, "loss": 5.6819, "step": 131000 }, { "epoch": 1.44, "learning_rate": 9.86713179650934e-06, "loss": 5.6773, "step": 131500 }, { "epoch": 1.44, "learning_rate": 9.866585013778926e-06, "loss": 5.6766, "step": 132000 }, { "epoch": 1.45, "learning_rate": 9.866038231048512e-06, "loss": 5.6685, "step": 132500 }, { "epoch": 1.45, "learning_rate": 9.865491448318097e-06, "loss": 5.6682, "step": 133000 }, { "epoch": 1.46, "learning_rate": 9.864944665587683e-06, "loss": 5.6615, "step": 133500 }, { "epoch": 1.46, "learning_rate": 9.864397882857269e-06, "loss": 5.6577, "step": 134000 }, { "epoch": 1.47, "learning_rate": 9.863851100126855e-06, "loss": 5.6493, "step": 134500 }, { "epoch": 1.47, "learning_rate": 9.86330431739644e-06, "loss": 5.6482, "step": 135000 }, { "epoch": 1.48, "learning_rate": 9.862757534666025e-06, "loss": 5.6448, "step": 135500 }, { "epoch": 1.49, "learning_rate": 9.862210751935612e-06, "loss": 5.6404, "step": 136000 }, { "epoch": 1.49, "learning_rate": 9.861663969205198e-06, "loss": 5.6273, "step": 136500 }, { "epoch": 1.5, "learning_rate": 9.861117186474784e-06, "loss": 5.6264, "step": 137000 }, { "epoch": 1.5, "learning_rate": 9.86057040374437e-06, "loss": 5.6244, "step": 137500 }, { "epoch": 1.51, "learning_rate": 9.860023621013954e-06, "loss": 5.6176, "step": 138000 }, { "epoch": 1.51, "learning_rate": 9.859476838283541e-06, "loss": 5.6103, "step": 138500 }, { "epoch": 1.52, "learning_rate": 9.858930055553127e-06, "loss": 5.6109, "step": 139000 }, { "epoch": 1.52, "learning_rate": 9.858383272822713e-06, "loss": 5.6011, "step": 139500 }, { "epoch": 1.53, "learning_rate": 9.857836490092297e-06, "loss": 5.5992, "step": 140000 }, { "epoch": 1.53, "learning_rate": 9.857289707361883e-06, "loss": 5.5934, "step": 140500 }, { "epoch": 1.54, "learning_rate": 9.85674292463147e-06, "loss": 5.5927, "step": 141000 }, { "epoch": 1.55, "learning_rate": 9.856196141901056e-06, "loss": 5.5832, "step": 141500 }, { "epoch": 1.55, "learning_rate": 9.85564935917064e-06, "loss": 5.5755, "step": 142000 }, { "epoch": 1.56, "learning_rate": 9.855102576440226e-06, "loss": 5.5805, "step": 142500 }, { "epoch": 1.56, "learning_rate": 9.854555793709812e-06, "loss": 5.5722, "step": 143000 }, { "epoch": 1.57, "learning_rate": 9.854009010979399e-06, "loss": 5.5577, "step": 143500 }, { "epoch": 1.57, "learning_rate": 9.853462228248983e-06, "loss": 5.5574, "step": 144000 }, { "epoch": 1.58, "learning_rate": 9.852915445518569e-06, "loss": 5.554, "step": 144500 }, { "epoch": 1.58, "learning_rate": 9.852368662788155e-06, "loss": 5.5387, "step": 145000 }, { "epoch": 1.59, "learning_rate": 9.851821880057742e-06, "loss": 5.5396, "step": 145500 }, { "epoch": 1.59, "learning_rate": 9.851275097327326e-06, "loss": 5.5271, "step": 146000 }, { "epoch": 1.6, "learning_rate": 9.850728314596912e-06, "loss": 5.514, "step": 146500 }, { "epoch": 1.61, "learning_rate": 9.850181531866498e-06, "loss": 5.5001, "step": 147000 }, { "epoch": 1.61, "learning_rate": 9.849634749136084e-06, "loss": 5.4887, "step": 147500 }, { "epoch": 1.62, "learning_rate": 9.84908796640567e-06, "loss": 5.4701, "step": 148000 }, { "epoch": 1.62, "learning_rate": 9.848541183675255e-06, "loss": 5.4462, "step": 148500 }, { "epoch": 1.63, "learning_rate": 9.847994400944841e-06, "loss": 5.4345, "step": 149000 }, { "epoch": 1.63, "learning_rate": 9.847447618214427e-06, "loss": 5.4187, "step": 149500 }, { "epoch": 1.64, "learning_rate": 9.846900835484013e-06, "loss": 5.4015, "step": 150000 }, { "epoch": 1.64, "learning_rate": 9.846354052753598e-06, "loss": 5.3738, "step": 150500 }, { "epoch": 1.65, "learning_rate": 9.845807270023184e-06, "loss": 5.3668, "step": 151000 }, { "epoch": 1.65, "learning_rate": 9.84526048729277e-06, "loss": 5.346, "step": 151500 }, { "epoch": 1.66, "learning_rate": 9.844713704562356e-06, "loss": 5.3218, "step": 152000 }, { "epoch": 1.67, "learning_rate": 9.844166921831942e-06, "loss": 5.2992, "step": 152500 }, { "epoch": 1.67, "learning_rate": 9.843620139101527e-06, "loss": 5.284, "step": 153000 }, { "epoch": 1.68, "learning_rate": 9.843073356371113e-06, "loss": 