{ "best_metric": null, "best_model_checkpoint": null, "epoch": 5.9924041112024895, "global_step": 2900000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 3.99965560860331e-06, "loss": 8.3557, "step": 500 }, { "epoch": 0.0, "learning_rate": 3.9993112172066205e-06, "loss": 7.6896, "step": 1000 }, { "epoch": 0.0, "learning_rate": 3.998966825809931e-06, "loss": 7.4825, "step": 1500 }, { "epoch": 0.0, "learning_rate": 3.998622434413241e-06, "loss": 7.3522, "step": 2000 }, { "epoch": 0.0, "learning_rate": 3.9982780430165514e-06, "loss": 7.2424, "step": 2500 }, { "epoch": 0.0, "learning_rate": 3.997933651619862e-06, "loss": 7.1508, "step": 3000 }, { "epoch": 0.0, "learning_rate": 3.997589260223172e-06, "loss": 7.0708, "step": 3500 }, { "epoch": 0.0, "learning_rate": 3.997244868826483e-06, "loss": 6.9848, "step": 4000 }, { "epoch": 0.0, "learning_rate": 3.996900477429793e-06, "loss": 6.9134, "step": 4500 }, { "epoch": 0.01, "learning_rate": 3.996556086033104e-06, "loss": 6.8522, "step": 5000 }, { "epoch": 0.01, "learning_rate": 3.996211694636413e-06, "loss": 6.7865, "step": 5500 }, { "epoch": 0.01, "learning_rate": 3.9958673032397245e-06, "loss": 6.7303, "step": 6000 }, { "epoch": 0.01, "learning_rate": 3.995522911843035e-06, "loss": 6.6764, "step": 6500 }, { "epoch": 0.01, "learning_rate": 3.995178520446344e-06, "loss": 6.6253, "step": 7000 }, { "epoch": 0.01, "learning_rate": 3.9948341290496555e-06, "loss": 6.572, "step": 7500 }, { "epoch": 0.01, "learning_rate": 3.994489737652965e-06, "loss": 6.5255, "step": 8000 }, { "epoch": 0.01, "learning_rate": 3.994145346256276e-06, "loss": 6.4814, "step": 8500 }, { "epoch": 0.01, "learning_rate": 3.9938009548595865e-06, "loss": 6.4416, "step": 9000 }, { "epoch": 0.01, "learning_rate": 3.993456563462897e-06, "loss": 6.4007, "step": 9500 }, { "epoch": 0.01, "learning_rate": 3.993112172066207e-06, "loss": 6.3494, "step": 10000 }, { "epoch": 0.01, "learning_rate": 3.9927677806695174e-06, "loss": 6.3175, "step": 10500 }, { "epoch": 0.01, "learning_rate": 3.992423389272828e-06, "loss": 6.2636, "step": 11000 }, { "epoch": 0.01, "learning_rate": 3.992078997876138e-06, "loss": 6.241, "step": 11500 }, { "epoch": 0.01, "learning_rate": 3.991734606479448e-06, "loss": 6.2113, "step": 12000 }, { "epoch": 0.01, "learning_rate": 3.991390215082759e-06, "loss": 6.1746, "step": 12500 }, { "epoch": 0.01, "learning_rate": 3.991045823686069e-06, "loss": 6.1459, "step": 13000 }, { "epoch": 0.01, "learning_rate": 3.990701432289379e-06, "loss": 6.1061, "step": 13500 }, { "epoch": 0.01, "learning_rate": 3.99035704089269e-06, "loss": 6.0712, "step": 14000 }, { "epoch": 0.01, "learning_rate": 3.990012649496e-06, "loss": 6.0384, "step": 14500 }, { "epoch": 0.02, "learning_rate": 3.98966825809931e-06, "loss": 6.0229, "step": 15000 }, { "epoch": 0.02, "learning_rate": 3.989323866702621e-06, "loss": 5.9854, "step": 15500 }, { "epoch": 0.02, "learning_rate": 3.988979475305931e-06, "loss": 5.9707, "step": 16000 }, { "epoch": 0.02, "learning_rate": 3.988635083909241e-06, "loss": 5.9438, "step": 16500 }, { "epoch": 0.02, "learning_rate": 3.9882906925125525e-06, "loss": 5.9116, "step": 17000 }, { "epoch": 0.02, "learning_rate": 3.987946301115862e-06, "loss": 5.8896, "step": 17500 }, { "epoch": 0.02, "learning_rate": 3.987601909719173e-06, "loss": 5.8604, "step": 18000 }, { "epoch": 0.02, "learning_rate": 3.987257518322483e-06, "loss": 5.8416, "step": 18500 }, { "epoch": 0.02, "learning_rate": 3.986913126925794e-06, "loss": 5.8157, "step": 19000 }, { "epoch": 0.02, "learning_rate": 3.986568735529104e-06, "loss": 5.7923, "step": 19500 }, { "epoch": 0.02, "learning_rate": 3.986224344132414e-06, "loss": 5.7784, "step": 20000 }, { "epoch": 0.02, "learning_rate": 3.985879952735725e-06, "loss": 5.7518, "step": 20500 }, { "epoch": 0.02, "learning_rate": 3.985535561339035e-06, "loss": 5.7338, "step": 21000 }, { "epoch": 0.02, "learning_rate": 3.985191169942345e-06, "loss": 5.717, "step": 21500 }, { "epoch": 0.02, "learning_rate": 3.984846778545656e-06, "loss": 5.6839, "step": 22000 }, { "epoch": 0.02, "learning_rate": 3.984502387148966e-06, "loss": 5.6727, "step": 22500 }, { "epoch": 0.02, "learning_rate": 3.984157995752276e-06, "loss": 5.6531, "step": 23000 }, { "epoch": 0.02, "learning_rate": 3.983813604355587e-06, "loss": 5.6393, "step": 23500 }, { "epoch": 0.02, "learning_rate": 3.983469212958897e-06, "loss": 5.6119, "step": 24000 }, { "epoch": 0.03, "learning_rate": 3.983124821562207e-06, "loss": 5.6036, "step": 24500 }, { "epoch": 0.03, "learning_rate": 3.982780430165518e-06, "loss": 5.5893, "step": 25000 }, { "epoch": 0.03, "learning_rate": 3.982436038768828e-06, "loss": 5.5609, "step": 25500 }, { "epoch": 0.03, "learning_rate": 3.982091647372138e-06, "loss": 5.5475, "step": 26000 }, { "epoch": 0.03, "learning_rate": 3.981747255975449e-06, "loss": 5.5341, "step": 26500 }, { "epoch": 0.03, "learning_rate": 3.981402864578759e-06, "loss": 5.5128, "step": 27000 }, { "epoch": 0.03, "learning_rate": 3.98105847318207e-06, "loss": 5.4956, "step": 27500 }, { "epoch": 0.03, "learning_rate": 3.9807140817853795e-06, "loss": 5.4745, "step": 28000 }, { "epoch": 0.03, "learning_rate": 3.98036969038869e-06, "loss": 5.4591, "step": 28500 }, { "epoch": 0.03, "learning_rate": 3.980025298992001e-06, "loss": 5.4589, "step": 29000 }, { "epoch": 0.03, "learning_rate": 3.9796809075953105e-06, "loss": 5.4404, "step": 29500 }, { "epoch": 0.03, "learning_rate": 3.979336516198622e-06, "loss": 5.4239, "step": 30000 }, { "epoch": 0.03, "learning_rate": 3.978992124801932e-06, "loss": 5.4106, "step": 30500 }, { "epoch": 0.03, "learning_rate": 3.978647733405242e-06, "loss": 5.3914, "step": 31000 }, { "epoch": 0.03, "learning_rate": 3.978303342008553e-06, "loss": 5.3878, "step": 31500 }, { "epoch": 0.03, "learning_rate": 3.977958950611863e-06, "loss": 5.3787, "step": 32000 }, { "epoch": 0.03, "learning_rate": 3.977614559215173e-06, "loss": 5.3599, "step": 32500 }, { "epoch": 0.03, "learning_rate": 3.977270167818484e-06, "loss": 5.3435, "step": 33000 }, { "epoch": 0.03, "learning_rate": 3.976925776421794e-06, "loss": 5.3195, "step": 33500 }, { "epoch": 0.04, "learning_rate": 3.976581385025104e-06, "loss": 5.3206, "step": 34000 }, { "epoch": 0.04, "learning_rate": 3.9762369936284146e-06, "loss": 5.3074, "step": 34500 }, { "epoch": 0.04, "learning_rate": 3.975892602231725e-06, "loss": 5.3008, "step": 35000 }, { "epoch": 0.04, "learning_rate": 3.975548210835035e-06, "loss": 5.2806, "step": 35500 }, { "epoch": 0.04, "learning_rate": 3.9752038194383455e-06, "loss": 5.2725, "step": 36000 }, { "epoch": 0.04, "learning_rate": 3.974859428041656e-06, "loss": 5.2509, "step": 36500 }, { "epoch": 0.04, "learning_rate": 3.974515036644966e-06, "loss": 5.2519, "step": 37000 }, { "epoch": 0.04, "learning_rate": 3.9741706452482765e-06, "loss": 5.2415, "step": 37500 }, { "epoch": 0.04, "learning_rate": 3.973826253851587e-06, "loss": 5.2251, "step": 38000 }, { "epoch": 0.04, "learning_rate": 3.973481862454898e-06, "loss": 5.2206, "step": 38500 }, { "epoch": 0.04, "learning_rate": 3.9731374710582075e-06, "loss": 5.2179, "step": 39000 }, { "epoch": 0.04, "learning_rate": 3.972793079661519e-06, "loss": 5.2073, "step": 39500 }, { "epoch": 0.04, "learning_rate": 3.972448688264828e-06, "loss": 5.1818, "step": 40000 }, { "epoch": 0.04, "learning_rate": 3.972104296868139e-06, "loss": 5.1812, "step": 40500 }, { "epoch": 0.04, "learning_rate": 3.97175990547145e-06, "loss": 5.1706, "step": 41000 }, { "epoch": 0.04, "learning_rate": 3.97141551407476e-06, "loss": 5.1595, "step": 41500 }, { "epoch": 0.04, "learning_rate": 3.97107112267807e-06, "loss": 5.1363, "step": 42000 }, { "epoch": 0.04, "learning_rate": 3.97072673128138e-06, "loss": 5.1414, "step": 42500 }, { "epoch": 0.04, "learning_rate": 3.970382339884691e-06, "loss": 5.1235, "step": 43000 }, { "epoch": 0.04, "learning_rate": 3.970037948488001e-06, "loss": 5.1188, "step": 43500 }, { "epoch": 0.05, "learning_rate": 3.9696935570913115e-06, "loss": 5.1068, "step": 44000 }, { "epoch": 0.05, "learning_rate": 3.969349165694622e-06, "loss": 5.0976, "step": 44500 }, { "epoch": 0.05, "learning_rate": 3.969004774297932e-06, "loss": 5.09, "step": 45000 }, { "epoch": 0.05, "learning_rate": 3.9686603829012425e-06, "loss": 5.0812, "step": 45500 }, { "epoch": 0.05, "learning_rate": 3.968315991504553e-06, "loss": 5.071, "step": 46000 }, { "epoch": 0.05, "learning_rate": 3.967971600107863e-06, "loss": 5.0633, "step": 46500 }, { "epoch": 0.05, "learning_rate": 3.9676272087111735e-06, "loss": 5.0521, "step": 47000 }, { "epoch": 0.05, "learning_rate": 3.967282817314484e-06, "loss": 5.0393, "step": 47500 }, { "epoch": 0.05, "learning_rate": 3.966938425917794e-06, "loss": 5.0371, "step": 48000 }, { "epoch": 0.05, "learning_rate": 3.9665940345211044e-06, "loss": 5.0239, "step": 48500 }, { "epoch": 0.05, "learning_rate": 3.966249643124415e-06, "loss": 5.0153, "step": 49000 }, { "epoch": 0.05, "learning_rate": 3.965905251727725e-06, "loss": 5.0079, "step": 49500 }, { "epoch": 0.05, "learning_rate": 3.965560860331035e-06, "loss": 5.0067, "step": 50000 }, { "epoch": 0.05, "learning_rate": 3.965216468934346e-06, "loss": 5.0012, "step": 50500 }, { "epoch": 0.05, "learning_rate": 3.964872077537656e-06, "loss": 5.0004, "step": 51000 }, { "epoch": 0.05, "learning_rate": 3.964527686140967e-06, "loss": 4.9871, "step": 51500 }, { "epoch": 0.05, "learning_rate": 3.964183294744277e-06, "loss": 4.9748, "step": 52000 }, { "epoch": 0.05, "learning_rate": 3.963838903347588e-06, "loss": 4.9677, "step": 52500 }, { "epoch": 0.05, "learning_rate": 3.963494511950898e-06, "loss": 4.9666, "step": 53000 }, { "epoch": 0.06, "learning_rate": 3.9631501205542085e-06, "loss": 4.9498, "step": 53500 }, { "epoch": 0.06, "learning_rate": 3.962805729157519e-06, "loss": 4.9409, "step": 54000 }, { "epoch": 0.06, "learning_rate": 3.962461337760829e-06, "loss": 4.932, "step": 54500 }, { "epoch": 0.06, "learning_rate": 3.9621169463641395e-06, "loss": 4.9199, "step": 55000 }, { "epoch": 0.06, "learning_rate": 3.96177255496745e-06, "loss": 4.9253, "step": 55500 }, { "epoch": 0.06, "learning_rate": 3.96142816357076e-06, "loss": 4.9203, "step": 56000 }, { "epoch": 0.06, "learning_rate": 3.9610837721740704e-06, "loss": 4.9258, "step": 56500 }, { "epoch": 0.06, "learning_rate": 3.960739380777381e-06, "loss": 4.9058, "step": 57000 }, { "epoch": 0.06, "learning_rate": 3.960394989380691e-06, "loss": 4.8971, "step": 57500 }, { "epoch": 0.06, "learning_rate": 3.960050597984001e-06, "loss": 4.8877, "step": 58000 }, { "epoch": 0.06, "learning_rate": 3.959706206587312e-06, "loss": 4.8902, "step": 58500 }, { "epoch": 0.06, "learning_rate": 3.959361815190622e-06, "loss": 4.8816, "step": 59000 }, { "epoch": 0.06, "learning_rate": 3.959017423793932e-06, "loss": 4.8715, "step": 59500 }, { "epoch": 0.06, "learning_rate": 3.958673032397243e-06, "loss": 4.8676, "step": 60000 }, { "epoch": 0.06, "learning_rate": 3.958328641000553e-06, "loss": 4.8544, "step": 60500 }, { "epoch": 0.06, "learning_rate": 3.957984249603864e-06, "loss": 4.8502, "step": 61000 }, { "epoch": 0.06, "learning_rate": 3.957639858207174e-06, "loss": 4.845, "step": 61500 }, { "epoch": 0.06, "learning_rate": 3.957295466810485e-06, "loss": 4.8331, "step": 62000 }, { "epoch": 0.06, "learning_rate": 3.956951075413794e-06, "loss": 4.8295, "step": 62500 }, { "epoch": 0.07, "learning_rate": 3.956606684017105e-06, "loss": 4.8232, "step": 63000 }, { "epoch": 0.07, "learning_rate": 3.956262292620416e-06, "loss": 4.8188, "step": 63500 }, { "epoch": 0.07, "learning_rate": 3.955917901223725e-06, "loss": 4.8157, "step": 64000 }, { "epoch": 0.07, "learning_rate": 3.9555735098270364e-06, "loss": 4.8021, "step": 64500 }, { "epoch": 0.07, "learning_rate": 3.955229118430347e-06, "loss": 4.7937, "step": 65000 }, { "epoch": 0.07, "learning_rate": 3.954884727033657e-06, "loss": 4.8008, "step": 65500 }, { "epoch": 0.07, "learning_rate": 3.954540335636967e-06, "loss": 4.7907, "step": 66000 }, { "epoch": 0.07, "learning_rate": 3.954195944240278e-06, "loss": 4.7826, "step": 66500 }, { "epoch": 0.07, "learning_rate": 3.953851552843588e-06, "loss": 4.7841, "step": 67000 }, { "epoch": 0.07, "learning_rate": 3.953507161446898e-06, "loss": 4.7735, "step": 67500 }, { "epoch": 0.07, "learning_rate": 3.953162770050209e-06, "loss": 4.7677, "step": 68000 }, { "epoch": 0.07, "learning_rate": 3.952818378653519e-06, "loss": 4.7591, "step": 68500 }, { "epoch": 0.07, "learning_rate": 3.952473987256829e-06, "loss": 4.7518, "step": 69000 }, { "epoch": 0.07, "learning_rate": 3.95212959586014e-06, "loss": 4.7546, "step": 69500 }, { "epoch": 0.07, "learning_rate": 3.95178520446345e-06, "loss": 4.7502, "step": 70000 }, { "epoch": 0.07, "learning_rate": 3.95144081306676e-06, "loss": 4.7408, "step": 70500 }, { "epoch": 0.07, "learning_rate": 3.951096421670071e-06, "loss": 4.7372, "step": 71000 }, { "epoch": 0.07, "learning_rate": 3.950752030273381e-06, "loss": 4.7221, "step": 71500 }, { "epoch": 0.07, "learning_rate": 3.950407638876691e-06, "loss": 4.7373, "step": 72000 }, { "epoch": 0.07, "learning_rate": 3.9500632474800016e-06, "loss": 4.7228, "step": 72500 }, { "epoch": 0.08, "learning_rate": 3.949718856083313e-06, "loss": 4.7159, "step": 73000 }, { "epoch": 0.08, "learning_rate": 3.949374464686622e-06, "loss": 4.7039, "step": 73500 }, { "epoch": 0.08, "learning_rate": 3.949030073289933e-06, "loss": 4.7014, "step": 74000 }, { "epoch": 0.08, "learning_rate": 3.948685681893243e-06, "loss": 4.7018, "step": 74500 }, { "epoch": 0.08, "learning_rate": 3.948341290496554e-06, "loss": 4.691, "step": 75000 }, { "epoch": 0.08, "learning_rate": 3.947996899099864e-06, "loss": 4.6932, "step": 75500 }, { "epoch": 0.08, "learning_rate": 3.947652507703175e-06, "loss": 4.6831, "step": 76000 }, { "epoch": 0.08, "learning_rate": 3.947308116306485e-06, "loss": 4.6762, "step": 76500 }, { "epoch": 0.08, "learning_rate": 3.946963724909795e-06, "loss": 4.6758, "step": 77000 }, { "epoch": 0.08, "learning_rate": 3.946619333513106e-06, "loss": 4.6778, "step": 77500 }, { "epoch": 0.08, "learning_rate": 3.946274942116416e-06, "loss": 4.6597, "step": 78000 }, { "epoch": 0.08, "learning_rate": 3.945930550719726e-06, "loss": 4.6696, "step": 78500 }, { "epoch": 0.08, "learning_rate": 3.945586159323037e-06, "loss": 4.6557, "step": 79000 }, { "epoch": 0.08, "learning_rate": 3.945241767926347e-06, "loss": 4.6515, "step": 79500 }, { "epoch": 0.08, "learning_rate": 3.944897376529657e-06, "loss": 4.6504, "step": 80000 }, { "epoch": 0.08, "learning_rate": 3.9445529851329676e-06, "loss": 4.6391, "step": 80500 }, { "epoch": 0.08, "learning_rate": 3.944208593736278e-06, "loss": 4.6388, "step": 81000 }, { "epoch": 0.08, "learning_rate": 3.943864202339588e-06, "loss": 4.6356, "step": 81500 }, { "epoch": 0.08, "learning_rate": 3.9435198109428985e-06, "loss": 4.632, "step": 82000 }, { "epoch": 0.09, "learning_rate": 3.943175419546209e-06, "loss": 4.6233, "step": 82500 }, { "epoch": 0.09, "learning_rate": 3.942831028149519e-06, "loss": 4.6226, "step": 83000 }, { "epoch": 0.09, "learning_rate": 3.9424866367528295e-06, "loss": 4.6148, "step": 83500 }, { "epoch": 0.09, "learning_rate": 3.94214224535614e-06, "loss": 4.6165, "step": 84000 }, { "epoch": 0.09, "learning_rate": 3.94179785395945e-06, "loss": 4.6069, "step": 84500 }, { "epoch": 0.09, "learning_rate": 3.941453462562761e-06, "loss": 4.5973, "step": 85000 }, { "epoch": 0.09, "learning_rate": 3.941109071166071e-06, "loss": 4.5986, "step": 85500 }, { "epoch": 0.09, "learning_rate": 3.940764679769382e-06, "loss": 4.5944, "step": 86000 }, { "epoch": 0.09, "learning_rate": 3.9404202883726914e-06, "loss": 4.5922, "step": 86500 }, { "epoch": 0.09, "learning_rate": 3.940075896976003e-06, "loss": 4.5866, "step": 87000 }, { "epoch": 0.09, "learning_rate": 3.939731505579313e-06, "loss": 4.5786, "step": 87500 }, { "epoch": 0.09, "learning_rate": 3.939387114182623e-06, "loss": 4.5754, "step": 88000 }, { "epoch": 0.09, "learning_rate": 3.9390427227859336e-06, "loss": 4.5784, "step": 88500 }, { "epoch": 0.09, "learning_rate": 3.938698331389244e-06, "loss": 4.5784, "step": 89000 }, { "epoch": 0.09, "learning_rate": 3.938353939992554e-06, "loss": 4.5627, "step": 89500 }, { "epoch": 0.09, "learning_rate": 3.9380095485958645e-06, "loss": 4.5696, "step": 90000 }, { "epoch": 0.09, "learning_rate": 3.937665157199175e-06, "loss": 4.5622, "step": 90500 }, { "epoch": 0.09, "learning_rate": 3.937320765802485e-06, "loss": 4.5515, "step": 91000 }, { "epoch": 0.09, "learning_rate": 3.9369763744057955e-06, "loss": 4.5539, "step": 91500 }, { "epoch": 0.1, "learning_rate": 3.936631983009106e-06, "loss": 4.5544, "step": 92000 }, { "epoch": 0.1, "learning_rate": 3.936287591612416e-06, "loss": 4.5488, "step": 92500 }, { "epoch": 0.1, "learning_rate": 3.9359432002157265e-06, "loss": 4.5447, "step": 93000 }, { "epoch": 0.1, "learning_rate": 3.935598808819037e-06, "loss": 4.5385, "step": 93500 }, { "epoch": 0.1, "learning_rate": 3.935254417422347e-06, "loss": 4.539, "step": 94000 }, { "epoch": 0.1, "learning_rate": 3.9349100260256574e-06, "loss": 4.5229, "step": 94500 }, { "epoch": 0.1, "learning_rate": 3.934565634628968e-06, "loss": 4.5272, "step": 95000 }, { "epoch": 0.1, "learning_rate": 3.934221243232279e-06, "loss": 4.5188, "step": 95500 }, { "epoch": 0.1, "learning_rate": 3.933876851835588e-06, "loss": 4.5227, "step": 96000 }, { "epoch": 0.1, "learning_rate": 3.9335324604388996e-06, "loss": 4.5141, "step": 96500 }, { "epoch": 0.1, "learning_rate": 3.933188069042209e-06, "loss": 4.5082, "step": 97000 }, { "epoch": 0.1, "learning_rate": 3.932843677645519e-06, "loss": 4.5063, "step": 97500 }, { "epoch": 0.1, "learning_rate": 3.9324992862488305e-06, "loss": 4.5177, "step": 98000 }, { "epoch": 0.1, "learning_rate": 3.93215489485214e-06, "loss": 4.4989, "step": 98500 }, { "epoch": 0.1, "learning_rate": 3.931810503455451e-06, "loss": 4.5002, "step": 99000 }, { "epoch": 0.1, "learning_rate": 3.9314661120587615e-06, "loss": 4.4882, "step": 99500 }, { "epoch": 0.1, "learning_rate": 3.931121720662072e-06, "loss": 4.4877, "step": 100000 }, { "epoch": 0.1, "learning_rate": 3.930777329265382e-06, "loss": 4.4882, "step": 100500 }, { "epoch": 0.1, "learning_rate": 3.9304329378686925e-06, "loss": 4.4884, "step": 101000 }, { "epoch": 0.1, "learning_rate": 3.930088546472003e-06, "loss": 4.4788, "step": 101500 }, { "epoch": 0.11, "learning_rate": 3.929744155075313e-06, "loss": 4.4834, "step": 102000 }, { "epoch": 0.11, "learning_rate": 3.9293997636786234e-06, "loss": 4.4765, "step": 102500 }, { "epoch": 0.11, "learning_rate": 3.929055372281934e-06, "loss": 4.4787, "step": 103000 }, { "epoch": 0.11, "learning_rate": 3.928710980885244e-06, "loss": 4.4709, "step": 103500 }, { "epoch": 0.11, "learning_rate": 3.928366589488554e-06, "loss": 4.4638, "step": 104000 }, { "epoch": 0.11, "learning_rate": 3.928022198091865e-06, "loss": 4.4568, "step": 104500 }, { "epoch": 0.11, "learning_rate": 3.927677806695175e-06, "loss": 4.4485, "step": 105000 }, { "epoch": 0.11, "learning_rate": 3.927333415298485e-06, "loss": 4.4568, "step": 105500 }, { "epoch": 0.11, "learning_rate": 3.926989023901796e-06, "loss": 4.4517, "step": 106000 }, { "epoch": 0.11, "learning_rate": 3.926644632505106e-06, "loss": 4.4592, "step": 106500 }, { "epoch": 0.11, "learning_rate": 3.926300241108416e-06, "loss": 4.4496, "step": 107000 }, { "epoch": 0.11, "learning_rate": 3.9259558497117275e-06, "loss": 4.4393, "step": 107500 }, { "epoch": 0.11, "learning_rate": 3.925611458315037e-06, "loss": 4.4432, "step": 108000 }, { "epoch": 0.11, "learning_rate": 3.925267066918348e-06, "loss": 4.4357, "step": 108500 }, { "epoch": 0.11, "learning_rate": 3.924922675521658e-06, "loss": 4.4324, "step": 109000 }, { "epoch": 0.11, "learning_rate": 3.924578284124969e-06, "loss": 4.4331, "step": 109500 }, { "epoch": 0.11, "learning_rate": 3.924233892728279e-06, "loss": 4.4397, "step": 110000 }, { "epoch": 0.11, "learning_rate": 3.9238895013315894e-06, "loss": 4.4288, "step": 110500 }, { "epoch": 0.11, "learning_rate": 3.9235451099349e-06, "loss": 4.418, "step": 111000 }, { "epoch": 0.12, "learning_rate": 3.92320071853821e-06, "loss": 4.4224, "step": 111500 }, { "epoch": 0.12, "learning_rate": 3.92285632714152e-06, "loss": 4.4141, "step": 112000 }, { "epoch": 0.12, "learning_rate": 3.922511935744831e-06, "loss": 4.417, "step": 112500 }, { "epoch": 0.12, "learning_rate": 3.922167544348141e-06, "loss": 4.409, "step": 113000 }, { "epoch": 0.12, "learning_rate": 3.921823152951451e-06, "loss": 4.4124, "step": 113500 }, { "epoch": 0.12, "learning_rate": 3.921478761554762e-06, "loss": 4.4077, "step": 114000 }, { "epoch": 0.12, "learning_rate": 3.921134370158072e-06, "loss": 4.4066, "step": 114500 }, { "epoch": 0.12, "learning_rate": 3.920789978761382e-06, "loss": 4.4059, "step": 115000 }, { "epoch": 0.12, "learning_rate": 3.920445587364693e-06, "loss": 4.3979, "step": 115500 }, { "epoch": 0.12, "learning_rate": 3.920101195968003e-06, "loss": 4.3965, "step": 116000 }, { "epoch": 0.12, "learning_rate": 3.919756804571313e-06, "loss": 4.399, "step": 116500 }, { "epoch": 0.12, "learning_rate": 3.919412413174624e-06, "loss": 4.3779, "step": 117000 }, { "epoch": 0.12, "learning_rate": 3.919068021777934e-06, "loss": 4.3857, "step": 117500 }, { "epoch": 0.12, "learning_rate": 3.918723630381245e-06, "loss": 4.3896, "step": 118000 }, { "epoch": 0.12, "learning_rate": 3.918379238984555e-06, "loss": 4.3873, "step": 118500 }, { "epoch": 0.12, "learning_rate": 3.918034847587865e-06, "loss": 4.3818, "step": 119000 }, { "epoch": 0.12, "learning_rate": 3.917690456191176e-06, "loss": 4.3796, "step": 119500 }, { "epoch": 0.12, "learning_rate": 3.9173460647944855e-06, "loss": 4.3682, "step": 120000 }, { "epoch": 0.12, "learning_rate": 3.917001673397797e-06, "loss": 4.3802, "step": 120500 }, { "epoch": 0.13, "learning_rate": 3.916657282001106e-06, "loss": 4.3663, "step": 121000 }, { "epoch": 0.13, "learning_rate": 3.916312890604417e-06, "loss": 4.3701, "step": 121500 }, { "epoch": 0.13, "learning_rate": 3.915968499207728e-06, "loss": 4.3606, "step": 122000 }, { "epoch": 0.13, "learning_rate": 3.915624107811038e-06, "loss": 4.3634, "step": 122500 }, { "epoch": 0.13, "learning_rate": 3.915279716414348e-06, "loss": 4.3474, "step": 123000 }, { "epoch": 0.13, "learning_rate": 3.914935325017659e-06, "loss": 4.3574, "step": 123500 }, { "epoch": 0.13, "learning_rate": 3.914590933620969e-06, "loss": 4.3558, "step": 124000 }, { "epoch": 0.13, "learning_rate": 3.914246542224279e-06, "loss": 4.3515, "step": 124500 }, { "epoch": 0.13, "learning_rate": 3.91390215082759e-06, "loss": 4.3413, "step": 125000 }, { "epoch": 0.13, "learning_rate": 3.9135577594309e-06, "loss": 4.3434, "step": 125500 }, { "epoch": 0.13, "learning_rate": 3.91321336803421e-06, "loss": 4.3429, "step": 126000 }, { "epoch": 0.13, "learning_rate": 3.9128689766375206e-06, "loss": 4.3447, "step": 126500 }, { "epoch": 0.13, "learning_rate": 3.912524585240831e-06, "loss": 4.3442, "step": 127000 }, { "epoch": 0.13, "learning_rate": 3.912180193844141e-06, "loss": 4.3419, "step": 127500 }, { "epoch": 0.13, "learning_rate": 3.9118358024474515e-06, "loss": 4.3324, "step": 128000 }, { "epoch": 0.13, "learning_rate": 3.911491411050762e-06, "loss": 4.3342, "step": 128500 }, { "epoch": 0.13, "learning_rate": 3.911147019654072e-06, "loss": 4.3318, "step": 129000 }, { "epoch": 0.13, "learning_rate": 3.9108026282573825e-06, "loss": 4.3283, "step": 129500 }, { "epoch": 0.13, "learning_rate": 3.910458236860694e-06, "loss": 4.3123, "step": 130000 }, { "epoch": 0.13, "learning_rate": 3.910113845464003e-06, "loss": 4.3252, "step": 130500 }, { "epoch": 0.14, "learning_rate": 3.909769454067314e-06, "loss": 4.3214, "step": 131000 }, { "epoch": 0.14, "learning_rate": 3.909425062670625e-06, "loss": 4.3145, "step": 131500 }, { "epoch": 0.14, "learning_rate": 3.909080671273935e-06, "loss": 4.3191, "step": 132000 }, { "epoch": 0.14, "learning_rate": 3.908736279877245e-06, "loss": 4.3176, "step": 132500 }, { "epoch": 0.14, "learning_rate": 3.908391888480555e-06, "loss": 4.3079, "step": 133000 }, { "epoch": 0.14, "learning_rate": 3.908047497083866e-06, "loss": 4.3069, "step": 133500 }, { "epoch": 0.14, "learning_rate": 3.907703105687176e-06, "loss": 4.3078, "step": 134000 }, { "epoch": 0.14, "learning_rate": 3.9073587142904866e-06, "loss": 4.2965, "step": 134500 }, { "epoch": 0.14, "learning_rate": 3.907014322893797e-06, "loss": 4.3024, "step": 135000 }, { "epoch": 0.14, "learning_rate": 3.906669931497107e-06, "loss": 4.2921, "step": 135500 }, { "epoch": 0.14, "learning_rate": 3.9063255401004175e-06, "loss": 4.3018, "step": 136000 }, { "epoch": 0.14, "learning_rate": 3.905981148703728e-06, "loss": 4.2941, "step": 136500 }, { "epoch": 0.14, "learning_rate": 3.905636757307038e-06, "loss": 4.2948, "step": 137000 }, { "epoch": 0.14, "learning_rate": 3.9052923659103485e-06, "loss": 4.2895, "step": 137500 }, { "epoch": 0.14, "learning_rate": 3.904947974513659e-06, "loss": 4.2964, "step": 138000 }, { "epoch": 0.14, "learning_rate": 3.904603583116969e-06, "loss": 4.2969, "step": 138500 }, { "epoch": 0.14, "learning_rate": 3.9042591917202795e-06, "loss": 4.2917, "step": 139000 }, { "epoch": 0.14, "learning_rate": 3.90391480032359e-06, "loss": 4.2822, "step": 139500 }, { "epoch": 0.14, "learning_rate": 3.9035704089269e-06, "loss": 4.2851, "step": 140000 }, { "epoch": 0.15, "learning_rate": 3.9032260175302104e-06, "loss": 4.2801, "step": 140500 }, { "epoch": 0.15, "learning_rate": 3.902881626133521e-06, "loss": 4.2836, "step": 141000 }, { "epoch": 0.15, "learning_rate": 3.902537234736831e-06, "loss": 4.2768, "step": 141500 }, { "epoch": 0.15, "learning_rate": 3.902192843340142e-06, "loss": 4.2711, "step": 142000 }, { "epoch": 0.15, "learning_rate": 3.901848451943452e-06, "loss": 4.2708, "step": 142500 }, { "epoch": 0.15, "learning_rate": 3.901504060546763e-06, "loss": 4.2595, "step": 143000 }, { "epoch": 0.15, "learning_rate": 3.901159669150072e-06, "loss": 4.2714, "step": 143500 }, { "epoch": 0.15, "learning_rate": 3.9008152777533835e-06, "loss": 4.2608, "step": 144000 }, { "epoch": 0.15, "learning_rate": 3.900470886356694e-06, "loss": 4.2724, "step": 144500 }, { "epoch": 0.15, "learning_rate": 3.900126494960004e-06, "loss": 4.2661, "step": 145000 }, { "epoch": 0.15, "learning_rate": 3.8997821035633145e-06, "loss": 4.276, "step": 145500 }, { "epoch": 0.15, "learning_rate": 3.899437712166625e-06, "loss": 4.2616, "step": 146000 }, { "epoch": 0.15, "learning_rate": 3.899093320769935e-06, "loss": 4.2512, "step": 146500 }, { "epoch": 0.15, "learning_rate": 3.8987489293732455e-06, "loss": 4.2537, "step": 147000 }, { "epoch": 0.15, "learning_rate": 3.898404537976556e-06, "loss": 4.2505, "step": 147500 }, { "epoch": 0.15, "learning_rate": 3.898060146579866e-06, "loss": 4.2571, "step": 148000 }, { "epoch": 0.15, "learning_rate": 3.8977157551831764e-06, "loss": 4.2428, "step": 148500 }, { "epoch": 0.15, "learning_rate": 3.897371363786487e-06, "loss": 4.2491, "step": 149000 }, { "epoch": 0.15, "learning_rate": 3.897026972389797e-06, "loss": 4.2403, "step": 149500 }, { "epoch": 0.15, "learning_rate": 3.896682580993107e-06, "loss": 4.2454, "step": 150000 }, { "epoch": 0.16, "learning_rate": 3.896338189596418e-06, "loss": 4.2349, "step": 150500 }, { "epoch": 0.16, "learning_rate": 3.895993798199728e-06, "loss": 4.2424, "step": 151000 }, { "epoch": 0.16, "learning_rate": 3.895649406803038e-06, "loss": 4.244, "step": 151500 }, { "epoch": 0.16, "learning_rate": 3.895305015406349e-06, "loss": 4.2314, "step": 152000 }, { "epoch": 0.16, "learning_rate": 3.89496062400966e-06, "loss": 4.2283, "step": 152500 }, { "epoch": 0.16, "learning_rate": 3.894616232612969e-06, "loss": 4.2285, "step": 153000 }, { "epoch": 0.16, "learning_rate": 3.89427184121628e-06, "loss": 4.2328, "step": 153500 }, { "epoch": 0.16, "learning_rate": 3.893927449819591e-06, "loss": 4.2293, "step": 154000 }, { "epoch": 0.16, "learning_rate": 3.8935830584229e-06, "loss": 4.2278, "step": 154500 }, { "epoch": 0.16, "learning_rate": 3.8932386670262115e-06, "loss": 4.2296, "step": 155000 }, { "epoch": 0.16, "learning_rate": 3.892894275629521e-06, "loss": 4.2303, "step": 155500 }, { "epoch": 0.16, "learning_rate": 3.892549884232832e-06, "loss": 4.2265, "step": 156000 }, { "epoch": 0.16, "learning_rate": 3.8922054928361424e-06, "loss": 4.2276, "step": 156500 }, { "epoch": 0.16, "learning_rate": 3.891861101439453e-06, "loss": 4.2191, "step": 157000 }, { "epoch": 0.16, "learning_rate": 3.891516710042763e-06, "loss": 4.2226, "step": 157500 }, { "epoch": 0.16, "learning_rate": 3.891172318646073e-06, "loss": 4.2156, "step": 158000 }, { "epoch": 0.16, "learning_rate": 3.890827927249384e-06, "loss": 4.2108, "step": 158500 }, { "epoch": 0.16, "learning_rate": 3.890483535852694e-06, "loss": 4.2117, "step": 159000 }, { "epoch": 0.16, "learning_rate": 3.890139144456004e-06, "loss": 4.2072, "step": 159500 }, { "epoch": 0.17, "learning_rate": 3.889794753059315e-06, "loss": 4.21, "step": 160000 }, { "epoch": 0.17, "learning_rate": 3.889450361662625e-06, "loss": 4.21, "step": 160500 }, { "epoch": 0.17, "learning_rate": 3.889105970265935e-06, "loss": 4.202, "step": 161000 }, { "epoch": 0.17, "learning_rate": 3.888761578869246e-06, "loss": 4.191, "step": 161500 }, { "epoch": 0.17, "learning_rate": 3.888417187472556e-06, "loss": 4.2051, "step": 162000 }, { "epoch": 0.17, "learning_rate": 3.888072796075866e-06, "loss": 4.2083, "step": 162500 }, { "epoch": 0.17, "learning_rate": 3.887728404679177e-06, "loss": 4.1994, "step": 163000 }, { "epoch": 0.17, "learning_rate": 3.887384013282487e-06, "loss": 4.1962, "step": 163500 }, { "epoch": 0.17, "learning_rate": 3.887039621885797e-06, "loss": 4.1977, "step": 164000 }, { "epoch": 0.17, "learning_rate": 3.8866952304891084e-06, "loss": 4.1927, "step": 164500 }, { "epoch": 0.17, "learning_rate": 3.886350839092418e-06, "loss": 4.1915, "step": 165000 }, { "epoch": 0.17, "learning_rate": 3.886006447695729e-06, "loss": 4.1836, "step": 165500 }, { "epoch": 0.17, "learning_rate": 3.885662056299039e-06, "loss": 4.1823, "step": 166000 }, { "epoch": 0.17, "learning_rate": 3.88531766490235e-06, "loss": 4.1884, "step": 166500 }, { "epoch": 0.17, "learning_rate": 3.88497327350566e-06, "loss": 4.1848, "step": 167000 }, { "epoch": 0.17, "learning_rate": 3.8846288821089695e-06, "loss": 4.186, "step": 167500 }, { "epoch": 0.17, "learning_rate": 3.884284490712281e-06, "loss": 4.1807, "step": 168000 }, { "epoch": 0.17, "learning_rate": 3.883940099315591e-06, "loss": 4.1788, "step": 168500 }, { "epoch": 0.17, "learning_rate": 3.883595707918901e-06, "loss": 4.1728, "step": 169000 }, { "epoch": 0.18, "learning_rate": 3.883251316522212e-06, "loss": 4.1799, "step": 169500 }, { "epoch": 0.18, "learning_rate": 3.882906925125522e-06, "loss": 4.1772, "step": 170000 }, { "epoch": 0.18, "learning_rate": 3.882562533728832e-06, "loss": 4.171, "step": 170500 }, { "epoch": 0.18, "learning_rate": 3.882218142332143e-06, "loss": 4.1746, "step": 171000 }, { "epoch": 0.18, "learning_rate": 3.881873750935453e-06, "loss": 4.1685, "step": 171500 }, { "epoch": 0.18, "learning_rate": 3.881529359538763e-06, "loss": 4.1753, "step": 172000 }, { "epoch": 0.18, "learning_rate": 3.8811849681420736e-06, "loss": 4.1676, "step": 172500 }, { "epoch": 0.18, "learning_rate": 3.880840576745384e-06, "loss": 4.1658, "step": 173000 }, { "epoch": 0.18, "learning_rate": 3.880496185348694e-06, "loss": 4.1719, "step": 173500 }, { "epoch": 0.18, "learning_rate": 3.8801517939520045e-06, "loss": 4.1756, "step": 174000 }, { "epoch": 0.18, "learning_rate": 3.879807402555315e-06, "loss": 4.1668, "step": 174500 }, { "epoch": 0.18, "learning_rate": 3.879463011158625e-06, "loss": 4.1555, "step": 175000 }, { "epoch": 0.18, "learning_rate": 3.8791186197619355e-06, "loss": 4.156, "step": 175500 }, { "epoch": 0.18, "learning_rate": 3.878774228365246e-06, "loss": 4.1539, "step": 176000 }, { "epoch": 0.18, "learning_rate": 3.878429836968557e-06, "loss": 4.1514, "step": 176500 }, { "epoch": 0.18, "learning_rate": 3.8780854455718665e-06, "loss": 4.1543, "step": 177000 }, { "epoch": 0.18, "learning_rate": 3.877741054175178e-06, "loss": 4.1555, "step": 177500 }, { "epoch": 0.18, "learning_rate": 3.877396662778487e-06, "loss": 4.1494, "step": 178000 }, { "epoch": 0.18, "learning_rate": 3.877052271381798e-06, "loss": 4.1458, "step": 178500 }, { "epoch": 0.18, "learning_rate": 3.876707879985109e-06, "loss": 4.146, "step": 179000 }, { "epoch": 0.19, "learning_rate": 3.876363488588419e-06, "loss": 4.1558, "step": 179500 }, { "epoch": 0.19, "learning_rate": 3.876019097191729e-06, "loss": 4.1523, "step": 180000 }, { "epoch": 0.19, "learning_rate": 3.8756747057950396e-06, "loss": 4.1455, "step": 180500 }, { "epoch": 0.19, "learning_rate": 3.87533031439835e-06, "loss": 4.1469, "step": 181000 }, { "epoch": 0.19, "learning_rate": 3.87498592300166e-06, "loss": 4.1418, "step": 181500 }, { "epoch": 0.19, "learning_rate": 3.8746415316049705e-06, "loss": 4.1456, "step": 182000 }, { "epoch": 0.19, "learning_rate": 3.874297140208281e-06, "loss": 4.1415, "step": 182500 }, { "epoch": 0.19, "learning_rate": 3.873952748811591e-06, "loss": 4.1423, "step": 183000 }, { "epoch": 0.19, "learning_rate": 3.8736083574149015e-06, "loss": 4.131, "step": 183500 }, { "epoch": 0.19, "learning_rate": 3.873263966018212e-06, "loss": 4.1335, "step": 184000 }, { "epoch": 0.19, "learning_rate": 3.872919574621522e-06, "loss": 4.1326, "step": 184500 }, { "epoch": 0.19, "learning_rate": 3.8725751832248325e-06, "loss": 4.1288, "step": 185000 }, { "epoch": 0.19, "learning_rate": 3.872230791828143e-06, "loss": 4.1297, "step": 185500 }, { "epoch": 0.19, "learning_rate": 3.871886400431453e-06, "loss": 4.1252, "step": 186000 }, { "epoch": 0.19, "learning_rate": 3.8715420090347634e-06, "loss": 4.1335, "step": 186500 }, { "epoch": 0.19, "learning_rate": 3.871197617638075e-06, "loss": 4.1274, "step": 187000 }, { "epoch": 0.19, "learning_rate": 3.870853226241384e-06, "loss": 4.1311, "step": 187500 }, { "epoch": 0.19, "learning_rate": 3.870508834844694e-06, "loss": 4.1263, "step": 188000 }, { "epoch": 0.19, "learning_rate": 3.8701644434480056e-06, "loss": 4.1198, "step": 188500 }, { "epoch": 0.2, "learning_rate": 3.869820052051315e-06, "loss": 4.1251, "step": 189000 }, { "epoch": 0.2, "learning_rate": 3.869475660654626e-06, "loss": 4.1149, "step": 189500 }, { "epoch": 0.2, "learning_rate": 3.869131269257936e-06, "loss": 4.106, "step": 190000 }, { "epoch": 0.2, "learning_rate": 3.868786877861247e-06, "loss": 4.1195, "step": 190500 }, { "epoch": 0.2, "learning_rate": 3.868442486464557e-06, "loss": 4.113, "step": 191000 }, { "epoch": 0.2, "learning_rate": 3.8680980950678675e-06, "loss": 4.1109, "step": 191500 }, { "epoch": 0.2, "learning_rate": 3.867753703671178e-06, "loss": 4.1114, "step": 192000 }, { "epoch": 0.2, "learning_rate": 3.867409312274488e-06, "loss": 4.1135, "step": 192500 }, { "epoch": 0.2, "learning_rate": 3.8670649208777985e-06, "loss": 4.1154, "step": 193000 }, { "epoch": 0.2, "learning_rate": 3.866720529481109e-06, "loss": 4.1152, "step": 193500 }, { "epoch": 0.2, "learning_rate": 3.866376138084419e-06, "loss": 4.1081, "step": 194000 }, { "epoch": 0.2, "learning_rate": 3.8660317466877294e-06, "loss": 4.1015, "step": 194500 }, { "epoch": 0.2, "learning_rate": 3.86568735529104e-06, "loss": 4.0976, "step": 195000 }, { "epoch": 0.2, "learning_rate": 3.86534296389435e-06, "loss": 4.1028, "step": 195500 }, { "epoch": 0.2, "learning_rate": 3.86499857249766e-06, "loss": 4.1032, "step": 196000 }, { "epoch": 0.2, "learning_rate": 3.864654181100971e-06, "loss": 4.0966, "step": 196500 }, { "epoch": 0.2, "learning_rate": 3.864309789704281e-06, "loss": 4.1007, "step": 197000 }, { "epoch": 0.2, "learning_rate": 3.863965398307591e-06, "loss": 4.0785, "step": 197500 }, { "epoch": 0.2, "learning_rate": 3.863621006910902e-06, "loss": 4.0992, "step": 198000 }, { "epoch": 0.21, "learning_rate": 3.863276615514212e-06, "loss": 4.097, "step": 198500 }, { "epoch": 0.21, "learning_rate": 3.862932224117523e-06, "loss": 4.0923, "step": 199000 }, { "epoch": 0.21, "learning_rate": 3.862587832720833e-06, "loss": 4.088, "step": 199500 }, { "epoch": 0.21, "learning_rate": 3.862243441324144e-06, "loss": 4.0899, "step": 200000 }, { "epoch": 0.21, "learning_rate": 3.861899049927454e-06, "loss": 4.0995, "step": 200500 }, { "epoch": 0.21, "learning_rate": 3.8615546585307645e-06, "loss": 4.0874, "step": 201000 }, { "epoch": 0.21, "learning_rate": 3.861210267134075e-06, "loss": 4.0852, "step": 201500 }, { "epoch": 0.21, "learning_rate": 3.860865875737384e-06, "loss": 4.0867, "step": 202000 }, { "epoch": 0.21, "learning_rate": 3.8605214843406954e-06, "loss": 4.0906, "step": 202500 }, { "epoch": 0.21, "learning_rate": 3.860177092944006e-06, "loss": 4.0806, "step": 203000 }, { "epoch": 0.21, "learning_rate": 3.859832701547316e-06, "loss": 4.0808, "step": 203500 }, { "epoch": 0.21, "learning_rate": 3.859488310150626e-06, "loss": 4.0793, "step": 204000 }, { "epoch": 0.21, "learning_rate": 3.859143918753937e-06, "loss": 4.0802, "step": 204500 }, { "epoch": 0.21, "learning_rate": 3.858799527357247e-06, "loss": 4.0756, "step": 205000 }, { "epoch": 0.21, "learning_rate": 3.858455135960557e-06, "loss": 4.0686, "step": 205500 }, { "epoch": 0.21, "learning_rate": 3.858110744563868e-06, "loss": 4.069, "step": 206000 }, { "epoch": 0.21, "learning_rate": 3.857766353167178e-06, "loss": 4.0798, "step": 206500 }, { "epoch": 0.21, "learning_rate": 3.857421961770488e-06, "loss": 4.0727, "step": 207000 }, { "epoch": 0.21, "learning_rate": 3.857077570373799e-06, "loss": 4.0679, "step": 207500 }, { "epoch": 0.21, "learning_rate": 3.856733178977109e-06, "loss": 4.08, "step": 208000 }, { "epoch": 0.22, "learning_rate": 3.856388787580419e-06, "loss": 4.0679, "step": 208500 }, { "epoch": 0.22, "learning_rate": 3.85604439618373e-06, "loss": 4.0701, "step": 209000 }, { "epoch": 0.22, "learning_rate": 3.85570000478704e-06, "loss": 4.0729, "step": 209500 }, { "epoch": 0.22, "learning_rate": 3.85535561339035e-06, "loss": 4.0688, "step": 210000 }, { "epoch": 0.22, "learning_rate": 3.855011221993661e-06, "loss": 4.0603, "step": 210500 }, { "epoch": 0.22, "learning_rate": 3.854666830596972e-06, "loss": 4.0542, "step": 211000 }, { "epoch": 0.22, "learning_rate": 3.854322439200281e-06, "loss": 4.0566, "step": 211500 }, { "epoch": 0.22, "learning_rate": 3.853978047803592e-06, "loss": 4.0594, "step": 212000 }, { "epoch": 0.22, "learning_rate": 3.853633656406903e-06, "loss": 4.0577, "step": 212500 }, { "epoch": 0.22, "learning_rate": 3.853289265010213e-06, "loss": 4.0605, "step": 213000 }, { "epoch": 0.22, "learning_rate": 3.852944873613523e-06, "loss": 4.0596, "step": 213500 }, { "epoch": 0.22, "learning_rate": 3.852600482216834e-06, "loss": 4.0563, "step": 214000 }, { "epoch": 0.22, "learning_rate": 3.852256090820144e-06, "loss": 4.0605, "step": 214500 }, { "epoch": 0.22, "learning_rate": 3.851911699423454e-06, "loss": 4.0513, "step": 215000 }, { "epoch": 0.22, "learning_rate": 3.851567308026765e-06, "loss": 4.0481, "step": 215500 }, { "epoch": 0.22, "learning_rate": 3.851222916630075e-06, "loss": 4.0568, "step": 216000 }, { "epoch": 0.22, "learning_rate": 3.850878525233385e-06, "loss": 4.0446, "step": 216500 }, { "epoch": 0.22, "learning_rate": 3.850534133836696e-06, "loss": 4.044, "step": 217000 }, { "epoch": 0.22, "learning_rate": 3.850189742440006e-06, "loss": 4.0507, "step": 217500 }, { "epoch": 0.23, "learning_rate": 3.849845351043316e-06, "loss": 4.0466, "step": 218000 }, { "epoch": 0.23, "learning_rate": 3.849500959646627e-06, "loss": 4.0446, "step": 218500 }, { "epoch": 0.23, "learning_rate": 3.849156568249937e-06, "loss": 4.047, "step": 219000 }, { "epoch": 0.23, "learning_rate": 3.848812176853247e-06, "loss": 4.0395, "step": 219500 }, { "epoch": 0.23, "learning_rate": 3.8484677854565575e-06, "loss": 4.0524, "step": 220000 }, { "epoch": 0.23, "learning_rate": 3.848123394059869e-06, "loss": 4.0457, "step": 220500 }, { "epoch": 0.23, "learning_rate": 3.847779002663178e-06, "loss": 4.0423, "step": 221000 }, { "epoch": 0.23, "learning_rate": 3.847434611266489e-06, "loss": 4.0359, "step": 221500 }, { "epoch": 0.23, "learning_rate": 3.847090219869799e-06, "loss": 4.0391, "step": 222000 }, { "epoch": 0.23, "learning_rate": 3.846745828473109e-06, "loss": 4.0389, "step": 222500 }, { "epoch": 0.23, "learning_rate": 3.84640143707642e-06, "loss": 4.0297, "step": 223000 }, { "epoch": 0.23, "learning_rate": 3.84605704567973e-06, "loss": 4.0441, "step": 223500 }, { "epoch": 0.23, "learning_rate": 3.845712654283041e-06, "loss": 4.0296, "step": 224000 }, { "epoch": 0.23, "learning_rate": 3.8453682628863504e-06, "loss": 4.0372, "step": 224500 }, { "epoch": 0.23, "learning_rate": 3.845023871489662e-06, "loss": 4.0316, "step": 225000 }, { "epoch": 0.23, "learning_rate": 3.844679480092972e-06, "loss": 4.0374, "step": 225500 }, { "epoch": 0.23, "learning_rate": 3.844335088696282e-06, "loss": 4.0387, "step": 226000 }, { "epoch": 0.23, "learning_rate": 3.8439906972995926e-06, "loss": 4.0366, "step": 226500 }, { "epoch": 0.23, "learning_rate": 3.843646305902903e-06, "loss": 4.0313, "step": 227000 }, { "epoch": 0.24, "learning_rate": 3.843301914506213e-06, "loss": 4.0315, "step": 227500 }, { "epoch": 0.24, "learning_rate": 3.8429575231095235e-06, "loss": 4.033, "step": 228000 }, { "epoch": 0.24, "learning_rate": 3.842613131712834e-06, "loss": 4.027, "step": 228500 }, { "epoch": 0.24, "learning_rate": 3.842268740316144e-06, "loss": 4.0211, "step": 229000 }, { "epoch": 0.24, "learning_rate": 3.8419243489194545e-06, "loss": 4.0233, "step": 229500 }, { "epoch": 0.24, "learning_rate": 3.841579957522765e-06, "loss": 4.0104, "step": 230000 }, { "epoch": 0.24, "learning_rate": 3.841235566126075e-06, "loss": 4.0182, "step": 230500 }, { "epoch": 0.24, "learning_rate": 3.8408911747293855e-06, "loss": 4.0132, "step": 231000 }, { "epoch": 0.24, "learning_rate": 3.840546783332696e-06, "loss": 4.0134, "step": 231500 }, { "epoch": 0.24, "learning_rate": 3.840202391936006e-06, "loss": 4.0182, "step": 232000 }, { "epoch": 0.24, "learning_rate": 3.8398580005393164e-06, "loss": 4.0115, "step": 232500 }, { "epoch": 0.24, "learning_rate": 3.839513609142627e-06, "loss": 4.0139, "step": 233000 }, { "epoch": 0.24, "learning_rate": 3.839169217745938e-06, "loss": 4.0093, "step": 233500 }, { "epoch": 0.24, "learning_rate": 3.838824826349247e-06, "loss": 4.0141, "step": 234000 }, { "epoch": 0.24, "learning_rate": 3.8384804349525586e-06, "loss": 4.0131, "step": 234500 }, { "epoch": 0.24, "learning_rate": 3.838136043555869e-06, "loss": 4.0098, "step": 235000 }, { "epoch": 0.24, "learning_rate": 3.837791652159179e-06, "loss": 4.0154, "step": 235500 }, { "epoch": 0.24, "learning_rate": 3.8374472607624895e-06, "loss": 4.0204, "step": 236000 }, { "epoch": 0.24, "learning_rate": 3.837102869365799e-06, "loss": 4.0026, "step": 236500 }, { "epoch": 0.24, "learning_rate": 3.83675847796911e-06, "loss": 4.0046, "step": 237000 }, { "epoch": 0.25, "learning_rate": 3.8364140865724205e-06, "loss": 4.0098, "step": 237500 }, { "epoch": 0.25, "learning_rate": 3.836069695175731e-06, "loss": 4.009, "step": 238000 }, { "epoch": 0.25, "learning_rate": 3.835725303779041e-06, "loss": 4.0057, "step": 238500 }, { "epoch": 0.25, "learning_rate": 3.8353809123823515e-06, "loss": 4.0006, "step": 239000 }, { "epoch": 0.25, "learning_rate": 3.835036520985662e-06, "loss": 4.0029, "step": 239500 }, { "epoch": 0.25, "learning_rate": 3.834692129588972e-06, "loss": 4.0014, "step": 240000 }, { "epoch": 0.25, "learning_rate": 3.8343477381922824e-06, "loss": 4.0068, "step": 240500 }, { "epoch": 0.25, "learning_rate": 3.834003346795593e-06, "loss": 3.9944, "step": 241000 }, { "epoch": 0.25, "learning_rate": 3.833658955398903e-06, "loss": 3.9998, "step": 241500 }, { "epoch": 0.25, "learning_rate": 3.833314564002213e-06, "loss": 4.0117, "step": 242000 }, { "epoch": 0.25, "learning_rate": 3.832970172605524e-06, "loss": 3.9932, "step": 242500 }, { "epoch": 0.25, "learning_rate": 3.832625781208835e-06, "loss": 4.0061, "step": 243000 }, { "epoch": 0.25, "learning_rate": 3.832281389812144e-06, "loss": 4.0024, "step": 243500 }, { "epoch": 0.25, "learning_rate": 3.831936998415455e-06, "loss": 4.0058, "step": 244000 }, { "epoch": 0.25, "learning_rate": 3.831592607018765e-06, "loss": 3.9957, "step": 244500 }, { "epoch": 0.25, "learning_rate": 3.831248215622075e-06, "loss": 3.9909, "step": 245000 }, { "epoch": 0.25, "learning_rate": 3.8309038242253865e-06, "loss": 3.9953, "step": 245500 }, { "epoch": 0.25, "learning_rate": 3.830559432828696e-06, "loss": 3.997, "step": 246000 }, { "epoch": 0.25, "learning_rate": 3.830215041432007e-06, "loss": 3.9983, "step": 246500 }, { "epoch": 0.26, "learning_rate": 3.8298706500353175e-06, "loss": 3.9879, "step": 247000 }, { "epoch": 0.26, "learning_rate": 3.829526258638628e-06, "loss": 3.978, "step": 247500 }, { "epoch": 0.26, "learning_rate": 3.829181867241938e-06, "loss": 3.9937, "step": 248000 }, { "epoch": 0.26, "learning_rate": 3.8288374758452484e-06, "loss": 3.9889, "step": 248500 }, { "epoch": 0.26, "learning_rate": 3.828493084448559e-06, "loss": 3.9909, "step": 249000 }, { "epoch": 0.26, "learning_rate": 3.828148693051869e-06, "loss": 3.9844, "step": 249500 }, { "epoch": 0.26, "learning_rate": 3.827804301655179e-06, "loss": 3.9794, "step": 250000 }, { "epoch": 0.26, "learning_rate": 3.82745991025849e-06, "loss": 3.9828, "step": 250500 }, { "epoch": 0.26, "learning_rate": 3.8271155188618e-06, "loss": 3.9712, "step": 251000 }, { "epoch": 0.26, "learning_rate": 3.82677112746511e-06, "loss": 3.9756, "step": 251500 }, { "epoch": 0.26, "learning_rate": 3.826426736068421e-06, "loss": 3.9763, "step": 252000 }, { "epoch": 0.26, "learning_rate": 3.826082344671731e-06, "loss": 3.9744, "step": 252500 }, { "epoch": 0.26, "learning_rate": 3.825737953275041e-06, "loss": 3.9764, "step": 253000 }, { "epoch": 0.26, "learning_rate": 3.825393561878352e-06, "loss": 3.9758, "step": 253500 }, { "epoch": 0.26, "learning_rate": 3.825049170481662e-06, "loss": 3.9765, "step": 254000 }, { "epoch": 0.26, "learning_rate": 3.824704779084972e-06, "loss": 3.9782, "step": 254500 }, { "epoch": 0.26, "learning_rate": 3.8243603876882835e-06, "loss": 3.9627, "step": 255000 }, { "epoch": 0.26, "learning_rate": 3.824015996291593e-06, "loss": 3.9744, "step": 255500 }, { "epoch": 0.26, "learning_rate": 3.823671604894904e-06, "loss": 3.9692, "step": 256000 }, { "epoch": 0.27, "learning_rate": 3.823327213498214e-06, "loss": 3.9725, "step": 256500 }, { "epoch": 0.27, "learning_rate": 3.822982822101525e-06, "loss": 3.9794, "step": 257000 }, { "epoch": 0.27, "learning_rate": 3.822638430704835e-06, "loss": 3.974, "step": 257500 }, { "epoch": 0.27, "learning_rate": 3.8222940393081445e-06, "loss": 3.9689, "step": 258000 }, { "epoch": 0.27, "learning_rate": 3.821949647911456e-06, "loss": 3.9642, "step": 258500 }, { "epoch": 0.27, "learning_rate": 3.821605256514766e-06, "loss": 3.966, "step": 259000 }, { "epoch": 0.27, "learning_rate": 3.821260865118076e-06, "loss": 3.9722, "step": 259500 }, { "epoch": 0.27, "learning_rate": 3.820916473721387e-06, "loss": 3.9663, "step": 260000 }, { "epoch": 0.27, "learning_rate": 3.820572082324697e-06, "loss": 3.9606, "step": 260500 }, { "epoch": 0.27, "learning_rate": 3.820227690928007e-06, "loss": 3.9637, "step": 261000 }, { "epoch": 0.27, "learning_rate": 3.819883299531318e-06, "loss": 3.9588, "step": 261500 }, { "epoch": 0.27, "learning_rate": 3.819538908134628e-06, "loss": 3.9598, "step": 262000 }, { "epoch": 0.27, "learning_rate": 3.819194516737938e-06, "loss": 3.9595, "step": 262500 }, { "epoch": 0.27, "learning_rate": 3.818850125341249e-06, "loss": 3.9619, "step": 263000 }, { "epoch": 0.27, "learning_rate": 3.818505733944559e-06, "loss": 3.9539, "step": 263500 }, { "epoch": 0.27, "learning_rate": 3.818161342547869e-06, "loss": 3.9511, "step": 264000 }, { "epoch": 0.27, "learning_rate": 3.81781695115118e-06, "loss": 3.963, "step": 264500 }, { "epoch": 0.27, "learning_rate": 3.81747255975449e-06, "loss": 3.9658, "step": 265000 }, { "epoch": 0.27, "learning_rate": 3.8171281683578e-06, "loss": 3.9582, "step": 265500 }, { "epoch": 0.27, "learning_rate": 3.8167837769611105e-06, "loss": 3.9449, "step": 266000 }, { "epoch": 0.28, "learning_rate": 3.816439385564421e-06, "loss": 3.9474, "step": 266500 }, { "epoch": 0.28, "learning_rate": 3.816094994167732e-06, "loss": 3.9597, "step": 267000 }, { "epoch": 0.28, "learning_rate": 3.8157506027710415e-06, "loss": 3.9503, "step": 267500 }, { "epoch": 0.28, "learning_rate": 3.815406211374353e-06, "loss": 3.9476, "step": 268000 }, { "epoch": 0.28, "learning_rate": 3.815061819977662e-06, "loss": 3.9541, "step": 268500 }, { "epoch": 0.28, "learning_rate": 3.814717428580973e-06, "loss": 3.9532, "step": 269000 }, { "epoch": 0.28, "learning_rate": 3.8143730371842832e-06, "loss": 3.9503, "step": 269500 }, { "epoch": 0.28, "learning_rate": 3.814028645787594e-06, "loss": 3.9505, "step": 270000 }, { "epoch": 0.28, "learning_rate": 3.813684254390904e-06, "loss": 3.9443, "step": 270500 }, { "epoch": 0.28, "learning_rate": 3.8133398629942146e-06, "loss": 3.9513, "step": 271000 }, { "epoch": 0.28, "learning_rate": 3.812995471597525e-06, "loss": 3.9598, "step": 271500 }, { "epoch": 0.28, "learning_rate": 3.812651080200835e-06, "loss": 3.9415, "step": 272000 }, { "epoch": 0.28, "learning_rate": 3.8123066888041456e-06, "loss": 3.9458, "step": 272500 }, { "epoch": 0.28, "learning_rate": 3.8119622974074555e-06, "loss": 3.9463, "step": 273000 }, { "epoch": 0.28, "learning_rate": 3.8116179060107662e-06, "loss": 3.9534, "step": 273500 }, { "epoch": 0.28, "learning_rate": 3.8112735146140765e-06, "loss": 3.9467, "step": 274000 }, { "epoch": 0.28, "learning_rate": 3.810929123217387e-06, "loss": 3.9392, "step": 274500 }, { "epoch": 0.28, "learning_rate": 3.810584731820697e-06, "loss": 3.946, "step": 275000 }, { "epoch": 0.28, "learning_rate": 3.810240340424008e-06, "loss": 3.9338, "step": 275500 }, { "epoch": 0.29, "learning_rate": 3.809895949027318e-06, "loss": 3.9402, "step": 276000 }, { "epoch": 0.29, "learning_rate": 3.8095515576306286e-06, "loss": 3.9361, "step": 276500 }, { "epoch": 0.29, "learning_rate": 3.8092071662339385e-06, "loss": 3.9407, "step": 277000 }, { "epoch": 0.29, "learning_rate": 3.8088627748372492e-06, "loss": 3.9371, "step": 277500 }, { "epoch": 0.29, "learning_rate": 3.8085183834405595e-06, "loss": 3.9468, "step": 278000 }, { "epoch": 0.29, "learning_rate": 3.8081739920438694e-06, "loss": 3.9394, "step": 278500 }, { "epoch": 0.29, "learning_rate": 3.80782960064718e-06, "loss": 3.9353, "step": 279000 }, { "epoch": 0.29, "learning_rate": 3.8074852092504905e-06, "loss": 3.9379, "step": 279500 }, { "epoch": 0.29, "learning_rate": 3.807140817853801e-06, "loss": 3.9445, "step": 280000 }, { "epoch": 0.29, "learning_rate": 3.806796426457111e-06, "loss": 3.9355, "step": 280500 }, { "epoch": 0.29, "learning_rate": 3.8064520350604215e-06, "loss": 3.9209, "step": 281000 }, { "epoch": 0.29, "learning_rate": 3.806107643663732e-06, "loss": 3.9314, "step": 281500 }, { "epoch": 0.29, "learning_rate": 3.8057632522670425e-06, "loss": 3.9349, "step": 282000 }, { "epoch": 0.29, "learning_rate": 3.8054188608703524e-06, "loss": 3.9256, "step": 282500 }, { "epoch": 0.29, "learning_rate": 3.805074469473663e-06, "loss": 3.9271, "step": 283000 }, { "epoch": 0.29, "learning_rate": 3.8047300780769735e-06, "loss": 3.921, "step": 283500 }, { "epoch": 0.29, "learning_rate": 3.804385686680284e-06, "loss": 3.9232, "step": 284000 }, { "epoch": 0.29, "learning_rate": 3.804041295283594e-06, "loss": 3.927, "step": 284500 }, { "epoch": 0.29, "learning_rate": 3.803696903886904e-06, "loss": 3.9229, "step": 285000 }, { "epoch": 0.29, "learning_rate": 3.803352512490215e-06, "loss": 3.9249, "step": 285500 }, { "epoch": 0.3, "learning_rate": 3.803008121093525e-06, "loss": 3.9272, "step": 286000 }, { "epoch": 0.3, "learning_rate": 3.8026637296968354e-06, "loss": 3.9168, "step": 286500 }, { "epoch": 0.3, "learning_rate": 3.8023193383001458e-06, "loss": 3.9277, "step": 287000 }, { "epoch": 0.3, "learning_rate": 3.8019749469034565e-06, "loss": 3.9184, "step": 287500 }, { "epoch": 0.3, "learning_rate": 3.8016305555067664e-06, "loss": 3.9219, "step": 288000 }, { "epoch": 0.3, "learning_rate": 3.801286164110077e-06, "loss": 3.9203, "step": 288500 }, { "epoch": 0.3, "learning_rate": 3.800941772713387e-06, "loss": 3.9134, "step": 289000 }, { "epoch": 0.3, "learning_rate": 3.800597381316698e-06, "loss": 3.9224, "step": 289500 }, { "epoch": 0.3, "learning_rate": 3.800252989920008e-06, "loss": 3.9112, "step": 290000 }, { "epoch": 0.3, "learning_rate": 3.7999085985233184e-06, "loss": 3.9188, "step": 290500 }, { "epoch": 0.3, "learning_rate": 3.7995642071266288e-06, "loss": 3.9168, "step": 291000 }, { "epoch": 0.3, "learning_rate": 3.7992198157299395e-06, "loss": 3.919, "step": 291500 }, { "epoch": 0.3, "learning_rate": 3.7988754243332494e-06, "loss": 3.9195, "step": 292000 }, { "epoch": 0.3, "learning_rate": 3.7985310329365597e-06, "loss": 3.9171, "step": 292500 }, { "epoch": 0.3, "learning_rate": 3.79818664153987e-06, "loss": 3.9104, "step": 293000 }, { "epoch": 0.3, "learning_rate": 3.7978422501431804e-06, "loss": 3.9126, "step": 293500 }, { "epoch": 0.3, "learning_rate": 3.797497858746491e-06, "loss": 3.917, "step": 294000 }, { "epoch": 0.3, "learning_rate": 3.797153467349801e-06, "loss": 3.908, "step": 294500 }, { "epoch": 0.3, "learning_rate": 3.7968090759531118e-06, "loss": 3.9031, "step": 295000 }, { "epoch": 0.31, "learning_rate": 3.796464684556422e-06, "loss": 3.9083, "step": 295500 }, { "epoch": 0.31, "learning_rate": 3.7961202931597324e-06, "loss": 3.9071, "step": 296000 }, { "epoch": 0.31, "learning_rate": 3.7957759017630427e-06, "loss": 3.9075, "step": 296500 }, { "epoch": 0.31, "learning_rate": 3.795431510366353e-06, "loss": 3.9085, "step": 297000 }, { "epoch": 0.31, "learning_rate": 3.7950871189696634e-06, "loss": 3.907, "step": 297500 }, { "epoch": 0.31, "learning_rate": 3.794742727572974e-06, "loss": 3.9179, "step": 298000 }, { "epoch": 0.31, "learning_rate": 3.794398336176284e-06, "loss": 3.8973, "step": 298500 }, { "epoch": 0.31, "learning_rate": 3.7940539447795943e-06, "loss": 3.9062, "step": 299000 }, { "epoch": 0.31, "learning_rate": 3.793709553382905e-06, "loss": 3.911, "step": 299500 }, { "epoch": 0.31, "learning_rate": 3.793365161986215e-06, "loss": 3.9053, "step": 300000 }, { "epoch": 0.31, "learning_rate": 3.7930207705895257e-06, "loss": 3.9043, "step": 300500 }, { "epoch": 0.31, "learning_rate": 3.7926763791928356e-06, "loss": 3.897, "step": 301000 }, { "epoch": 0.31, "learning_rate": 3.7923319877961464e-06, "loss": 3.9085, "step": 301500 }, { "epoch": 0.31, "learning_rate": 3.7919875963994567e-06, "loss": 3.9003, "step": 302000 }, { "epoch": 0.31, "learning_rate": 3.791643205002767e-06, "loss": 3.9019, "step": 302500 }, { "epoch": 0.31, "learning_rate": 3.7912988136060773e-06, "loss": 3.9004, "step": 303000 }, { "epoch": 0.31, "learning_rate": 3.790954422209388e-06, "loss": 3.8962, "step": 303500 }, { "epoch": 0.31, "learning_rate": 3.790610030812698e-06, "loss": 3.8937, "step": 304000 }, { "epoch": 0.31, "learning_rate": 3.7902656394160087e-06, "loss": 3.9017, "step": 304500 }, { "epoch": 0.32, "learning_rate": 3.7899212480193186e-06, "loss": 3.8998, "step": 305000 }, { "epoch": 0.32, "learning_rate": 3.7895768566226294e-06, "loss": 3.89, "step": 305500 }, { "epoch": 0.32, "learning_rate": 3.7892324652259397e-06, "loss": 3.9042, "step": 306000 }, { "epoch": 0.32, "learning_rate": 3.7888880738292496e-06, "loss": 3.8938, "step": 306500 }, { "epoch": 0.32, "learning_rate": 3.7885436824325603e-06, "loss": 3.8921, "step": 307000 }, { "epoch": 0.32, "learning_rate": 3.7881992910358702e-06, "loss": 3.8904, "step": 307500 }, { "epoch": 0.32, "learning_rate": 3.787854899639181e-06, "loss": 3.8896, "step": 308000 }, { "epoch": 0.32, "learning_rate": 3.7875105082424913e-06, "loss": 3.8864, "step": 308500 }, { "epoch": 0.32, "learning_rate": 3.7871661168458016e-06, "loss": 3.8835, "step": 309000 }, { "epoch": 0.32, "learning_rate": 3.786821725449112e-06, "loss": 3.8933, "step": 309500 }, { "epoch": 0.32, "learning_rate": 3.7864773340524227e-06, "loss": 3.8845, "step": 310000 }, { "epoch": 0.32, "learning_rate": 3.7861329426557326e-06, "loss": 3.888, "step": 310500 }, { "epoch": 0.32, "learning_rate": 3.7857885512590433e-06, "loss": 3.8839, "step": 311000 }, { "epoch": 0.32, "learning_rate": 3.7854441598623532e-06, "loss": 3.8877, "step": 311500 }, { "epoch": 0.32, "learning_rate": 3.785099768465664e-06, "loss": 3.8859, "step": 312000 }, { "epoch": 0.32, "learning_rate": 3.7847553770689743e-06, "loss": 3.8908, "step": 312500 }, { "epoch": 0.32, "learning_rate": 3.784410985672284e-06, "loss": 3.889, "step": 313000 }, { "epoch": 0.32, "learning_rate": 3.784066594275595e-06, "loss": 3.8852, "step": 313500 }, { "epoch": 0.32, "learning_rate": 3.7837222028789053e-06, "loss": 3.8842, "step": 314000 }, { "epoch": 0.32, "learning_rate": 3.7833778114822156e-06, "loss": 3.8816, "step": 314500 }, { "epoch": 0.33, "learning_rate": 3.783033420085526e-06, "loss": 3.8866, "step": 315000 }, { "epoch": 0.33, "learning_rate": 3.7826890286888366e-06, "loss": 3.8835, "step": 315500 }, { "epoch": 0.33, "learning_rate": 3.7823446372921465e-06, "loss": 3.8833, "step": 316000 }, { "epoch": 0.33, "learning_rate": 3.7820002458954573e-06, "loss": 3.8791, "step": 316500 }, { "epoch": 0.33, "learning_rate": 3.781655854498767e-06, "loss": 3.8779, "step": 317000 }, { "epoch": 0.33, "learning_rate": 3.781311463102078e-06, "loss": 3.8822, "step": 317500 }, { "epoch": 0.33, "learning_rate": 3.7809670717053883e-06, "loss": 3.882, "step": 318000 }, { "epoch": 0.33, "learning_rate": 3.7806226803086986e-06, "loss": 3.8735, "step": 318500 }, { "epoch": 0.33, "learning_rate": 3.780278288912009e-06, "loss": 3.881, "step": 319000 }, { "epoch": 0.33, "learning_rate": 3.7799338975153196e-06, "loss": 3.8641, "step": 319500 }, { "epoch": 0.33, "learning_rate": 3.7795895061186295e-06, "loss": 3.8721, "step": 320000 }, { "epoch": 0.33, "learning_rate": 3.77924511472194e-06, "loss": 3.8748, "step": 320500 }, { "epoch": 0.33, "learning_rate": 3.77890072332525e-06, "loss": 3.8732, "step": 321000 }, { "epoch": 0.33, "learning_rate": 3.7785563319285605e-06, "loss": 3.8818, "step": 321500 }, { "epoch": 0.33, "learning_rate": 3.7782119405318713e-06, "loss": 3.873, "step": 322000 }, { "epoch": 0.33, "learning_rate": 3.777867549135181e-06, "loss": 3.8677, "step": 322500 }, { "epoch": 0.33, "learning_rate": 3.777523157738492e-06, "loss": 3.8744, "step": 323000 }, { "epoch": 0.33, "learning_rate": 3.777178766341802e-06, "loss": 3.8759, "step": 323500 }, { "epoch": 0.33, "learning_rate": 3.7768343749451125e-06, "loss": 3.8715, "step": 324000 }, { "epoch": 0.34, "learning_rate": 3.776489983548423e-06, "loss": 3.8726, "step": 324500 }, { "epoch": 0.34, "learning_rate": 3.776145592151733e-06, "loss": 3.873, "step": 325000 }, { "epoch": 0.34, "learning_rate": 3.7758012007550435e-06, "loss": 3.8751, "step": 325500 }, { "epoch": 0.34, "learning_rate": 3.7754568093583543e-06, "loss": 3.8713, "step": 326000 }, { "epoch": 0.34, "learning_rate": 3.775112417961664e-06, "loss": 3.8702, "step": 326500 }, { "epoch": 0.34, "learning_rate": 3.7747680265649745e-06, "loss": 3.8735, "step": 327000 }, { "epoch": 0.34, "learning_rate": 3.774423635168285e-06, "loss": 3.8649, "step": 327500 }, { "epoch": 0.34, "learning_rate": 3.774079243771595e-06, "loss": 3.8651, "step": 328000 }, { "epoch": 0.34, "learning_rate": 3.773734852374906e-06, "loss": 3.8745, "step": 328500 }, { "epoch": 0.34, "learning_rate": 3.7733904609782158e-06, "loss": 3.8687, "step": 329000 }, { "epoch": 0.34, "learning_rate": 3.7730460695815265e-06, "loss": 3.8663, "step": 329500 }, { "epoch": 0.34, "learning_rate": 3.772701678184837e-06, "loss": 3.8557, "step": 330000 }, { "epoch": 0.34, "learning_rate": 3.772357286788147e-06, "loss": 3.8672, "step": 330500 }, { "epoch": 0.34, "learning_rate": 3.7720128953914575e-06, "loss": 3.8652, "step": 331000 }, { "epoch": 0.34, "learning_rate": 3.771668503994768e-06, "loss": 3.854, "step": 331500 }, { "epoch": 0.34, "learning_rate": 3.771324112598078e-06, "loss": 3.8537, "step": 332000 }, { "epoch": 0.34, "learning_rate": 3.770979721201389e-06, "loss": 3.8633, "step": 332500 }, { "epoch": 0.34, "learning_rate": 3.7706353298046988e-06, "loss": 3.8476, "step": 333000 }, { "epoch": 0.34, "learning_rate": 3.7702909384080095e-06, "loss": 3.8603, "step": 333500 }, { "epoch": 0.35, "learning_rate": 3.76994654701132e-06, "loss": 3.8564, "step": 334000 }, { "epoch": 0.35, "learning_rate": 3.7696021556146297e-06, "loss": 3.8479, "step": 334500 }, { "epoch": 0.35, "learning_rate": 3.7692577642179405e-06, "loss": 3.8524, "step": 335000 }, { "epoch": 0.35, "learning_rate": 3.7689133728212504e-06, "loss": 3.8527, "step": 335500 }, { "epoch": 0.35, "learning_rate": 3.768568981424561e-06, "loss": 3.8593, "step": 336000 }, { "epoch": 0.35, "learning_rate": 3.7682245900278714e-06, "loss": 3.8565, "step": 336500 }, { "epoch": 0.35, "learning_rate": 3.7678801986311818e-06, "loss": 3.8488, "step": 337000 }, { "epoch": 0.35, "learning_rate": 3.767535807234492e-06, "loss": 3.8646, "step": 337500 }, { "epoch": 0.35, "learning_rate": 3.767191415837803e-06, "loss": 3.8464, "step": 338000 }, { "epoch": 0.35, "learning_rate": 3.7668470244411127e-06, "loss": 3.8471, "step": 338500 }, { "epoch": 0.35, "learning_rate": 3.7665026330444235e-06, "loss": 3.8461, "step": 339000 }, { "epoch": 0.35, "learning_rate": 3.7661582416477334e-06, "loss": 3.8496, "step": 339500 }, { "epoch": 0.35, "learning_rate": 3.765813850251044e-06, "loss": 3.8515, "step": 340000 }, { "epoch": 0.35, "learning_rate": 3.7654694588543544e-06, "loss": 3.8516, "step": 340500 }, { "epoch": 0.35, "learning_rate": 3.7651250674576643e-06, "loss": 3.8424, "step": 341000 }, { "epoch": 0.35, "learning_rate": 3.764780676060975e-06, "loss": 3.8439, "step": 341500 }, { "epoch": 0.35, "learning_rate": 3.7644362846642854e-06, "loss": 3.8559, "step": 342000 }, { "epoch": 0.35, "learning_rate": 3.7640918932675957e-06, "loss": 3.8497, "step": 342500 }, { "epoch": 0.35, "learning_rate": 3.763747501870906e-06, "loss": 3.8458, "step": 343000 }, { "epoch": 0.35, "learning_rate": 3.7634031104742164e-06, "loss": 3.8417, "step": 343500 }, { "epoch": 0.36, "learning_rate": 3.7630587190775267e-06, "loss": 3.8459, "step": 344000 }, { "epoch": 0.36, "learning_rate": 3.7627143276808374e-06, "loss": 3.8475, "step": 344500 }, { "epoch": 0.36, "learning_rate": 3.7623699362841473e-06, "loss": 3.8448, "step": 345000 }, { "epoch": 0.36, "learning_rate": 3.762025544887458e-06, "loss": 3.8478, "step": 345500 }, { "epoch": 0.36, "learning_rate": 3.7616811534907684e-06, "loss": 3.8436, "step": 346000 }, { "epoch": 0.36, "learning_rate": 3.7613367620940787e-06, "loss": 3.8458, "step": 346500 }, { "epoch": 0.36, "learning_rate": 3.760992370697389e-06, "loss": 3.8422, "step": 347000 }, { "epoch": 0.36, "learning_rate": 3.760647979300699e-06, "loss": 3.8435, "step": 347500 }, { "epoch": 0.36, "learning_rate": 3.7603035879040097e-06, "loss": 3.8469, "step": 348000 }, { "epoch": 0.36, "learning_rate": 3.75995919650732e-06, "loss": 3.8394, "step": 348500 }, { "epoch": 0.36, "learning_rate": 3.7596148051106303e-06, "loss": 3.8341, "step": 349000 }, { "epoch": 0.36, "learning_rate": 3.7592704137139407e-06, "loss": 3.8431, "step": 349500 }, { "epoch": 0.36, "learning_rate": 3.7589260223172514e-06, "loss": 3.8432, "step": 350000 }, { "epoch": 0.36, "learning_rate": 3.7585816309205613e-06, "loss": 3.8397, "step": 350500 }, { "epoch": 0.36, "learning_rate": 3.758237239523872e-06, "loss": 3.8452, "step": 351000 }, { "epoch": 0.36, "learning_rate": 3.757892848127182e-06, "loss": 3.8277, "step": 351500 }, { "epoch": 0.36, "learning_rate": 3.7575484567304927e-06, "loss": 3.8429, "step": 352000 }, { "epoch": 0.36, "learning_rate": 3.757204065333803e-06, "loss": 3.838, "step": 352500 }, { "epoch": 0.36, "learning_rate": 3.7568596739371133e-06, "loss": 3.8327, "step": 353000 }, { "epoch": 0.37, "learning_rate": 3.7565152825404237e-06, "loss": 3.832, "step": 353500 }, { "epoch": 0.37, "learning_rate": 3.7561708911437344e-06, "loss": 3.8433, "step": 354000 }, { "epoch": 0.37, "learning_rate": 3.7558264997470443e-06, "loss": 3.8285, "step": 354500 }, { "epoch": 0.37, "learning_rate": 3.7554821083503546e-06, "loss": 3.837, "step": 355000 }, { "epoch": 0.37, "learning_rate": 3.755137716953665e-06, "loss": 3.8313, "step": 355500 }, { "epoch": 0.37, "learning_rate": 3.7547933255569753e-06, "loss": 3.8304, "step": 356000 }, { "epoch": 0.37, "learning_rate": 3.754448934160286e-06, "loss": 3.825, "step": 356500 }, { "epoch": 0.37, "learning_rate": 3.754104542763596e-06, "loss": 3.828, "step": 357000 }, { "epoch": 0.37, "learning_rate": 3.7537601513669067e-06, "loss": 3.8313, "step": 357500 }, { "epoch": 0.37, "learning_rate": 3.7534157599702165e-06, "loss": 3.8412, "step": 358000 }, { "epoch": 0.37, "learning_rate": 3.7530713685735273e-06, "loss": 3.8216, "step": 358500 }, { "epoch": 0.37, "learning_rate": 3.7527269771768376e-06, "loss": 3.8318, "step": 359000 }, { "epoch": 0.37, "learning_rate": 3.752382585780148e-06, "loss": 3.8315, "step": 359500 }, { "epoch": 0.37, "learning_rate": 3.7520381943834583e-06, "loss": 3.8204, "step": 360000 }, { "epoch": 0.37, "learning_rate": 3.751693802986769e-06, "loss": 3.8267, "step": 360500 }, { "epoch": 0.37, "learning_rate": 3.751349411590079e-06, "loss": 3.8286, "step": 361000 }, { "epoch": 0.37, "learning_rate": 3.7510050201933892e-06, "loss": 3.8183, "step": 361500 }, { "epoch": 0.37, "learning_rate": 3.7506606287966995e-06, "loss": 3.8303, "step": 362000 }, { "epoch": 0.37, "learning_rate": 3.75031623740001e-06, "loss": 3.8228, "step": 362500 }, { "epoch": 0.38, "learning_rate": 3.7499718460033206e-06, "loss": 3.8191, "step": 363000 }, { "epoch": 0.38, "learning_rate": 3.7496274546066305e-06, "loss": 3.821, "step": 363500 }, { "epoch": 0.38, "learning_rate": 3.7492830632099413e-06, "loss": 3.8209, "step": 364000 }, { "epoch": 0.38, "learning_rate": 3.7489386718132516e-06, "loss": 3.8285, "step": 364500 }, { "epoch": 0.38, "learning_rate": 3.748594280416562e-06, "loss": 3.8338, "step": 365000 }, { "epoch": 0.38, "learning_rate": 3.7482498890198722e-06, "loss": 3.818, "step": 365500 }, { "epoch": 0.38, "learning_rate": 3.7479054976231825e-06, "loss": 3.82, "step": 366000 }, { "epoch": 0.38, "learning_rate": 3.747561106226493e-06, "loss": 3.8257, "step": 366500 }, { "epoch": 0.38, "learning_rate": 3.7472167148298036e-06, "loss": 3.8184, "step": 367000 }, { "epoch": 0.38, "learning_rate": 3.7468723234331135e-06, "loss": 3.821, "step": 367500 }, { "epoch": 0.38, "learning_rate": 3.7465279320364243e-06, "loss": 3.8222, "step": 368000 }, { "epoch": 0.38, "learning_rate": 3.7461835406397346e-06, "loss": 3.8164, "step": 368500 }, { "epoch": 0.38, "learning_rate": 3.7458391492430445e-06, "loss": 3.8233, "step": 369000 }, { "epoch": 0.38, "learning_rate": 3.7454947578463552e-06, "loss": 3.812, "step": 369500 }, { "epoch": 0.38, "learning_rate": 3.745150366449665e-06, "loss": 3.8212, "step": 370000 }, { "epoch": 0.38, "learning_rate": 3.744805975052976e-06, "loss": 3.8138, "step": 370500 }, { "epoch": 0.38, "learning_rate": 3.744461583656286e-06, "loss": 3.8171, "step": 371000 }, { "epoch": 0.38, "learning_rate": 3.7441171922595965e-06, "loss": 3.8123, "step": 371500 }, { "epoch": 0.38, "learning_rate": 3.743772800862907e-06, "loss": 3.8013, "step": 372000 }, { "epoch": 0.38, "learning_rate": 3.7434284094662176e-06, "loss": 3.8174, "step": 372500 }, { "epoch": 0.39, "learning_rate": 3.7430840180695275e-06, "loss": 3.7999, "step": 373000 }, { "epoch": 0.39, "learning_rate": 3.7427396266728382e-06, "loss": 3.8217, "step": 373500 }, { "epoch": 0.39, "learning_rate": 3.742395235276148e-06, "loss": 3.8142, "step": 374000 }, { "epoch": 0.39, "learning_rate": 3.742050843879459e-06, "loss": 3.8063, "step": 374500 }, { "epoch": 0.39, "learning_rate": 3.741706452482769e-06, "loss": 3.816, "step": 375000 }, { "epoch": 0.39, "learning_rate": 3.741362061086079e-06, "loss": 3.8099, "step": 375500 }, { "epoch": 0.39, "learning_rate": 3.74101766968939e-06, "loss": 3.8088, "step": 376000 }, { "epoch": 0.39, "learning_rate": 3.7406732782927e-06, "loss": 3.8119, "step": 376500 }, { "epoch": 0.39, "learning_rate": 3.7403288868960105e-06, "loss": 3.8068, "step": 377000 }, { "epoch": 0.39, "learning_rate": 3.739984495499321e-06, "loss": 3.8033, "step": 377500 }, { "epoch": 0.39, "learning_rate": 3.739640104102631e-06, "loss": 3.8074, "step": 378000 }, { "epoch": 0.39, "learning_rate": 3.7392957127059414e-06, "loss": 3.815, "step": 378500 }, { "epoch": 0.39, "learning_rate": 3.738951321309252e-06, "loss": 3.8131, "step": 379000 }, { "epoch": 0.39, "learning_rate": 3.738606929912562e-06, "loss": 3.8128, "step": 379500 }, { "epoch": 0.39, "learning_rate": 3.738262538515873e-06, "loss": 3.8058, "step": 380000 }, { "epoch": 0.39, "learning_rate": 3.737918147119183e-06, "loss": 3.8077, "step": 380500 }, { "epoch": 0.39, "learning_rate": 3.7375737557224935e-06, "loss": 3.8095, "step": 381000 }, { "epoch": 0.39, "learning_rate": 3.737229364325804e-06, "loss": 3.802, "step": 381500 }, { "epoch": 0.39, "learning_rate": 3.736884972929114e-06, "loss": 3.8055, "step": 382000 }, { "epoch": 0.4, "learning_rate": 3.7365405815324244e-06, "loss": 3.7974, "step": 382500 }, { "epoch": 0.4, "learning_rate": 3.7361961901357348e-06, "loss": 3.7946, "step": 383000 }, { "epoch": 0.4, "learning_rate": 3.735851798739045e-06, "loss": 3.813, "step": 383500 }, { "epoch": 0.4, "learning_rate": 3.7355074073423554e-06, "loss": 3.8, "step": 384000 }, { "epoch": 0.4, "learning_rate": 3.735163015945666e-06, "loss": 3.8093, "step": 384500 }, { "epoch": 0.4, "learning_rate": 3.734818624548976e-06, "loss": 3.8071, "step": 385000 }, { "epoch": 0.4, "learning_rate": 3.734474233152287e-06, "loss": 3.8007, "step": 385500 }, { "epoch": 0.4, "learning_rate": 3.7341298417555967e-06, "loss": 3.8042, "step": 386000 }, { "epoch": 0.4, "learning_rate": 3.7337854503589074e-06, "loss": 3.7932, "step": 386500 }, { "epoch": 0.4, "learning_rate": 3.7334410589622178e-06, "loss": 3.8027, "step": 387000 }, { "epoch": 0.4, "learning_rate": 3.733096667565528e-06, "loss": 3.7941, "step": 387500 }, { "epoch": 0.4, "learning_rate": 3.7327522761688384e-06, "loss": 3.7973, "step": 388000 }, { "epoch": 0.4, "learning_rate": 3.732407884772149e-06, "loss": 3.7915, "step": 388500 }, { "epoch": 0.4, "learning_rate": 3.732063493375459e-06, "loss": 3.8039, "step": 389000 }, { "epoch": 0.4, "learning_rate": 3.7317191019787694e-06, "loss": 3.7963, "step": 389500 }, { "epoch": 0.4, "learning_rate": 3.7313747105820797e-06, "loss": 3.7939, "step": 390000 }, { "epoch": 0.4, "learning_rate": 3.73103031918539e-06, "loss": 3.7858, "step": 390500 }, { "epoch": 0.4, "learning_rate": 3.7306859277887008e-06, "loss": 3.8048, "step": 391000 }, { "epoch": 0.4, "learning_rate": 3.7303415363920107e-06, "loss": 3.7995, "step": 391500 }, { "epoch": 0.41, "learning_rate": 3.7299971449953214e-06, "loss": 3.7933, "step": 392000 }, { "epoch": 0.41, "learning_rate": 3.7296527535986317e-06, "loss": 3.8033, "step": 392500 }, { "epoch": 0.41, "learning_rate": 3.729308362201942e-06, "loss": 3.7947, "step": 393000 }, { "epoch": 0.41, "learning_rate": 3.7289639708052524e-06, "loss": 3.7855, "step": 393500 }, { "epoch": 0.41, "learning_rate": 3.7286195794085627e-06, "loss": 3.7975, "step": 394000 }, { "epoch": 0.41, "learning_rate": 3.728275188011873e-06, "loss": 3.7955, "step": 394500 }, { "epoch": 0.41, "learning_rate": 3.7279307966151838e-06, "loss": 3.7868, "step": 395000 }, { "epoch": 0.41, "learning_rate": 3.7275864052184937e-06, "loss": 3.7879, "step": 395500 }, { "epoch": 0.41, "learning_rate": 3.7272420138218044e-06, "loss": 3.8006, "step": 396000 }, { "epoch": 0.41, "learning_rate": 3.7268976224251147e-06, "loss": 3.7881, "step": 396500 }, { "epoch": 0.41, "learning_rate": 3.7265532310284246e-06, "loss": 3.7923, "step": 397000 }, { "epoch": 0.41, "learning_rate": 3.7262088396317354e-06, "loss": 3.7998, "step": 397500 }, { "epoch": 0.41, "learning_rate": 3.7258644482350453e-06, "loss": 3.7884, "step": 398000 }, { "epoch": 0.41, "learning_rate": 3.725520056838356e-06, "loss": 3.783, "step": 398500 }, { "epoch": 0.41, "learning_rate": 3.7251756654416663e-06, "loss": 3.8002, "step": 399000 }, { "epoch": 0.41, "learning_rate": 3.7248312740449767e-06, "loss": 3.7948, "step": 399500 }, { "epoch": 0.41, "learning_rate": 3.724486882648287e-06, "loss": 3.7973, "step": 400000 }, { "epoch": 0.41, "learning_rate": 3.7241424912515977e-06, "loss": 3.7883, "step": 400500 }, { "epoch": 0.41, "learning_rate": 3.7237980998549076e-06, "loss": 3.7827, "step": 401000 }, { "epoch": 0.41, "learning_rate": 3.7234537084582184e-06, "loss": 3.7858, "step": 401500 }, { "epoch": 0.42, "learning_rate": 3.7231093170615283e-06, "loss": 3.7839, "step": 402000 }, { "epoch": 0.42, "learning_rate": 3.722764925664839e-06, "loss": 3.7878, "step": 402500 }, { "epoch": 0.42, "learning_rate": 3.7224205342681493e-06, "loss": 3.7774, "step": 403000 }, { "epoch": 0.42, "learning_rate": 3.7220761428714592e-06, "loss": 3.7852, "step": 403500 }, { "epoch": 0.42, "learning_rate": 3.72173175147477e-06, "loss": 3.7871, "step": 404000 }, { "epoch": 0.42, "learning_rate": 3.72138736007808e-06, "loss": 3.7858, "step": 404500 }, { "epoch": 0.42, "learning_rate": 3.7210429686813906e-06, "loss": 3.7823, "step": 405000 }, { "epoch": 0.42, "learning_rate": 3.720698577284701e-06, "loss": 3.7956, "step": 405500 }, { "epoch": 0.42, "learning_rate": 3.7203541858880113e-06, "loss": 3.7722, "step": 406000 }, { "epoch": 0.42, "learning_rate": 3.7200097944913216e-06, "loss": 3.7792, "step": 406500 }, { "epoch": 0.42, "learning_rate": 3.7196654030946323e-06, "loss": 3.7679, "step": 407000 }, { "epoch": 0.42, "learning_rate": 3.7193210116979422e-06, "loss": 3.7816, "step": 407500 }, { "epoch": 0.42, "learning_rate": 3.718976620301253e-06, "loss": 3.7857, "step": 408000 }, { "epoch": 0.42, "learning_rate": 3.718632228904563e-06, "loss": 3.77, "step": 408500 }, { "epoch": 0.42, "learning_rate": 3.7182878375078736e-06, "loss": 3.7771, "step": 409000 }, { "epoch": 0.42, "learning_rate": 3.717943446111184e-06, "loss": 3.7839, "step": 409500 }, { "epoch": 0.42, "learning_rate": 3.717599054714494e-06, "loss": 3.7769, "step": 410000 }, { "epoch": 0.42, "learning_rate": 3.7172546633178046e-06, "loss": 3.7733, "step": 410500 }, { "epoch": 0.42, "learning_rate": 3.716910271921115e-06, "loss": 3.7725, "step": 411000 }, { "epoch": 0.43, "learning_rate": 3.7165658805244252e-06, "loss": 3.7878, "step": 411500 }, { "epoch": 0.43, "learning_rate": 3.7162214891277355e-06, "loss": 3.7753, "step": 412000 }, { "epoch": 0.43, "learning_rate": 3.715877097731046e-06, "loss": 3.7731, "step": 412500 }, { "epoch": 0.43, "learning_rate": 3.715532706334356e-06, "loss": 3.7732, "step": 413000 }, { "epoch": 0.43, "learning_rate": 3.715188314937667e-06, "loss": 3.7738, "step": 413500 }, { "epoch": 0.43, "learning_rate": 3.714843923540977e-06, "loss": 3.7744, "step": 414000 }, { "epoch": 0.43, "learning_rate": 3.7144995321442876e-06, "loss": 3.7733, "step": 414500 }, { "epoch": 0.43, "learning_rate": 3.714155140747598e-06, "loss": 3.77, "step": 415000 }, { "epoch": 0.43, "learning_rate": 3.7138107493509082e-06, "loss": 3.7764, "step": 415500 }, { "epoch": 0.43, "learning_rate": 3.7134663579542185e-06, "loss": 3.7756, "step": 416000 }, { "epoch": 0.43, "learning_rate": 3.713121966557529e-06, "loss": 3.7655, "step": 416500 }, { "epoch": 0.43, "learning_rate": 3.712777575160839e-06, "loss": 3.7657, "step": 417000 }, { "epoch": 0.43, "learning_rate": 3.7124331837641495e-06, "loss": 3.7658, "step": 417500 }, { "epoch": 0.43, "learning_rate": 3.71208879236746e-06, "loss": 3.7755, "step": 418000 }, { "epoch": 0.43, "learning_rate": 3.71174440097077e-06, "loss": 3.7703, "step": 418500 }, { "epoch": 0.43, "learning_rate": 3.711400009574081e-06, "loss": 3.7647, "step": 419000 }, { "epoch": 0.43, "learning_rate": 3.711055618177391e-06, "loss": 3.7746, "step": 419500 }, { "epoch": 0.43, "learning_rate": 3.7107112267807015e-06, "loss": 3.7667, "step": 420000 }, { "epoch": 0.43, "learning_rate": 3.7103668353840114e-06, "loss": 3.7735, "step": 420500 }, { "epoch": 0.43, "learning_rate": 3.710022443987322e-06, "loss": 3.7578, "step": 421000 }, { "epoch": 0.44, "learning_rate": 3.7096780525906325e-06, "loss": 3.7644, "step": 421500 }, { "epoch": 0.44, "learning_rate": 3.709333661193943e-06, "loss": 3.7655, "step": 422000 }, { "epoch": 0.44, "learning_rate": 3.708989269797253e-06, "loss": 3.7659, "step": 422500 }, { "epoch": 0.44, "learning_rate": 3.708644878400564e-06, "loss": 3.7626, "step": 423000 }, { "epoch": 0.44, "learning_rate": 3.708300487003874e-06, "loss": 3.7626, "step": 423500 }, { "epoch": 0.44, "learning_rate": 3.707956095607184e-06, "loss": 3.7606, "step": 424000 }, { "epoch": 0.44, "learning_rate": 3.7076117042104944e-06, "loss": 3.7543, "step": 424500 }, { "epoch": 0.44, "learning_rate": 3.7072673128138048e-06, "loss": 3.7633, "step": 425000 }, { "epoch": 0.44, "learning_rate": 3.7069229214171155e-06, "loss": 3.7617, "step": 425500 }, { "epoch": 0.44, "learning_rate": 3.7065785300204254e-06, "loss": 3.7631, "step": 426000 }, { "epoch": 0.44, "learning_rate": 3.706234138623736e-06, "loss": 3.7596, "step": 426500 }, { "epoch": 0.44, "learning_rate": 3.7058897472270465e-06, "loss": 3.7609, "step": 427000 }, { "epoch": 0.44, "learning_rate": 3.705545355830357e-06, "loss": 3.7594, "step": 427500 }, { "epoch": 0.44, "learning_rate": 3.705200964433667e-06, "loss": 3.762, "step": 428000 }, { "epoch": 0.44, "learning_rate": 3.7048565730369774e-06, "loss": 3.7532, "step": 428500 }, { "epoch": 0.44, "learning_rate": 3.7045121816402878e-06, "loss": 3.7599, "step": 429000 }, { "epoch": 0.44, "learning_rate": 3.7041677902435985e-06, "loss": 3.7631, "step": 429500 }, { "epoch": 0.44, "learning_rate": 3.7038233988469084e-06, "loss": 3.757, "step": 430000 }, { "epoch": 0.44, "learning_rate": 3.703479007450219e-06, "loss": 3.7655, "step": 430500 }, { "epoch": 0.45, "learning_rate": 3.7031346160535295e-06, "loss": 3.7601, "step": 431000 }, { "epoch": 0.45, "learning_rate": 3.7027902246568394e-06, "loss": 3.7613, "step": 431500 }, { "epoch": 0.45, "learning_rate": 3.70244583326015e-06, "loss": 3.7578, "step": 432000 }, { "epoch": 0.45, "learning_rate": 3.70210144186346e-06, "loss": 3.7575, "step": 432500 }, { "epoch": 0.45, "learning_rate": 3.7017570504667708e-06, "loss": 3.7518, "step": 433000 }, { "epoch": 0.45, "learning_rate": 3.701412659070081e-06, "loss": 3.7538, "step": 433500 }, { "epoch": 0.45, "learning_rate": 3.7010682676733914e-06, "loss": 3.7588, "step": 434000 }, { "epoch": 0.45, "learning_rate": 3.7007238762767017e-06, "loss": 3.749, "step": 434500 }, { "epoch": 0.45, "learning_rate": 3.7003794848800125e-06, "loss": 3.7596, "step": 435000 }, { "epoch": 0.45, "learning_rate": 3.7000350934833224e-06, "loss": 3.7538, "step": 435500 }, { "epoch": 0.45, "learning_rate": 3.699690702086633e-06, "loss": 3.7571, "step": 436000 }, { "epoch": 0.45, "learning_rate": 3.699346310689943e-06, "loss": 3.7567, "step": 436500 }, { "epoch": 0.45, "learning_rate": 3.6990019192932538e-06, "loss": 3.7591, "step": 437000 }, { "epoch": 0.45, "learning_rate": 3.698657527896564e-06, "loss": 3.7536, "step": 437500 }, { "epoch": 0.45, "learning_rate": 3.698313136499874e-06, "loss": 3.7523, "step": 438000 }, { "epoch": 0.45, "learning_rate": 3.6979687451031847e-06, "loss": 3.7602, "step": 438500 }, { "epoch": 0.45, "learning_rate": 3.697624353706495e-06, "loss": 3.7492, "step": 439000 }, { "epoch": 0.45, "learning_rate": 3.6972799623098054e-06, "loss": 3.7544, "step": 439500 }, { "epoch": 0.45, "learning_rate": 3.6969355709131157e-06, "loss": 3.7545, "step": 440000 }, { "epoch": 0.46, "learning_rate": 3.696591179516426e-06, "loss": 3.7402, "step": 440500 }, { "epoch": 0.46, "learning_rate": 3.6962467881197363e-06, "loss": 3.7573, "step": 441000 }, { "epoch": 0.46, "learning_rate": 3.695902396723047e-06, "loss": 3.7494, "step": 441500 }, { "epoch": 0.46, "learning_rate": 3.695558005326357e-06, "loss": 3.7536, "step": 442000 }, { "epoch": 0.46, "learning_rate": 3.6952136139296677e-06, "loss": 3.7489, "step": 442500 }, { "epoch": 0.46, "learning_rate": 3.694869222532978e-06, "loss": 3.7373, "step": 443000 }, { "epoch": 0.46, "learning_rate": 3.6945248311362884e-06, "loss": 3.7494, "step": 443500 }, { "epoch": 0.46, "learning_rate": 3.6941804397395987e-06, "loss": 3.7416, "step": 444000 }, { "epoch": 0.46, "learning_rate": 3.693836048342909e-06, "loss": 3.7608, "step": 444500 }, { "epoch": 0.46, "learning_rate": 3.6934916569462193e-06, "loss": 3.745, "step": 445000 }, { "epoch": 0.46, "learning_rate": 3.6931472655495297e-06, "loss": 3.7494, "step": 445500 }, { "epoch": 0.46, "learning_rate": 3.69280287415284e-06, "loss": 3.7488, "step": 446000 }, { "epoch": 0.46, "learning_rate": 3.6924584827561503e-06, "loss": 3.7469, "step": 446500 }, { "epoch": 0.46, "learning_rate": 3.692114091359461e-06, "loss": 3.7448, "step": 447000 }, { "epoch": 0.46, "learning_rate": 3.691769699962771e-06, "loss": 3.7474, "step": 447500 }, { "epoch": 0.46, "learning_rate": 3.6914253085660817e-06, "loss": 3.7482, "step": 448000 }, { "epoch": 0.46, "learning_rate": 3.6910809171693916e-06, "loss": 3.7371, "step": 448500 }, { "epoch": 0.46, "learning_rate": 3.6907365257727023e-06, "loss": 3.7459, "step": 449000 }, { "epoch": 0.46, "learning_rate": 3.6903921343760127e-06, "loss": 3.744, "step": 449500 }, { "epoch": 0.46, "learning_rate": 3.690047742979323e-06, "loss": 3.739, "step": 450000 }, { "epoch": 0.47, "learning_rate": 3.6897033515826333e-06, "loss": 3.7346, "step": 450500 }, { "epoch": 0.47, "learning_rate": 3.689358960185944e-06, "loss": 3.7475, "step": 451000 }, { "epoch": 0.47, "learning_rate": 3.689014568789254e-06, "loss": 3.7401, "step": 451500 }, { "epoch": 0.47, "learning_rate": 3.6886701773925643e-06, "loss": 3.7453, "step": 452000 }, { "epoch": 0.47, "learning_rate": 3.6883257859958746e-06, "loss": 3.7437, "step": 452500 }, { "epoch": 0.47, "learning_rate": 3.687981394599185e-06, "loss": 3.7396, "step": 453000 }, { "epoch": 0.47, "learning_rate": 3.6876370032024957e-06, "loss": 3.744, "step": 453500 }, { "epoch": 0.47, "learning_rate": 3.6872926118058056e-06, "loss": 3.7368, "step": 454000 }, { "epoch": 0.47, "learning_rate": 3.6869482204091163e-06, "loss": 3.7408, "step": 454500 }, { "epoch": 0.47, "learning_rate": 3.686603829012426e-06, "loss": 3.7428, "step": 455000 }, { "epoch": 0.47, "learning_rate": 3.686259437615737e-06, "loss": 3.7401, "step": 455500 }, { "epoch": 0.47, "learning_rate": 3.6859150462190473e-06, "loss": 3.7433, "step": 456000 }, { "epoch": 0.47, "learning_rate": 3.6855706548223576e-06, "loss": 3.7439, "step": 456500 }, { "epoch": 0.47, "learning_rate": 3.685226263425668e-06, "loss": 3.7356, "step": 457000 }, { "epoch": 0.47, "learning_rate": 3.6848818720289787e-06, "loss": 3.7424, "step": 457500 }, { "epoch": 0.47, "learning_rate": 3.6845374806322885e-06, "loss": 3.7371, "step": 458000 }, { "epoch": 0.47, "learning_rate": 3.6841930892355993e-06, "loss": 3.736, "step": 458500 }, { "epoch": 0.47, "learning_rate": 3.683848697838909e-06, "loss": 3.7422, "step": 459000 }, { "epoch": 0.47, "learning_rate": 3.6835043064422195e-06, "loss": 3.739, "step": 459500 }, { "epoch": 0.48, "learning_rate": 3.6831599150455303e-06, "loss": 3.7348, "step": 460000 }, { "epoch": 0.48, "learning_rate": 3.68281552364884e-06, "loss": 3.7331, "step": 460500 }, { "epoch": 0.48, "learning_rate": 3.682471132252151e-06, "loss": 3.7401, "step": 461000 }, { "epoch": 0.48, "learning_rate": 3.6821267408554612e-06, "loss": 3.7312, "step": 461500 }, { "epoch": 0.48, "learning_rate": 3.6817823494587715e-06, "loss": 3.7373, "step": 462000 }, { "epoch": 0.48, "learning_rate": 3.681437958062082e-06, "loss": 3.7313, "step": 462500 }, { "epoch": 0.48, "learning_rate": 3.681093566665392e-06, "loss": 3.7315, "step": 463000 }, { "epoch": 0.48, "learning_rate": 3.6807491752687025e-06, "loss": 3.7391, "step": 463500 }, { "epoch": 0.48, "learning_rate": 3.6804047838720133e-06, "loss": 3.7357, "step": 464000 }, { "epoch": 0.48, "learning_rate": 3.680060392475323e-06, "loss": 3.7314, "step": 464500 }, { "epoch": 0.48, "learning_rate": 3.679716001078634e-06, "loss": 3.7313, "step": 465000 }, { "epoch": 0.48, "learning_rate": 3.6793716096819442e-06, "loss": 3.7284, "step": 465500 }, { "epoch": 0.48, "learning_rate": 3.679027218285254e-06, "loss": 3.7319, "step": 466000 }, { "epoch": 0.48, "learning_rate": 3.678682826888565e-06, "loss": 3.7441, "step": 466500 }, { "epoch": 0.48, "learning_rate": 3.6783384354918748e-06, "loss": 3.7246, "step": 467000 }, { "epoch": 0.48, "learning_rate": 3.6779940440951855e-06, "loss": 3.7369, "step": 467500 }, { "epoch": 0.48, "learning_rate": 3.677649652698496e-06, "loss": 3.7258, "step": 468000 }, { "epoch": 0.48, "learning_rate": 3.677305261301806e-06, "loss": 3.7328, "step": 468500 }, { "epoch": 0.48, "learning_rate": 3.6769608699051165e-06, "loss": 3.728, "step": 469000 }, { "epoch": 0.49, "learning_rate": 3.6766164785084272e-06, "loss": 3.7307, "step": 469500 }, { "epoch": 0.49, "learning_rate": 3.676272087111737e-06, "loss": 3.7367, "step": 470000 }, { "epoch": 0.49, "learning_rate": 3.675927695715048e-06, "loss": 3.7295, "step": 470500 }, { "epoch": 0.49, "learning_rate": 3.6755833043183578e-06, "loss": 3.7301, "step": 471000 }, { "epoch": 0.49, "learning_rate": 3.6752389129216685e-06, "loss": 3.7239, "step": 471500 }, { "epoch": 0.49, "learning_rate": 3.674894521524979e-06, "loss": 3.7211, "step": 472000 }, { "epoch": 0.49, "learning_rate": 3.674550130128289e-06, "loss": 3.7264, "step": 472500 }, { "epoch": 0.49, "learning_rate": 3.6742057387315995e-06, "loss": 3.7261, "step": 473000 }, { "epoch": 0.49, "learning_rate": 3.67386134733491e-06, "loss": 3.7342, "step": 473500 }, { "epoch": 0.49, "learning_rate": 3.67351695593822e-06, "loss": 3.7211, "step": 474000 }, { "epoch": 0.49, "learning_rate": 3.6731725645415304e-06, "loss": 3.727, "step": 474500 }, { "epoch": 0.49, "learning_rate": 3.6728281731448408e-06, "loss": 3.7194, "step": 475000 }, { "epoch": 0.49, "learning_rate": 3.672483781748151e-06, "loss": 3.7149, "step": 475500 }, { "epoch": 0.49, "learning_rate": 3.672139390351462e-06, "loss": 3.7166, "step": 476000 }, { "epoch": 0.49, "learning_rate": 3.6717949989547717e-06, "loss": 3.7261, "step": 476500 }, { "epoch": 0.49, "learning_rate": 3.6714506075580825e-06, "loss": 3.7171, "step": 477000 }, { "epoch": 0.49, "learning_rate": 3.671106216161393e-06, "loss": 3.7183, "step": 477500 }, { "epoch": 0.49, "learning_rate": 3.670761824764703e-06, "loss": 3.7211, "step": 478000 }, { "epoch": 0.49, "learning_rate": 3.6704174333680134e-06, "loss": 3.7216, "step": 478500 }, { "epoch": 0.49, "learning_rate": 3.6700730419713238e-06, "loss": 3.7295, "step": 479000 }, { "epoch": 0.5, "learning_rate": 3.669728650574634e-06, "loss": 3.7193, "step": 479500 }, { "epoch": 0.5, "learning_rate": 3.6693842591779444e-06, "loss": 3.7185, "step": 480000 }, { "epoch": 0.5, "learning_rate": 3.6690398677812547e-06, "loss": 3.7139, "step": 480500 }, { "epoch": 0.5, "learning_rate": 3.668695476384565e-06, "loss": 3.7258, "step": 481000 }, { "epoch": 0.5, "learning_rate": 3.668351084987876e-06, "loss": 3.7146, "step": 481500 }, { "epoch": 0.5, "learning_rate": 3.6680066935911857e-06, "loss": 3.7138, "step": 482000 }, { "epoch": 0.5, "learning_rate": 3.6676623021944964e-06, "loss": 3.7298, "step": 482500 }, { "epoch": 0.5, "learning_rate": 3.6673179107978063e-06, "loss": 3.7225, "step": 483000 }, { "epoch": 0.5, "learning_rate": 3.666973519401117e-06, "loss": 3.7119, "step": 483500 }, { "epoch": 0.5, "learning_rate": 3.6666291280044274e-06, "loss": 3.7207, "step": 484000 }, { "epoch": 0.5, "learning_rate": 3.6662847366077377e-06, "loss": 3.7224, "step": 484500 }, { "epoch": 0.5, "learning_rate": 3.665940345211048e-06, "loss": 3.7145, "step": 485000 }, { "epoch": 0.5, "learning_rate": 3.665595953814359e-06, "loss": 3.708, "step": 485500 }, { "epoch": 0.5, "learning_rate": 3.6652515624176687e-06, "loss": 3.7195, "step": 486000 }, { "epoch": 0.5, "learning_rate": 3.664907171020979e-06, "loss": 3.7206, "step": 486500 }, { "epoch": 0.5, "learning_rate": 3.6645627796242893e-06, "loss": 3.714, "step": 487000 }, { "epoch": 0.5, "learning_rate": 3.6642183882275997e-06, "loss": 3.7142, "step": 487500 }, { "epoch": 0.5, "learning_rate": 3.6638739968309104e-06, "loss": 3.7147, "step": 488000 }, { "epoch": 0.5, "learning_rate": 3.6635296054342203e-06, "loss": 3.7167, "step": 488500 }, { "epoch": 0.51, "learning_rate": 3.663185214037531e-06, "loss": 3.7135, "step": 489000 }, { "epoch": 0.51, "learning_rate": 3.662840822640841e-06, "loss": 3.7104, "step": 489500 }, { "epoch": 0.51, "learning_rate": 3.6624964312441517e-06, "loss": 3.7128, "step": 490000 }, { "epoch": 0.51, "learning_rate": 3.662152039847462e-06, "loss": 3.7138, "step": 490500 }, { "epoch": 0.51, "learning_rate": 3.6618076484507723e-06, "loss": 3.7158, "step": 491000 }, { "epoch": 0.51, "learning_rate": 3.6614632570540827e-06, "loss": 3.7087, "step": 491500 }, { "epoch": 0.51, "learning_rate": 3.6611188656573934e-06, "loss": 3.7163, "step": 492000 }, { "epoch": 0.51, "learning_rate": 3.6607744742607033e-06, "loss": 3.7024, "step": 492500 }, { "epoch": 0.51, "learning_rate": 3.660430082864014e-06, "loss": 3.7058, "step": 493000 }, { "epoch": 0.51, "learning_rate": 3.660085691467324e-06, "loss": 3.7033, "step": 493500 }, { "epoch": 0.51, "learning_rate": 3.6597413000706343e-06, "loss": 3.7139, "step": 494000 }, { "epoch": 0.51, "learning_rate": 3.659396908673945e-06, "loss": 3.7082, "step": 494500 }, { "epoch": 0.51, "learning_rate": 3.659052517277255e-06, "loss": 3.7117, "step": 495000 }, { "epoch": 0.51, "learning_rate": 3.6587081258805657e-06, "loss": 3.7025, "step": 495500 }, { "epoch": 0.51, "learning_rate": 3.658363734483876e-06, "loss": 3.7121, "step": 496000 }, { "epoch": 0.51, "learning_rate": 3.6580193430871863e-06, "loss": 3.7063, "step": 496500 }, { "epoch": 0.51, "learning_rate": 3.6576749516904966e-06, "loss": 3.7099, "step": 497000 }, { "epoch": 0.51, "learning_rate": 3.657330560293807e-06, "loss": 3.697, "step": 497500 }, { "epoch": 0.51, "learning_rate": 3.6569861688971173e-06, "loss": 3.7092, "step": 498000 }, { "epoch": 0.52, "learning_rate": 3.656641777500428e-06, "loss": 3.7042, "step": 498500 }, { "epoch": 0.52, "learning_rate": 3.656297386103738e-06, "loss": 3.7037, "step": 499000 }, { "epoch": 0.52, "learning_rate": 3.6559529947070487e-06, "loss": 3.7033, "step": 499500 }, { "epoch": 0.52, "learning_rate": 3.655608603310359e-06, "loss": 3.7031, "step": 500000 }, { "epoch": 0.52, "learning_rate": 3.655264211913669e-06, "loss": 3.7087, "step": 500500 }, { "epoch": 0.52, "learning_rate": 3.6549198205169796e-06, "loss": 3.7034, "step": 501000 }, { "epoch": 0.52, "learning_rate": 3.6545754291202895e-06, "loss": 3.7017, "step": 501500 }, { "epoch": 0.52, "learning_rate": 3.6542310377236003e-06, "loss": 3.7104, "step": 502000 }, { "epoch": 0.52, "learning_rate": 3.6538866463269106e-06, "loss": 3.7017, "step": 502500 }, { "epoch": 0.52, "learning_rate": 3.653542254930221e-06, "loss": 3.6995, "step": 503000 }, { "epoch": 0.52, "learning_rate": 3.6531978635335312e-06, "loss": 3.7064, "step": 503500 }, { "epoch": 0.52, "learning_rate": 3.652853472136842e-06, "loss": 3.7073, "step": 504000 }, { "epoch": 0.52, "learning_rate": 3.652509080740152e-06, "loss": 3.7011, "step": 504500 }, { "epoch": 0.52, "learning_rate": 3.6521646893434626e-06, "loss": 3.7039, "step": 505000 }, { "epoch": 0.52, "learning_rate": 3.6518202979467725e-06, "loss": 3.7029, "step": 505500 }, { "epoch": 0.52, "learning_rate": 3.6514759065500833e-06, "loss": 3.7007, "step": 506000 }, { "epoch": 0.52, "learning_rate": 3.6511315151533936e-06, "loss": 3.6942, "step": 506500 }, { "epoch": 0.52, "learning_rate": 3.650787123756704e-06, "loss": 3.6915, "step": 507000 }, { "epoch": 0.52, "learning_rate": 3.6504427323600142e-06, "loss": 3.6946, "step": 507500 }, { "epoch": 0.52, "learning_rate": 3.6500983409633246e-06, "loss": 3.7012, "step": 508000 }, { "epoch": 0.53, "learning_rate": 3.649753949566635e-06, "loss": 3.6997, "step": 508500 }, { "epoch": 0.53, "learning_rate": 3.649409558169945e-06, "loss": 3.7029, "step": 509000 }, { "epoch": 0.53, "learning_rate": 3.6490651667732555e-06, "loss": 3.6988, "step": 509500 }, { "epoch": 0.53, "learning_rate": 3.648720775376566e-06, "loss": 3.6866, "step": 510000 }, { "epoch": 0.53, "learning_rate": 3.6483763839798766e-06, "loss": 3.706, "step": 510500 }, { "epoch": 0.53, "learning_rate": 3.6480319925831865e-06, "loss": 3.6931, "step": 511000 }, { "epoch": 0.53, "learning_rate": 3.6476876011864972e-06, "loss": 3.6901, "step": 511500 }, { "epoch": 0.53, "learning_rate": 3.6473432097898075e-06, "loss": 3.697, "step": 512000 }, { "epoch": 0.53, "learning_rate": 3.646998818393118e-06, "loss": 3.69, "step": 512500 }, { "epoch": 0.53, "learning_rate": 3.646654426996428e-06, "loss": 3.698, "step": 513000 }, { "epoch": 0.53, "learning_rate": 3.6463100355997385e-06, "loss": 3.6918, "step": 513500 }, { "epoch": 0.53, "learning_rate": 3.645965644203049e-06, "loss": 3.6901, "step": 514000 }, { "epoch": 0.53, "learning_rate": 3.645621252806359e-06, "loss": 3.6929, "step": 514500 }, { "epoch": 0.53, "learning_rate": 3.6452768614096695e-06, "loss": 3.6977, "step": 515000 }, { "epoch": 0.53, "learning_rate": 3.64493247001298e-06, "loss": 3.7048, "step": 515500 }, { "epoch": 0.53, "learning_rate": 3.6445880786162905e-06, "loss": 3.6895, "step": 516000 }, { "epoch": 0.53, "learning_rate": 3.6442436872196004e-06, "loss": 3.6955, "step": 516500 }, { "epoch": 0.53, "learning_rate": 3.643899295822911e-06, "loss": 3.6992, "step": 517000 }, { "epoch": 0.53, "learning_rate": 3.643554904426221e-06, "loss": 3.6902, "step": 517500 }, { "epoch": 0.54, "learning_rate": 3.643210513029532e-06, "loss": 3.6934, "step": 518000 }, { "epoch": 0.54, "learning_rate": 3.642866121632842e-06, "loss": 3.6973, "step": 518500 }, { "epoch": 0.54, "learning_rate": 3.6425217302361525e-06, "loss": 3.697, "step": 519000 }, { "epoch": 0.54, "learning_rate": 3.642177338839463e-06, "loss": 3.696, "step": 519500 }, { "epoch": 0.54, "learning_rate": 3.6418329474427735e-06, "loss": 3.6849, "step": 520000 }, { "epoch": 0.54, "learning_rate": 3.6414885560460834e-06, "loss": 3.6876, "step": 520500 }, { "epoch": 0.54, "learning_rate": 3.641144164649394e-06, "loss": 3.6987, "step": 521000 }, { "epoch": 0.54, "learning_rate": 3.640799773252704e-06, "loss": 3.6908, "step": 521500 }, { "epoch": 0.54, "learning_rate": 3.6404553818560144e-06, "loss": 3.6849, "step": 522000 }, { "epoch": 0.54, "learning_rate": 3.640110990459325e-06, "loss": 3.6889, "step": 522500 }, { "epoch": 0.54, "learning_rate": 3.639766599062635e-06, "loss": 3.6863, "step": 523000 }, { "epoch": 0.54, "learning_rate": 3.639422207665946e-06, "loss": 3.6844, "step": 523500 }, { "epoch": 0.54, "learning_rate": 3.639077816269256e-06, "loss": 3.6881, "step": 524000 }, { "epoch": 0.54, "learning_rate": 3.6387334248725664e-06, "loss": 3.6916, "step": 524500 }, { "epoch": 0.54, "learning_rate": 3.6383890334758768e-06, "loss": 3.689, "step": 525000 }, { "epoch": 0.54, "learning_rate": 3.638044642079187e-06, "loss": 3.6871, "step": 525500 }, { "epoch": 0.54, "learning_rate": 3.6377002506824974e-06, "loss": 3.6887, "step": 526000 }, { "epoch": 0.54, "learning_rate": 3.637355859285808e-06, "loss": 3.6813, "step": 526500 }, { "epoch": 0.54, "learning_rate": 3.637011467889118e-06, "loss": 3.6813, "step": 527000 }, { "epoch": 0.54, "learning_rate": 3.636667076492429e-06, "loss": 3.6875, "step": 527500 }, { "epoch": 0.55, "learning_rate": 3.636322685095739e-06, "loss": 3.6914, "step": 528000 }, { "epoch": 0.55, "learning_rate": 3.635978293699049e-06, "loss": 3.6814, "step": 528500 }, { "epoch": 0.55, "learning_rate": 3.6356339023023598e-06, "loss": 3.6819, "step": 529000 }, { "epoch": 0.55, "learning_rate": 3.6352895109056697e-06, "loss": 3.6864, "step": 529500 }, { "epoch": 0.55, "learning_rate": 3.6349451195089804e-06, "loss": 3.6884, "step": 530000 }, { "epoch": 0.55, "learning_rate": 3.6346007281122907e-06, "loss": 3.6853, "step": 530500 }, { "epoch": 0.55, "learning_rate": 3.634256336715601e-06, "loss": 3.6803, "step": 531000 }, { "epoch": 0.55, "learning_rate": 3.6339119453189114e-06, "loss": 3.6853, "step": 531500 }, { "epoch": 0.55, "learning_rate": 3.633567553922222e-06, "loss": 3.685, "step": 532000 }, { "epoch": 0.55, "learning_rate": 3.633223162525532e-06, "loss": 3.6887, "step": 532500 }, { "epoch": 0.55, "learning_rate": 3.6328787711288428e-06, "loss": 3.684, "step": 533000 }, { "epoch": 0.55, "learning_rate": 3.6325343797321527e-06, "loss": 3.6838, "step": 533500 }, { "epoch": 0.55, "learning_rate": 3.6321899883354634e-06, "loss": 3.6846, "step": 534000 }, { "epoch": 0.55, "learning_rate": 3.6318455969387737e-06, "loss": 3.6829, "step": 534500 }, { "epoch": 0.55, "learning_rate": 3.631501205542084e-06, "loss": 3.6678, "step": 535000 }, { "epoch": 0.55, "learning_rate": 3.6311568141453944e-06, "loss": 3.6734, "step": 535500 }, { "epoch": 0.55, "learning_rate": 3.6308124227487043e-06, "loss": 3.6786, "step": 536000 }, { "epoch": 0.55, "learning_rate": 3.630468031352015e-06, "loss": 3.679, "step": 536500 }, { "epoch": 0.55, "learning_rate": 3.6301236399553253e-06, "loss": 3.6847, "step": 537000 }, { "epoch": 0.56, "learning_rate": 3.6297792485586357e-06, "loss": 3.6834, "step": 537500 }, { "epoch": 0.56, "learning_rate": 3.629434857161946e-06, "loss": 3.6751, "step": 538000 }, { "epoch": 0.56, "learning_rate": 3.6290904657652567e-06, "loss": 3.6878, "step": 538500 }, { "epoch": 0.56, "learning_rate": 3.6287460743685666e-06, "loss": 3.6727, "step": 539000 }, { "epoch": 0.56, "learning_rate": 3.6284016829718774e-06, "loss": 3.6809, "step": 539500 }, { "epoch": 0.56, "learning_rate": 3.6280572915751873e-06, "loss": 3.681, "step": 540000 }, { "epoch": 0.56, "learning_rate": 3.627712900178498e-06, "loss": 3.6865, "step": 540500 }, { "epoch": 0.56, "learning_rate": 3.6273685087818083e-06, "loss": 3.6826, "step": 541000 }, { "epoch": 0.56, "learning_rate": 3.6270241173851187e-06, "loss": 3.68, "step": 541500 }, { "epoch": 0.56, "learning_rate": 3.626679725988429e-06, "loss": 3.6723, "step": 542000 }, { "epoch": 0.56, "learning_rate": 3.6263353345917393e-06, "loss": 3.6817, "step": 542500 }, { "epoch": 0.56, "learning_rate": 3.6259909431950496e-06, "loss": 3.6784, "step": 543000 }, { "epoch": 0.56, "learning_rate": 3.62564655179836e-06, "loss": 3.6733, "step": 543500 }, { "epoch": 0.56, "learning_rate": 3.6253021604016703e-06, "loss": 3.6766, "step": 544000 }, { "epoch": 0.56, "learning_rate": 3.6249577690049806e-06, "loss": 3.6831, "step": 544500 }, { "epoch": 0.56, "learning_rate": 3.6246133776082913e-06, "loss": 3.68, "step": 545000 }, { "epoch": 0.56, "learning_rate": 3.6242689862116012e-06, "loss": 3.6753, "step": 545500 }, { "epoch": 0.56, "learning_rate": 3.623924594814912e-06, "loss": 3.6686, "step": 546000 }, { "epoch": 0.56, "learning_rate": 3.6235802034182223e-06, "loss": 3.6755, "step": 546500 }, { "epoch": 0.57, "learning_rate": 3.6232358120215326e-06, "loss": 3.6665, "step": 547000 }, { "epoch": 0.57, "learning_rate": 3.622891420624843e-06, "loss": 3.6784, "step": 547500 }, { "epoch": 0.57, "learning_rate": 3.6225470292281533e-06, "loss": 3.6644, "step": 548000 }, { "epoch": 0.57, "learning_rate": 3.6222026378314636e-06, "loss": 3.6665, "step": 548500 }, { "epoch": 0.57, "learning_rate": 3.621858246434774e-06, "loss": 3.6692, "step": 549000 }, { "epoch": 0.57, "learning_rate": 3.6215138550380842e-06, "loss": 3.6625, "step": 549500 }, { "epoch": 0.57, "learning_rate": 3.6211694636413946e-06, "loss": 3.6661, "step": 550000 }, { "epoch": 0.57, "learning_rate": 3.6208250722447053e-06, "loss": 3.6734, "step": 550500 }, { "epoch": 0.57, "learning_rate": 3.620480680848015e-06, "loss": 3.6781, "step": 551000 }, { "epoch": 0.57, "learning_rate": 3.620136289451326e-06, "loss": 3.6747, "step": 551500 }, { "epoch": 0.57, "learning_rate": 3.619791898054636e-06, "loss": 3.6739, "step": 552000 }, { "epoch": 0.57, "learning_rate": 3.6194475066579466e-06, "loss": 3.66, "step": 552500 }, { "epoch": 0.57, "learning_rate": 3.619103115261257e-06, "loss": 3.6762, "step": 553000 }, { "epoch": 0.57, "learning_rate": 3.6187587238645672e-06, "loss": 3.6763, "step": 553500 }, { "epoch": 0.57, "learning_rate": 3.6184143324678776e-06, "loss": 3.6737, "step": 554000 }, { "epoch": 0.57, "learning_rate": 3.6180699410711883e-06, "loss": 3.6682, "step": 554500 }, { "epoch": 0.57, "learning_rate": 3.617725549674498e-06, "loss": 3.6642, "step": 555000 }, { "epoch": 0.57, "learning_rate": 3.617381158277809e-06, "loss": 3.667, "step": 555500 }, { "epoch": 0.57, "learning_rate": 3.617036766881119e-06, "loss": 3.6659, "step": 556000 }, { "epoch": 0.57, "learning_rate": 3.616692375484429e-06, "loss": 3.6632, "step": 556500 }, { "epoch": 0.58, "learning_rate": 3.61634798408774e-06, "loss": 3.6744, "step": 557000 }, { "epoch": 0.58, "learning_rate": 3.61600359269105e-06, "loss": 3.6615, "step": 557500 }, { "epoch": 0.58, "learning_rate": 3.6156592012943606e-06, "loss": 3.6681, "step": 558000 }, { "epoch": 0.58, "learning_rate": 3.615314809897671e-06, "loss": 3.6731, "step": 558500 }, { "epoch": 0.58, "learning_rate": 3.614970418500981e-06, "loss": 3.6673, "step": 559000 }, { "epoch": 0.58, "learning_rate": 3.6146260271042915e-06, "loss": 3.6644, "step": 559500 }, { "epoch": 0.58, "learning_rate": 3.614281635707602e-06, "loss": 3.6648, "step": 560000 }, { "epoch": 0.58, "learning_rate": 3.613937244310912e-06, "loss": 3.6675, "step": 560500 }, { "epoch": 0.58, "learning_rate": 3.613592852914223e-06, "loss": 3.6642, "step": 561000 }, { "epoch": 0.58, "learning_rate": 3.613248461517533e-06, "loss": 3.6675, "step": 561500 }, { "epoch": 0.58, "learning_rate": 3.6129040701208435e-06, "loss": 3.6604, "step": 562000 }, { "epoch": 0.58, "learning_rate": 3.612559678724154e-06, "loss": 3.6656, "step": 562500 }, { "epoch": 0.58, "learning_rate": 3.6122152873274638e-06, "loss": 3.6624, "step": 563000 }, { "epoch": 0.58, "learning_rate": 3.6118708959307745e-06, "loss": 3.664, "step": 563500 }, { "epoch": 0.58, "learning_rate": 3.6115265045340844e-06, "loss": 3.6701, "step": 564000 }, { "epoch": 0.58, "learning_rate": 3.611182113137395e-06, "loss": 3.6516, "step": 564500 }, { "epoch": 0.58, "learning_rate": 3.6108377217407055e-06, "loss": 3.665, "step": 565000 }, { "epoch": 0.58, "learning_rate": 3.610493330344016e-06, "loss": 3.6652, "step": 565500 }, { "epoch": 0.58, "learning_rate": 3.610148938947326e-06, "loss": 3.6588, "step": 566000 }, { "epoch": 0.59, "learning_rate": 3.609804547550637e-06, "loss": 3.6735, "step": 566500 }, { "epoch": 0.59, "learning_rate": 3.6094601561539468e-06, "loss": 3.6649, "step": 567000 }, { "epoch": 0.59, "learning_rate": 3.6091157647572575e-06, "loss": 3.657, "step": 567500 }, { "epoch": 0.59, "learning_rate": 3.6087713733605674e-06, "loss": 3.6611, "step": 568000 }, { "epoch": 0.59, "learning_rate": 3.608426981963878e-06, "loss": 3.6493, "step": 568500 }, { "epoch": 0.59, "learning_rate": 3.6080825905671885e-06, "loss": 3.6597, "step": 569000 }, { "epoch": 0.59, "learning_rate": 3.607738199170499e-06, "loss": 3.6607, "step": 569500 }, { "epoch": 0.59, "learning_rate": 3.607393807773809e-06, "loss": 3.6551, "step": 570000 }, { "epoch": 0.59, "learning_rate": 3.6070494163771194e-06, "loss": 3.6682, "step": 570500 }, { "epoch": 0.59, "learning_rate": 3.6067050249804298e-06, "loss": 3.6588, "step": 571000 }, { "epoch": 0.59, "learning_rate": 3.60636063358374e-06, "loss": 3.6641, "step": 571500 }, { "epoch": 0.59, "learning_rate": 3.6060162421870504e-06, "loss": 3.6497, "step": 572000 }, { "epoch": 0.59, "learning_rate": 3.6056718507903607e-06, "loss": 3.6688, "step": 572500 }, { "epoch": 0.59, "learning_rate": 3.6053274593936715e-06, "loss": 3.6668, "step": 573000 }, { "epoch": 0.59, "learning_rate": 3.6049830679969814e-06, "loss": 3.6572, "step": 573500 }, { "epoch": 0.59, "learning_rate": 3.604638676600292e-06, "loss": 3.6561, "step": 574000 }, { "epoch": 0.59, "learning_rate": 3.6042942852036024e-06, "loss": 3.6604, "step": 574500 }, { "epoch": 0.59, "learning_rate": 3.6039498938069128e-06, "loss": 3.6545, "step": 575000 }, { "epoch": 0.59, "learning_rate": 3.603605502410223e-06, "loss": 3.6548, "step": 575500 }, { "epoch": 0.6, "learning_rate": 3.6032611110135334e-06, "loss": 3.6568, "step": 576000 }, { "epoch": 0.6, "learning_rate": 3.6029167196168437e-06, "loss": 3.6534, "step": 576500 }, { "epoch": 0.6, "learning_rate": 3.602572328220154e-06, "loss": 3.6524, "step": 577000 }, { "epoch": 0.6, "learning_rate": 3.6022279368234644e-06, "loss": 3.6527, "step": 577500 }, { "epoch": 0.6, "learning_rate": 3.6018835454267747e-06, "loss": 3.6586, "step": 578000 }, { "epoch": 0.6, "learning_rate": 3.6015391540300854e-06, "loss": 3.6566, "step": 578500 }, { "epoch": 0.6, "learning_rate": 3.6011947626333953e-06, "loss": 3.6537, "step": 579000 }, { "epoch": 0.6, "learning_rate": 3.600850371236706e-06, "loss": 3.6653, "step": 579500 }, { "epoch": 0.6, "learning_rate": 3.600505979840016e-06, "loss": 3.6537, "step": 580000 }, { "epoch": 0.6, "learning_rate": 3.6001615884433267e-06, "loss": 3.6563, "step": 580500 }, { "epoch": 0.6, "learning_rate": 3.599817197046637e-06, "loss": 3.6597, "step": 581000 }, { "epoch": 0.6, "learning_rate": 3.5994728056499474e-06, "loss": 3.6543, "step": 581500 }, { "epoch": 0.6, "learning_rate": 3.5991284142532577e-06, "loss": 3.6604, "step": 582000 }, { "epoch": 0.6, "learning_rate": 3.5987840228565684e-06, "loss": 3.6584, "step": 582500 }, { "epoch": 0.6, "learning_rate": 3.5984396314598783e-06, "loss": 3.6556, "step": 583000 }, { "epoch": 0.6, "learning_rate": 3.598095240063189e-06, "loss": 3.656, "step": 583500 }, { "epoch": 0.6, "learning_rate": 3.597750848666499e-06, "loss": 3.654, "step": 584000 }, { "epoch": 0.6, "learning_rate": 3.5974064572698093e-06, "loss": 3.6582, "step": 584500 }, { "epoch": 0.6, "learning_rate": 3.59706206587312e-06, "loss": 3.649, "step": 585000 }, { "epoch": 0.6, "learning_rate": 3.59671767447643e-06, "loss": 3.656, "step": 585500 }, { "epoch": 0.61, "learning_rate": 3.5963732830797407e-06, "loss": 3.6553, "step": 586000 }, { "epoch": 0.61, "learning_rate": 3.5960288916830506e-06, "loss": 3.6528, "step": 586500 }, { "epoch": 0.61, "learning_rate": 3.5956845002863613e-06, "loss": 3.6475, "step": 587000 }, { "epoch": 0.61, "learning_rate": 3.5953401088896717e-06, "loss": 3.649, "step": 587500 }, { "epoch": 0.61, "learning_rate": 3.594995717492982e-06, "loss": 3.6389, "step": 588000 }, { "epoch": 0.61, "learning_rate": 3.5946513260962923e-06, "loss": 3.6504, "step": 588500 }, { "epoch": 0.61, "learning_rate": 3.594306934699603e-06, "loss": 3.6564, "step": 589000 }, { "epoch": 0.61, "learning_rate": 3.593962543302913e-06, "loss": 3.6461, "step": 589500 }, { "epoch": 0.61, "learning_rate": 3.5936181519062237e-06, "loss": 3.6423, "step": 590000 }, { "epoch": 0.61, "learning_rate": 3.5932737605095336e-06, "loss": 3.6443, "step": 590500 }, { "epoch": 0.61, "learning_rate": 3.592929369112844e-06, "loss": 3.6496, "step": 591000 }, { "epoch": 0.61, "learning_rate": 3.5925849777161547e-06, "loss": 3.6501, "step": 591500 }, { "epoch": 0.61, "learning_rate": 3.5922405863194646e-06, "loss": 3.6412, "step": 592000 }, { "epoch": 0.61, "learning_rate": 3.5918961949227753e-06, "loss": 3.6439, "step": 592500 }, { "epoch": 0.61, "learning_rate": 3.5915518035260856e-06, "loss": 3.6531, "step": 593000 }, { "epoch": 0.61, "learning_rate": 3.591207412129396e-06, "loss": 3.6487, "step": 593500 }, { "epoch": 0.61, "learning_rate": 3.5908630207327063e-06, "loss": 3.6453, "step": 594000 }, { "epoch": 0.61, "learning_rate": 3.5905186293360166e-06, "loss": 3.6479, "step": 594500 }, { "epoch": 0.61, "learning_rate": 3.590174237939327e-06, "loss": 3.6492, "step": 595000 }, { "epoch": 0.62, "learning_rate": 3.5898298465426377e-06, "loss": 3.6464, "step": 595500 }, { "epoch": 0.62, "learning_rate": 3.5894854551459476e-06, "loss": 3.6462, "step": 596000 }, { "epoch": 0.62, "learning_rate": 3.5891410637492583e-06, "loss": 3.6428, "step": 596500 }, { "epoch": 0.62, "learning_rate": 3.5887966723525686e-06, "loss": 3.6395, "step": 597000 }, { "epoch": 0.62, "learning_rate": 3.588452280955879e-06, "loss": 3.6476, "step": 597500 }, { "epoch": 0.62, "learning_rate": 3.5881078895591893e-06, "loss": 3.6374, "step": 598000 }, { "epoch": 0.62, "learning_rate": 3.587763498162499e-06, "loss": 3.6331, "step": 598500 }, { "epoch": 0.62, "learning_rate": 3.58741910676581e-06, "loss": 3.6484, "step": 599000 }, { "epoch": 0.62, "learning_rate": 3.5870747153691202e-06, "loss": 3.6417, "step": 599500 }, { "epoch": 0.62, "learning_rate": 3.5867303239724306e-06, "loss": 3.6498, "step": 600000 }, { "epoch": 0.62, "learning_rate": 3.586385932575741e-06, "loss": 3.6447, "step": 600500 }, { "epoch": 0.62, "learning_rate": 3.5860415411790516e-06, "loss": 3.6446, "step": 601000 }, { "epoch": 0.62, "learning_rate": 3.5856971497823615e-06, "loss": 3.6409, "step": 601500 }, { "epoch": 0.62, "learning_rate": 3.5853527583856723e-06, "loss": 3.6457, "step": 602000 }, { "epoch": 0.62, "learning_rate": 3.585008366988982e-06, "loss": 3.6489, "step": 602500 }, { "epoch": 0.62, "learning_rate": 3.584663975592293e-06, "loss": 3.6427, "step": 603000 }, { "epoch": 0.62, "learning_rate": 3.5843195841956032e-06, "loss": 3.6388, "step": 603500 }, { "epoch": 0.62, "learning_rate": 3.5839751927989136e-06, "loss": 3.6323, "step": 604000 }, { "epoch": 0.62, "learning_rate": 3.583630801402224e-06, "loss": 3.6392, "step": 604500 }, { "epoch": 0.63, "learning_rate": 3.583286410005534e-06, "loss": 3.6421, "step": 605000 }, { "epoch": 0.63, "learning_rate": 3.5829420186088445e-06, "loss": 3.6344, "step": 605500 }, { "epoch": 0.63, "learning_rate": 3.582597627212155e-06, "loss": 3.6332, "step": 606000 }, { "epoch": 0.63, "learning_rate": 3.582253235815465e-06, "loss": 3.6387, "step": 606500 }, { "epoch": 0.63, "learning_rate": 3.5819088444187755e-06, "loss": 3.6404, "step": 607000 }, { "epoch": 0.63, "learning_rate": 3.5815644530220862e-06, "loss": 3.6407, "step": 607500 }, { "epoch": 0.63, "learning_rate": 3.581220061625396e-06, "loss": 3.6453, "step": 608000 }, { "epoch": 0.63, "learning_rate": 3.580875670228707e-06, "loss": 3.6428, "step": 608500 }, { "epoch": 0.63, "learning_rate": 3.580531278832017e-06, "loss": 3.6438, "step": 609000 }, { "epoch": 0.63, "learning_rate": 3.5801868874353275e-06, "loss": 3.6343, "step": 609500 }, { "epoch": 0.63, "learning_rate": 3.579842496038638e-06, "loss": 3.6431, "step": 610000 }, { "epoch": 0.63, "learning_rate": 3.579498104641948e-06, "loss": 3.6395, "step": 610500 }, { "epoch": 0.63, "learning_rate": 3.5791537132452585e-06, "loss": 3.6324, "step": 611000 }, { "epoch": 0.63, "learning_rate": 3.5788093218485692e-06, "loss": 3.6354, "step": 611500 }, { "epoch": 0.63, "learning_rate": 3.578464930451879e-06, "loss": 3.6265, "step": 612000 }, { "epoch": 0.63, "learning_rate": 3.5781205390551894e-06, "loss": 3.6413, "step": 612500 }, { "epoch": 0.63, "learning_rate": 3.5777761476585e-06, "loss": 3.6346, "step": 613000 }, { "epoch": 0.63, "learning_rate": 3.57743175626181e-06, "loss": 3.6373, "step": 613500 }, { "epoch": 0.63, "learning_rate": 3.577087364865121e-06, "loss": 3.6427, "step": 614000 }, { "epoch": 0.63, "learning_rate": 3.5767429734684307e-06, "loss": 3.6426, "step": 614500 }, { "epoch": 0.64, "learning_rate": 3.5763985820717415e-06, "loss": 3.6308, "step": 615000 }, { "epoch": 0.64, "learning_rate": 3.576054190675052e-06, "loss": 3.6404, "step": 615500 }, { "epoch": 0.64, "learning_rate": 3.575709799278362e-06, "loss": 3.638, "step": 616000 }, { "epoch": 0.64, "learning_rate": 3.5753654078816724e-06, "loss": 3.6329, "step": 616500 }, { "epoch": 0.64, "learning_rate": 3.575021016484983e-06, "loss": 3.6292, "step": 617000 }, { "epoch": 0.64, "learning_rate": 3.574676625088293e-06, "loss": 3.6373, "step": 617500 }, { "epoch": 0.64, "learning_rate": 3.574332233691604e-06, "loss": 3.6358, "step": 618000 }, { "epoch": 0.64, "learning_rate": 3.5739878422949137e-06, "loss": 3.6366, "step": 618500 }, { "epoch": 0.64, "learning_rate": 3.573643450898224e-06, "loss": 3.6307, "step": 619000 }, { "epoch": 0.64, "learning_rate": 3.573299059501535e-06, "loss": 3.6298, "step": 619500 }, { "epoch": 0.64, "learning_rate": 3.5729546681048447e-06, "loss": 3.6264, "step": 620000 }, { "epoch": 0.64, "learning_rate": 3.5726102767081554e-06, "loss": 3.6376, "step": 620500 }, { "epoch": 0.64, "learning_rate": 3.5722658853114653e-06, "loss": 3.6359, "step": 621000 }, { "epoch": 0.64, "learning_rate": 3.571921493914776e-06, "loss": 3.6325, "step": 621500 }, { "epoch": 0.64, "learning_rate": 3.5715771025180864e-06, "loss": 3.6316, "step": 622000 }, { "epoch": 0.64, "learning_rate": 3.5712327111213967e-06, "loss": 3.6283, "step": 622500 }, { "epoch": 0.64, "learning_rate": 3.570888319724707e-06, "loss": 3.6345, "step": 623000 }, { "epoch": 0.64, "learning_rate": 3.570543928328018e-06, "loss": 3.6272, "step": 623500 }, { "epoch": 0.64, "learning_rate": 3.5701995369313277e-06, "loss": 3.6302, "step": 624000 }, { "epoch": 0.65, "learning_rate": 3.5698551455346384e-06, "loss": 3.6315, "step": 624500 }, { "epoch": 0.65, "learning_rate": 3.5695107541379488e-06, "loss": 3.6293, "step": 625000 }, { "epoch": 0.65, "learning_rate": 3.5691663627412587e-06, "loss": 3.6278, "step": 625500 }, { "epoch": 0.65, "learning_rate": 3.5688219713445694e-06, "loss": 3.6255, "step": 626000 }, { "epoch": 0.65, "learning_rate": 3.5684775799478793e-06, "loss": 3.628, "step": 626500 }, { "epoch": 0.65, "learning_rate": 3.56813318855119e-06, "loss": 3.6343, "step": 627000 }, { "epoch": 0.65, "learning_rate": 3.5677887971545004e-06, "loss": 3.6274, "step": 627500 }, { "epoch": 0.65, "learning_rate": 3.5674444057578107e-06, "loss": 3.6369, "step": 628000 }, { "epoch": 0.65, "learning_rate": 3.567100014361121e-06, "loss": 3.6316, "step": 628500 }, { "epoch": 0.65, "learning_rate": 3.5667556229644318e-06, "loss": 3.6284, "step": 629000 }, { "epoch": 0.65, "learning_rate": 3.5664112315677417e-06, "loss": 3.6237, "step": 629500 }, { "epoch": 0.65, "learning_rate": 3.5660668401710524e-06, "loss": 3.6248, "step": 630000 }, { "epoch": 0.65, "learning_rate": 3.5657224487743623e-06, "loss": 3.6345, "step": 630500 }, { "epoch": 0.65, "learning_rate": 3.565378057377673e-06, "loss": 3.6306, "step": 631000 }, { "epoch": 0.65, "learning_rate": 3.5650336659809834e-06, "loss": 3.6179, "step": 631500 }, { "epoch": 0.65, "learning_rate": 3.5646892745842937e-06, "loss": 3.6251, "step": 632000 }, { "epoch": 0.65, "learning_rate": 3.564344883187604e-06, "loss": 3.6218, "step": 632500 }, { "epoch": 0.65, "learning_rate": 3.564000491790914e-06, "loss": 3.6238, "step": 633000 }, { "epoch": 0.65, "learning_rate": 3.5636561003942247e-06, "loss": 3.6275, "step": 633500 }, { "epoch": 0.66, "learning_rate": 3.563311708997535e-06, "loss": 3.6292, "step": 634000 }, { "epoch": 0.66, "learning_rate": 3.5629673176008453e-06, "loss": 3.6217, "step": 634500 }, { "epoch": 0.66, "learning_rate": 3.5626229262041556e-06, "loss": 3.6173, "step": 635000 }, { "epoch": 0.66, "learning_rate": 3.5622785348074664e-06, "loss": 3.6323, "step": 635500 }, { "epoch": 0.66, "learning_rate": 3.5619341434107763e-06, "loss": 3.6299, "step": 636000 }, { "epoch": 0.66, "learning_rate": 3.561589752014087e-06, "loss": 3.6294, "step": 636500 }, { "epoch": 0.66, "learning_rate": 3.561245360617397e-06, "loss": 3.6302, "step": 637000 }, { "epoch": 0.66, "learning_rate": 3.5609009692207077e-06, "loss": 3.6305, "step": 637500 }, { "epoch": 0.66, "learning_rate": 3.560556577824018e-06, "loss": 3.617, "step": 638000 }, { "epoch": 0.66, "learning_rate": 3.5602121864273283e-06, "loss": 3.6234, "step": 638500 }, { "epoch": 0.66, "learning_rate": 3.5598677950306386e-06, "loss": 3.621, "step": 639000 }, { "epoch": 0.66, "learning_rate": 3.559523403633949e-06, "loss": 3.6225, "step": 639500 }, { "epoch": 0.66, "learning_rate": 3.5591790122372593e-06, "loss": 3.62, "step": 640000 }, { "epoch": 0.66, "learning_rate": 3.5588346208405696e-06, "loss": 3.6306, "step": 640500 }, { "epoch": 0.66, "learning_rate": 3.55849022944388e-06, "loss": 3.6315, "step": 641000 }, { "epoch": 0.66, "learning_rate": 3.5581458380471902e-06, "loss": 3.6318, "step": 641500 }, { "epoch": 0.66, "learning_rate": 3.557801446650501e-06, "loss": 3.6213, "step": 642000 }, { "epoch": 0.66, "learning_rate": 3.557457055253811e-06, "loss": 3.6227, "step": 642500 }, { "epoch": 0.66, "learning_rate": 3.5571126638571216e-06, "loss": 3.6145, "step": 643000 }, { "epoch": 0.66, "learning_rate": 3.556768272460432e-06, "loss": 3.6253, "step": 643500 }, { "epoch": 0.67, "learning_rate": 3.5564238810637423e-06, "loss": 3.6319, "step": 644000 }, { "epoch": 0.67, "learning_rate": 3.5560794896670526e-06, "loss": 3.619, "step": 644500 }, { "epoch": 0.67, "learning_rate": 3.555735098270363e-06, "loss": 3.6169, "step": 645000 }, { "epoch": 0.67, "learning_rate": 3.5553907068736732e-06, "loss": 3.6171, "step": 645500 }, { "epoch": 0.67, "learning_rate": 3.555046315476984e-06, "loss": 3.6079, "step": 646000 }, { "epoch": 0.67, "learning_rate": 3.554701924080294e-06, "loss": 3.6158, "step": 646500 }, { "epoch": 0.67, "learning_rate": 3.554357532683604e-06, "loss": 3.6218, "step": 647000 }, { "epoch": 0.67, "learning_rate": 3.554013141286915e-06, "loss": 3.6292, "step": 647500 }, { "epoch": 0.67, "learning_rate": 3.553668749890225e-06, "loss": 3.6171, "step": 648000 }, { "epoch": 0.67, "learning_rate": 3.5533243584935356e-06, "loss": 3.6187, "step": 648500 }, { "epoch": 0.67, "learning_rate": 3.5529799670968455e-06, "loss": 3.6108, "step": 649000 }, { "epoch": 0.67, "learning_rate": 3.5526355757001562e-06, "loss": 3.6142, "step": 649500 }, { "epoch": 0.67, "learning_rate": 3.5522911843034666e-06, "loss": 3.6185, "step": 650000 }, { "epoch": 0.67, "learning_rate": 3.551946792906777e-06, "loss": 3.6127, "step": 650500 }, { "epoch": 0.67, "learning_rate": 3.551602401510087e-06, "loss": 3.6142, "step": 651000 }, { "epoch": 0.67, "learning_rate": 3.551258010113398e-06, "loss": 3.6169, "step": 651500 }, { "epoch": 0.67, "learning_rate": 3.550913618716708e-06, "loss": 3.6157, "step": 652000 }, { "epoch": 0.67, "learning_rate": 3.5505692273200186e-06, "loss": 3.6149, "step": 652500 }, { "epoch": 0.67, "learning_rate": 3.5502248359233285e-06, "loss": 3.6155, "step": 653000 }, { "epoch": 0.68, "learning_rate": 3.549880444526639e-06, "loss": 3.6093, "step": 653500 }, { "epoch": 0.68, "learning_rate": 3.5495360531299496e-06, "loss": 3.6184, "step": 654000 }, { "epoch": 0.68, "learning_rate": 3.5491916617332595e-06, "loss": 3.6203, "step": 654500 }, { "epoch": 0.68, "learning_rate": 3.54884727033657e-06, "loss": 3.6176, "step": 655000 }, { "epoch": 0.68, "learning_rate": 3.5485028789398805e-06, "loss": 3.6187, "step": 655500 }, { "epoch": 0.68, "learning_rate": 3.548158487543191e-06, "loss": 3.621, "step": 656000 }, { "epoch": 0.68, "learning_rate": 3.547814096146501e-06, "loss": 3.6096, "step": 656500 }, { "epoch": 0.68, "learning_rate": 3.5474697047498115e-06, "loss": 3.6142, "step": 657000 }, { "epoch": 0.68, "learning_rate": 3.547125313353122e-06, "loss": 3.6107, "step": 657500 }, { "epoch": 0.68, "learning_rate": 3.5467809219564326e-06, "loss": 3.614, "step": 658000 }, { "epoch": 0.68, "learning_rate": 3.5464365305597425e-06, "loss": 3.6113, "step": 658500 }, { "epoch": 0.68, "learning_rate": 3.546092139163053e-06, "loss": 3.6103, "step": 659000 }, { "epoch": 0.68, "learning_rate": 3.5457477477663635e-06, "loss": 3.6155, "step": 659500 }, { "epoch": 0.68, "learning_rate": 3.545403356369674e-06, "loss": 3.611, "step": 660000 }, { "epoch": 0.68, "learning_rate": 3.545058964972984e-06, "loss": 3.615, "step": 660500 }, { "epoch": 0.68, "learning_rate": 3.544714573576294e-06, "loss": 3.6108, "step": 661000 }, { "epoch": 0.68, "learning_rate": 3.544370182179605e-06, "loss": 3.6097, "step": 661500 }, { "epoch": 0.68, "learning_rate": 3.544025790782915e-06, "loss": 3.6119, "step": 662000 }, { "epoch": 0.68, "learning_rate": 3.5436813993862254e-06, "loss": 3.6113, "step": 662500 }, { "epoch": 0.68, "learning_rate": 3.5433370079895358e-06, "loss": 3.6117, "step": 663000 }, { "epoch": 0.69, "learning_rate": 3.5429926165928465e-06, "loss": 3.6083, "step": 663500 }, { "epoch": 0.69, "learning_rate": 3.5426482251961564e-06, "loss": 3.6062, "step": 664000 }, { "epoch": 0.69, "learning_rate": 3.542303833799467e-06, "loss": 3.6217, "step": 664500 }, { "epoch": 0.69, "learning_rate": 3.541959442402777e-06, "loss": 3.6083, "step": 665000 }, { "epoch": 0.69, "learning_rate": 3.541615051006088e-06, "loss": 3.6138, "step": 665500 }, { "epoch": 0.69, "learning_rate": 3.541270659609398e-06, "loss": 3.612, "step": 666000 }, { "epoch": 0.69, "learning_rate": 3.5409262682127084e-06, "loss": 3.6086, "step": 666500 }, { "epoch": 0.69, "learning_rate": 3.5405818768160188e-06, "loss": 3.6151, "step": 667000 }, { "epoch": 0.69, "learning_rate": 3.5402374854193287e-06, "loss": 3.6127, "step": 667500 }, { "epoch": 0.69, "learning_rate": 3.5398930940226394e-06, "loss": 3.6078, "step": 668000 }, { "epoch": 0.69, "learning_rate": 3.5395487026259497e-06, "loss": 3.6118, "step": 668500 }, { "epoch": 0.69, "learning_rate": 3.53920431122926e-06, "loss": 3.6162, "step": 669000 }, { "epoch": 0.69, "learning_rate": 3.5388599198325704e-06, "loss": 3.6118, "step": 669500 }, { "epoch": 0.69, "learning_rate": 3.538515528435881e-06, "loss": 3.6149, "step": 670000 }, { "epoch": 0.69, "learning_rate": 3.538171137039191e-06, "loss": 3.6184, "step": 670500 }, { "epoch": 0.69, "learning_rate": 3.5378267456425018e-06, "loss": 3.6108, "step": 671000 }, { "epoch": 0.69, "learning_rate": 3.5374823542458117e-06, "loss": 3.6079, "step": 671500 }, { "epoch": 0.69, "learning_rate": 3.5371379628491224e-06, "loss": 3.5999, "step": 672000 }, { "epoch": 0.69, "learning_rate": 3.5367935714524327e-06, "loss": 3.6157, "step": 672500 }, { "epoch": 0.7, "learning_rate": 3.536449180055743e-06, "loss": 3.6157, "step": 673000 }, { "epoch": 0.7, "learning_rate": 3.5361047886590534e-06, "loss": 3.6114, "step": 673500 }, { "epoch": 0.7, "learning_rate": 3.535760397262364e-06, "loss": 3.6103, "step": 674000 }, { "epoch": 0.7, "learning_rate": 3.535416005865674e-06, "loss": 3.6111, "step": 674500 }, { "epoch": 0.7, "learning_rate": 3.5350716144689843e-06, "loss": 3.607, "step": 675000 }, { "epoch": 0.7, "learning_rate": 3.5347272230722947e-06, "loss": 3.6053, "step": 675500 }, { "epoch": 0.7, "learning_rate": 3.534382831675605e-06, "loss": 3.6125, "step": 676000 }, { "epoch": 0.7, "learning_rate": 3.5340384402789157e-06, "loss": 3.5983, "step": 676500 }, { "epoch": 0.7, "learning_rate": 3.5336940488822256e-06, "loss": 3.6086, "step": 677000 }, { "epoch": 0.7, "learning_rate": 3.5333496574855364e-06, "loss": 3.6007, "step": 677500 }, { "epoch": 0.7, "learning_rate": 3.5330052660888467e-06, "loss": 3.5939, "step": 678000 }, { "epoch": 0.7, "learning_rate": 3.532660874692157e-06, "loss": 3.6112, "step": 678500 }, { "epoch": 0.7, "learning_rate": 3.5323164832954673e-06, "loss": 3.6027, "step": 679000 }, { "epoch": 0.7, "learning_rate": 3.5319720918987777e-06, "loss": 3.6115, "step": 679500 }, { "epoch": 0.7, "learning_rate": 3.531627700502088e-06, "loss": 3.6123, "step": 680000 }, { "epoch": 0.7, "learning_rate": 3.5312833091053987e-06, "loss": 3.6055, "step": 680500 }, { "epoch": 0.7, "learning_rate": 3.5309389177087086e-06, "loss": 3.5997, "step": 681000 }, { "epoch": 0.7, "learning_rate": 3.530594526312019e-06, "loss": 3.6062, "step": 681500 }, { "epoch": 0.7, "learning_rate": 3.5302501349153297e-06, "loss": 3.6031, "step": 682000 }, { "epoch": 0.71, "learning_rate": 3.5299057435186396e-06, "loss": 3.6054, "step": 682500 }, { "epoch": 0.71, "learning_rate": 3.5295613521219503e-06, "loss": 3.6069, "step": 683000 }, { "epoch": 0.71, "learning_rate": 3.5292169607252602e-06, "loss": 3.5979, "step": 683500 }, { "epoch": 0.71, "learning_rate": 3.528872569328571e-06, "loss": 3.6029, "step": 