{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.49847046802871836, "global_step": 803500, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 1.9997932086836637e-05, "loss": 1.8211, "step": 500 }, { "epoch": 0.0, "learning_rate": 1.9995864173673275e-05, "loss": 1.8484, "step": 1000 }, { "epoch": 0.0, "learning_rate": 1.9993796260509913e-05, "loss": 1.832, "step": 1500 }, { "epoch": 0.0, "learning_rate": 1.9991728347346548e-05, "loss": 1.8583, "step": 2000 }, { "epoch": 0.0, "learning_rate": 1.9989660434183183e-05, "loss": 1.8529, "step": 2500 }, { "epoch": 0.0, "learning_rate": 1.998759252101982e-05, "loss": 1.8312, "step": 3000 }, { "epoch": 0.0, "learning_rate": 1.998552460785646e-05, "loss": 1.8302, "step": 3500 }, { "epoch": 0.0, "learning_rate": 1.9983456694693095e-05, "loss": 1.8357, "step": 4000 }, { "epoch": 0.0, "learning_rate": 1.998138878152973e-05, "loss": 1.8555, "step": 4500 }, { "epoch": 0.0, "learning_rate": 1.9979320868366368e-05, "loss": 1.8106, "step": 5000 }, { "epoch": 0.0, "learning_rate": 1.9977252955203007e-05, "loss": 1.7992, "step": 5500 }, { "epoch": 0.0, "learning_rate": 1.997518504203964e-05, "loss": 1.8011, "step": 6000 }, { "epoch": 0.0, "learning_rate": 1.997311712887628e-05, "loss": 1.8131, "step": 6500 }, { "epoch": 0.0, "learning_rate": 1.9971049215712918e-05, "loss": 1.8333, "step": 7000 }, { "epoch": 0.0, "learning_rate": 1.9968981302549553e-05, "loss": 1.8279, "step": 7500 }, { "epoch": 0.0, "learning_rate": 1.9966913389386188e-05, "loss": 1.8247, "step": 8000 }, { "epoch": 0.01, "learning_rate": 1.9964845476222826e-05, "loss": 1.7957, "step": 8500 }, { "epoch": 0.01, "learning_rate": 1.9962777563059465e-05, "loss": 1.8243, "step": 9000 }, { "epoch": 0.01, "learning_rate": 1.99607096498961e-05, "loss": 1.7959, "step": 9500 }, { "epoch": 0.01, "learning_rate": 1.9958641736732735e-05, "loss": 1.8339, "step": 10000 }, { "epoch": 0.01, "learning_rate": 1.9956573823569373e-05, "loss": 1.8002, "step": 10500 }, { "epoch": 0.01, "learning_rate": 1.995450591040601e-05, "loss": 1.8096, "step": 11000 }, { "epoch": 0.01, "learning_rate": 1.9952437997242646e-05, "loss": 1.7897, "step": 11500 }, { "epoch": 0.01, "learning_rate": 1.995037008407928e-05, "loss": 1.7928, "step": 12000 }, { "epoch": 0.01, "learning_rate": 1.994830217091592e-05, "loss": 1.788, "step": 12500 }, { "epoch": 0.01, "learning_rate": 1.9946234257752558e-05, "loss": 1.776, "step": 13000 }, { "epoch": 0.01, "learning_rate": 1.9944166344589193e-05, "loss": 1.7895, "step": 13500 }, { "epoch": 0.01, "learning_rate": 1.9942098431425828e-05, "loss": 1.7952, "step": 14000 }, { "epoch": 0.01, "learning_rate": 1.9940030518262466e-05, "loss": 1.8282, "step": 14500 }, { "epoch": 0.01, "learning_rate": 1.9937962605099105e-05, "loss": 1.7913, "step": 15000 }, { "epoch": 0.01, "learning_rate": 1.993589469193574e-05, "loss": 1.7591, "step": 15500 }, { "epoch": 0.01, "learning_rate": 1.9933826778772375e-05, "loss": 1.7948, "step": 16000 }, { "epoch": 0.01, "learning_rate": 1.9931758865609013e-05, "loss": 1.8091, "step": 16500 }, { "epoch": 0.01, "learning_rate": 1.992969095244565e-05, "loss": 1.7862, "step": 17000 }, { "epoch": 0.01, "learning_rate": 1.9927623039282286e-05, "loss": 1.8192, "step": 17500 }, { "epoch": 0.01, "learning_rate": 1.992555512611892e-05, "loss": 1.8088, "step": 18000 }, { "epoch": 0.01, "learning_rate": 1.992348721295556e-05, "loss": 1.7959, "step": 18500 }, { "epoch": 0.01, "learning_rate": 1.9921419299792198e-05, "loss": 1.803, "step": 19000 }, { "epoch": 0.01, "learning_rate": 1.9919351386628833e-05, "loss": 1.7873, "step": 19500 }, { "epoch": 0.01, "learning_rate": 1.991728347346547e-05, "loss": 1.7821, "step": 20000 }, { "epoch": 0.01, "learning_rate": 1.991521556030211e-05, "loss": 1.7863, "step": 20500 }, { "epoch": 0.01, "learning_rate": 1.9913147647138745e-05, "loss": 1.8086, "step": 21000 }, { "epoch": 0.01, "learning_rate": 1.991107973397538e-05, "loss": 1.7648, "step": 21500 }, { "epoch": 0.01, "learning_rate": 1.9909011820812018e-05, "loss": 1.774, "step": 22000 }, { "epoch": 0.01, "learning_rate": 1.9906943907648656e-05, "loss": 1.8018, "step": 22500 }, { "epoch": 0.01, "learning_rate": 1.990487599448529e-05, "loss": 1.7961, "step": 23000 }, { "epoch": 0.01, "learning_rate": 1.9902808081321926e-05, "loss": 1.7624, "step": 23500 }, { "epoch": 0.01, "learning_rate": 1.9900740168158564e-05, "loss": 1.7494, "step": 24000 }, { "epoch": 0.02, "learning_rate": 1.9898672254995203e-05, "loss": 1.7513, "step": 24500 }, { "epoch": 0.02, "learning_rate": 1.9896604341831838e-05, "loss": 1.7641, "step": 25000 }, { "epoch": 0.02, "learning_rate": 1.9894536428668473e-05, "loss": 1.7823, "step": 25500 }, { "epoch": 0.02, "learning_rate": 1.989246851550511e-05, "loss": 1.7488, "step": 26000 }, { "epoch": 0.02, "learning_rate": 1.989040060234175e-05, "loss": 1.7275, "step": 26500 }, { "epoch": 0.02, "learning_rate": 1.9888332689178384e-05, "loss": 1.78, "step": 27000 }, { "epoch": 0.02, "learning_rate": 1.988626477601502e-05, "loss": 1.7703, "step": 27500 }, { "epoch": 0.02, "learning_rate": 1.9884196862851658e-05, "loss": 1.759, "step": 28000 }, { "epoch": 0.02, "learning_rate": 1.9882128949688296e-05, "loss": 1.7876, "step": 28500 }, { "epoch": 0.02, "learning_rate": 1.988006103652493e-05, "loss": 1.7472, "step": 29000 }, { "epoch": 0.02, "learning_rate": 1.9877993123361566e-05, "loss": 1.786, "step": 29500 }, { "epoch": 0.02, "learning_rate": 1.9875925210198204e-05, "loss": 1.7707, "step": 30000 }, { "epoch": 0.02, "learning_rate": 1.9873857297034843e-05, "loss": 1.749, "step": 30500 }, { "epoch": 0.02, "learning_rate": 1.9871789383871478e-05, "loss": 1.7522, "step": 31000 }, { "epoch": 0.02, "learning_rate": 1.9869721470708113e-05, "loss": 1.7915, "step": 31500 }, { "epoch": 0.02, "learning_rate": 1.9867653557544754e-05, "loss": 1.7413, "step": 32000 }, { "epoch": 0.02, "learning_rate": 1.986558564438139e-05, "loss": 1.735, "step": 32500 }, { "epoch": 0.02, "learning_rate": 1.9863517731218024e-05, "loss": 1.7725, "step": 33000 }, { "epoch": 0.02, "learning_rate": 1.9861449818054663e-05, "loss": 1.79, "step": 33500 }, { "epoch": 0.02, "learning_rate": 1.98593819048913e-05, "loss": 1.7809, "step": 34000 }, { "epoch": 0.02, "learning_rate": 1.9857313991727936e-05, "loss": 1.7557, "step": 34500 }, { "epoch": 0.02, "learning_rate": 1.985524607856457e-05, "loss": 1.7474, "step": 35000 }, { "epoch": 0.02, "learning_rate": 1.985317816540121e-05, "loss": 1.7717, "step": 35500 }, { "epoch": 0.02, "learning_rate": 1.9851110252237848e-05, "loss": 1.761, "step": 36000 }, { "epoch": 0.02, "learning_rate": 1.9849042339074483e-05, "loss": 1.763, "step": 36500 }, { "epoch": 0.02, "learning_rate": 1.9846974425911118e-05, "loss": 1.7306, "step": 37000 }, { "epoch": 0.02, "learning_rate": 1.9844906512747756e-05, "loss": 1.7409, "step": 37500 }, { "epoch": 0.02, "learning_rate": 1.9842838599584394e-05, "loss": 1.7731, "step": 38000 }, { "epoch": 0.02, "learning_rate": 1.984077068642103e-05, "loss": 1.782, "step": 38500 }, { "epoch": 0.02, "learning_rate": 1.9838702773257664e-05, "loss": 1.7416, "step": 39000 }, { "epoch": 0.02, "learning_rate": 1.9836634860094302e-05, "loss": 1.7537, "step": 39500 }, { "epoch": 0.02, "learning_rate": 1.983456694693094e-05, "loss": 1.7449, "step": 40000 }, { "epoch": 0.03, "learning_rate": 1.9832499033767576e-05, "loss": 1.7629, "step": 40500 }, { "epoch": 0.03, "learning_rate": 1.983043112060421e-05, "loss": 1.7539, "step": 41000 }, { "epoch": 0.03, "learning_rate": 1.982836320744085e-05, "loss": 1.7311, "step": 41500 }, { "epoch": 0.03, "learning_rate": 1.9826295294277487e-05, "loss": 1.7415, "step": 42000 }, { "epoch": 0.03, "learning_rate": 1.9824227381114122e-05, "loss": 1.7529, "step": 42500 }, { "epoch": 0.03, "learning_rate": 1.9822159467950757e-05, "loss": 1.7372, "step": 43000 }, { "epoch": 0.03, "learning_rate": 1.9820091554787396e-05, "loss": 1.7288, "step": 43500 }, { "epoch": 0.03, "learning_rate": 1.9818023641624034e-05, "loss": 1.7581, "step": 44000 }, { "epoch": 0.03, "learning_rate": 1.981595572846067e-05, "loss": 1.7325, "step": 44500 }, { "epoch": 0.03, "learning_rate": 1.9813887815297307e-05, "loss": 1.7552, "step": 45000 }, { "epoch": 0.03, "learning_rate": 1.9811819902133946e-05, "loss": 1.7689, "step": 45500 }, { "epoch": 0.03, "learning_rate": 1.980975198897058e-05, "loss": 1.7547, "step": 46000 }, { "epoch": 0.03, "learning_rate": 1.9807684075807216e-05, "loss": 1.7676, "step": 46500 }, { "epoch": 0.03, "learning_rate": 1.9805616162643854e-05, "loss": 1.7406, "step": 47000 }, { "epoch": 0.03, "learning_rate": 1.9803548249480492e-05, "loss": 1.7515, "step": 47500 }, { "epoch": 0.03, "learning_rate": 1.9801480336317127e-05, "loss": 1.7379, "step": 48000 }, { "epoch": 0.03, "learning_rate": 1.9799412423153762e-05, "loss": 1.7673, "step": 48500 }, { "epoch": 0.03, "learning_rate": 1.97973445099904e-05, "loss": 1.7142, "step": 49000 }, { "epoch": 0.03, "learning_rate": 1.979527659682704e-05, "loss": 1.7152, "step": 49500 }, { "epoch": 0.03, "learning_rate": 1.9793208683663674e-05, "loss": 1.7406, "step": 50000 }, { "epoch": 0.03, "learning_rate": 1.979114077050031e-05, "loss": 1.752, "step": 50500 }, { "epoch": 0.03, "learning_rate": 1.9789072857336947e-05, "loss": 1.7744, "step": 51000 }, { "epoch": 0.03, "learning_rate": 1.9787004944173586e-05, "loss": 1.754, "step": 51500 }, { "epoch": 0.03, "learning_rate": 1.978493703101022e-05, "loss": 1.7402, "step": 52000 }, { "epoch": 0.03, "learning_rate": 1.9782869117846856e-05, "loss": 1.7219, "step": 52500 }, { "epoch": 0.03, "learning_rate": 1.9780801204683494e-05, "loss": 1.7076, "step": 53000 }, { "epoch": 0.03, "learning_rate": 1.9778733291520132e-05, "loss": 1.7554, "step": 53500 }, { "epoch": 0.03, "learning_rate": 1.9776665378356767e-05, "loss": 1.7478, "step": 54000 }, { "epoch": 0.03, "learning_rate": 1.9774597465193402e-05, "loss": 1.7663, "step": 54500 }, { "epoch": 0.03, "learning_rate": 1.977252955203004e-05, "loss": 1.753, "step": 55000 }, { "epoch": 0.03, "learning_rate": 1.977046163886668e-05, "loss": 1.7328, "step": 55500 }, { "epoch": 0.03, "learning_rate": 1.9768393725703314e-05, "loss": 1.7462, "step": 56000 }, { "epoch": 0.04, "learning_rate": 1.976632581253995e-05, "loss": 1.7636, "step": 56500 }, { "epoch": 0.04, "learning_rate": 1.9764257899376587e-05, "loss": 1.7446, "step": 57000 }, { "epoch": 0.04, "learning_rate": 1.9762189986213225e-05, "loss": 1.7484, "step": 57500 }, { "epoch": 0.04, "learning_rate": 1.976012207304986e-05, "loss": 1.7466, "step": 58000 }, { "epoch": 0.04, "learning_rate": 1.97580541598865e-05, "loss": 1.7511, "step": 58500 }, { "epoch": 0.04, "learning_rate": 1.9755986246723137e-05, "loss": 1.7163, "step": 59000 }, { "epoch": 0.04, "learning_rate": 1.9753918333559772e-05, "loss": 1.7215, "step": 59500 }, { "epoch": 0.04, "learning_rate": 1.9751850420396407e-05, "loss": 1.7513, "step": 60000 }, { "epoch": 0.04, "learning_rate": 1.9749782507233045e-05, "loss": 1.7199, "step": 60500 }, { "epoch": 0.04, "learning_rate": 1.9747714594069684e-05, "loss": 1.7385, "step": 61000 }, { "epoch": 0.04, "learning_rate": 1.974564668090632e-05, "loss": 1.7485, "step": 61500 }, { "epoch": 0.04, "learning_rate": 1.9743578767742954e-05, "loss": 1.7382, "step": 62000 }, { "epoch": 0.04, "learning_rate": 1.9741510854579592e-05, "loss": 1.7108, "step": 62500 }, { "epoch": 0.04, "learning_rate": 1.973944294141623e-05, "loss": 1.7437, "step": 63000 }, { "epoch": 0.04, "learning_rate": 1.9737375028252865e-05, "loss": 1.7325, "step": 63500 }, { "epoch": 0.04, "learning_rate": 1.97353071150895e-05, "loss": 1.775, "step": 64000 }, { "epoch": 0.04, "learning_rate": 1.973323920192614e-05, "loss": 1.7149, "step": 64500 }, { "epoch": 0.04, "learning_rate": 1.9731171288762777e-05, "loss": 1.7412, "step": 65000 }, { "epoch": 0.04, "learning_rate": 1.9729103375599412e-05, "loss": 1.7411, "step": 65500 }, { "epoch": 0.04, "learning_rate": 1.9727035462436047e-05, "loss": 1.716, "step": 66000 }, { "epoch": 0.04, "learning_rate": 1.9724967549272685e-05, "loss": 1.722, "step": 66500 }, { "epoch": 0.04, "learning_rate": 1.9722899636109324e-05, "loss": 1.7307, "step": 67000 }, { "epoch": 0.04, "learning_rate": 1.972083172294596e-05, "loss": 1.7038, "step": 67500 }, { "epoch": 0.04, "learning_rate": 1.9718763809782594e-05, "loss": 1.7468, "step": 68000 }, { "epoch": 0.04, "learning_rate": 1.9716695896619232e-05, "loss": 1.7389, "step": 68500 }, { "epoch": 0.04, "learning_rate": 1.971462798345587e-05, "loss": 1.7329, "step": 69000 }, { "epoch": 0.04, "learning_rate": 1.9712560070292505e-05, "loss": 1.7209, "step": 69500 }, { "epoch": 0.04, "learning_rate": 1.9710492157129144e-05, "loss": 1.715, "step": 70000 }, { "epoch": 0.04, "learning_rate": 1.9708424243965782e-05, "loss": 1.7383, "step": 70500 }, { "epoch": 0.04, "learning_rate": 1.9706356330802417e-05, "loss": 1.7256, "step": 71000 }, { "epoch": 0.04, "learning_rate": 1.9704288417639052e-05, "loss": 1.7646, "step": 71500 }, { "epoch": 0.04, "learning_rate": 1.970222050447569e-05, "loss": 1.7673, "step": 72000 }, { "epoch": 0.04, "learning_rate": 1.970015259131233e-05, "loss": 1.7027, "step": 72500 }, { "epoch": 0.05, "learning_rate": 1.9698084678148963e-05, "loss": 1.7549, "step": 73000 }, { "epoch": 0.05, "learning_rate": 1.96960167649856e-05, "loss": 1.7388, "step": 73500 }, { "epoch": 0.05, "learning_rate": 1.9693948851822237e-05, "loss": 1.7039, "step": 74000 }, { "epoch": 0.05, "learning_rate": 1.9691880938658875e-05, "loss": 1.7451, "step": 74500 }, { "epoch": 0.05, "learning_rate": 1.968981302549551e-05, "loss": 1.7338, "step": 75000 }, { "epoch": 0.05, "learning_rate": 1.9687745112332145e-05, "loss": 1.7265, "step": 75500 }, { "epoch": 0.05, "learning_rate": 1.9685677199168783e-05, "loss": 1.7263, "step": 76000 }, { "epoch": 0.05, "learning_rate": 1.9683609286005422e-05, "loss": 1.7253, "step": 76500 }, { "epoch": 0.05, "learning_rate": 1.9681541372842057e-05, "loss": 1.728, "step": 77000 }, { "epoch": 0.05, "learning_rate": 1.967947345967869e-05, "loss": 1.7316, "step": 77500 }, { "epoch": 0.05, "learning_rate": 1.967740554651533e-05, "loss": 1.7585, "step": 78000 }, { "epoch": 0.05, "learning_rate": 1.967533763335197e-05, "loss": 1.7129, "step": 78500 }, { "epoch": 0.05, "learning_rate": 1.9673269720188603e-05, "loss": 1.7137, "step": 79000 }, { "epoch": 0.05, "learning_rate": 1.9671201807025238e-05, "loss": 1.7334, "step": 79500 }, { "epoch": 0.05, "learning_rate": 1.9669133893861877e-05, "loss": 1.7323, "step": 80000 }, { "epoch": 0.05, "learning_rate": 1.9667065980698515e-05, "loss": 1.7381, "step": 80500 }, { "epoch": 0.05, "learning_rate": 1.966499806753515e-05, "loss": 1.722, "step": 81000 }, { "epoch": 0.05, "learning_rate": 1.9662930154371785e-05, "loss": 1.7139, "step": 81500 }, { "epoch": 0.05, "learning_rate": 1.9660862241208423e-05, "loss": 1.7404, "step": 82000 }, { "epoch": 0.05, "learning_rate": 1.965879432804506e-05, "loss": 1.7501, "step": 82500 }, { "epoch": 0.05, "learning_rate": 1.9656726414881697e-05, "loss": 1.7188, "step": 83000 }, { "epoch": 0.05, "learning_rate": 1.9654658501718335e-05, "loss": 1.7154, "step": 83500 }, { "epoch": 0.05, "learning_rate": 1.9652590588554973e-05, "loss": 1.7433, "step": 84000 }, { "epoch": 0.05, "learning_rate": 1.9650522675391608e-05, "loss": 1.6987, "step": 84500 }, { "epoch": 0.05, "learning_rate": 1.9648454762228243e-05, "loss": 1.7371, "step": 85000 }, { "epoch": 0.05, "learning_rate": 1.964638684906488e-05, "loss": 1.7143, "step": 85500 }, { "epoch": 0.05, "learning_rate": 1.964431893590152e-05, "loss": 1.7327, "step": 86000 }, { "epoch": 0.05, "learning_rate": 1.9642251022738155e-05, "loss": 1.7334, "step": 86500 }, { "epoch": 0.05, "learning_rate": 1.964018310957479e-05, "loss": 1.7079, "step": 87000 }, { "epoch": 0.05, "learning_rate": 1.9638115196411428e-05, "loss": 1.7426, "step": 87500 }, { "epoch": 0.05, "learning_rate": 1.9636047283248067e-05, "loss": 1.7066, "step": 88000 }, { "epoch": 0.05, "learning_rate": 1.96339793700847e-05, "loss": 1.7613, "step": 88500 }, { "epoch": 0.06, "learning_rate": 1.9631911456921336e-05, "loss": 1.7257, "step": 89000 }, { "epoch": 0.06, "learning_rate": 1.9629843543757975e-05, "loss": 1.7413, "step": 89500 }, { "epoch": 0.06, "learning_rate": 1.9627775630594613e-05, "loss": 1.7053, "step": 90000 }, { "epoch": 0.06, "learning_rate": 1.9625707717431248e-05, "loss": 1.7156, "step": 90500 }, { "epoch": 0.06, "learning_rate": 1.9623639804267883e-05, "loss": 1.7176, "step": 91000 }, { "epoch": 0.06, "learning_rate": 1.962157189110452e-05, "loss": 1.7132, "step": 91500 }, { "epoch": 0.06, "learning_rate": 1.961950397794116e-05, "loss": 1.7286, "step": 92000 }, { "epoch": 0.06, "learning_rate": 1.9617436064777795e-05, "loss": 1.7361, "step": 92500 }, { "epoch": 0.06, "learning_rate": 1.961536815161443e-05, "loss": 1.7267, "step": 93000 }, { "epoch": 0.06, "learning_rate": 1.9613300238451068e-05, "loss": 1.7048, "step": 93500 }, { "epoch": 0.06, "learning_rate": 1.9611232325287706e-05, "loss": 1.7163, "step": 94000 }, { "epoch": 0.06, "learning_rate": 1.960916441212434e-05, "loss": 1.7627, "step": 94500 }, { "epoch": 0.06, "learning_rate": 1.9607096498960976e-05, "loss": 1.7167, "step": 95000 }, { "epoch": 0.06, "learning_rate": 1.9605028585797618e-05, "loss": 1.7274, "step": 95500 }, { "epoch": 0.06, "learning_rate": 1.9602960672634253e-05, "loss": 1.7079, "step": 96000 }, { "epoch": 0.06, "learning_rate": 1.9600892759470888e-05, "loss": 1.7104, "step": 96500 }, { "epoch": 0.06, "learning_rate": 1.9598824846307526e-05, "loss": 1.7126, "step": 97000 }, { "epoch": 0.06, "learning_rate": 1.9596756933144165e-05, "loss": 1.7055, "step": 97500 }, { "epoch": 0.06, "learning_rate": 1.95946890199808e-05, "loss": 1.6893, "step": 98000 }, { "epoch": 0.06, "learning_rate": 1.9592621106817435e-05, "loss": 1.7458, "step": 98500 }, { "epoch": 0.06, "learning_rate": 1.9590553193654073e-05, "loss": 1.7388, "step": 99000 }, { "epoch": 0.06, "learning_rate": 1.958848528049071e-05, "loss": 1.7242, "step": 99500 }, { "epoch": 0.06, "learning_rate": 1.9586417367327346e-05, "loss": 1.7237, "step": 100000 }, { "epoch": 0.06, "learning_rate": 1.958434945416398e-05, "loss": 1.7167, "step": 100500 }, { "epoch": 0.06, "learning_rate": 1.958228154100062e-05, "loss": 1.7259, "step": 101000 }, { "epoch": 0.06, "learning_rate": 1.9580213627837258e-05, "loss": 1.719, "step": 101500 }, { "epoch": 0.06, "learning_rate": 1.9578145714673893e-05, "loss": 1.7311, "step": 102000 }, { "epoch": 0.06, "learning_rate": 1.9576077801510528e-05, "loss": 1.6825, "step": 102500 }, { "epoch": 0.06, "learning_rate": 1.9574009888347166e-05, "loss": 1.7203, "step": 103000 }, { "epoch": 0.06, "learning_rate": 1.9571941975183805e-05, "loss": 1.7543, "step": 103500 }, { "epoch": 0.06, "learning_rate": 1.956987406202044e-05, "loss": 1.7323, "step": 104000 }, { "epoch": 0.06, "learning_rate": 1.9567806148857074e-05, "loss": 1.7179, "step": 104500 }, { "epoch": 0.07, "learning_rate": 1.9565738235693713e-05, "loss": 1.6992, "step": 105000 }, { "epoch": 0.07, "learning_rate": 1.956367032253035e-05, "loss": 1.7269, "step": 105500 }, { "epoch": 0.07, "learning_rate": 1.9561602409366986e-05, "loss": 1.7197, "step": 106000 }, { "epoch": 0.07, "learning_rate": 1.955953449620362e-05, "loss": 1.7175, "step": 106500 }, { "epoch": 0.07, "learning_rate": 1.955746658304026e-05, "loss": 1.731, "step": 107000 }, { "epoch": 0.07, "learning_rate": 1.9555398669876898e-05, "loss": 1.6981, "step": 107500 }, { "epoch": 0.07, "learning_rate": 1.9553330756713533e-05, "loss": 1.6977, "step": 108000 }, { "epoch": 0.07, "learning_rate": 1.955126284355017e-05, "loss": 1.7397, "step": 108500 }, { "epoch": 0.07, "learning_rate": 1.954919493038681e-05, "loss": 1.692, "step": 109000 }, { "epoch": 0.07, "learning_rate": 1.9547127017223444e-05, "loss": 1.7, "step": 109500 }, { "epoch": 0.07, "learning_rate": 1.954505910406008e-05, "loss": 1.733, "step": 110000 }, { "epoch": 0.07, "learning_rate": 1.9542991190896718e-05, "loss": 1.703, "step": 110500 }, { "epoch": 0.07, "learning_rate": 1.9540923277733356e-05, "loss": 1.714, "step": 111000 }, { "epoch": 0.07, "learning_rate": 1.953885536456999e-05, "loss": 1.7271, "step": 111500 }, { "epoch": 0.07, "learning_rate": 1.9536787451406626e-05, "loss": 1.7385, "step": 112000 }, { "epoch": 0.07, "learning_rate": 1.9534719538243264e-05, "loss": 1.7427, "step": 112500 }, { "epoch": 0.07, "learning_rate": 1.9532651625079903e-05, "loss": 1.7234, "step": 113000 }, { "epoch": 0.07, "learning_rate": 1.9530583711916538e-05, "loss": 1.7279, "step": 113500 }, { "epoch": 0.07, "learning_rate": 1.9528515798753173e-05, "loss": 1.6994, "step": 114000 }, { "epoch": 0.07, "learning_rate": 1.952644788558981e-05, "loss": 1.7076, "step": 114500 }, { "epoch": 0.07, "learning_rate": 1.952437997242645e-05, "loss": 1.7031, "step": 115000 }, { "epoch": 0.07, "learning_rate": 1.9522312059263084e-05, "loss": 1.7195, "step": 115500 }, { "epoch": 0.07, "learning_rate": 1.952024414609972e-05, "loss": 1.6933, "step": 116000 }, { "epoch": 0.07, "learning_rate": 1.9518176232936358e-05, "loss": 1.7005, "step": 116500 }, { "epoch": 0.07, "learning_rate": 1.9516108319772996e-05, "loss": 1.7131, "step": 117000 }, { "epoch": 0.07, "learning_rate": 1.951404040660963e-05, "loss": 1.7252, "step": 117500 }, { "epoch": 0.07, "learning_rate": 1.9511972493446266e-05, "loss": 1.7333, "step": 118000 }, { "epoch": 0.07, "learning_rate": 1.9509904580282904e-05, "loss": 1.6931, "step": 118500 }, { "epoch": 0.07, "learning_rate": 1.9507836667119543e-05, "loss": 1.7487, "step": 119000 }, { "epoch": 0.07, "learning_rate": 1.9505768753956178e-05, "loss": 1.7313, "step": 119500 }, { "epoch": 0.07, "learning_rate": 1.9503700840792812e-05, "loss": 1.6854, "step": 120000 }, { "epoch": 0.07, "learning_rate": 1.950163292762945e-05, "loss": 1.7253, "step": 120500 }, { "epoch": 0.08, "learning_rate": 1.949956501446609e-05, "loss": 1.7121, "step": 121000 }, { "epoch": 0.08, "learning_rate": 1.9497497101302724e-05, "loss": 1.7068, "step": 121500 }, { "epoch": 0.08, "learning_rate": 1.9495429188139362e-05, "loss": 1.7373, "step": 122000 }, { "epoch": 0.08, "learning_rate": 1.9493361274976e-05, "loss": 1.731, "step": 122500 }, { "epoch": 0.08, "learning_rate": 1.9491293361812636e-05, "loss": 1.6952, "step": 123000 }, { "epoch": 0.08, "learning_rate": 1.948922544864927e-05, "loss": 1.7152, "step": 123500 }, { "epoch": 0.08, "learning_rate": 1.948715753548591e-05, "loss": 1.718, "step": 124000 }, { "epoch": 0.08, "learning_rate": 1.9485089622322547e-05, "loss": 1.6984, "step": 124500 }, { "epoch": 0.08, "learning_rate": 1.9483021709159182e-05, "loss": 1.7289, "step": 125000 }, { "epoch": 0.08, "learning_rate": 1.9480953795995817e-05, "loss": 1.7152, "step": 125500 }, { "epoch": 0.08, "learning_rate": 1.9478885882832456e-05, "loss": 1.7138, "step": 126000 }, { "epoch": 0.08, "learning_rate": 1.9476817969669094e-05, "loss": 1.7083, "step": 126500 }, { "epoch": 0.08, "learning_rate": 1.947475005650573e-05, "loss": 1.7135, "step": 127000 }, { "epoch": 0.08, "learning_rate": 1.9472682143342364e-05, "loss": 1.6916, "step": 127500 }, { "epoch": 0.08, "learning_rate": 1.9470614230179002e-05, "loss": 1.7172, "step": 128000 }, { "epoch": 0.08, "learning_rate": 1.946854631701564e-05, "loss": 1.7369, "step": 128500 }, { "epoch": 0.08, "learning_rate": 1.9466478403852276e-05, "loss": 1.7164, "step": 129000 }, { "epoch": 0.08, "learning_rate": 1.946441049068891e-05, "loss": 1.7208, "step": 129500 }, { "epoch": 0.08, "learning_rate": 1.946234257752555e-05, "loss": 1.7315, "step": 130000 }, { "epoch": 0.08, "learning_rate": 1.9460274664362187e-05, "loss": 1.7234, "step": 130500 }, { "epoch": 0.08, "learning_rate": 1.9458206751198822e-05, "loss": 1.73, "step": 131000 }, { "epoch": 0.08, "learning_rate": 1.9456138838035457e-05, "loss": 1.7105, "step": 131500 }, { "epoch": 0.08, "learning_rate": 1.9454070924872096e-05, "loss": 1.7049, "step": 132000 }, { "epoch": 0.08, "learning_rate": 1.9452003011708734e-05, "loss": 1.7187, "step": 132500 }, { "epoch": 0.08, "learning_rate": 1.944993509854537e-05, "loss": 1.7466, "step": 133000 }, { "epoch": 0.08, "learning_rate": 1.9447867185382007e-05, "loss": 1.6927, "step": 133500 }, { "epoch": 0.08, "learning_rate": 1.9445799272218646e-05, "loss": 1.7113, "step": 134000 }, { "epoch": 0.08, "learning_rate": 1.944373135905528e-05, "loss": 1.7202, "step": 134500 }, { "epoch": 0.08, "learning_rate": 1.9441663445891916e-05, "loss": 1.6841, "step": 135000 }, { "epoch": 0.08, "learning_rate": 1.9439595532728554e-05, "loss": 1.7161, "step": 135500 }, { "epoch": 0.08, "learning_rate": 1.9437527619565192e-05, "loss": 1.7156, "step": 136000 }, { "epoch": 0.08, "learning_rate": 1.9435459706401827e-05, "loss": 1.7228, "step": 136500 }, { "epoch": 0.08, "learning_rate": 1.9433391793238462e-05, "loss": 1.7018, "step": 137000 }, { "epoch": 0.09, "learning_rate": 1.94313238800751e-05, "loss": 1.7207, "step": 137500 }, { "epoch": 0.09, "learning_rate": 1.942925596691174e-05, "loss": 1.7134, "step": 138000 }, { "epoch": 0.09, "learning_rate": 1.9427188053748374e-05, "loss": 1.6893, "step": 138500 }, { "epoch": 0.09, "learning_rate": 1.942512014058501e-05, "loss": 1.7211, "step": 139000 }, { "epoch": 0.09, "learning_rate": 1.9423052227421647e-05, "loss": 1.7061, "step": 139500 }, { "epoch": 0.09, "learning_rate": 1.9420984314258285e-05, "loss": 1.7193, "step": 140000 }, { "epoch": 0.09, "learning_rate": 1.941891640109492e-05, "loss": 1.706, "step": 140500 }, { "epoch": 0.09, "learning_rate": 1.9416848487931555e-05, "loss": 1.7256, "step": 141000 }, { "epoch": 0.09, "learning_rate": 1.9414780574768194e-05, "loss": 1.7544, "step": 141500 }, { "epoch": 0.09, "learning_rate": 1.9412712661604832e-05, "loss": 1.7104, "step": 142000 }, { "epoch": 0.09, "learning_rate": 1.9410644748441467e-05, "loss": 1.7459, "step": 142500 }, { "epoch": 0.09, "learning_rate": 1.9408576835278102e-05, "loss": 1.7049, "step": 143000 }, { "epoch": 0.09, "learning_rate": 1.940650892211474e-05, "loss": 1.7099, "step": 143500 }, { "epoch": 0.09, "learning_rate": 1.940444100895138e-05, "loss": 1.697, "step": 144000 }, { "epoch": 0.09, "learning_rate": 1.9402373095788014e-05, "loss": 1.6939, "step": 144500 }, { "epoch": 0.09, "learning_rate": 1.940030518262465e-05, "loss": 1.7076, "step": 145000 }, { "epoch": 0.09, "learning_rate": 1.9398237269461287e-05, "loss": 1.7028, "step": 145500 }, { "epoch": 0.09, "learning_rate": 1.9396169356297925e-05, "loss": 1.6949, "step": 146000 }, { "epoch": 0.09, "learning_rate": 1.939410144313456e-05, "loss": 1.7152, "step": 146500 }, { "epoch": 0.09, "learning_rate": 1.93920335299712e-05, "loss": 1.7053, "step": 147000 }, { "epoch": 0.09, "learning_rate": 1.9389965616807837e-05, "loss": 1.7175, "step": 147500 }, { "epoch": 0.09, "learning_rate": 1.9387897703644472e-05, "loss": 1.6896, "step": 148000 }, { "epoch": 0.09, "learning_rate": 1.9385829790481107e-05, "loss": 1.6895, "step": 148500 }, { "epoch": 0.09, "learning_rate": 1.9383761877317745e-05, "loss": 1.7108, "step": 149000 }, { "epoch": 0.09, "learning_rate": 1.9381693964154384e-05, "loss": 1.7032, "step": 149500 }, { "epoch": 0.09, "learning_rate": 1.937962605099102e-05, "loss": 1.7051, "step": 150000 }, { "epoch": 0.09, "learning_rate": 1.9377558137827654e-05, "loss": 1.7253, "step": 150500 }, { "epoch": 0.09, "learning_rate": 1.9375490224664292e-05, "loss": 1.6897, "step": 151000 }, { "epoch": 0.09, "learning_rate": 1.937342231150093e-05, "loss": 1.6875, "step": 151500 }, { "epoch": 0.09, "learning_rate": 1.9371354398337565e-05, "loss": 1.6933, "step": 152000 }, { "epoch": 0.09, "learning_rate": 1.93692864851742e-05, "loss": 1.6915, "step": 152500 }, { "epoch": 0.09, "learning_rate": 1.936721857201084e-05, "loss": 1.7162, "step": 153000 }, { "epoch": 0.1, "learning_rate": 1.9365150658847477e-05, "loss": 1.6907, "step": 153500 }, { "epoch": 0.1, "learning_rate": 1.9363082745684112e-05, "loss": 1.7201, "step": 154000 }, { "epoch": 0.1, "learning_rate": 1.9361014832520747e-05, "loss": 1.6888, "step": 154500 }, { "epoch": 0.1, "learning_rate": 1.9358946919357385e-05, "loss": 1.6645, "step": 155000 }, { "epoch": 0.1, "learning_rate": 1.9356879006194023e-05, "loss": 1.7112, "step": 155500 }, { "epoch": 0.1, "learning_rate": 1.935481109303066e-05, "loss": 1.7021, "step": 156000 }, { "epoch": 0.1, "learning_rate": 1.9352743179867293e-05, "loss": 1.6912, "step": 156500 }, { "epoch": 0.1, "learning_rate": 1.9350675266703932e-05, "loss": 1.7171, "step": 157000 }, { "epoch": 0.1, "learning_rate": 1.934860735354057e-05, "loss": 1.6884, "step": 157500 }, { "epoch": 0.1, "learning_rate": 1.9346539440377205e-05, "loss": 1.6607, "step": 158000 }, { "epoch": 0.1, "learning_rate": 1.934447152721384e-05, "loss": 1.6743, "step": 158500 }, { "epoch": 0.1, "learning_rate": 1.934240361405048e-05, "loss": 1.6976, "step": 159000 }, { "epoch": 0.1, "learning_rate": 1.9340335700887117e-05, "loss": 1.6957, "step": 159500 }, { "epoch": 0.1, "learning_rate": 1.933826778772375e-05, "loss": 1.7103, "step": 160000 }, { "epoch": 0.1, "learning_rate": 1.933619987456039e-05, "loss": 1.7008, "step": 160500 }, { "epoch": 0.1, "learning_rate": 1.933413196139703e-05, "loss": 1.7077, "step": 161000 }, { "epoch": 0.1, "learning_rate": 1.9332064048233663e-05, "loss": 1.7027, "step": 161500 }, { "epoch": 0.1, "learning_rate": 1.9329996135070298e-05, "loss": 1.7152, "step": 162000 }, { "epoch": 0.1, "learning_rate": 1.9327928221906937e-05, "loss": 1.6772, "step": 162500 }, { "epoch": 0.1, "learning_rate": 1.9325860308743575e-05, "loss": 1.6789, "step": 163000 }, { "epoch": 0.1, "learning_rate": 1.932379239558021e-05, "loss": 1.679, "step": 163500 }, { "epoch": 0.1, "learning_rate": 1.9321724482416845e-05, "loss": 1.7125, "step": 164000 }, { "epoch": 0.1, "learning_rate": 1.9319656569253483e-05, "loss": 1.7123, "step": 164500 }, { "epoch": 0.1, "learning_rate": 1.931758865609012e-05, "loss": 1.6982, "step": 165000 }, { "epoch": 0.1, "learning_rate": 1.9315520742926757e-05, "loss": 1.7348, "step": 165500 }, { "epoch": 0.1, "learning_rate": 1.931345282976339e-05, "loss": 1.6996, "step": 166000 }, { "epoch": 0.1, "learning_rate": 1.931138491660003e-05, "loss": 1.712, "step": 166500 }, { "epoch": 0.1, "learning_rate": 1.9309317003436668e-05, "loss": 1.7365, "step": 167000 }, { "epoch": 0.1, "learning_rate": 1.9307249090273303e-05, "loss": 1.7034, "step": 167500 }, { "epoch": 0.1, "learning_rate": 1.9305181177109938e-05, "loss": 1.7086, "step": 168000 }, { "epoch": 0.1, "learning_rate": 1.9303113263946577e-05, "loss": 1.6911, "step": 168500 }, { "epoch": 0.1, "learning_rate": 1.9301045350783215e-05, "loss": 1.6881, "step": 169000 }, { "epoch": 0.11, "learning_rate": 1.929897743761985e-05, "loss": 1.7006, "step": 169500 }, { "epoch": 0.11, "learning_rate": 1.9296909524456485e-05, "loss": 1.7111, "step": 170000 }, { "epoch": 0.11, "learning_rate": 1.9294841611293123e-05, "loss": 1.6961, "step": 170500 }, { "epoch": 0.11, "learning_rate": 1.929277369812976e-05, "loss": 1.7163, "step": 171000 }, { "epoch": 0.11, "learning_rate": 1.9290705784966396e-05, "loss": 1.6837, "step": 171500 }, { "epoch": 0.11, "learning_rate": 1.9288637871803035e-05, "loss": 1.6935, "step": 172000 }, { "epoch": 0.11, "learning_rate": 1.928656995863967e-05, "loss": 1.7296, "step": 172500 }, { "epoch": 0.11, "learning_rate": 1.9284502045476308e-05, "loss": 1.7189, "step": 173000 }, { "epoch": 0.11, "learning_rate": 1.9282434132312943e-05, "loss": 1.7131, "step": 173500 }, { "epoch": 0.11, "learning_rate": 1.928036621914958e-05, "loss": 1.6656, "step": 174000 }, { "epoch": 0.11, "learning_rate": 1.927829830598622e-05, "loss": 1.7097, "step": 174500 }, { "epoch": 0.11, "learning_rate": 1.9276230392822855e-05, "loss": 1.7183, "step": 175000 }, { "epoch": 0.11, "learning_rate": 1.927416247965949e-05, "loss": 1.6925, "step": 175500 }, { "epoch": 0.11, "learning_rate": 1.9272094566496128e-05, "loss": 1.7156, "step": 176000 }, { "epoch": 0.11, "learning_rate": 1.9270026653332766e-05, "loss": 1.7002, "step": 176500 }, { "epoch": 0.11, "learning_rate": 1.92679587401694e-05, "loss": 1.7181, "step": 177000 }, { "epoch": 0.11, "learning_rate": 1.9265890827006036e-05, "loss": 1.6844, "step": 177500 }, { "epoch": 0.11, "learning_rate": 1.9263822913842675e-05, "loss": 1.714, "step": 178000 }, { "epoch": 0.11, "learning_rate": 1.9261755000679313e-05, "loss": 1.6939, "step": 178500 }, { "epoch": 0.11, "learning_rate": 1.9259687087515948e-05, "loss": 1.7179, "step": 179000 }, { "epoch": 0.11, "learning_rate": 1.9257619174352583e-05, "loss": 1.6719, "step": 179500 }, { "epoch": 0.11, "learning_rate": 1.925555126118922e-05, "loss": 1.7066, "step": 180000 }, { "epoch": 0.11, "learning_rate": 1.925348334802586e-05, "loss": 1.7037, "step": 180500 }, { "epoch": 0.11, "learning_rate": 1.9251415434862495e-05, "loss": 1.7064, "step": 181000 }, { "epoch": 0.11, "learning_rate": 1.924934752169913e-05, "loss": 1.6772, "step": 181500 }, { "epoch": 0.11, "learning_rate": 1.9247279608535768e-05, "loss": 1.6937, "step": 182000 }, { "epoch": 0.11, "learning_rate": 1.9245211695372406e-05, "loss": 1.6681, "step": 182500 }, { "epoch": 0.11, "learning_rate": 1.924314378220904e-05, "loss": 1.7035, "step": 183000 }, { "epoch": 0.11, "learning_rate": 1.9241075869045676e-05, "loss": 1.7057, "step": 183500 }, { "epoch": 0.11, "learning_rate": 1.9239007955882315e-05, "loss": 1.6688, "step": 184000 }, { "epoch": 0.11, "learning_rate": 1.9236940042718953e-05, "loss": 1.6797, "step": 184500 }, { "epoch": 0.11, "learning_rate": 1.9234872129555588e-05, "loss": 1.6937, "step": 185000 }, { "epoch": 0.12, "learning_rate": 1.9232804216392226e-05, "loss": 1.7253, "step": 185500 }, { "epoch": 0.12, "learning_rate": 1.923073630322886e-05, "loss": 1.7019, "step": 186000 }, { "epoch": 0.12, "learning_rate": 1.92286683900655e-05, "loss": 1.685, "step": 186500 }, { "epoch": 0.12, "learning_rate": 1.9226600476902134e-05, "loss": 1.7247, "step": 187000 }, { "epoch": 0.12, "learning_rate": 1.9224532563738773e-05, "loss": 1.706, "step": 187500 }, { "epoch": 0.12, "learning_rate": 1.922246465057541e-05, "loss": 1.7113, "step": 188000 }, { "epoch": 0.12, "learning_rate": 1.9220396737412046e-05, "loss": 1.7225, "step": 188500 }, { "epoch": 0.12, "learning_rate": 1.921832882424868e-05, "loss": 1.6968, "step": 189000 }, { "epoch": 0.12, "learning_rate": 1.921626091108532e-05, "loss": 1.6904, "step": 189500 }, { "epoch": 0.12, "learning_rate": 1.9214192997921958e-05, "loss": 1.6812, "step": 190000 }, { "epoch": 0.12, "learning_rate": 1.9212125084758593e-05, "loss": 1.6845, "step": 190500 }, { "epoch": 0.12, "learning_rate": 1.9210057171595228e-05, "loss": 1.7069, "step": 191000 }, { "epoch": 0.12, "learning_rate": 1.9207989258431866e-05, "loss": 1.6864, "step": 191500 }, { "epoch": 0.12, "learning_rate": 1.9205921345268504e-05, "loss": 1.6812, "step": 192000 }, { "epoch": 0.12, "learning_rate": 1.920385343210514e-05, "loss": 1.6656, "step": 192500 }, { "epoch": 0.12, "learning_rate": 1.9201785518941774e-05, "loss": 1.7053, "step": 193000 }, { "epoch": 0.12, "learning_rate": 1.9199717605778413e-05, "loss": 1.6912, "step": 193500 }, { "epoch": 0.12, "learning_rate": 1.919764969261505e-05, "loss": 1.6788, "step": 194000 }, { "epoch": 0.12, "learning_rate": 1.9195581779451686e-05, "loss": 1.7159, "step": 194500 }, { "epoch": 0.12, "learning_rate": 1.919351386628832e-05, "loss": 1.6926, "step": 195000 }, { "epoch": 0.12, "learning_rate": 1.919144595312496e-05, "loss": 1.6993, "step": 195500 }, { "epoch": 0.12, "learning_rate": 1.9189378039961598e-05, "loss": 1.6873, "step": 196000 }, { "epoch": 0.12, "learning_rate": 1.9187310126798233e-05, "loss": 1.6958, "step": 196500 }, { "epoch": 0.12, "learning_rate": 1.918524221363487e-05, "loss": 1.707, "step": 197000 }, { "epoch": 0.12, "learning_rate": 1.9183174300471506e-05, "loss": 1.7106, "step": 197500 }, { "epoch": 0.12, "learning_rate": 1.9181106387308144e-05, "loss": 1.6955, "step": 198000 }, { "epoch": 0.12, "learning_rate": 1.917903847414478e-05, "loss": 1.6852, "step": 198500 }, { "epoch": 0.12, "learning_rate": 1.9176970560981418e-05, "loss": 1.6947, "step": 199000 }, { "epoch": 0.12, "learning_rate": 1.9174902647818056e-05, "loss": 1.6855, "step": 199500 }, { "epoch": 0.12, "learning_rate": 1.917283473465469e-05, "loss": 1.6682, "step": 200000 }, { "epoch": 0.12, "learning_rate": 1.9170766821491326e-05, "loss": 1.6652, "step": 200500 }, { "epoch": 0.12, "learning_rate": 1.9168698908327964e-05, "loss": 1.6933, "step": 201000 }, { "epoch": 0.13, "learning_rate": 1.9166630995164603e-05, "loss": 1.6796, "step": 201500 }, { "epoch": 0.13, "learning_rate": 1.9164563082001237e-05, "loss": 1.6792, "step": 202000 }, { "epoch": 0.13, "learning_rate": 1.9162495168837872e-05, "loss": 1.6971, "step": 202500 }, { "epoch": 0.13, "learning_rate": 1.916042725567451e-05, "loss": 1.68, "step": 203000 }, { "epoch": 0.13, "learning_rate": 1.915835934251115e-05, "loss": 1.7343, "step": 203500 }, { "epoch": 0.13, "learning_rate": 1.9156291429347784e-05, "loss": 1.6952, "step": 204000 }, { "epoch": 0.13, "learning_rate": 1.915422351618442e-05, "loss": 1.6982, "step": 204500 }, { "epoch": 0.13, "learning_rate": 1.9152155603021057e-05, "loss": 1.6913, "step": 205000 }, { "epoch": 0.13, "learning_rate": 1.9150087689857696e-05, "loss": 1.7325, "step": 205500 }, { "epoch": 0.13, "learning_rate": 1.914801977669433e-05, "loss": 1.702, "step": 206000 }, { "epoch": 0.13, "learning_rate": 1.9145951863530966e-05, "loss": 1.7036, "step": 206500 }, { "epoch": 0.13, "learning_rate": 1.9143883950367604e-05, "loss": 1.6976, "step": 207000 }, { "epoch": 0.13, "learning_rate": 1.9141816037204242e-05, "loss": 1.6641, "step": 207500 }, { "epoch": 0.13, "learning_rate": 1.9139748124040877e-05, "loss": 1.6834, "step": 208000 }, { "epoch": 0.13, "learning_rate": 1.9137680210877512e-05, "loss": 1.6544, "step": 208500 }, { "epoch": 0.13, "learning_rate": 1.913561229771415e-05, "loss": 1.6664, "step": 209000 }, { "epoch": 0.13, "learning_rate": 1.913354438455079e-05, "loss": 1.7106, "step": 209500 }, { "epoch": 0.13, "learning_rate": 1.9131476471387424e-05, "loss": 1.7085, "step": 210000 }, { "epoch": 0.13, "learning_rate": 1.9129408558224062e-05, "loss": 1.7068, "step": 210500 }, { "epoch": 0.13, "learning_rate": 1.9127340645060697e-05, "loss": 1.6862, "step": 211000 }, { "epoch": 0.13, "learning_rate": 1.9125272731897336e-05, "loss": 1.7104, "step": 211500 }, { "epoch": 0.13, "learning_rate": 1.912320481873397e-05, "loss": 1.7098, "step": 212000 }, { "epoch": 0.13, "learning_rate": 1.912113690557061e-05, "loss": 1.724, "step": 212500 }, { "epoch": 0.13, "learning_rate": 1.9119068992407247e-05, "loss": 1.6682, "step": 213000 }, { "epoch": 0.13, "learning_rate": 1.9117001079243882e-05, "loss": 1.6904, "step": 213500 }, { "epoch": 0.13, "learning_rate": 1.9114933166080517e-05, "loss": 1.6882, "step": 214000 }, { "epoch": 0.13, "learning_rate": 1.9112865252917156e-05, "loss": 1.6934, "step": 214500 }, { "epoch": 0.13, "learning_rate": 1.9110797339753794e-05, "loss": 1.661, "step": 215000 }, { "epoch": 0.13, "learning_rate": 1.910872942659043e-05, "loss": 1.7105, "step": 215500 }, { "epoch": 0.13, "learning_rate": 1.9106661513427064e-05, "loss": 1.6951, "step": 216000 }, { "epoch": 0.13, "learning_rate": 1.9104593600263702e-05, "loss": 1.6618, "step": 216500 }, { "epoch": 0.13, "learning_rate": 1.910252568710034e-05, "loss": 1.6655, "step": 217000 }, { "epoch": 0.13, "learning_rate": 1.9100457773936976e-05, "loss": 1.6697, "step": 217500 }, { "epoch": 0.14, "learning_rate": 1.909838986077361e-05, "loss": 1.697, "step": 218000 }, { "epoch": 0.14, "learning_rate": 1.909632194761025e-05, "loss": 1.7151, "step": 218500 }, { "epoch": 0.14, "learning_rate": 1.9094254034446887e-05, "loss": 1.6973, "step": 219000 }, { "epoch": 0.14, "learning_rate": 1.9092186121283522e-05, "loss": 1.6952, "step": 219500 }, { "epoch": 0.14, "learning_rate": 1.9090118208120157e-05, "loss": 1.6862, "step": 220000 }, { "epoch": 0.14, "learning_rate": 1.9088050294956795e-05, "loss": 1.6556, "step": 220500 }, { "epoch": 0.14, "learning_rate": 1.9085982381793434e-05, "loss": 1.6698, "step": 221000 }, { "epoch": 0.14, "learning_rate": 1.908391446863007e-05, "loss": 1.7042, "step": 221500 }, { "epoch": 0.14, "learning_rate": 1.9081846555466704e-05, "loss": 1.675, "step": 222000 }, { "epoch": 0.14, "learning_rate": 1.9079778642303342e-05, "loss": 1.6962, "step": 222500 }, { "epoch": 0.14, "learning_rate": 1.907771072913998e-05, "loss": 1.7022, "step": 223000 }, { "epoch": 0.14, "learning_rate": 1.9075642815976615e-05, "loss": 1.705, "step": 223500 }, { "epoch": 0.14, "learning_rate": 1.9073574902813254e-05, "loss": 1.6785, "step": 224000 }, { "epoch": 0.14, "learning_rate": 1.907150698964989e-05, "loss": 1.6881, "step": 224500 }, { "epoch": 0.14, "learning_rate": 1.9069439076486527e-05, "loss": 1.6617, "step": 225000 }, { "epoch": 0.14, "learning_rate": 1.9067371163323162e-05, "loss": 1.6976, "step": 225500 }, { "epoch": 0.14, "learning_rate": 1.90653032501598e-05, "loss": 1.67, "step": 226000 }, { "epoch": 0.14, "learning_rate": 1.906323533699644e-05, "loss": 1.6941, "step": 226500 }, { "epoch": 0.14, "learning_rate": 1.9061167423833074e-05, "loss": 1.6841, "step": 227000 }, { "epoch": 0.14, "learning_rate": 1.905909951066971e-05, "loss": 1.6705, "step": 227500 }, { "epoch": 0.14, "learning_rate": 1.9057031597506347e-05, "loss": 1.6706, "step": 228000 }, { "epoch": 0.14, "learning_rate": 1.9054963684342985e-05, "loss": 1.6915, "step": 228500 }, { "epoch": 0.14, "learning_rate": 1.905289577117962e-05, "loss": 1.6837, "step": 229000 }, { "epoch": 0.14, "learning_rate": 1.9050827858016255e-05, "loss": 1.6841, "step": 229500 }, { "epoch": 0.14, "learning_rate": 1.9048759944852894e-05, "loss": 1.6806, "step": 230000 }, { "epoch": 0.14, "learning_rate": 1.9046692031689532e-05, "loss": 1.6783, "step": 230500 }, { "epoch": 0.14, "learning_rate": 1.9044624118526167e-05, "loss": 1.6878, "step": 231000 }, { "epoch": 0.14, "learning_rate": 1.9042556205362802e-05, "loss": 1.6912, "step": 231500 }, { "epoch": 0.14, "learning_rate": 1.904048829219944e-05, "loss": 1.6867, "step": 232000 }, { "epoch": 0.14, "learning_rate": 1.903842037903608e-05, "loss": 1.6788, "step": 232500 }, { "epoch": 0.14, "learning_rate": 1.9036352465872714e-05, "loss": 1.6876, "step": 233000 }, { "epoch": 0.14, "learning_rate": 1.903428455270935e-05, "loss": 1.6774, "step": 233500 }, { "epoch": 0.15, "learning_rate": 1.9032216639545987e-05, "loss": 1.6914, "step": 234000 }, { "epoch": 0.15, "learning_rate": 1.9030148726382625e-05, "loss": 1.6734, "step": 234500 }, { "epoch": 0.15, "learning_rate": 1.902808081321926e-05, "loss": 1.6902, "step": 235000 }, { "epoch": 0.15, "learning_rate": 1.90260129000559e-05, "loss": 1.6824, "step": 235500 }, { "epoch": 0.15, "learning_rate": 1.9023944986892533e-05, "loss": 1.7159, "step": 236000 }, { "epoch": 0.15, "learning_rate": 1.9021877073729172e-05, "loss": 1.6848, "step": 236500 }, { "epoch": 0.15, "learning_rate": 1.9019809160565807e-05, "loss": 1.6727, "step": 237000 }, { "epoch": 0.15, "learning_rate": 1.9017741247402445e-05, "loss": 1.6647, "step": 237500 }, { "epoch": 0.15, "learning_rate": 1.901567333423908e-05, "loss": 1.666, "step": 238000 }, { "epoch": 0.15, "learning_rate": 1.901360542107572e-05, "loss": 1.7109, "step": 238500 }, { "epoch": 0.15, "learning_rate": 1.9011537507912353e-05, "loss": 1.6651, "step": 239000 }, { "epoch": 0.15, "learning_rate": 1.9009469594748992e-05, "loss": 1.6668, "step": 239500 }, { "epoch": 0.15, "learning_rate": 1.900740168158563e-05, "loss": 1.682, "step": 240000 }, { "epoch": 0.15, "learning_rate": 1.9005333768422265e-05, "loss": 1.7031, "step": 240500 }, { "epoch": 0.15, "learning_rate": 1.90032658552589e-05, "loss": 1.6993, "step": 241000 }, { "epoch": 0.15, "learning_rate": 1.900119794209554e-05, "loss": 1.6602, "step": 241500 }, { "epoch": 0.15, "learning_rate": 1.8999130028932177e-05, "loss": 1.6772, "step": 242000 }, { "epoch": 0.15, "learning_rate": 1.899706211576881e-05, "loss": 1.7098, "step": 242500 }, { "epoch": 0.15, "learning_rate": 1.8994994202605447e-05, "loss": 1.6754, "step": 243000 }, { "epoch": 0.15, "learning_rate": 1.8992926289442085e-05, "loss": 1.6923, "step": 243500 }, { "epoch": 0.15, "learning_rate": 1.8990858376278723e-05, "loss": 1.6801, "step": 244000 }, { "epoch": 0.15, "learning_rate": 1.8988790463115358e-05, "loss": 1.6797, "step": 244500 }, { "epoch": 0.15, "learning_rate": 1.8986722549951993e-05, "loss": 1.6852, "step": 245000 }, { "epoch": 0.15, "learning_rate": 1.898465463678863e-05, "loss": 1.6869, "step": 245500 }, { "epoch": 0.15, "learning_rate": 1.898258672362527e-05, "loss": 1.6933, "step": 246000 }, { "epoch": 0.15, "learning_rate": 1.8980518810461905e-05, "loss": 1.6877, "step": 246500 }, { "epoch": 0.15, "learning_rate": 1.897845089729854e-05, "loss": 1.6923, "step": 247000 }, { "epoch": 0.15, "learning_rate": 1.8976382984135178e-05, "loss": 1.7072, "step": 247500 }, { "epoch": 0.15, "learning_rate": 1.8974315070971817e-05, "loss": 1.7022, "step": 248000 }, { "epoch": 0.15, "learning_rate": 1.897224715780845e-05, "loss": 1.6557, "step": 248500 }, { "epoch": 0.15, "learning_rate": 1.897017924464509e-05, "loss": 1.679, "step": 249000 }, { "epoch": 0.15, "learning_rate": 1.8968111331481725e-05, "loss": 1.6773, "step": 249500 }, { "epoch": 0.16, "learning_rate": 1.8966043418318363e-05, "loss": 1.6589, "step": 250000 }, { "epoch": 0.16, "learning_rate": 1.8963975505154998e-05, "loss": 1.6512, "step": 250500 }, { "epoch": 0.16, "learning_rate": 1.8961907591991636e-05, "loss": 1.677, "step": 251000 }, { "epoch": 0.16, "learning_rate": 1.895983967882827e-05, "loss": 1.6426, "step": 251500 }, { "epoch": 0.16, "learning_rate": 1.895777176566491e-05, "loss": 1.6895, "step": 252000 }, { "epoch": 0.16, "learning_rate": 1.8955703852501545e-05, "loss": 1.7015, "step": 252500 }, { "epoch": 0.16, "learning_rate": 1.8953635939338183e-05, "loss": 1.6814, "step": 253000 }, { "epoch": 0.16, "learning_rate": 1.895156802617482e-05, "loss": 1.6872, "step": 253500 }, { "epoch": 0.16, "learning_rate": 1.8949500113011456e-05, "loss": 1.6808, "step": 254000 }, { "epoch": 0.16, "learning_rate": 1.894743219984809e-05, "loss": 1.6724, "step": 254500 }, { "epoch": 0.16, "learning_rate": 1.894536428668473e-05, "loss": 1.6583, "step": 255000 }, { "epoch": 0.16, "learning_rate": 1.8943296373521368e-05, "loss": 1.6886, "step": 255500 }, { "epoch": 0.16, "learning_rate": 1.8941228460358003e-05, "loss": 1.6697, "step": 256000 }, { "epoch": 0.16, "learning_rate": 1.8939160547194638e-05, "loss": 1.6663, "step": 256500 }, { "epoch": 0.16, "learning_rate": 1.8937092634031276e-05, "loss": 1.6772, "step": 257000 }, { "epoch": 0.16, "learning_rate": 1.8935024720867915e-05, "loss": 1.686, "step": 257500 }, { "epoch": 0.16, "learning_rate": 1.893295680770455e-05, "loss": 1.6776, "step": 258000 }, { "epoch": 0.16, "learning_rate": 1.8930888894541185e-05, "loss": 1.6644, "step": 258500 }, { "epoch": 0.16, "learning_rate": 1.8928820981377823e-05, "loss": 1.709, "step": 259000 }, { "epoch": 0.16, "learning_rate": 1.892675306821446e-05, "loss": 1.6555, "step": 259500 }, { "epoch": 0.16, "learning_rate": 1.8924685155051096e-05, "loss": 1.7072, "step": 260000 }, { "epoch": 0.16, "learning_rate": 1.8922617241887735e-05, "loss": 1.6783, "step": 260500 }, { "epoch": 0.16, "learning_rate": 1.892054932872437e-05, "loss": 1.6766, "step": 261000 }, { "epoch": 0.16, "learning_rate": 1.8918481415561008e-05, "loss": 1.6712, "step": 261500 }, { "epoch": 0.16, "learning_rate": 1.8916413502397643e-05, "loss": 1.6923, "step": 262000 }, { "epoch": 0.16, "learning_rate": 1.891434558923428e-05, "loss": 1.699, "step": 262500 }, { "epoch": 0.16, "learning_rate": 1.8912277676070916e-05, "loss": 1.6557, "step": 263000 }, { "epoch": 0.16, "learning_rate": 1.8910209762907555e-05, "loss": 1.6932, "step": 263500 }, { "epoch": 0.16, "learning_rate": 1.890814184974419e-05, "loss": 1.6695, "step": 264000 }, { "epoch": 0.16, "learning_rate": 1.8906073936580828e-05, "loss": 1.6708, "step": 264500 }, { "epoch": 0.16, "learning_rate": 1.8904006023417463e-05, "loss": 1.6846, "step": 265000 }, { "epoch": 0.16, "learning_rate": 1.89019381102541e-05, "loss": 1.6674, "step": 265500 }, { "epoch": 0.17, "learning_rate": 1.8899870197090736e-05, "loss": 1.6888, "step": 266000 }, { "epoch": 0.17, "learning_rate": 1.8897802283927375e-05, "loss": 1.6255, "step": 266500 }, { "epoch": 0.17, "learning_rate": 1.8895734370764013e-05, "loss": 1.6834, "step": 267000 }, { "epoch": 0.17, "learning_rate": 1.8893666457600648e-05, "loss": 1.6467, "step": 267500 }, { "epoch": 0.17, "learning_rate": 1.8891598544437283e-05, "loss": 1.6775, "step": 268000 }, { "epoch": 0.17, "learning_rate": 1.888953063127392e-05, "loss": 1.6667, "step": 268500 }, { "epoch": 0.17, "learning_rate": 1.888746271811056e-05, "loss": 1.6797, "step": 269000 }, { "epoch": 0.17, "learning_rate": 1.8885394804947194e-05, "loss": 1.6653, "step": 269500 }, { "epoch": 0.17, "learning_rate": 1.888332689178383e-05, "loss": 1.6725, "step": 270000 }, { "epoch": 0.17, "learning_rate": 1.8881258978620468e-05, "loss": 1.6932, "step": 270500 }, { "epoch": 0.17, "learning_rate": 1.8879191065457106e-05, "loss": 1.7109, "step": 271000 }, { "epoch": 0.17, "learning_rate": 1.887712315229374e-05, "loss": 1.6952, "step": 271500 }, { "epoch": 0.17, "learning_rate": 1.8875055239130376e-05, "loss": 1.6407, "step": 272000 }, { "epoch": 0.17, "learning_rate": 1.8872987325967014e-05, "loss": 1.6619, "step": 272500 }, { "epoch": 0.17, "learning_rate": 1.8870919412803653e-05, "loss": 1.7035, "step": 273000 }, { "epoch": 0.17, "learning_rate": 1.8868851499640288e-05, "loss": 1.6827, "step": 273500 }, { "epoch": 0.17, "learning_rate": 1.8866783586476926e-05, "loss": 1.6668, "step": 274000 }, { "epoch": 0.17, "learning_rate": 1.886471567331356e-05, "loss": 1.6379, "step": 274500 }, { "epoch": 0.17, "learning_rate": 1.88626477601502e-05, "loss": 1.6813, "step": 275000 }, { "epoch": 0.17, "learning_rate": 1.8860579846986834e-05, "loss": 1.7091, "step": 275500 }, { "epoch": 0.17, "learning_rate": 1.8858511933823473e-05, "loss": 1.6762, "step": 276000 }, { "epoch": 0.17, "learning_rate": 1.8856444020660108e-05, "loss": 1.688, "step": 276500 }, { "epoch": 0.17, "learning_rate": 1.8854376107496746e-05, "loss": 1.6393, "step": 277000 }, { "epoch": 0.17, "learning_rate": 1.885230819433338e-05, "loss": 1.6629, "step": 277500 }, { "epoch": 0.17, "learning_rate": 1.885024028117002e-05, "loss": 1.6881, "step": 278000 }, { "epoch": 0.17, "learning_rate": 1.8848172368006654e-05, "loss": 1.7069, "step": 278500 }, { "epoch": 0.17, "learning_rate": 1.8846104454843293e-05, "loss": 1.6752, "step": 279000 }, { "epoch": 0.17, "learning_rate": 1.8844036541679928e-05, "loss": 1.678, "step": 279500 }, { "epoch": 0.17, "learning_rate": 1.8841968628516566e-05, "loss": 1.6643, "step": 280000 }, { "epoch": 0.17, "learning_rate": 1.8839900715353204e-05, "loss": 1.6525, "step": 280500 }, { "epoch": 0.17, "learning_rate": 1.883783280218984e-05, "loss": 1.7002, "step": 281000 }, { "epoch": 0.17, "learning_rate": 1.8835764889026474e-05, "loss": 1.6542, "step": 281500 }, { "epoch": 0.17, "learning_rate": 1.8833696975863113e-05, "loss": 1.7043, "step": 282000 }, { "epoch": 0.18, "learning_rate": 1.883162906269975e-05, "loss": 1.6496, "step": 282500 }, { "epoch": 0.18, "learning_rate": 1.8829561149536386e-05, "loss": 1.6587, "step": 283000 }, { "epoch": 0.18, "learning_rate": 1.882749323637302e-05, "loss": 1.6738, "step": 283500 }, { "epoch": 0.18, "learning_rate": 1.882542532320966e-05, "loss": 1.6681, "step": 284000 }, { "epoch": 0.18, "learning_rate": 1.8823357410046297e-05, "loss": 1.633, "step": 284500 }, { "epoch": 0.18, "learning_rate": 1.8821289496882932e-05, "loss": 1.6639, "step": 285000 }, { "epoch": 0.18, "learning_rate": 1.8819221583719567e-05, "loss": 1.6569, "step": 285500 }, { "epoch": 0.18, "learning_rate": 1.8817153670556206e-05, "loss": 1.7017, "step": 286000 }, { "epoch": 0.18, "learning_rate": 1.8815085757392844e-05, "loss": 1.6748, "step": 286500 }, { "epoch": 0.18, "learning_rate": 1.881301784422948e-05, "loss": 1.6641, "step": 287000 }, { "epoch": 0.18, "learning_rate": 1.8810949931066117e-05, "loss": 1.6913, "step": 287500 }, { "epoch": 0.18, "learning_rate": 1.8808882017902752e-05, "loss": 1.6746, "step": 288000 }, { "epoch": 0.18, "learning_rate": 1.880681410473939e-05, "loss": 1.7007, "step": 288500 }, { "epoch": 0.18, "learning_rate": 1.8804746191576026e-05, "loss": 1.6874, "step": 289000 }, { "epoch": 0.18, "learning_rate": 1.8802678278412664e-05, "loss": 1.6801, "step": 289500 }, { "epoch": 0.18, "learning_rate": 1.88006103652493e-05, "loss": 1.6809, "step": 290000 }, { "epoch": 0.18, "learning_rate": 1.8798542452085937e-05, "loss": 1.6858, "step": 290500 }, { "epoch": 0.18, "learning_rate": 1.8796474538922572e-05, "loss": 1.6333, "step": 291000 }, { "epoch": 0.18, "learning_rate": 1.879440662575921e-05, "loss": 1.6655, "step": 291500 }, { "epoch": 0.18, "learning_rate": 1.8792338712595846e-05, "loss": 1.6815, "step": 292000 }, { "epoch": 0.18, "learning_rate": 1.8790270799432484e-05, "loss": 1.6881, "step": 292500 }, { "epoch": 0.18, "learning_rate": 1.878820288626912e-05, "loss": 1.6599, "step": 293000 }, { "epoch": 0.18, "learning_rate": 1.8786134973105757e-05, "loss": 1.6517, "step": 293500 }, { "epoch": 0.18, "learning_rate": 1.8784067059942396e-05, "loss": 1.6852, "step": 294000 }, { "epoch": 0.18, "learning_rate": 1.878199914677903e-05, "loss": 1.6945, "step": 294500 }, { "epoch": 0.18, "learning_rate": 1.8779931233615666e-05, "loss": 1.6562, "step": 295000 }, { "epoch": 0.18, "learning_rate": 1.8777863320452304e-05, "loss": 1.6828, "step": 295500 }, { "epoch": 0.18, "learning_rate": 1.8775795407288942e-05, "loss": 1.6758, "step": 296000 }, { "epoch": 0.18, "learning_rate": 1.8773727494125577e-05, "loss": 1.6738, "step": 296500 }, { "epoch": 0.18, "learning_rate": 1.8771659580962212e-05, "loss": 1.6369, "step": 297000 }, { "epoch": 0.18, "learning_rate": 1.876959166779885e-05, "loss": 1.6627, "step": 297500 }, { "epoch": 0.18, "learning_rate": 1.876752375463549e-05, "loss": 1.6529, "step": 298000 }, { "epoch": 0.19, "learning_rate": 1.8765455841472124e-05, "loss": 1.6635, "step": 298500 }, { "epoch": 0.19, "learning_rate": 1.8763387928308762e-05, "loss": 1.6566, "step": 299000 }, { "epoch": 0.19, "learning_rate": 1.8761320015145397e-05, "loss": 1.6997, "step": 299500 }, { "epoch": 0.19, "learning_rate": 1.8759252101982035e-05, "loss": 1.6699, "step": 300000 }, { "epoch": 0.19, "learning_rate": 1.875718418881867e-05, "loss": 1.6844, "step": 300500 }, { "epoch": 0.19, "learning_rate": 1.875511627565531e-05, "loss": 1.6682, "step": 301000 }, { "epoch": 0.19, "learning_rate": 1.8753048362491944e-05, "loss": 1.6541, "step": 301500 }, { "epoch": 0.19, "learning_rate": 1.8750980449328582e-05, "loss": 