5.2631, "step": 153500 }, { "epoch": 1.68, "learning_rate": 9.842526573640699e-06, "loss": 5.249, "step": 154000 }, { "epoch": 1.69, "learning_rate": 9.841979790910285e-06, "loss": 5.2232, "step": 154500 }, { "epoch": 1.69, "learning_rate": 9.84143300817987e-06, "loss": 5.1994, "step": 155000 }, { "epoch": 1.7, "learning_rate": 9.840886225449456e-06, "loss": 5.1831, "step": 155500 }, { "epoch": 1.7, "learning_rate": 9.840339442719042e-06, "loss": 5.1611, "step": 156000 }, { "epoch": 1.71, "learning_rate": 9.839792659988628e-06, "loss": 5.1488, "step": 156500 }, { "epoch": 1.72, "learning_rate": 9.839245877258214e-06, "loss": 5.1222, "step": 157000 }, { "epoch": 1.72, "learning_rate": 9.8386990945278e-06, "loss": 5.0967, "step": 157500 }, { "epoch": 1.73, "learning_rate": 9.838152311797385e-06, "loss": 5.0844, "step": 158000 }, { "epoch": 1.73, "learning_rate": 9.83760552906697e-06, "loss": 5.0637, "step": 158500 }, { "epoch": 1.74, "learning_rate": 9.837058746336557e-06, "loss": 5.0471, "step": 159000 }, { "epoch": 1.74, "learning_rate": 9.836511963606143e-06, "loss": 5.0245, "step": 159500 }, { "epoch": 1.75, "learning_rate": 9.835965180875729e-06, "loss": 5.0092, "step": 160000 }, { "epoch": 1.75, "learning_rate": 9.835418398145313e-06, "loss": 4.9868, "step": 160500 }, { "epoch": 1.76, "learning_rate": 9.8348716154149e-06, "loss": 4.9697, "step": 161000 }, { "epoch": 1.76, "learning_rate": 9.834324832684486e-06, "loss": 4.954, "step": 161500 }, { "epoch": 1.77, "learning_rate": 9.833778049954072e-06, "loss": 4.9358, "step": 162000 }, { "epoch": 1.78, "learning_rate": 9.833231267223656e-06, "loss": 4.9229, "step": 162500 }, { "epoch": 1.78, "learning_rate": 9.832684484493242e-06, "loss": 4.8988, "step": 163000 }, { "epoch": 1.79, "learning_rate": 9.832137701762829e-06, "loss": 4.8938, "step": 163500 }, { "epoch": 1.79, "learning_rate": 9.831590919032415e-06, "loss": 4.8687, "step": 164000 }, { "epoch": 1.8, "learning_rate": 9.831044136302e-06, "loss": 4.8627, "step": 164500 }, { "epoch": 1.8, "learning_rate": 9.830497353571585e-06, "loss": 4.8373, "step": 165000 }, { "epoch": 1.81, "learning_rate": 9.82995057084117e-06, "loss": 4.835, "step": 165500 }, { "epoch": 1.81, "learning_rate": 9.829403788110758e-06, "loss": 4.8168, "step": 166000 }, { "epoch": 1.82, "learning_rate": 9.828857005380344e-06, "loss": 4.8015, "step": 166500 }, { "epoch": 1.82, "learning_rate": 9.828310222649928e-06, "loss": 4.7961, "step": 167000 }, { "epoch": 1.83, "learning_rate": 9.827763439919514e-06, "loss": 4.777, "step": 167500 }, { "epoch": 1.84, "learning_rate": 9.8272166571891e-06, "loss": 4.7692, "step": 168000 }, { "epoch": 1.84, "learning_rate": 9.826669874458687e-06, "loss": 4.7501, "step": 168500 }, { "epoch": 1.85, "learning_rate": 9.826123091728271e-06, "loss": 4.7493, "step": 169000 }, { "epoch": 1.85, "learning_rate": 9.825576308997857e-06, "loss": 4.7184, "step": 169500 }, { "epoch": 1.86, "learning_rate": 9.825029526267443e-06, "loss": 4.7173, "step": 170000 }, { "epoch": 1.86, "learning_rate": 9.824482743537029e-06, "loss": 4.7014, "step": 170500 }, { "epoch": 1.87, "learning_rate": 9.823935960806614e-06, "loss": 4.688, "step": 171000 }, { "epoch": 1.87, "learning_rate": 9.8233891780762e-06, "loss": 4.6697, "step": 171500 }, { "epoch": 1.88, "learning_rate": 9.822842395345786e-06, "loss": 4.6638, "step": 172000 }, { "epoch": 1.88, "learning_rate": 9.822295612615372e-06, "loss": 4.6493, "step": 172500 }, { "epoch": 1.89, "learning_rate": 9.821748829884957e-06, "loss": 4.6314, "step": 173000 }, { "epoch": 1.9, "learning_rate": 9.821202047154543e-06, "loss": 4.619, "step": 173500 }, { "epoch": 1.9, "learning_rate": 9.820655264424129e-06, "loss": 4.6043, "step": 174000 }, { "epoch": 1.91, "learning_rate": 9.820108481693715e-06, "loss": 4.5653, "step": 174500 }, { "epoch": 1.91, "learning_rate": 9.8195616989633e-06, "loss": 4.5358, "step": 175000 }, { "epoch": 1.92, "learning_rate": 9.819014916232886e-06, "loss": 4.5157, "step": 175500 }, { "epoch": 1.92, "learning_rate": 9.818468133502472e-06, "loss": 