684000 }, { "epoch": 0.71, "learning_rate": 3.5285281779318813e-06, "loss": 3.5954, "step": 684500 }, { "epoch": 0.71, "learning_rate": 3.5281837865351916e-06, "loss": 3.6039, "step": 685000 }, { "epoch": 1.42, "learning_rate": 3.055679765924297e-06, "loss": 3.5816, "step": 685500 }, { "epoch": 1.42, "learning_rate": 3.0549909838425496e-06, "loss": 3.5817, "step": 686000 }, { "epoch": 1.42, "learning_rate": 3.0543022017608024e-06, "loss": 3.5709, "step": 686500 }, { "epoch": 1.42, "learning_rate": 3.053613419679055e-06, "loss": 3.5712, "step": 687000 }, { "epoch": 1.42, "learning_rate": 3.0529246375973077e-06, "loss": 3.5701, "step": 687500 }, { "epoch": 1.42, "learning_rate": 3.05223585551556e-06, "loss": 3.5709, "step": 688000 }, { "epoch": 1.42, "learning_rate": 3.051547073433813e-06, "loss": 3.5688, "step": 688500 }, { "epoch": 1.42, "learning_rate": 3.0508582913520653e-06, "loss": 3.5633, "step": 689000 }, { "epoch": 1.42, "learning_rate": 3.0501695092703177e-06, "loss": 3.5676, "step": 689500 }, { "epoch": 1.43, "learning_rate": 3.0494807271885706e-06, "loss": 3.5635, "step": 690000 }, { "epoch": 1.43, "learning_rate": 3.048791945106823e-06, "loss": 3.5682, "step": 690500 }, { "epoch": 1.43, "learning_rate": 3.048103163025076e-06, "loss": 3.5701, "step": 691000 }, { "epoch": 1.43, "learning_rate": 3.047414380943328e-06, "loss": 3.5648, "step": 691500 }, { "epoch": 1.43, "learning_rate": 3.046725598861581e-06, "loss": 3.5613, "step": 692000 }, { "epoch": 1.43, "learning_rate": 3.0460368167798335e-06, "loss": 3.5656, "step": 692500 }, { "epoch": 1.43, "learning_rate": 3.0453480346980863e-06, "loss": 3.5661, "step": 693000 }, { "epoch": 1.43, "learning_rate": 3.0446592526163387e-06, "loss": 3.5662, "step": 693500 }, { "epoch": 1.43, "learning_rate": 3.043970470534591e-06, "loss": 3.5624, "step": 694000 }, { "epoch": 1.44, "learning_rate": 3.043281688452844e-06, "loss": 3.5646, "step": 694500 }, { "epoch": 1.44, "learning_rate": 3.0425929063710963e-06, "loss": 3.5624, "step": 695000 }, { "epoch": 1.44, "learning_rate": 3.041904124289349e-06, "loss": 3.5663, "step": 695500 }, { "epoch": 1.44, "learning_rate": 3.0412153422076016e-06, "loss": 3.5668, "step": 696000 }, { "epoch": 1.44, "learning_rate": 3.0405265601258544e-06, "loss": 3.5559, "step": 696500 }, { "epoch": 1.44, "learning_rate": 3.039837778044107e-06, "loss": 3.5612, "step": 697000 }, { "epoch": 1.44, "learning_rate": 3.0391489959623597e-06, "loss": 3.5583, "step": 697500 }, { "epoch": 1.44, "learning_rate": 3.038460213880612e-06, "loss": 3.5603, "step": 698000 }, { "epoch": 1.44, "learning_rate": 3.0377714317988645e-06, "loss": 3.5576, "step": 698500 }, { "epoch": 1.44, "learning_rate": 3.0370826497171173e-06, "loss": 3.5591, "step": 699000 }, { "epoch": 1.45, "learning_rate": 3.0363938676353697e-06, "loss": 3.5575, "step": 699500 }, { "epoch": 1.45, "learning_rate": 3.0357050855536226e-06, "loss": 3.5558, "step": 700000 }, { "epoch": 1.45, "learning_rate": 3.035016303471875e-06, "loss": 3.5598, "step": 700500 }, { "epoch": 1.45, "learning_rate": 3.034327521390128e-06, "loss": 3.5579, "step": 701000 }, { "epoch": 1.45, "learning_rate": 3.03363873930838e-06, "loss": 3.5608, "step": 701500 }, { "epoch": 1.45, "learning_rate": 3.032949957226632e-06, "loss": 3.5573, "step": 702000 }, { "epoch": 1.45, "learning_rate": 3.032261175144885e-06, "loss": 3.5621, "step": 702500 }, { "epoch": 1.45, "learning_rate": 3.0315723930631374e-06, "loss": 3.5551, "step": 703000 }, { "epoch": 1.45, "learning_rate": 3.0308836109813903e-06, "loss": 3.5552, "step": 703500 }, { "epoch": 1.45, "learning_rate": 3.0301948288996427e-06, "loss": 3.557, "step": 704000 }, { "epoch": 1.46, "learning_rate": 3.0295060468178955e-06, "loss": 3.5583, "step": 704500 }, { "epoch": 1.46, "learning_rate": 3.028817264736148e-06, "loss": 3.5488, "step": 705000 }, { "epoch": 1.46, "learning_rate": 3.0281284826544008e-06, "loss": 3.5551, "step": 705500 }, { "epoch": 1.46, "learning_rate": 3.027439700572653e-06, "loss": 3.5538, "step": 706000 }, { "epoch": 1.46, "learning_rate": 3.0267509184909056e-06, "loss": 3.5576, "step": 706500 }, { "epoch": 1.46, "learning_rate": 3.0260621364091584e-06, "loss": 3.5568, "step": 707000 }, { "epoch": 1.46, "learning_rate": 3.025373354327411e-06, "loss": 3.5529, "step": 707500 }, { "epoch": 1.46, "learning_rate": 3.0246845722456637e-06, "loss": 3.5507, "step": 708000 }, { "epoch": 1.46, "learning_rate": 3.023995790163916e-06, "loss": 3.553, "step": 708500 }, { "epoch": 1.47, "learning_rate": 3.023307008082169e-06, "loss": 3.5549, "step": 709000 }, { "epoch": 1.47, "learning_rate": 3.0226182260004213e-06, "loss": 3.5543, "step": 709500 }, { "epoch": 1.47, "learning_rate": 3.0219294439186737e-06, "loss": 3.5525, "step": 710000 }, { "epoch": 1.47, "learning_rate": 3.0212406618369266e-06, "loss": 3.5548, "step": 710500 }, { "epoch": 1.47, "learning_rate": 3.020551879755179e-06, "loss": 3.5565, "step": 711000 }, { "epoch": 1.47, "learning_rate": 3.019863097673432e-06, "loss": 3.5516, "step": 711500 }, { "epoch": 1.47, "learning_rate": 3.019174315591684e-06, "loss": 3.5517, "step": 712000 }, { "epoch": 1.47, "learning_rate": 3.018485533509937e-06, "loss": 3.5483, "step": 712500 }, { "epoch": 1.47, "learning_rate": 3.0177967514281895e-06, "loss": 3.5541, "step": 713000 }, { "epoch": 1.47, "learning_rate": 3.0171079693464423e-06, "loss": 3.5474, "step": 713500 }, { "epoch": 1.48, "learning_rate": 3.0164191872646947e-06, "loss": 3.5513, "step": 714000 }, { "epoch": 1.48, "learning_rate": 3.015730405182947e-06, "loss": 3.5536, "step": 714500 }, { "epoch": 1.48, "learning_rate": 3.0150416231012e-06, "loss": 3.5505, "step": 715000 }, { "epoch": 1.48, "learning_rate": 3.0143528410194523e-06, "loss": 3.5502, "step": 715500 }, { "epoch": 1.48, "learning_rate": 3.013664058937705e-06, "loss": 3.5427, "step": 716000 }, { "epoch": 1.48, "learning_rate": 3.0129752768559576e-06, "loss": 3.5471, "step": 716500 }, { "epoch": 1.48, "learning_rate": 3.0122864947742104e-06, "loss": 3.5479, "step": 717000 }, { "epoch": 1.48, "learning_rate": 3.011597712692463e-06, "loss": 3.5503, "step": 717500 }, { "epoch": 1.48, "learning_rate": 3.0109089306107157e-06, "loss": 3.5476, "step": 718000 }, { "epoch": 1.48, "learning_rate": 3.010220148528968e-06, "loss": 3.5415, "step": 718500 }, { "epoch": 1.49, "learning_rate": 3.0095313664472205e-06, "loss": 3.5487, "step": 719000 }, { "epoch": 1.49, "learning_rate": 3.0088425843654733e-06, "loss": 3.546, "step": 719500 }, { "epoch": 1.49, "learning_rate": 3.0081538022837257e-06, "loss": 3.5423, "step": 720000 }, { "epoch": 1.49, "learning_rate": 3.0074650202019786e-06, "loss": 3.5366, "step": 720500 }, { "epoch": 1.49, "learning_rate": 3.006776238120231e-06, "loss": 3.5458, "step": 721000 }, { "epoch": 1.49, "learning_rate": 3.006087456038484e-06, "loss": 3.5452, "step": 721500 }, { "epoch": 1.49, "learning_rate": 3.0053986739567362e-06, "loss": 3.5438, "step": 722000 }, { "epoch": 1.49, "learning_rate": 3.0047098918749886e-06, "loss": 3.5399, "step": 722500 }, { "epoch": 1.49, "learning_rate": 3.0040211097932415e-06, "loss": 3.5486, "step": 723000 }, { "epoch": 1.5, "learning_rate": 3.003332327711494e-06, "loss": 3.5447, "step": 723500 }, { "epoch": 1.5, "learning_rate": 3.0026435456297467e-06, "loss": 3.5421, "step": 724000 }, { "epoch": 1.5, "learning_rate": 3.001954763547999e-06, "loss": 3.5502, "step": 724500 }, { "epoch": 1.5, "learning_rate": 3.001265981466252e-06, "loss": 3.5462, "step": 725000 }, { "epoch": 1.5, "learning_rate": 3.0005771993845044e-06, "loss": 3.54, "step": 725500 }, { "epoch": 1.5, "learning_rate": 2.999888417302757e-06, "loss": 3.5416, "step": 726000 }, { "epoch": 1.5, "learning_rate": 2.999199635221009e-06, "loss": 3.5426, "step": 726500 }, { "epoch": 1.5, "learning_rate": 2.9985108531392616e-06, "loss": 3.5374, "step": 727000 }, { "epoch": 1.5, "learning_rate": 2.9978220710575144e-06, "loss": 3.5446, "step": 727500 }, { "epoch": 1.5, "learning_rate": 2.997133288975767e-06, "loss": 3.5378, "step": 728000 }, { "epoch": 1.51, "learning_rate": 2.9964445068940197e-06, "loss": 3.5415, "step": 728500 }, { "epoch": 1.51, "learning_rate": 2.995755724812272e-06, "loss": 3.5419, "step": 729000 }, { "epoch": 1.51, "learning_rate": 2.995066942730525e-06, "loss": 3.5473, "step": 729500 }, { "epoch": 1.51, "learning_rate": 2.9943781606487773e-06, "loss": 3.5433, "step": 730000 }, { "epoch": 1.51, "learning_rate": 2.9936893785670297e-06, "loss": 3.542, "step": 730500 }, { "epoch": 1.51, "learning_rate": 2.9930005964852826e-06, "loss": 3.5381, "step": 731000 }, { "epoch": 1.51, "learning_rate": 2.992311814403535e-06, "loss": 3.537, "step": 731500 }, { "epoch": 1.51, "learning_rate": 2.991623032321788e-06, "loss": 3.5406, "step": 732000 }, { "epoch": 1.51, "learning_rate": 2.99093425024004e-06, "loss": 3.5383, "step": 732500 }, { "epoch": 1.51, "learning_rate": 2.990245468158293e-06, "loss": 3.5422, "step": 733000 }, { "epoch": 1.52, "learning_rate": 2.9895566860765455e-06, "loss": 3.5373, "step": 733500 }, { "epoch": 1.52, "learning_rate": 2.9888679039947983e-06, "loss": 3.5372, "step": 734000 }, { "epoch": 1.52, "learning_rate": 2.9881791219130507e-06, "loss": 3.537, "step": 734500 }, { "epoch": 1.52, "learning_rate": 2.987490339831303e-06, "loss": 3.5371, "step": 735000 }, { "epoch": 1.52, "learning_rate": 2.986801557749556e-06, "loss": 3.5329, "step": 735500 }, { "epoch": 1.52, "learning_rate": 2.9861127756678083e-06, "loss": 3.536, "step": 736000 }, { "epoch": 1.52, "learning_rate": 2.985423993586061e-06, "loss": 3.5347, "step": 736500 }, { "epoch": 1.52, "learning_rate": 2.9847352115043136e-06, "loss": 3.5384, "step": 737000 }, { "epoch": 1.52, "learning_rate": 2.9840464294225664e-06, "loss": 3.5393, "step": 737500 }, { "epoch": 1.52, "learning_rate": 2.983357647340819e-06, "loss": 3.532, "step": 738000 }, { "epoch": 1.53, "learning_rate": 2.9826688652590717e-06, "loss": 3.5312, "step": 738500 }, { "epoch": 1.53, "learning_rate": 2.981980083177324e-06, "loss": 3.5318, "step": 739000 }, { "epoch": 1.53, "learning_rate": 2.9812913010955765e-06, "loss": 3.5321, "step": 739500 }, { "epoch": 1.53, "learning_rate": 2.9806025190138293e-06, "loss": 3.5332, "step": 740000 }, { "epoch": 1.53, "learning_rate": 2.9799137369320817e-06, "loss": 3.5327, "step": 740500 }, { "epoch": 1.53, "learning_rate": 2.9792249548503346e-06, "loss": 3.5393, "step": 741000 }, { "epoch": 1.53, "learning_rate": 2.978536172768587e-06, "loss": 3.5343, "step": 741500 }, { "epoch": 1.53, "learning_rate": 2.97784739068684e-06, "loss": 3.545, "step": 742000 }, { "epoch": 1.53, "learning_rate": 2.9771586086050922e-06, "loss": 3.5376, "step": 742500 }, { "epoch": 1.54, "learning_rate": 2.9764698265233446e-06, "loss": 3.535, "step": 743000 }, { "epoch": 1.54, "learning_rate": 2.9757810444415975e-06, "loss": 3.5335, "step": 743500 }, { "epoch": 1.54, "learning_rate": 2.97509226235985e-06, "loss": 3.532, "step": 744000 }, { "epoch": 1.54, "learning_rate": 2.9744034802781027e-06, "loss": 3.5298, "step": 744500 }, { "epoch": 1.54, "learning_rate": 2.973714698196355e-06, "loss": 3.5354, "step": 745000 }, { "epoch": 1.54, "learning_rate": 2.973025916114608e-06, "loss": 3.5302, "step": 745500 }, { "epoch": 1.54, "learning_rate": 2.9723371340328604e-06, "loss": 3.5329, "step": 746000 }, { "epoch": 1.54, "learning_rate": 2.971648351951113e-06, "loss": 3.5334, "step": 746500 }, { "epoch": 1.54, "learning_rate": 2.9709595698693656e-06, "loss": 3.5313, "step": 747000 }, { "epoch": 1.54, "learning_rate": 2.970270787787618e-06, "loss": 3.5284, "step": 747500 }, { "epoch": 1.55, "learning_rate": 2.969582005705871e-06, "loss": 3.5273, "step": 748000 }, { "epoch": 1.55, "learning_rate": 2.9688932236241233e-06, "loss": 3.5355, "step": 748500 }, { "epoch": 1.55, "learning_rate": 2.968204441542376e-06, "loss": 3.5276, "step": 749000 }, { "epoch": 1.55, "learning_rate": 2.9675156594606285e-06, "loss": 3.5297, "step": 749500 }, { "epoch": 1.55, "learning_rate": 2.9668268773788813e-06, "loss": 3.5324, "step": 750000 }, { "epoch": 1.55, "learning_rate": 2.9661380952971337e-06, "loss": 3.5316, "step": 750500 }, { "epoch": 1.55, "learning_rate": 2.965449313215386e-06, "loss": 3.5296, "step": 751000 }, { "epoch": 1.55, "learning_rate": 2.964760531133639e-06, "loss": 3.529, "step": 751500 }, { "epoch": 1.55, "learning_rate": 2.964071749051891e-06, "loss": 3.5355, "step": 752000 }, { "epoch": 1.55, "learning_rate": 2.963382966970144e-06, "loss": 3.5253, "step": 752500 }, { "epoch": 1.56, "learning_rate": 2.9626941848883962e-06, "loss": 3.5301, "step": 753000 }, { "epoch": 1.56, "learning_rate": 2.962005402806649e-06, "loss": 3.5272, "step": 753500 }, { "epoch": 1.56, "learning_rate": 2.9613166207249015e-06, "loss": 3.5277, "step": 754000 }, { "epoch": 1.56, "learning_rate": 2.9606278386431543e-06, "loss": 3.5201, "step": 754500 }, { "epoch": 1.56, "learning_rate": 2.9599390565614067e-06, "loss": 3.5266, "step": 755000 }, { "epoch": 1.56, "learning_rate": 2.959250274479659e-06, "loss": 3.521, "step": 755500 }, { "epoch": 1.56, "learning_rate": 2.958561492397912e-06, "loss": 3.5284, "step": 756000 }, { "epoch": 1.56, "learning_rate": 2.9578727103161644e-06, "loss": 3.5273, "step": 756500 }, { "epoch": 1.56, "learning_rate": 2.957183928234417e-06, "loss": 3.5306, "step": 757000 }, { "epoch": 1.57, "learning_rate": 2.9564951461526696e-06, "loss": 3.5251, "step": 757500 }, { "epoch": 1.57, "learning_rate": 2.9558063640709224e-06, "loss": 3.525, "step": 758000 }, { "epoch": 1.57, "learning_rate": 2.955117581989175e-06, "loss": 3.5272, "step": 758500 }, { "epoch": 1.57, "learning_rate": 2.9544287999074277e-06, "loss": 3.5204, "step": 759000 }, { "epoch": 1.57, "learning_rate": 2.95374001782568e-06, "loss": 3.5244, "step": 759500 }, { "epoch": 1.57, "learning_rate": 2.9530512357439325e-06, "loss": 3.5256, "step": 760000 }, { "epoch": 1.57, "learning_rate": 2.9523624536621853e-06, "loss": 3.5261, "step": 760500 }, { "epoch": 1.57, "learning_rate": 2.9516736715804377e-06, "loss": 3.5203, "step": 761000 }, { "epoch": 1.57, "learning_rate": 2.9509848894986906e-06, "loss": 3.5254, "step": 761500 }, { "epoch": 1.57, "learning_rate": 2.950296107416943e-06, "loss": 3.5293, "step": 762000 }, { "epoch": 1.58, "learning_rate": 2.949607325335196e-06, "loss": 3.5235, "step": 762500 }, { "epoch": 1.58, "learning_rate": 2.9489185432534482e-06, "loss": 3.5241, "step": 763000 }, { "epoch": 1.58, "learning_rate": 2.9482297611717006e-06, "loss": 3.5192, "step": 763500 }, { "epoch": 1.58, "learning_rate": 2.9475409790899535e-06, "loss": 3.5265, "step": 764000 }, { "epoch": 1.58, "learning_rate": 2.946852197008206e-06, "loss": 3.5225, "step": 764500 }, { "epoch": 1.58, "learning_rate": 2.9461634149264587e-06, "loss": 3.5229, "step": 765000 }, { "epoch": 1.58, "learning_rate": 2.945474632844711e-06, "loss": 3.5208, "step": 765500 }, { "epoch": 1.58, "learning_rate": 2.944785850762964e-06, "loss": 3.5239, "step": 766000 }, { "epoch": 1.58, "learning_rate": 2.9440970686812164e-06, "loss": 3.5183, "step": 766500 }, { "epoch": 1.58, "learning_rate": 2.943408286599469e-06, "loss": 3.5205, "step": 767000 }, { "epoch": 1.59, "learning_rate": 2.9427195045177216e-06, "loss": 3.5203, "step": 767500 }, { "epoch": 1.59, "learning_rate": 2.942030722435974e-06, "loss": 3.5229, "step": 768000 }, { "epoch": 1.59, "learning_rate": 2.941341940354227e-06, "loss": 3.5233, "step": 768500 }, { "epoch": 1.59, "learning_rate": 2.9406531582724793e-06, "loss": 3.5213, "step": 769000 }, { "epoch": 1.59, "learning_rate": 2.939964376190732e-06, "loss": 3.5196, "step": 769500 }, { "epoch": 1.59, "learning_rate": 2.9392755941089845e-06, "loss": 3.5233, "step": 770000 }, { "epoch": 1.59, "learning_rate": 2.9385868120272373e-06, "loss": 3.5162, "step": 770500 }, { "epoch": 1.59, "learning_rate": 2.9378980299454897e-06, "loss": 3.5207, "step": 771000 }, { "epoch": 1.59, "learning_rate": 2.937209247863742e-06, "loss": 3.5211, "step": 771500 }, { "epoch": 1.6, "learning_rate": 2.936520465781995e-06, "loss": 3.5181, "step": 772000 }, { "epoch": 1.6, "learning_rate": 2.9358316837002474e-06, "loss": 3.5194, "step": 772500 }, { "epoch": 1.6, "learning_rate": 2.9351429016185002e-06, "loss": 3.5197, "step": 773000 }, { "epoch": 1.6, "learning_rate": 2.9344541195367526e-06, "loss": 3.5147, "step": 773500 }, { "epoch": 1.6, "learning_rate": 2.9337653374550055e-06, "loss": 3.5161, "step": 774000 }, { "epoch": 1.6, "learning_rate": 2.933076555373258e-06, "loss": 3.5194, "step": 774500 }, { "epoch": 1.6, "learning_rate": 2.9323877732915107e-06, "loss": 3.5184, "step": 775000 }, { "epoch": 1.6, "learning_rate": 2.931698991209763e-06, "loss": 3.5206, "step": 775500 }, { "epoch": 1.6, "learning_rate": 2.9310102091280155e-06, "loss": 3.5159, "step": 776000 }, { "epoch": 1.6, "learning_rate": 2.9303214270462684e-06, "loss": 3.5146, "step": 776500 }, { "epoch": 1.61, "learning_rate": 2.9296326449645204e-06, "loss": 3.5153, "step": 777000 }, { "epoch": 1.61, "learning_rate": 2.928943862882773e-06, "loss": 3.5174, "step": 777500 }, { "epoch": 1.61, "learning_rate": 2.9282550808010256e-06, "loss": 3.5144, "step": 778000 }, { "epoch": 1.61, "learning_rate": 2.9275662987192784e-06, "loss": 3.5172, "step": 778500 }, { "epoch": 1.61, "learning_rate": 2.926877516637531e-06, "loss": 3.5178, "step": 779000 }, { "epoch": 1.61, "learning_rate": 2.9261887345557837e-06, "loss": 3.5137, "step": 779500 }, { "epoch": 1.61, "learning_rate": 2.925499952474036e-06, "loss": 3.5196, "step": 780000 }, { "epoch": 1.61, "learning_rate": 2.9248111703922885e-06, "loss": 3.5146, "step": 780500 }, { "epoch": 1.61, "learning_rate": 2.9241223883105413e-06, "loss": 3.5148, "step": 781000 }, { "epoch": 1.61, "learning_rate": 2.9234336062287937e-06, "loss": 3.5177, "step": 781500 }, { "epoch": 1.62, "learning_rate": 2.9227448241470466e-06, "loss": 3.5117, "step": 782000 }, { "epoch": 1.62, "learning_rate": 2.922056042065299e-06, "loss": 3.5154, "step": 782500 }, { "epoch": 1.62, "learning_rate": 2.921367259983552e-06, "loss": 3.5185, "step": 783000 }, { "epoch": 1.62, "learning_rate": 2.9206784779018042e-06, "loss": 3.5044, "step": 783500 }, { "epoch": 1.62, "learning_rate": 2.9199896958200566e-06, "loss": 3.5136, "step": 784000 }, { "epoch": 1.62, "learning_rate": 2.9193009137383095e-06, "loss": 3.5095, "step": 784500 }, { "epoch": 1.62, "learning_rate": 2.918612131656562e-06, "loss": 3.5175, "step": 785000 }, { "epoch": 1.62, "learning_rate": 2.9179233495748147e-06, "loss": 3.5074, "step": 785500 }, { "epoch": 1.62, "learning_rate": 2.917234567493067e-06, "loss": 3.5117, "step": 786000 }, { "epoch": 1.63, "learning_rate": 2.91654578541132e-06, "loss": 3.5096, "step": 786500 }, { "epoch": 1.63, "learning_rate": 2.9158570033295724e-06, "loss": 3.5124, "step": 787000 }, { "epoch": 1.63, "learning_rate": 2.915168221247825e-06, "loss": 3.5174, "step": 787500 }, { "epoch": 1.63, "learning_rate": 2.9144794391660776e-06, "loss": 3.5144, "step": 788000 }, { "epoch": 1.63, "learning_rate": 2.91379065708433e-06, "loss": 3.5146, "step": 788500 }, { "epoch": 1.63, "learning_rate": 2.913101875002583e-06, "loss": 3.5074, "step": 789000 }, { "epoch": 1.63, "learning_rate": 2.9124130929208353e-06, "loss": 3.513, "step": 789500 }, { "epoch": 1.63, "learning_rate": 2.911724310839088e-06, "loss": 3.5165, "step": 790000 }, { "epoch": 1.63, "learning_rate": 2.9110355287573405e-06, "loss": 3.5088, "step": 790500 }, { "epoch": 1.63, "learning_rate": 2.9103467466755933e-06, "loss": 3.5155, "step": 791000 }, { "epoch": 1.64, "learning_rate": 2.9096579645938457e-06, "loss": 3.5134, "step": 791500 }, { "epoch": 1.64, "learning_rate": 2.908969182512098e-06, "loss": 3.5022, "step": 792000 }, { "epoch": 1.64, "learning_rate": 2.908280400430351e-06, "loss": 3.5059, "step": 792500 }, { "epoch": 1.64, "learning_rate": 2.9075916183486034e-06, "loss": 3.5165, "step": 793000 }, { "epoch": 1.64, "learning_rate": 2.9069028362668562e-06, "loss": 3.5104, "step": 793500 }, { "epoch": 1.64, "learning_rate": 2.9062140541851086e-06, "loss": 3.5135, "step": 794000 }, { "epoch": 1.64, "learning_rate": 2.9055252721033615e-06, "loss": 3.5153, "step": 794500 }, { "epoch": 1.64, "learning_rate": 2.904836490021614e-06, "loss": 3.5072, "step": 795000 }, { "epoch": 1.64, "learning_rate": 2.9041477079398667e-06, "loss": 3.5069, "step": 795500 }, { "epoch": 1.64, "learning_rate": 2.903458925858119e-06, "loss": 3.5061, "step": 796000 }, { "epoch": 1.65, "learning_rate": 2.9027701437763715e-06, "loss": 3.5105, "step": 796500 }, { "epoch": 1.65, "learning_rate": 2.9020813616946244e-06, "loss": 3.5094, "step": 797000 }, { "epoch": 1.65, "learning_rate": 2.9013925796128768e-06, "loss": 3.5078, "step": 797500 }, { "epoch": 1.65, "learning_rate": 2.9007037975311296e-06, "loss": 3.5018, "step": 798000 }, { "epoch": 1.65, "learning_rate": 2.900015015449382e-06, "loss": 3.512, "step": 798500 }, { "epoch": 1.65, "learning_rate": 2.899326233367635e-06, "loss": 3.5109, "step": 799000 }, { "epoch": 1.65, "learning_rate": 2.8986374512858873e-06, "loss": 3.5058, "step": 799500 }, { "epoch": 1.65, "learning_rate": 2.89794866920414e-06, "loss": 3.5136, "step": 800000 }, { "epoch": 1.65, "learning_rate": 2.8972598871223925e-06, "loss": 3.5047, "step": 800500 }, { "epoch": 1.66, "learning_rate": 2.896571105040645e-06, "loss": 3.5022, "step": 801000 }, { "epoch": 1.66, "learning_rate": 2.8958823229588978e-06, "loss": 3.5035, "step": 801500 }, { "epoch": 1.66, "learning_rate": 2.89519354087715e-06, "loss": 3.505, "step": 802000 }, { "epoch": 1.66, "learning_rate": 2.894504758795403e-06, "loss": 3.5091, "step": 802500 }, { "epoch": 1.66, "learning_rate": 2.893815976713655e-06, "loss": 3.5043, "step": 803000 }, { "epoch": 1.66, "learning_rate": 2.893127194631908e-06, "loss": 3.5034, "step": 803500 }, { "epoch": 1.66, "learning_rate": 2.8924384125501602e-06, "loss": 3.5032, "step": 804000 }, { "epoch": 1.66, "learning_rate": 2.8917496304684126e-06, "loss": 3.5086, "step": 804500 }, { "epoch": 1.66, "learning_rate": 2.8910608483866655e-06, "loss": 3.5046, "step": 805000 }, { "epoch": 1.66, "learning_rate": 2.890372066304918e-06, "loss": 3.5047, "step": 805500 }, { "epoch": 1.67, "learning_rate": 2.8896832842231707e-06, "loss": 3.501, "step": 806000 }, { "epoch": 1.67, "learning_rate": 2.888994502141423e-06, "loss": 3.5046, "step": 806500 }, { "epoch": 1.67, "learning_rate": 2.888305720059676e-06, "loss": 3.5024, "step": 807000 }, { "epoch": 1.67, "learning_rate": 2.8876169379779284e-06, "loss": 3.4984, "step": 807500 }, { "epoch": 1.67, "learning_rate": 2.886928155896181e-06, "loss": 3.5124, "step": 808000 }, { "epoch": 1.67, "learning_rate": 2.8862393738144336e-06, "loss": 3.5077, "step": 808500 }, { "epoch": 1.67, "learning_rate": 2.885550591732686e-06, "loss": 3.5037, "step": 809000 }, { "epoch": 1.67, "learning_rate": 2.884861809650939e-06, "loss": 3.4954, "step": 809500 }, { "epoch": 1.67, "learning_rate": 2.8841730275691913e-06, "loss": 3.5053, "step": 810000 }, { "epoch": 1.67, "learning_rate": 2.883484245487444e-06, "loss": 3.511, "step": 810500 }, { "epoch": 1.68, "learning_rate": 2.8827954634056965e-06, "loss": 3.5032, "step": 811000 }, { "epoch": 1.68, "learning_rate": 2.8821066813239493e-06, "loss": 3.5007, "step": 811500 }, { "epoch": 1.68, "learning_rate": 2.8814178992422017e-06, "loss": 3.5009, "step": 812000 }, { "epoch": 1.68, "learning_rate": 2.880729117160454e-06, "loss": 3.5013, "step": 812500 }, { "epoch": 1.68, "learning_rate": 2.880040335078707e-06, "loss": 3.5015, "step": 813000 }, { "epoch": 1.68, "learning_rate": 2.8793515529969594e-06, "loss": 3.5019, "step": 813500 }, { "epoch": 1.68, "learning_rate": 2.8786627709152122e-06, "loss": 3.5027, "step": 814000 }, { "epoch": 1.68, "learning_rate": 2.8779739888334646e-06, "loss": 3.5013, "step": 814500 }, { "epoch": 1.68, "learning_rate": 2.8772852067517175e-06, "loss": 3.4941, "step": 815000 }, { "epoch": 1.69, "learning_rate": 2.87659642466997e-06, "loss": 3.4982, "step": 815500 }, { "epoch": 1.69, "learning_rate": 2.8759076425882227e-06, "loss": 3.506, "step": 816000 }, { "epoch": 1.69, "learning_rate": 2.875218860506475e-06, "loss": 3.4934, "step": 816500 }, { "epoch": 1.69, "learning_rate": 2.8745300784247275e-06, "loss": 3.4968, "step": 817000 }, { "epoch": 1.69, "learning_rate": 2.8738412963429804e-06, "loss": 3.4997, "step": 817500 }, { "epoch": 1.69, "learning_rate": 2.8731525142612328e-06, "loss": 3.4992, "step": 818000 }, { "epoch": 1.69, "learning_rate": 2.8724637321794856e-06, "loss": 3.508, "step": 818500 }, { "epoch": 1.69, "learning_rate": 2.871774950097738e-06, "loss": 3.5021, "step": 819000 }, { "epoch": 1.69, "learning_rate": 2.871086168015991e-06, "loss": 3.4969, "step": 819500 }, { "epoch": 1.69, "learning_rate": 2.8703973859342433e-06, "loss": 3.5004, "step": 820000 }, { "epoch": 1.7, "learning_rate": 2.869708603852496e-06, "loss": 3.4987, "step": 820500 }, { "epoch": 1.7, "learning_rate": 2.8690198217707485e-06, "loss": 3.4964, "step": 821000 }, { "epoch": 1.7, "learning_rate": 2.868331039689001e-06, "loss": 3.4956, "step": 821500 }, { "epoch": 1.7, "learning_rate": 2.8676422576072538e-06, "loss": 3.4931, "step": 822000 }, { "epoch": 1.7, "learning_rate": 2.866953475525506e-06, "loss": 3.4991, "step": 822500 }, { "epoch": 1.7, "learning_rate": 2.866264693443759e-06, "loss": 3.4943, "step": 823000 }, { "epoch": 1.7, "learning_rate": 2.8655759113620114e-06, "loss": 3.4961, "step": 823500 }, { "epoch": 1.7, "learning_rate": 2.8648871292802642e-06, "loss": 3.4942, "step": 824000 }, { "epoch": 1.7, "learning_rate": 2.8641983471985166e-06, "loss": 3.5015, "step": 824500 }, { "epoch": 1.7, "learning_rate": 2.863509565116769e-06, "loss": 3.4998, "step": 825000 }, { "epoch": 1.71, "learning_rate": 2.862820783035022e-06, "loss": 3.4935, "step": 825500 }, { "epoch": 1.71, "learning_rate": 2.8621320009532743e-06, "loss": 3.5041, "step": 826000 }, { "epoch": 1.71, "learning_rate": 2.861443218871527e-06, "loss": 3.4986, "step": 826500 }, { "epoch": 1.71, "learning_rate": 2.8607544367897795e-06, "loss": 3.5044, "step": 827000 }, { "epoch": 1.71, "learning_rate": 2.8600656547080324e-06, "loss": 3.496, "step": 827500 }, { "epoch": 1.71, "learning_rate": 2.8593768726262848e-06, "loss": 3.5015, "step": 828000 }, { "epoch": 1.71, "learning_rate": 2.8586880905445376e-06, "loss": 3.5012, "step": 828500 }, { "epoch": 1.71, "learning_rate": 2.8579993084627896e-06, "loss": 3.4901, "step": 829000 }, { "epoch": 1.71, "learning_rate": 2.857310526381042e-06, "loss": 3.4917, "step": 829500 }, { "epoch": 1.72, "learning_rate": 2.856621744299295e-06, "loss": 3.5014, "step": 830000 }, { "epoch": 1.72, "learning_rate": 2.8559329622175473e-06, "loss": 3.4949, "step": 830500 }, { "epoch": 1.72, "learning_rate": 2.8552441801358e-06, "loss": 3.4943, "step": 831000 }, { "epoch": 1.72, "learning_rate": 2.8545553980540525e-06, "loss": 3.4964, "step": 831500 }, { "epoch": 1.72, "learning_rate": 2.8538666159723053e-06, "loss": 3.4902, "step": 832000 }, { "epoch": 1.72, "learning_rate": 2.8531778338905577e-06, "loss": 3.497, "step": 832500 }, { "epoch": 1.72, "learning_rate": 2.85248905180881e-06, "loss": 3.4922, "step": 833000 }, { "epoch": 1.72, "learning_rate": 2.851800269727063e-06, "loss": 3.4893, "step": 833500 }, { "epoch": 1.72, "learning_rate": 2.8511114876453154e-06, "loss": 3.4946, "step": 834000 }, { "epoch": 1.72, "learning_rate": 2.8504227055635682e-06, "loss": 3.4899, "step": 834500 }, { "epoch": 1.73, "learning_rate": 2.8497339234818206e-06, "loss": 3.4935, "step": 835000 }, { "epoch": 1.73, "learning_rate": 2.8490451414000735e-06, "loss": 3.5002, "step": 835500 }, { "epoch": 1.73, "learning_rate": 2.848356359318326e-06, "loss": 3.4918, "step": 836000 }, { "epoch": 1.73, "learning_rate": 2.8476675772365787e-06, "loss": 3.4906, "step": 836500 }, { "epoch": 1.73, "learning_rate": 2.846978795154831e-06, "loss": 3.49, "step": 837000 }, { "epoch": 1.73, "learning_rate": 2.8462900130730835e-06, "loss": 3.4885, "step": 837500 }, { "epoch": 1.73, "learning_rate": 2.8456012309913364e-06, "loss": 3.496, "step": 838000 }, { "epoch": 1.73, "learning_rate": 2.8449124489095888e-06, "loss": 3.4913, "step": 838500 }, { "epoch": 1.73, "learning_rate": 2.8442236668278416e-06, "loss": 3.4932, "step": 839000 }, { "epoch": 1.73, "learning_rate": 2.843534884746094e-06, "loss": 3.49, "step": 839500 }, { "epoch": 1.74, "learning_rate": 2.842846102664347e-06, "loss": 3.4938, "step": 840000 }, { "epoch": 1.74, "learning_rate": 2.8421573205825993e-06, "loss": 3.4881, "step": 840500 }, { "epoch": 1.74, "learning_rate": 2.841468538500852e-06, "loss": 3.496, "step": 841000 }, { "epoch": 1.74, "learning_rate": 2.8407797564191045e-06, "loss": 3.4894, "step": 841500 }, { "epoch": 1.74, "learning_rate": 2.840090974337357e-06, "loss": 3.4864, "step": 842000 }, { "epoch": 1.74, "learning_rate": 2.8394021922556098e-06, "loss": 3.4887, "step": 842500 }, { "epoch": 1.74, "learning_rate": 2.838713410173862e-06, "loss": 3.4883, "step": 843000 }, { "epoch": 1.74, "learning_rate": 2.838024628092115e-06, "loss": 3.4879, "step": 843500 }, { "epoch": 1.74, "learning_rate": 2.8373358460103674e-06, "loss": 3.4854, "step": 844000 }, { "epoch": 1.75, "learning_rate": 2.8366470639286202e-06, "loss": 3.4881, "step": 844500 }, { "epoch": 1.75, "learning_rate": 2.8359582818468726e-06, "loss": 3.4859, "step": 845000 }, { "epoch": 1.75, "learning_rate": 2.835269499765125e-06, "loss": 3.4927, "step": 845500 }, { "epoch": 1.75, "learning_rate": 2.834580717683378e-06, "loss": 3.4837, "step": 846000 }, { "epoch": 1.75, "learning_rate": 2.8338919356016303e-06, "loss": 3.492, "step": 846500 }, { "epoch": 1.75, "learning_rate": 2.833203153519883e-06, "loss": 3.4884, "step": 847000 }, { "epoch": 1.75, "learning_rate": 2.8325143714381355e-06, "loss": 3.4969, "step": 847500 }, { "epoch": 1.75, "learning_rate": 2.8318255893563884e-06, "loss": 3.4862, "step": 848000 }, { "epoch": 1.75, "learning_rate": 2.8311368072746408e-06, "loss": 3.4893, "step": 848500 }, { "epoch": 1.75, "learning_rate": 2.8304480251928936e-06, "loss": 3.4949, "step": 849000 }, { "epoch": 1.76, "learning_rate": 2.829759243111146e-06, "loss": 3.4896, "step": 849500 }, { "epoch": 1.76, "learning_rate": 2.8290704610293984e-06, "loss": 3.4888, "step": 850000 }, { "epoch": 1.76, "learning_rate": 2.8283816789476513e-06, "loss": 3.4848, "step": 850500 }, { "epoch": 1.76, "learning_rate": 2.8276928968659037e-06, "loss": 3.4876, "step": 851000 }, { "epoch": 1.76, "learning_rate": 2.8270041147841565e-06, "loss": 3.4844, "step": 851500 }, { "epoch": 1.76, "learning_rate": 2.826315332702409e-06, "loss": 3.4857, "step": 852000 }, { "epoch": 1.76, "learning_rate": 2.8256265506206618e-06, "loss": 3.4844, "step": 852500 }, { "epoch": 1.76, "learning_rate": 2.824937768538914e-06, "loss": 3.4813, "step": 853000 }, { "epoch": 1.76, "learning_rate": 2.824248986457166e-06, "loss": 3.4912, "step": 853500 }, { "epoch": 1.76, "learning_rate": 2.823560204375419e-06, "loss": 3.4827, "step": 854000 }, { "epoch": 1.77, "learning_rate": 2.8228714222936714e-06, "loss": 3.4837, "step": 854500 }, { "epoch": 1.77, "learning_rate": 2.8221826402119242e-06, "loss": 3.4834, "step": 855000 }, { "epoch": 1.77, "learning_rate": 2.8214938581301766e-06, "loss": 3.4891, "step": 855500 }, { "epoch": 1.77, "learning_rate": 2.8208050760484295e-06, "loss": 3.4871, "step": 856000 }, { "epoch": 1.77, "learning_rate": 2.820116293966682e-06, "loss": 3.4857, "step": 856500 }, { "epoch": 1.77, "learning_rate": 2.8194275118849347e-06, "loss": 3.487, "step": 857000 }, { "epoch": 1.77, "learning_rate": 2.818738729803187e-06, "loss": 3.4882, "step": 857500 }, { "epoch": 1.77, "learning_rate": 2.8180499477214395e-06, "loss": 3.4842, "step": 858000 }, { "epoch": 1.77, "learning_rate": 2.8173611656396924e-06, "loss": 3.479, "step": 858500 }, { "epoch": 1.77, "learning_rate": 2.8166723835579448e-06, "loss": 3.4871, "step": 859000 }, { "epoch": 1.78, "learning_rate": 2.8159836014761976e-06, "loss": 3.4844, "step": 859500 }, { "epoch": 1.78, "learning_rate": 2.81529481939445e-06, "loss": 3.4814, "step": 860000 }, { "epoch": 1.78, "learning_rate": 2.814606037312703e-06, "loss": 3.4827, "step": 860500 }, { "epoch": 1.78, "learning_rate": 2.8139172552309553e-06, "loss": 3.4749, "step": 861000 }, { "epoch": 1.78, "learning_rate": 2.813228473149208e-06, "loss": 3.4837, "step": 861500 }, { "epoch": 1.78, "learning_rate": 2.8125396910674605e-06, "loss": 3.4911, "step": 862000 }, { "epoch": 1.78, "learning_rate": 2.811850908985713e-06, "loss": 3.4807, "step": 862500 }, { "epoch": 1.78, "learning_rate": 2.8111621269039658e-06, "loss": 3.4848, "step": 863000 }, { "epoch": 1.78, "learning_rate": 2.810473344822218e-06, "loss": 3.4806, "step": 863500 }, { "epoch": 1.79, "learning_rate": 2.809784562740471e-06, "loss": 3.4859, "step": 864000 }, { "epoch": 1.79, "learning_rate": 2.8090957806587234e-06, "loss": 3.476, "step": 864500 }, { "epoch": 1.79, "learning_rate": 2.8084069985769762e-06, "loss": 3.4791, "step": 865000 }, { "epoch": 1.79, "learning_rate": 2.8077182164952287e-06, "loss": 3.4797, "step": 865500 }, { "epoch": 1.79, "learning_rate": 2.807029434413481e-06, "loss": 3.4804, "step": 866000 }, { "epoch": 1.79, "learning_rate": 2.806340652331734e-06, "loss": 3.4876, "step": 866500 }, { "epoch": 1.79, "learning_rate": 2.8056518702499863e-06, "loss": 3.4781, "step": 867000 }, { "epoch": 1.79, "learning_rate": 2.804963088168239e-06, "loss": 3.4838, "step": 867500 }, { "epoch": 1.79, "learning_rate": 2.8042743060864915e-06, "loss": 3.477, "step": 868000 }, { "epoch": 1.79, "learning_rate": 2.8035855240047444e-06, "loss": 3.4829, "step": 868500 }, { "epoch": 1.8, "learning_rate": 2.802896741922997e-06, "loss": 3.4838, "step": 869000 }, { "epoch": 1.8, "learning_rate": 2.8022079598412496e-06, "loss": 3.4832, "step": 869500 }, { "epoch": 1.8, "learning_rate": 2.801519177759502e-06, "loss": 3.4791, "step": 870000 }, { "epoch": 1.8, "learning_rate": 2.8008303956777544e-06, "loss": 3.4753, "step": 870500 }, { "epoch": 1.8, "learning_rate": 2.8001416135960073e-06, "loss": 3.4795, "step": 871000 }, { "epoch": 1.8, "learning_rate": 2.7994528315142597e-06, "loss": 3.4796, "step": 871500 }, { "epoch": 1.8, "learning_rate": 2.7987640494325125e-06, "loss": 3.4774, "step": 872000 }, { "epoch": 1.8, "learning_rate": 2.798075267350765e-06, "loss": 3.4828, "step": 872500 }, { "epoch": 1.8, "learning_rate": 2.7973864852690178e-06, "loss": 3.4792, "step": 873000 }, { "epoch": 1.8, "learning_rate": 2.79669770318727e-06, "loss": 3.4769, "step": 873500 }, { "epoch": 1.81, "learning_rate": 2.7960089211055226e-06, "loss": 3.4736, "step": 874000 }, { "epoch": 1.81, "learning_rate": 2.7953201390237754e-06, "loss": 3.4793, "step": 874500 }, { "epoch": 1.81, "learning_rate": 2.794631356942028e-06, "loss": 3.4745, "step": 875000 }, { "epoch": 1.81, "learning_rate": 2.7939425748602807e-06, "loss": 3.4776, "step": 875500 }, { "epoch": 1.81, "learning_rate": 2.793253792778533e-06, "loss": 3.4782, "step": 876000 }, { "epoch": 1.81, "learning_rate": 2.792565010696786e-06, "loss": 3.4748, "step": 876500 }, { "epoch": 1.81, "learning_rate": 2.7918762286150383e-06, "loss": 3.4853, "step": 877000 }, { "epoch": 1.81, "learning_rate": 2.791187446533291e-06, "loss": 3.476, "step": 877500 }, { "epoch": 1.81, "learning_rate": 2.7904986644515436e-06, "loss": 3.4731, "step": 878000 }, { "epoch": 1.82, "learning_rate": 2.789809882369796e-06, "loss": 3.4833, "step": 878500 }, { "epoch": 1.82, "learning_rate": 2.789121100288049e-06, "loss": 3.4815, "step": 879000 }, { "epoch": 1.82, "learning_rate": 2.7884323182063008e-06, "loss": 3.4789, "step": 879500 }, { "epoch": 1.82, "learning_rate": 2.7877435361245536e-06, "loss": 3.4765, "step": 880000 }, { "epoch": 1.82, "learning_rate": 2.787054754042806e-06, "loss": 3.4737, "step": 880500 }, { "epoch": 1.82, "learning_rate": 2.786365971961059e-06, "loss": 3.478, "step": 881000 }, { "epoch": 1.82, "learning_rate": 2.7856771898793113e-06, "loss": 3.4742, "step": 881500 }, { "epoch": 1.82, "learning_rate": 2.784988407797564e-06, "loss": 3.4729, "step": 882000 }, { "epoch": 1.82, "learning_rate": 2.7842996257158165e-06, "loss": 3.4846, "step": 882500 }, { "epoch": 1.82, "learning_rate": 2.783610843634069e-06, "loss": 3.4772, "step": 883000 }, { "epoch": 1.83, "learning_rate": 2.7829220615523218e-06, "loss": 3.4849, "step": 883500 }, { "epoch": 1.83, "learning_rate": 2.782233279470574e-06, "loss": 3.4781, "step": 884000 }, { "epoch": 1.83, "learning_rate": 2.781544497388827e-06, "loss": 3.471, "step": 884500 }, { "epoch": 1.83, "learning_rate": 2.7808557153070794e-06, "loss": 3.4746, "step": 885000 }, { "epoch": 1.83, "learning_rate": 2.7801669332253322e-06, "loss": 3.4711, "step": 885500 }, { "epoch": 1.83, "learning_rate": 2.7794781511435847e-06, "loss": 3.4729, "step": 886000 }, { "epoch": 1.83, "learning_rate": 2.778789369061837e-06, "loss": 3.4729, "step": 886500 }, { "epoch": 1.83, "learning_rate": 2.77810058698009e-06, "loss": 3.469, "step": 887000 }, { "epoch": 1.83, "learning_rate": 2.7774118048983423e-06, "loss": 3.4734, "step": 887500 }, { "epoch": 1.83, "learning_rate": 2.776723022816595e-06, "loss": 3.4738, "step": 888000 }, { "epoch": 1.84, "learning_rate": 2.7760342407348475e-06, "loss": 3.4698, "step": 888500 }, { "epoch": 1.84, "learning_rate": 2.7753454586531004e-06, "loss": 3.4739, "step": 889000 }, { "epoch": 1.84, "learning_rate": 2.774656676571353e-06, "loss": 3.4763, "step": 889500 }, { "epoch": 1.84, "learning_rate": 2.7739678944896056e-06, "loss": 3.4742, "step": 890000 }, { "epoch": 1.84, "learning_rate": 2.773279112407858e-06, "loss": 3.4784, "step": 890500 }, { "epoch": 1.84, "learning_rate": 2.7725903303261104e-06, "loss": 3.4663, "step": 891000 }, { "epoch": 1.84, "learning_rate": 2.7719015482443633e-06, "loss": 3.4784, "step": 891500 }, { "epoch": 1.84, "learning_rate": 2.7712127661626157e-06, "loss": 3.4704, "step": 892000 }, { "epoch": 1.84, "learning_rate": 2.7705239840808685e-06, "loss": 3.4708, "step": 892500 }, { "epoch": 1.85, "learning_rate": 2.769835201999121e-06, "loss": 3.4746, "step": 893000 }, { "epoch": 1.85, "learning_rate": 2.7691464199173738e-06, "loss": 3.4803, "step": 893500 }, { "epoch": 1.85, "learning_rate": 2.768457637835626e-06, "loss": 3.4753, "step": 894000 }, { "epoch": 1.85, "learning_rate": 2.767768855753879e-06, "loss": 3.4698, "step": 894500 }, { "epoch": 1.85, "learning_rate": 2.7670800736721314e-06, "loss": 3.4729, "step": 895000 }, { "epoch": 1.85, "learning_rate": 2.766391291590384e-06, "loss": 3.4662, "step": 895500 }, { "epoch": 1.85, "learning_rate": 2.7657025095086367e-06, "loss": 3.4713, "step": 896000 }, { "epoch": 1.85, "learning_rate": 2.765013727426889e-06, "loss": 3.472, "step": 896500 }, { "epoch": 1.85, "learning_rate": 2.764324945345142e-06, "loss": 3.4723, "step": 897000 }, { "epoch": 1.85, "learning_rate": 2.7636361632633943e-06, "loss": 3.4766, "step": 897500 }, { "epoch": 1.86, "learning_rate": 2.762947381181647e-06, "loss": 3.472, "step": 898000 }, { "epoch": 1.86, "learning_rate": 2.7622585990998996e-06, "loss": 3.4639, "step": 898500 }, { "epoch": 1.86, "learning_rate": 2.761569817018152e-06, "loss": 3.4739, "step": 899000 }, { "epoch": 1.86, "learning_rate": 2.760881034936405e-06, "loss": 3.4715, "step": 899500 }, { "epoch": 1.86, "learning_rate": 2.760192252854657e-06, "loss": 3.4731, "step": 900000 }, { "epoch": 1.86, "learning_rate": 2.75950347077291e-06, "loss": 3.4709, "step": 900500 }, { "epoch": 1.86, "learning_rate": 2.7588146886911625e-06, "loss": 3.4612, "step": 901000 }, { "epoch": 1.86, "learning_rate": 2.7581259066094153e-06, "loss": 3.4646, "step": 901500 }, { "epoch": 1.86, "learning_rate": 2.7574371245276677e-06, "loss": 3.4668, "step": 902000 }, { "epoch": 1.86, "learning_rate": 2.7567483424459205e-06, "loss": 3.4717, "step": 902500 }, { "epoch": 1.87, "learning_rate": 2.756059560364173e-06, "loss": 3.4672, "step": 903000 }, { "epoch": 1.87, "learning_rate": 2.7553707782824253e-06, "loss": 3.4726, "step": 903500 }, { "epoch": 1.87, "learning_rate": 2.754681996200678e-06, "loss": 3.4693, "step": 904000 }, { "epoch": 1.87, "learning_rate": 2.75399321411893e-06, "loss": 3.464, "step": 904500 }, { "epoch": 1.87, "learning_rate": 2.753304432037183e-06, "loss": 3.4646, "step": 905000 }, { "epoch": 1.87, "learning_rate": 2.7526156499554354e-06, "loss": 3.4652, "step": 905500 }, { "epoch": 1.87, "learning_rate": 2.7519268678736882e-06, "loss": 3.4695, "step": 906000 }, { "epoch": 1.87, "learning_rate": 2.7512380857919407e-06, "loss": 3.4671, "step": 906500 }, { "epoch": 1.87, "learning_rate": 2.750549303710193e-06, "loss": 3.4701, "step": 907000 }, { "epoch": 1.88, "learning_rate": 2.749860521628446e-06, "loss": 3.4686, "step": 907500 }, { "epoch": 1.88, "learning_rate": 2.7491717395466983e-06, "loss": 3.464, "step": 908000 }, { "epoch": 1.88, "learning_rate": 2.748482957464951e-06, "loss": 3.4735, "step": 908500 }, { "epoch": 1.88, "learning_rate": 2.7477941753832035e-06, "loss": 3.4666, "step": 909000 }, { "epoch": 1.88, "learning_rate": 2.7471053933014564e-06, "loss": 3.4673, "step": 909500 }, { "epoch": 1.88, "learning_rate": 2.746416611219709e-06, "loss": 3.4661, "step": 910000 }, { "epoch": 1.88, "learning_rate": 2.7457278291379616e-06, "loss": 3.4684, "step": 910500 }, { "epoch": 1.88, "learning_rate": 2.745039047056214e-06, "loss": 3.4692, "step": 911000 }, { "epoch": 1.88, "learning_rate": 