1.6626, "step": 302000 }, { "epoch": 0.19, "learning_rate": 1.8748912536165217e-05, "loss": 1.6739, "step": 302500 }, { "epoch": 0.19, "learning_rate": 1.8746844623001855e-05, "loss": 1.6582, "step": 303000 }, { "epoch": 0.19, "learning_rate": 1.874477670983849e-05, "loss": 1.6743, "step": 303500 }, { "epoch": 0.19, "learning_rate": 1.874270879667513e-05, "loss": 1.6741, "step": 304000 }, { "epoch": 0.19, "learning_rate": 1.8740640883511764e-05, "loss": 1.6588, "step": 304500 }, { "epoch": 0.19, "learning_rate": 1.8738572970348402e-05, "loss": 1.6654, "step": 305000 }, { "epoch": 0.19, "learning_rate": 1.8736505057185037e-05, "loss": 1.6849, "step": 305500 }, { "epoch": 0.19, "learning_rate": 1.8734437144021675e-05, "loss": 1.6606, "step": 306000 }, { "epoch": 0.19, "learning_rate": 1.873236923085831e-05, "loss": 1.7128, "step": 306500 }, { "epoch": 0.19, "learning_rate": 1.873030131769495e-05, "loss": 1.6696, "step": 307000 }, { "epoch": 0.19, "learning_rate": 1.8728233404531587e-05, "loss": 1.6637, "step": 307500 }, { "epoch": 0.19, "learning_rate": 1.8726165491368222e-05, "loss": 1.6955, "step": 308000 }, { "epoch": 0.19, "learning_rate": 1.8724097578204857e-05, "loss": 1.6834, "step": 308500 }, { "epoch": 0.19, "learning_rate": 1.8722029665041495e-05, "loss": 1.6335, "step": 309000 }, { "epoch": 0.19, "learning_rate": 1.8719961751878134e-05, "loss": 1.6748, "step": 309500 }, { "epoch": 0.19, "learning_rate": 1.871789383871477e-05, "loss": 1.6522, "step": 310000 }, { "epoch": 0.19, "learning_rate": 1.8715825925551404e-05, "loss": 1.6767, "step": 310500 }, { "epoch": 0.19, "learning_rate": 1.8713758012388042e-05, "loss": 1.6893, "step": 311000 }, { "epoch": 0.19, "learning_rate": 1.871169009922468e-05, "loss": 1.6616, "step": 311500 }, { "epoch": 0.19, "learning_rate": 1.8709622186061315e-05, "loss": 1.6518, "step": 312000 }, { "epoch": 0.19, "learning_rate": 1.8707554272897954e-05, "loss": 1.6703, "step": 312500 }, { "epoch": 0.19, "learning_rate": 1.870548635973459e-05, "loss": 1.6511, "step": 313000 }, { "epoch": 0.19, "learning_rate": 1.8703418446571227e-05, "loss": 1.712, "step": 313500 }, { "epoch": 0.19, "learning_rate": 1.8701350533407862e-05, "loss": 1.684, "step": 314000 }, { "epoch": 0.2, "learning_rate": 1.86992826202445e-05, "loss": 1.6989, "step": 314500 }, { "epoch": 0.2, "learning_rate": 1.8697214707081135e-05, "loss": 1.6937, "step": 315000 }, { "epoch": 0.2, "learning_rate": 1.8695146793917774e-05, "loss": 1.679, "step": 315500 }, { "epoch": 0.2, "learning_rate": 1.869307888075441e-05, "loss": 1.6523, "step": 316000 }, { "epoch": 0.2, "learning_rate": 1.8691010967591047e-05, "loss": 1.6638, "step": 316500 }, { "epoch": 0.2, "learning_rate": 1.8688943054427682e-05, "loss": 1.6578, "step": 317000 }, { "epoch": 0.2, "learning_rate": 1.868687514126432e-05, "loss": 1.668, "step": 317500 }, { "epoch": 0.2, "learning_rate": 1.8684807228100955e-05, "loss": 1.6638, "step": 318000 }, { "epoch": 0.2, "learning_rate": 1.8682739314937593e-05, "loss": 1.6585, "step": 318500 }, { "epoch": 0.2, "learning_rate": 1.8680671401774232e-05, "loss": 1.6564, "step": 319000 }, { "epoch": 0.2, "learning_rate": 1.8678603488610867e-05, "loss": 1.679, "step": 319500 }, { "epoch": 0.2, "learning_rate": 1.8676535575447502e-05, "loss": 1.6669, "step": 320000 }, { "epoch": 0.2, "learning_rate": 1.867446766228414e-05, "loss": 1.6687, "step": 320500 }, { "epoch": 0.2, "learning_rate": 1.867239974912078e-05, "loss": 1.6963, "step": 321000 }, { "epoch": 0.2, "learning_rate": 1.8670331835957413e-05, "loss": 1.6617, "step": 321500 }, { "epoch": 0.2, "learning_rate": 1.866826392279405e-05, "loss": 1.6586, "step": 322000 }, { "epoch": 0.2, "learning_rate": 1.8666196009630687e-05, "loss": 1.6685, "step": 322500 }, { "epoch": 0.2, "learning_rate": 1.8664128096467325e-05, "loss": 1.6909, "step": 323000 }, { "epoch": 0.2, "learning_rate": 1.866206018330396e-05, "loss": 1.6458, "step": 323500 }, { "epoch": 0.2, "learning_rate": 1.86599922701406e-05, "loss": 1.6812, "step": 324000 }, { "epoch": 0.2, "learning_rate": 1.8657924356977233e-05, "loss": 1.6596, "step": 324500 }, { "epoch": 0.2, "learning_rate": 1.865585644381387e-05, "loss": 1.6848, "step": 325000 }, { "epoch": 0.2, "learning_rate": 1.8653788530650507e-05, "loss": 1.6796, "step": 325500 }, { "epoch": 0.2, "learning_rate": 1.8651720617487145e-05, "loss": 1.6883, "step": 326000 }, { "epoch": 0.2, "learning_rate": 1.864965270432378e-05, "loss": 1.6402, "step": 326500 }, { "epoch": 0.2, "learning_rate": 1.8647584791160418e-05, "loss": 1.6754, "step": 327000 }, { "epoch": 0.2, "learning_rate": 1.8645516877997053e-05, "loss": 1.6419, "step": 327500 }, { "epoch": 0.2, "learning_rate": 1.864344896483369e-05, "loss": 1.6601, "step": 328000 }, { "epoch": 0.2, "learning_rate": 1.8641381051670327e-05, "loss": 1.6689, "step": 328500 }, { "epoch": 0.2, "learning_rate": 1.8639313138506965e-05, "loss": 1.6372, "step": 329000 }, { "epoch": 0.2, "learning_rate": 1.86372452253436e-05, "loss": 1.6361, "step": 329500 }, { "epoch": 0.2, "learning_rate": 1.8635177312180238e-05, "loss": 1.6986, "step": 330000 }, { "epoch": 0.21, "learning_rate": 1.8633109399016873e-05, "loss": 1.6626, "step": 330500 }, { "epoch": 0.21, "learning_rate": 1.863104148585351e-05, "loss": 1.6471, "step": 331000 }, { "epoch": 0.21, "learning_rate": 1.8628973572690146e-05, "loss": 1.6749, "step": 331500 }, { "epoch": 0.21, "learning_rate": 1.8626905659526785e-05, "loss": 1.6646, "step": 332000 }, { "epoch": 0.21, "learning_rate": 1.8624837746363423e-05, "loss": 1.6745, "step": 332500 }, { "epoch": 0.21, "learning_rate": 1.8622769833200058e-05, "loss": 1.6759, "step": 333000 }, { "epoch": 0.21, "learning_rate": 1.8620701920036693e-05, "loss": 1.6502, "step": 333500 }, { "epoch": 0.21, "learning_rate": 1.861863400687333e-05, "loss": 1.6745, "step": 334000 }, { "epoch": 0.21, "learning_rate": 1.861656609370997e-05, "loss": 1.6366, "step": 334500 }, { "epoch": 0.21, "learning_rate": 1.8614498180546605e-05, "loss": 1.6612, "step": 335000 }, { "epoch": 0.21, "learning_rate": 1.861243026738324e-05, "loss": 1.6645, "step": 335500 }, { "epoch": 0.21, "learning_rate": 1.8610362354219878e-05, "loss": 1.6613, "step": 336000 }, { "epoch": 0.21, "learning_rate": 1.8608294441056516e-05, "loss": 1.6703, "step": 336500 }, { "epoch": 0.21, "learning_rate": 1.860622652789315e-05, "loss": 1.6633, "step": 337000 }, { "epoch": 0.21, "learning_rate": 1.860415861472979e-05, "loss": 1.6559, "step": 337500 }, { "epoch": 0.21, "learning_rate": 1.8602090701566425e-05, "loss": 1.6805, "step": 338000 }, { "epoch": 0.21, "learning_rate": 1.8600022788403063e-05, "loss": 1.6817, "step": 338500 }, { "epoch": 0.21, "learning_rate": 1.8597954875239698e-05, "loss": 1.7016, "step": 339000 }, { "epoch": 0.21, "learning_rate": 1.8595886962076336e-05, "loss": 1.6582, "step": 339500 }, { "epoch": 0.21, "learning_rate": 1.859381904891297e-05, "loss": 1.6472, "step": 340000 }, { "epoch": 0.21, "learning_rate": 1.859175113574961e-05, "loss": 1.6682, "step": 340500 }, { "epoch": 0.21, "learning_rate": 1.8589683222586245e-05, "loss": 1.7143, "step": 341000 }, { "epoch": 0.21, "learning_rate": 1.8587615309422883e-05, "loss": 1.6578, "step": 341500 }, { "epoch": 0.21, "learning_rate": 1.8585547396259518e-05, "loss": 1.662, "step": 342000 }, { "epoch": 0.21, "learning_rate": 1.8583479483096156e-05, "loss": 1.6454, "step": 342500 }, { "epoch": 0.21, "learning_rate": 1.858141156993279e-05, "loss": 1.6586, "step": 343000 }, { "epoch": 0.21, "learning_rate": 1.857934365676943e-05, "loss": 1.6859, "step": 343500 }, { "epoch": 0.21, "learning_rate": 1.8577275743606065e-05, "loss": 1.6667, "step": 344000 }, { "epoch": 0.21, "learning_rate": 1.8575207830442703e-05, "loss": 1.6875, "step": 344500 }, { "epoch": 0.21, "learning_rate": 1.8573139917279338e-05, "loss": 1.6784, "step": 345000 }, { "epoch": 0.21, "learning_rate": 1.8571072004115976e-05, "loss": 1.6744, "step": 345500 }, { "epoch": 0.21, "learning_rate": 1.8569004090952615e-05, "loss": 1.6499, "step": 346000 }, { "epoch": 0.21, "learning_rate": 1.856693617778925e-05, "loss": 1.6434, "step": 346500 }, { "epoch": 0.22, "learning_rate": 1.8564868264625884e-05, "loss": 1.6592, "step": 347000 }, { "epoch": 0.22, "learning_rate": 1.8562800351462523e-05, "loss": 1.6665, "step": 347500 }, { "epoch": 0.22, "learning_rate": 1.856073243829916e-05, "loss": 1.6438, "step": 348000 }, { "epoch": 0.22, "learning_rate": 1.8558664525135796e-05, "loss": 1.6838, "step": 348500 }, { "epoch": 0.22, "learning_rate": 1.855659661197243e-05, "loss": 1.6925, "step": 349000 }, { "epoch": 0.22, "learning_rate": 1.855452869880907e-05, "loss": 1.6616, "step": 349500 }, { "epoch": 0.22, "learning_rate": 1.8552460785645708e-05, "loss": 1.6478, "step": 350000 }, { "epoch": 0.22, "learning_rate": 1.8550392872482343e-05, "loss": 1.6539, "step": 350500 }, { "epoch": 0.22, "learning_rate": 1.854832495931898e-05, "loss": 1.6667, "step": 351000 }, { "epoch": 0.22, "learning_rate": 1.8546257046155616e-05, "loss": 1.698, "step": 351500 }, { "epoch": 0.22, "learning_rate": 1.8544189132992254e-05, "loss": 1.6305, "step": 352000 }, { "epoch": 0.22, "learning_rate": 1.854212121982889e-05, "loss": 1.6525, "step": 352500 }, { "epoch": 0.22, "learning_rate": 1.8540053306665528e-05, "loss": 1.6506, "step": 353000 }, { "epoch": 0.22, "learning_rate": 1.8537985393502163e-05, "loss": 1.6907, "step": 353500 }, { "epoch": 0.22, "learning_rate": 1.85359174803388e-05, "loss": 1.6641, "step": 354000 }, { "epoch": 0.22, "learning_rate": 1.8533849567175436e-05, "loss": 1.6587, "step": 354500 }, { "epoch": 0.22, "learning_rate": 1.8531781654012074e-05, "loss": 1.6549, "step": 355000 }, { "epoch": 0.22, "learning_rate": 1.852971374084871e-05, "loss": 1.6669, "step": 355500 }, { "epoch": 0.22, "learning_rate": 1.8527645827685348e-05, "loss": 1.6615, "step": 356000 }, { "epoch": 0.22, "learning_rate": 1.8525577914521983e-05, "loss": 1.7056, "step": 356500 }, { "epoch": 0.22, "learning_rate": 1.852351000135862e-05, "loss": 1.6965, "step": 357000 }, { "epoch": 0.22, "learning_rate": 1.8521442088195256e-05, "loss": 1.65, "step": 357500 }, { "epoch": 0.22, "learning_rate": 1.8519374175031894e-05, "loss": 1.662, "step": 358000 }, { "epoch": 0.22, "learning_rate": 1.851730626186853e-05, "loss": 1.6659, "step": 358500 }, { "epoch": 0.22, "learning_rate": 1.8515238348705168e-05, "loss": 1.668, "step": 359000 }, { "epoch": 0.22, "learning_rate": 1.8513170435541806e-05, "loss": 1.6712, "step": 359500 }, { "epoch": 0.22, "learning_rate": 1.851110252237844e-05, "loss": 1.655, "step": 360000 }, { "epoch": 0.22, "learning_rate": 1.8509034609215076e-05, "loss": 1.6694, "step": 360500 }, { "epoch": 0.22, "learning_rate": 1.8506966696051714e-05, "loss": 1.6588, "step": 361000 }, { "epoch": 0.22, "learning_rate": 1.8504898782888353e-05, "loss": 1.6963, "step": 361500 }, { "epoch": 0.22, "learning_rate": 1.8502830869724988e-05, "loss": 1.67, "step": 362000 }, { "epoch": 0.22, "learning_rate": 1.8500762956561626e-05, "loss": 1.6612, "step": 362500 }, { "epoch": 0.23, "learning_rate": 1.849869504339826e-05, "loss": 1.6683, "step": 363000 }, { "epoch": 0.23, "learning_rate": 1.84966271302349e-05, "loss": 1.6851, "step": 363500 }, { "epoch": 0.23, "learning_rate": 1.8494559217071534e-05, "loss": 1.6498, "step": 364000 }, { "epoch": 0.23, "learning_rate": 1.8492491303908173e-05, "loss": 1.644, "step": 364500 }, { "epoch": 0.23, "learning_rate": 1.8490423390744807e-05, "loss": 1.6754, "step": 365000 }, { "epoch": 0.23, "learning_rate": 1.8488355477581446e-05, "loss": 1.6836, "step": 365500 }, { "epoch": 0.23, "learning_rate": 1.848628756441808e-05, "loss": 1.6537, "step": 366000 }, { "epoch": 0.23, "learning_rate": 1.848421965125472e-05, "loss": 1.651, "step": 366500 }, { "epoch": 0.23, "learning_rate": 1.8482151738091354e-05, "loss": 1.6182, "step": 367000 }, { "epoch": 0.23, "learning_rate": 1.8480083824927992e-05, "loss": 1.6661, "step": 367500 }, { "epoch": 0.23, "learning_rate": 1.8478015911764627e-05, "loss": 1.6385, "step": 368000 }, { "epoch": 0.23, "learning_rate": 1.8475947998601266e-05, "loss": 1.6284, "step": 368500 }, { "epoch": 0.23, "learning_rate": 1.84738800854379e-05, "loss": 1.6813, "step": 369000 }, { "epoch": 0.23, "learning_rate": 1.847181217227454e-05, "loss": 1.6621, "step": 369500 }, { "epoch": 0.23, "learning_rate": 1.8469744259111174e-05, "loss": 1.663, "step": 370000 }, { "epoch": 0.23, "learning_rate": 1.8467676345947812e-05, "loss": 1.6451, "step": 370500 }, { "epoch": 0.23, "learning_rate": 1.8465608432784447e-05, "loss": 1.6663, "step": 371000 }, { "epoch": 0.23, "learning_rate": 1.8463540519621086e-05, "loss": 1.63, "step": 371500 }, { "epoch": 0.23, "learning_rate": 1.846147260645772e-05, "loss": 1.6637, "step": 372000 }, { "epoch": 0.23, "learning_rate": 1.845940469329436e-05, "loss": 1.6485, "step": 372500 }, { "epoch": 0.23, "learning_rate": 1.8457336780130997e-05, "loss": 1.6679, "step": 373000 }, { "epoch": 0.23, "learning_rate": 1.8455268866967632e-05, "loss": 1.6681, "step": 373500 }, { "epoch": 0.23, "learning_rate": 1.8453200953804267e-05, "loss": 1.6559, "step": 374000 }, { "epoch": 0.23, "learning_rate": 1.8451133040640906e-05, "loss": 1.6885, "step": 374500 }, { "epoch": 0.23, "learning_rate": 1.8449065127477544e-05, "loss": 1.6863, "step": 375000 }, { "epoch": 0.23, "learning_rate": 1.844699721431418e-05, "loss": 1.6402, "step": 375500 }, { "epoch": 0.23, "learning_rate": 1.8444929301150817e-05, "loss": 1.6368, "step": 376000 }, { "epoch": 0.23, "learning_rate": 1.8442861387987452e-05, "loss": 1.6648, "step": 376500 }, { "epoch": 0.23, "learning_rate": 1.844079347482409e-05, "loss": 1.6663, "step": 377000 }, { "epoch": 0.23, "learning_rate": 1.8438725561660726e-05, "loss": 1.6628, "step": 377500 }, { "epoch": 0.23, "learning_rate": 1.8436657648497364e-05, "loss": 1.6763, "step": 378000 }, { "epoch": 0.23, "learning_rate": 1.8434589735334e-05, "loss": 1.6907, "step": 378500 }, { "epoch": 0.24, "learning_rate": 1.8432521822170637e-05, "loss": 1.6456, "step": 379000 }, { "epoch": 0.24, "learning_rate": 1.8430453909007272e-05, "loss": 1.6476, "step": 379500 }, { "epoch": 0.24, "learning_rate": 1.842838599584391e-05, "loss": 1.6527, "step": 380000 }, { "epoch": 0.24, "learning_rate": 1.8426318082680545e-05, "loss": 1.6693, "step": 380500 }, { "epoch": 0.24, "learning_rate": 1.8424250169517184e-05, "loss": 1.6449, "step": 381000 }, { "epoch": 0.24, "learning_rate": 1.842218225635382e-05, "loss": 1.6448, "step": 381500 }, { "epoch": 0.24, "learning_rate": 1.8420114343190457e-05, "loss": 1.6584, "step": 382000 }, { "epoch": 0.24, "learning_rate": 1.8418046430027092e-05, "loss": 1.6626, "step": 382500 }, { "epoch": 0.24, "learning_rate": 1.841597851686373e-05, "loss": 1.6332, "step": 383000 }, { "epoch": 0.24, "learning_rate": 1.8413910603700365e-05, "loss": 1.6822, "step": 383500 }, { "epoch": 0.24, "learning_rate": 1.8411842690537004e-05, "loss": 1.6918, "step": 384000 }, { "epoch": 0.24, "learning_rate": 1.840977477737364e-05, "loss": 1.6372, "step": 384500 }, { "epoch": 0.24, "learning_rate": 1.8407706864210277e-05, "loss": 1.6666, "step": 385000 }, { "epoch": 0.24, "learning_rate": 1.8405638951046912e-05, "loss": 1.6548, "step": 385500 }, { "epoch": 0.24, "learning_rate": 1.840357103788355e-05, "loss": 1.6538, "step": 386000 }, { "epoch": 0.24, "learning_rate": 1.840150312472019e-05, "loss": 1.6661, "step": 386500 }, { "epoch": 0.24, "learning_rate": 1.8399435211556824e-05, "loss": 1.6869, "step": 387000 }, { "epoch": 0.24, "learning_rate": 1.8397367298393462e-05, "loss": 1.6475, "step": 387500 }, { "epoch": 0.24, "learning_rate": 1.8395299385230097e-05, "loss": 1.6752, "step": 388000 }, { "epoch": 0.24, "learning_rate": 1.8393231472066735e-05, "loss": 1.6536, "step": 388500 }, { "epoch": 0.24, "learning_rate": 1.839116355890337e-05, "loss": 1.6247, "step": 389000 }, { "epoch": 0.24, "learning_rate": 1.838909564574001e-05, "loss": 1.6753, "step": 389500 }, { "epoch": 0.24, "learning_rate": 1.8387027732576644e-05, "loss": 1.6638, "step": 390000 }, { "epoch": 0.24, "learning_rate": 1.8384959819413282e-05, "loss": 1.6797, "step": 390500 }, { "epoch": 0.24, "learning_rate": 1.8382891906249917e-05, "loss": 1.6426, "step": 391000 }, { "epoch": 0.24, "learning_rate": 1.8380823993086555e-05, "loss": 1.6834, "step": 391500 }, { "epoch": 0.24, "learning_rate": 1.837875607992319e-05, "loss": 1.6424, "step": 392000 }, { "epoch": 0.24, "learning_rate": 1.837668816675983e-05, "loss": 1.6996, "step": 392500 }, { "epoch": 0.24, "learning_rate": 1.8374620253596464e-05, "loss": 1.6475, "step": 393000 }, { "epoch": 0.24, "learning_rate": 1.8372552340433102e-05, "loss": 1.668, "step": 393500 }, { "epoch": 0.24, "learning_rate": 1.8370484427269737e-05, "loss": 1.6578, "step": 394000 }, { "epoch": 0.24, "learning_rate": 1.8368416514106375e-05, "loss": 1.6566, "step": 394500 }, { "epoch": 0.25, "learning_rate": 1.836634860094301e-05, "loss": 1.6448, "step": 395000 }, { "epoch": 0.25, "learning_rate": 1.836428068777965e-05, "loss": 1.6473, "step": 395500 }, { "epoch": 0.25, "learning_rate": 1.8362212774616283e-05, "loss": 1.6196, "step": 396000 }, { "epoch": 0.25, "learning_rate": 1.8360144861452922e-05, "loss": 1.6599, "step": 396500 }, { "epoch": 0.25, "learning_rate": 1.8358076948289557e-05, "loss": 1.6793, "step": 397000 }, { "epoch": 0.25, "learning_rate": 1.8356009035126195e-05, "loss": 1.6576, "step": 397500 }, { "epoch": 0.25, "learning_rate": 1.835394112196283e-05, "loss": 1.6568, "step": 398000 }, { "epoch": 0.25, "learning_rate": 1.835187320879947e-05, "loss": 1.6515, "step": 398500 }, { "epoch": 0.25, "learning_rate": 1.8349805295636103e-05, "loss": 1.6276, "step": 399000 }, { "epoch": 0.25, "learning_rate": 1.8347737382472742e-05, "loss": 1.6365, "step": 399500 }, { "epoch": 0.25, "learning_rate": 1.834566946930938e-05, "loss": 1.658, "step": 400000 }, { "epoch": 0.25, "learning_rate": 1.8343601556146015e-05, "loss": 1.6499, "step": 400500 }, { "epoch": 0.25, "learning_rate": 1.8341533642982653e-05, "loss": 1.653, "step": 401000 }, { "epoch": 0.25, "learning_rate": 1.833946572981929e-05, "loss": 1.635, "step": 401500 }, { "epoch": 0.25, "learning_rate": 1.8337397816655927e-05, "loss": 1.675, "step": 402000 }, { "epoch": 0.25, "learning_rate": 1.8335329903492562e-05, "loss": 