4.4936, "step": 176000 }, { "epoch": 1.93, "learning_rate": 9.817921350772058e-06, "loss": 4.4699, "step": 176500 }, { "epoch": 1.93, "learning_rate": 9.817374568041644e-06, "loss": 4.4478, "step": 177000 }, { "epoch": 1.94, "learning_rate": 9.81682778531123e-06, "loss": 4.4207, "step": 177500 }, { "epoch": 1.94, "learning_rate": 9.816281002580815e-06, "loss": 4.4084, "step": 178000 }, { "epoch": 1.95, "learning_rate": 9.815734219850401e-06, "loss": 4.3834, "step": 178500 }, { "epoch": 1.96, "learning_rate": 9.815187437119987e-06, "loss": 4.3628, "step": 179000 }, { "epoch": 1.96, "learning_rate": 9.814640654389573e-06, "loss": 4.3531, "step": 179500 }, { "epoch": 1.97, "learning_rate": 9.814093871659159e-06, "loss": 4.3332, "step": 180000 }, { "epoch": 1.97, "learning_rate": 9.813547088928744e-06, "loss": 4.305, "step": 180500 }, { "epoch": 1.98, "learning_rate": 9.81300030619833e-06, "loss": 4.2959, "step": 181000 }, { "epoch": 1.98, "learning_rate": 9.812453523467916e-06, "loss": 4.2751, "step": 181500 }, { "epoch": 1.99, "learning_rate": 9.811906740737502e-06, "loss": 4.2622, "step": 182000 }, { "epoch": 1.99, "learning_rate": 9.811359958007088e-06, "loss": 4.2502, "step": 182500 }, { "epoch": 2.0, "learning_rate": 9.810813175276673e-06, "loss": 4.2322, "step": 183000 }, { "epoch": 2.0, "learning_rate": 9.810266392546257e-06, "loss": 4.2145, "step": 183500 }, { "epoch": 2.01, "learning_rate": 9.809719609815845e-06, "loss": 4.1986, "step": 184000 }, { "epoch": 2.02, "learning_rate": 9.80917282708543e-06, "loss": 4.1864, "step": 184500 }, { "epoch": 2.02, "learning_rate": 9.808626044355017e-06, "loss": 4.1727, "step": 185000 }, { "epoch": 2.03, "learning_rate": 9.8080792616246e-06, "loss": 4.1536, "step": 185500 }, { "epoch": 2.03, "learning_rate": 9.807532478894186e-06, "loss": 4.1434, "step": 186000 }, { "epoch": 2.04, "learning_rate": 9.806985696163774e-06, "loss": 4.1301, "step": 186500 }, { "epoch": 2.04, "learning_rate": 9.80643891343336e-06, "loss": 4.1111, "step": 187000 }, { "epoch": 2.05, "learning_rate": 9.805892130702944e-06, "loss": 4.0944, "step": 187500 }, { "epoch": 2.05, "learning_rate": 9.80534534797253e-06, "loss": 4.0766, "step": 188000 }, { "epoch": 2.06, "learning_rate": 9.804798565242117e-06, "loss": 4.0642, "step": 188500 }, { "epoch": 2.06, "learning_rate": 9.804251782511703e-06, "loss": 4.0497, "step": 189000 }, { "epoch": 2.07, "learning_rate": 9.803704999781287e-06, "loss": 4.0346, "step": 189500 }, { "epoch": 2.08, "learning_rate": 9.803158217050873e-06, "loss": 4.0273, "step": 190000 }, { "epoch": 2.08, "learning_rate": 9.802611434320459e-06, "loss": 3.9973, "step": 190500 }, { "epoch": 2.09, "learning_rate": 9.802064651590046e-06, "loss": 3.9944, "step": 191000 }, { "epoch": 2.09, "learning_rate": 9.80151786885963e-06, "loss": 3.9771, "step": 191500 }, { "epoch": 2.1, "learning_rate": 9.800971086129216e-06, "loss": 3.963, "step": 192000 }, { "epoch": 2.1, "learning_rate": 9.800424303398802e-06, "loss": 3.9549, "step": 192500 }, { "epoch": 2.11, "learning_rate": 9.799877520668388e-06, "loss": 3.9439, "step": 193000 }, { "epoch": 2.11, "learning_rate": 9.799330737937975e-06, "loss": 3.9168, "step": 193500 }, { "epoch": 2.12, "learning_rate": 9.798783955207559e-06, "loss": 3.911, "step": 194000 }, { "epoch": 2.12, "learning_rate": 9.798237172477145e-06, "loss": 3.8925, "step": 194500 }, { "epoch": 2.13, "learning_rate": 9.79769038974673e-06, "loss": 3.8884, "step": 195000 }, { "epoch": 2.14, "learning_rate": 9.797143607016316e-06, "loss": 3.8734, "step": 195500 }, { "epoch": 2.14, "learning_rate": 9.796596824285902e-06, "loss": 3.8583, "step": 196000 }, { "epoch": 2.15, "learning_rate": 9.796050041555488e-06, "loss": 3.8526, "step": 196500 }, { "epoch": 2.15, "learning_rate": 9.795503258825074e-06, "loss": 3.8396, "step": 197000 }, { "epoch": 2.16, "learning_rate": 9.79495647609466e-06, "loss": 3.8237, "step": 197500 }, { "epoch": 2.16, "learning_rate": 9.794409693364245e-06, "loss": 3.8166, "step": 198000 }, { "epoch": 2.17, "learning_rate": 9.793862910633831e-06, "loss": 3.8045, "step": 