2.7443502649744664e-06, "loss": 3.4728, "step": 911500 }, { "epoch": 1.88, "learning_rate": 2.7436614828927193e-06, "loss": 3.463, "step": 912000 }, { "epoch": 1.89, "learning_rate": 2.7429727008109717e-06, "loss": 3.4641, "step": 912500 }, { "epoch": 1.89, "learning_rate": 2.7422839187292245e-06, "loss": 3.4626, "step": 913000 }, { "epoch": 1.89, "learning_rate": 2.741595136647477e-06, "loss": 3.4599, "step": 913500 }, { "epoch": 1.89, "learning_rate": 2.7409063545657298e-06, "loss": 3.4613, "step": 914000 }, { "epoch": 1.89, "learning_rate": 2.740217572483982e-06, "loss": 3.46, "step": 914500 }, { "epoch": 1.89, "learning_rate": 2.739528790402235e-06, "loss": 3.4642, "step": 915000 }, { "epoch": 1.89, "learning_rate": 2.7388400083204874e-06, "loss": 3.466, "step": 915500 }, { "epoch": 1.89, "learning_rate": 2.73815122623874e-06, "loss": 3.462, "step": 916000 }, { "epoch": 1.89, "learning_rate": 2.7374624441569927e-06, "loss": 3.4597, "step": 916500 }, { "epoch": 1.89, "learning_rate": 2.736773662075245e-06, "loss": 3.4557, "step": 917000 }, { "epoch": 1.9, "learning_rate": 2.736084879993498e-06, "loss": 3.4684, "step": 917500 }, { "epoch": 1.9, "learning_rate": 2.7353960979117503e-06, "loss": 3.457, "step": 918000 }, { "epoch": 1.9, "learning_rate": 2.734707315830003e-06, "loss": 3.4584, "step": 918500 }, { "epoch": 1.9, "learning_rate": 2.7340185337482556e-06, "loss": 3.4607, "step": 919000 }, { "epoch": 1.9, "learning_rate": 2.733329751666508e-06, "loss": 3.4645, "step": 919500 }, { "epoch": 1.9, "learning_rate": 2.732640969584761e-06, "loss": 3.4618, "step": 920000 }, { "epoch": 1.9, "learning_rate": 2.731952187503013e-06, "loss": 3.459, "step": 920500 }, { "epoch": 1.9, "learning_rate": 2.731263405421266e-06, "loss": 3.4676, "step": 921000 }, { "epoch": 1.9, "learning_rate": 2.7305746233395185e-06, "loss": 3.4618, "step": 921500 }, { "epoch": 1.91, "learning_rate": 2.7298858412577713e-06, "loss": 3.4572, "step": 922000 }, { "epoch": 1.91, "learning_rate": 2.7291970591760237e-06, "loss": 3.4595, "step": 922500 }, { "epoch": 1.91, "learning_rate": 2.7285082770942765e-06, "loss": 3.4665, "step": 923000 }, { "epoch": 1.91, "learning_rate": 2.727819495012529e-06, "loss": 3.4579, "step": 923500 }, { "epoch": 1.91, "learning_rate": 2.7271307129307813e-06, "loss": 3.4595, "step": 924000 }, { "epoch": 1.91, "learning_rate": 2.726441930849034e-06, "loss": 3.4633, "step": 924500 }, { "epoch": 1.91, "learning_rate": 2.7257531487672866e-06, "loss": 3.4611, "step": 925000 }, { "epoch": 1.91, "learning_rate": 2.7250643666855394e-06, "loss": 3.4601, "step": 925500 }, { "epoch": 1.91, "learning_rate": 2.724375584603792e-06, "loss": 3.4623, "step": 926000 }, { "epoch": 1.91, "learning_rate": 2.7236868025220447e-06, "loss": 3.4618, "step": 926500 }, { "epoch": 1.92, "learning_rate": 2.722998020440297e-06, "loss": 3.4609, "step": 927000 }, { "epoch": 1.92, "learning_rate": 2.7223092383585495e-06, "loss": 3.4589, "step": 927500 }, { "epoch": 1.92, "learning_rate": 2.7216204562768023e-06, "loss": 3.4614, "step": 928000 }, { "epoch": 1.92, "learning_rate": 2.7209316741950547e-06, "loss": 3.464, "step": 928500 }, { "epoch": 1.92, "learning_rate": 2.7202428921133076e-06, "loss": 3.457, "step": 929000 }, { "epoch": 1.92, "learning_rate": 2.71955411003156e-06, "loss": 3.4644, "step": 929500 }, { "epoch": 1.92, "learning_rate": 2.718865327949813e-06, "loss": 3.4576, "step": 930000 }, { "epoch": 1.92, "learning_rate": 2.718176545868065e-06, "loss": 3.4572, "step": 930500 }, { "epoch": 1.92, "learning_rate": 2.7174877637863176e-06, "loss": 3.4532, "step": 931000 }, { "epoch": 1.92, "learning_rate": 2.71679898170457e-06, "loss": 3.4612, "step": 931500 }, { "epoch": 1.93, "learning_rate": 2.7161101996228224e-06, "loss": 3.4569, "step": 932000 }, { "epoch": 1.93, "learning_rate": 2.7154214175410753e-06, "loss": 3.4502, "step": 932500 }, { "epoch": 1.93, "learning_rate": 2.7147326354593277e-06, "loss": 3.4597, "step": 933000 }, { "epoch": 1.93, "learning_rate": 2.7140438533775805e-06, "loss": 3.464, "step": 933500 }, { "epoch": 1.93, "learning_rate": 2.713355071295833e-06, "loss": 3.4507, "step": 934000 }, { "epoch": 1.93, "learning_rate": 2.7126662892140858e-06, "loss": 3.4604, "step": 934500 }, { "epoch": 1.93, "learning_rate": 2.711977507132338e-06, "loss": 3.4574, "step": 935000 }, { "epoch": 1.93, "learning_rate": 2.711288725050591e-06, "loss": 3.4571, "step": 935500 }, { "epoch": 1.93, "learning_rate": 2.7105999429688434e-06, "loss": 3.4542, "step": 936000 }, { "epoch": 1.94, "learning_rate": 2.709911160887096e-06, "loss": 3.4503, "step": 936500 }, { "epoch": 1.94, "learning_rate": 2.7092223788053487e-06, "loss": 3.4545, "step": 937000 }, { "epoch": 1.94, "learning_rate": 2.708533596723601e-06, "loss": 3.4546, "step": 937500 }, { "epoch": 1.94, "learning_rate": 2.707844814641854e-06, "loss": 3.458, "step": 938000 }, { "epoch": 1.94, "learning_rate": 2.7071560325601063e-06, "loss": 3.4559, "step": 938500 }, { "epoch": 1.94, "learning_rate": 2.706467250478359e-06, "loss": 3.4518, "step": 939000 }, { "epoch": 1.94, "learning_rate": 2.7057784683966116e-06, "loss": 3.4618, "step": 939500 }, { "epoch": 1.94, "learning_rate": 2.705089686314864e-06, "loss": 3.454, "step": 940000 }, { "epoch": 1.94, "learning_rate": 2.704400904233117e-06, "loss": 3.458, "step": 940500 }, { "epoch": 1.94, "learning_rate": 2.703712122151369e-06, "loss": 3.4524, "step": 941000 }, { "epoch": 1.95, "learning_rate": 2.703023340069622e-06, "loss": 3.4557, "step": 941500 }, { "epoch": 1.95, "learning_rate": 2.7023345579878745e-06, "loss": 3.4509, "step": 942000 }, { "epoch": 1.95, "learning_rate": 2.7016457759061273e-06, "loss": 3.4557, "step": 942500 }, { "epoch": 1.95, "learning_rate": 2.7009569938243797e-06, "loss": 3.462, "step": 943000 }, { "epoch": 1.95, "learning_rate": 2.7002682117426325e-06, "loss": 3.4565, "step": 943500 }, { "epoch": 1.95, "learning_rate": 2.699579429660885e-06, "loss": 3.4529, "step": 944000 }, { "epoch": 1.95, "learning_rate": 2.6988906475791374e-06, "loss": 3.4541, "step": 944500 }, { "epoch": 1.95, "learning_rate": 2.69820186549739e-06, "loss": 3.4478, "step": 945000 }, { "epoch": 1.95, "learning_rate": 2.6975130834156426e-06, "loss": 3.455, "step": 945500 }, { "epoch": 1.95, "learning_rate": 2.6968243013338954e-06, "loss": 3.459, "step": 946000 }, { "epoch": 1.96, "learning_rate": 2.696135519252148e-06, "loss": 3.4495, "step": 946500 }, { "epoch": 1.96, "learning_rate": 2.6954467371704007e-06, "loss": 3.4607, "step": 947000 }, { "epoch": 1.96, "learning_rate": 2.694757955088653e-06, "loss": 3.4536, "step": 947500 }, { "epoch": 1.96, "learning_rate": 2.6940691730069055e-06, "loss": 3.4587, "step": 948000 }, { "epoch": 1.96, "learning_rate": 2.6933803909251583e-06, "loss": 3.4607, "step": 948500 }, { "epoch": 1.96, "learning_rate": 2.6926916088434107e-06, "loss": 3.4589, "step": 949000 }, { "epoch": 1.96, "learning_rate": 2.6920028267616636e-06, "loss": 3.4569, "step": 949500 }, { "epoch": 1.96, "learning_rate": 2.691314044679916e-06, "loss": 3.4577, "step": 950000 }, { "epoch": 1.96, "learning_rate": 2.690625262598169e-06, "loss": 3.4507, "step": 950500 }, { "epoch": 1.97, "learning_rate": 2.6899364805164212e-06, "loss": 3.4467, "step": 951000 }, { "epoch": 1.97, "learning_rate": 2.689247698434674e-06, "loss": 3.4523, "step": 951500 }, { "epoch": 1.97, "learning_rate": 2.6885589163529265e-06, "loss": 3.4571, "step": 952000 }, { "epoch": 1.97, "learning_rate": 2.687870134271179e-06, "loss": 3.4515, "step": 952500 }, { "epoch": 1.97, "learning_rate": 2.6871813521894317e-06, "loss": 3.4541, "step": 953000 }, { "epoch": 1.97, "learning_rate": 2.686492570107684e-06, "loss": 3.4576, "step": 953500 }, { "epoch": 1.97, "learning_rate": 2.685803788025937e-06, "loss": 3.4507, "step": 954000 }, { "epoch": 1.97, "learning_rate": 2.6851150059441894e-06, "loss": 3.4568, "step": 954500 }, { "epoch": 1.97, "learning_rate": 2.684426223862442e-06, "loss": 3.4539, "step": 955000 }, { "epoch": 1.97, "learning_rate": 2.683737441780694e-06, "loss": 3.4471, "step": 955500 }, { "epoch": 1.98, "learning_rate": 2.6830486596989474e-06, "loss": 3.4567, "step": 956000 }, { "epoch": 1.98, "learning_rate": 2.6823598776171994e-06, "loss": 3.4498, "step": 956500 }, { "epoch": 1.98, "learning_rate": 2.681671095535452e-06, "loss": 3.4519, "step": 957000 }, { "epoch": 1.98, "learning_rate": 2.6809823134537047e-06, "loss": 3.4531, "step": 957500 }, { "epoch": 1.98, "learning_rate": 2.680293531371957e-06, "loss": 3.4445, "step": 958000 }, { "epoch": 1.98, "learning_rate": 2.67960474929021e-06, "loss": 3.4488, "step": 958500 }, { "epoch": 1.98, "learning_rate": 2.6789159672084623e-06, "loss": 3.4581, "step": 959000 }, { "epoch": 1.98, "learning_rate": 2.678227185126715e-06, "loss": 3.4552, "step": 959500 }, { "epoch": 1.98, "learning_rate": 2.6775384030449676e-06, "loss": 3.4432, "step": 960000 }, { "epoch": 1.98, "learning_rate": 2.67684962096322e-06, "loss": 3.4495, "step": 960500 }, { "epoch": 1.99, "learning_rate": 2.676160838881473e-06, "loss": 3.449, "step": 961000 }, { "epoch": 1.99, "learning_rate": 2.6754720567997252e-06, "loss": 3.4522, "step": 961500 }, { "epoch": 1.99, "learning_rate": 2.674783274717978e-06, "loss": 3.4413, "step": 962000 }, { "epoch": 1.99, "learning_rate": 2.6740944926362305e-06, "loss": 3.4553, "step": 962500 }, { "epoch": 1.99, "learning_rate": 2.6734057105544833e-06, "loss": 3.451, "step": 963000 }, { "epoch": 1.99, "learning_rate": 2.6727169284727357e-06, "loss": 3.45, "step": 963500 }, { "epoch": 1.99, "learning_rate": 2.6720281463909885e-06, "loss": 3.4532, "step": 964000 }, { "epoch": 1.99, "learning_rate": 2.671339364309241e-06, "loss": 3.4528, "step": 964500 }, { "epoch": 1.99, "learning_rate": 2.6706505822274934e-06, "loss": 3.4518, "step": 965000 }, { "epoch": 2.0, "learning_rate": 2.669961800145746e-06, "loss": 3.4464, "step": 965500 }, { "epoch": 2.0, "learning_rate": 2.6692730180639986e-06, "loss": 3.4509, "step": 966000 }, { "epoch": 2.0, "learning_rate": 2.6685842359822514e-06, "loss": 3.4485, "step": 966500 }, { "epoch": 2.0, "learning_rate": 2.667895453900504e-06, "loss": 3.4472, "step": 967000 }, { "epoch": 2.0, "learning_rate": 2.6672066718187567e-06, "loss": 3.4504, "step": 967500 }, { "epoch": 2.0, "eval_loss": 3.439384937286377, "eval_runtime": 23570.7725, "eval_samples_per_second": 146.002, "eval_steps_per_second": 2.281, "step": 967892 }, { "epoch": 2.0, "learning_rate": 2.666517889737009e-06, "loss": 3.4485, "step": 968000 }, { "epoch": 2.0, "learning_rate": 2.6658291076552615e-06, "loss": 3.4393, "step": 968500 }, { "epoch": 2.0, "learning_rate": 2.6651403255735143e-06, "loss": 3.4439, "step": 969000 }, { "epoch": 2.0, "learning_rate": 2.6644515434917667e-06, "loss": 3.434, "step": 969500 }, { "epoch": 2.0, "learning_rate": 2.6637627614100196e-06, "loss": 3.4342, "step": 970000 }, { "epoch": 2.01, "learning_rate": 2.663073979328272e-06, "loss": 3.4316, "step": 970500 }, { "epoch": 2.01, "learning_rate": 2.662385197246525e-06, "loss": 3.4347, "step": 971000 }, { "epoch": 2.01, "learning_rate": 2.6616964151647772e-06, "loss": 3.4344, "step": 971500 }, { "epoch": 2.01, "learning_rate": 2.66100763308303e-06, "loss": 3.4348, "step": 972000 }, { "epoch": 2.01, "learning_rate": 2.6603188510012825e-06, "loss": 3.4316, "step": 972500 }, { "epoch": 2.01, "learning_rate": 2.659630068919535e-06, "loss": 3.4348, "step": 973000 }, { "epoch": 2.01, "learning_rate": 2.6589412868377877e-06, "loss": 3.4375, "step": 973500 }, { "epoch": 2.01, "learning_rate": 2.65825250475604e-06, "loss": 3.4344, "step": 974000 }, { "epoch": 2.01, "learning_rate": 2.657563722674293e-06, "loss": 3.4266, "step": 974500 }, { "epoch": 2.01, "learning_rate": 2.6568749405925454e-06, "loss": 3.4361, "step": 975000 }, { "epoch": 2.02, "learning_rate": 2.656186158510798e-06, "loss": 3.4368, "step": 975500 }, { "epoch": 2.02, "learning_rate": 2.6554973764290506e-06, "loss": 3.4321, "step": 976000 }, { "epoch": 2.02, "learning_rate": 2.6548085943473034e-06, "loss": 3.4305, "step": 976500 }, { "epoch": 2.02, "learning_rate": 2.654119812265556e-06, "loss": 3.4332, "step": 977000 }, { "epoch": 2.02, "learning_rate": 2.6534310301838083e-06, "loss": 3.4288, "step": 977500 }, { "epoch": 2.02, "learning_rate": 2.652742248102061e-06, "loss": 3.4346, "step": 978000 }, { "epoch": 2.02, "learning_rate": 2.6520534660203135e-06, "loss": 3.4295, "step": 978500 }, { "epoch": 2.02, "learning_rate": 2.6513646839385663e-06, "loss": 3.4289, "step": 979000 }, { "epoch": 2.02, "learning_rate": 2.6506759018568187e-06, "loss": 3.4329, "step": 979500 }, { "epoch": 2.03, "learning_rate": 2.6499871197750716e-06, "loss": 3.433, "step": 980000 }, { "epoch": 2.03, "learning_rate": 2.649298337693324e-06, "loss": 3.4284, "step": 980500 }, { "epoch": 2.03, "learning_rate": 2.648609555611576e-06, "loss": 3.428, "step": 981000 }, { "epoch": 2.03, "learning_rate": 2.647920773529829e-06, "loss": 3.4336, "step": 981500 }, { "epoch": 2.03, "learning_rate": 2.6472319914480812e-06, "loss": 3.4326, "step": 982000 }, { "epoch": 2.03, "learning_rate": 2.646543209366334e-06, "loss": 3.4317, "step": 982500 }, { "epoch": 2.03, "learning_rate": 2.6458544272845865e-06, "loss": 3.4262, "step": 983000 }, { "epoch": 2.03, "learning_rate": 2.6451656452028393e-06, "loss": 3.4386, "step": 983500 }, { "epoch": 2.03, "learning_rate": 2.6444768631210917e-06, "loss": 3.4263, "step": 984000 }, { "epoch": 2.03, "learning_rate": 2.6437880810393445e-06, "loss": 3.4322, "step": 984500 }, { "epoch": 2.04, "learning_rate": 2.643099298957597e-06, "loss": 3.4255, "step": 985000 }, { "epoch": 2.04, "learning_rate": 2.6424105168758494e-06, "loss": 3.4313, "step": 985500 }, { "epoch": 2.04, "learning_rate": 2.641721734794102e-06, "loss": 3.4268, "step": 986000 }, { "epoch": 2.04, "learning_rate": 2.6410329527123546e-06, "loss": 3.4344, "step": 986500 }, { "epoch": 2.04, "learning_rate": 2.6403441706306074e-06, "loss": 3.432, "step": 987000 }, { "epoch": 2.04, "learning_rate": 2.63965538854886e-06, "loss": 3.4241, "step": 987500 }, { "epoch": 2.04, "learning_rate": 2.6389666064671127e-06, "loss": 3.428, "step": 988000 }, { "epoch": 2.04, "learning_rate": 2.638277824385365e-06, "loss": 3.4256, "step": 988500 }, { "epoch": 2.04, "learning_rate": 2.6375890423036175e-06, "loss": 3.4266, "step": 989000 }, { "epoch": 2.04, "learning_rate": 2.6369002602218703e-06, "loss": 3.4322, "step": 989500 }, { "epoch": 2.05, "learning_rate": 2.6362114781401227e-06, "loss": 3.4269, "step": 990000 }, { "epoch": 2.05, "learning_rate": 2.6355226960583756e-06, "loss": 3.4327, "step": 990500 }, { "epoch": 2.05, "learning_rate": 2.634833913976628e-06, "loss": 3.4303, "step": 991000 }, { "epoch": 2.05, "learning_rate": 2.634145131894881e-06, "loss": 3.4291, "step": 991500 }, { "epoch": 2.05, "learning_rate": 2.6334563498131332e-06, "loss": 3.4301, "step": 992000 }, { "epoch": 2.05, "learning_rate": 2.632767567731386e-06, "loss": 3.4346, "step": 992500 }, { "epoch": 2.05, "learning_rate": 2.6320787856496385e-06, "loss": 3.4252, "step": 993000 }, { "epoch": 2.05, "learning_rate": 2.631390003567891e-06, "loss": 3.437, "step": 993500 }, { "epoch": 2.05, "learning_rate": 2.6307012214861437e-06, "loss": 3.4233, "step": 994000 }, { "epoch": 2.05, "learning_rate": 2.630012439404396e-06, "loss": 3.4199, "step": 994500 }, { "epoch": 2.06, "learning_rate": 2.629323657322649e-06, "loss": 3.43, "step": 995000 }, { "epoch": 2.06, "learning_rate": 2.6286348752409014e-06, "loss": 3.4268, "step": 995500 }, { "epoch": 2.06, "learning_rate": 2.627946093159154e-06, "loss": 3.4275, "step": 996000 }, { "epoch": 2.06, "learning_rate": 2.6272573110774066e-06, "loss": 3.4254, "step": 996500 }, { "epoch": 2.06, "learning_rate": 2.6265685289956594e-06, "loss": 3.4277, "step": 997000 }, { "epoch": 2.06, "learning_rate": 2.625879746913912e-06, "loss": 3.4322, "step": 997500 }, { "epoch": 2.06, "learning_rate": 2.6251909648321643e-06, "loss": 3.4229, "step": 998000 }, { "epoch": 2.06, "learning_rate": 2.624502182750417e-06, "loss": 3.4287, "step": 998500 }, { "epoch": 2.06, "learning_rate": 2.6238134006686695e-06, "loss": 3.4252, "step": 999000 }, { "epoch": 2.07, "learning_rate": 2.6231246185869223e-06, "loss": 3.4312, "step": 999500 }, { "epoch": 2.07, "learning_rate": 2.6224358365051747e-06, "loss": 3.4308, "step": 1000000 }, { "epoch": 2.07, "learning_rate": 2.6217470544234276e-06, "loss": 3.4312, "step": 1000500 }, { "epoch": 2.07, "learning_rate": 2.62105827234168e-06, "loss": 3.4319, "step": 1001000 }, { "epoch": 2.07, "learning_rate": 2.6203694902599324e-06, "loss": 3.4193, "step": 1001500 }, { "epoch": 2.07, "learning_rate": 2.6196807081781852e-06, "loss": 3.428, "step": 1002000 }, { "epoch": 2.07, "learning_rate": 2.6189919260964376e-06, "loss": 3.4295, "step": 1002500 }, { "epoch": 2.07, "learning_rate": 2.6183031440146905e-06, "loss": 3.4242, "step": 1003000 }, { "epoch": 2.07, "learning_rate": 2.617614361932943e-06, "loss": 3.4241, "step": 1003500 }, { "epoch": 2.07, "learning_rate": 2.6169255798511957e-06, "loss": 3.4261, "step": 1004000 }, { "epoch": 2.08, "learning_rate": 2.616236797769448e-06, "loss": 3.4247, "step": 1004500 }, { "epoch": 2.08, "learning_rate": 2.615548015687701e-06, "loss": 3.4247, "step": 1005000 }, { "epoch": 2.08, "learning_rate": 2.6148592336059534e-06, "loss": 3.4275, "step": 1005500 }, { "epoch": 2.08, "learning_rate": 2.6141704515242058e-06, "loss": 3.4229, "step": 1006000 }, { "epoch": 2.08, "learning_rate": 2.6134816694424586e-06, "loss": 3.4225, "step": 1006500 }, { "epoch": 2.08, "learning_rate": 2.6127928873607106e-06, "loss": 3.4282, "step": 1007000 }, { "epoch": 2.08, "learning_rate": 2.6121041052789634e-06, "loss": 3.4228, "step": 1007500 }, { "epoch": 2.08, "learning_rate": 2.611415323197216e-06, "loss": 3.4262, "step": 1008000 }, { "epoch": 2.08, "learning_rate": 2.6107265411154687e-06, "loss": 3.426, "step": 1008500 }, { "epoch": 2.08, "learning_rate": 2.610037759033721e-06, "loss": 3.4258, "step": 1009000 }, { "epoch": 2.09, "learning_rate": 2.6093489769519735e-06, "loss": 3.4189, "step": 1009500 }, { "epoch": 2.09, "learning_rate": 2.6086601948702263e-06, "loss": 3.4322, "step": 1010000 }, { "epoch": 2.09, "learning_rate": 2.6079714127884787e-06, "loss": 3.4261, "step": 1010500 }, { "epoch": 2.09, "learning_rate": 2.6072826307067316e-06, "loss": 3.4191, "step": 1011000 }, { "epoch": 2.09, "learning_rate": 2.606593848624984e-06, "loss": 3.4284, "step": 1011500 }, { "epoch": 2.09, "learning_rate": 2.605905066543237e-06, "loss": 3.4264, "step": 1012000 }, { "epoch": 2.09, "learning_rate": 2.6052162844614892e-06, "loss": 3.4209, "step": 1012500 }, { "epoch": 2.09, "learning_rate": 2.604527502379742e-06, "loss": 3.4248, "step": 1013000 }, { "epoch": 2.09, "learning_rate": 2.6038387202979945e-06, "loss": 3.4198, "step": 1013500 }, { "epoch": 2.1, "learning_rate": 2.603149938216247e-06, "loss": 3.4264, "step": 1014000 }, { "epoch": 2.1, "learning_rate": 2.6024611561344997e-06, "loss": 3.4191, "step": 1014500 }, { "epoch": 2.1, "learning_rate": 2.601772374052752e-06, "loss": 3.4234, "step": 1015000 }, { "epoch": 2.1, "learning_rate": 2.601083591971005e-06, "loss": 3.4198, "step": 1015500 }, { "epoch": 2.1, "learning_rate": 2.6003948098892574e-06, "loss": 3.4221, "step": 1016000 }, { "epoch": 2.1, "learning_rate": 2.59970602780751e-06, "loss": 3.4245, "step": 1016500 }, { "epoch": 2.1, "learning_rate": 2.5990172457257626e-06, "loss": 3.4211, "step": 1017000 }, { "epoch": 2.1, "learning_rate": 2.5983284636440154e-06, "loss": 3.4264, "step": 1017500 }, { "epoch": 2.1, "learning_rate": 2.597639681562268e-06, "loss": 3.4163, "step": 1018000 }, { "epoch": 2.1, "learning_rate": 2.5969508994805203e-06, "loss": 3.4237, "step": 1018500 }, { "epoch": 2.11, "learning_rate": 2.596262117398773e-06, "loss": 3.4246, "step": 1019000 }, { "epoch": 2.11, "learning_rate": 2.5955733353170255e-06, "loss": 3.4251, "step": 1019500 }, { "epoch": 2.11, "learning_rate": 2.5948845532352783e-06, "loss": 3.422, "step": 1020000 }, { "epoch": 2.11, "learning_rate": 2.5941957711535307e-06, "loss": 3.4229, "step": 1020500 }, { "epoch": 2.11, "learning_rate": 2.5935069890717836e-06, "loss": 3.4233, "step": 1021000 }, { "epoch": 2.11, "learning_rate": 2.592818206990036e-06, "loss": 3.4252, "step": 1021500 }, { "epoch": 2.11, "learning_rate": 2.5921294249082884e-06, "loss": 3.4295, "step": 1022000 }, { "epoch": 2.11, "learning_rate": 2.5914406428265412e-06, "loss": 3.4211, "step": 1022500 }, { "epoch": 2.11, "learning_rate": 2.5907518607447936e-06, "loss": 3.4222, "step": 1023000 }, { "epoch": 2.11, "learning_rate": 2.5900630786630465e-06, "loss": 3.4167, "step": 1023500 }, { "epoch": 2.12, "learning_rate": 2.589374296581299e-06, "loss": 3.4168, "step": 1024000 }, { "epoch": 2.12, "learning_rate": 2.5886855144995517e-06, "loss": 3.4181, "step": 1024500 }, { "epoch": 2.12, "learning_rate": 2.587996732417804e-06, "loss": 3.4215, "step": 1025000 }, { "epoch": 2.12, "learning_rate": 2.587307950336057e-06, "loss": 3.4233, "step": 1025500 }, { "epoch": 2.12, "learning_rate": 2.5866191682543094e-06, "loss": 3.4216, "step": 1026000 }, { "epoch": 2.12, "learning_rate": 2.5859303861725618e-06, "loss": 3.4217, "step": 1026500 }, { "epoch": 2.12, "learning_rate": 2.5852416040908146e-06, "loss": 3.4265, "step": 1027000 }, { "epoch": 2.12, "learning_rate": 2.584552822009067e-06, "loss": 3.4224, "step": 1027500 }, { "epoch": 2.12, "learning_rate": 2.58386403992732e-06, "loss": 3.425, "step": 1028000 }, { "epoch": 2.13, "learning_rate": 2.5831752578455723e-06, "loss": 3.4247, "step": 1028500 }, { "epoch": 2.13, "learning_rate": 2.582486475763825e-06, "loss": 3.4153, "step": 1029000 }, { "epoch": 2.13, "learning_rate": 2.5817976936820775e-06, "loss": 3.4182, "step": 1029500 }, { "epoch": 2.13, "learning_rate": 2.58110891160033e-06, "loss": 3.4191, "step": 1030000 }, { "epoch": 2.13, "learning_rate": 2.5804201295185828e-06, "loss": 3.4147, "step": 1030500 }, { "epoch": 2.13, "learning_rate": 2.579731347436835e-06, "loss": 3.423, "step": 1031000 }, { "epoch": 2.13, "learning_rate": 2.579042565355088e-06, "loss": 3.4149, "step": 1031500 }, { "epoch": 2.13, "learning_rate": 2.57835378327334e-06, "loss": 3.4227, "step": 1032000 }, { "epoch": 2.13, "learning_rate": 2.577665001191593e-06, "loss": 3.4257, "step": 1032500 }, { "epoch": 2.13, "learning_rate": 2.5769762191098452e-06, "loss": 3.4179, "step": 1033000 }, { "epoch": 2.14, "learning_rate": 2.576287437028098e-06, "loss": 3.4176, "step": 1033500 }, { "epoch": 2.14, "learning_rate": 2.5755986549463505e-06, "loss": 3.4206, "step": 1034000 }, { "epoch": 2.14, "learning_rate": 2.574909872864603e-06, "loss": 3.4166, "step": 1034500 }, { "epoch": 2.14, "learning_rate": 2.5742210907828557e-06, "loss": 3.4236, "step": 1035000 }, { "epoch": 2.14, "learning_rate": 2.573532308701108e-06, "loss": 3.4172, "step": 1035500 }, { "epoch": 2.14, "learning_rate": 2.572843526619361e-06, "loss": 3.4189, "step": 1036000 }, { "epoch": 2.14, "learning_rate": 2.5721547445376134e-06, "loss": 3.4172, "step": 1036500 }, { "epoch": 2.14, "learning_rate": 2.571465962455866e-06, "loss": 3.4242, "step": 1037000 }, { "epoch": 2.14, "learning_rate": 2.5707771803741186e-06, "loss": 3.419, "step": 1037500 }, { "epoch": 2.14, "learning_rate": 2.5700883982923714e-06, "loss": 3.4226, "step": 1038000 }, { "epoch": 2.15, "learning_rate": 2.569399616210624e-06, "loss": 3.4153, "step": 1038500 }, { "epoch": 2.15, "learning_rate": 2.5687108341288763e-06, "loss": 3.4141, "step": 1039000 }, { "epoch": 2.15, "learning_rate": 2.568022052047129e-06, "loss": 3.4165, "step": 1039500 }, { "epoch": 2.15, "learning_rate": 2.5673332699653815e-06, "loss": 3.4165, "step": 1040000 }, { "epoch": 2.15, "learning_rate": 2.5666444878836343e-06, "loss": 3.416, "step": 1040500 }, { "epoch": 2.15, "learning_rate": 2.5659557058018867e-06, "loss": 3.4177, "step": 1041000 }, { "epoch": 2.15, "learning_rate": 2.5652669237201396e-06, "loss": 3.4153, "step": 1041500 }, { "epoch": 2.15, "learning_rate": 2.564578141638392e-06, "loss": 3.4181, "step": 1042000 }, { "epoch": 2.15, "learning_rate": 2.5638893595566444e-06, "loss": 3.4219, "step": 1042500 }, { "epoch": 2.16, "learning_rate": 2.5632005774748972e-06, "loss": 3.4222, "step": 1043000 }, { "epoch": 2.16, "learning_rate": 2.5625117953931496e-06, "loss": 3.4173, "step": 1043500 }, { "epoch": 2.16, "learning_rate": 2.5618230133114025e-06, "loss": 3.4199, "step": 1044000 }, { "epoch": 2.16, "learning_rate": 2.561134231229655e-06, "loss": 3.4135, "step": 1044500 }, { "epoch": 2.16, "learning_rate": 2.5604454491479077e-06, "loss": 3.4167, "step": 1045000 }, { "epoch": 2.16, "learning_rate": 2.55975666706616e-06, "loss": 3.4097, "step": 1045500 }, { "epoch": 2.16, "learning_rate": 2.559067884984413e-06, "loss": 3.4218, "step": 1046000 }, { "epoch": 2.16, "learning_rate": 2.5583791029026654e-06, "loss": 3.4217, "step": 1046500 }, { "epoch": 2.16, "learning_rate": 2.5576903208209178e-06, "loss": 3.408, "step": 1047000 }, { "epoch": 2.16, "learning_rate": 2.5570015387391706e-06, "loss": 3.409, "step": 1047500 }, { "epoch": 2.17, "learning_rate": 2.556312756657423e-06, "loss": 3.417, "step": 1048000 }, { "epoch": 2.17, "learning_rate": 2.555623974575676e-06, "loss": 3.4154, "step": 1048500 }, { "epoch": 2.17, "learning_rate": 2.5549351924939283e-06, "loss": 3.42, "step": 1049000 }, { "epoch": 2.17, "learning_rate": 2.554246410412181e-06, "loss": 3.4151, "step": 1049500 }, { "epoch": 2.17, "learning_rate": 2.5535576283304335e-06, "loss": 3.4171, "step": 1050000 }, { "epoch": 2.17, "learning_rate": 2.552868846248686e-06, "loss": 3.4144, "step": 1050500 }, { "epoch": 2.17, "learning_rate": 2.5521800641669388e-06, "loss": 3.4191, "step": 1051000 }, { "epoch": 2.17, "learning_rate": 2.551491282085191e-06, "loss": 3.4237, "step": 1051500 }, { "epoch": 2.17, "learning_rate": 2.550802500003444e-06, "loss": 3.4211, "step": 1052000 }, { "epoch": 2.17, "learning_rate": 2.5501137179216964e-06, "loss": 3.4101, "step": 1052500 }, { "epoch": 2.18, "learning_rate": 2.5494249358399492e-06, "loss": 3.4157, "step": 1053000 }, { "epoch": 2.18, "learning_rate": 2.5487361537582016e-06, "loss": 3.4163, "step": 1053500 }, { "epoch": 2.18, "learning_rate": 2.5480473716764545e-06, "loss": 3.4144, "step": 1054000 }, { "epoch": 2.18, "learning_rate": 2.547358589594707e-06, "loss": 3.4196, "step": 1054500 }, { "epoch": 2.18, "learning_rate": 2.5466698075129593e-06, "loss": 3.4198, "step": 1055000 }, { "epoch": 2.18, "learning_rate": 2.545981025431212e-06, "loss": 3.4163, "step": 1055500 }, { "epoch": 2.18, "learning_rate": 2.5452922433494645e-06, "loss": 3.4145, "step": 1056000 }, { "epoch": 2.18, "learning_rate": 2.5446034612677174e-06, "loss": 3.4123, "step": 1056500 }, { "epoch": 2.18, "learning_rate": 2.54391467918597e-06, "loss": 3.4108, "step": 1057000 }, { "epoch": 2.19, "learning_rate": 2.5432258971042226e-06, "loss": 3.4148, "step": 1057500 }, { "epoch": 2.19, "learning_rate": 2.5425371150224746e-06, "loss": 3.4129, "step": 1058000 }, { "epoch": 2.19, "learning_rate": 2.5418483329407274e-06, "loss": 3.4165, "step": 1058500 }, { "epoch": 2.19, "learning_rate": 2.54115955085898e-06, "loss": 3.4135, "step": 1059000 }, { "epoch": 2.19, "learning_rate": 2.5404707687772323e-06, "loss": 3.4202, "step": 1059500 }, { "epoch": 2.19, "learning_rate": 2.539781986695485e-06, "loss": 3.4142, "step": 1060000 }, { "epoch": 2.19, "learning_rate": 2.5390932046137375e-06, "loss": 3.4067, "step": 1060500 }, { "epoch": 2.19, "learning_rate": 2.5384044225319903e-06, "loss": 3.415, "step": 1061000 }, { "epoch": 2.19, "learning_rate": 2.5377156404502427e-06, "loss": 3.4077, "step": 1061500 }, { "epoch": 2.19, "learning_rate": 2.5370268583684956e-06, "loss": 3.4085, "step": 1062000 }, { "epoch": 2.2, "learning_rate": 2.536338076286748e-06, "loss": 3.4056, "step": 1062500 }, { "epoch": 2.2, "learning_rate": 2.5356492942050004e-06, "loss": 3.4143, "step": 1063000 }, { "epoch": 2.2, "learning_rate": 2.5349605121232532e-06, "loss": 3.4121, "step": 1063500 }, { "epoch": 2.2, "learning_rate": 2.5342717300415056e-06, "loss": 3.404, "step": 1064000 }, { "epoch": 2.2, "learning_rate": 2.5335829479597585e-06, "loss": 3.4075, "step": 1064500 }, { "epoch": 2.2, "learning_rate": 2.532894165878011e-06, "loss": 3.4117, "step": 1065000 }, { "epoch": 2.2, "learning_rate": 2.5322053837962637e-06, "loss": 3.4105, "step": 1065500 }, { "epoch": 2.2, "learning_rate": 2.531516601714516e-06, "loss": 3.4169, "step": 1066000 }, { "epoch": 2.2, "learning_rate": 2.530827819632769e-06, "loss": 3.4138, "step": 1066500 }, { "epoch": 2.2, "learning_rate": 2.5301390375510214e-06, "loss": 3.4143, "step": 1067000 }, { "epoch": 2.21, "learning_rate": 2.5294502554692738e-06, "loss": 3.4083, "step": 1067500 }, { "epoch": 2.21, "learning_rate": 2.5287614733875266e-06, "loss": 3.4114, "step": 1068000 }, { "epoch": 2.21, "learning_rate": 2.528072691305779e-06, "loss": 3.4071, "step": 1068500 }, { "epoch": 2.21, "learning_rate": 2.527383909224032e-06, "loss": 3.4086, "step": 1069000 }, { "epoch": 2.21, "learning_rate": 2.5266951271422843e-06, "loss": 3.418, "step": 1069500 }, { "epoch": 2.21, "learning_rate": 2.526006345060537e-06, "loss": 3.4147, "step": 1070000 }, { "epoch": 2.21, "learning_rate": 2.5253175629787895e-06, "loss": 3.403, "step": 1070500 }, { "epoch": 2.21, "learning_rate": 2.524628780897042e-06, "loss": 3.407, "step": 1071000 }, { "epoch": 2.21, "learning_rate": 2.5239399988152948e-06, "loss": 3.4045, "step": 1071500 }, { "epoch": 2.22, "learning_rate": 2.523251216733547e-06, "loss": 3.4072, "step": 1072000 }, { "epoch": 2.22, "learning_rate": 2.5225624346518e-06, "loss": 3.4078, "step": 1072500 }, { "epoch": 2.22, "learning_rate": 2.5218736525700524e-06, "loss": 3.4098, "step": 1073000 }, { "epoch": 2.22, "learning_rate": 2.5211848704883052e-06, "loss": 3.414, "step": 1073500 }, { "epoch": 2.22, "learning_rate": 2.5204960884065577e-06, "loss": 3.4104, "step": 1074000 }, { "epoch": 2.22, "learning_rate": 2.5198073063248105e-06, "loss": 3.4094, "step": 1074500 }, { "epoch": 2.22, "learning_rate": 2.519118524243063e-06, "loss": 3.4083, "step": 1075000 }, { "epoch": 2.22, "learning_rate": 2.5184297421613153e-06, "loss": 3.4094, "step": 1075500 }, { "epoch": 2.22, "learning_rate": 2.517740960079568e-06, "loss": 3.4034, "step": 1076000 }, { "epoch": 2.22, "learning_rate": 2.5170521779978205e-06, "loss": 3.4106, "step": 1076500 }, { "epoch": 2.23, "learning_rate": 2.5163633959160734e-06, "loss": 3.4064, "step": 1077000 }, { "epoch": 2.23, "learning_rate": 2.515674613834326e-06, "loss": 3.4127, "step": 1077500 }, { "epoch": 2.23, "learning_rate": 2.5149858317525786e-06, "loss": 3.4094, "step": 1078000 }, { "epoch": 2.23, "learning_rate": 2.514297049670831e-06, "loss": 3.4142, "step": 1078500 }, { "epoch": 2.23, "learning_rate": 2.513608267589084e-06, "loss": 3.409, "step": 1079000 }, { "epoch": 2.23, "learning_rate": 2.5129194855073363e-06, "loss": 3.4107, "step": 1079500 }, { "epoch": 2.23, "learning_rate": 2.5122307034255887e-06, "loss": 3.4125, "step": 1080000 }, { "epoch": 2.23, "learning_rate": 2.5115419213438415e-06, "loss": 3.4105, "step": 1080500 }, { "epoch": 2.23, "learning_rate": 2.510853139262094e-06, "loss": 3.4096, "step": 1081000 }, { "epoch": 2.23, "learning_rate": 2.5101643571803468e-06, "loss": 3.4164, "step": 1081500 }, { "epoch": 2.24, "learning_rate": 2.509475575098599e-06, "loss": 3.4087, "step": 1082000 }, { "epoch": 2.24, "learning_rate": 2.508786793016852e-06, "loss": 3.4016, "step": 1082500 }, { "epoch": 2.24, "learning_rate": 2.508098010935104e-06, "loss": 3.4104, "step": 1083000 }, { "epoch": 2.24, "learning_rate": 2.5074092288533564e-06, "loss": 3.4073, "step": 1083500 }, { "epoch": 2.24, "learning_rate": 2.5067204467716092e-06, "loss": 3.406, "step": 1084000 }, { "epoch": 2.24, "learning_rate": 2.5060316646898616e-06, "loss": 3.4103, "step": 1084500 }, { "epoch": 2.24, "learning_rate": 2.5053428826081145e-06, "loss": 3.4115, "step": 1085000 }, { "epoch": 2.24, "learning_rate": 2.504654100526367e-06, "loss": 3.4138, "step": 1085500 }, { "epoch": 2.24, "learning_rate": 2.5039653184446197e-06, "loss": 3.4079, "step": 1086000 }, { "epoch": 2.25, "learning_rate": 2.503276536362872e-06, "loss": 3.4056, "step": 1086500 }, { "epoch": 2.25, "learning_rate": 2.502587754281125e-06, "loss": 3.4078, "step": 1087000 }, { "epoch": 2.25, "learning_rate": 2.5018989721993774e-06, "loss": 3.4079, "step": 1087500 }, { "epoch": 2.25, "learning_rate": 2.5012101901176298e-06, "loss": 3.4067, "step": 1088000 }, { "epoch": 2.25, "learning_rate": 2.5005214080358826e-06, "loss": 3.4084, "step": 1088500 }, { "epoch": 2.25, "learning_rate": 2.499832625954135e-06, "loss": 3.401, "step": 1089000 }, { "epoch": 2.25, "learning_rate": 2.499143843872388e-06, "loss": 3.4115, "step": 1089500 }, { "epoch": 2.25, "learning_rate": 2.4984550617906403e-06, "loss": 3.4063, "step": 1090000 }, { "epoch": 2.25, "learning_rate": 2.497766279708893e-06, "loss": 3.3982, "step": 1090500 }, { "epoch": 2.25, "learning_rate": 2.4970774976271455e-06, "loss": 3.4099, "step": 1091000 }, { "epoch": 2.26, "learning_rate": 2.496388715545398e-06, "loss": 3.405, "step": 1091500 }, { "epoch": 2.26, "learning_rate": 2.4956999334636508e-06, "loss": 3.3991, "step": 1092000 }, { "epoch": 2.26, "learning_rate": 2.495011151381903e-06, "loss": 3.4097, "step": 1092500 }, { "epoch": 2.26, "learning_rate": 2.494322369300156e-06, "loss": 3.407, "step": 1093000 }, { "epoch": 2.26, "learning_rate": 2.4936335872184084e-06, "loss": 3.4046, "step": 1093500 }, { "epoch": 2.26, "learning_rate": 2.4929448051366612e-06, "loss": 3.4037, "step": 1094000 }, { "epoch": 2.26, "learning_rate": 2.4922560230549137e-06, "loss": 3.4103, "step": 1094500 }, { "epoch": 2.26, "learning_rate": 2.4915672409731665e-06, "loss": 3.4066, "step": 1095000 }, { "epoch": 2.26, "learning_rate": 2.490878458891419e-06, "loss": 3.4116, "step": 1095500 }, { "epoch": 2.26, "learning_rate": 2.4901896768096713e-06, "loss": 3.4035, "step": 1096000 }, { "epoch": 2.27, "learning_rate": 2.489500894727924e-06, "loss": 3.4075, "step": 1096500 }, { "epoch": 2.27, "learning_rate": 2.4888121126461765e-06, "loss": 3.4074, "step": 1097000 }, { "epoch": 2.27, "learning_rate": 2.4881233305644294e-06, "loss": 3.4008, "step": 1097500 }, { "epoch": 2.27, "learning_rate": 2.487434548482682e-06, "loss": 3.4045, "step": 1098000 }, { "epoch": 2.27, "learning_rate": 2.4867457664009346e-06, "loss": 3.4015, "step": 1098500 }, { "epoch": 2.27, "learning_rate": 2.486056984319187e-06, "loss": 3.4095, "step": 1099000 }, { "epoch": 2.27, "learning_rate": 2.48536820223744e-06, "loss": 3.397, "step": 1099500 }, { "epoch": 2.27, "learning_rate": 2.4846794201556923e-06, "loss": 3.4014, "step": 1100000 }, { "epoch": 2.27, "learning_rate": 2.4839906380739447e-06, "loss": 3.4047, "step": 1100500 }, { "epoch": 2.28, "learning_rate": 2.4833018559921975e-06, "loss": 3.3986, "step": 1101000 }, { "epoch": 2.28, "learning_rate": 2.48261307391045e-06, "loss": 3.4026, "step": 1101500 }, { "epoch": 2.28, "learning_rate": 2.4819242918287028e-06, "loss": 3.4041, "step": 1102000 }, { "epoch": 2.28, "learning_rate": 2.481235509746955e-06, "loss": 3.4075, "step": 1102500 }, { "epoch": 2.28, "learning_rate": 2.480546727665208e-06, "loss": 3.4058, "step": 1103000 }, { "epoch": 2.28, "learning_rate": 2.4798579455834604e-06, "loss": 3.4069, "step": 1103500 }, { "epoch": 2.28, "learning_rate": 2.479169163501713e-06, "loss": 3.4075, "step": 1104000 }, { "epoch": 2.28, "learning_rate": 2.4784803814199657e-06, "loss": 3.3982, "step": 1104500 }, { "epoch": 2.28, "learning_rate": 2.477791599338218e-06, "loss": 3.4052, "step": 1105000 }, { "epoch": 2.28, "learning_rate": 2.477102817256471e-06, "loss": 3.3978, "step": 1105500 }, { "epoch": 2.29, "learning_rate": 2.4764140351747233e-06, "loss": 3.4024, "step": 1106000 }, { "epoch": 2.29, "learning_rate": 2.475725253092976e-06, "loss": 3.4011, "step": 1106500 }, { "epoch": 2.29, "learning_rate": 2.4750364710112286e-06, "loss": 3.4037, "step": 1107000 }, { "epoch": 2.29, "learning_rate": 2.4743476889294814e-06, "loss": 3.402, "step": 1107500 }, { "epoch": 2.29, "learning_rate": 2.473658906847734e-06, "loss": 3.4016, "step": 1108000 }, { "epoch": 2.29, "learning_rate": 2.4729701247659858e-06, "loss": 3.4024, "step": 1108500 }, { "epoch": 2.29, "learning_rate": 2.4722813426842386e-06, "loss": 3.4048, "step": 1109000 }, { "epoch": 2.29, "learning_rate": 2.471592560602491e-06, "loss": 3.4085, "step": 1109500 }, { "epoch": 2.29, "learning_rate": 2.470903778520744e-06, "loss": 3.4012, "step": 1110000 }, { "epoch": 2.29, "learning_rate": 2.4702149964389963e-06, "loss": 3.4045, "step": 1110500 }, { "epoch": 2.3, "learning_rate": 2.469526214357249e-06, "loss": 3.3987, "step": 1111000 }, { "epoch": 2.3, "learning_rate": 2.4688374322755015e-06, "loss": 3.4059, "step": 1111500 }, { "epoch": 2.3, "learning_rate": 2.468148650193754e-06, "loss": 3.4039, "step": 1112000 }, { "epoch": 2.3, "learning_rate": 2.4674598681120068e-06, "loss": 3.4066, "step": 1112500 }, { "epoch": 2.3, "learning_rate": 2.466771086030259e-06, "loss": 3.4052, "step": 1113000 }, { "epoch": 2.3, "learning_rate": 2.466082303948512e-06, "loss": 3.3978, "step": 1113500 }, { "epoch": 2.3, "learning_rate": 2.4653935218667644e-06, "loss": 3.4036, "step": 1114000 }, { "epoch": 2.3, "learning_rate": 2.4647047397850172e-06, "loss": 3.3994, "step": 1114500 }, { "epoch": 2.3, "learning_rate": 2.4640159577032697e-06, "loss": 3.4004, "step": 1115000 }, { "epoch": 2.31, "learning_rate": 2.4633271756215225e-06, "loss": 3.3948, "step": 1115500 }, { "epoch": 2.31, "learning_rate": 2.462638393539775e-06, "loss": 3.3951, "step": 1116000 }, { "epoch": 2.31, "learning_rate": 2.4619496114580273e-06, "loss": 3.3984, "step": 1116500 }, { "epoch": 2.31, "learning_rate": 2.46126082937628e-06, "loss": 3.4028, "step": 1117000 }, { "epoch": 2.31, "learning_rate": 2.4605720472945326e-06, "loss": 3.4012, "step": 1117500 }, { "epoch": 2.31, "learning_rate": 2.4598832652127854e-06, "loss": 3.4001, "step": 1118000 }, { "epoch": 2.31, "learning_rate": 2.459194483131038e-06, "loss": 3.3987, "step": 1118500 }, { "epoch": 2.31, "learning_rate": 2.4585057010492906e-06, "loss": 3.3983, "step": 1119000 }, { "epoch": 2.31, "learning_rate": 2.457816918967543e-06, "loss": 3.3976, "step": 1119500 }, { "epoch": 2.31, "learning_rate": 2.457128136885796e-06, "loss": 3.4055, "step": 1120000 }, { "epoch": 2.32, "learning_rate": 2.4564393548040483e-06, "loss": 3.3992, "step": 1120500 }, { "epoch": 2.32, "learning_rate": 2.4557505727223007e-06, "loss": 3.4058, "step": 1121000 }, { "epoch": 2.32, "learning_rate": 2.4550617906405535e-06, "loss": 3.4055, "step": 1121500 }, { "epoch": 2.32, "learning_rate": 2.454373008558806e-06, "loss": 3.4014, "step": 1122000 }, { "epoch": 2.32, "learning_rate": 2.4536842264770588e-06, "loss": 3.3943, "step": 1122500 }, { "epoch": 2.32, "learning_rate": 2.452995444395311e-06, "loss": 3.3989, "step": 1123000 }, { "epoch": 2.32, "learning_rate": 2.452306662313564e-06, "loss": 3.3989, "step": 1123500 }, { "epoch": 2.32, "learning_rate": 2.4516178802318164e-06, "loss": 3.3996, "step": 1124000 }, { "epoch": 2.32, "learning_rate": 2.450929098150069e-06, "loss": 3.3984, "step": 1124500 }, { "epoch": 2.32, "learning_rate": 2.4502403160683217e-06, "loss": 3.3999, "step": 1125000 }, { "epoch": 2.33, "learning_rate": 2.449551533986574e-06, "loss": 3.3996, "step": 1125500 }, { "epoch": 2.33, "learning_rate": 2.448862751904827e-06, "loss": 3.3999, "step": 1126000 }, { "epoch": 2.33, "learning_rate": 2.4481739698230793e-06, "loss": 3.3977, "step": 1126500 }, { "epoch": 2.33, "learning_rate": 2.447485187741332e-06, "loss": 3.3914, "step": 1127000 }, { "epoch": 2.33, "learning_rate": 2.4467964056595846e-06, "loss": 3.3999, "step": 1127500 }, { "epoch": 2.33, "learning_rate": 2.4461076235778374e-06, "loss": 3.4034, "step": 1128000 }, { "epoch": 2.33, "learning_rate": 2.44541884149609e-06, "loss": 3.3971, "step": 1128500 }, { "epoch": 2.33, "learning_rate": 2.444730059414342e-06, "loss": 3.3975, "step": 1129000 }, { "epoch": 2.33, "learning_rate": 2.444041277332595e-06, "loss": 3.3967, "step": 1129500 }, { "epoch": 2.33, "learning_rate": 2.4433524952508475e-06, "loss": 3.398, "step": 1130000 }, { "epoch": 2.34, "learning_rate": 2.4426637131691003e-06, "loss": 3.3946, "step": 1130500 }, { "epoch": 2.34, "learning_rate": 2.4419749310873527e-06, "loss": 3.3895, "step": 1131000 }, { "epoch": 2.34, "learning_rate": 2.4412861490056055e-06, "loss": 3.3992, "step": 1131500 }, { "epoch": 2.34, "learning_rate": 2.440597366923858e-06, "loss": 3.3978, "step": 1132000 }, { "epoch": 2.34, "learning_rate": 2.4399085848421103e-06, "loss": 3.3997, "step": 1132500 }, { "epoch": 2.34, "learning_rate": 2.439219802760363e-06, "loss": 3.4033, "step": 1133000 }, { "epoch": 2.34, "learning_rate": 2.438531020678615e-06, "loss": 3.3952, "step": 1133500 }, { "epoch": 2.34, "learning_rate": 2.4378422385968684e-06, "loss": 3.3954, "step": 1134000 }, { "epoch": 2.34, "learning_rate": 2.4371534565151204e-06, "loss": 3.3947, "step": 1134500 }, { "epoch": 2.35, "learning_rate": 2.4364646744333732e-06, "loss": 3.395, "step": 1135000 }, { "epoch": 2.35, "learning_rate": 2.4357758923516257e-06, "loss": 3.3955, "step": 1135500 }, { "epoch": 2.35, "learning_rate": 2.4350871102698785e-06, "loss": 3.3973, "step": 1136000 }, { "epoch": 2.35, "learning_rate": 