1.6724, "step": 402500 }, { "epoch": 0.25, "learning_rate": 1.83332619903292e-05, "loss": 1.6298, "step": 403000 }, { "epoch": 0.25, "learning_rate": 1.8331194077165835e-05, "loss": 1.6759, "step": 403500 }, { "epoch": 0.25, "learning_rate": 1.8329126164002473e-05, "loss": 1.6709, "step": 404000 }, { "epoch": 0.25, "learning_rate": 1.832705825083911e-05, "loss": 1.6522, "step": 404500 }, { "epoch": 0.25, "learning_rate": 1.8324990337675747e-05, "loss": 1.6463, "step": 405000 }, { "epoch": 0.25, "learning_rate": 1.832292242451238e-05, "loss": 1.6643, "step": 405500 }, { "epoch": 0.25, "learning_rate": 1.832085451134902e-05, "loss": 1.6055, "step": 406000 }, { "epoch": 0.25, "learning_rate": 1.8318786598185655e-05, "loss": 1.6392, "step": 406500 }, { "epoch": 0.25, "learning_rate": 1.8316718685022293e-05, "loss": 1.6522, "step": 407000 }, { "epoch": 0.25, "learning_rate": 1.8314650771858928e-05, "loss": 1.6631, "step": 407500 }, { "epoch": 0.25, "learning_rate": 1.8312582858695567e-05, "loss": 1.6838, "step": 408000 }, { "epoch": 0.25, "learning_rate": 1.83105149455322e-05, "loss": 1.6631, "step": 408500 }, { "epoch": 0.25, "learning_rate": 1.830844703236884e-05, "loss": 1.6685, "step": 409000 }, { "epoch": 0.25, "learning_rate": 1.8306379119205475e-05, "loss": 1.653, "step": 409500 }, { "epoch": 0.25, "learning_rate": 1.8304311206042113e-05, "loss": 1.6389, "step": 410000 }, { "epoch": 0.25, "learning_rate": 1.8302243292878748e-05, "loss": 1.675, "step": 410500 }, { "epoch": 0.25, "learning_rate": 1.8300175379715387e-05, "loss": 1.6373, "step": 411000 }, { "epoch": 0.26, "learning_rate": 1.829810746655202e-05, "loss": 1.6883, "step": 411500 }, { "epoch": 0.26, "learning_rate": 1.829603955338866e-05, "loss": 1.6283, "step": 412000 }, { "epoch": 0.26, "learning_rate": 1.8293971640225295e-05, "loss": 1.6554, "step": 412500 }, { "epoch": 0.26, "learning_rate": 1.8291903727061933e-05, "loss": 1.6459, "step": 413000 }, { "epoch": 0.26, "learning_rate": 1.828983581389857e-05, "loss": 1.6659, "step": 413500 }, { "epoch": 0.26, "learning_rate": 1.8287767900735206e-05, "loss": 1.6516, "step": 414000 }, { "epoch": 0.26, "learning_rate": 1.8285699987571845e-05, "loss": 1.6383, "step": 414500 }, { "epoch": 0.26, "learning_rate": 1.828363207440848e-05, "loss": 1.6741, "step": 415000 }, { "epoch": 0.26, "learning_rate": 1.8281564161245118e-05, "loss": 1.6367, "step": 415500 }, { "epoch": 0.26, "learning_rate": 1.8279496248081753e-05, "loss": 1.643, "step": 416000 }, { "epoch": 0.26, "learning_rate": 1.827742833491839e-05, "loss": 1.6696, "step": 416500 }, { "epoch": 0.26, "learning_rate": 1.8275360421755026e-05, "loss": 1.6456, "step": 417000 }, { "epoch": 0.26, "learning_rate": 1.8273292508591665e-05, "loss": 1.6417, "step": 417500 }, { "epoch": 0.26, "learning_rate": 1.82712245954283e-05, "loss": 1.6375, "step": 418000 }, { "epoch": 0.26, "learning_rate": 1.8269156682264938e-05, "loss": 1.6403, "step": 418500 }, { "epoch": 0.26, "learning_rate": 1.8267088769101573e-05, "loss": 1.66, "step": 419000 }, { "epoch": 0.26, "learning_rate": 1.826502085593821e-05, "loss": 1.6382, "step": 419500 }, { "epoch": 0.26, "learning_rate": 1.8262952942774846e-05, "loss": 1.6647, "step": 420000 }, { "epoch": 0.26, "learning_rate": 1.8260885029611485e-05, "loss": 1.6479, "step": 420500 }, { "epoch": 0.26, "learning_rate": 1.825881711644812e-05, "loss": 1.6657, "step": 421000 }, { "epoch": 0.26, "learning_rate": 1.8256749203284758e-05, "loss": 1.614, "step": 421500 }, { "epoch": 0.26, "learning_rate": 1.8254681290121393e-05, "loss": 1.6482, "step": 422000 }, { "epoch": 0.26, "learning_rate": 1.825261337695803e-05, "loss": 1.6583, "step": 422500 }, { "epoch": 0.26, "learning_rate": 1.8250545463794666e-05, "loss": 1.6448, "step": 423000 }, { "epoch": 0.26, "learning_rate": 1.8248477550631305e-05, "loss": 1.6754, "step": 423500 }, { "epoch": 0.26, "learning_rate": 1.824640963746794e-05, "loss": 1.6287, "step": 424000 }, { "epoch": 0.26, "learning_rate": 1.8244341724304578e-05, "loss": 1.6743, "step": 424500 }, { "epoch": 0.26, "learning_rate": 1.8242273811141213e-05, "loss": 1.665, "step": 425000 }, { "epoch": 0.26, "learning_rate": 1.824020589797785e-05, "loss": 1.6557, "step": 425500 }, { "epoch": 0.26, "learning_rate": 1.823813798481449e-05, "loss": 1.6336, "step": 426000 }, { "epoch": 0.26, "learning_rate": 1.8236070071651125e-05, "loss": 1.6197, "step": 426500 }, { "epoch": 0.26, "learning_rate": 1.8234002158487763e-05, "loss": 1.6367, "step": 427000 }, { "epoch": 0.27, "learning_rate": 1.8231934245324398e-05, "loss": 1.624, "step": 427500 }, { "epoch": 0.27, "learning_rate": 1.8229866332161036e-05, "loss": 1.6275, "step": 428000 }, { "epoch": 0.27, "learning_rate": 1.822779841899767e-05, "loss": 1.6556, "step": 428500 }, { "epoch": 0.27, "learning_rate": 1.822573050583431e-05, "loss": 1.6741, "step": 429000 }, { "epoch": 0.27, "learning_rate": 1.8223662592670944e-05, "loss": 1.6421, "step": 429500 }, { "epoch": 0.27, "learning_rate": 1.8221594679507583e-05, "loss": 1.6785, "step": 430000 }, { "epoch": 0.27, "learning_rate": 1.8219526766344218e-05, "loss": 1.6487, "step": 430500 }, { "epoch": 0.27, "learning_rate": 1.8217458853180856e-05, "loss": 1.6681, "step": 431000 }, { "epoch": 0.27, "learning_rate": 1.821539094001749e-05, "loss": 1.6533, "step": 431500 }, { "epoch": 0.27, "learning_rate": 1.821332302685413e-05, "loss": 1.6671, "step": 432000 }, { "epoch": 0.27, "learning_rate": 1.8211255113690764e-05, "loss": 1.6432, "step": 432500 }, { "epoch": 0.27, "learning_rate": 1.8209187200527403e-05, "loss": 1.6305, "step": 433000 }, { "epoch": 0.27, "learning_rate": 1.8207119287364038e-05, "loss": 1.6523, "step": 433500 }, { "epoch": 0.27, "learning_rate": 1.8205051374200676e-05, "loss": 1.6561, "step": 434000 }, { "epoch": 0.27, "learning_rate": 1.820298346103731e-05, "loss": 1.6446, "step": 434500 }, { "epoch": 0.27, "learning_rate": 1.820091554787395e-05, "loss": 1.6156, "step": 435000 }, { "epoch": 0.27, "learning_rate": 1.8198847634710584e-05, "loss": 1.6394, "step": 435500 }, { "epoch": 0.27, "learning_rate": 1.8196779721547223e-05, "loss": 1.6407, "step": 436000 }, { "epoch": 0.27, "learning_rate": 1.8194711808383858e-05, "loss": 1.6342, "step": 436500 }, { "epoch": 0.27, "learning_rate": 1.8192643895220496e-05, "loss": 1.6749, "step": 437000 }, { "epoch": 0.27, "learning_rate": 1.819057598205713e-05, "loss": 1.6508, "step": 437500 }, { "epoch": 0.27, "learning_rate": 1.818850806889377e-05, "loss": 1.6519, "step": 438000 }, { "epoch": 0.27, "learning_rate": 1.8186440155730404e-05, "loss": 1.6573, "step": 438500 }, { "epoch": 0.27, "learning_rate": 1.8184372242567043e-05, "loss": 1.667, "step": 439000 }, { "epoch": 0.27, "learning_rate": 1.818230432940368e-05, "loss": 1.6384, "step": 439500 }, { "epoch": 0.27, "learning_rate": 1.8180236416240316e-05, "loss": 1.6238, "step": 440000 }, { "epoch": 0.27, "learning_rate": 1.8178168503076954e-05, "loss": 1.6725, "step": 440500 }, { "epoch": 0.27, "learning_rate": 1.817610058991359e-05, "loss": 1.6449, "step": 441000 }, { "epoch": 0.27, "learning_rate": 1.8174032676750228e-05, "loss": 1.6505, "step": 441500 }, { "epoch": 0.27, "learning_rate": 1.8171964763586863e-05, "loss": 1.6707, "step": 442000 }, { "epoch": 0.27, "learning_rate": 1.81698968504235e-05, "loss": 1.6427, "step": 442500 }, { "epoch": 0.27, "learning_rate": 1.8167828937260136e-05, "loss": 1.6475, "step": 443000 }, { "epoch": 0.28, "learning_rate": 1.8165761024096774e-05, "loss": 1.6559, "step": 443500 }, { "epoch": 0.28, "learning_rate": 1.816369311093341e-05, "loss": 1.6613, "step": 444000 }, { "epoch": 0.28, "learning_rate": 1.8161625197770048e-05, "loss": 1.6699, "step": 444500 }, { "epoch": 0.28, "learning_rate": 1.8159557284606682e-05, "loss": 1.6719, "step": 445000 }, { "epoch": 0.28, "learning_rate": 1.815748937144332e-05, "loss": 1.6476, "step": 445500 }, { "epoch": 0.28, "learning_rate": 1.8155421458279956e-05, "loss": 1.6824, "step": 446000 }, { "epoch": 0.28, "learning_rate": 1.8153353545116594e-05, "loss": 1.6431, "step": 446500 }, { "epoch": 0.28, "learning_rate": 1.815128563195323e-05, "loss": 1.6254, "step": 447000 }, { "epoch": 0.28, "learning_rate": 1.8149217718789867e-05, "loss": 1.6346, "step": 447500 }, { "epoch": 0.28, "learning_rate": 1.8147149805626502e-05, "loss": 1.6573, "step": 448000 }, { "epoch": 0.28, "learning_rate": 1.814508189246314e-05, "loss": 1.6255, "step": 448500 }, { "epoch": 0.28, "learning_rate": 1.8143013979299776e-05, "loss": 1.6647, "step": 449000 }, { "epoch": 0.28, "learning_rate": 1.8140946066136414e-05, "loss": 1.6665, "step": 449500 }, { "epoch": 0.28, "learning_rate": 1.813887815297305e-05, "loss": 1.6266, "step": 450000 }, { "epoch": 0.28, "learning_rate": 1.8136810239809687e-05, "loss": 1.6343, "step": 450500 }, { "epoch": 0.28, "learning_rate": 1.8134742326646326e-05, "loss": 1.6593, "step": 451000 }, { "epoch": 0.28, "learning_rate": 1.813267441348296e-05, "loss": 1.6333, "step": 451500 }, { "epoch": 0.28, "learning_rate": 1.81306065003196e-05, "loss": 1.6328, "step": 452000 }, { "epoch": 0.28, "learning_rate": 1.8128538587156234e-05, "loss": 1.6466, "step": 452500 }, { "epoch": 0.28, "learning_rate": 1.8126470673992872e-05, "loss": 1.6815, "step": 453000 }, { "epoch": 0.28, "learning_rate": 1.8124402760829507e-05, "loss": 1.638, "step": 453500 }, { "epoch": 0.28, "learning_rate": 1.8122334847666146e-05, "loss": 1.6642, "step": 454000 }, { "epoch": 0.28, "learning_rate": 1.812026693450278e-05, "loss": 1.667, "step": 454500 }, { "epoch": 0.28, "learning_rate": 1.811819902133942e-05, "loss": 1.6592, "step": 455000 }, { "epoch": 0.28, "learning_rate": 1.8116131108176054e-05, "loss": 1.6665, "step": 455500 }, { "epoch": 0.28, "learning_rate": 1.8114063195012692e-05, "loss": 1.638, "step": 456000 }, { "epoch": 0.28, "learning_rate": 1.8111995281849327e-05, "loss": 1.678, "step": 456500 }, { "epoch": 0.28, "learning_rate": 1.8109927368685966e-05, "loss": 1.6459, "step": 457000 }, { "epoch": 0.28, "learning_rate": 1.81078594555226e-05, "loss": 1.626, "step": 457500 }, { "epoch": 0.28, "learning_rate": 1.810579154235924e-05, "loss": 1.6603, "step": 458000 }, { "epoch": 0.28, "learning_rate": 1.8103723629195874e-05, "loss": 1.6515, "step": 458500 }, { "epoch": 0.28, "learning_rate": 1.8101655716032512e-05, "loss": 1.6363, "step": 459000 }, { "epoch": 0.29, "learning_rate": 1.8099587802869147e-05, "loss": 1.6601, "step": 459500 }, { "epoch": 0.29, "learning_rate": 1.8097519889705786e-05, "loss": 1.6861, "step": 460000 }, { "epoch": 0.29, "learning_rate": 1.809545197654242e-05, "loss": 1.6588, "step": 460500 }, { "epoch": 0.29, "learning_rate": 1.809338406337906e-05, "loss": 1.639, "step": 461000 }, { "epoch": 0.29, "learning_rate": 1.8091316150215694e-05, "loss": 1.6452, "step": 461500 }, { "epoch": 0.29, "learning_rate": 1.8089248237052332e-05, "loss": 1.6557, "step": 462000 }, { "epoch": 0.29, "learning_rate": 1.8087180323888967e-05, "loss": 1.6331, "step": 462500 }, { "epoch": 0.29, "learning_rate": 1.8085112410725605e-05, "loss": 1.667, "step": 463000 }, { "epoch": 0.29, "learning_rate": 1.808304449756224e-05, "loss": 1.6583, "step": 463500 }, { "epoch": 0.29, "learning_rate": 1.808097658439888e-05, "loss": 1.6553, "step": 464000 }, { "epoch": 0.29, "learning_rate": 1.8078908671235517e-05, "loss": 1.6531, "step": 464500 }, { "epoch": 0.29, "learning_rate": 1.8076840758072152e-05, "loss": 1.6146, "step": 465000 }, { "epoch": 0.29, "learning_rate": 1.807477284490879e-05, "loss": 1.648, "step": 465500 }, { "epoch": 0.29, "learning_rate": 1.8072704931745425e-05, "loss": 1.6284, "step": 466000 }, { "epoch": 0.29, "learning_rate": 1.8070637018582064e-05, "loss": 1.6384, "step": 466500 }, { "epoch": 0.29, "learning_rate": 1.80685691054187e-05, "loss": 1.6111, "step": 467000 }, { "epoch": 0.29, "learning_rate": 1.8066501192255337e-05, "loss": 1.6365, "step": 467500 }, { "epoch": 0.29, "learning_rate": 1.8064433279091972e-05, "loss": 1.6376, "step": 468000 }, { "epoch": 0.29, "learning_rate": 1.806236536592861e-05, "loss": 1.6842, "step": 468500 }, { "epoch": 0.29, "learning_rate": 1.8060297452765245e-05, "loss": 1.6258, "step": 469000 }, { "epoch": 0.29, "learning_rate": 1.8058229539601884e-05, "loss": 1.6524, "step": 469500 }, { "epoch": 0.29, "learning_rate": 1.805616162643852e-05, "loss": 1.672, "step": 470000 }, { "epoch": 0.29, "learning_rate": 1.8054093713275157e-05, "loss": 1.6601, "step": 470500 }, { "epoch": 0.29, "learning_rate": 1.8052025800111792e-05, "loss": 1.6481, "step": 471000 }, { "epoch": 0.29, "learning_rate": 1.804995788694843e-05, "loss": 1.6419, "step": 471500 }, { "epoch": 0.29, "learning_rate": 1.8047889973785065e-05, "loss": 1.6351, "step": 472000 }, { "epoch": 0.29, "learning_rate": 1.8045822060621704e-05, "loss": 1.7028, "step": 472500 }, { "epoch": 0.29, "learning_rate": 1.804375414745834e-05, "loss": 1.6305, "step": 473000 }, { "epoch": 0.29, "learning_rate": 1.8041686234294977e-05, "loss": 1.6622, "step": 473500 }, { "epoch": 0.29, "learning_rate": 1.8039618321131612e-05, "loss": 1.6547, "step": 474000 }, { "epoch": 0.29, "learning_rate": 1.803755040796825e-05, "loss": 1.6331, "step": 474500 }, { "epoch": 0.29, "learning_rate": 1.8035482494804885e-05, "loss": 1.6587, "step": 475000 }, { "epoch": 0.29, "learning_rate": 1.8033414581641524e-05, "loss": 1.6488, "step": 475500 }, { "epoch": 0.3, "learning_rate": 1.803134666847816e-05, "loss": 1.6752, "step": 476000 }, { "epoch": 0.3, "learning_rate": 1.8029278755314797e-05, "loss": 1.6321, "step": 476500 }, { "epoch": 0.3, "learning_rate": 1.8027210842151432e-05, "loss": 1.6399, "step": 477000 }, { "epoch": 0.3, "learning_rate": 1.802514292898807e-05, "loss": 1.6356, "step": 477500 }, { "epoch": 0.3, "learning_rate": 1.802307501582471e-05, "loss": 1.6602, "step": 478000 }, { "epoch": 0.3, "learning_rate": 1.8021007102661343e-05, "loss": 1.645, "step": 478500 }, { "epoch": 0.3, "learning_rate": 1.8018939189497982e-05, "loss": 1.6481, "step": 479000 }, { "epoch": 0.3, "learning_rate": 1.8016871276334617e-05, "loss": 1.6616, "step": 479500 }, { "epoch": 0.3, "learning_rate": 1.8014803363171255e-05, "loss": 1.6492, "step": 480000 }, { "epoch": 0.3, "learning_rate": 1.801273545000789e-05, "loss": 1.6401, "step": 480500 }, { "epoch": 0.3, "learning_rate": 1.801066753684453e-05, "loss": 1.6495, "step": 481000 }, { "epoch": 0.3, "learning_rate": 1.8008599623681163e-05, "loss": 1.638, "step": 481500 }, { "epoch": 0.3, "learning_rate": 1.8006531710517802e-05, "loss": 1.6777, "step": 482000 }, { "epoch": 0.3, "learning_rate": 1.8004463797354437e-05, "loss": 1.623, "step": 482500 }, { "epoch": 0.3, "learning_rate": 1.8002395884191075e-05, "loss": 1.6565, "step": 483000 }, { "epoch": 0.3, "learning_rate": 1.800032797102771e-05, "loss": 1.652, "step": 483500 }, { "epoch": 0.3, "learning_rate": 1.799826005786435e-05, "loss": 1.6234, "step": 484000 }, { "epoch": 0.3, "learning_rate": 1.7996192144700983e-05, "loss": 1.6683, "step": 484500 }, { "epoch": 0.3, "learning_rate": 1.799412423153762e-05, "loss": 1.6404, "step": 485000 }, { "epoch": 0.3, "learning_rate": 1.7992056318374257e-05, "loss": 1.6737, "step": 485500 }, { "epoch": 0.3, "learning_rate": 1.7989988405210895e-05, "loss": 1.6639, "step": 486000 }, { "epoch": 0.3, "learning_rate": 1.798792049204753e-05, "loss": 1.6638, "step": 486500 }, { "epoch": 0.3, "learning_rate": 1.798585257888417e-05, "loss": 1.6462, "step": 487000 }, { "epoch": 0.3, "learning_rate": 1.7983784665720803e-05, "loss": 1.636, "step": 487500 }, { "epoch": 0.3, "learning_rate": 1.798171675255744e-05, "loss": 1.6169, "step": 488000 }, { "epoch": 0.3, "learning_rate": 1.7979648839394077e-05, "loss": 1.6738, "step": 488500 }, { "epoch": 0.3, "learning_rate": 1.7977580926230715e-05, "loss": 1.6582, "step": 489000 }, { "epoch": 0.3, "learning_rate": 1.7975513013067353e-05, "loss": 1.6413, "step": 489500 }, { "epoch": 0.3, "learning_rate": 1.7973445099903988e-05, "loss": 1.6314, "step": 490000 }, { "epoch": 0.3, "learning_rate": 1.7971377186740623e-05, "loss": 1.6558, "step": 490500 }, { "epoch": 0.3, "learning_rate": 1.796930927357726e-05, "loss": 1.6365, "step": 491000 }, { "epoch": 0.3, "learning_rate": 1.79672413604139e-05, "loss": 1.6507, "step": 491500 }, { "epoch": 0.31, "learning_rate": 1.7965173447250535e-05, "loss": 1.6312, "step": 492000 }, { "epoch": 0.31, "learning_rate": 1.7963105534087173e-05, "loss": 1.6446, "step": 492500 }, { "epoch": 0.31, "learning_rate": 1.7961037620923808e-05, "loss": 1.617, "step": 493000 }, { "epoch": 0.31, "learning_rate": 1.7958969707760447e-05, "loss": 1.6339, "step": 493500 }, { "epoch": 0.31, "learning_rate": 1.795690179459708e-05, "loss": 1.6548, "step": 494000 }, { "epoch": 0.31, "learning_rate": 1.795483388143372e-05, "loss": 1.6461, "step": 494500 }, { "epoch": 0.31, "learning_rate": 1.7952765968270355e-05, "loss": 1.6437, "step": 495000 }, { "epoch": 0.31, "learning_rate": 1.7950698055106993e-05, "loss": 1.6661, "step": 495500 }, { "epoch": 0.31, "learning_rate": 1.7948630141943628e-05, "loss": 1.6442, "step": 496000 }, { "epoch": 0.31, "learning_rate": 1.7946562228780266e-05, "loss": 1.6483, "step": 496500 }, { "epoch": 0.31, "learning_rate": 1.79444943156169e-05, "loss": 1.633, "step": 497000 }, { "epoch": 0.31, "learning_rate": 1.794242640245354e-05, "loss": 1.6162, "step": 497500 }, { "epoch": 0.31, "learning_rate": 1.7940358489290175e-05, "loss": 1.662, "step": 498000 }, { "epoch": 0.31, "learning_rate": 1.7938290576126813e-05, "loss": 1.6637, "step": 498500 }, { "epoch": 0.31, "learning_rate": 1.7936222662963448e-05, "loss": 1.6344, "step": 499000 }, { "epoch": 0.31, "learning_rate": 1.7934154749800086e-05, "loss": 1.6536, "step": 499500 }, { "epoch": 0.31, "learning_rate": 1.793208683663672e-05, "loss": 1.6527, "step": 500000 }, { "epoch": 0.31, "learning_rate": 1.793001892347336e-05, "loss": 1.6556, "step": 500500 }, { "epoch": 0.31, "learning_rate": 1.7927951010309995e-05, "loss": 1.65, "step": 501000 }, { "epoch": 0.31, "learning_rate": 1.7925883097146633e-05, "loss": 1.6368, "step": 501500 }, { "epoch": 0.31, "learning_rate": 1.7923815183983268e-05, "loss": 1.6548, "step": 502000 }, { "epoch": 0.31, "learning_rate": 1.7921747270819906e-05, "loss": 1.6426, "step": 502500 }, { "epoch": 0.31, "learning_rate": 1.7919679357656545e-05, "loss": 1.653, "step": 