198500 }, { "epoch": 2.17, "learning_rate": 9.793316127903417e-06, "loss": 3.7962, "step": 199000 }, { "epoch": 2.18, "learning_rate": 9.792769345173003e-06, "loss": 3.7779, "step": 199500 }, { "epoch": 2.18, "learning_rate": 9.792222562442589e-06, "loss": 3.7746, "step": 200000 }, { "epoch": 2.19, "learning_rate": 9.791675779712174e-06, "loss": 3.7582, "step": 200500 }, { "epoch": 2.2, "learning_rate": 9.79112899698176e-06, "loss": 3.7514, "step": 201000 }, { "epoch": 2.2, "learning_rate": 9.790582214251346e-06, "loss": 3.7355, "step": 201500 }, { "epoch": 2.21, "learning_rate": 9.790035431520932e-06, "loss": 3.7286, "step": 202000 }, { "epoch": 2.21, "learning_rate": 9.789488648790518e-06, "loss": 3.7243, "step": 202500 }, { "epoch": 2.22, "learning_rate": 9.788941866060103e-06, "loss": 3.7161, "step": 203000 }, { "epoch": 2.22, "learning_rate": 9.78839508332969e-06, "loss": 3.703, "step": 203500 }, { "epoch": 2.23, "learning_rate": 9.787848300599275e-06, "loss": 3.6907, "step": 204000 }, { "epoch": 2.23, "learning_rate": 9.78730151786886e-06, "loss": 3.6817, "step": 204500 }, { "epoch": 2.24, "learning_rate": 9.786754735138447e-06, "loss": 3.6714, "step": 205000 }, { "epoch": 2.24, "learning_rate": 9.786207952408032e-06, "loss": 3.6614, "step": 205500 }, { "epoch": 2.25, "learning_rate": 9.785661169677618e-06, "loss": 3.6513, "step": 206000 }, { "epoch": 2.26, "learning_rate": 9.785114386947204e-06, "loss": 3.6473, "step": 206500 }, { "epoch": 2.26, "learning_rate": 9.78456760421679e-06, "loss": 3.6368, "step": 207000 }, { "epoch": 2.27, "learning_rate": 9.784020821486376e-06, "loss": 3.6283, "step": 207500 }, { "epoch": 2.27, "learning_rate": 9.783474038755961e-06, "loss": 3.6227, "step": 208000 }, { "epoch": 2.28, "learning_rate": 9.782927256025545e-06, "loss": 3.6226, "step": 208500 }, { "epoch": 2.28, "learning_rate": 9.782380473295133e-06, "loss": 3.6003, "step": 209000 }, { "epoch": 2.29, "learning_rate": 9.781833690564719e-06, "loss": 3.5948, "step": 209500 }, { "epoch": 2.29, "learning_rate": 9.781286907834304e-06, "loss": 3.5877, "step": 210000 }, { "epoch": 2.3, "learning_rate": 9.780740125103889e-06, "loss": 3.5795, "step": 210500 }, { "epoch": 2.3, "learning_rate": 9.780193342373474e-06, "loss": 3.5765, "step": 211000 }, { "epoch": 2.31, "learning_rate": 9.779646559643062e-06, "loss": 3.5659, "step": 211500 }, { "epoch": 2.32, "learning_rate": 9.779099776912648e-06, "loss": 3.556, "step": 212000 }, { "epoch": 2.32, "learning_rate": 9.778552994182232e-06, "loss": 3.5431, "step": 212500 }, { "epoch": 2.33, "learning_rate": 9.778006211451818e-06, "loss": 3.5406, "step": 213000 }, { "epoch": 2.33, "learning_rate": 9.777459428721405e-06, "loss": 3.531, "step": 213500 }, { "epoch": 2.34, "learning_rate": 9.77691264599099e-06, "loss": 3.5333, "step": 214000 }, { "epoch": 2.34, "learning_rate": 9.776365863260575e-06, "loss": 3.5236, "step": 214500 }, { "epoch": 2.35, "learning_rate": 9.77581908053016e-06, "loss": 3.5095, "step": 215000 }, { "epoch": 2.35, "learning_rate": 9.775272297799747e-06, "loss": 3.5124, "step": 215500 }, { "epoch": 2.36, "learning_rate": 9.774725515069334e-06, "loss": 3.4987, "step": 216000 }, { "epoch": 2.36, "learning_rate": 9.774178732338918e-06, "loss": 3.4854, "step": 216500 }, { "epoch": 2.37, "learning_rate": 9.773631949608504e-06, "loss": 3.4959, "step": 217000 }, { "epoch": 2.38, "learning_rate": 9.77308516687809e-06, "loss": 3.4789, "step": 217500 }, { "epoch": 2.38, "learning_rate": 9.772538384147675e-06, "loss": 3.4779, "step": 218000 }, { "epoch": 2.39, "learning_rate": 9.771991601417261e-06, "loss": 3.4707, "step": 218500 }, { "epoch": 2.39, "learning_rate": 9.771444818686847e-06, "loss": 3.4631, "step": 219000 }, { "epoch": 2.4, "learning_rate": 9.770898035956433e-06, "loss": 3.4584, "step": 219500 }, { "epoch": 2.4, "learning_rate": 9.770351253226019e-06, "loss": 3.4555, "step": 220000 }, { "epoch": 2.41, "learning_rate": 9.769804470495604e-06, "loss": 3.4457, "step": 220500 }, { "epoch": 2.41, "learning_rate": 9.76925768776519e-06, "loss": 3.434, "step": 