2.434398328188131e-06, "loss": 3.3994, "step": 1136500 }, { "epoch": 2.35, "learning_rate": 2.4337095461063833e-06, "loss": 3.3942, "step": 1137000 }, { "epoch": 2.35, "learning_rate": 2.433020764024636e-06, "loss": 3.3949, "step": 1137500 }, { "epoch": 2.35, "learning_rate": 2.4323319819428886e-06, "loss": 3.3915, "step": 1138000 }, { "epoch": 2.35, "learning_rate": 2.4316431998611414e-06, "loss": 3.3991, "step": 1138500 }, { "epoch": 2.35, "learning_rate": 2.430954417779394e-06, "loss": 3.3945, "step": 1139000 }, { "epoch": 2.35, "learning_rate": 2.4302656356976466e-06, "loss": 3.4007, "step": 1139500 }, { "epoch": 2.36, "learning_rate": 2.429576853615899e-06, "loss": 3.3892, "step": 1140000 }, { "epoch": 2.36, "learning_rate": 2.428888071534152e-06, "loss": 3.3921, "step": 1140500 }, { "epoch": 2.36, "learning_rate": 2.4281992894524043e-06, "loss": 3.3931, "step": 1141000 }, { "epoch": 2.36, "learning_rate": 2.4275105073706567e-06, "loss": 3.3983, "step": 1141500 }, { "epoch": 2.36, "learning_rate": 2.4268217252889095e-06, "loss": 3.3968, "step": 1142000 }, { "epoch": 2.36, "learning_rate": 2.426132943207162e-06, "loss": 3.3976, "step": 1142500 }, { "epoch": 2.36, "learning_rate": 2.4254441611254148e-06, "loss": 3.3915, "step": 1143000 }, { "epoch": 2.36, "learning_rate": 2.424755379043667e-06, "loss": 3.395, "step": 1143500 }, { "epoch": 2.36, "learning_rate": 2.42406659696192e-06, "loss": 3.3982, "step": 1144000 }, { "epoch": 2.36, "learning_rate": 2.4233778148801724e-06, "loss": 3.3979, "step": 1144500 }, { "epoch": 2.37, "learning_rate": 2.422689032798425e-06, "loss": 3.3966, "step": 1145000 }, { "epoch": 2.37, "learning_rate": 2.4220002507166777e-06, "loss": 3.4032, "step": 1145500 }, { "epoch": 2.37, "learning_rate": 2.42131146863493e-06, "loss": 3.3949, "step": 1146000 }, { "epoch": 2.37, "learning_rate": 2.420622686553183e-06, "loss": 3.3946, "step": 1146500 }, { "epoch": 2.37, "learning_rate": 2.4199339044714353e-06, "loss": 3.3921, "step": 1147000 }, { "epoch": 2.37, "learning_rate": 2.419245122389688e-06, "loss": 3.3983, "step": 1147500 }, { "epoch": 2.37, "learning_rate": 2.4185563403079406e-06, "loss": 3.3929, "step": 1148000 }, { "epoch": 2.37, "learning_rate": 2.4178675582261934e-06, "loss": 3.3859, "step": 1148500 }, { "epoch": 2.37, "learning_rate": 2.417178776144446e-06, "loss": 3.3919, "step": 1149000 }, { "epoch": 2.38, "learning_rate": 2.4164899940626982e-06, "loss": 3.4002, "step": 1149500 }, { "epoch": 2.38, "learning_rate": 2.415801211980951e-06, "loss": 3.3976, "step": 1150000 }, { "epoch": 2.38, "learning_rate": 2.4151124298992035e-06, "loss": 3.3874, "step": 1150500 }, { "epoch": 2.38, "learning_rate": 2.4144236478174563e-06, "loss": 3.3962, "step": 1151000 }, { "epoch": 2.38, "learning_rate": 2.4137348657357087e-06, "loss": 3.3937, "step": 1151500 }, { "epoch": 2.38, "learning_rate": 2.4130460836539615e-06, "loss": 3.3928, "step": 1152000 }, { "epoch": 2.38, "learning_rate": 2.412357301572214e-06, "loss": 3.3954, "step": 1152500 }, { "epoch": 2.38, "learning_rate": 2.4116685194904668e-06, "loss": 3.3871, "step": 1153000 }, { "epoch": 2.38, "learning_rate": 2.410979737408719e-06, "loss": 3.3906, "step": 1153500 }, { "epoch": 2.38, "learning_rate": 2.4102909553269716e-06, "loss": 3.3995, "step": 1154000 }, { "epoch": 2.39, "learning_rate": 2.4096021732452244e-06, "loss": 3.3951, "step": 1154500 }, { "epoch": 2.39, "learning_rate": 2.408913391163477e-06, "loss": 3.3937, "step": 1155000 }, { "epoch": 2.39, "learning_rate": 2.4082246090817297e-06, "loss": 3.3915, "step": 1155500 }, { "epoch": 2.39, "learning_rate": 2.407535826999982e-06, "loss": 3.3941, "step": 1156000 }, { "epoch": 2.39, "learning_rate": 2.406847044918235e-06, "loss": 3.3921, "step": 1156500 }, { "epoch": 2.39, "learning_rate": 2.4061582628364873e-06, "loss": 3.3873, "step": 1157000 }, { "epoch": 2.39, "learning_rate": 2.4054694807547397e-06, "loss": 3.4035, "step": 1157500 }, { "epoch": 2.39, "learning_rate": 2.4047806986729926e-06, "loss": 3.3889, "step": 1158000 }, { "epoch": 2.39, "learning_rate": 2.404091916591245e-06, "loss": 3.3928, "step": 1158500 }, { "epoch": 2.39, "learning_rate": 2.403403134509498e-06, "loss": 3.3914, "step": 1159000 }, { "epoch": 2.4, "learning_rate": 2.40271435242775e-06, "loss": 3.3945, "step": 1159500 }, { "epoch": 2.4, "learning_rate": 2.4020255703460026e-06, "loss": 3.3919, "step": 1160000 }, { "epoch": 2.4, "learning_rate": 2.401336788264255e-06, "loss": 3.3873, "step": 1160500 }, { "epoch": 2.4, "learning_rate": 2.400648006182508e-06, "loss": 3.3912, "step": 1161000 }, { "epoch": 2.4, "learning_rate": 2.3999592241007603e-06, "loss": 3.3934, "step": 1161500 }, { "epoch": 2.4, "learning_rate": 2.3992704420190127e-06, "loss": 3.3929, "step": 1162000 }, { "epoch": 2.4, "learning_rate": 2.3985816599372655e-06, "loss": 3.3914, "step": 1162500 }, { "epoch": 2.4, "learning_rate": 2.397892877855518e-06, "loss": 3.3989, "step": 1163000 }, { "epoch": 2.4, "learning_rate": 2.3972040957737708e-06, "loss": 3.3964, "step": 1163500 }, { "epoch": 2.41, "learning_rate": 2.396515313692023e-06, "loss": 3.3948, "step": 1164000 }, { "epoch": 2.41, "learning_rate": 2.395826531610276e-06, "loss": 3.3908, "step": 1164500 }, { "epoch": 2.41, "learning_rate": 2.3951377495285284e-06, "loss": 3.3916, "step": 1165000 }, { "epoch": 2.41, "learning_rate": 2.394448967446781e-06, "loss": 3.3926, "step": 1165500 }, { "epoch": 2.41, "learning_rate": 2.3937601853650337e-06, "loss": 3.3849, "step": 1166000 }, { "epoch": 2.41, "learning_rate": 2.393071403283286e-06, "loss": 3.3982, "step": 1166500 }, { "epoch": 2.41, "learning_rate": 2.392382621201539e-06, "loss": 3.3957, "step": 1167000 }, { "epoch": 2.41, "learning_rate": 2.3916938391197913e-06, "loss": 3.3913, "step": 1167500 }, { "epoch": 2.41, "learning_rate": 2.391005057038044e-06, "loss": 3.3893, "step": 1168000 }, { "epoch": 2.41, "learning_rate": 2.3903162749562966e-06, "loss": 3.3896, "step": 1168500 }, { "epoch": 2.42, "learning_rate": 2.3896274928745494e-06, "loss": 3.3892, "step": 1169000 }, { "epoch": 2.42, "learning_rate": 2.388938710792802e-06, "loss": 3.3883, "step": 1169500 }, { "epoch": 2.42, "learning_rate": 2.3882499287110542e-06, "loss": 3.3893, "step": 1170000 }, { "epoch": 2.42, "learning_rate": 2.387561146629307e-06, "loss": 3.3891, "step": 1170500 }, { "epoch": 2.42, "learning_rate": 2.3868723645475595e-06, "loss": 3.3875, "step": 1171000 }, { "epoch": 2.42, "learning_rate": 2.3861835824658123e-06, "loss": 3.387, "step": 1171500 }, { "epoch": 2.42, "learning_rate": 2.3854948003840647e-06, "loss": 3.3912, "step": 1172000 }, { "epoch": 2.42, "learning_rate": 2.3848060183023175e-06, "loss": 3.3916, "step": 1172500 }, { "epoch": 2.42, "learning_rate": 2.38411723622057e-06, "loss": 3.39, "step": 1173000 }, { "epoch": 2.42, "learning_rate": 2.3834284541388228e-06, "loss": 3.3943, "step": 1173500 }, { "epoch": 2.43, "learning_rate": 2.382739672057075e-06, "loss": 3.3899, "step": 1174000 }, { "epoch": 2.43, "learning_rate": 2.3820508899753276e-06, "loss": 3.392, "step": 1174500 }, { "epoch": 2.43, "learning_rate": 2.3813621078935804e-06, "loss": 3.3928, "step": 1175000 }, { "epoch": 2.43, "learning_rate": 2.380673325811833e-06, "loss": 3.3882, "step": 1175500 }, { "epoch": 2.43, "learning_rate": 2.3799845437300857e-06, "loss": 3.3818, "step": 1176000 }, { "epoch": 2.43, "learning_rate": 2.379295761648338e-06, "loss": 3.3919, "step": 1176500 }, { "epoch": 2.43, "learning_rate": 2.378606979566591e-06, "loss": 3.3932, "step": 1177000 }, { "epoch": 2.43, "learning_rate": 2.3779181974848433e-06, "loss": 3.3914, "step": 1177500 }, { "epoch": 2.43, "learning_rate": 2.3772294154030957e-06, "loss": 3.385, "step": 1178000 }, { "epoch": 2.44, "learning_rate": 2.3765406333213486e-06, "loss": 3.3877, "step": 1178500 }, { "epoch": 2.44, "learning_rate": 2.375851851239601e-06, "loss": 3.3925, "step": 1179000 }, { "epoch": 2.44, "learning_rate": 2.375163069157854e-06, "loss": 3.3913, "step": 1179500 }, { "epoch": 2.44, "learning_rate": 2.3744742870761062e-06, "loss": 3.3831, "step": 1180000 }, { "epoch": 2.44, "learning_rate": 2.373785504994359e-06, "loss": 3.3927, "step": 1180500 }, { "epoch": 2.44, "learning_rate": 2.3730967229126115e-06, "loss": 3.3835, "step": 1181000 }, { "epoch": 2.44, "learning_rate": 2.3724079408308643e-06, "loss": 3.3857, "step": 1181500 }, { "epoch": 2.44, "learning_rate": 2.3717191587491167e-06, "loss": 3.389, "step": 1182000 }, { "epoch": 2.44, "learning_rate": 2.371030376667369e-06, "loss": 3.3871, "step": 1182500 }, { "epoch": 2.44, "learning_rate": 2.370341594585622e-06, "loss": 3.3857, "step": 1183000 }, { "epoch": 2.45, "learning_rate": 2.3696528125038744e-06, "loss": 3.389, "step": 1183500 }, { "epoch": 2.45, "learning_rate": 2.368964030422127e-06, "loss": 3.3816, "step": 1184000 }, { "epoch": 2.45, "learning_rate": 2.3682752483403796e-06, "loss": 3.388, "step": 1184500 }, { "epoch": 2.45, "learning_rate": 2.3675864662586324e-06, "loss": 3.3831, "step": 1185000 }, { "epoch": 2.45, "learning_rate": 2.3668976841768844e-06, "loss": 3.3918, "step": 1185500 }, { "epoch": 2.45, "learning_rate": 2.366208902095137e-06, "loss": 3.3897, "step": 1186000 }, { "epoch": 2.45, "learning_rate": 2.3655201200133897e-06, "loss": 3.3901, "step": 1186500 }, { "epoch": 2.45, "learning_rate": 2.364831337931642e-06, "loss": 3.3911, "step": 1187000 }, { "epoch": 2.45, "learning_rate": 2.364142555849895e-06, "loss": 3.3837, "step": 1187500 }, { "epoch": 2.45, "learning_rate": 2.3634537737681473e-06, "loss": 3.3888, "step": 1188000 }, { "epoch": 2.46, "learning_rate": 2.3627649916864e-06, "loss": 3.393, "step": 1188500 }, { "epoch": 2.46, "learning_rate": 2.3620762096046526e-06, "loss": 3.3851, "step": 1189000 }, { "epoch": 2.46, "learning_rate": 2.3613874275229054e-06, "loss": 3.3858, "step": 1189500 }, { "epoch": 2.46, "learning_rate": 2.360698645441158e-06, "loss": 3.3959, "step": 1190000 }, { "epoch": 2.46, "learning_rate": 2.3600098633594102e-06, "loss": 3.384, "step": 1190500 }, { "epoch": 2.46, "learning_rate": 2.359321081277663e-06, "loss": 3.3806, "step": 1191000 }, { "epoch": 2.46, "learning_rate": 2.3586322991959155e-06, "loss": 3.3776, "step": 1191500 }, { "epoch": 2.46, "learning_rate": 2.3579435171141683e-06, "loss": 3.389, "step": 1192000 }, { "epoch": 2.46, "learning_rate": 2.3572547350324207e-06, "loss": 3.3852, "step": 1192500 }, { "epoch": 2.47, "learning_rate": 2.3565659529506735e-06, "loss": 3.3808, "step": 1193000 }, { "epoch": 2.47, "learning_rate": 2.355877170868926e-06, "loss": 3.3845, "step": 1193500 }, { "epoch": 2.47, "learning_rate": 2.3551883887871788e-06, "loss": 3.3793, "step": 1194000 }, { "epoch": 2.47, "learning_rate": 2.354499606705431e-06, "loss": 3.3829, "step": 1194500 }, { "epoch": 2.47, "learning_rate": 2.3538108246236836e-06, "loss": 3.3814, "step": 1195000 }, { "epoch": 2.47, "learning_rate": 2.3531220425419364e-06, "loss": 3.3832, "step": 1195500 }, { "epoch": 2.47, "learning_rate": 2.352433260460189e-06, "loss": 3.3844, "step": 1196000 }, { "epoch": 2.47, "learning_rate": 2.3517444783784417e-06, "loss": 3.3893, "step": 1196500 }, { "epoch": 2.47, "learning_rate": 2.351055696296694e-06, "loss": 3.3802, "step": 1197000 }, { "epoch": 2.47, "learning_rate": 2.350366914214947e-06, "loss": 3.3869, "step": 1197500 }, { "epoch": 2.48, "learning_rate": 2.3496781321331993e-06, "loss": 3.3884, "step": 1198000 }, { "epoch": 2.48, "learning_rate": 2.3489893500514517e-06, "loss": 3.3895, "step": 1198500 }, { "epoch": 2.48, "learning_rate": 2.3483005679697046e-06, "loss": 3.3863, "step": 1199000 }, { "epoch": 2.48, "learning_rate": 2.347611785887957e-06, "loss": 3.3822, "step": 1199500 }, { "epoch": 2.48, "learning_rate": 2.34692300380621e-06, "loss": 3.385, "step": 1200000 }, { "epoch": 2.48, "learning_rate": 2.3462342217244622e-06, "loss": 3.3844, "step": 1200500 }, { "epoch": 2.48, "learning_rate": 2.345545439642715e-06, "loss": 3.3817, "step": 1201000 }, { "epoch": 2.48, "learning_rate": 2.3448566575609675e-06, "loss": 3.388, "step": 1201500 }, { "epoch": 2.48, "learning_rate": 2.3441678754792203e-06, "loss": 3.3883, "step": 1202000 }, { "epoch": 2.48, "learning_rate": 2.3434790933974727e-06, "loss": 3.3875, "step": 1202500 }, { "epoch": 2.49, "learning_rate": 2.342790311315725e-06, "loss": 3.3878, "step": 1203000 }, { "epoch": 2.49, "learning_rate": 2.342101529233978e-06, "loss": 3.3874, "step": 1203500 }, { "epoch": 2.49, "learning_rate": 2.3414127471522304e-06, "loss": 3.3744, "step": 1204000 }, { "epoch": 2.49, "learning_rate": 2.340723965070483e-06, "loss": 3.372, "step": 1204500 }, { "epoch": 2.49, "learning_rate": 2.3400351829887356e-06, "loss": 3.379, "step": 1205000 }, { "epoch": 2.49, "learning_rate": 2.3393464009069884e-06, "loss": 3.3746, "step": 1205500 }, { "epoch": 2.49, "learning_rate": 2.338657618825241e-06, "loss": 3.3822, "step": 1206000 }, { "epoch": 2.49, "learning_rate": 2.3379688367434933e-06, "loss": 3.3778, "step": 1206500 }, { "epoch": 2.49, "learning_rate": 2.337280054661746e-06, "loss": 3.378, "step": 1207000 }, { "epoch": 2.5, "learning_rate": 2.3365912725799985e-06, "loss": 3.3852, "step": 1207500 }, { "epoch": 2.5, "learning_rate": 2.3359024904982513e-06, "loss": 3.3809, "step": 1208000 }, { "epoch": 2.5, "learning_rate": 2.3352137084165037e-06, "loss": 3.3784, "step": 1208500 }, { "epoch": 2.5, "learning_rate": 2.3345249263347566e-06, "loss": 3.3813, "step": 1209000 }, { "epoch": 2.5, "learning_rate": 2.333836144253009e-06, "loss": 3.383, "step": 1209500 }, { "epoch": 2.5, "learning_rate": 2.333147362171262e-06, "loss": 3.3785, "step": 1210000 }, { "epoch": 2.5, "learning_rate": 2.332458580089514e-06, "loss": 3.3868, "step": 1210500 }, { "epoch": 2.5, "learning_rate": 2.3317697980077662e-06, "loss": 3.3789, "step": 1211000 }, { "epoch": 2.5, "learning_rate": 2.331081015926019e-06, "loss": 3.3787, "step": 1211500 }, { "epoch": 2.5, "learning_rate": 2.3303922338442715e-06, "loss": 3.3804, "step": 1212000 }, { "epoch": 2.51, "learning_rate": 2.3297034517625243e-06, "loss": 3.3838, "step": 1212500 }, { "epoch": 2.51, "learning_rate": 2.3290146696807767e-06, "loss": 3.3801, "step": 1213000 }, { "epoch": 2.51, "learning_rate": 2.3283258875990295e-06, "loss": 3.3762, "step": 1213500 }, { "epoch": 2.51, "learning_rate": 2.327637105517282e-06, "loss": 3.3756, "step": 1214000 }, { "epoch": 2.51, "learning_rate": 2.3269483234355348e-06, "loss": 3.3845, "step": 1214500 }, { "epoch": 2.51, "learning_rate": 2.326259541353787e-06, "loss": 3.3814, "step": 1215000 }, { "epoch": 2.51, "learning_rate": 2.3255707592720396e-06, "loss": 3.3833, "step": 1215500 }, { "epoch": 2.51, "learning_rate": 2.3248819771902924e-06, "loss": 3.3831, "step": 1216000 }, { "epoch": 2.51, "learning_rate": 2.324193195108545e-06, "loss": 3.38, "step": 1216500 }, { "epoch": 2.51, "learning_rate": 2.3235044130267977e-06, "loss": 3.3813, "step": 1217000 }, { "epoch": 2.52, "learning_rate": 2.32281563094505e-06, "loss": 3.3836, "step": 1217500 }, { "epoch": 2.52, "learning_rate": 2.322126848863303e-06, "loss": 3.375, "step": 1218000 }, { "epoch": 2.52, "learning_rate": 2.3214380667815553e-06, "loss": 3.3791, "step": 1218500 }, { "epoch": 2.52, "learning_rate": 2.3207492846998077e-06, "loss": 3.3833, "step": 1219000 }, { "epoch": 2.52, "learning_rate": 2.3200605026180606e-06, "loss": 3.38, "step": 1219500 }, { "epoch": 2.52, "learning_rate": 2.319371720536313e-06, "loss": 3.3815, "step": 1220000 }, { "epoch": 2.52, "learning_rate": 2.318682938454566e-06, "loss": 3.3836, "step": 1220500 }, { "epoch": 2.52, "learning_rate": 2.3179941563728182e-06, "loss": 3.3783, "step": 1221000 }, { "epoch": 2.52, "learning_rate": 2.317305374291071e-06, "loss": 3.3754, "step": 1221500 }, { "epoch": 2.53, "learning_rate": 2.3166165922093235e-06, "loss": 3.3754, "step": 1222000 }, { "epoch": 2.53, "learning_rate": 2.3159278101275763e-06, "loss": 3.3757, "step": 1222500 }, { "epoch": 2.53, "learning_rate": 2.3152390280458287e-06, "loss": 3.3834, "step": 1223000 }, { "epoch": 2.53, "learning_rate": 2.314550245964081e-06, "loss": 3.3798, "step": 1223500 }, { "epoch": 2.53, "learning_rate": 2.313861463882334e-06, "loss": 3.3829, "step": 1224000 }, { "epoch": 2.53, "learning_rate": 2.3131726818005864e-06, "loss": 3.3792, "step": 1224500 }, { "epoch": 2.53, "learning_rate": 2.312483899718839e-06, "loss": 3.3787, "step": 1225000 }, { "epoch": 2.53, "learning_rate": 2.3117951176370916e-06, "loss": 3.3795, "step": 1225500 }, { "epoch": 2.53, "learning_rate": 2.3111063355553444e-06, "loss": 3.3788, "step": 1226000 }, { "epoch": 2.53, "learning_rate": 2.310417553473597e-06, "loss": 3.377, "step": 1226500 }, { "epoch": 2.54, "learning_rate": 2.3097287713918493e-06, "loss": 3.3767, "step": 1227000 }, { "epoch": 2.54, "learning_rate": 2.309039989310102e-06, "loss": 3.3812, "step": 1227500 }, { "epoch": 2.54, "learning_rate": 2.3083512072283545e-06, "loss": 3.3785, "step": 1228000 }, { "epoch": 2.54, "learning_rate": 2.3076624251466073e-06, "loss": 3.3797, "step": 1228500 }, { "epoch": 2.54, "learning_rate": 2.3069736430648597e-06, "loss": 3.3756, "step": 1229000 }, { "epoch": 2.54, "learning_rate": 2.3062848609831126e-06, "loss": 3.3756, "step": 1229500 }, { "epoch": 2.54, "learning_rate": 2.305596078901365e-06, "loss": 3.378, "step": 1230000 }, { "epoch": 2.54, "learning_rate": 2.304907296819618e-06, "loss": 3.3716, "step": 1230500 }, { "epoch": 2.54, "learning_rate": 2.3042185147378702e-06, "loss": 3.3788, "step": 1231000 }, { "epoch": 2.54, "learning_rate": 2.3035297326561226e-06, "loss": 3.3754, "step": 1231500 }, { "epoch": 2.55, "learning_rate": 2.3028409505743755e-06, "loss": 3.3758, "step": 1232000 }, { "epoch": 2.55, "learning_rate": 2.302152168492628e-06, "loss": 3.3799, "step": 1232500 }, { "epoch": 2.55, "learning_rate": 2.3014633864108807e-06, "loss": 3.3848, "step": 1233000 }, { "epoch": 2.55, "learning_rate": 2.300774604329133e-06, "loss": 3.3729, "step": 1233500 }, { "epoch": 2.55, "learning_rate": 2.300085822247386e-06, "loss": 3.3752, "step": 1234000 }, { "epoch": 2.55, "learning_rate": 2.2993970401656384e-06, "loss": 3.3765, "step": 1234500 }, { "epoch": 2.55, "learning_rate": 2.298708258083891e-06, "loss": 3.3769, "step": 1235000 }, { "epoch": 2.55, "learning_rate": 2.2980194760021436e-06, "loss": 3.3752, "step": 1235500 }, { "epoch": 2.55, "learning_rate": 2.2973306939203956e-06, "loss": 3.3743, "step": 1236000 }, { "epoch": 2.56, "learning_rate": 2.2966419118386484e-06, "loss": 3.3707, "step": 1236500 }, { "epoch": 2.56, "learning_rate": 2.295953129756901e-06, "loss": 3.3723, "step": 1237000 }, { "epoch": 2.56, "learning_rate": 2.2952643476751537e-06, "loss": 3.3748, "step": 1237500 }, { "epoch": 2.56, "learning_rate": 2.294575565593406e-06, "loss": 3.3775, "step": 1238000 }, { "epoch": 2.56, "learning_rate": 2.293886783511659e-06, "loss": 3.3834, "step": 1238500 }, { "epoch": 2.56, "learning_rate": 2.2931980014299113e-06, "loss": 3.3765, "step": 1239000 }, { "epoch": 2.56, "learning_rate": 2.2925092193481637e-06, "loss": 3.379, "step": 1239500 }, { "epoch": 2.56, "learning_rate": 2.2918204372664166e-06, "loss": 3.3767, "step": 1240000 }, { "epoch": 2.56, "learning_rate": 2.291131655184669e-06, "loss": 3.3767, "step": 1240500 }, { "epoch": 2.56, "learning_rate": 2.290442873102922e-06, "loss": 3.376, "step": 1241000 }, { "epoch": 2.57, "learning_rate": 2.2897540910211742e-06, "loss": 3.3817, "step": 1241500 }, { "epoch": 2.57, "learning_rate": 2.289065308939427e-06, "loss": 3.3697, "step": 1242000 }, { "epoch": 2.57, "learning_rate": 2.2883765268576795e-06, "loss": 3.3757, "step": 1242500 }, { "epoch": 2.57, "learning_rate": 2.2876877447759323e-06, "loss": 3.3701, "step": 1243000 }, { "epoch": 2.57, "learning_rate": 2.2869989626941847e-06, "loss": 3.3798, "step": 1243500 }, { "epoch": 2.57, "learning_rate": 2.286310180612437e-06, "loss": 3.3705, "step": 1244000 }, { "epoch": 2.57, "learning_rate": 2.28562139853069e-06, "loss": 3.3768, "step": 1244500 }, { "epoch": 2.57, "learning_rate": 2.2849326164489424e-06, "loss": 3.3733, "step": 1245000 }, { "epoch": 2.57, "learning_rate": 2.284243834367195e-06, "loss": 3.378, "step": 1245500 }, { "epoch": 2.57, "learning_rate": 2.2835550522854476e-06, "loss": 3.3657, "step": 1246000 }, { "epoch": 2.58, "learning_rate": 2.2828662702037004e-06, "loss": 3.375, "step": 1246500 }, { "epoch": 2.58, "learning_rate": 2.282177488121953e-06, "loss": 3.3858, "step": 1247000 }, { "epoch": 2.58, "learning_rate": 2.2814887060402053e-06, "loss": 3.3683, "step": 1247500 }, { "epoch": 2.58, "learning_rate": 2.280799923958458e-06, "loss": 3.3745, "step": 1248000 }, { "epoch": 2.58, "learning_rate": 2.2801111418767105e-06, "loss": 3.3718, "step": 1248500 }, { "epoch": 2.58, "learning_rate": 2.2794223597949633e-06, "loss": 3.3712, "step": 1249000 }, { "epoch": 2.58, "learning_rate": 2.2787335777132157e-06, "loss": 3.3741, "step": 1249500 }, { "epoch": 2.58, "learning_rate": 2.2780447956314686e-06, "loss": 3.3755, "step": 1250000 }, { "epoch": 2.58, "learning_rate": 2.277356013549721e-06, "loss": 3.3731, "step": 1250500 }, { "epoch": 2.58, "learning_rate": 2.276667231467974e-06, "loss": 3.3699, "step": 1251000 }, { "epoch": 2.59, "learning_rate": 2.2759784493862262e-06, "loss": 3.3805, "step": 1251500 }, { "epoch": 2.59, "learning_rate": 2.2752896673044786e-06, "loss": 3.3653, "step": 1252000 }, { "epoch": 2.59, "learning_rate": 2.2746008852227315e-06, "loss": 3.3733, "step": 1252500 }, { "epoch": 2.59, "learning_rate": 2.273912103140984e-06, "loss": 3.374, "step": 1253000 }, { "epoch": 2.59, "learning_rate": 2.2732233210592367e-06, "loss": 3.3681, "step": 1253500 }, { "epoch": 2.59, "learning_rate": 2.272534538977489e-06, "loss": 3.3781, "step": 1254000 }, { "epoch": 2.59, "learning_rate": 2.271845756895742e-06, "loss": 3.3721, "step": 1254500 }, { "epoch": 2.59, "learning_rate": 2.2711569748139944e-06, "loss": 3.3718, "step": 1255000 }, { "epoch": 2.59, "learning_rate": 2.270468192732247e-06, "loss": 3.3653, "step": 1255500 }, { "epoch": 2.6, "learning_rate": 2.2697794106504996e-06, "loss": 3.3691, "step": 1256000 }, { "epoch": 2.6, "learning_rate": 2.269090628568752e-06, "loss": 3.3683, "step": 1256500 }, { "epoch": 2.6, "learning_rate": 2.268401846487005e-06, "loss": 3.3688, "step": 1257000 }, { "epoch": 2.6, "learning_rate": 2.2677130644052573e-06, "loss": 3.3707, "step": 1257500 }, { "epoch": 2.6, "learning_rate": 2.26702428232351e-06, "loss": 3.3657, "step": 1258000 }, { "epoch": 2.6, "learning_rate": 2.2663355002417625e-06, "loss": 3.3748, "step": 1258500 }, { "epoch": 2.6, "learning_rate": 2.2656467181600153e-06, "loss": 3.377, "step": 1259000 }, { "epoch": 2.6, "learning_rate": 2.2649579360782678e-06, "loss": 3.3756, "step": 1259500 }, { "epoch": 2.6, "learning_rate": 2.26426915399652e-06, "loss": 3.3661, "step": 1260000 }, { "epoch": 2.6, "learning_rate": 2.263580371914773e-06, "loss": 3.3702, "step": 1260500 }, { "epoch": 2.61, "learning_rate": 2.262891589833025e-06, "loss": 3.3711, "step": 1261000 }, { "epoch": 2.61, "learning_rate": 2.2622028077512782e-06, "loss": 3.3748, "step": 1261500 }, { "epoch": 2.61, "learning_rate": 2.2615140256695302e-06, "loss": 3.3725, "step": 1262000 }, { "epoch": 2.61, "learning_rate": 2.260825243587783e-06, "loss": 3.3685, "step": 1262500 }, { "epoch": 2.61, "learning_rate": 2.2601364615060355e-06, "loss": 3.3753, "step": 1263000 }, { "epoch": 2.61, "learning_rate": 2.2594476794242883e-06, "loss": 3.3695, "step": 1263500 }, { "epoch": 2.61, "learning_rate": 2.2587588973425407e-06, "loss": 3.3704, "step": 1264000 }, { "epoch": 2.61, "learning_rate": 2.258070115260793e-06, "loss": 3.3695, "step": 1264500 }, { "epoch": 2.61, "learning_rate": 2.257381333179046e-06, "loss": 3.3699, "step": 1265000 }, { "epoch": 2.61, "learning_rate": 2.2566925510972984e-06, "loss": 3.3724, "step": 1265500 }, { "epoch": 2.62, "learning_rate": 2.256003769015551e-06, "loss": 3.3727, "step": 1266000 }, { "epoch": 2.62, "learning_rate": 2.2553149869338036e-06, "loss": 3.3701, "step": 1266500 }, { "epoch": 2.62, "learning_rate": 2.2546262048520564e-06, "loss": 3.3688, "step": 1267000 }, { "epoch": 2.62, "learning_rate": 2.253937422770309e-06, "loss": 3.3742, "step": 1267500 }, { "epoch": 2.62, "learning_rate": 2.2532486406885613e-06, "loss": 3.3651, "step": 1268000 }, { "epoch": 2.62, "learning_rate": 2.252559858606814e-06, "loss": 3.3731, "step": 1268500 }, { "epoch": 2.62, "learning_rate": 2.2518710765250665e-06, "loss": 3.3645, "step": 1269000 }, { "epoch": 2.62, "learning_rate": 2.2511822944433193e-06, "loss": 3.3749, "step": 1269500 }, { "epoch": 2.62, "learning_rate": 2.2504935123615717e-06, "loss": 3.371, "step": 1270000 }, { "epoch": 2.63, "learning_rate": 2.2498047302798246e-06, "loss": 3.3601, "step": 1270500 }, { "epoch": 2.63, "learning_rate": 2.249115948198077e-06, "loss": 3.361, "step": 1271000 }, { "epoch": 2.63, "learning_rate": 2.24842716611633e-06, "loss": 3.3766, "step": 1271500 }, { "epoch": 2.63, "learning_rate": 2.2477383840345822e-06, "loss": 3.3717, "step": 1272000 }, { "epoch": 2.63, "learning_rate": 2.2470496019528346e-06, "loss": 3.3678, "step": 1272500 }, { "epoch": 2.63, "learning_rate": 2.2463608198710875e-06, "loss": 3.3657, "step": 1273000 }, { "epoch": 2.63, "learning_rate": 2.24567203778934e-06, "loss": 3.3639, "step": 1273500 }, { "epoch": 2.63, "learning_rate": 2.2449832557075927e-06, "loss": 3.3712, "step": 1274000 }, { "epoch": 2.63, "learning_rate": 2.244294473625845e-06, "loss": 3.3651, "step": 1274500 }, { "epoch": 2.63, "learning_rate": 2.243605691544098e-06, "loss": 3.3717, "step": 1275000 }, { "epoch": 2.64, "learning_rate": 2.2429169094623504e-06, "loss": 3.3636, "step": 1275500 }, { "epoch": 2.64, "learning_rate": 2.242228127380603e-06, "loss": 3.3699, "step": 1276000 }, { "epoch": 2.64, "learning_rate": 2.2415393452988556e-06, "loss": 3.3635, "step": 1276500 }, { "epoch": 2.64, "learning_rate": 2.240850563217108e-06, "loss": 3.3656, "step": 1277000 }, { "epoch": 2.64, "learning_rate": 2.240161781135361e-06, "loss": 3.3739, "step": 1277500 }, { "epoch": 2.64, "learning_rate": 2.2394729990536133e-06, "loss": 3.3696, "step": 1278000 }, { "epoch": 2.64, "learning_rate": 2.238784216971866e-06, "loss": 3.3713, "step": 1278500 }, { "epoch": 2.64, "learning_rate": 2.2380954348901185e-06, "loss": 3.3656, "step": 1279000 }, { "epoch": 2.64, "learning_rate": 2.2374066528083713e-06, "loss": 3.3637, "step": 1279500 }, { "epoch": 2.64, "learning_rate": 2.2367178707266238e-06, "loss": 3.3672, "step": 1280000 }, { "epoch": 2.65, "learning_rate": 2.236029088644876e-06, "loss": 3.3656, "step": 1280500 }, { "epoch": 2.65, "learning_rate": 2.235340306563129e-06, "loss": 3.3721, "step": 1281000 }, { "epoch": 2.65, "learning_rate": 2.2346515244813814e-06, "loss": 3.3735, "step": 1281500 }, { "epoch": 2.65, "learning_rate": 2.2339627423996342e-06, "loss": 3.3732, "step": 1282000 }, { "epoch": 2.65, "learning_rate": 2.2332739603178867e-06, "loss": 3.3743, "step": 1282500 }, { "epoch": 2.65, "learning_rate": 2.2325851782361395e-06, "loss": 3.3696, "step": 1283000 }, { "epoch": 2.65, "learning_rate": 2.231896396154392e-06, "loss": 3.3651, "step": 1283500 }, { "epoch": 2.65, "learning_rate": 2.2312076140726447e-06, "loss": 3.3671, "step": 1284000 }, { "epoch": 2.65, "learning_rate": 2.230518831990897e-06, "loss": 3.3667, "step": 1284500 }, { "epoch": 2.66, "learning_rate": 2.2298300499091495e-06, "loss": 3.3636, "step": 1285000 }, { "epoch": 2.66, "learning_rate": 2.2291412678274024e-06, "loss": 3.3704, "step": 1285500 }, { "epoch": 2.66, "learning_rate": 2.228452485745655e-06, "loss": 3.3687, "step": 1286000 }, { "epoch": 2.66, "learning_rate": 2.2277637036639076e-06, "loss": 3.3632, "step": 1286500 }, { "epoch": 2.66, "learning_rate": 2.2270749215821596e-06, "loss": 3.3705, "step": 1287000 }, { "epoch": 2.66, "learning_rate": 2.2263861395004124e-06, "loss": 3.3699, "step": 1287500 }, { "epoch": 2.66, "learning_rate": 2.225697357418665e-06, "loss": 3.3719, "step": 1288000 }, { "epoch": 2.66, "learning_rate": 2.2250085753369173e-06, "loss": 3.3669, "step": 1288500 }, { "epoch": 2.66, "learning_rate": 2.22431979325517e-06, "loss": 3.3708, "step": 1289000 }, { "epoch": 2.66, "learning_rate": 2.2236310111734225e-06, "loss": 3.3618, "step": 1289500 }, { "epoch": 2.67, "learning_rate": 2.2229422290916753e-06, "loss": 3.3708, "step": 1290000 }, { "epoch": 2.67, "learning_rate": 2.2222534470099277e-06, "loss": 3.3697, "step": 1290500 }, { "epoch": 2.67, "learning_rate": 2.2215646649281806e-06, "loss": 3.3686, "step": 1291000 }, { "epoch": 2.67, "learning_rate": 2.220875882846433e-06, "loss": 3.3695, "step": 1291500 }, { "epoch": 2.67, "learning_rate": 2.220187100764686e-06, "loss": 3.3656, "step": 1292000 }, { "epoch": 2.67, "learning_rate": 2.2194983186829382e-06, "loss": 3.3732, "step": 1292500 }, { "epoch": 2.67, "learning_rate": 2.2188095366011906e-06, "loss": 3.3664, "step": 1293000 }, { "epoch": 2.67, "learning_rate": 2.2181207545194435e-06, "loss": 3.3684, "step": 1293500 }, { "epoch": 2.67, "learning_rate": 2.217431972437696e-06, "loss": 3.3656, "step": 1294000 }, { "epoch": 2.67, "learning_rate": 2.2167431903559487e-06, "loss": 3.3644, "step": 1294500 }, { "epoch": 2.68, "learning_rate": 2.216054408274201e-06, "loss": 3.3634, "step": 1295000 }, { "epoch": 2.68, "learning_rate": 2.215365626192454e-06, "loss": 3.3657, "step": 1295500 }, { "epoch": 2.68, "learning_rate": 2.2146768441107064e-06, "loss": 3.3602, "step": 1296000 }, { "epoch": 2.68, "learning_rate": 2.213988062028959e-06, "loss": 3.3632, "step": 1296500 }, { "epoch": 2.68, "learning_rate": 2.2132992799472116e-06, "loss": 3.3655, "step": 1297000 }, { "epoch": 2.68, "learning_rate": 2.212610497865464e-06, "loss": 3.361, "step": 1297500 }, { "epoch": 2.68, "learning_rate": 2.211921715783717e-06, "loss": 3.3699, "step": 1298000 }, { "epoch": 2.68, "learning_rate": 2.2112329337019693e-06, "loss": 3.3676, "step": 1298500 }, { "epoch": 2.68, "learning_rate": 2.210544151620222e-06, "loss": 3.3651, "step": 1299000 }, { "epoch": 2.69, "learning_rate": 2.2098553695384745e-06, "loss": 3.3629, "step": 1299500 }, { "epoch": 2.69, "learning_rate": 2.2091665874567273e-06, "loss": 3.3603, "step": 1300000 }, { "epoch": 2.69, "learning_rate": 2.2084778053749798e-06, "loss": 3.3611, "step": 1300500 }, { "epoch": 2.69, "learning_rate": 2.207789023293232e-06, "loss": 3.3582, "step": 1301000 }, { "epoch": 2.69, "learning_rate": 2.207100241211485e-06, "loss": 3.3632, "step": 1301500 }, { "epoch": 2.69, "learning_rate": 2.2064114591297374e-06, "loss": 3.3713, "step": 1302000 }, { "epoch": 2.69, "learning_rate": 2.2057226770479902e-06, "loss": 3.3576, "step": 1302500 }, { "epoch": 2.69, "learning_rate": 2.2050338949662427e-06, "loss": 3.3639, "step": 1303000 }, { "epoch": 2.69, "learning_rate": 2.2043451128844955e-06, "loss": 3.3629, "step": 1303500 }, { "epoch": 2.69, "learning_rate": 2.203656330802748e-06, "loss": 3.3641, "step": 1304000 }, { "epoch": 2.7, "learning_rate": 2.2029675487210007e-06, "loss": 3.3659, "step": 1304500 }, { "epoch": 2.7, "learning_rate": 2.202278766639253e-06, "loss": 3.3616, "step": 1305000 }, { "epoch": 2.7, "learning_rate": 2.2015899845575055e-06, "loss": 3.3681, "step": 1305500 }, { "epoch": 2.7, "learning_rate": 2.2009012024757584e-06, "loss": 3.363, "step": 1306000 }, { "epoch": 2.7, "learning_rate": 2.200212420394011e-06, "loss": 3.3697, "step": 1306500 }, { "epoch": 2.7, "learning_rate": 2.1995236383122636e-06, "loss": 3.364, "step": 1307000 }, { "epoch": 2.7, "learning_rate": 2.198834856230516e-06, "loss": 3.361, "step": 1307500 }, { "epoch": 2.7, "learning_rate": 2.198146074148769e-06, "loss": 3.3624, "step": 1308000 }, { "epoch": 2.7, "learning_rate": 2.1974572920670213e-06, "loss": 3.3676, "step": 1308500 }, { "epoch": 2.7, "learning_rate": 2.1967685099852737e-06, "loss": 3.3628, "step": 1309000 }, { "epoch": 2.71, "learning_rate": 2.1960797279035265e-06, "loss": 3.3639, "step": 1309500 }, { "epoch": 2.71, "learning_rate": 2.195390945821779e-06, "loss": 3.3664, "step": 1310000 }, { "epoch": 2.71, "learning_rate": 2.1947021637400318e-06, "loss": 3.3651, "step": 1310500 }, { "epoch": 2.71, "learning_rate": 2.194013381658284e-06, "loss": 3.361, "step": 1311000 }, { "epoch": 2.71, "learning_rate": 2.193324599576537e-06, "loss": 3.3563, "step": 1311500 }, { "epoch": 2.71, "learning_rate": 2.1926358174947894e-06, "loss": 3.3627, "step": 1312000 }, { "epoch": 2.71, "learning_rate": 2.1919470354130423e-06, "loss": 3.3594, "step": 1312500 }, { "epoch": 2.71, "learning_rate": 2.1912582533312942e-06, "loss": 3.3649, "step": 1313000 }, { "epoch": 2.71, "learning_rate": 2.1905694712495466e-06, "loss": 3.3612, "step": 1313500 }, { "epoch": 2.72, "learning_rate": 2.1898806891677995e-06, "loss": 3.3652, "step": 1314000 }, { "epoch": 2.72, "learning_rate": 2.189191907086052e-06, "loss": 3.3555, "step": 1314500 }, { "epoch": 2.72, "learning_rate": 2.1885031250043047e-06, "loss": 3.3609, "step": 1315000 }, { "epoch": 2.72, "learning_rate": 2.187814342922557e-06, "loss": 3.3631, "step": 1315500 }, { "epoch": 2.72, "learning_rate": 2.18712556084081e-06, "loss": 3.3673, "step": 1316000 }, { "epoch": 2.72, "learning_rate": 2.1864367787590624e-06, "loss": 3.3634, "step": 1316500 }, { "epoch": 2.72, "learning_rate": 2.185747996677315e-06, "loss": 3.3629, "step": 1317000 }, { "epoch": 2.72, "learning_rate": 2.1850592145955676e-06, "loss": 3.3662, "step": 1317500 }, { "epoch": 2.72, "learning_rate": 2.18437043251382e-06, "loss": 3.3676, "step": 1318000 }, { "epoch": 2.72, "learning_rate": 2.183681650432073e-06, "loss": 3.3628, "step": 1318500 }, { "epoch": 2.73, "learning_rate": 2.1829928683503253e-06, "loss": 3.3621, "step": 1319000 }, { "epoch": 2.73, "learning_rate": 2.182304086268578e-06, "loss": 3.3626, "step": 1319500 }, { "epoch": 2.73, "learning_rate": 2.1816153041868305e-06, "loss": 3.3595, "step": 1320000 }, { "epoch": 2.73, "learning_rate": 2.1809265221050833e-06, "loss": 3.3636, "step": 1320500 }, { "epoch": 2.73, "learning_rate": 2.1802377400233358e-06, "loss": 3.3641, "step": 1321000 }, { "epoch": 2.73, "learning_rate": 2.179548957941588e-06, "loss": 3.3603, "step": 1321500 }, { "epoch": 2.73, "learning_rate": 2.178860175859841e-06, "loss": 3.3649, "step": 1322000 }, { "epoch": 2.73, "learning_rate": 2.1781713937780934e-06, "loss": 3.3606, "step": 1322500 }, { "epoch": 2.73, "learning_rate": 2.1774826116963462e-06, "loss": 3.3638, "step": 1323000 }, { "epoch": 2.73, "learning_rate": 2.1767938296145987e-06, "loss": 3.3614, "step": 1323500 }, { "epoch": 2.74, "learning_rate": 2.1761050475328515e-06, "loss": 3.3625, "step": 1324000 }, { "epoch": 2.74, "learning_rate": 2.175416265451104e-06, "loss": 3.3627, "step": 1324500 }, { "epoch": 2.74, "learning_rate": 2.1747274833693567e-06, "loss": 3.3638, "step": 1325000 }, { "epoch": 2.74, "learning_rate": 2.174038701287609e-06, "loss": 3.3574, "step": 1325500 }, { "epoch": 2.74, "learning_rate": 2.1733499192058616e-06, "loss": 3.3633, "step": 1326000 }, { "epoch": 2.74, "learning_rate": 2.1726611371241144e-06, "loss": 3.3629, "step": 1326500 }, { "epoch": 2.74, "learning_rate": 2.171972355042367e-06, "loss": 3.3646, "step": 1327000 }, { "epoch": 2.74, "learning_rate": 2.1712835729606196e-06, "loss": 3.3573, "step": 1327500 }, { "epoch": 2.74, "learning_rate": 2.170594790878872e-06, "loss": 3.366, "step": 1328000 }, { "epoch": 2.75, "learning_rate": 2.169906008797125e-06, "loss": 3.3579, "step": 1328500 }, { "epoch": 2.75, "learning_rate": 2.1692172267153773e-06, "loss": 3.3593, "step": 1329000 }, { "epoch": 2.75, "learning_rate": 2.1685284446336297e-06, "loss": 3.3584, "step": 1329500 }, { "epoch": 2.75, "learning_rate": 2.1678396625518825e-06, "loss": 3.3641, "step": 1330000 }, { "epoch": 2.75, "learning_rate": 2.167150880470135e-06, "loss": 3.3556, "step": 1330500 }, { "epoch": 2.75, "learning_rate": 2.1664620983883878e-06, "loss": 3.3607, "step": 1331000 }, { "epoch": 2.75, "learning_rate": 2.16577331630664e-06, "loss": 3.355, "step": 1331500 }, { "epoch": 2.75, "learning_rate": 2.165084534224893e-06, "loss": 3.3578, "step": 1332000 }, { "epoch": 2.75, "learning_rate": 2.1643957521431454e-06, "loss": 3.3616, "step": 1332500 }, { "epoch": 2.75, "learning_rate": 2.1637069700613983e-06, "loss": 3.3647, "step": 1333000 }, { "epoch": 2.76, "learning_rate": 2.1630181879796507e-06, "loss": 3.3598, "step": 1333500 }, { "epoch": 2.76, "learning_rate": 2.162329405897903e-06, "loss": 3.354, "step": 1334000 }, { "epoch": 2.76, "learning_rate": 2.161640623816156e-06, "loss": 3.3619, "step": 1334500 }, { "epoch": 2.76, "learning_rate": 2.1609518417344083e-06, "loss": 3.3557, "step": 1335000 }, { "epoch": 2.76, "learning_rate": 2.160263059652661e-06, "loss": 3.3602, "step": 1335500 }, { "epoch": 2.76, "learning_rate": 2.1595742775709136e-06, "loss": 3.3622, "step": 1336000 }, { "epoch": 2.76, "learning_rate": 2.1588854954891664e-06, "loss": 3.3627, "step": 1336500 }, { "epoch": 2.76, "learning_rate": 2.158196713407419e-06, "loss": 3.3569, "step": 1337000 }, { "epoch": 2.76, "learning_rate": 2.1575079313256716e-06, "loss": 3.3579, "step": 1337500 }, { "epoch": 2.76, "learning_rate": 2.1568191492439236e-06, "loss": 3.3531, "step": 1338000 }, { "epoch": 2.77, "learning_rate": 2.156130367162176e-06, "loss": 3.357, "step": 1338500 }, { "epoch": 2.77, "learning_rate": 2.155441585080429e-06, "loss": 3.3661, "step": 1339000 }, { "epoch": 2.77, "learning_rate": 2.1547528029986813e-06, "loss": 3.3597, "step": 1339500 }, { "epoch": 2.77, "learning_rate": 2.154064020916934e-06, "loss": 3.3559, "step": 1340000 }, { "epoch": 2.77, "learning_rate": 2.1533752388351865e-06, "loss": 3.358, "step": 1340500 }, { "epoch": 2.77, "learning_rate": 2.1526864567534394e-06, "loss": 3.3627, "step": 1341000 }, { "epoch": 2.77, "learning_rate": 2.1519976746716918e-06, "loss": 3.3633, "step": 1341500 }, { "epoch": 2.77, "learning_rate": 2.151308892589944e-06, "loss": 3.3607, "step": 1342000 }, { "epoch": 2.77, "learning_rate": 2.150620110508197e-06, "loss": 3.3579, "step": 1342500 }, { "epoch": 2.78, "learning_rate": 2.1499313284264494e-06, "loss": 3.3482, "step": 1343000 }, { "epoch": 2.78, "learning_rate": 2.1492425463447022e-06, "loss": 3.3571, "step": 1343500 }, { "epoch": 2.78, "learning_rate": 2.1485537642629547e-06, "loss": 3.3534, "step": 1344000 }, { "epoch": 2.78, "learning_rate": 2.1478649821812075e-06, "loss": 3.3556, "step": 1344500 }, { "epoch": 2.78, "learning_rate": 2.14717620009946e-06, "loss": 3.3556, "step": 1345000 }, { "epoch": 2.78, "learning_rate": 2.1464874180177127e-06, "loss": 3.3653, "step": 1345500 }, { "epoch": 2.78, "learning_rate": 2.145798635935965e-06, "loss": 3.3589, "step": 1346000 }, { "epoch": 2.78, "learning_rate": 2.1451098538542176e-06, "loss": 3.3592, "step": 1346500 }, { "epoch": 2.78, "learning_rate": 2.1444210717724704e-06, "loss": 3.3611, "step": 1347000 }, { "epoch": 2.78, "learning_rate": 2.143732289690723e-06, "loss": 3.3598, "step": 1347500 }, { "epoch": 2.79, "learning_rate": 2.1430435076089756e-06, "loss": 3.3579, "step": 1348000 }, { "epoch": 2.79, "learning_rate": 2.142354725527228e-06, "loss": 3.3608, "step": 1348500 }, { "epoch": 2.79, "learning_rate": 2.141665943445481e-06, "loss": 3.3569, "step": 1349000 }, { "epoch": 2.79, "learning_rate": 2.1409771613637333e-06, "loss": 3.355, "step": 1349500 }, { "epoch": 2.79, "learning_rate": 2.1402883792819857e-06, "loss": 3.3598, "step": 1350000 }, { "epoch": 2.79, "learning_rate": 2.1395995972002385e-06, "loss": 3.3575, "step": 1350500 }, { "epoch": 2.79, "learning_rate": 2.138910815118491e-06, "loss": 3.3546, "step": 1351000 }, { "epoch": 2.79, "learning_rate": 2.1382220330367438e-06, "loss": 3.3586, "step": 1351500 }, { "epoch": 2.79, "learning_rate": 2.137533250954996e-06, "loss": 3.3586, "step": 1352000 }, { "epoch": 2.79, "learning_rate": 2.136844468873249e-06, "loss": 3.3575, "step": 1352500 }, { "epoch": 2.8, "learning_rate": 2.1361556867915014e-06, "loss": 3.3584, "step": 1353000 }, { "epoch": 2.8, "learning_rate": 2.1354669047097543e-06, "loss": 3.3546, "step": 1353500 }, { "epoch": 2.8, "learning_rate": 2.1347781226280067e-06, "loss": 3.3518, "step": 1354000 }, { "epoch": 2.8, "learning_rate": 2.134089340546259e-06, "loss": 3.3465, "step": 1354500 }, { "epoch": 2.8, "learning_rate": 2.133400558464512e-06, "loss": 3.3586, "step": 1355000 }, { "epoch": 2.8, "learning_rate": 2.1327117763827643e-06, "loss": 3.3578, "step": 1355500 }, { "epoch": 2.8, "learning_rate": 2.132022994301017e-06, "loss": 3.3575, "step": 1356000 }, { "epoch": 2.8, "learning_rate": 2.1313342122192696e-06, "loss": 3.357, "step": 1356500 }, { "epoch": 2.8, "learning_rate": 2.1306454301375224e-06, "loss": 3.361, "step": 1357000 }, { "epoch": 2.81, "learning_rate": 2.129956648055775e-06, "loss": 3.3559, "step": 1357500 }, { "epoch": 2.81, "learning_rate": 2.1292678659740276e-06, "loss": 3.3541, "step": 1358000 }, { "epoch": 2.81, "learning_rate": 2.12857908389228e-06, "loss": 3.3566, "step": 1358500 }, { "epoch": 2.81, "learning_rate": 2.1278903018105325e-06, "loss": 3.3558, "step": 1359000 }, { "epoch": 2.81, "learning_rate": 2.1272015197287853e-06, "loss": 3.3545, "step": 1359500 }, { "epoch": 2.81, "learning_rate": 2.1265127376470377e-06, "loss": 3.3601, "step": 1360000 }, { "epoch": 2.81, "learning_rate": 2.1258239555652905e-06, "loss": 3.3552, "step": 1360500 }, { "epoch": 2.81, "learning_rate": 2.125135173483543e-06, "loss": 3.3504, "step": 1361000 }, { "epoch": 