503000 }, { "epoch": 0.31, "learning_rate": 1.791761144449318e-05, "loss": 1.6329, "step": 503500 }, { "epoch": 0.31, "learning_rate": 1.7915543531329815e-05, "loss": 1.6587, "step": 504000 }, { "epoch": 0.31, "learning_rate": 1.7913475618166453e-05, "loss": 1.6381, "step": 504500 }, { "epoch": 0.31, "learning_rate": 1.791140770500309e-05, "loss": 1.6562, "step": 505000 }, { "epoch": 0.31, "learning_rate": 1.7909339791839726e-05, "loss": 1.6149, "step": 505500 }, { "epoch": 0.31, "learning_rate": 1.7907271878676365e-05, "loss": 1.6132, "step": 506000 }, { "epoch": 0.31, "learning_rate": 1.7905203965513e-05, "loss": 1.6335, "step": 506500 }, { "epoch": 0.31, "learning_rate": 1.7903136052349638e-05, "loss": 1.6401, "step": 507000 }, { "epoch": 0.31, "learning_rate": 1.7901068139186273e-05, "loss": 1.6226, "step": 507500 }, { "epoch": 0.32, "learning_rate": 1.789900022602291e-05, "loss": 1.6317, "step": 508000 }, { "epoch": 0.32, "learning_rate": 1.7896932312859546e-05, "loss": 1.6391, "step": 508500 }, { "epoch": 0.32, "learning_rate": 1.7894864399696185e-05, "loss": 1.6428, "step": 509000 }, { "epoch": 0.32, "learning_rate": 1.789279648653282e-05, "loss": 1.6388, "step": 509500 }, { "epoch": 0.32, "learning_rate": 1.7890728573369458e-05, "loss": 1.6535, "step": 510000 }, { "epoch": 0.32, "learning_rate": 1.7888660660206093e-05, "loss": 1.6337, "step": 510500 }, { "epoch": 0.32, "learning_rate": 1.788659274704273e-05, "loss": 1.6459, "step": 511000 }, { "epoch": 0.32, "learning_rate": 1.7884524833879366e-05, "loss": 1.6372, "step": 511500 }, { "epoch": 0.32, "learning_rate": 1.7882456920716004e-05, "loss": 1.6263, "step": 512000 }, { "epoch": 0.32, "learning_rate": 1.788038900755264e-05, "loss": 1.6255, "step": 512500 }, { "epoch": 0.32, "learning_rate": 1.7878321094389278e-05, "loss": 1.6396, "step": 513000 }, { "epoch": 0.32, "learning_rate": 1.7876253181225913e-05, "loss": 1.6647, "step": 513500 }, { "epoch": 0.32, "learning_rate": 1.787418526806255e-05, "loss": 1.6595, "step": 514000 }, { "epoch": 0.32, "learning_rate": 1.787211735489919e-05, "loss": 1.6335, "step": 514500 }, { "epoch": 0.32, "learning_rate": 1.7870049441735824e-05, "loss": 1.6682, "step": 515000 }, { "epoch": 0.32, "learning_rate": 1.786798152857246e-05, "loss": 1.6296, "step": 515500 }, { "epoch": 0.32, "learning_rate": 1.7865913615409098e-05, "loss": 1.5955, "step": 516000 }, { "epoch": 0.32, "learning_rate": 1.7863845702245736e-05, "loss": 1.6446, "step": 516500 }, { "epoch": 0.32, "learning_rate": 1.786177778908237e-05, "loss": 1.6368, "step": 517000 }, { "epoch": 0.32, "learning_rate": 1.7859709875919006e-05, "loss": 1.6246, "step": 517500 }, { "epoch": 0.32, "learning_rate": 1.7857641962755644e-05, "loss": 1.6548, "step": 518000 }, { "epoch": 0.32, "learning_rate": 1.7855574049592283e-05, "loss": 1.6405, "step": 518500 }, { "epoch": 0.32, "learning_rate": 1.7853506136428918e-05, "loss": 1.6844, "step": 519000 }, { "epoch": 0.32, "learning_rate": 1.7851438223265556e-05, "loss": 1.6358, "step": 519500 }, { "epoch": 0.32, "learning_rate": 1.784937031010219e-05, "loss": 1.6695, "step": 520000 }, { "epoch": 0.32, "learning_rate": 1.784730239693883e-05, "loss": 1.5935, "step": 520500 }, { "epoch": 0.32, "learning_rate": 1.7845234483775464e-05, "loss": 1.6619, "step": 521000 }, { "epoch": 0.32, "learning_rate": 1.7843166570612103e-05, "loss": 1.6272, "step": 521500 }, { "epoch": 0.32, "learning_rate": 1.7841098657448738e-05, "loss": 1.6283, "step": 522000 }, { "epoch": 0.32, "learning_rate": 1.7839030744285376e-05, "loss": 1.6553, "step": 522500 }, { "epoch": 0.32, "learning_rate": 1.783696283112201e-05, "loss": 1.6153, "step": 523000 }, { "epoch": 0.32, "learning_rate": 1.783489491795865e-05, "loss": 1.6412, "step": 523500 }, { "epoch": 0.33, "learning_rate": 1.7832827004795284e-05, "loss": 1.6449, "step": 524000 }, { "epoch": 0.33, "learning_rate": 1.7830759091631923e-05, "loss": 1.5893, "step": 524500 }, { "epoch": 0.33, "learning_rate": 1.7828691178468558e-05, "loss": 1.6059, "step": 525000 }, { "epoch": 0.33, "learning_rate": 1.7826623265305196e-05, "loss": 1.6054, "step": 525500 }, { "epoch": 0.33, "learning_rate": 1.782455535214183e-05, "loss": 1.6312, "step": 526000 }, { "epoch": 0.33, "learning_rate": 1.782248743897847e-05, "loss": 1.6631, "step": 526500 }, { "epoch": 0.33, "learning_rate": 1.7820419525815104e-05, "loss": 1.6257, "step": 527000 }, { "epoch": 0.33, "learning_rate": 1.7818351612651742e-05, "loss": 1.6556, "step": 527500 }, { "epoch": 0.33, "learning_rate": 1.781628369948838e-05, "loss": 1.6308, "step": 528000 }, { "epoch": 0.33, "learning_rate": 1.7814215786325016e-05, "loss": 1.6606, "step": 528500 }, { "epoch": 0.33, "learning_rate": 1.781214787316165e-05, "loss": 1.6317, "step": 529000 }, { "epoch": 0.33, "learning_rate": 1.781007995999829e-05, "loss": 1.6716, "step": 529500 }, { "epoch": 0.33, "learning_rate": 1.7808012046834927e-05, "loss": 1.6568, "step": 530000 }, { "epoch": 0.33, "learning_rate": 1.7805944133671562e-05, "loss": 1.5854, "step": 530500 }, { "epoch": 0.33, "learning_rate": 1.7803876220508197e-05, "loss": 1.6572, "step": 531000 }, { "epoch": 0.33, "learning_rate": 1.7801808307344836e-05, "loss": 1.6564, "step": 531500 }, { "epoch": 0.33, "learning_rate": 1.7799740394181474e-05, "loss": 1.6512, "step": 532000 }, { "epoch": 0.33, "learning_rate": 1.779767248101811e-05, "loss": 1.6238, "step": 532500 }, { "epoch": 0.33, "learning_rate": 1.7795604567854747e-05, "loss": 1.6626, "step": 533000 }, { "epoch": 0.33, "learning_rate": 1.7793536654691382e-05, "loss": 1.6555, "step": 533500 }, { "epoch": 0.33, "learning_rate": 1.779146874152802e-05, "loss": 1.633, "step": 534000 }, { "epoch": 0.33, "learning_rate": 1.7789400828364656e-05, "loss": 1.6286, "step": 534500 }, { "epoch": 0.33, "learning_rate": 1.7787332915201294e-05, "loss": 1.6621, "step": 535000 }, { "epoch": 0.33, "learning_rate": 1.778526500203793e-05, "loss": 1.664, "step": 535500 }, { "epoch": 0.33, "learning_rate": 1.7783197088874567e-05, "loss": 1.6794, "step": 536000 }, { "epoch": 0.33, "learning_rate": 1.7781129175711202e-05, "loss": 1.6317, "step": 536500 }, { "epoch": 0.33, "learning_rate": 1.777906126254784e-05, "loss": 1.6345, "step": 537000 }, { "epoch": 0.33, "learning_rate": 1.7776993349384476e-05, "loss": 1.6339, "step": 537500 }, { "epoch": 0.33, "learning_rate": 1.7774925436221114e-05, "loss": 1.648, "step": 538000 }, { "epoch": 0.33, "learning_rate": 1.777285752305775e-05, "loss": 1.6169, "step": 538500 }, { "epoch": 0.33, "learning_rate": 1.7770789609894387e-05, "loss": 1.6781, "step": 539000 }, { "epoch": 0.33, "learning_rate": 1.7768721696731022e-05, "loss": 1.6373, "step": 539500 }, { "epoch": 0.34, "learning_rate": 1.776665378356766e-05, "loss": 1.6333, "step": 540000 }, { "epoch": 0.34, "learning_rate": 1.7764585870404296e-05, "loss": 1.6021, "step": 540500 }, { "epoch": 0.34, "learning_rate": 1.7762517957240934e-05, "loss": 1.6452, "step": 541000 }, { "epoch": 0.34, "learning_rate": 1.7760450044077572e-05, "loss": 1.6011, "step": 541500 }, { "epoch": 0.34, "learning_rate": 1.7758382130914207e-05, "loss": 1.6314, "step": 542000 }, { "epoch": 0.34, "learning_rate": 1.7756314217750842e-05, "loss": 1.6631, "step": 542500 }, { "epoch": 0.34, "learning_rate": 1.775424630458748e-05, "loss": 1.6245, "step": 543000 }, { "epoch": 0.34, "learning_rate": 1.775217839142412e-05, "loss": 1.6129, "step": 543500 }, { "epoch": 0.34, "learning_rate": 1.7750110478260754e-05, "loss": 1.641, "step": 544000 }, { "epoch": 0.34, "learning_rate": 1.774804256509739e-05, "loss": 1.642, "step": 544500 }, { "epoch": 0.34, "learning_rate": 1.7745974651934027e-05, "loss": 1.6146, "step": 545000 }, { "epoch": 0.34, "learning_rate": 1.7743906738770665e-05, "loss": 1.6357, "step": 545500 }, { "epoch": 0.34, "learning_rate": 1.77418388256073e-05, "loss": 1.6486, "step": 546000 }, { "epoch": 0.34, "learning_rate": 1.773977091244394e-05, "loss": 1.6318, "step": 546500 }, { "epoch": 0.34, "learning_rate": 1.7737702999280574e-05, "loss": 1.6513, "step": 547000 }, { "epoch": 0.34, "learning_rate": 1.7735635086117212e-05, "loss": 1.6505, "step": 547500 }, { "epoch": 0.34, "learning_rate": 1.7733567172953847e-05, "loss": 1.6147, "step": 548000 }, { "epoch": 0.34, "learning_rate": 1.7731499259790485e-05, "loss": 1.6534, "step": 548500 }, { "epoch": 0.34, "learning_rate": 1.772943134662712e-05, "loss": 1.6261, "step": 549000 }, { "epoch": 0.34, "learning_rate": 1.772736343346376e-05, "loss": 1.6144, "step": 549500 }, { "epoch": 0.34, "learning_rate": 1.7725295520300394e-05, "loss": 1.6204, "step": 550000 }, { "epoch": 0.34, "learning_rate": 1.7723227607137032e-05, "loss": 1.6198, "step": 550500 }, { "epoch": 0.34, "learning_rate": 1.7721159693973667e-05, "loss": 1.6431, "step": 551000 }, { "epoch": 0.34, "learning_rate": 1.7719091780810305e-05, "loss": 1.6504, "step": 551500 }, { "epoch": 0.34, "learning_rate": 1.771702386764694e-05, "loss": 1.6136, "step": 552000 }, { "epoch": 0.34, "learning_rate": 1.771495595448358e-05, "loss": 1.6396, "step": 552500 }, { "epoch": 0.34, "learning_rate": 1.7712888041320217e-05, "loss": 1.6491, "step": 553000 }, { "epoch": 0.34, "learning_rate": 1.7710820128156852e-05, "loss": 1.6219, "step": 553500 }, { "epoch": 0.34, "learning_rate": 1.7708752214993487e-05, "loss": 1.6575, "step": 554000 }, { "epoch": 0.34, "learning_rate": 1.7706684301830125e-05, "loss": 1.6177, "step": 554500 }, { "epoch": 0.34, "learning_rate": 1.7704616388666764e-05, "loss": 1.6549, "step": 555000 }, { "epoch": 0.34, "learning_rate": 1.77025484755034e-05, "loss": 1.6602, "step": 555500 }, { "epoch": 0.34, "learning_rate": 1.7700480562340034e-05, "loss": 1.6244, "step": 556000 }, { "epoch": 0.35, "learning_rate": 1.7698412649176672e-05, "loss": 1.6532, "step": 556500 }, { "epoch": 0.35, "learning_rate": 1.769634473601331e-05, "loss": 1.6365, "step": 557000 }, { "epoch": 0.35, "learning_rate": 1.7694276822849945e-05, "loss": 1.6516, "step": 557500 }, { "epoch": 0.35, "learning_rate": 1.769220890968658e-05, "loss": 1.6576, "step": 558000 }, { "epoch": 0.35, "learning_rate": 1.769014099652322e-05, "loss": 1.6514, "step": 558500 }, { "epoch": 0.35, "learning_rate": 1.7688073083359857e-05, "loss": 1.6329, "step": 559000 }, { "epoch": 0.35, "learning_rate": 1.7686005170196492e-05, "loss": 1.6732, "step": 559500 }, { "epoch": 0.35, "learning_rate": 1.768393725703313e-05, "loss": 1.6065, "step": 560000 }, { "epoch": 0.35, "learning_rate": 1.7681869343869765e-05, "loss": 1.6091, "step": 560500 }, { "epoch": 0.35, "learning_rate": 1.7679801430706403e-05, "loss": 1.66, "step": 561000 }, { "epoch": 0.35, "learning_rate": 1.767773351754304e-05, "loss": 1.6477, "step": 561500 }, { "epoch": 0.35, "learning_rate": 1.7675665604379677e-05, "loss": 1.641, "step": 562000 }, { "epoch": 0.35, "learning_rate": 1.7673597691216312e-05, "loss": 1.6301, "step": 562500 }, { "epoch": 0.35, "learning_rate": 1.767152977805295e-05, "loss": 1.6249, "step": 563000 }, { "epoch": 0.35, "learning_rate": 1.7669461864889585e-05, "loss": 1.6138, "step": 563500 }, { "epoch": 0.35, "learning_rate": 1.7667393951726223e-05, "loss": 1.5931, "step": 564000 }, { "epoch": 0.35, "learning_rate": 1.766532603856286e-05, "loss": 1.622, "step": 564500 }, { "epoch": 0.35, "learning_rate": 1.7663258125399497e-05, "loss": 1.6384, "step": 565000 }, { "epoch": 0.35, "learning_rate": 1.766119021223613e-05, "loss": 1.6417, "step": 565500 }, { "epoch": 0.35, "learning_rate": 1.765912229907277e-05, "loss": 1.6032, "step": 566000 }, { "epoch": 0.35, "learning_rate": 1.765705438590941e-05, "loss": 1.6349, "step": 566500 }, { "epoch": 0.35, "learning_rate": 1.7654986472746043e-05, "loss": 1.6122, "step": 567000 }, { "epoch": 0.35, "learning_rate": 1.7652918559582678e-05, "loss": 1.6405, "step": 567500 }, { "epoch": 0.35, "learning_rate": 1.7650850646419317e-05, "loss": 1.6618, "step": 568000 }, { "epoch": 0.35, "learning_rate": 1.7648782733255955e-05, "loss": 1.6489, "step": 568500 }, { "epoch": 0.35, "learning_rate": 1.764671482009259e-05, "loss": 1.6121, "step": 569000 }, { "epoch": 0.35, "learning_rate": 1.7644646906929225e-05, "loss": 1.6462, "step": 569500 }, { "epoch": 0.35, "learning_rate": 1.7642578993765863e-05, "loss": 1.624, "step": 570000 }, { "epoch": 0.35, "learning_rate": 1.76405110806025e-05, "loss": 1.6397, "step": 570500 }, { "epoch": 0.35, "learning_rate": 1.7638443167439137e-05, "loss": 1.6166, "step": 571000 }, { "epoch": 0.35, "learning_rate": 1.763637525427577e-05, "loss": 1.6125, "step": 571500 }, { "epoch": 0.35, "learning_rate": 1.763430734111241e-05, "loss": 1.6181, "step": 572000 }, { "epoch": 0.36, "learning_rate": 1.7632239427949048e-05, "loss": 1.6209, "step": 572500 }, { "epoch": 0.36, "learning_rate": 1.7630171514785683e-05, "loss": 1.6457, "step": 573000 }, { "epoch": 0.36, "learning_rate": 1.762810360162232e-05, "loss": 1.6035, "step": 573500 }, { "epoch": 0.36, "learning_rate": 1.7626035688458957e-05, "loss": 1.628, "step": 574000 }, { "epoch": 0.36, "learning_rate": 1.7623967775295595e-05, "loss": 1.6419, "step": 574500 }, { "epoch": 0.36, "learning_rate": 1.762189986213223e-05, "loss": 1.6502, "step": 575000 }, { "epoch": 0.36, "learning_rate": 1.7619831948968868e-05, "loss": 1.6417, "step": 575500 }, { "epoch": 0.36, "learning_rate": 1.7617764035805503e-05, "loss": 1.6496, "step": 576000 }, { "epoch": 0.36, "learning_rate": 1.761569612264214e-05, "loss": 1.6203, "step": 576500 }, { "epoch": 0.36, "learning_rate": 1.7613628209478776e-05, "loss": 1.6238, "step": 577000 }, { "epoch": 0.36, "learning_rate": 1.7611560296315415e-05, "loss": 1.6238, "step": 577500 }, { "epoch": 0.36, "learning_rate": 1.7609492383152053e-05, "loss": 1.6371, "step": 578000 }, { "epoch": 0.36, "learning_rate": 1.7607424469988688e-05, "loss": 1.6438, "step": 578500 }, { "epoch": 0.36, "learning_rate": 1.7605356556825323e-05, "loss": 1.6448, "step": 579000 }, { "epoch": 0.36, "learning_rate": 1.760328864366196e-05, "loss": 1.6503, "step": 579500 }, { "epoch": 0.36, "learning_rate": 1.76012207304986e-05, "loss": 1.6263, "step": 580000 }, { "epoch": 0.36, "learning_rate": 1.7599152817335235e-05, "loss": 1.6184, "step": 580500 }, { "epoch": 0.36, "learning_rate": 1.759708490417187e-05, "loss": 1.6244, "step": 581000 }, { "epoch": 0.36, "learning_rate": 1.7595016991008508e-05, "loss": 1.6449, "step": 581500 }, { "epoch": 0.36, "learning_rate": 1.7592949077845146e-05, "loss": 1.62, "step": 582000 }, { "epoch": 0.36, "learning_rate": 1.759088116468178e-05, "loss": 1.6307, "step": 582500 }, { "epoch": 0.36, "learning_rate": 1.7588813251518416e-05, "loss": 1.6465, "step": 583000 }, { "epoch": 0.36, "learning_rate": 1.7586745338355055e-05, "loss": 1.6325, "step": 583500 }, { "epoch": 0.36, "learning_rate": 1.7584677425191693e-05, "loss": 1.6253, "step": 584000 }, { "epoch": 0.36, "learning_rate": 1.7582609512028328e-05, "loss": 1.6174, "step": 584500 }, { "epoch": 0.36, "learning_rate": 1.7580541598864966e-05, "loss": 1.6509, "step": 585000 }, { "epoch": 0.36, "learning_rate": 1.75784736857016e-05, "loss": 1.651, "step": 585500 }, { "epoch": 0.36, "learning_rate": 1.757640577253824e-05, "loss": 1.6609, "step": 586000 }, { "epoch": 0.36, "learning_rate": 1.7574337859374875e-05, "loss": 1.659, "step": 586500 }, { "epoch": 0.36, "learning_rate": 1.7572269946211513e-05, "loss": 1.648, "step": 587000 }, { "epoch": 0.36, "learning_rate": 1.7570202033048148e-05, "loss": 1.6242, "step": 587500 }, { "epoch": 0.36, "learning_rate": 1.7568134119884786e-05, "loss": 1.6211, "step": 588000 }, { "epoch": 0.37, "learning_rate": 1.756606620672142e-05, "loss": 1.6353, "step": 588500 }, { "epoch": 0.37, "learning_rate": 1.756399829355806e-05, "loss": 1.623, "step": 589000 }, { "epoch": 0.37, "learning_rate": 1.7561930380394695e-05, "loss": 1.6158, "step": 589500 }, { "epoch": 0.37, "learning_rate": 1.7559862467231333e-05, "loss": 1.6285, "step": 590000 }, { "epoch": 0.37, "learning_rate": 1.7557794554067968e-05, "loss": 1.6366, "step": 590500 }, { "epoch": 0.37, "learning_rate": 1.7555726640904606e-05, "loss": 1.6492, "step": 591000 }, { "epoch": 0.37, "learning_rate": 1.7553658727741245e-05, "loss": 1.6514, "step": 591500 }, { "epoch": 0.37, "learning_rate": 1.755159081457788e-05, "loss": 1.6418, "step": 592000 }, { "epoch": 0.37, "learning_rate": 1.7549522901414514e-05, "loss": 1.6543, "step": 592500 }, { "epoch": 0.37, "learning_rate": 1.7547454988251153e-05, "loss": 1.666, "step": 593000 }, { "epoch": 0.37, "learning_rate": 1.754538707508779e-05, "loss": 1.6268, "step": 593500 }, { "epoch": 0.37, "learning_rate": 1.7543319161924426e-05, "loss": 1.6264, "step": 594000 }, { "epoch": 0.37, "learning_rate": 1.754125124876106e-05, "loss": 1.6544, "step": 594500 }, { "epoch": 0.37, "learning_rate": 1.75391833355977e-05, "loss": 1.6506, "step": 595000 }, { "epoch": 0.37, "learning_rate": 1.7537115422434338e-05, "loss": 1.6444, "step": 595500 }, { "epoch": 0.37, "learning_rate": 1.7535047509270973e-05, "loss": 1.6227, "step": 596000 }, { "epoch": 0.37, "learning_rate": 1.7532979596107608e-05, "loss": 1.6318, "step": 596500 }, { "epoch": 0.37, "learning_rate": 1.7530911682944246e-05, "loss": 1.67, "step": 597000 }, { "epoch": 0.37, "learning_rate": 1.7528843769780884e-05, "loss": 1.632, "step": 597500 }, { "epoch": 0.37, "learning_rate": 1.752677585661752e-05, "loss": 1.6357, "step": 598000 }, { "epoch": 0.37, "learning_rate": 1.7524707943454158e-05, "loss": 1.6154, "step": 598500 }, { "epoch": 0.37, "learning_rate": 1.7522640030290793e-05, "loss": 1.6264, "step": 599000 }, { "epoch": 0.37, "learning_rate": 1.752057211712743e-05, "loss": 1.6287, "step": 599500 }, { "epoch": 0.37, "learning_rate": 1.7518504203964066e-05, "loss": 1.6764, "step": 600000 }, { "epoch": 0.37, "learning_rate": 1.7516436290800704e-05, "loss": 1.6294, "step": 600500 }, { "epoch": 0.37, "learning_rate": 1.751436837763734e-05, "loss": 1.6131, "step": 601000 }, { "epoch": 0.37, "learning_rate": 1.7512300464473978e-05, "loss": 1.6096, "step": 601500 }, { "epoch": 0.37, "learning_rate": 1.7510232551310613e-05, "loss": 1.6342, "step": 602000 }, { "epoch": 0.37, "learning_rate": 1.750816463814725e-05, "loss": 1.6407, "step": 602500 }, { "epoch": 0.37, "learning_rate": 1.7506096724983886e-05, "loss": 1.6358, "step": 603000 }, { "epoch": 0.37, "learning_rate": 