221000 }, { "epoch": 2.42, "learning_rate": 9.768710905034776e-06, "loss": 3.4329, "step": 221500 }, { "epoch": 2.43, "learning_rate": 9.768164122304362e-06, "loss": 3.4249, "step": 222000 }, { "epoch": 2.43, "learning_rate": 9.767617339573948e-06, "loss": 3.4238, "step": 222500 }, { "epoch": 2.44, "learning_rate": 9.767070556843533e-06, "loss": 3.414, "step": 223000 }, { "epoch": 2.44, "learning_rate": 9.76652377411312e-06, "loss": 3.4074, "step": 223500 }, { "epoch": 2.45, "learning_rate": 9.765976991382705e-06, "loss": 3.4066, "step": 224000 }, { "epoch": 2.45, "learning_rate": 9.76543020865229e-06, "loss": 3.399, "step": 224500 }, { "epoch": 2.46, "learning_rate": 9.764883425921877e-06, "loss": 3.3975, "step": 225000 }, { "epoch": 2.46, "learning_rate": 9.764336643191462e-06, "loss": 3.3818, "step": 225500 }, { "epoch": 2.47, "learning_rate": 9.763789860461048e-06, "loss": 3.3861, "step": 226000 }, { "epoch": 2.47, "learning_rate": 9.763243077730634e-06, "loss": 3.3842, "step": 226500 }, { "epoch": 2.48, "learning_rate": 9.76269629500022e-06, "loss": 3.3747, "step": 227000 }, { "epoch": 2.49, "learning_rate": 9.762149512269806e-06, "loss": 3.3666, "step": 227500 }, { "epoch": 2.49, "learning_rate": 9.761602729539391e-06, "loss": 3.3616, "step": 228000 }, { "epoch": 2.5, "learning_rate": 9.761055946808977e-06, "loss": 3.3621, "step": 228500 }, { "epoch": 2.5, "learning_rate": 9.760509164078563e-06, "loss": 3.3538, "step": 229000 }, { "epoch": 2.51, "learning_rate": 9.759962381348149e-06, "loss": 3.3512, "step": 229500 }, { "epoch": 2.51, "learning_rate": 9.759415598617735e-06, "loss": 3.3492, "step": 230000 }, { "epoch": 2.52, "learning_rate": 9.75886881588732e-06, "loss": 3.3349, "step": 230500 }, { "epoch": 2.52, "learning_rate": 9.758322033156904e-06, "loss": 3.3314, "step": 231000 }, { "epoch": 2.53, "learning_rate": 9.757775250426492e-06, "loss": 3.3278, "step": 231500 }, { "epoch": 2.53, "learning_rate": 9.757228467696078e-06, "loss": 3.3328, "step": 232000 }, { "epoch": 2.54, "learning_rate": 9.756681684965663e-06, "loss": 3.3167, "step": 232500 }, { "epoch": 2.55, "learning_rate": 9.756134902235248e-06, "loss": 3.3179, "step": 233000 }, { "epoch": 2.55, "learning_rate": 9.755588119504833e-06, "loss": 3.3142, "step": 233500 }, { "epoch": 2.56, "learning_rate": 9.75504133677442e-06, "loss": 3.3055, "step": 234000 }, { "epoch": 2.56, "learning_rate": 9.754494554044007e-06, "loss": 3.3036, "step": 234500 }, { "epoch": 2.57, "learning_rate": 9.753947771313592e-06, "loss": 3.3001, "step": 235000 }, { "epoch": 2.57, "learning_rate": 9.753400988583177e-06, "loss": 3.2993, "step": 235500 }, { "epoch": 2.58, "learning_rate": 9.752854205852762e-06, "loss": 3.2922, "step": 236000 }, { "epoch": 2.58, "learning_rate": 9.75230742312235e-06, "loss": 3.2861, "step": 236500 }, { "epoch": 2.59, "learning_rate": 9.751760640391936e-06, "loss": 3.295, "step": 237000 }, { "epoch": 2.59, "learning_rate": 9.75121385766152e-06, "loss": 3.2767, "step": 237500 }, { "epoch": 2.6, "learning_rate": 9.750667074931105e-06, "loss": 3.274, "step": 238000 }, { "epoch": 2.61, "learning_rate": 9.750120292200691e-06, "loss": 3.2711, "step": 238500 }, { "epoch": 2.61, "learning_rate": 9.749573509470279e-06, "loss": 3.2646, "step": 239000 }, { "epoch": 2.62, "learning_rate": 9.749026726739863e-06, "loss": 3.2661, "step": 239500 }, { "epoch": 2.62, "learning_rate": 9.748479944009449e-06, "loss": 3.2614, "step": 240000 }, { "epoch": 2.63, "learning_rate": 9.747933161279034e-06, "loss": 3.2591, "step": 240500 }, { "epoch": 2.63, "learning_rate": 9.747386378548622e-06, "loss": 3.2537, "step": 241000 }, { "epoch": 2.64, "learning_rate": 9.746839595818206e-06, "loss": 3.2446, "step": 241500 }, { "epoch": 2.64, "learning_rate": 9.746292813087792e-06, "loss": 3.2426, "step": 242000 }, { "epoch": 2.65, "learning_rate": 9.745746030357378e-06, "loss": 3.2456, "step": 242500 }, { "epoch": 2.65, "learning_rate": 9.745199247626963e-06, "loss": 3.2345, "step": 243000 }, { "epoch": 2.66, "learning_rate": 9.74465246489655e-06, "loss": 3.2275, "step": 243500 }, { "epoch": 2.67, "learning_rate": 9.744105682166135e-06, "loss": 3.2308, "step": 244000 }, { "epoch": 2.67, "learning_rate": 9.74355889943572e-06, "loss": 3.2321, "step": 244500 }, { "epoch": 2.68, "learning_rate": 9.743012116705307e-06, "loss": 3.2252, "step": 245000 }, { "epoch": 2.68, "learning_rate": 9.742465333974892e-06, "loss": 3.2247, "step": 245500 }, { "epoch": 2.69, "learning_rate": 9.741918551244478e-06, "loss": 3.221, "step": 246000 }, { "epoch": 2.69, "learning_rate": 9.741371768514064e-06, "loss": 3.2136, "step": 246500 }, { "epoch": 2.7, "learning_rate": 9.74082498578365e-06, "loss": 3.2123, "step": 247000 }, { "epoch": 2.7, "learning_rate": 9.740278203053236e-06, "loss": 3.2046, "step": 247500 }, { "epoch": 2.71, "learning_rate": 9.739731420322821e-06, "loss": 3.2027, "step": 248000 }, { "epoch": 2.71, "learning_rate": 9.739184637592407e-06, "loss": 3.198, "step": 248500 }, { "epoch": 2.72, "learning_rate": 9.738637854861993e-06, "loss": 3.1987, "step": 249000 }, { "epoch": 2.73, "learning_rate": 9.738091072131579e-06, "loss": 3.1978, "step": 249500 }, { "epoch": 2.73, "learning_rate": 9.737544289401165e-06, "loss": 3.1874, "step": 250000 }, { "epoch": 2.74, "learning_rate": 9.73699750667075e-06, "loss": 3.1871, "step": 250500 }, { "epoch": 2.74, "learning_rate": 9.736450723940336e-06, "loss": 3.1793, "step": 251000 }, { "epoch": 2.75, "learning_rate": 9.735903941209922e-06, "loss": 3.1834, "step": 251500 }, { "epoch": 2.75, "learning_rate": 9.735357158479508e-06, "loss": 3.1776, "step": 252000 }, { "epoch": 2.76, "learning_rate": 9.734810375749093e-06, "loss": 3.1715, "step": 252500 }, { "epoch": 2.76, "learning_rate": 9.73426359301868e-06, "loss": 3.1676, "step": 253000 }, { "epoch": 2.77, "learning_rate": 9.733716810288265e-06, "loss": 3.1667, "step": 253500 }, { "epoch": 2.77, "learning_rate": 9.73317002755785e-06, "loss": 3.1695, "step": 254000 }, { "epoch": 2.78, "learning_rate": 9.732623244827437e-06, "loss": 3.164, "step": 254500 }, { "epoch": 2.79, "learning_rate": 9.732076462097022e-06, "loss": 3.1557, "step": 255000 }, { "epoch": 2.79, "learning_rate": 9.731529679366608e-06, "loss": 3.1561, "step": 255500 }, { "epoch": 2.8, "learning_rate": 9.730982896636192e-06, "loss": 3.1536, "step": 256000 }, { "epoch": 2.8, "learning_rate": 9.73043611390578e-06, "loss": 3.1505, "step": 256500 }, { "epoch": 2.81, "learning_rate": 9.729889331175366e-06, "loss": 3.1481, "step": 257000 }, { "epoch": 2.81, "learning_rate": 9.729342548444951e-06, "loss": 3.1386, "step": 257500 }, { "epoch": 2.82, "learning_rate": 9.728795765714536e-06, "loss": 3.1425, "step": 258000 }, { "epoch": 2.82, "learning_rate": 9.728248982984121e-06, "loss": 3.1455, "step": 258500 }, { "epoch": 2.83, "learning_rate": 9.727702200253709e-06, "loss": 3.1324, "step": 259000 }, { "epoch": 2.83, "learning_rate": 9.727155417523295e-06, "loss": 3.1355, "step": 259500 }, { "epoch": 2.84, "learning_rate": 9.726608634792879e-06, "loss": 3.1283, "step": 260000 }, { "epoch": 2.85, "learning_rate": 9.726061852062464e-06, "loss": 3.1276, "step": 260500 }, { "epoch": 2.85, "learning_rate": 9.72551506933205e-06, "loss": 3.1221, "step": 261000 }, { "epoch": 2.86, "learning_rate": 9.724968286601638e-06, "loss": 3.1231, "step": 261500 }, { "epoch": 2.86, "learning_rate": 9.724421503871224e-06, "loss": 3.122, "step": 262000 }, { "epoch": 2.87, "learning_rate": 9.723874721140808e-06, "loss": 3.1151, "step": 262500 }, { "epoch": 2.87, "learning_rate": 9.723327938410393e-06, "loss": 3.1118, "step": 263000 }, { "epoch": 2.88, "learning_rate": 9.72278115567998e-06, "loss": 3.107, "step": 263500 }, { "epoch": 2.88, "learning_rate": 9.722234372949567e-06, "loss": 3.107, "step": 264000 }, { "epoch": 2.89, "learning_rate": 9.72168759021915e-06, "loss": 3.1059, "step": 264500 }, { "epoch": 2.89, "learning_rate": 9.721140807488737e-06, "loss": 3.0991, "step": 265000 }, { "epoch": 2.9, "learning_rate": 9.720594024758322e-06, "loss": 3.0975, "step": 265500 }, { "epoch": 2.91, "learning_rate": 9.72004724202791e-06, "loss": 3.0922, "step": 266000 }, { "epoch": 2.91, "learning_rate": 9.719500459297494e-06, "loss": 3.085, "step": 266500 }, { "epoch": 2.92, "learning_rate": 9.71895367656708e-06, "loss": 3.0863, "step": 267000 }, { "epoch": 2.92, "learning_rate": 9.718406893836666e-06, "loss": 3.0894, "step": 267500 }, { "epoch": 2.93, "learning_rate": 9.717860111106251e-06, "loss": 3.083, "step": 268000 }, { "epoch": 2.93, "learning_rate": 9.717313328375837e-06, "loss": 3.0803, "step": 268500 }, { "epoch": 2.94, "learning_rate": 9.716766545645423e-06, "loss": 3.0754, "step": 269000 }, { "epoch": 2.94, "learning_rate": 9.716219762915009e-06, "loss": 3.078, "step": 269500 }, { "epoch": 2.95, "learning_rate": 9.715672980184595e-06, "loss": 3.0794, "step": 270000 }, { "epoch": 2.95, "learning_rate": 9.71512619745418e-06, "loss": 3.0722, "step": 270500 }, { "epoch": 2.96, "learning_rate": 9.714579414723766e-06, "loss": 3.0665, "step": 271000 }, { "epoch": 2.97, "learning_rate": 9.714032631993352e-06, "loss": 3.0688, "step": 271500 }, { "epoch": 2.97, "learning_rate": 9.713485849262938e-06, "loss": 3.0578, "step": 272000 }, { "epoch": 2.98, "learning_rate": 9.712939066532524e-06, "loss": 3.0648, "step": 272500 }, { "epoch": 2.98, "learning_rate": 9.71239228380211e-06, "loss": 3.0561, "step": 273000 }, { "epoch": 2.99, "learning_rate": 9.711845501071695e-06, "loss": 3.0573, "step": 273500 }, { "epoch": 2.99, "learning_rate": 9.711298718341281e-06, "loss": 3.0597, "step": 274000 }, { "epoch": 3.0, "learning_rate": 9.710751935610867e-06, "loss": 3.0464, "step": 274500 }, { "epoch": 3.0, "learning_rate": 9.710205152880452e-06, "loss": 3.0488, "step": 275000 }, { "epoch": 3.01, "learning_rate": 9.709658370150038e-06, "loss": 3.0518, "step": 275500 }, { "epoch": 3.01, "learning_rate": 9.709111587419624e-06, "loss": 3.0415, "step": 276000 }, { "epoch": 3.02, "learning_rate": 9.70856480468921e-06, "loss": 3.0393, "step": 276500 }, { "epoch": 3.03, "learning_rate": 9.708018021958796e-06, "loss": 3.0366, "step": 277000 }, { "epoch": 3.03, "learning_rate": 9.707471239228381e-06, "loss": 3.0453, "step": 277500 }, { "epoch": 3.04, "learning_rate": 9.706924456497967e-06, "loss": 3.0335, "step": 278000 }, { "epoch": 3.04, "learning_rate": 9.706377673767553e-06, "loss": 3.0391, "step": 278500 }, { "epoch": 3.05, "learning_rate": 9.705830891037137e-06, "loss": 3.0254, "step": 279000 }, { "epoch": 3.05, "learning_rate": 9.705284108306725e-06, "loss": 3.0255, "step": 279500 }, { "epoch": 3.06, "learning_rate": 9.70473732557631e-06, "loss": 3.0244, "step": 280000 }, { "epoch": 3.06, "learning_rate": 9.704190542845896e-06, "loss": 3.0236, "step": 280500 }, { "epoch": 3.07, "learning_rate": 9.70364376011548e-06, "loss": 3.0197, "step": 281000 }, { "epoch": 3.08, "learning_rate": 9.703096977385068e-06, "loss": 3.02, "step": 281500 }, { "epoch": 3.08, "learning_rate": 9.702550194654654e-06, "loss": 3.018, "step": 282000 }, { "epoch": 3.09, "learning_rate": 9.70200341192424e-06, "loss": 3.0072, "step": 282500 }, { "epoch": 3.09, "learning_rate": 9.701456629193823e-06, "loss": 3.0099, "step": 283000 }, { "epoch": 3.1, "learning_rate": 9.70090984646341e-06, "loss": 3.0113, "step": 283500 }, { "epoch": 3.1, "learning_rate": 9.700363063732997e-06, "loss": 3.0024, "step": 284000 }, { "epoch": 3.11, "learning_rate": 9.699816281002583e-06, "loss": 3.0053, "step": 284500 }, { "epoch": 3.11, "learning_rate": 9.699269498272167e-06, "loss": 3.0021, "step": 285000 }, { "epoch": 3.12, "learning_rate": 9.698722715541752e-06, "loss": 3.0013, "step": 285500 }, { "epoch": 3.12, "learning_rate": 9.698175932811338e-06, "loss": 2.9937, "step": 286000 }, { "epoch": 3.13, "learning_rate": 9.697629150080926e-06, "loss": 2.9957, "step": 286500 }, { "epoch": 3.14, "learning_rate": 9.69708236735051e-06, "loss": 2.9905, "step": 287000 }, { "epoch": 3.14, "learning_rate": 9.696535584620096e-06, "loss": 2.9906, "step": 287500 }, { "epoch": 3.15, "learning_rate": 9.695988801889681e-06, "loss": 2.9886, "step": 288000 }, { "epoch": 3.15, "learning_rate": 9.695442019159267e-06, "loss": 2.9872, "step": 288500 }, { "epoch": 