2.81, "learning_rate": 2.1244463914017958e-06, "loss": 3.3528, "step": 1361500 }, { "epoch": 2.81, "learning_rate": 2.123757609320048e-06, "loss": 3.3463, "step": 1362000 }, { "epoch": 2.82, "learning_rate": 2.1230688272383006e-06, "loss": 3.355, "step": 1362500 }, { "epoch": 2.82, "learning_rate": 2.1223800451565534e-06, "loss": 3.3503, "step": 1363000 }, { "epoch": 2.82, "learning_rate": 2.1216912630748054e-06, "loss": 3.3566, "step": 1363500 }, { "epoch": 2.82, "learning_rate": 2.1210024809930582e-06, "loss": 3.3581, "step": 1364000 }, { "epoch": 2.82, "learning_rate": 2.1203136989113107e-06, "loss": 3.3549, "step": 1364500 }, { "epoch": 2.82, "learning_rate": 2.1196249168295635e-06, "loss": 3.3527, "step": 1365000 }, { "epoch": 2.82, "learning_rate": 2.118936134747816e-06, "loss": 3.3603, "step": 1365500 }, { "epoch": 2.82, "learning_rate": 2.1182473526660687e-06, "loss": 3.3547, "step": 1366000 }, { "epoch": 2.82, "learning_rate": 2.117558570584321e-06, "loss": 3.3576, "step": 1366500 }, { "epoch": 2.82, "learning_rate": 2.1168697885025736e-06, "loss": 3.3542, "step": 1367000 }, { "epoch": 2.83, "learning_rate": 2.1161810064208264e-06, "loss": 3.352, "step": 1367500 }, { "epoch": 2.83, "learning_rate": 2.115492224339079e-06, "loss": 3.3547, "step": 1368000 }, { "epoch": 2.83, "learning_rate": 2.1148034422573316e-06, "loss": 3.3518, "step": 1368500 }, { "epoch": 2.83, "learning_rate": 2.114114660175584e-06, "loss": 3.3521, "step": 1369000 }, { "epoch": 2.83, "learning_rate": 2.113425878093837e-06, "loss": 3.3533, "step": 1369500 }, { "epoch": 2.83, "learning_rate": 2.1127370960120893e-06, "loss": 3.353, "step": 1370000 }, { "epoch": 2.83, "learning_rate": 2.1120483139303417e-06, "loss": 3.3534, "step": 1370500 }, { "epoch": 2.83, "learning_rate": 2.1113595318485945e-06, "loss": 3.3504, "step": 1371000 }, { "epoch": 2.83, "learning_rate": 2.110670749766847e-06, "loss": 3.3473, "step": 1371500 }, { "epoch": 2.84, "learning_rate": 2.1099819676850998e-06, "loss": 3.3541, "step": 1372000 }, { "epoch": 2.84, "learning_rate": 2.109293185603352e-06, "loss": 3.3491, "step": 1372500 }, { "epoch": 2.84, "learning_rate": 2.108604403521605e-06, "loss": 3.3566, "step": 1373000 }, { "epoch": 2.84, "learning_rate": 2.1079156214398574e-06, "loss": 3.358, "step": 1373500 }, { "epoch": 2.84, "learning_rate": 2.1072268393581103e-06, "loss": 3.3546, "step": 1374000 }, { "epoch": 2.84, "learning_rate": 2.1065380572763627e-06, "loss": 3.3561, "step": 1374500 }, { "epoch": 2.84, "learning_rate": 2.105849275194615e-06, "loss": 3.3578, "step": 1375000 }, { "epoch": 2.84, "learning_rate": 2.105160493112868e-06, "loss": 3.3566, "step": 1375500 }, { "epoch": 2.84, "learning_rate": 2.1044717110311203e-06, "loss": 3.3553, "step": 1376000 }, { "epoch": 2.84, "learning_rate": 2.103782928949373e-06, "loss": 3.3552, "step": 1376500 }, { "epoch": 2.85, "learning_rate": 2.1030941468676256e-06, "loss": 3.3503, "step": 1377000 }, { "epoch": 2.85, "learning_rate": 2.1024053647858784e-06, "loss": 3.3539, "step": 1377500 }, { "epoch": 2.85, "learning_rate": 2.101716582704131e-06, "loss": 3.352, "step": 1378000 }, { "epoch": 2.85, "learning_rate": 2.1010278006223836e-06, "loss": 3.3531, "step": 1378500 }, { "epoch": 2.85, "learning_rate": 2.100339018540636e-06, "loss": 3.3507, "step": 1379000 }, { "epoch": 2.85, "learning_rate": 2.0996502364588885e-06, "loss": 3.3524, "step": 1379500 }, { "epoch": 2.85, "learning_rate": 2.0989614543771413e-06, "loss": 3.3516, "step": 1380000 }, { "epoch": 2.85, "learning_rate": 2.0982726722953937e-06, "loss": 3.3546, "step": 1380500 }, { "epoch": 2.85, "learning_rate": 2.0975838902136465e-06, "loss": 3.3491, "step": 1381000 }, { "epoch": 2.85, "learning_rate": 2.096895108131899e-06, "loss": 3.3511, "step": 1381500 }, { "epoch": 2.86, "learning_rate": 2.0962063260501518e-06, "loss": 3.3528, "step": 1382000 }, { "epoch": 2.86, "learning_rate": 2.095517543968404e-06, "loss": 3.3525, "step": 1382500 }, { "epoch": 2.86, "learning_rate": 2.0948287618866566e-06, "loss": 3.3525, "step": 1383000 }, { "epoch": 2.86, "learning_rate": 2.0941399798049094e-06, "loss": 3.3515, "step": 1383500 }, { "epoch": 2.86, "learning_rate": 2.093451197723162e-06, "loss": 3.3486, "step": 1384000 }, { "epoch": 2.86, "learning_rate": 2.0927624156414147e-06, "loss": 3.3578, "step": 1384500 }, { "epoch": 2.86, "learning_rate": 2.092073633559667e-06, "loss": 3.3485, "step": 1385000 }, { "epoch": 2.86, "learning_rate": 2.09138485147792e-06, "loss": 3.3484, "step": 1385500 }, { "epoch": 2.86, "learning_rate": 2.0906960693961723e-06, "loss": 3.3532, "step": 1386000 }, { "epoch": 2.86, "learning_rate": 2.090007287314425e-06, "loss": 3.3532, "step": 1386500 }, { "epoch": 2.87, "learning_rate": 2.0893185052326776e-06, "loss": 3.3446, "step": 1387000 }, { "epoch": 2.87, "learning_rate": 2.08862972315093e-06, "loss": 3.353, "step": 1387500 }, { "epoch": 2.87, "learning_rate": 2.087940941069183e-06, "loss": 3.3516, "step": 1388000 }, { "epoch": 2.87, "learning_rate": 2.087252158987435e-06, "loss": 3.3509, "step": 1388500 }, { "epoch": 2.87, "learning_rate": 2.086563376905688e-06, "loss": 3.3543, "step": 1389000 }, { "epoch": 2.87, "learning_rate": 2.08587459482394e-06, "loss": 3.3559, "step": 1389500 }, { "epoch": 2.87, "learning_rate": 2.085185812742193e-06, "loss": 3.3556, "step": 1390000 }, { "epoch": 2.87, "learning_rate": 2.0844970306604453e-06, "loss": 3.3516, "step": 1390500 }, { "epoch": 2.87, "learning_rate": 2.0838082485786977e-06, "loss": 3.3525, "step": 1391000 }, { "epoch": 2.88, "learning_rate": 2.0831194664969505e-06, "loss": 3.3471, "step": 1391500 }, { "epoch": 2.88, "learning_rate": 2.082430684415203e-06, "loss": 3.3457, "step": 1392000 }, { "epoch": 2.88, "learning_rate": 2.0817419023334558e-06, "loss": 3.3533, "step": 1392500 }, { "epoch": 2.88, "learning_rate": 2.081053120251708e-06, "loss": 3.3449, "step": 1393000 }, { "epoch": 2.88, "learning_rate": 2.080364338169961e-06, "loss": 3.3536, "step": 1393500 }, { "epoch": 2.88, "learning_rate": 2.0796755560882134e-06, "loss": 3.3527, "step": 1394000 }, { "epoch": 2.88, "learning_rate": 2.0789867740064663e-06, "loss": 3.3525, "step": 1394500 }, { "epoch": 2.88, "learning_rate": 2.0782979919247187e-06, "loss": 3.3502, "step": 1395000 }, { "epoch": 2.88, "learning_rate": 2.077609209842971e-06, "loss": 3.352, "step": 1395500 }, { "epoch": 2.88, "learning_rate": 2.076920427761224e-06, "loss": 3.3506, "step": 1396000 }, { "epoch": 2.89, "learning_rate": 2.0762316456794763e-06, "loss": 3.3543, "step": 1396500 }, { "epoch": 2.89, "learning_rate": 2.075542863597729e-06, "loss": 3.3424, "step": 1397000 }, { "epoch": 2.89, "learning_rate": 2.0748540815159816e-06, "loss": 3.3488, "step": 1397500 }, { "epoch": 2.89, "learning_rate": 2.0741652994342344e-06, "loss": 3.3471, "step": 1398000 }, { "epoch": 2.89, "learning_rate": 2.073476517352487e-06, "loss": 3.3426, "step": 1398500 }, { "epoch": 2.89, "learning_rate": 2.0727877352707396e-06, "loss": 3.3476, "step": 1399000 }, { "epoch": 2.89, "learning_rate": 2.072098953188992e-06, "loss": 3.3476, "step": 1399500 }, { "epoch": 2.89, "learning_rate": 2.0714101711072445e-06, "loss": 3.3442, "step": 1400000 }, { "epoch": 2.89, "learning_rate": 2.0707213890254973e-06, "loss": 3.3533, "step": 1400500 }, { "epoch": 2.89, "learning_rate": 2.0700326069437497e-06, "loss": 3.336, "step": 1401000 }, { "epoch": 2.9, "learning_rate": 2.0693438248620025e-06, "loss": 3.3522, "step": 1401500 }, { "epoch": 2.9, "learning_rate": 2.068655042780255e-06, "loss": 3.3563, "step": 1402000 }, { "epoch": 2.9, "learning_rate": 2.0679662606985078e-06, "loss": 3.3508, "step": 1402500 }, { "epoch": 2.9, "learning_rate": 2.06727747861676e-06, "loss": 3.348, "step": 1403000 }, { "epoch": 2.9, "learning_rate": 2.0665886965350126e-06, "loss": 3.3463, "step": 1403500 }, { "epoch": 2.9, "learning_rate": 2.0658999144532654e-06, "loss": 3.3522, "step": 1404000 }, { "epoch": 2.9, "learning_rate": 2.065211132371518e-06, "loss": 3.355, "step": 1404500 }, { "epoch": 2.9, "learning_rate": 2.0645223502897707e-06, "loss": 3.3482, "step": 1405000 }, { "epoch": 2.9, "learning_rate": 2.063833568208023e-06, "loss": 3.3499, "step": 1405500 }, { "epoch": 2.91, "learning_rate": 2.063144786126276e-06, "loss": 3.3494, "step": 1406000 }, { "epoch": 2.91, "learning_rate": 2.0624560040445283e-06, "loss": 3.3468, "step": 1406500 }, { "epoch": 2.91, "learning_rate": 2.061767221962781e-06, "loss": 3.3467, "step": 1407000 }, { "epoch": 2.91, "learning_rate": 2.0610784398810336e-06, "loss": 3.353, "step": 1407500 }, { "epoch": 2.91, "learning_rate": 2.060389657799286e-06, "loss": 3.339, "step": 1408000 }, { "epoch": 2.91, "learning_rate": 2.059700875717539e-06, "loss": 3.3493, "step": 1408500 }, { "epoch": 2.91, "learning_rate": 2.0590120936357912e-06, "loss": 3.3403, "step": 1409000 }, { "epoch": 2.91, "learning_rate": 2.058323311554044e-06, "loss": 3.3474, "step": 1409500 }, { "epoch": 2.91, "learning_rate": 2.0576345294722965e-06, "loss": 3.3486, "step": 1410000 }, { "epoch": 2.91, "learning_rate": 2.0569457473905493e-06, "loss": 3.3513, "step": 1410500 }, { "epoch": 2.92, "learning_rate": 2.0562569653088017e-06, "loss": 3.3434, "step": 1411000 }, { "epoch": 2.92, "learning_rate": 2.0555681832270545e-06, "loss": 3.3423, "step": 1411500 }, { "epoch": 2.92, "learning_rate": 2.054879401145307e-06, "loss": 3.3514, "step": 1412000 }, { "epoch": 2.92, "learning_rate": 2.0541906190635594e-06, "loss": 3.3419, "step": 1412500 }, { "epoch": 2.92, "learning_rate": 2.053501836981812e-06, "loss": 3.349, "step": 1413000 }, { "epoch": 2.92, "learning_rate": 2.0528130549000646e-06, "loss": 3.3509, "step": 1413500 }, { "epoch": 2.92, "learning_rate": 2.0521242728183174e-06, "loss": 3.3459, "step": 1414000 }, { "epoch": 2.92, "learning_rate": 2.0514354907365694e-06, "loss": 3.3461, "step": 1414500 }, { "epoch": 2.92, "learning_rate": 2.0507467086548223e-06, "loss": 3.3463, "step": 1415000 }, { "epoch": 2.92, "learning_rate": 2.0500579265730747e-06, "loss": 3.3408, "step": 1415500 }, { "epoch": 2.93, "learning_rate": 2.049369144491327e-06, "loss": 3.3482, "step": 1416000 }, { "epoch": 2.93, "learning_rate": 2.04868036240958e-06, "loss": 3.3446, "step": 1416500 }, { "epoch": 2.93, "learning_rate": 2.0479915803278323e-06, "loss": 3.3463, "step": 1417000 }, { "epoch": 2.93, "learning_rate": 2.047302798246085e-06, "loss": 3.3388, "step": 1417500 }, { "epoch": 2.93, "learning_rate": 2.0466140161643376e-06, "loss": 3.3506, "step": 1418000 }, { "epoch": 2.93, "learning_rate": 2.0459252340825904e-06, "loss": 3.3426, "step": 1418500 }, { "epoch": 2.93, "learning_rate": 2.045236452000843e-06, "loss": 3.3509, "step": 1419000 }, { "epoch": 2.93, "learning_rate": 2.0445476699190956e-06, "loss": 3.3476, "step": 1419500 }, { "epoch": 2.93, "learning_rate": 2.043858887837348e-06, "loss": 3.3446, "step": 1420000 }, { "epoch": 2.94, "learning_rate": 2.0431701057556005e-06, "loss": 3.3451, "step": 1420500 }, { "epoch": 2.94, "learning_rate": 2.0424813236738533e-06, "loss": 3.3378, "step": 1421000 }, { "epoch": 2.94, "learning_rate": 2.0417925415921057e-06, "loss": 3.3427, "step": 1421500 }, { "epoch": 2.94, "learning_rate": 2.0411037595103585e-06, "loss": 3.3428, "step": 1422000 }, { "epoch": 2.94, "learning_rate": 2.040414977428611e-06, "loss": 3.3459, "step": 1422500 }, { "epoch": 2.94, "learning_rate": 2.0397261953468638e-06, "loss": 3.3462, "step": 1423000 }, { "epoch": 2.94, "learning_rate": 2.039037413265116e-06, "loss": 3.344, "step": 1423500 }, { "epoch": 2.94, "learning_rate": 2.0383486311833686e-06, "loss": 3.3463, "step": 1424000 }, { "epoch": 2.94, "learning_rate": 2.0376598491016214e-06, "loss": 3.3479, "step": 1424500 }, { "epoch": 2.94, "learning_rate": 2.036971067019874e-06, "loss": 3.3521, "step": 1425000 }, { "epoch": 2.95, "learning_rate": 2.0362822849381267e-06, "loss": 3.3457, "step": 1425500 }, { "epoch": 2.95, "learning_rate": 2.035593502856379e-06, "loss": 3.3461, "step": 1426000 }, { "epoch": 2.95, "learning_rate": 2.034904720774632e-06, "loss": 3.3439, "step": 1426500 }, { "epoch": 2.95, "learning_rate": 2.0342159386928843e-06, "loss": 3.3488, "step": 1427000 }, { "epoch": 2.95, "learning_rate": 2.033527156611137e-06, "loss": 3.3431, "step": 1427500 }, { "epoch": 2.95, "learning_rate": 2.0328383745293896e-06, "loss": 3.3466, "step": 1428000 }, { "epoch": 2.95, "learning_rate": 2.032149592447642e-06, "loss": 3.3445, "step": 1428500 }, { "epoch": 2.95, "learning_rate": 2.031460810365895e-06, "loss": 3.3471, "step": 1429000 }, { "epoch": 2.95, "learning_rate": 2.0307720282841472e-06, "loss": 3.3477, "step": 1429500 }, { "epoch": 2.95, "learning_rate": 2.0300832462024e-06, "loss": 3.3469, "step": 1430000 }, { "epoch": 2.96, "learning_rate": 2.0293944641206525e-06, "loss": 3.3485, "step": 1430500 }, { "epoch": 2.96, "learning_rate": 2.0287056820389053e-06, "loss": 3.3401, "step": 1431000 }, { "epoch": 2.96, "learning_rate": 2.0280168999571577e-06, "loss": 3.3427, "step": 1431500 }, { "epoch": 2.96, "learning_rate": 2.0273281178754105e-06, "loss": 3.3479, "step": 1432000 }, { "epoch": 2.96, "learning_rate": 2.026639335793663e-06, "loss": 3.3439, "step": 1432500 }, { "epoch": 2.96, "learning_rate": 2.0259505537119154e-06, "loss": 3.3499, "step": 1433000 }, { "epoch": 2.96, "learning_rate": 2.025261771630168e-06, "loss": 3.3518, "step": 1433500 }, { "epoch": 2.96, "learning_rate": 2.0245729895484206e-06, "loss": 3.3432, "step": 1434000 }, { "epoch": 2.96, "learning_rate": 2.0238842074666734e-06, "loss": 3.3434, "step": 1434500 }, { "epoch": 2.97, "learning_rate": 2.023195425384926e-06, "loss": 3.3401, "step": 1435000 }, { "epoch": 2.97, "learning_rate": 2.0225066433031787e-06, "loss": 3.3416, "step": 1435500 }, { "epoch": 2.97, "learning_rate": 2.021817861221431e-06, "loss": 3.3487, "step": 1436000 }, { "epoch": 2.97, "learning_rate": 2.0211290791396835e-06, "loss": 3.3428, "step": 1436500 }, { "epoch": 2.97, "learning_rate": 2.0204402970579363e-06, "loss": 3.3452, "step": 1437000 }, { "epoch": 2.97, "learning_rate": 2.0197515149761887e-06, "loss": 3.3389, "step": 1437500 }, { "epoch": 2.97, "learning_rate": 2.0190627328944416e-06, "loss": 3.3416, "step": 1438000 }, { "epoch": 2.97, "learning_rate": 2.018373950812694e-06, "loss": 3.3396, "step": 1438500 }, { "epoch": 2.97, "learning_rate": 2.017685168730947e-06, "loss": 3.3427, "step": 1439000 }, { "epoch": 2.97, "learning_rate": 2.0169963866491992e-06, "loss": 3.3477, "step": 1439500 }, { "epoch": 2.98, "learning_rate": 2.016307604567452e-06, "loss": 3.3445, "step": 1440000 }, { "epoch": 2.98, "learning_rate": 2.015618822485704e-06, "loss": 3.344, "step": 1440500 }, { "epoch": 2.98, "learning_rate": 2.0149300404039565e-06, "loss": 3.3382, "step": 1441000 }, { "epoch": 2.98, "learning_rate": 2.0142412583222093e-06, "loss": 3.3408, "step": 1441500 }, { "epoch": 2.98, "learning_rate": 2.0135524762404617e-06, "loss": 3.341, "step": 1442000 }, { "epoch": 2.98, "learning_rate": 2.0128636941587145e-06, "loss": 3.3421, "step": 1442500 }, { "epoch": 2.98, "learning_rate": 2.012174912076967e-06, "loss": 3.3429, "step": 1443000 }, { "epoch": 2.98, "learning_rate": 2.0114861299952198e-06, "loss": 3.3457, "step": 1443500 }, { "epoch": 2.98, "learning_rate": 2.010797347913472e-06, "loss": 3.3465, "step": 1444000 }, { "epoch": 2.98, "learning_rate": 2.0101085658317246e-06, "loss": 3.3354, "step": 1444500 }, { "epoch": 2.99, "learning_rate": 2.0094197837499774e-06, "loss": 3.3436, "step": 1445000 }, { "epoch": 2.99, "learning_rate": 2.00873100166823e-06, "loss": 3.3409, "step": 1445500 }, { "epoch": 2.99, "learning_rate": 2.0080422195864827e-06, "loss": 3.3432, "step": 1446000 }, { "epoch": 2.99, "learning_rate": 2.007353437504735e-06, "loss": 3.3501, "step": 1446500 }, { "epoch": 2.99, "learning_rate": 2.006664655422988e-06, "loss": 3.3417, "step": 1447000 }, { "epoch": 2.99, "learning_rate": 2.0059758733412403e-06, "loss": 3.3414, "step": 1447500 }, { "epoch": 2.99, "learning_rate": 2.005287091259493e-06, "loss": 3.338, "step": 1448000 }, { "epoch": 2.99, "learning_rate": 2.0045983091777456e-06, "loss": 3.336, "step": 1448500 }, { "epoch": 2.99, "learning_rate": 2.003909527095998e-06, "loss": 3.3456, "step": 1449000 }, { "epoch": 3.0, "learning_rate": 2.003220745014251e-06, "loss": 3.3449, "step": 1449500 }, { "epoch": 3.0, "learning_rate": 2.0025319629325032e-06, "loss": 3.3393, "step": 1450000 }, { "epoch": 3.0, "learning_rate": 2.001843180850756e-06, "loss": 3.3431, "step": 1450500 }, { "epoch": 3.0, "learning_rate": 2.0011543987690085e-06, "loss": 3.3403, "step": 1451000 }, { "epoch": 3.0, "learning_rate": 2.0004656166872613e-06, "loss": 3.3422, "step": 1451500 }, { "epoch": 3.0, "eval_loss": 3.3317129611968994, "eval_runtime": 22762.644, "eval_samples_per_second": 151.186, "eval_steps_per_second": 2.362, "step": 1451838 }, { "epoch": 3.0, "learning_rate": 1.9997768346055137e-06, "loss": 3.3298, "step": 1452000 }, { "epoch": 3.0, "learning_rate": 1.999088052523766e-06, "loss": 3.3204, "step": 1452500 }, { "epoch": 3.0, "learning_rate": 1.998399270442019e-06, "loss": 3.3236, "step": 1453000 }, { "epoch": 3.0, "learning_rate": 1.9977104883602714e-06, "loss": 3.327, "step": 1453500 }, { "epoch": 3.0, "learning_rate": 1.997021706278524e-06, "loss": 3.3194, "step": 1454000 }, { "epoch": 3.01, "learning_rate": 1.9963329241967766e-06, "loss": 3.3194, "step": 1454500 }, { "epoch": 3.01, "learning_rate": 1.995644142115029e-06, "loss": 3.3239, "step": 1455000 }, { "epoch": 3.01, "learning_rate": 1.994955360033282e-06, "loss": 3.3219, "step": 1455500 }, { "epoch": 3.01, "learning_rate": 1.9942665779515343e-06, "loss": 3.3209, "step": 1456000 }, { "epoch": 3.01, "learning_rate": 1.993577795869787e-06, "loss": 3.3239, "step": 1456500 }, { "epoch": 3.01, "learning_rate": 1.9928890137880395e-06, "loss": 3.3218, "step": 1457000 }, { "epoch": 3.01, "learning_rate": 1.9922002317062923e-06, "loss": 3.3223, "step": 1457500 }, { "epoch": 3.01, "learning_rate": 1.9915114496245447e-06, "loss": 3.3155, "step": 1458000 }, { "epoch": 3.01, "learning_rate": 1.9908226675427976e-06, "loss": 3.3236, "step": 1458500 }, { "epoch": 3.01, "learning_rate": 1.99013388546105e-06, "loss": 3.3248, "step": 1459000 }, { "epoch": 3.02, "learning_rate": 1.9894451033793024e-06, "loss": 3.3232, "step": 1459500 }, { "epoch": 3.02, "learning_rate": 1.9887563212975552e-06, "loss": 3.3242, "step": 1460000 }, { "epoch": 3.02, "learning_rate": 1.9880675392158076e-06, "loss": 3.3206, "step": 1460500 }, { "epoch": 3.02, "learning_rate": 1.9873787571340605e-06, "loss": 3.3265, "step": 1461000 }, { "epoch": 3.02, "learning_rate": 1.986689975052313e-06, "loss": 3.3229, "step": 1461500 }, { "epoch": 3.02, "learning_rate": 1.9860011929705657e-06, "loss": 3.3243, "step": 1462000 }, { "epoch": 3.02, "learning_rate": 1.985312410888818e-06, "loss": 3.3195, "step": 1462500 }, { "epoch": 3.02, "learning_rate": 1.9846236288070705e-06, "loss": 3.3242, "step": 1463000 }, { "epoch": 3.02, "learning_rate": 1.9839348467253234e-06, "loss": 3.3267, "step": 1463500 }, { "epoch": 3.03, "learning_rate": 1.9832460646435758e-06, "loss": 3.3246, "step": 1464000 }, { "epoch": 3.03, "learning_rate": 1.9825572825618286e-06, "loss": 3.3252, "step": 1464500 }, { "epoch": 3.03, "learning_rate": 1.981868500480081e-06, "loss": 3.3213, "step": 1465000 }, { "epoch": 3.03, "learning_rate": 1.9811797183983334e-06, "loss": 3.3207, "step": 1465500 }, { "epoch": 3.03, "learning_rate": 1.9804909363165863e-06, "loss": 3.3226, "step": 1466000 }, { "epoch": 3.03, "learning_rate": 1.9798021542348387e-06, "loss": 3.3219, "step": 1466500 }, { "epoch": 3.03, "learning_rate": 1.979113372153091e-06, "loss": 3.3201, "step": 1467000 }, { "epoch": 3.03, "learning_rate": 1.978424590071344e-06, "loss": 3.3275, "step": 1467500 }, { "epoch": 3.03, "learning_rate": 1.9777358079895963e-06, "loss": 3.3201, "step": 1468000 }, { "epoch": 3.03, "learning_rate": 1.977047025907849e-06, "loss": 3.3163, "step": 1468500 }, { "epoch": 3.04, "learning_rate": 1.9763582438261016e-06, "loss": 3.316, "step": 1469000 }, { "epoch": 3.04, "learning_rate": 1.9756694617443544e-06, "loss": 3.3264, "step": 1469500 }, { "epoch": 3.04, "learning_rate": 1.974980679662607e-06, "loss": 3.3313, "step": 1470000 }, { "epoch": 3.04, "learning_rate": 1.9742918975808597e-06, "loss": 3.325, "step": 1470500 }, { "epoch": 3.04, "learning_rate": 1.973603115499112e-06, "loss": 3.3179, "step": 1471000 }, { "epoch": 3.04, "learning_rate": 1.9729143334173645e-06, "loss": 3.3233, "step": 1471500 }, { "epoch": 3.04, "learning_rate": 1.9722255513356173e-06, "loss": 3.3257, "step": 1472000 }, { "epoch": 3.04, "learning_rate": 1.9715367692538697e-06, "loss": 3.3245, "step": 1472500 }, { "epoch": 3.04, "learning_rate": 1.9708479871721225e-06, "loss": 3.3198, "step": 1473000 }, { "epoch": 3.04, "learning_rate": 1.970159205090375e-06, "loss": 3.3213, "step": 1473500 }, { "epoch": 3.05, "learning_rate": 1.969470423008628e-06, "loss": 3.3233, "step": 1474000 }, { "epoch": 3.05, "learning_rate": 1.96878164092688e-06, "loss": 3.3229, "step": 1474500 }, { "epoch": 3.05, "learning_rate": 1.968092858845133e-06, "loss": 3.3184, "step": 1475000 }, { "epoch": 3.05, "learning_rate": 1.9674040767633854e-06, "loss": 3.3206, "step": 1475500 }, { "epoch": 3.05, "learning_rate": 1.966715294681638e-06, "loss": 3.3235, "step": 1476000 }, { "epoch": 3.05, "learning_rate": 1.9660265125998907e-06, "loss": 3.3203, "step": 1476500 }, { "epoch": 3.05, "learning_rate": 1.965337730518143e-06, "loss": 3.3246, "step": 1477000 }, { "epoch": 3.05, "learning_rate": 1.964648948436396e-06, "loss": 3.3212, "step": 1477500 }, { "epoch": 3.05, "learning_rate": 1.9639601663546483e-06, "loss": 3.3161, "step": 1478000 }, { "epoch": 3.06, "learning_rate": 1.9632713842729007e-06, "loss": 3.3192, "step": 1478500 }, { "epoch": 3.06, "learning_rate": 1.9625826021911536e-06, "loss": 3.3208, "step": 1479000 }, { "epoch": 3.06, "learning_rate": 1.961893820109406e-06, "loss": 3.3202, "step": 1479500 }, { "epoch": 3.06, "learning_rate": 1.9612050380276584e-06, "loss": 3.327, "step": 1480000 }, { "epoch": 3.06, "learning_rate": 1.9605162559459112e-06, "loss": 3.3231, "step": 1480500 }, { "epoch": 3.06, "learning_rate": 1.9598274738641636e-06, "loss": 3.3188, "step": 1481000 }, { "epoch": 3.06, "learning_rate": 1.9591386917824165e-06, "loss": 3.3295, "step": 1481500 }, { "epoch": 3.06, "learning_rate": 1.958449909700669e-06, "loss": 3.3172, "step": 1482000 }, { "epoch": 3.06, "learning_rate": 1.9577611276189217e-06, "loss": 3.3205, "step": 1482500 }, { "epoch": 3.06, "learning_rate": 1.957072345537174e-06, "loss": 3.3238, "step": 1483000 }, { "epoch": 3.07, "learning_rate": 1.9563835634554265e-06, "loss": 3.3195, "step": 1483500 }, { "epoch": 3.07, "learning_rate": 1.9556947813736794e-06, "loss": 3.3179, "step": 1484000 }, { "epoch": 3.07, "learning_rate": 1.9550059992919318e-06, "loss": 3.3215, "step": 1484500 }, { "epoch": 3.07, "learning_rate": 1.9543172172101846e-06, "loss": 3.3258, "step": 1485000 }, { "epoch": 3.07, "learning_rate": 1.953628435128437e-06, "loss": 3.3258, "step": 1485500 }, { "epoch": 3.07, "learning_rate": 1.95293965304669e-06, "loss": 3.3158, "step": 1486000 }, { "epoch": 3.07, "learning_rate": 1.9522508709649423e-06, "loss": 3.3256, "step": 1486500 }, { "epoch": 3.07, "learning_rate": 1.951562088883195e-06, "loss": 3.3233, "step": 1487000 }, { "epoch": 3.07, "learning_rate": 1.9508733068014475e-06, "loss": 3.3183, "step": 1487500 }, { "epoch": 3.07, "learning_rate": 1.9501845247197e-06, "loss": 3.3203, "step": 1488000 }, { "epoch": 3.08, "learning_rate": 1.9494957426379528e-06, "loss": 3.3206, "step": 1488500 }, { "epoch": 3.08, "learning_rate": 1.948806960556205e-06, "loss": 3.3223, "step": 1489000 }, { "epoch": 3.08, "learning_rate": 1.948118178474458e-06, "loss": 3.3201, "step": 1489500 }, { "epoch": 3.08, "learning_rate": 1.9474293963927104e-06, "loss": 3.3253, "step": 1490000 }, { "epoch": 3.08, "learning_rate": 1.9467406143109632e-06, "loss": 3.3258, "step": 1490500 }, { "epoch": 3.08, "learning_rate": 1.9460518322292157e-06, "loss": 3.3236, "step": 1491000 }, { "epoch": 3.08, "learning_rate": 1.945363050147468e-06, "loss": 3.3192, "step": 1491500 }, { "epoch": 3.08, "learning_rate": 1.9446742680657205e-06, "loss": 3.3161, "step": 1492000 }, { "epoch": 3.08, "learning_rate": 1.9439854859839733e-06, "loss": 3.3171, "step": 1492500 }, { "epoch": 3.09, "learning_rate": 1.9432967039022257e-06, "loss": 3.3238, "step": 1493000 }, { "epoch": 3.09, "learning_rate": 1.9426079218204785e-06, "loss": 3.3228, "step": 1493500 }, { "epoch": 3.09, "learning_rate": 1.941919139738731e-06, "loss": 3.3185, "step": 1494000 }, { "epoch": 3.09, "learning_rate": 1.941230357656984e-06, "loss": 3.318, "step": 1494500 }, { "epoch": 3.09, "learning_rate": 1.940541575575236e-06, "loss": 3.3222, "step": 1495000 }, { "epoch": 3.09, "learning_rate": 1.939852793493489e-06, "loss": 3.3189, "step": 1495500 }, { "epoch": 3.09, "learning_rate": 1.9391640114117414e-06, "loss": 3.3242, "step": 1496000 }, { "epoch": 3.09, "learning_rate": 1.938475229329994e-06, "loss": 3.3194, "step": 1496500 }, { "epoch": 3.09, "learning_rate": 1.9377864472482467e-06, "loss": 3.3198, "step": 1497000 }, { "epoch": 3.09, "learning_rate": 1.937097665166499e-06, "loss": 3.3176, "step": 1497500 }, { "epoch": 3.1, "learning_rate": 1.936408883084752e-06, "loss": 3.3228, "step": 1498000 }, { "epoch": 3.1, "learning_rate": 1.9357201010030043e-06, "loss": 3.3209, "step": 1498500 }, { "epoch": 3.1, "learning_rate": 1.935031318921257e-06, "loss": 3.3251, "step": 1499000 }, { "epoch": 3.1, "learning_rate": 1.9343425368395096e-06, "loss": 3.3222, "step": 1499500 }, { "epoch": 3.1, "learning_rate": 1.933653754757762e-06, "loss": 3.3179, "step": 1500000 }, { "epoch": 3.1, "learning_rate": 1.932964972676015e-06, "loss": 3.318, "step": 1500500 }, { "epoch": 3.1, "learning_rate": 1.9322761905942672e-06, "loss": 3.3221, "step": 1501000 }, { "epoch": 3.1, "learning_rate": 1.93158740851252e-06, "loss": 3.3193, "step": 1501500 }, { "epoch": 3.1, "learning_rate": 1.9308986264307725e-06, "loss": 3.3198, "step": 1502000 }, { "epoch": 3.1, "learning_rate": 1.9302098443490253e-06, "loss": 3.3207, "step": 1502500 }, { "epoch": 3.11, "learning_rate": 1.9295210622672777e-06, "loss": 3.3237, "step": 1503000 }, { "epoch": 3.11, "learning_rate": 1.9288322801855306e-06, "loss": 3.3225, "step": 1503500 }, { "epoch": 3.11, "learning_rate": 1.9281434981037825e-06, "loss": 3.3155, "step": 1504000 }, { "epoch": 3.11, "learning_rate": 1.9274547160220354e-06, "loss": 3.3134, "step": 1504500 }, { "epoch": 3.11, "learning_rate": 1.9267659339402878e-06, "loss": 3.3197, "step": 1505000 }, { "epoch": 3.11, "learning_rate": 1.9260771518585406e-06, "loss": 3.3196, "step": 1505500 }, { "epoch": 3.11, "learning_rate": 1.925388369776793e-06, "loss": 3.3234, "step": 1506000 }, { "epoch": 3.11, "learning_rate": 1.924699587695046e-06, "loss": 3.3152, "step": 1506500 }, { "epoch": 3.11, "learning_rate": 1.9240108056132983e-06, "loss": 3.3211, "step": 1507000 }, { "epoch": 3.12, "learning_rate": 1.923322023531551e-06, "loss": 3.3248, "step": 1507500 }, { "epoch": 3.12, "learning_rate": 1.9226332414498035e-06, "loss": 3.3201, "step": 1508000 }, { "epoch": 3.12, "learning_rate": 1.921944459368056e-06, "loss": 3.3135, "step": 1508500 }, { "epoch": 3.12, "learning_rate": 1.9212556772863088e-06, "loss": 3.3274, "step": 1509000 }, { "epoch": 3.12, "learning_rate": 1.920566895204561e-06, "loss": 3.3192, "step": 1509500 }, { "epoch": 3.12, "learning_rate": 1.919878113122814e-06, "loss": 3.3189, "step": 1510000 }, { "epoch": 3.12, "learning_rate": 1.9191893310410664e-06, "loss": 3.3234, "step": 1510500 }, { "epoch": 3.12, "learning_rate": 1.9185005489593192e-06, "loss": 3.3129, "step": 1511000 }, { "epoch": 3.12, "learning_rate": 1.9178117668775717e-06, "loss": 3.3185, "step": 1511500 }, { "epoch": 3.12, "learning_rate": 1.9171229847958245e-06, "loss": 3.3172, "step": 1512000 }, { "epoch": 3.13, "learning_rate": 1.916434202714077e-06, "loss": 3.3112, "step": 1512500 }, { "epoch": 3.13, "learning_rate": 1.9157454206323293e-06, "loss": 3.3234, "step": 1513000 }, { "epoch": 3.13, "learning_rate": 1.915056638550582e-06, "loss": 3.3207, "step": 1513500 }, { "epoch": 3.13, "learning_rate": 1.9143678564688345e-06, "loss": 3.32, "step": 1514000 }, { "epoch": 3.13, "learning_rate": 1.9136790743870874e-06, "loss": 3.3151, "step": 1514500 }, { "epoch": 3.13, "learning_rate": 1.91299029230534e-06, "loss": 3.3189, "step": 1515000 }, { "epoch": 3.13, "learning_rate": 1.9123015102235926e-06, "loss": 3.3165, "step": 1515500 }, { "epoch": 3.13, "learning_rate": 1.911612728141845e-06, "loss": 3.3149, "step": 1516000 }, { "epoch": 3.13, "learning_rate": 1.9109239460600974e-06, "loss": 3.3226, "step": 1516500 }, { "epoch": 3.13, "learning_rate": 1.91023516397835e-06, "loss": 3.3199, "step": 1517000 }, { "epoch": 3.14, "learning_rate": 1.9095463818966027e-06, "loss": 3.3182, "step": 1517500 }, { "epoch": 3.14, "learning_rate": 1.908857599814855e-06, "loss": 3.325, "step": 1518000 }, { "epoch": 3.14, "learning_rate": 1.908168817733108e-06, "loss": 3.3228, "step": 1518500 }, { "epoch": 3.14, "learning_rate": 1.9074800356513603e-06, "loss": 3.3137, "step": 1519000 }, { "epoch": 3.14, "learning_rate": 1.9067912535696132e-06, "loss": 3.3171, "step": 1519500 }, { "epoch": 3.14, "learning_rate": 1.9061024714878658e-06, "loss": 3.3155, "step": 1520000 }, { "epoch": 3.14, "learning_rate": 1.9054136894061182e-06, "loss": 3.323, "step": 1520500 }, { "epoch": 3.14, "learning_rate": 1.9047249073243708e-06, "loss": 3.3155, "step": 1521000 }, { "epoch": 3.14, "learning_rate": 1.9040361252426234e-06, "loss": 3.3184, "step": 1521500 }, { "epoch": 3.14, "learning_rate": 1.903347343160876e-06, "loss": 3.3208, "step": 1522000 }, { "epoch": 3.15, "learning_rate": 1.9026585610791287e-06, "loss": 3.3181, "step": 1522500 }, { "epoch": 3.15, "learning_rate": 1.901969778997381e-06, "loss": 3.3177, "step": 1523000 }, { "epoch": 3.15, "learning_rate": 1.9012809969156337e-06, "loss": 3.3201, "step": 1523500 }, { "epoch": 3.15, "learning_rate": 1.9005922148338863e-06, "loss": 3.3207, "step": 1524000 }, { "epoch": 3.15, "learning_rate": 1.8999034327521388e-06, "loss": 3.3137, "step": 1524500 }, { "epoch": 3.15, "learning_rate": 1.8992146506703914e-06, "loss": 3.3216, "step": 1525000 }, { "epoch": 3.15, "learning_rate": 1.898525868588644e-06, "loss": 3.3183, "step": 1525500 }, { "epoch": 3.15, "learning_rate": 1.8978370865068966e-06, "loss": 3.3194, "step": 1526000 }, { "epoch": 3.15, "learning_rate": 1.8971483044251492e-06, "loss": 3.3141, "step": 1526500 }, { "epoch": 3.16, "learning_rate": 1.8964595223434019e-06, "loss": 3.3202, "step": 1527000 }, { "epoch": 3.16, "learning_rate": 1.8957707402616545e-06, "loss": 3.3128, "step": 1527500 }, { "epoch": 3.16, "learning_rate": 1.8950819581799071e-06, "loss": 3.3138, "step": 1528000 }, { "epoch": 3.16, "learning_rate": 1.8943931760981595e-06, "loss": 3.3214, "step": 1528500 }, { "epoch": 3.16, "learning_rate": 1.8937043940164121e-06, "loss": 3.3199, "step": 1529000 }, { "epoch": 3.16, "learning_rate": 1.8930156119346648e-06, "loss": 3.3189, "step": 1529500 }, { "epoch": 3.16, "learning_rate": 1.8923268298529174e-06, "loss": 3.3183, "step": 1530000 }, { "epoch": 3.16, "learning_rate": 1.89163804777117e-06, "loss": 3.3182, "step": 1530500 }, { "epoch": 3.16, "learning_rate": 1.8909492656894226e-06, "loss": 3.3098, "step": 1531000 }, { "epoch": 3.16, "learning_rate": 1.8902604836076752e-06, "loss": 3.3153, "step": 1531500 }, { "epoch": 3.17, "learning_rate": 1.8895717015259279e-06, "loss": 3.3138, "step": 1532000 }, { "epoch": 3.17, "learning_rate": 1.8888829194441805e-06, "loss": 3.3246, "step": 1532500 }, { "epoch": 3.17, "learning_rate": 1.888194137362433e-06, "loss": 3.3156, "step": 1533000 }, { "epoch": 3.17, "learning_rate": 1.8875053552806855e-06, "loss": 3.3156, "step": 1533500 }, { "epoch": 3.17, "learning_rate": 1.8868165731989381e-06, "loss": 3.3164, "step": 1534000 }, { "epoch": 3.17, "learning_rate": 1.8861277911171908e-06, "loss": 3.3095, "step": 1534500 }, { "epoch": 3.17, "learning_rate": 1.8854390090354434e-06, "loss": 3.3151, "step": 1535000 }, { "epoch": 3.17, "learning_rate": 1.8847502269536958e-06, "loss": 3.3161, "step": 1535500 }, { "epoch": 3.17, "learning_rate": 1.8840614448719484e-06, "loss": 3.3164, "step": 1536000 }, { "epoch": 3.17, "learning_rate": 1.883372662790201e-06, "loss": 3.3163, "step": 1536500 }, { "epoch": 3.18, "learning_rate": 1.8826838807084534e-06, "loss": 3.3122, "step": 1537000 }, { "epoch": 3.18, "learning_rate": 1.881995098626706e-06, "loss": 3.322, "step": 1537500 }, { "epoch": 3.18, "learning_rate": 1.8813063165449587e-06, "loss": 3.3115, "step": 1538000 }, { "epoch": 3.18, "learning_rate": 1.8806175344632113e-06, "loss": 3.3141, "step": 1538500 }, { "epoch": 3.18, "learning_rate": 1.879928752381464e-06, "loss": 3.316, "step": 1539000 }, { "epoch": 3.18, "learning_rate": 1.8792399702997166e-06, "loss": 3.313, "step": 1539500 }, { "epoch": 3.18, "learning_rate": 1.8785511882179692e-06, "loss": 3.3163, "step": 1540000 }, { "epoch": 3.18, "learning_rate": 1.8778624061362218e-06, "loss": 3.3177, "step": 1540500 }, { "epoch": 3.18, "learning_rate": 1.8771736240544742e-06, "loss": 3.3155, "step": 1541000 }, { "epoch": 3.19, "learning_rate": 1.8764848419727268e-06, "loss": 3.3166, "step": 1541500 }, { "epoch": 3.19, "learning_rate": 1.8757960598909795e-06, "loss": 3.3145, "step": 1542000 }, { "epoch": 3.19, "learning_rate": 1.875107277809232e-06, "loss": 3.3121, "step": 1542500 }, { "epoch": 3.19, "learning_rate": 1.8744184957274847e-06, "loss": 3.3112, "step": 1543000 }, { "epoch": 3.19, "learning_rate": 1.8737297136457373e-06, "loss": 3.3137, "step": 1543500 }, { "epoch": 3.19, "learning_rate": 1.87304093156399e-06, "loss": 3.3185, "step": 1544000 }, { "epoch": 3.19, "learning_rate": 1.8723521494822426e-06, "loss": 3.3249, "step": 1544500 }, { "epoch": 3.19, "learning_rate": 1.871663367400495e-06, "loss": 3.3086, "step": 1545000 }, { "epoch": 3.19, "learning_rate": 1.8709745853187476e-06, "loss": 3.3152, "step": 1545500 }, { "epoch": 3.19, "learning_rate": 1.8702858032370002e-06, "loss": 3.314, "step": 1546000 }, { "epoch": 3.2, "learning_rate": 1.8695970211552528e-06, "loss": 3.316, "step": 1546500 }, { "epoch": 3.2, "learning_rate": 1.8689082390735055e-06, "loss": 3.3188, "step": 1547000 }, { "epoch": 3.2, "learning_rate": 1.868219456991758e-06, "loss": 3.3184, "step": 1547500 }, { "epoch": 3.2, "learning_rate": 1.8675306749100107e-06, "loss": 3.3101, "step": 1548000 }, { "epoch": 3.2, "learning_rate": 1.8668418928282631e-06, "loss": 3.317, "step": 1548500 }, { "epoch": 3.2, "learning_rate": 1.8661531107465155e-06, "loss": 3.3123, "step": 1549000 }, { "epoch": 3.2, "learning_rate": 1.8654643286647681e-06, "loss": 3.3094, "step": 1549500 }, { "epoch": 3.2, "learning_rate": 1.8647755465830208e-06, "loss": 3.3185, "step": 1550000 }, { "epoch": 3.2, "learning_rate": 1.8640867645012734e-06, "loss": 3.3198, "step": 1550500 }, { "epoch": 3.2, "learning_rate": 1.863397982419526e-06, "loss": 3.3176, "step": 1551000 }, { "epoch": 3.21, "learning_rate": 1.8627092003377786e-06, "loss": 3.3117, "step": 1551500 }, { "epoch": 3.21, "learning_rate": 1.8620204182560312e-06, "loss": 3.3156, "step": 1552000 }, { "epoch": 3.21, "learning_rate": 1.8613316361742839e-06, "loss": 3.3188, "step": 1552500 }, { "epoch": 3.21, "learning_rate": 1.8606428540925365e-06, "loss": 3.3185, "step": 1553000 }, { "epoch": 3.21, "learning_rate": 1.859954072010789e-06, "loss": 3.3175, "step": 1553500 }, { "epoch": 3.21, "learning_rate": 1.8592652899290415e-06, "loss": 3.3171, "step": 1554000 }, { "epoch": 3.21, "learning_rate": 1.8585765078472941e-06, "loss": 3.315, "step": 1554500 }, { "epoch": 3.21, "learning_rate": 1.8578877257655468e-06, "loss": 3.3185, "step": 1555000 }, { "epoch": 3.21, "learning_rate": 1.8571989436837994e-06, "loss": 3.3144, "step": 1555500 }, { "epoch": 3.22, "learning_rate": 1.856510161602052e-06, "loss": 3.3096, "step": 1556000 }, { "epoch": 3.22, "learning_rate": 1.8558213795203046e-06, "loss": 3.3105, "step": 1556500 }, { "epoch": 3.22, "learning_rate": 1.8551325974385573e-06, "loss": 3.3172, "step": 1557000 }, { "epoch": 3.22, "learning_rate": 1.8544438153568097e-06, "loss": 3.3143, "step": 1557500 }, { "epoch": 3.22, "learning_rate": 1.8537550332750623e-06, "loss": 3.3117, "step": 1558000 }, { "epoch": 3.22, "learning_rate": 1.853066251193315e-06, "loss": 3.3163, "step": 1558500 }, { "epoch": 3.22, "learning_rate": 1.8523774691115675e-06, "loss": 3.3181, "step": 1559000 }, { "epoch": 3.22, "learning_rate": 1.8516886870298201e-06, "loss": 3.3165, "step": 1559500 }, { "epoch": 3.22, "learning_rate": 1.8509999049480728e-06, "loss": 3.3164, "step": 1560000 }, { "epoch": 3.22, "learning_rate": 1.8503111228663254e-06, "loss": 3.3147, "step": 1560500 }, { "epoch": 3.23, "learning_rate": 1.849622340784578e-06, "loss": 3.3109, "step": 1561000 }, { "epoch": 3.23, "learning_rate": 1.8489335587028302e-06, "loss": 3.3136, "step": 1561500 }, { "epoch": 3.23, "learning_rate": 1.8482447766210828e-06, "loss": 3.3102, "step": 1562000 }, { "epoch": 3.23, "learning_rate": 1.8475559945393355e-06, "loss": 3.3158, "step": 1562500 }, { "epoch": 3.23, "learning_rate": 1.846867212457588e-06, "loss": 3.3108, "step": 1563000 }, { "epoch": 3.23, "learning_rate": 1.8461784303758407e-06, "loss": 3.3136, "step": 1563500 }, { "epoch": 3.23, "learning_rate": 1.8454896482940933e-06, "loss": 3.315, "step": 1564000 }, { "epoch": 3.23, "learning_rate": 1.844800866212346e-06, "loss": 3.3093, "step": 1564500 }, { "epoch": 3.23, "learning_rate": 1.8441120841305986e-06, "loss": 3.3159, "step": 1565000 }, { "epoch": 3.23, "learning_rate": 1.843423302048851e-06, "loss": 3.3116, "step": 1565500 }, { "epoch": 3.24, "learning_rate": 1.8427345199671036e-06, "loss": 3.3137, "step": 1566000 }, { "epoch": 3.24, "learning_rate": 1.8420457378853562e-06, "loss": 3.3116, "step": 1566500 }, { "epoch": 3.24, "learning_rate": 1.8413569558036088e-06, "loss": 3.3156, "step": 1567000 }, { "epoch": 3.24, "learning_rate": 1.8406681737218615e-06, "loss": 3.3129, "step": 1567500 }, { "epoch": 3.24, "learning_rate": 1.839979391640114e-06, "loss": 3.3111, "step": 1568000 }, { "epoch": 3.24, "learning_rate": 1.8392906095583667e-06, "loss": 3.3106, "step": 1568500 }, { "epoch": 3.24, "learning_rate": 1.8386018274766193e-06, "loss": 3.3087, "step": 1569000 }, { "epoch": 3.24, "learning_rate": 1.8379130453948717e-06, "loss": 3.316, "step": 1569500 }, { "epoch": 3.24, "learning_rate": 1.8372242633131244e-06, "loss": 3.3146, "step": 1570000 }, { "epoch": 3.25, "learning_rate": 1.836535481231377e-06, "loss": 3.3112, "step": 1570500 }, { "epoch": 3.25, "learning_rate": 1.8358466991496296e-06, "loss": 3.3172, "step": 1571000 }, { "epoch": 3.25, "learning_rate": 1.8351579170678822e-06, "loss": 3.3159, "step": 1571500 }, { "epoch": 3.25, "learning_rate": 1.8344691349861348e-06, "loss": 3.3147, "step": 1572000 }, { "epoch": 3.25, "learning_rate": 1.8337803529043875e-06, "loss": 3.3131, "step": 1572500 }, { "epoch": 3.25, "learning_rate": 1.83309157082264e-06, "loss": 3.3085, "step": 1573000 }, { "epoch": 3.25, "learning_rate": 1.8324027887408927e-06, "loss": 3.3189, "step": 1573500 }, { "epoch": 3.25, "learning_rate": 1.831714006659145e-06, "loss": 3.3106, "step": 1574000 }, { "epoch": 3.25, "learning_rate": 1.8310252245773975e-06, "loss": 3.3191, "step": 1574500 }, { "epoch": 3.25, "learning_rate": 1.8303364424956501e-06, "loss": 3.3133, "step": 1575000 }, { "epoch": 3.26, "learning_rate": 1.8296476604139028e-06, "loss": 3.3136, "step": 1575500 }, { "epoch": 3.26, "learning_rate": 1.8289588783321554e-06, "loss": 3.3106, "step": 1576000 }, { "epoch": 3.26, "learning_rate": 1.828270096250408e-06, "loss": 3.31, "step": 1576500 }, { "epoch": 3.26, "learning_rate": 1.8275813141686606e-06, "loss": 3.3195, "step": 1577000 }, { "epoch": 3.26, "learning_rate": 1.8268925320869133e-06, "loss": 3.3197, "step": 1577500 }, { "epoch": 3.26, "learning_rate": 1.8262037500051657e-06, "loss": 3.3091, "step": 1578000 }, { "epoch": 3.26, "learning_rate": 1.8255149679234183e-06, "loss": 3.3048, "step": 1578500 }, { "epoch": 3.26, "learning_rate": 1.824826185841671e-06, "loss": 3.3092, "step": 1579000 }, { "epoch": 3.26, "learning_rate": 1.8241374037599235e-06, "loss": 3.3087, "step": 1579500 }, { "epoch": 3.26, "learning_rate": 1.8234486216781761e-06, "loss": 3.3165, "step": 1580000 }, { "epoch": 3.27, "learning_rate": 1.8227598395964288e-06, "loss": 3.3157, "step": 1580500 }, { "epoch": 3.27, "learning_rate": 1.8220710575146814e-06, "loss": 3.3097, "step": 1581000 }, { "epoch": 3.27, "learning_rate": 1.821382275432934e-06, "loss": 3.3087, "step": 1581500 }, { "epoch": 3.27, "learning_rate": 1.8206934933511864e-06, "loss": 3.3184, "step": 1582000 }, { "epoch": 3.27, "learning_rate": 1.820004711269439e-06, "loss": 3.3112, "step": 1582500 }, { "epoch": 3.27, "learning_rate": 1.8193159291876917e-06, "loss": 3.3084, "step": 1583000 }, { "epoch": 3.27, "learning_rate": 1.8186271471059443e-06, "loss": 3.3135, "step": 1583500 }, { "epoch": 3.27, "learning_rate": 1.817938365024197e-06, "loss": 3.3119, "step": 1584000 }, { "epoch": 3.27, "learning_rate": 1.8172495829424495e-06, "loss": 3.3165, "step": 1584500 }, { "epoch": 3.28, "learning_rate": 1.8165608008607022e-06, "loss": 