1.7504028811820524e-05, "loss": 1.6466, "step": 603500 }, { "epoch": 0.37, "learning_rate": 1.750196089865716e-05, "loss": 1.6399, "step": 604000 }, { "epoch": 0.38, "learning_rate": 1.7499892985493798e-05, "loss": 1.6246, "step": 604500 }, { "epoch": 0.38, "learning_rate": 1.7497825072330436e-05, "loss": 1.6343, "step": 605000 }, { "epoch": 0.38, "learning_rate": 1.749575715916707e-05, "loss": 1.6361, "step": 605500 }, { "epoch": 0.38, "learning_rate": 1.7493689246003706e-05, "loss": 1.629, "step": 606000 }, { "epoch": 0.38, "learning_rate": 1.7491621332840344e-05, "loss": 1.6218, "step": 606500 }, { "epoch": 0.38, "learning_rate": 1.7489553419676983e-05, "loss": 1.6061, "step": 607000 }, { "epoch": 0.38, "learning_rate": 1.7487485506513617e-05, "loss": 1.6301, "step": 607500 }, { "epoch": 0.38, "learning_rate": 1.7485417593350252e-05, "loss": 1.6347, "step": 608000 }, { "epoch": 0.38, "learning_rate": 1.748334968018689e-05, "loss": 1.6262, "step": 608500 }, { "epoch": 0.38, "learning_rate": 1.748128176702353e-05, "loss": 1.6135, "step": 609000 }, { "epoch": 0.38, "learning_rate": 1.7479213853860164e-05, "loss": 1.6469, "step": 609500 }, { "epoch": 0.38, "learning_rate": 1.74771459406968e-05, "loss": 1.6475, "step": 610000 }, { "epoch": 0.38, "learning_rate": 1.7475078027533437e-05, "loss": 1.6186, "step": 610500 }, { "epoch": 0.38, "learning_rate": 1.7473010114370076e-05, "loss": 1.6156, "step": 611000 }, { "epoch": 0.38, "learning_rate": 1.747094220120671e-05, "loss": 1.6327, "step": 611500 }, { "epoch": 0.38, "learning_rate": 1.746887428804335e-05, "loss": 1.605, "step": 612000 }, { "epoch": 0.38, "learning_rate": 1.7466806374879984e-05, "loss": 1.643, "step": 612500 }, { "epoch": 0.38, "learning_rate": 1.7464738461716622e-05, "loss": 1.6171, "step": 613000 }, { "epoch": 0.38, "learning_rate": 1.7462670548553257e-05, "loss": 1.6221, "step": 613500 }, { "epoch": 0.38, "learning_rate": 1.7460602635389896e-05, "loss": 1.6524, "step": 614000 }, { "epoch": 0.38, "learning_rate": 1.745853472222653e-05, "loss": 1.6575, "step": 614500 }, { "epoch": 0.38, "learning_rate": 1.745646680906317e-05, "loss": 1.6086, "step": 615000 }, { "epoch": 0.38, "learning_rate": 1.7454398895899804e-05, "loss": 1.6231, "step": 615500 }, { "epoch": 0.38, "learning_rate": 1.7452330982736442e-05, "loss": 1.623, "step": 616000 }, { "epoch": 0.38, "learning_rate": 1.745026306957308e-05, "loss": 1.629, "step": 616500 }, { "epoch": 0.38, "learning_rate": 1.7448195156409716e-05, "loss": 1.6311, "step": 617000 }, { "epoch": 0.38, "learning_rate": 1.744612724324635e-05, "loss": 1.6315, "step": 617500 }, { "epoch": 0.38, "learning_rate": 1.744405933008299e-05, "loss": 1.6265, "step": 618000 }, { "epoch": 0.38, "learning_rate": 1.7441991416919627e-05, "loss": 1.6621, "step": 618500 }, { "epoch": 0.38, "learning_rate": 1.7439923503756262e-05, "loss": 1.6387, "step": 619000 }, { "epoch": 0.38, "learning_rate": 1.7437855590592897e-05, "loss": 1.6451, "step": 619500 }, { "epoch": 0.38, "learning_rate": 1.7435787677429536e-05, "loss": 1.6337, "step": 620000 }, { "epoch": 0.38, "learning_rate": 1.7433719764266174e-05, "loss": 1.6355, "step": 620500 }, { "epoch": 0.39, "learning_rate": 1.743165185110281e-05, "loss": 1.601, "step": 621000 }, { "epoch": 0.39, "learning_rate": 1.7429583937939444e-05, "loss": 1.6154, "step": 621500 }, { "epoch": 0.39, "learning_rate": 1.7427516024776082e-05, "loss": 1.6416, "step": 622000 }, { "epoch": 0.39, "learning_rate": 1.742544811161272e-05, "loss": 1.5854, "step": 622500 }, { "epoch": 0.39, "learning_rate": 1.7423380198449356e-05, "loss": 1.6032, "step": 623000 }, { "epoch": 0.39, "learning_rate": 1.742131228528599e-05, "loss": 1.6338, "step": 623500 }, { "epoch": 0.39, "learning_rate": 1.741924437212263e-05, "loss": 1.637, "step": 624000 }, { "epoch": 0.39, "learning_rate": 1.7417176458959267e-05, "loss": 1.6116, "step": 624500 }, { "epoch": 0.39, "learning_rate": 1.7415108545795902e-05, "loss": 1.6159, "step": 625000 }, { "epoch": 0.39, "learning_rate": 1.741304063263254e-05, "loss": 1.662, "step": 625500 }, { "epoch": 0.39, "learning_rate": 1.7410972719469175e-05, "loss": 1.6573, "step": 626000 }, { "epoch": 0.39, "learning_rate": 1.7408904806305814e-05, "loss": 1.619, "step": 626500 }, { "epoch": 0.39, "learning_rate": 1.740683689314245e-05, "loss": 1.6382, "step": 627000 }, { "epoch": 0.39, "learning_rate": 1.7404768979979087e-05, "loss": 1.6311, "step": 627500 }, { "epoch": 0.39, "learning_rate": 1.7402701066815722e-05, "loss": 1.6368, "step": 628000 }, { "epoch": 0.39, "learning_rate": 1.740063315365236e-05, "loss": 1.6384, "step": 628500 }, { "epoch": 0.39, "learning_rate": 1.7398565240488995e-05, "loss": 1.6278, "step": 629000 }, { "epoch": 0.39, "learning_rate": 1.7396497327325634e-05, "loss": 1.6204, "step": 629500 }, { "epoch": 0.39, "learning_rate": 1.7394429414162272e-05, "loss": 1.6479, "step": 630000 }, { "epoch": 0.39, "learning_rate": 1.7392361500998907e-05, "loss": 1.6141, "step": 630500 }, { "epoch": 0.39, "learning_rate": 1.7390293587835542e-05, "loss": 1.6368, "step": 631000 }, { "epoch": 0.39, "learning_rate": 1.738822567467218e-05, "loss": 1.6722, "step": 631500 }, { "epoch": 0.39, "learning_rate": 1.738615776150882e-05, "loss": 1.6306, "step": 632000 }, { "epoch": 0.39, "learning_rate": 1.7384089848345454e-05, "loss": 1.603, "step": 632500 }, { "epoch": 0.39, "learning_rate": 1.738202193518209e-05, "loss": 1.6092, "step": 633000 }, { "epoch": 0.39, "learning_rate": 1.7379954022018727e-05, "loss": 1.6071, "step": 633500 }, { "epoch": 0.39, "learning_rate": 1.7377886108855365e-05, "loss": 1.6586, "step": 634000 }, { "epoch": 0.39, "learning_rate": 1.7375818195692e-05, "loss": 1.6435, "step": 634500 }, { "epoch": 0.39, "learning_rate": 1.7373750282528635e-05, "loss": 1.6015, "step": 635000 }, { "epoch": 0.39, "learning_rate": 1.7371682369365274e-05, "loss": 1.6129, "step": 635500 }, { "epoch": 0.39, "learning_rate": 1.7369614456201912e-05, "loss": 1.6231, "step": 636000 }, { "epoch": 0.39, "learning_rate": 1.7367546543038547e-05, "loss": 1.6303, "step": 636500 }, { "epoch": 0.4, "learning_rate": 1.7365478629875182e-05, "loss": 1.6416, "step": 637000 }, { "epoch": 0.4, "learning_rate": 1.736341071671182e-05, "loss": 1.6392, "step": 637500 }, { "epoch": 0.4, "learning_rate": 1.736134280354846e-05, "loss": 1.6424, "step": 638000 }, { "epoch": 0.4, "learning_rate": 1.7359274890385094e-05, "loss": 1.6172, "step": 638500 }, { "epoch": 0.4, "learning_rate": 1.7357206977221732e-05, "loss": 1.6347, "step": 639000 }, { "epoch": 0.4, "learning_rate": 1.7355139064058367e-05, "loss": 1.6149, "step": 639500 }, { "epoch": 0.4, "learning_rate": 1.7353071150895005e-05, "loss": 1.6068, "step": 640000 }, { "epoch": 0.4, "learning_rate": 1.735100323773164e-05, "loss": 1.6347, "step": 640500 }, { "epoch": 0.4, "learning_rate": 1.734893532456828e-05, "loss": 1.6446, "step": 641000 }, { "epoch": 0.4, "learning_rate": 1.7346867411404917e-05, "loss": 1.6167, "step": 641500 }, { "epoch": 0.4, "learning_rate": 1.7344799498241552e-05, "loss": 1.6412, "step": 642000 }, { "epoch": 0.4, "learning_rate": 1.7342731585078187e-05, "loss": 1.6243, "step": 642500 }, { "epoch": 0.4, "learning_rate": 1.7340663671914825e-05, "loss": 1.6058, "step": 643000 }, { "epoch": 0.4, "learning_rate": 1.7338595758751463e-05, "loss": 1.6145, "step": 643500 }, { "epoch": 0.4, "learning_rate": 1.73365278455881e-05, "loss": 1.6231, "step": 644000 }, { "epoch": 0.4, "learning_rate": 1.7334459932424733e-05, "loss": 1.6071, "step": 644500 }, { "epoch": 0.4, "learning_rate": 1.7332392019261372e-05, "loss": 1.6086, "step": 645000 }, { "epoch": 0.4, "learning_rate": 1.733032410609801e-05, "loss": 1.6516, "step": 645500 }, { "epoch": 0.4, "learning_rate": 1.7328256192934645e-05, "loss": 1.6462, "step": 646000 }, { "epoch": 0.4, "learning_rate": 1.732618827977128e-05, "loss": 1.6195, "step": 646500 }, { "epoch": 0.4, "learning_rate": 1.732412036660792e-05, "loss": 1.6253, "step": 647000 }, { "epoch": 0.4, "learning_rate": 1.7322052453444557e-05, "loss": 1.6312, "step": 647500 }, { "epoch": 0.4, "learning_rate": 1.731998454028119e-05, "loss": 1.609, "step": 648000 }, { "epoch": 0.4, "learning_rate": 1.7317916627117827e-05, "loss": 1.6005, "step": 648500 }, { "epoch": 0.4, "learning_rate": 1.7315848713954465e-05, "loss": 1.6201, "step": 649000 }, { "epoch": 0.4, "learning_rate": 1.7313780800791103e-05, "loss": 1.6343, "step": 649500 }, { "epoch": 0.4, "learning_rate": 1.7311712887627738e-05, "loss": 1.6419, "step": 650000 }, { "epoch": 0.4, "learning_rate": 1.7309644974464373e-05, "loss": 1.6027, "step": 650500 }, { "epoch": 0.4, "learning_rate": 1.730757706130101e-05, "loss": 1.6262, "step": 651000 }, { "epoch": 0.4, "learning_rate": 1.730550914813765e-05, "loss": 1.6312, "step": 651500 }, { "epoch": 0.4, "learning_rate": 1.7303441234974285e-05, "loss": 1.6311, "step": 652000 }, { "epoch": 0.4, "learning_rate": 1.7301373321810923e-05, "loss": 1.6296, "step": 652500 }, { "epoch": 0.41, "learning_rate": 1.7299305408647558e-05, "loss": 1.6482, "step": 653000 }, { "epoch": 0.41, "learning_rate": 1.7297237495484197e-05, "loss": 1.66, "step": 653500 }, { "epoch": 0.41, "learning_rate": 1.729516958232083e-05, "loss": 1.601, "step": 654000 }, { "epoch": 0.41, "learning_rate": 1.729310166915747e-05, "loss": 1.6438, "step": 654500 }, { "epoch": 0.41, "learning_rate": 1.7291033755994108e-05, "loss": 1.6462, "step": 655000 }, { "epoch": 0.41, "learning_rate": 1.7288965842830743e-05, "loss": 1.6466, "step": 655500 }, { "epoch": 0.41, "learning_rate": 1.7286897929667378e-05, "loss": 1.6312, "step": 656000 }, { "epoch": 0.41, "learning_rate": 1.7284830016504016e-05, "loss": 1.6351, "step": 656500 }, { "epoch": 0.41, "learning_rate": 1.7282762103340655e-05, "loss": 1.6702, "step": 657000 }, { "epoch": 0.41, "learning_rate": 1.728069419017729e-05, "loss": 1.6228, "step": 657500 }, { "epoch": 0.41, "learning_rate": 1.7278626277013925e-05, "loss": 1.6196, "step": 658000 }, { "epoch": 0.41, "learning_rate": 1.7276558363850563e-05, "loss": 1.6107, "step": 658500 }, { "epoch": 0.41, "learning_rate": 1.72744904506872e-05, "loss": 1.6189, "step": 659000 }, { "epoch": 0.41, "learning_rate": 1.7272422537523836e-05, "loss": 1.6207, "step": 659500 }, { "epoch": 0.41, "learning_rate": 1.727035462436047e-05, "loss": 1.6378, "step": 660000 }, { "epoch": 0.41, "learning_rate": 1.726828671119711e-05, "loss": 1.6469, "step": 660500 }, { "epoch": 0.41, "learning_rate": 1.7266218798033748e-05, "loss": 1.6155, "step": 661000 }, { "epoch": 0.41, "learning_rate": 1.7264150884870383e-05, "loss": 1.6233, "step": 661500 }, { "epoch": 0.41, "learning_rate": 1.7262082971707018e-05, "loss": 1.6268, "step": 662000 }, { "epoch": 0.41, "learning_rate": 1.7260015058543656e-05, "loss": 1.62, "step": 662500 }, { "epoch": 0.41, "learning_rate": 1.7257947145380295e-05, "loss": 1.5998, "step": 663000 }, { "epoch": 0.41, "learning_rate": 1.725587923221693e-05, "loss": 1.6149, "step": 663500 }, { "epoch": 0.41, "learning_rate": 1.7253811319053565e-05, "loss": 1.6559, "step": 664000 }, { "epoch": 0.41, "learning_rate": 1.7251743405890203e-05, "loss": 1.6312, "step": 664500 }, { "epoch": 0.41, "learning_rate": 1.724967549272684e-05, "loss": 1.6357, "step": 665000 }, { "epoch": 0.41, "learning_rate": 1.7247607579563476e-05, "loss": 1.6029, "step": 665500 }, { "epoch": 0.41, "learning_rate": 1.7245539666400115e-05, "loss": 1.6246, "step": 666000 }, { "epoch": 0.41, "learning_rate": 1.724347175323675e-05, "loss": 1.6299, "step": 666500 }, { "epoch": 0.41, "learning_rate": 1.7241403840073388e-05, "loss": 1.6287, "step": 667000 }, { "epoch": 0.41, "learning_rate": 1.7239335926910023e-05, "loss": 1.6016, "step": 667500 }, { "epoch": 0.41, "learning_rate": 1.723726801374666e-05, "loss": 1.647, "step": 668000 }, { "epoch": 0.41, "learning_rate": 1.72352001005833e-05, "loss": 1.6383, "step": 668500 }, { "epoch": 0.42, "learning_rate": 1.7233132187419935e-05, "loss": 1.6502, "step": 669000 }, { "epoch": 0.42, "learning_rate": 1.723106427425657e-05, "loss": 1.6618, "step": 669500 }, { "epoch": 0.42, "learning_rate": 1.7228996361093208e-05, "loss": 1.6288, "step": 670000 }, { "epoch": 0.42, "learning_rate": 1.7226928447929846e-05, "loss": 1.6322, "step": 670500 }, { "epoch": 0.42, "learning_rate": 1.722486053476648e-05, "loss": 1.6003, "step": 671000 }, { "epoch": 0.42, "learning_rate": 1.7222792621603116e-05, "loss": 1.626, "step": 671500 }, { "epoch": 0.42, "learning_rate": 1.7220724708439755e-05, "loss": 1.6195, "step": 672000 }, { "epoch": 0.42, "learning_rate": 1.7218656795276393e-05, "loss": 1.6523, "step": 672500 }, { "epoch": 0.42, "learning_rate": 1.7216588882113028e-05, "loss": 1.6001, "step": 673000 }, { "epoch": 0.42, "learning_rate": 1.7214520968949663e-05, "loss": 1.6395, "step": 673500 }, { "epoch": 0.42, "learning_rate": 1.72124530557863e-05, "loss": 1.6355, "step": 674000 }, { "epoch": 0.42, "learning_rate": 1.721038514262294e-05, "loss": 1.6219, "step": 674500 }, { "epoch": 0.42, "learning_rate": 1.7208317229459574e-05, "loss": 1.6117, "step": 675000 }, { "epoch": 0.42, "learning_rate": 1.720624931629621e-05, "loss": 1.6335, "step": 675500 }, { "epoch": 0.42, "learning_rate": 1.7204181403132848e-05, "loss": 1.6276, "step": 676000 }, { "epoch": 0.42, "learning_rate": 1.7202113489969486e-05, "loss": 1.6281, "step": 676500 }, { "epoch": 0.42, "learning_rate": 1.720004557680612e-05, "loss": 1.6304, "step": 677000 }, { "epoch": 0.42, "learning_rate": 1.7197977663642756e-05, "loss": 1.6321, "step": 677500 }, { "epoch": 0.42, "learning_rate": 1.7195909750479394e-05, "loss": 1.6247, "step": 678000 }, { "epoch": 0.42, "learning_rate": 1.7193841837316033e-05, "loss": 1.6113, "step": 678500 }, { "epoch": 0.42, "learning_rate": 1.7191773924152668e-05, "loss": 1.629, "step": 679000 }, { "epoch": 0.42, "learning_rate": 1.7189706010989306e-05, "loss": 1.603, "step": 679500 }, { "epoch": 0.42, "learning_rate": 1.7187638097825944e-05, "loss": 1.5872, "step": 680000 }, { "epoch": 0.42, "learning_rate": 1.718557018466258e-05, "loss": 1.6194, "step": 680500 }, { "epoch": 0.42, "learning_rate": 1.7183502271499214e-05, "loss": 1.6865, "step": 681000 }, { "epoch": 0.42, "learning_rate": 1.7181434358335853e-05, "loss": 1.6145, "step": 681500 }, { "epoch": 0.42, "learning_rate": 1.717936644517249e-05, "loss": 1.6291, "step": 682000 }, { "epoch": 0.42, "learning_rate": 1.7177298532009126e-05, "loss": 1.6212, "step": 682500 }, { "epoch": 0.42, "learning_rate": 1.717523061884576e-05, "loss": 1.6258, "step": 683000 }, { "epoch": 0.42, "learning_rate": 1.71731627056824e-05, "loss": 1.621, "step": 683500 }, { "epoch": 0.42, "learning_rate": 1.7171094792519038e-05, "loss": 1.6305, "step": 684000 }, { "epoch": 0.42, "learning_rate": 1.7169026879355673e-05, "loss": 1.6323, "step": 684500 }, { "epoch": 0.42, "learning_rate": 1.7166958966192308e-05, "loss": 1.6341, "step": 685000 }, { "epoch": 0.43, "learning_rate": 1.7164891053028946e-05, "loss": 1.6249, "step": 685500 }, { "epoch": 0.43, "learning_rate": 1.7162823139865584e-05, "loss": 1.6121, "step": 686000 }, { "epoch": 0.43, "learning_rate": 1.716075522670222e-05, "loss": 1.584, "step": 686500 }, { "epoch": 0.43, "learning_rate": 1.7158687313538854e-05, "loss": 1.6156, "step": 687000 }, { "epoch": 0.43, "learning_rate": 1.7156619400375493e-05, "loss": 1.6302, "step": 687500 }, { "epoch": 0.43, "learning_rate": 1.715455148721213e-05, "loss": 1.6081, "step": 688000 }, { "epoch": 0.43, "learning_rate": 1.7152483574048766e-05, "loss": 1.6222, "step": 688500 }, { "epoch": 0.43, "learning_rate": 1.71504156608854e-05, "loss": 1.6334, "step": 689000 }, { "epoch": 0.43, "learning_rate": 1.714834774772204e-05, "loss": 1.6235, "step": 689500 }, { "epoch": 0.43, "learning_rate": 1.7146279834558677e-05, "loss": 1.5851, "step": 690000 }, { "epoch": 0.43, "learning_rate": 1.7144211921395312e-05, "loss": 1.6439, "step": 690500 }, { "epoch": 0.43, "learning_rate": 1.7142144008231947e-05, "loss": 1.6358, "step": 691000 }, { "epoch": 0.43, "learning_rate": 1.7140076095068586e-05, "loss": 1.6366, "step": 691500 }, { "epoch": 0.43, "learning_rate": 1.7138008181905224e-05, "loss": 1.6105, "step": 692000 }, { "epoch": 0.43, "learning_rate": 1.713594026874186e-05, "loss": 1.6611, "step": 692500 }, { "epoch": 0.43, "learning_rate": 1.7133872355578497e-05, "loss": 1.6261, "step": 693000 }, { "epoch": 0.43, "learning_rate": 1.7131804442415136e-05, "loss": 1.6112, "step": 693500 }, { "epoch": 0.43, "learning_rate": 1.712973652925177e-05, "loss": 1.6321, "step": 694000 }, { "epoch": 0.43, "learning_rate": 1.7127668616088406e-05, "loss": 1.6309, "step": 694500 }, { "epoch": 0.43, "learning_rate": 1.7125600702925044e-05, "loss": 1.6227, "step": 695000 }, { "epoch": 0.43, "learning_rate": 1.7123532789761682e-05, "loss": 1.6312, "step": 695500 }, { "epoch": 0.43, "learning_rate": 1.7121464876598317e-05, "loss": 1.5981, "step": 696000 }, { "epoch": 0.43, "learning_rate": 1.7119396963434952e-05, "loss": 1.6602, "step": 696500 }, { "epoch": 0.43, "learning_rate": 1.711732905027159e-05, "loss": 1.6249, "step": 697000 }, { "epoch": 0.43, "learning_rate": 1.711526113710823e-05, "loss": 1.6476, "step": 697500 }, { "epoch": 0.43, "learning_rate": 1.7113193223944864e-05, "loss": 1.6283, "step": 698000 }, { "epoch": 0.43, "learning_rate": 1.71111253107815e-05, "loss": 1.6297, "step": 698500 }, { "epoch": 0.43, "learning_rate": 1.7109057397618137e-05, "loss": 1.6111, "step": 699000 }, { "epoch": 0.43, "learning_rate": 1.7106989484454776e-05, "loss": 1.6241, "step": 699500 }, { "epoch": 0.43, "learning_rate": 1.710492157129141e-05, "loss": 1.6062, "step": 700000 }, { "epoch": 0.43, "learning_rate": 1.7102853658128046e-05, "loss": 1.5961, "step": 700500 }, { "epoch": 0.43, "learning_rate": 1.7100785744964684e-05, "loss": 1.6076, "step": 701000 }, { "epoch": 0.44, "learning_rate": 1.7098717831801322e-05, "loss": 1.6305, "step": 701500 }, { "epoch": 0.44, "learning_rate": 1.7096649918637957e-05, "loss": 1.6294, "step": 702000 }, { "epoch": 0.44, "learning_rate": 1.7094582005474592e-05, "loss": 1.616, "step": 702500 }, { "epoch": 0.44, "learning_rate": 1.709251409231123e-05, "loss": 1.6168, "step": 703000 }, { "epoch": 0.44, "learning_rate": 1.709044617914787e-05, "loss": 1.6258, "step": 703500 }, { "epoch": 0.44, "learning_rate": 1.7088378265984504e-05, "loss": 