3.16, "learning_rate": 9.694895236428853e-06, "loss": 2.9837, "step": 289000 }, { "epoch": 3.16, "learning_rate": 9.694348453698439e-06, "loss": 2.986, "step": 289500 }, { "epoch": 3.17, "learning_rate": 9.693801670968025e-06, "loss": 2.9816, "step": 290000 }, { "epoch": 3.17, "learning_rate": 9.69325488823761e-06, "loss": 2.974, "step": 290500 }, { "epoch": 3.18, "learning_rate": 9.692708105507196e-06, "loss": 2.984, "step": 291000 }, { "epoch": 3.18, "learning_rate": 9.692161322776782e-06, "loss": 2.9765, "step": 291500 }, { "epoch": 3.19, "learning_rate": 9.691614540046368e-06, "loss": 2.9745, "step": 292000 }, { "epoch": 3.2, "learning_rate": 9.691067757315954e-06, "loss": 2.972, "step": 292500 }, { "epoch": 3.2, "learning_rate": 9.69052097458554e-06, "loss": 2.9698, "step": 293000 }, { "epoch": 3.21, "learning_rate": 9.689974191855125e-06, "loss": 2.9652, "step": 293500 }, { "epoch": 3.21, "learning_rate": 9.689427409124711e-06, "loss": 2.966, "step": 294000 }, { "epoch": 3.22, "learning_rate": 9.688880626394297e-06, "loss": 2.9612, "step": 294500 }, { "epoch": 3.22, "learning_rate": 9.688333843663883e-06, "loss": 2.9603, "step": 295000 }, { "epoch": 3.23, "learning_rate": 9.687787060933468e-06, "loss": 2.954, "step": 295500 }, { "epoch": 3.23, "learning_rate": 9.687240278203054e-06, "loss": 2.9559, "step": 296000 }, { "epoch": 3.24, "learning_rate": 9.68669349547264e-06, "loss": 2.959, "step": 296500 }, { "epoch": 3.24, "learning_rate": 9.686146712742226e-06, "loss": 2.9559, "step": 297000 }, { "epoch": 3.25, "learning_rate": 9.685599930011811e-06, "loss": 2.9496, "step": 297500 }, { "epoch": 3.26, "learning_rate": 9.685053147281397e-06, "loss": 2.9504, "step": 298000 }, { "epoch": 3.26, "learning_rate": 9.684506364550983e-06, "loss": 2.9536, "step": 298500 }, { "epoch": 3.27, "learning_rate": 9.683959581820569e-06, "loss": 2.9454, "step": 299000 }, { "epoch": 3.27, "learning_rate": 9.683412799090155e-06, "loss": 2.943, "step": 299500 }, { "epoch": 3.28, "learning_rate": 9.68286601635974e-06, "loss": 2.9354, "step": 300000 }, { "epoch": 3.28, "learning_rate": 9.682319233629326e-06, "loss": 2.9377, "step": 300500 }, { "epoch": 3.29, "learning_rate": 9.681772450898912e-06, "loss": 2.9418, "step": 301000 }, { "epoch": 3.29, "learning_rate": 9.681225668168496e-06, "loss": 2.9379, "step": 301500 }, { "epoch": 3.3, "learning_rate": 9.680678885438084e-06, "loss": 2.9308, "step": 302000 }, { "epoch": 3.3, "learning_rate": 9.68013210270767e-06, "loss": 2.9352, "step": 302500 }, { "epoch": 3.31, "learning_rate": 9.679585319977255e-06, "loss": 2.9296, "step": 303000 }, { "epoch": 3.32, "learning_rate": 9.67903853724684e-06, "loss": 2.9307, "step": 303500 }, { "epoch": 3.32, "learning_rate": 9.678491754516425e-06, "loss": 2.9244, "step": 304000 }, { "epoch": 3.33, "learning_rate": 9.677944971786013e-06, "loss": 2.9184, "step": 304500 }, { "epoch": 3.33, "learning_rate": 9.677398189055598e-06, "loss": 2.9236, "step": 305000 }, { "epoch": 3.34, "learning_rate": 9.676851406325184e-06, "loss": 2.9218, "step": 305500 }, { "epoch": 3.34, "learning_rate": 9.676304623594768e-06, "loss": 2.9188, "step": 306000 }, { "epoch": 3.35, "learning_rate": 9.675757840864354e-06, "loss": 2.9212, "step": 306500 }, { "epoch": 3.35, "learning_rate": 9.675211058133942e-06, "loss": 2.9109, "step": 307000 }, { "epoch": 3.36, "learning_rate": 9.674664275403527e-06, "loss": 2.9138, "step": 307500 }, { "epoch": 3.36, "learning_rate": 9.674117492673111e-06, "loss": 2.9076, "step": 308000 }, { "epoch": 3.37, "learning_rate": 9.673570709942697e-06, "loss": 2.91, "step": 308500 }, { "epoch": 3.38, "learning_rate": 9.673023927212285e-06, "loss": 2.9044, "step": 309000 }, { "epoch": 3.38, "step": 309276, "total_flos": 2.1777712513705574e+18, "train_loss": 4.827055456554494, "train_runtime": 197999.4407, "train_samples_per_second": 2958.977, "train_steps_per_second": 46.234 } ], "logging_steps": 500, "max_steps": 9154400, "num_train_epochs": 100, "save_steps": 1000000, "total_flos": 2.1777712513705574e+18, "trial_name": null, "trial_params": null }