1.6252, "step": 704000 }, { "epoch": 0.44, "learning_rate": 1.7086310352821142e-05, "loss": 1.6517, "step": 704500 }, { "epoch": 0.44, "learning_rate": 1.708424243965778e-05, "loss": 1.5765, "step": 705000 }, { "epoch": 0.44, "learning_rate": 1.7082174526494415e-05, "loss": 1.6487, "step": 705500 }, { "epoch": 0.44, "learning_rate": 1.708010661333105e-05, "loss": 1.6345, "step": 706000 }, { "epoch": 0.44, "learning_rate": 1.707803870016769e-05, "loss": 1.6031, "step": 706500 }, { "epoch": 0.44, "learning_rate": 1.7075970787004327e-05, "loss": 1.6342, "step": 707000 }, { "epoch": 0.44, "learning_rate": 1.7073902873840962e-05, "loss": 1.6206, "step": 707500 }, { "epoch": 0.44, "learning_rate": 1.7071834960677597e-05, "loss": 1.6423, "step": 708000 }, { "epoch": 0.44, "learning_rate": 1.7069767047514235e-05, "loss": 1.6234, "step": 708500 }, { "epoch": 0.44, "learning_rate": 1.7067699134350874e-05, "loss": 1.6136, "step": 709000 }, { "epoch": 0.44, "learning_rate": 1.706563122118751e-05, "loss": 1.6081, "step": 709500 }, { "epoch": 0.44, "learning_rate": 1.7063563308024144e-05, "loss": 1.6156, "step": 710000 }, { "epoch": 0.44, "learning_rate": 1.7061495394860782e-05, "loss": 1.6147, "step": 710500 }, { "epoch": 0.44, "learning_rate": 1.705942748169742e-05, "loss": 1.6214, "step": 711000 }, { "epoch": 0.44, "learning_rate": 1.7057359568534055e-05, "loss": 1.6178, "step": 711500 }, { "epoch": 0.44, "learning_rate": 1.705529165537069e-05, "loss": 1.6208, "step": 712000 }, { "epoch": 0.44, "learning_rate": 1.705322374220733e-05, "loss": 1.6071, "step": 712500 }, { "epoch": 0.44, "learning_rate": 1.7051155829043967e-05, "loss": 1.5874, "step": 713000 }, { "epoch": 0.44, "learning_rate": 1.7049087915880602e-05, "loss": 1.6096, "step": 713500 }, { "epoch": 0.44, "learning_rate": 1.7047020002717237e-05, "loss": 1.629, "step": 714000 }, { "epoch": 0.44, "learning_rate": 1.7044952089553875e-05, "loss": 1.5995, "step": 714500 }, { "epoch": 0.44, "learning_rate": 1.7042884176390514e-05, "loss": 1.6549, "step": 715000 }, { "epoch": 0.44, "learning_rate": 1.704081626322715e-05, "loss": 1.6188, "step": 715500 }, { "epoch": 0.44, "learning_rate": 1.7038748350063784e-05, "loss": 1.6344, "step": 716000 }, { "epoch": 0.44, "learning_rate": 1.7036680436900422e-05, "loss": 1.6217, "step": 716500 }, { "epoch": 0.44, "learning_rate": 1.703461252373706e-05, "loss": 1.6103, "step": 717000 }, { "epoch": 0.45, "learning_rate": 1.7032544610573695e-05, "loss": 1.636, "step": 717500 }, { "epoch": 0.45, "learning_rate": 1.7030476697410334e-05, "loss": 1.635, "step": 718000 }, { "epoch": 0.45, "learning_rate": 1.7028408784246972e-05, "loss": 1.6325, "step": 718500 }, { "epoch": 0.45, "learning_rate": 1.7026340871083607e-05, "loss": 1.6302, "step": 719000 }, { "epoch": 0.45, "learning_rate": 1.7024272957920242e-05, "loss": 1.5954, "step": 719500 }, { "epoch": 0.45, "learning_rate": 1.702220504475688e-05, "loss": 1.6313, "step": 720000 }, { "epoch": 0.45, "learning_rate": 1.702013713159352e-05, "loss": 1.6005, "step": 720500 }, { "epoch": 0.45, "learning_rate": 1.7018069218430154e-05, "loss": 1.6064, "step": 721000 }, { "epoch": 0.45, "learning_rate": 1.701600130526679e-05, "loss": 1.6423, "step": 721500 }, { "epoch": 0.45, "learning_rate": 1.7013933392103427e-05, "loss": 1.6485, "step": 722000 }, { "epoch": 0.45, "learning_rate": 1.7011865478940065e-05, "loss": 1.6033, "step": 722500 }, { "epoch": 0.45, "learning_rate": 1.70097975657767e-05, "loss": 1.627, "step": 723000 }, { "epoch": 0.45, "learning_rate": 1.7007729652613335e-05, "loss": 1.6045, "step": 723500 }, { "epoch": 0.45, "learning_rate": 1.7005661739449973e-05, "loss": 1.6407, "step": 724000 }, { "epoch": 0.45, "learning_rate": 1.7003593826286612e-05, "loss": 1.6423, "step": 724500 }, { "epoch": 0.45, "learning_rate": 1.7001525913123247e-05, "loss": 1.6242, "step": 725000 }, { "epoch": 0.45, "learning_rate": 1.6999457999959882e-05, "loss": 1.6556, "step": 725500 }, { "epoch": 0.45, "learning_rate": 1.699739008679652e-05, "loss": 1.6116, "step": 726000 }, { "epoch": 0.45, "learning_rate": 1.699532217363316e-05, "loss": 1.6284, "step": 726500 }, { "epoch": 0.45, "learning_rate": 1.6993254260469793e-05, "loss": 1.618, "step": 727000 }, { "epoch": 0.45, "learning_rate": 1.699118634730643e-05, "loss": 1.5947, "step": 727500 }, { "epoch": 0.45, "learning_rate": 1.6989118434143067e-05, "loss": 1.6173, "step": 728000 }, { "epoch": 0.45, "learning_rate": 1.6987050520979705e-05, "loss": 1.6308, "step": 728500 }, { "epoch": 0.45, "learning_rate": 1.698498260781634e-05, "loss": 1.6409, "step": 729000 }, { "epoch": 0.45, "learning_rate": 1.6982914694652975e-05, "loss": 1.6495, "step": 729500 }, { "epoch": 0.45, "learning_rate": 1.6980846781489613e-05, "loss": 1.6259, "step": 730000 }, { "epoch": 0.45, "learning_rate": 1.697877886832625e-05, "loss": 1.6356, "step": 730500 }, { "epoch": 0.45, "learning_rate": 1.6976710955162887e-05, "loss": 1.6001, "step": 731000 }, { "epoch": 0.45, "learning_rate": 1.6974643041999525e-05, "loss": 1.6428, "step": 731500 }, { "epoch": 0.45, "learning_rate": 1.6972575128836163e-05, "loss": 1.5979, "step": 732000 }, { "epoch": 0.45, "learning_rate": 1.6970507215672798e-05, "loss": 1.6392, "step": 732500 }, { "epoch": 0.45, "learning_rate": 1.6968439302509433e-05, "loss": 1.627, "step": 733000 }, { "epoch": 0.46, "learning_rate": 1.696637138934607e-05, "loss": 1.6309, "step": 733500 }, { "epoch": 0.46, "learning_rate": 1.696430347618271e-05, "loss": 1.6387, "step": 734000 }, { "epoch": 0.46, "learning_rate": 1.6962235563019345e-05, "loss": 1.6423, "step": 734500 }, { "epoch": 0.46, "learning_rate": 1.696016764985598e-05, "loss": 1.6428, "step": 735000 }, { "epoch": 0.46, "learning_rate": 1.6958099736692618e-05, "loss": 1.5919, "step": 735500 }, { "epoch": 0.46, "learning_rate": 1.6956031823529257e-05, "loss": 1.6586, "step": 736000 }, { "epoch": 0.46, "learning_rate": 1.695396391036589e-05, "loss": 1.6269, "step": 736500 }, { "epoch": 0.46, "learning_rate": 1.6951895997202526e-05, "loss": 1.6182, "step": 737000 }, { "epoch": 0.46, "learning_rate": 1.6949828084039165e-05, "loss": 1.6255, "step": 737500 }, { "epoch": 0.46, "learning_rate": 1.6947760170875803e-05, "loss": 1.6356, "step": 738000 }, { "epoch": 0.46, "learning_rate": 1.6945692257712438e-05, "loss": 1.5926, "step": 738500 }, { "epoch": 0.46, "learning_rate": 1.6943624344549073e-05, "loss": 1.6191, "step": 739000 }, { "epoch": 0.46, "learning_rate": 1.694155643138571e-05, "loss": 1.6305, "step": 739500 }, { "epoch": 0.46, "learning_rate": 1.693948851822235e-05, "loss": 1.6215, "step": 740000 }, { "epoch": 0.46, "learning_rate": 1.6937420605058985e-05, "loss": 1.6102, "step": 740500 }, { "epoch": 0.46, "learning_rate": 1.693535269189562e-05, "loss": 1.6127, "step": 741000 }, { "epoch": 0.46, "learning_rate": 1.6933284778732258e-05, "loss": 1.6285, "step": 741500 }, { "epoch": 0.46, "learning_rate": 1.6931216865568896e-05, "loss": 1.621, "step": 742000 }, { "epoch": 0.46, "learning_rate": 1.692914895240553e-05, "loss": 1.6199, "step": 742500 }, { "epoch": 0.46, "learning_rate": 1.692708103924217e-05, "loss": 1.6117, "step": 743000 }, { "epoch": 0.46, "learning_rate": 1.6925013126078808e-05, "loss": 1.6241, "step": 743500 }, { "epoch": 0.46, "learning_rate": 1.6922945212915443e-05, "loss": 1.5992, "step": 744000 }, { "epoch": 0.46, "learning_rate": 1.6920877299752078e-05, "loss": 1.6158, "step": 744500 }, { "epoch": 0.46, "learning_rate": 1.6918809386588716e-05, "loss": 1.6026, "step": 745000 }, { "epoch": 0.46, "learning_rate": 1.6916741473425355e-05, "loss": 1.6373, "step": 745500 }, { "epoch": 0.46, "learning_rate": 1.691467356026199e-05, "loss": 1.5959, "step": 746000 }, { "epoch": 0.46, "learning_rate": 1.6912605647098625e-05, "loss": 1.6257, "step": 746500 }, { "epoch": 0.46, "learning_rate": 1.6910537733935263e-05, "loss": 1.6163, "step": 747000 }, { "epoch": 0.46, "learning_rate": 1.69084698207719e-05, "loss": 1.5829, "step": 747500 }, { "epoch": 0.46, "learning_rate": 1.6906401907608536e-05, "loss": 1.6134, "step": 748000 }, { "epoch": 0.46, "learning_rate": 1.690433399444517e-05, "loss": 1.6381, "step": 748500 }, { "epoch": 0.46, "learning_rate": 1.690226608128181e-05, "loss": 1.6317, "step": 749000 }, { "epoch": 0.46, "learning_rate": 1.6900198168118448e-05, "loss": 1.63, "step": 749500 }, { "epoch": 0.47, "learning_rate": 1.6898130254955083e-05, "loss": 1.6404, "step": 750000 }, { "epoch": 0.47, "learning_rate": 1.6896062341791718e-05, "loss": 1.5971, "step": 750500 }, { "epoch": 0.47, "learning_rate": 1.6893994428628356e-05, "loss": 1.6156, "step": 751000 }, { "epoch": 0.47, "learning_rate": 1.6891926515464995e-05, "loss": 1.612, "step": 751500 }, { "epoch": 0.47, "learning_rate": 1.688985860230163e-05, "loss": 1.6083, "step": 752000 }, { "epoch": 0.47, "learning_rate": 1.6887790689138264e-05, "loss": 1.6326, "step": 752500 }, { "epoch": 0.47, "learning_rate": 1.6885722775974903e-05, "loss": 1.6283, "step": 753000 }, { "epoch": 0.47, "learning_rate": 1.688365486281154e-05, "loss": 1.6103, "step": 753500 }, { "epoch": 0.47, "learning_rate": 1.6881586949648176e-05, "loss": 1.5798, "step": 754000 }, { "epoch": 0.47, "learning_rate": 1.687951903648481e-05, "loss": 1.6315, "step": 754500 }, { "epoch": 0.47, "learning_rate": 1.687745112332145e-05, "loss": 1.6222, "step": 755000 }, { "epoch": 0.47, "learning_rate": 1.6875383210158088e-05, "loss": 1.6095, "step": 755500 }, { "epoch": 0.47, "learning_rate": 1.6873315296994723e-05, "loss": 1.6415, "step": 756000 }, { "epoch": 0.47, "learning_rate": 1.687124738383136e-05, "loss": 1.612, "step": 756500 }, { "epoch": 0.47, "learning_rate": 1.6869179470668e-05, "loss": 1.6159, "step": 757000 }, { "epoch": 0.47, "learning_rate": 1.6867111557504634e-05, "loss": 1.6069, "step": 757500 }, { "epoch": 0.47, "learning_rate": 1.686504364434127e-05, "loss": 1.6274, "step": 758000 }, { "epoch": 0.47, "learning_rate": 1.6862975731177908e-05, "loss": 1.6184, "step": 758500 }, { "epoch": 0.47, "learning_rate": 1.6860907818014546e-05, "loss": 1.6288, "step": 759000 }, { "epoch": 0.47, "learning_rate": 1.685883990485118e-05, "loss": 1.62, "step": 759500 }, { "epoch": 0.47, "learning_rate": 1.6856771991687816e-05, "loss": 1.6481, "step": 760000 }, { "epoch": 0.47, "learning_rate": 1.6854704078524454e-05, "loss": 1.6165, "step": 760500 }, { "epoch": 0.47, "learning_rate": 1.6852636165361093e-05, "loss": 1.6162, "step": 761000 }, { "epoch": 0.47, "learning_rate": 1.6850568252197728e-05, "loss": 1.6005, "step": 761500 }, { "epoch": 0.47, "learning_rate": 1.6848500339034363e-05, "loss": 1.6317, "step": 762000 }, { "epoch": 0.47, "learning_rate": 1.6846432425871e-05, "loss": 1.6315, "step": 762500 }, { "epoch": 0.47, "learning_rate": 1.684436451270764e-05, "loss": 1.6227, "step": 763000 }, { "epoch": 0.47, "learning_rate": 1.6842296599544274e-05, "loss": 1.6105, "step": 763500 }, { "epoch": 0.47, "learning_rate": 1.684022868638091e-05, "loss": 1.6221, "step": 764000 }, { "epoch": 0.47, "learning_rate": 1.6838160773217548e-05, "loss": 1.6395, "step": 764500 }, { "epoch": 0.47, "learning_rate": 1.6836092860054186e-05, "loss": 1.6034, "step": 765000 }, { "epoch": 0.47, "learning_rate": 1.683402494689082e-05, "loss": 1.5798, "step": 765500 }, { "epoch": 0.48, "learning_rate": 1.6831957033727456e-05, "loss": 1.6371, "step": 766000 }, { "epoch": 0.48, "learning_rate": 1.6829889120564094e-05, "loss": 1.6359, "step": 766500 }, { "epoch": 0.48, "learning_rate": 1.6827821207400733e-05, "loss": 1.5881, "step": 767000 }, { "epoch": 0.48, "learning_rate": 1.6825753294237368e-05, "loss": 1.6114, "step": 767500 }, { "epoch": 0.48, "learning_rate": 1.6823685381074002e-05, "loss": 1.608, "step": 768000 }, { "epoch": 0.48, "learning_rate": 1.6821617467910644e-05, "loss": 1.595, "step": 768500 }, { "epoch": 0.48, "learning_rate": 1.681954955474728e-05, "loss": 1.6101, "step": 769000 }, { "epoch": 0.48, "learning_rate": 1.6817481641583914e-05, "loss": 1.6065, "step": 769500 }, { "epoch": 0.48, "learning_rate": 1.6815413728420553e-05, "loss": 1.6117, "step": 770000 }, { "epoch": 0.48, "learning_rate": 1.681334581525719e-05, "loss": 1.6382, "step": 770500 }, { "epoch": 0.48, "learning_rate": 1.6811277902093826e-05, "loss": 1.6375, "step": 771000 }, { "epoch": 0.48, "learning_rate": 1.680920998893046e-05, "loss": 1.607, "step": 771500 }, { "epoch": 0.48, "learning_rate": 1.68071420757671e-05, "loss": 1.6272, "step": 772000 }, { "epoch": 0.48, "learning_rate": 1.6805074162603737e-05, "loss": 1.6165, "step": 772500 }, { "epoch": 0.48, "learning_rate": 1.6803006249440372e-05, "loss": 1.6434, "step": 773000 }, { "epoch": 0.48, "learning_rate": 1.6800938336277007e-05, "loss": 1.6218, "step": 773500 }, { "epoch": 0.48, "learning_rate": 1.6798870423113646e-05, "loss": 1.6327, "step": 774000 }, { "epoch": 0.48, "learning_rate": 1.6796802509950284e-05, "loss": 1.6334, "step": 774500 }, { "epoch": 0.48, "learning_rate": 1.679473459678692e-05, "loss": 1.6142, "step": 775000 }, { "epoch": 0.48, "learning_rate": 1.6792666683623554e-05, "loss": 1.6505, "step": 775500 }, { "epoch": 0.48, "learning_rate": 1.6790598770460192e-05, "loss": 1.6233, "step": 776000 }, { "epoch": 0.48, "learning_rate": 1.678853085729683e-05, "loss": 1.6019, "step": 776500 }, { "epoch": 0.48, "learning_rate": 1.6786462944133466e-05, "loss": 1.632, "step": 777000 }, { "epoch": 0.48, "learning_rate": 1.67843950309701e-05, "loss": 1.6164, "step": 777500 }, { "epoch": 0.48, "learning_rate": 1.678232711780674e-05, "loss": 1.5926, "step": 778000 }, { "epoch": 0.48, "learning_rate": 1.6780259204643377e-05, "loss": 1.6043, "step": 778500 }, { "epoch": 0.48, "learning_rate": 1.6778191291480012e-05, "loss": 1.6415, "step": 779000 }, { "epoch": 0.48, "learning_rate": 1.6776123378316647e-05, "loss": 1.617, "step": 779500 }, { "epoch": 0.48, "learning_rate": 1.6774055465153286e-05, "loss": 1.6147, "step": 780000 }, { "epoch": 0.48, "learning_rate": 1.6771987551989924e-05, "loss": 1.6235, "step": 780500 }, { "epoch": 0.48, "learning_rate": 1.676991963882656e-05, "loss": 1.5808, "step": 781000 }, { "epoch": 0.48, "learning_rate": 1.6767851725663197e-05, "loss": 1.6052, "step": 781500 }, { "epoch": 0.49, "learning_rate": 1.6765783812499836e-05, "loss": 1.6179, "step": 782000 }, { "epoch": 0.49, "learning_rate": 1.676371589933647e-05, "loss": 1.6264, "step": 782500 }, { "epoch": 0.49, "learning_rate": 1.6761647986173106e-05, "loss": 1.6164, "step": 783000 }, { "epoch": 0.49, "learning_rate": 1.6759580073009744e-05, "loss": 1.6288, "step": 783500 }, { "epoch": 0.49, "learning_rate": 1.6757512159846382e-05, "loss": 1.6343, "step": 784000 }, { "epoch": 0.49, "learning_rate": 1.6755444246683017e-05, "loss": 1.5849, "step": 784500 }, { "epoch": 0.49, "learning_rate": 1.6753376333519652e-05, "loss": 1.604, "step": 785000 }, { "epoch": 0.49, "learning_rate": 1.675130842035629e-05, "loss": 1.606, "step": 785500 }, { "epoch": 0.49, "learning_rate": 1.674924050719293e-05, "loss": 1.6209, "step": 786000 }, { "epoch": 0.49, "learning_rate": 1.6747172594029564e-05, "loss": 1.5959, "step": 786500 }, { "epoch": 0.49, "learning_rate": 1.67451046808662e-05, "loss": 1.6141, "step": 787000 }, { "epoch": 0.49, "learning_rate": 1.6743036767702837e-05, "loss": 1.6136, "step": 787500 }, { "epoch": 0.49, "learning_rate": 1.6740968854539475e-05, "loss": 1.6197, "step": 788000 }, { "epoch": 0.49, "learning_rate": 1.673890094137611e-05, "loss": 1.5811, "step": 788500 }, { "epoch": 0.49, "learning_rate": 1.6736833028212745e-05, "loss": 1.5927, "step": 789000 }, { "epoch": 0.49, "learning_rate": 1.6734765115049384e-05, "loss": 1.6014, "step": 789500 }, { "epoch": 0.49, "learning_rate": 1.6732697201886022e-05, "loss": 1.6378, "step": 790000 }, { "epoch": 0.49, "learning_rate": 1.6730629288722657e-05, "loss": 1.6117, "step": 790500 }, { "epoch": 0.49, "learning_rate": 1.6728561375559292e-05, "loss": 1.6138, "step": 791000 }, { "epoch": 0.49, "learning_rate": 1.672649346239593e-05, "loss": 1.6263, "step": 791500 }, { "epoch": 0.49, "learning_rate": 1.672442554923257e-05, "loss": 1.6092, "step": 792000 }, { "epoch": 0.49, "learning_rate": 1.6722357636069204e-05, "loss": 1.597, "step": 792500 }, { "epoch": 0.49, "learning_rate": 1.672028972290584e-05, "loss": 1.6182, "step": 793000 }, { "epoch": 0.49, "learning_rate": 1.6718221809742477e-05, "loss": 1.5879, "step": 793500 }, { "epoch": 0.49, "learning_rate": 1.6716153896579115e-05, "loss": 1.6249, "step": 794000 }, { "epoch": 0.49, "learning_rate": 1.671408598341575e-05, "loss": 1.6142, "step": 794500 }, { "epoch": 0.49, "learning_rate": 1.671201807025239e-05, "loss": 1.6236, "step": 795000 }, { "epoch": 0.49, "learning_rate": 1.6709950157089027e-05, "loss": 1.6165, "step": 795500 }, { "epoch": 0.49, "learning_rate": 1.6707882243925662e-05, "loss": 1.5858, "step": 796000 }, { "epoch": 0.49, "learning_rate": 1.6705814330762297e-05, "loss": 1.6236, "step": 796500 }, { "epoch": 0.49, "learning_rate": 1.6703746417598935e-05, "loss": 1.6028, "step": 797000 }, { "epoch": 0.49, "learning_rate": 1.6701678504435574e-05, "loss": 1.6031, "step": 797500 }, { "epoch": 0.5, "learning_rate": 1.669961059127221e-05, "loss": 1.6243, "step": 798000 }, { "epoch": 0.5, "learning_rate": 1.6697542678108844e-05, "loss": 1.5955, "step": 798500 }, { "epoch": 0.5, "learning_rate": 1.6695474764945482e-05, "loss": 1.5934, "step": 799000 }, { "epoch": 0.5, "learning_rate": 1.669340685178212e-05, "loss": 1.6422, "step": 799500 }, { "epoch": 0.5, "learning_rate": 1.6691338938618755e-05, "loss": 1.5994, "step": 800000 }, { "epoch": 0.5, "learning_rate": 1.668927102545539e-05, "loss": 1.5911, "step": 800500 }, { "epoch": 0.5, "learning_rate": 1.668720311229203e-05, "loss": 1.6031, "step": 801000 }, { "epoch": 0.5, "learning_rate": 1.6685135199128667e-05, "loss": 1.6206, "step": 801500 }, { "epoch": 0.5, "learning_rate": 1.6683067285965302e-05, "loss": 1.6125, "step": 802000 }, { "epoch": 0.5, "learning_rate": 1.6680999372801937e-05, "loss": 1.6397, "step": 802500 }, { "epoch": 0.5, "learning_rate": 1.6678931459638575e-05, "loss": 1.6119, "step": 803000 }, { "epoch": 0.5, "learning_rate": 1.6676863546475213e-05, "loss": 1.5956, "step": 803500 } ], "max_steps": 4835793, "num_train_epochs": 3, "total_flos": 5.587487855033885e+17, "trial_name": null, "trial_params": null }