3.3158, "step": 1585000 }, { "epoch": 3.28, "learning_rate": 1.8158720187789548e-06, "loss": 3.3082, "step": 1585500 }, { "epoch": 3.28, "learning_rate": 1.815183236697207e-06, "loss": 3.3087, "step": 1586000 }, { "epoch": 3.28, "learning_rate": 1.8144944546154596e-06, "loss": 3.314, "step": 1586500 }, { "epoch": 3.28, "learning_rate": 1.8138056725337122e-06, "loss": 3.3078, "step": 1587000 }, { "epoch": 3.28, "learning_rate": 1.8131168904519648e-06, "loss": 3.3087, "step": 1587500 }, { "epoch": 3.28, "learning_rate": 1.8124281083702175e-06, "loss": 3.3088, "step": 1588000 }, { "epoch": 3.28, "learning_rate": 1.81173932628847e-06, "loss": 3.3099, "step": 1588500 }, { "epoch": 3.28, "learning_rate": 1.8110505442067227e-06, "loss": 3.3061, "step": 1589000 }, { "epoch": 3.28, "learning_rate": 1.8103617621249753e-06, "loss": 3.3073, "step": 1589500 }, { "epoch": 3.29, "learning_rate": 1.809672980043228e-06, "loss": 3.3156, "step": 1590000 }, { "epoch": 3.29, "learning_rate": 1.8089841979614804e-06, "loss": 3.3088, "step": 1590500 }, { "epoch": 3.29, "learning_rate": 1.808295415879733e-06, "loss": 3.3086, "step": 1591000 }, { "epoch": 3.29, "learning_rate": 1.8076066337979856e-06, "loss": 3.3153, "step": 1591500 }, { "epoch": 3.29, "learning_rate": 1.8069178517162382e-06, "loss": 3.3099, "step": 1592000 }, { "epoch": 3.29, "learning_rate": 1.8062290696344908e-06, "loss": 3.31, "step": 1592500 }, { "epoch": 3.29, "learning_rate": 1.8055402875527435e-06, "loss": 3.3083, "step": 1593000 }, { "epoch": 3.29, "learning_rate": 1.804851505470996e-06, "loss": 3.3082, "step": 1593500 }, { "epoch": 3.29, "learning_rate": 1.8041627233892487e-06, "loss": 3.3094, "step": 1594000 }, { "epoch": 3.29, "learning_rate": 1.8034739413075011e-06, "loss": 3.3126, "step": 1594500 }, { "epoch": 3.3, "learning_rate": 1.8027851592257537e-06, "loss": 3.3122, "step": 1595000 }, { "epoch": 3.3, "learning_rate": 1.8020963771440064e-06, "loss": 3.3051, "step": 1595500 }, { "epoch": 3.3, "learning_rate": 1.801407595062259e-06, "loss": 3.3059, "step": 1596000 }, { "epoch": 3.3, "learning_rate": 1.8007188129805116e-06, "loss": 3.3131, "step": 1596500 }, { "epoch": 3.3, "learning_rate": 1.8000300308987642e-06, "loss": 3.3118, "step": 1597000 }, { "epoch": 3.3, "learning_rate": 1.7993412488170168e-06, "loss": 3.3053, "step": 1597500 }, { "epoch": 3.3, "learning_rate": 1.7986524667352695e-06, "loss": 3.3182, "step": 1598000 }, { "epoch": 3.3, "learning_rate": 1.7979636846535219e-06, "loss": 3.3082, "step": 1598500 }, { "epoch": 3.3, "learning_rate": 1.7972749025717743e-06, "loss": 3.3113, "step": 1599000 }, { "epoch": 3.31, "learning_rate": 1.796586120490027e-06, "loss": 3.3083, "step": 1599500 }, { "epoch": 3.31, "learning_rate": 1.7958973384082795e-06, "loss": 3.3081, "step": 1600000 }, { "epoch": 3.31, "learning_rate": 1.7952085563265321e-06, "loss": 3.3099, "step": 1600500 }, { "epoch": 3.31, "learning_rate": 1.7945197742447848e-06, "loss": 3.3151, "step": 1601000 }, { "epoch": 3.31, "learning_rate": 1.7938309921630374e-06, "loss": 3.3098, "step": 1601500 }, { "epoch": 3.31, "learning_rate": 1.79314221008129e-06, "loss": 3.3122, "step": 1602000 }, { "epoch": 3.31, "learning_rate": 1.7924534279995424e-06, "loss": 3.3039, "step": 1602500 }, { "epoch": 3.31, "learning_rate": 1.791764645917795e-06, "loss": 3.3077, "step": 1603000 }, { "epoch": 3.31, "learning_rate": 1.7910758638360477e-06, "loss": 3.3127, "step": 1603500 }, { "epoch": 3.31, "learning_rate": 1.7903870817543003e-06, "loss": 3.3096, "step": 1604000 }, { "epoch": 3.32, "learning_rate": 1.789698299672553e-06, "loss": 3.2999, "step": 1604500 }, { "epoch": 3.32, "learning_rate": 1.7890095175908055e-06, "loss": 3.3111, "step": 1605000 }, { "epoch": 3.32, "learning_rate": 1.7883207355090582e-06, "loss": 3.3058, "step": 1605500 }, { "epoch": 3.32, "learning_rate": 1.7876319534273108e-06, "loss": 3.3189, "step": 1606000 }, { "epoch": 3.32, "learning_rate": 1.7869431713455632e-06, "loss": 3.3028, "step": 1606500 }, { "epoch": 3.32, "learning_rate": 1.7862543892638158e-06, "loss": 3.3092, "step": 1607000 }, { "epoch": 3.32, "learning_rate": 1.7855656071820684e-06, "loss": 3.3122, "step": 1607500 }, { "epoch": 3.32, "learning_rate": 1.784876825100321e-06, "loss": 3.3172, "step": 1608000 }, { "epoch": 3.32, "learning_rate": 1.7841880430185737e-06, "loss": 3.3062, "step": 1608500 }, { "epoch": 3.32, "learning_rate": 1.7834992609368263e-06, "loss": 3.317, "step": 1609000 }, { "epoch": 3.33, "learning_rate": 1.782810478855079e-06, "loss": 3.3117, "step": 1609500 }, { "epoch": 3.33, "learning_rate": 1.7821216967733315e-06, "loss": 3.3186, "step": 1610000 }, { "epoch": 3.33, "learning_rate": 1.7814329146915842e-06, "loss": 3.3088, "step": 1610500 }, { "epoch": 3.33, "learning_rate": 1.7807441326098366e-06, "loss": 3.3081, "step": 1611000 }, { "epoch": 3.33, "learning_rate": 1.7800553505280892e-06, "loss": 3.3078, "step": 1611500 }, { "epoch": 3.33, "learning_rate": 1.7793665684463416e-06, "loss": 3.3081, "step": 1612000 }, { "epoch": 3.33, "learning_rate": 1.7786777863645942e-06, "loss": 3.3079, "step": 1612500 }, { "epoch": 3.33, "learning_rate": 1.7779890042828468e-06, "loss": 3.3076, "step": 1613000 }, { "epoch": 3.33, "learning_rate": 1.7773002222010995e-06, "loss": 3.3121, "step": 1613500 }, { "epoch": 3.34, "learning_rate": 1.776611440119352e-06, "loss": 3.3081, "step": 1614000 }, { "epoch": 3.34, "learning_rate": 1.7759226580376047e-06, "loss": 3.3039, "step": 1614500 }, { "epoch": 3.34, "learning_rate": 1.7752338759558571e-06, "loss": 3.3058, "step": 1615000 }, { "epoch": 3.34, "learning_rate": 1.7745450938741097e-06, "loss": 3.31, "step": 1615500 }, { "epoch": 3.34, "learning_rate": 1.7738563117923624e-06, "loss": 3.3042, "step": 1616000 }, { "epoch": 3.34, "learning_rate": 1.773167529710615e-06, "loss": 3.3053, "step": 1616500 }, { "epoch": 3.34, "learning_rate": 1.7724787476288676e-06, "loss": 3.3071, "step": 1617000 }, { "epoch": 3.34, "learning_rate": 1.7717899655471202e-06, "loss": 3.3077, "step": 1617500 }, { "epoch": 3.34, "learning_rate": 1.7711011834653728e-06, "loss": 3.3127, "step": 1618000 }, { "epoch": 3.34, "learning_rate": 1.7704124013836255e-06, "loss": 3.3118, "step": 1618500 }, { "epoch": 3.35, "learning_rate": 1.7697236193018779e-06, "loss": 3.3089, "step": 1619000 }, { "epoch": 3.35, "learning_rate": 1.7690348372201305e-06, "loss": 3.3098, "step": 1619500 }, { "epoch": 3.35, "learning_rate": 1.7683460551383831e-06, "loss": 3.3035, "step": 1620000 }, { "epoch": 3.35, "learning_rate": 1.7676572730566357e-06, "loss": 3.3069, "step": 1620500 }, { "epoch": 3.35, "learning_rate": 1.7669684909748884e-06, "loss": 3.3088, "step": 1621000 }, { "epoch": 3.35, "learning_rate": 1.766279708893141e-06, "loss": 3.3095, "step": 1621500 }, { "epoch": 3.35, "learning_rate": 1.7655909268113936e-06, "loss": 3.312, "step": 1622000 }, { "epoch": 3.35, "learning_rate": 1.7649021447296462e-06, "loss": 3.3124, "step": 1622500 }, { "epoch": 3.35, "learning_rate": 1.7642133626478986e-06, "loss": 3.3058, "step": 1623000 }, { "epoch": 3.35, "learning_rate": 1.7635245805661513e-06, "loss": 3.3159, "step": 1623500 }, { "epoch": 3.36, "learning_rate": 1.7628357984844039e-06, "loss": 3.3122, "step": 1624000 }, { "epoch": 3.36, "learning_rate": 1.7621470164026563e-06, "loss": 3.307, "step": 1624500 }, { "epoch": 3.36, "learning_rate": 1.761458234320909e-06, "loss": 3.3027, "step": 1625000 }, { "epoch": 3.36, "learning_rate": 1.7607694522391615e-06, "loss": 3.314, "step": 1625500 }, { "epoch": 3.36, "learning_rate": 1.7600806701574142e-06, "loss": 3.3106, "step": 1626000 }, { "epoch": 3.36, "learning_rate": 1.7593918880756668e-06, "loss": 3.3113, "step": 1626500 }, { "epoch": 3.36, "learning_rate": 1.7587031059939192e-06, "loss": 3.3059, "step": 1627000 }, { "epoch": 3.36, "learning_rate": 1.7580143239121718e-06, "loss": 3.3099, "step": 1627500 }, { "epoch": 3.36, "learning_rate": 1.7573255418304244e-06, "loss": 3.3064, "step": 1628000 }, { "epoch": 3.37, "learning_rate": 1.756636759748677e-06, "loss": 3.3079, "step": 1628500 }, { "epoch": 3.37, "learning_rate": 1.7559479776669297e-06, "loss": 3.3123, "step": 1629000 }, { "epoch": 3.37, "learning_rate": 1.7552591955851823e-06, "loss": 3.3044, "step": 1629500 }, { "epoch": 3.37, "learning_rate": 1.754570413503435e-06, "loss": 3.3111, "step": 1630000 }, { "epoch": 3.37, "learning_rate": 1.7538816314216875e-06, "loss": 3.3076, "step": 1630500 }, { "epoch": 3.37, "learning_rate": 1.7531928493399402e-06, "loss": 3.3106, "step": 1631000 }, { "epoch": 3.37, "learning_rate": 1.7525040672581926e-06, "loss": 3.3061, "step": 1631500 }, { "epoch": 3.37, "learning_rate": 1.7518152851764452e-06, "loss": 3.3058, "step": 1632000 }, { "epoch": 3.37, "learning_rate": 1.7511265030946978e-06, "loss": 3.3063, "step": 1632500 }, { "epoch": 3.37, "learning_rate": 1.7504377210129504e-06, "loss": 3.3055, "step": 1633000 }, { "epoch": 3.38, "learning_rate": 1.749748938931203e-06, "loss": 3.3083, "step": 1633500 }, { "epoch": 3.38, "learning_rate": 1.7490601568494557e-06, "loss": 3.3096, "step": 1634000 }, { "epoch": 3.38, "learning_rate": 1.7483713747677083e-06, "loss": 3.3064, "step": 1634500 }, { "epoch": 3.38, "learning_rate": 1.747682592685961e-06, "loss": 3.3098, "step": 1635000 }, { "epoch": 3.38, "learning_rate": 1.7469938106042133e-06, "loss": 3.3005, "step": 1635500 }, { "epoch": 3.38, "learning_rate": 1.746305028522466e-06, "loss": 3.3048, "step": 1636000 }, { "epoch": 3.38, "learning_rate": 1.7456162464407186e-06, "loss": 3.3031, "step": 1636500 }, { "epoch": 3.38, "learning_rate": 1.7449274643589712e-06, "loss": 3.3069, "step": 1637000 }, { "epoch": 3.38, "learning_rate": 1.7442386822772236e-06, "loss": 3.3059, "step": 1637500 }, { "epoch": 3.38, "learning_rate": 1.7435499001954762e-06, "loss": 3.3029, "step": 1638000 }, { "epoch": 3.39, "learning_rate": 1.7428611181137288e-06, "loss": 3.2997, "step": 1638500 }, { "epoch": 3.39, "learning_rate": 1.7421723360319815e-06, "loss": 3.3033, "step": 1639000 }, { "epoch": 3.39, "learning_rate": 1.7414835539502339e-06, "loss": 3.3043, "step": 1639500 }, { "epoch": 3.39, "learning_rate": 1.7407947718684865e-06, "loss": 3.3069, "step": 1640000 }, { "epoch": 3.39, "learning_rate": 1.7401059897867391e-06, "loss": 3.305, "step": 1640500 }, { "epoch": 3.39, "learning_rate": 1.7394172077049917e-06, "loss": 3.3016, "step": 1641000 }, { "epoch": 3.39, "learning_rate": 1.7387284256232444e-06, "loss": 3.3059, "step": 1641500 }, { "epoch": 3.39, "learning_rate": 1.738039643541497e-06, "loss": 3.3025, "step": 1642000 }, { "epoch": 3.39, "learning_rate": 1.7373508614597496e-06, "loss": 3.3055, "step": 1642500 }, { "epoch": 3.4, "learning_rate": 1.7366620793780022e-06, "loss": 3.3035, "step": 1643000 }, { "epoch": 3.4, "learning_rate": 1.7359732972962546e-06, "loss": 3.307, "step": 1643500 }, { "epoch": 3.4, "learning_rate": 1.7352845152145073e-06, "loss": 3.3064, "step": 1644000 }, { "epoch": 3.4, "learning_rate": 1.7345957331327599e-06, "loss": 3.307, "step": 1644500 }, { "epoch": 3.4, "learning_rate": 1.7339069510510125e-06, "loss": 3.3093, "step": 1645000 }, { "epoch": 3.4, "learning_rate": 1.7332181689692651e-06, "loss": 3.3071, "step": 1645500 }, { "epoch": 3.4, "learning_rate": 1.7325293868875177e-06, "loss": 3.3112, "step": 1646000 }, { "epoch": 3.4, "learning_rate": 1.7318406048057704e-06, "loss": 3.2986, "step": 1646500 }, { "epoch": 3.4, "learning_rate": 1.731151822724023e-06, "loss": 3.3016, "step": 1647000 }, { "epoch": 3.4, "learning_rate": 1.7304630406422754e-06, "loss": 3.3038, "step": 1647500 }, { "epoch": 3.41, "learning_rate": 1.729774258560528e-06, "loss": 3.307, "step": 1648000 }, { "epoch": 3.41, "learning_rate": 1.7290854764787806e-06, "loss": 3.314, "step": 1648500 }, { "epoch": 3.41, "learning_rate": 1.7283966943970333e-06, "loss": 3.3051, "step": 1649000 }, { "epoch": 3.41, "learning_rate": 1.7277079123152859e-06, "loss": 3.3082, "step": 1649500 }, { "epoch": 3.41, "learning_rate": 1.7270191302335385e-06, "loss": 3.3036, "step": 1650000 }, { "epoch": 3.41, "learning_rate": 1.726330348151791e-06, "loss": 3.2992, "step": 1650500 }, { "epoch": 3.41, "learning_rate": 1.7256415660700435e-06, "loss": 3.2998, "step": 1651000 }, { "epoch": 3.41, "learning_rate": 1.7249527839882962e-06, "loss": 3.3068, "step": 1651500 }, { "epoch": 3.41, "learning_rate": 1.7242640019065486e-06, "loss": 3.3037, "step": 1652000 }, { "epoch": 3.41, "learning_rate": 1.7235752198248012e-06, "loss": 3.3046, "step": 1652500 }, { "epoch": 3.42, "learning_rate": 1.7228864377430538e-06, "loss": 3.3088, "step": 1653000 }, { "epoch": 3.42, "learning_rate": 1.7221976556613064e-06, "loss": 3.3099, "step": 1653500 }, { "epoch": 3.42, "learning_rate": 1.721508873579559e-06, "loss": 3.3101, "step": 1654000 }, { "epoch": 3.42, "learning_rate": 1.7208200914978117e-06, "loss": 3.2985, "step": 1654500 }, { "epoch": 3.42, "learning_rate": 1.7201313094160643e-06, "loss": 3.3004, "step": 1655000 }, { "epoch": 3.42, "learning_rate": 1.719442527334317e-06, "loss": 3.3008, "step": 1655500 }, { "epoch": 3.42, "learning_rate": 1.7187537452525693e-06, "loss": 3.3063, "step": 1656000 }, { "epoch": 3.42, "learning_rate": 1.718064963170822e-06, "loss": 3.3014, "step": 1656500 }, { "epoch": 3.42, "learning_rate": 1.7173761810890746e-06, "loss": 3.3098, "step": 1657000 }, { "epoch": 3.42, "learning_rate": 1.7166873990073272e-06, "loss": 3.3025, "step": 1657500 }, { "epoch": 3.43, "learning_rate": 1.7159986169255798e-06, "loss": 3.3058, "step": 1658000 }, { "epoch": 3.43, "learning_rate": 1.7153098348438324e-06, "loss": 3.3083, "step": 1658500 }, { "epoch": 3.43, "learning_rate": 1.714621052762085e-06, "loss": 3.3075, "step": 1659000 }, { "epoch": 3.43, "learning_rate": 1.7139322706803377e-06, "loss": 3.2991, "step": 1659500 }, { "epoch": 3.43, "learning_rate": 1.71324348859859e-06, "loss": 3.3037, "step": 1660000 }, { "epoch": 3.43, "learning_rate": 1.7125547065168427e-06, "loss": 3.3077, "step": 1660500 }, { "epoch": 3.43, "learning_rate": 1.7118659244350953e-06, "loss": 3.3002, "step": 1661000 }, { "epoch": 3.43, "learning_rate": 1.711177142353348e-06, "loss": 3.3024, "step": 1661500 }, { "epoch": 3.43, "learning_rate": 1.7104883602716006e-06, "loss": 3.2995, "step": 1662000 }, { "epoch": 3.44, "learning_rate": 1.7097995781898532e-06, "loss": 3.3046, "step": 1662500 }, { "epoch": 3.44, "learning_rate": 1.7091107961081056e-06, "loss": 3.305, "step": 1663000 }, { "epoch": 3.44, "learning_rate": 1.7084220140263582e-06, "loss": 3.3051, "step": 1663500 }, { "epoch": 3.44, "learning_rate": 1.7077332319446106e-06, "loss": 3.3018, "step": 1664000 }, { "epoch": 3.44, "learning_rate": 1.7070444498628633e-06, "loss": 3.3021, "step": 1664500 }, { "epoch": 3.44, "learning_rate": 1.7063556677811159e-06, "loss": 3.3098, "step": 1665000 }, { "epoch": 3.44, "learning_rate": 1.7056668856993685e-06, "loss": 3.3047, "step": 1665500 }, { "epoch": 3.44, "learning_rate": 1.7049781036176211e-06, "loss": 3.3115, "step": 1666000 }, { "epoch": 3.44, "learning_rate": 1.7042893215358737e-06, "loss": 3.3026, "step": 1666500 }, { "epoch": 3.44, "learning_rate": 1.7036005394541264e-06, "loss": 3.301, "step": 1667000 }, { "epoch": 3.45, "learning_rate": 1.702911757372379e-06, "loss": 3.3035, "step": 1667500 }, { "epoch": 3.45, "learning_rate": 1.7022229752906314e-06, "loss": 3.297, "step": 1668000 }, { "epoch": 3.45, "learning_rate": 1.701534193208884e-06, "loss": 3.3051, "step": 1668500 }, { "epoch": 3.45, "learning_rate": 1.7008454111271366e-06, "loss": 3.3077, "step": 1669000 }, { "epoch": 3.45, "learning_rate": 1.7001566290453893e-06, "loss": 3.3043, "step": 1669500 }, { "epoch": 3.45, "learning_rate": 1.6994678469636419e-06, "loss": 3.3031, "step": 1670000 }, { "epoch": 3.45, "learning_rate": 1.6987790648818945e-06, "loss": 3.3003, "step": 1670500 }, { "epoch": 3.45, "learning_rate": 1.6980902828001471e-06, "loss": 3.3029, "step": 1671000 }, { "epoch": 3.45, "learning_rate": 1.6974015007183998e-06, "loss": 3.3083, "step": 1671500 }, { "epoch": 3.45, "learning_rate": 1.6967127186366524e-06, "loss": 3.2991, "step": 1672000 }, { "epoch": 3.46, "learning_rate": 1.6960239365549048e-06, "loss": 3.3024, "step": 1672500 }, { "epoch": 3.46, "learning_rate": 1.6953351544731574e-06, "loss": 3.2945, "step": 1673000 }, { "epoch": 3.46, "learning_rate": 1.69464637239141e-06, "loss": 3.3074, "step": 1673500 }, { "epoch": 3.46, "learning_rate": 1.6939575903096626e-06, "loss": 3.2997, "step": 1674000 }, { "epoch": 3.46, "learning_rate": 1.6932688082279153e-06, "loss": 3.3025, "step": 1674500 }, { "epoch": 3.46, "learning_rate": 1.6925800261461679e-06, "loss": 3.3099, "step": 1675000 }, { "epoch": 3.46, "learning_rate": 1.6918912440644205e-06, "loss": 3.301, "step": 1675500 }, { "epoch": 3.46, "learning_rate": 1.691202461982673e-06, "loss": 3.3024, "step": 1676000 }, { "epoch": 3.46, "learning_rate": 1.6905136799009253e-06, "loss": 3.3023, "step": 1676500 }, { "epoch": 3.47, "learning_rate": 1.689824897819178e-06, "loss": 3.304, "step": 1677000 }, { "epoch": 3.47, "learning_rate": 1.6891361157374306e-06, "loss": 3.3085, "step": 1677500 }, { "epoch": 3.47, "learning_rate": 1.6884473336556832e-06, "loss": 3.3018, "step": 1678000 }, { "epoch": 3.47, "learning_rate": 1.6877585515739358e-06, "loss": 3.2991, "step": 1678500 }, { "epoch": 3.47, "learning_rate": 1.6870697694921884e-06, "loss": 3.3021, "step": 1679000 }, { "epoch": 3.47, "learning_rate": 1.686380987410441e-06, "loss": 3.3009, "step": 1679500 }, { "epoch": 3.47, "learning_rate": 1.6856922053286937e-06, "loss": 3.3074, "step": 1680000 }, { "epoch": 3.47, "learning_rate": 1.685003423246946e-06, "loss": 3.3018, "step": 1680500 }, { "epoch": 3.47, "learning_rate": 1.6843146411651987e-06, "loss": 3.2986, "step": 1681000 }, { "epoch": 3.47, "learning_rate": 1.6836258590834513e-06, "loss": 3.3034, "step": 1681500 }, { "epoch": 3.48, "learning_rate": 1.682937077001704e-06, "loss": 3.3022, "step": 1682000 }, { "epoch": 3.48, "learning_rate": 1.6822482949199566e-06, "loss": 3.3017, "step": 1682500 }, { "epoch": 3.48, "learning_rate": 1.6815595128382092e-06, "loss": 3.3083, "step": 1683000 }, { "epoch": 3.48, "learning_rate": 1.6808707307564618e-06, "loss": 3.3064, "step": 1683500 }, { "epoch": 3.48, "learning_rate": 1.6801819486747144e-06, "loss": 3.3001, "step": 1684000 }, { "epoch": 3.48, "learning_rate": 1.6794931665929669e-06, "loss": 3.3027, "step": 1684500 }, { "epoch": 3.48, "learning_rate": 1.6788043845112195e-06, "loss": 3.2987, "step": 1685000 }, { "epoch": 3.48, "learning_rate": 1.678115602429472e-06, "loss": 3.2958, "step": 1685500 }, { "epoch": 3.48, "learning_rate": 1.6774268203477247e-06, "loss": 3.3014, "step": 1686000 }, { "epoch": 3.48, "learning_rate": 1.6767380382659773e-06, "loss": 3.3104, "step": 1686500 }, { "epoch": 3.49, "learning_rate": 1.67604925618423e-06, "loss": 3.3013, "step": 1687000 }, { "epoch": 3.49, "learning_rate": 1.6753604741024826e-06, "loss": 3.303, "step": 1687500 }, { "epoch": 3.49, "learning_rate": 1.6746716920207352e-06, "loss": 3.3045, "step": 1688000 }, { "epoch": 3.49, "learning_rate": 1.6739829099389874e-06, "loss": 3.3007, "step": 1688500 }, { "epoch": 3.49, "learning_rate": 1.67329412785724e-06, "loss": 3.2982, "step": 1689000 }, { "epoch": 3.49, "learning_rate": 1.6726053457754926e-06, "loss": 3.2981, "step": 1689500 }, { "epoch": 3.49, "learning_rate": 1.6719165636937453e-06, "loss": 3.299, "step": 1690000 }, { "epoch": 3.49, "learning_rate": 1.6712277816119979e-06, "loss": 3.3025, "step": 1690500 }, { "epoch": 3.49, "learning_rate": 1.6705389995302505e-06, "loss": 3.2999, "step": 1691000 }, { "epoch": 3.5, "learning_rate": 1.6698502174485031e-06, "loss": 3.3039, "step": 1691500 }, { "epoch": 3.5, "learning_rate": 1.6691614353667558e-06, "loss": 3.2955, "step": 1692000 }, { "epoch": 3.5, "learning_rate": 1.6684726532850084e-06, "loss": 3.3017, "step": 1692500 }, { "epoch": 3.5, "learning_rate": 1.6677838712032608e-06, "loss": 3.2955, "step": 1693000 }, { "epoch": 3.5, "learning_rate": 1.6670950891215134e-06, "loss": 3.2994, "step": 1693500 }, { "epoch": 3.5, "learning_rate": 1.666406307039766e-06, "loss": 3.2952, "step": 1694000 }, { "epoch": 3.5, "learning_rate": 1.6657175249580186e-06, "loss": 3.3034, "step": 1694500 }, { "epoch": 3.5, "learning_rate": 1.6650287428762713e-06, "loss": 3.3038, "step": 1695000 }, { "epoch": 3.5, "learning_rate": 1.6643399607945239e-06, "loss": 3.3004, "step": 1695500 }, { "epoch": 3.5, "learning_rate": 1.6636511787127765e-06, "loss": 3.299, "step": 1696000 }, { "epoch": 3.51, "learning_rate": 1.6629623966310291e-06, "loss": 3.2998, "step": 1696500 }, { "epoch": 3.51, "learning_rate": 1.6622736145492815e-06, "loss": 3.3031, "step": 1697000 }, { "epoch": 3.51, "learning_rate": 1.6615848324675342e-06, "loss": 3.2984, "step": 1697500 }, { "epoch": 3.51, "learning_rate": 1.6608960503857868e-06, "loss": 3.2969, "step": 1698000 }, { "epoch": 3.51, "learning_rate": 1.6602072683040394e-06, "loss": 3.3082, "step": 1698500 }, { "epoch": 3.51, "learning_rate": 1.659518486222292e-06, "loss": 3.3031, "step": 1699000 }, { "epoch": 3.51, "learning_rate": 1.6588297041405447e-06, "loss": 3.3078, "step": 1699500 }, { "epoch": 3.51, "learning_rate": 1.6581409220587973e-06, "loss": 3.3043, "step": 1700000 }, { "epoch": 3.51, "learning_rate": 1.65745213997705e-06, "loss": 3.3041, "step": 1700500 }, { "epoch": 3.51, "learning_rate": 1.656763357895302e-06, "loss": 3.2988, "step": 1701000 }, { "epoch": 3.52, "learning_rate": 1.6560745758135547e-06, "loss": 3.3, "step": 1701500 }, { "epoch": 3.52, "learning_rate": 1.6553857937318073e-06, "loss": 3.3022, "step": 1702000 }, { "epoch": 3.52, "learning_rate": 1.65469701165006e-06, "loss": 3.303, "step": 1702500 }, { "epoch": 3.52, "learning_rate": 1.6540082295683126e-06, "loss": 3.2959, "step": 1703000 }, { "epoch": 3.52, "learning_rate": 1.6533194474865652e-06, "loss": 3.3015, "step": 1703500 }, { "epoch": 3.52, "learning_rate": 1.6526306654048178e-06, "loss": 3.3005, "step": 1704000 }, { "epoch": 3.52, "learning_rate": 1.6519418833230704e-06, "loss": 3.3011, "step": 1704500 }, { "epoch": 3.52, "learning_rate": 1.6512531012413229e-06, "loss": 3.3059, "step": 1705000 }, { "epoch": 3.52, "learning_rate": 1.6505643191595755e-06, "loss": 3.3054, "step": 1705500 }, { "epoch": 3.53, "learning_rate": 1.649875537077828e-06, "loss": 3.3043, "step": 1706000 }, { "epoch": 3.53, "learning_rate": 1.6491867549960807e-06, "loss": 3.3005, "step": 1706500 }, { "epoch": 3.53, "learning_rate": 1.6484979729143333e-06, "loss": 3.2957, "step": 1707000 }, { "epoch": 3.53, "learning_rate": 1.647809190832586e-06, "loss": 3.2996, "step": 1707500 }, { "epoch": 3.53, "learning_rate": 1.6471204087508386e-06, "loss": 3.2975, "step": 1708000 }, { "epoch": 3.53, "learning_rate": 1.6464316266690912e-06, "loss": 3.3013, "step": 1708500 }, { "epoch": 3.53, "learning_rate": 1.6457428445873436e-06, "loss": 3.3, "step": 1709000 }, { "epoch": 3.53, "learning_rate": 1.6450540625055962e-06, "loss": 3.2987, "step": 1709500 }, { "epoch": 3.53, "learning_rate": 1.6443652804238489e-06, "loss": 3.3008, "step": 1710000 }, { "epoch": 3.53, "learning_rate": 1.6436764983421015e-06, "loss": 3.2982, "step": 1710500 }, { "epoch": 3.54, "learning_rate": 1.642987716260354e-06, "loss": 3.299, "step": 1711000 }, { "epoch": 3.54, "learning_rate": 1.6422989341786067e-06, "loss": 3.3033, "step": 1711500 }, { "epoch": 3.54, "learning_rate": 1.6416101520968593e-06, "loss": 3.2962, "step": 1712000 }, { "epoch": 3.54, "learning_rate": 1.640921370015112e-06, "loss": 3.2989, "step": 1712500 }, { "epoch": 3.54, "learning_rate": 1.6402325879333646e-06, "loss": 3.2925, "step": 1713000 }, { "epoch": 3.54, "learning_rate": 1.6395438058516168e-06, "loss": 3.2943, "step": 1713500 }, { "epoch": 3.54, "learning_rate": 1.6388550237698694e-06, "loss": 3.2947, "step": 1714000 }, { "epoch": 3.54, "learning_rate": 1.638166241688122e-06, "loss": 3.2999, "step": 1714500 }, { "epoch": 3.54, "learning_rate": 1.6374774596063747e-06, "loss": 3.2967, "step": 1715000 }, { "epoch": 3.54, "learning_rate": 1.6367886775246273e-06, "loss": 3.302, "step": 1715500 }, { "epoch": 3.55, "learning_rate": 1.6360998954428799e-06, "loss": 3.3009, "step": 1716000 }, { "epoch": 3.55, "learning_rate": 1.6354111133611325e-06, "loss": 3.2945, "step": 1716500 }, { "epoch": 3.55, "learning_rate": 1.6347223312793851e-06, "loss": 3.3002, "step": 1717000 }, { "epoch": 3.55, "learning_rate": 1.6340335491976375e-06, "loss": 3.2965, "step": 1717500 }, { "epoch": 3.55, "learning_rate": 1.6333447671158902e-06, "loss": 3.2861, "step": 1718000 }, { "epoch": 3.55, "learning_rate": 1.6326559850341428e-06, "loss": 3.3009, "step": 1718500 }, { "epoch": 3.55, "learning_rate": 1.6319672029523954e-06, "loss": 3.2983, "step": 1719000 }, { "epoch": 3.55, "learning_rate": 1.631278420870648e-06, "loss": 3.3024, "step": 1719500 }, { "epoch": 3.55, "learning_rate": 1.6305896387889007e-06, "loss": 3.2969, "step": 1720000 }, { "epoch": 3.56, "learning_rate": 1.6299008567071533e-06, "loss": 3.2967, "step": 1720500 }, { "epoch": 3.56, "learning_rate": 1.629212074625406e-06, "loss": 3.2936, "step": 1721000 }, { "epoch": 3.56, "learning_rate": 1.6285232925436583e-06, "loss": 3.3022, "step": 1721500 }, { "epoch": 3.56, "learning_rate": 1.627834510461911e-06, "loss": 3.2992, "step": 1722000 }, { "epoch": 3.56, "learning_rate": 1.6271457283801636e-06, "loss": 3.2961, "step": 1722500 }, { "epoch": 3.56, "learning_rate": 1.6264569462984162e-06, "loss": 3.2971, "step": 1723000 }, { "epoch": 3.56, "learning_rate": 1.6257681642166688e-06, "loss": 3.3037, "step": 1723500 }, { "epoch": 3.56, "learning_rate": 1.6250793821349214e-06, "loss": 3.3049, "step": 1724000 }, { "epoch": 3.56, "learning_rate": 1.624390600053174e-06, "loss": 3.2996, "step": 1724500 }, { "epoch": 3.56, "learning_rate": 1.6237018179714267e-06, "loss": 3.2947, "step": 1725000 }, { "epoch": 3.57, "learning_rate": 1.623013035889679e-06, "loss": 3.3028, "step": 1725500 }, { "epoch": 3.57, "learning_rate": 1.6223242538079317e-06, "loss": 3.2964, "step": 1726000 }, { "epoch": 3.57, "learning_rate": 1.621635471726184e-06, "loss": 3.2974, "step": 1726500 }, { "epoch": 3.57, "learning_rate": 1.6209466896444367e-06, "loss": 3.3043, "step": 1727000 }, { "epoch": 3.57, "learning_rate": 1.6202579075626893e-06, "loss": 3.2952, "step": 1727500 }, { "epoch": 3.57, "learning_rate": 1.619569125480942e-06, "loss": 3.2979, "step": 1728000 }, { "epoch": 3.57, "learning_rate": 1.6188803433991946e-06, "loss": 3.296, "step": 1728500 }, { "epoch": 3.57, "learning_rate": 1.6181915613174472e-06, "loss": 3.2911, "step": 1729000 }, { "epoch": 3.57, "learning_rate": 1.6175027792356998e-06, "loss": 3.296, "step": 1729500 }, { "epoch": 3.57, "learning_rate": 1.6168139971539522e-06, "loss": 3.3018, "step": 1730000 }, { "epoch": 3.58, "learning_rate": 1.6161252150722049e-06, "loss": 3.2981, "step": 1730500 }, { "epoch": 3.58, "learning_rate": 1.6154364329904575e-06, "loss": 3.2949, "step": 1731000 }, { "epoch": 3.58, "learning_rate": 1.61474765090871e-06, "loss": 3.29, "step": 1731500 }, { "epoch": 3.58, "learning_rate": 1.6140588688269627e-06, "loss": 3.2976, "step": 1732000 }, { "epoch": 3.58, "learning_rate": 1.6133700867452153e-06, "loss": 3.2955, "step": 1732500 }, { "epoch": 3.58, "learning_rate": 1.612681304663468e-06, "loss": 3.2937, "step": 1733000 }, { "epoch": 3.58, "learning_rate": 1.6119925225817206e-06, "loss": 3.2968, "step": 1733500 }, { "epoch": 3.58, "learning_rate": 1.611303740499973e-06, "loss": 3.2968, "step": 1734000 }, { "epoch": 3.58, "learning_rate": 1.6106149584182256e-06, "loss": 3.2955, "step": 1734500 }, { "epoch": 3.59, "learning_rate": 1.6099261763364782e-06, "loss": 3.2964, "step": 1735000 }, { "epoch": 3.59, "learning_rate": 1.6092373942547309e-06, "loss": 3.294, "step": 1735500 }, { "epoch": 3.59, "learning_rate": 1.6085486121729835e-06, "loss": 3.296, "step": 1736000 }, { "epoch": 3.59, "learning_rate": 1.6078598300912361e-06, "loss": 3.3001, "step": 1736500 }, { "epoch": 3.59, "learning_rate": 1.6071710480094887e-06, "loss": 3.2985, "step": 1737000 }, { "epoch": 3.59, "learning_rate": 1.6064822659277414e-06, "loss": 3.2899, "step": 1737500 }, { "epoch": 3.59, "learning_rate": 1.6057934838459938e-06, "loss": 3.2958, "step": 1738000 }, { "epoch": 3.59, "learning_rate": 1.6051047017642464e-06, "loss": 3.3022, "step": 1738500 }, { "epoch": 3.59, "learning_rate": 1.604415919682499e-06, "loss": 3.2894, "step": 1739000 }, { "epoch": 3.59, "learning_rate": 1.6037271376007514e-06, "loss": 3.2997, "step": 1739500 }, { "epoch": 3.6, "learning_rate": 1.603038355519004e-06, "loss": 3.2985, "step": 1740000 }, { "epoch": 3.6, "learning_rate": 1.6023495734372567e-06, "loss": 3.2972, "step": 1740500 }, { "epoch": 3.6, "learning_rate": 1.6016607913555093e-06, "loss": 3.2974, "step": 1741000 }, { "epoch": 3.6, "learning_rate": 1.600972009273762e-06, "loss": 3.2931, "step": 1741500 }, { "epoch": 3.6, "learning_rate": 1.6002832271920143e-06, "loss": 3.2927, "step": 1742000 }, { "epoch": 3.6, "learning_rate": 1.599594445110267e-06, "loss": 3.2983, "step": 1742500 }, { "epoch": 3.6, "learning_rate": 1.5989056630285196e-06, "loss": 3.2954, "step": 1743000 }, { "epoch": 3.6, "learning_rate": 1.5982168809467722e-06, "loss": 3.2984, "step": 1743500 }, { "epoch": 3.6, "learning_rate": 1.5975280988650248e-06, "loss": 3.2985, "step": 1744000 }, { "epoch": 3.6, "learning_rate": 1.5968393167832774e-06, "loss": 3.3012, "step": 1744500 }, { "epoch": 3.61, "learning_rate": 1.59615053470153e-06, "loss": 3.2905, "step": 1745000 }, { "epoch": 3.61, "learning_rate": 1.5954617526197827e-06, "loss": 3.2944, "step": 1745500 }, { "epoch": 3.61, "learning_rate": 1.594772970538035e-06, "loss": 3.2946, "step": 1746000 }, { "epoch": 3.61, "learning_rate": 1.5940841884562877e-06, "loss": 3.2962, "step": 1746500 }, { "epoch": 3.61, "learning_rate": 1.5933954063745403e-06, "loss": 3.2993, "step": 1747000 }, { "epoch": 3.61, "learning_rate": 1.592706624292793e-06, "loss": 3.3014, "step": 1747500 }, { "epoch": 3.61, "learning_rate": 1.5920178422110456e-06, "loss": 3.2975, "step": 1748000 }, { "epoch": 3.61, "learning_rate": 1.5913290601292982e-06, "loss": 3.2928, "step": 1748500 }, { "epoch": 3.61, "learning_rate": 1.5906402780475508e-06, "loss": 3.3009, "step": 1749000 }, { "epoch": 3.62, "learning_rate": 1.5899514959658034e-06, "loss": 3.3001, "step": 1749500 }, { "epoch": 3.62, "learning_rate": 1.589262713884056e-06, "loss": 3.2967, "step": 1750000 }, { "epoch": 3.62, "learning_rate": 1.5885739318023085e-06, "loss": 3.289, "step": 1750500 }, { "epoch": 3.62, "learning_rate": 1.587885149720561e-06, "loss": 3.2921, "step": 1751000 }, { "epoch": 3.62, "learning_rate": 1.5871963676388137e-06, "loss": 3.2914, "step": 1751500 }, { "epoch": 3.62, "learning_rate": 1.586507585557066e-06, "loss": 3.2943, "step": 1752000 }, { "epoch": 3.62, "learning_rate": 1.5858188034753187e-06, "loss": 3.2964, "step": 1752500 }, { "epoch": 3.62, "learning_rate": 1.5851300213935713e-06, "loss": 3.303, "step": 1753000 }, { "epoch": 3.62, "learning_rate": 1.584441239311824e-06, "loss": 3.2937, "step": 1753500 }, { "epoch": 3.62, "learning_rate": 1.5837524572300766e-06, "loss": 3.2978, "step": 1754000 }, { "epoch": 3.63, "learning_rate": 1.583063675148329e-06, "loss": 3.2923, "step": 1754500 }, { "epoch": 3.63, "learning_rate": 1.5823748930665816e-06, "loss": 3.2929, "step": 1755000 }, { "epoch": 3.63, "learning_rate": 1.5816861109848342e-06, "loss": 3.2932, "step": 1755500 }, { "epoch": 3.63, "learning_rate": 1.5809973289030869e-06, "loss": 3.2924, "step": 1756000 }, { "epoch": 3.63, "learning_rate": 1.5803085468213395e-06, "loss": 3.2936, "step": 1756500 }, { "epoch": 3.63, "learning_rate": 1.5796197647395921e-06, "loss": 3.2924, "step": 1757000 }, { "epoch": 3.63, "learning_rate": 1.5789309826578447e-06, "loss": 3.2945, "step": 1757500 }, { "epoch": 3.63, "learning_rate": 1.5782422005760974e-06, "loss": 3.2963, "step": 1758000 }, { "epoch": 3.63, "learning_rate": 1.5775534184943498e-06, "loss": 3.2962, "step": 1758500 }, { "epoch": 3.63, "learning_rate": 1.5768646364126024e-06, "loss": 3.2977, "step": 1759000 }, { "epoch": 3.64, "learning_rate": 1.576175854330855e-06, "loss": 3.2953, "step": 1759500 }, { "epoch": 3.64, "learning_rate": 1.5754870722491076e-06, "loss": 3.2945, "step": 1760000 }, { "epoch": 3.64, "learning_rate": 1.5747982901673602e-06, "loss": 3.2899, "step": 1760500 }, { "epoch": 3.64, "learning_rate": 1.5741095080856129e-06, "loss": 3.2924, "step": 1761000 }, { "epoch": 3.64, "learning_rate": 1.5734207260038655e-06, "loss": 3.294, "step": 1761500 }, { "epoch": 3.64, "learning_rate": 1.5727319439221181e-06, "loss": 3.2988, "step": 1762000 }, { "epoch": 3.64, "learning_rate": 1.5720431618403705e-06, "loss": 3.2938, "step": 1762500 }, { "epoch": 3.64, "learning_rate": 1.5713543797586231e-06, "loss": 3.2917, "step": 1763000 }, { "epoch": 3.64, "learning_rate": 1.5706655976768758e-06, "loss": 3.2931, "step": 1763500 }, { "epoch": 3.65, "learning_rate": 1.5699768155951284e-06, "loss": 3.2999, "step": 1764000 }, { "epoch": 3.65, "learning_rate": 1.569288033513381e-06, "loss": 3.2957, "step": 1764500 }, { "epoch": 3.65, "learning_rate": 1.5685992514316334e-06, "loss": 3.2886, "step": 1765000 }, { "epoch": 3.65, "learning_rate": 1.567910469349886e-06, "loss": 3.3026, "step": 1765500 }, { "epoch": 3.65, "learning_rate": 1.5672216872681387e-06, "loss": 3.2984, "step": 1766000 }, { "epoch": 3.65, "learning_rate": 1.566532905186391e-06, "loss": 3.2968, "step": 1766500 }, { "epoch": 3.65, "learning_rate": 1.5658441231046437e-06, "loss": 3.291, "step": 1767000 }, { "epoch": 3.65, "learning_rate": 1.5651553410228963e-06, "loss": 3.2954, "step": 1767500 }, { "epoch": 3.65, "learning_rate": 1.564466558941149e-06, "loss": 3.2944, "step": 1768000 }, { "epoch": 3.65, "learning_rate": 1.5637777768594016e-06, "loss": 3.2864, "step": 1768500 }, { "epoch": 3.66, "learning_rate": 1.5630889947776542e-06, "loss": 3.29, "step": 1769000 }, { "epoch": 3.66, "learning_rate": 1.5624002126959068e-06, "loss": 3.293, "step": 1769500 }, { "epoch": 3.66, "learning_rate": 1.5617114306141594e-06, "loss": 3.2905, "step": 1770000 }, { "epoch": 3.66, "learning_rate": 1.561022648532412e-06, "loss": 3.2981, "step": 1770500 }, { "epoch": 3.66, "learning_rate": 1.5603338664506645e-06, "loss": 3.2922, "step": 1771000 }, { "epoch": 3.66, "learning_rate": 1.559645084368917e-06, "loss": 3.2956, "step": 1771500 }, { "epoch": 3.66, "learning_rate": 1.5589563022871697e-06, "loss": 3.2958, "step": 1772000 }, { "epoch": 3.66, "learning_rate": 1.5582675202054223e-06, "loss": 3.2969, "step": 1772500 }, { "epoch": 3.66, "learning_rate": 1.557578738123675e-06, "loss": 3.2917, "step": 1773000 }, { "epoch": 3.66, "learning_rate": 1.5568899560419276e-06, "loss": 3.2916, "step": 1773500 }, { "epoch": 3.67, "learning_rate": 1.5562011739601802e-06, "loss": 3.297, "step": 1774000 }, { "epoch": 3.67, "learning_rate": 1.5555123918784328e-06, "loss": 3.2845, "step": 1774500 }, { "epoch": 3.67, "learning_rate": 1.5548236097966852e-06, "loss": 3.2977, "step": 1775000 }, { "epoch": 3.67, "learning_rate": 1.5541348277149378e-06, "loss": 3.2938, "step": 1775500 }, { "epoch": 3.67, "learning_rate": 1.5534460456331905e-06, "loss": 3.2932, "step": 1776000 }, { "epoch": 3.67, "learning_rate": 1.552757263551443e-06, "loss": 3.2962, "step": 1776500 }, { "epoch": 3.67, "learning_rate": 1.5520684814696957e-06, "loss": 3.2906, "step": 1777000 }, { "epoch": 3.67, "learning_rate": 1.5513796993879481e-06, "loss": 3.2913, "step": 1777500 }, { "epoch": 3.67, "learning_rate": 1.5506909173062007e-06, "loss": 3.2953, "step": 1778000 }, { "epoch": 3.67, "learning_rate": 1.5500021352244534e-06, "loss": 3.2916, "step": 1778500 }, { "epoch": 3.68, "learning_rate": 1.5493133531427058e-06, "loss": 3.2876, "step": 1779000 }, { "epoch": 3.68, "learning_rate": 1.5486245710609584e-06, "loss": 3.2953, "step": 1779500 }, { "epoch": 3.68, "learning_rate": 1.547935788979211e-06, "loss": 3.2943, "step": 1780000 }, { "epoch": 3.68, "learning_rate": 1.5472470068974636e-06, "loss": 3.2984, "step": 1780500 }, { "epoch": 3.68, "learning_rate": 1.5465582248157162e-06, "loss": 3.3001, "step": 1781000 }, { "epoch": 3.68, "learning_rate": 1.5458694427339689e-06, "loss": 3.2937, "step": 1781500 }, { "epoch": 3.68, "learning_rate": 1.5451806606522215e-06, "loss": 3.2917, "step": 1782000 }, { "epoch": 3.68, "learning_rate": 1.5444918785704741e-06, "loss": 3.2917, "step": 1782500 }, { "epoch": 3.68, "learning_rate": 1.5438030964887265e-06, "loss": 3.2938, "step": 1783000 }, { "epoch": 3.69, "learning_rate": 1.5431143144069791e-06, "loss": 3.294, "step": 1783500 }, { "epoch": 3.69, "learning_rate": 1.5424255323252318e-06, "loss": 3.2883, "step": 1784000 }, { "epoch": 3.69, "learning_rate": 1.5417367502434844e-06, "loss": 3.2969, "step": 1784500 }, { "epoch": 3.69, "learning_rate": 1.541047968161737e-06, "loss": 3.2908, "step": 1785000 }, { "epoch": 3.69, "learning_rate": 1.5403591860799896e-06, "loss": 3.2923, "step": 1785500 }, { "epoch": 3.69, "learning_rate": 1.5396704039982423e-06, "loss": 3.2938, "step": 1786000 }, { "epoch": 3.69, "learning_rate": 1.5389816219164949e-06, "loss": 3.2936, "step": 1786500 }, { "epoch": 3.69, "learning_rate": 1.5382928398347473e-06, "loss": 3.2887, "step": 1787000 }, { "epoch": 3.69, "learning_rate": 1.537604057753e-06, "loss": 3.3003, "step": 1787500 }, { "epoch": 3.69, "learning_rate": 1.5369152756712525e-06, "loss": 3.2823, "step": 1788000 }, { "epoch": 3.7, "learning_rate": 1.5362264935895051e-06, "loss": 3.2918, "step": 1788500 }, { "epoch": 3.7, "learning_rate": 1.5355377115077578e-06, "loss": 3.2875, "step": 1789000 }, { "epoch": 3.7, "learning_rate": 1.5348489294260104e-06, "loss": 3.2873, "step": 1789500 }, { "epoch": 3.7, "learning_rate": 1.534160147344263e-06, "loss": 3.284, "step": 1790000 }, { "epoch": 3.7, "learning_rate": 1.5334713652625154e-06, "loss": 3.2935, "step": 1790500 }, { "epoch": 3.7, "learning_rate": 1.532782583180768e-06, "loss": 3.2922, "step": 1791000 }, { "epoch": 3.7, "learning_rate": 1.5320938010990205e-06, "loss": 3.2888, "step": 1791500 }, { "epoch": 3.7, "learning_rate": 1.531405019017273e-06, "loss": 3.286, "step": 1792000 }, { "epoch": 3.7, "learning_rate": 1.5307162369355257e-06, "loss": 3.2977, "step": 1792500 }, { "epoch": 3.7, "learning_rate": 1.5300274548537783e-06, "loss": 3.2928, "step": 1793000 }, { "epoch": 3.71, "learning_rate": 1.529338672772031e-06, "loss": 3.292, "step": 1793500 }, { "epoch": 3.71, "learning_rate": 1.5286498906902836e-06, "loss": 3.2856, "step": 1794000 }, { "epoch": 3.71, "learning_rate": 1.5279611086085362e-06, "loss": 3.2922, "step": 1794500 }, { "epoch": 3.71, "learning_rate": 1.5272723265267888e-06, "loss": 3.2835, "step": 1795000 }, { "epoch": 3.71, "learning_rate": 1.5265835444450412e-06, "loss": 3.2879, "step": 1795500 }, { "epoch": 3.71, "learning_rate": 1.5258947623632938e-06, "loss": 3.2896, "step": 1796000 }, { "epoch": 3.71, "learning_rate": 1.5252059802815465e-06, "loss": 3.289, "step": 1796500 }, { "epoch": 3.71, "learning_rate": 1.524517198199799e-06, "loss": 3.2934, "step": 1797000 }, { "epoch": 3.71, "learning_rate": 1.5238284161180517e-06, "loss": 3.2924, "step": 1797500 }, { "epoch": 3.72, "learning_rate": 1.5231396340363043e-06, "loss": 3.292, "step": 1798000 }, { "epoch": 3.72, "learning_rate": 1.522450851954557e-06, "loss": 3.2887, "step": 1798500 }, { "epoch": 3.72, "learning_rate": 1.5217620698728096e-06, "loss": 3.2927, "step": 1799000 }, { "epoch": 3.72, "learning_rate": 1.521073287791062e-06, "loss": 3.2865, "step": 1799500 }, { "epoch": 3.72, "learning_rate": 1.5203845057093146e-06, "loss": 3.2949, "step": 1800000 }, { "epoch": 3.72, "learning_rate": 1.5196957236275672e-06, "loss": 3.2896, "step": 1800500 }, { "epoch": 3.72, "learning_rate": 1.5190069415458198e-06, "loss": 3.2918, "step": 1801000 }, { "epoch": 3.72, "learning_rate": 1.5183181594640725e-06, "loss": 3.2908, "step": 1801500 }, { "epoch": 3.72, "learning_rate": 1.517629377382325e-06, "loss": 3.2929, "step": 1802000 }, { "epoch": 3.72, "learning_rate": 1.5169405953005777e-06, "loss": 3.2903, "step": 1802500 }, { "epoch": 3.73, "learning_rate": 1.5162518132188303e-06, "loss": 3.2933, "step": 1803000 }, { "epoch": 3.73, "learning_rate": 1.5155630311370825e-06, "loss": 3.2916, "step": 1803500 }, { "epoch": 3.73, "learning_rate": 1.5148742490553351e-06, "loss": 3.2856, "step": 1804000 }, { "epoch": 3.73, "learning_rate": 1.5141854669735878e-06, "loss": 3.29, "step": 1804500 }, { "epoch": 3.73, "learning_rate": 1.5134966848918404e-06, "loss": 3.2893, "step": 1805000 }, { "epoch": 3.73, "learning_rate": 1.512807902810093e-06, "loss": 3.2922, "step": 1805500 }, { "epoch": 3.73, "learning_rate": 1.5121191207283456e-06, "loss": 3.2846, "step": 1806000 }, { "epoch": 3.73, "learning_rate": 1.5114303386465983e-06, "loss": 3.2899, "step": 1806500 }, { "epoch": 3.73, "learning_rate": 1.5107415565648509e-06, "loss": 3.2912, "step": 1807000 }, { "epoch": 3.73, "learning_rate": 1.5100527744831033e-06, "loss": 3.2916, "step": 1807500 }, { "epoch": 3.74, "learning_rate": 1.509363992401356e-06, "loss": 3.2882, "step": 1808000 }, { "epoch": 3.74, "learning_rate": 1.5086752103196085e-06, "loss": 3.294, "step": 1808500 }, { "epoch": 3.74, "learning_rate": 1.5079864282378612e-06, "loss": 3.2883, "step": 1809000 }, { "epoch": 3.74, "learning_rate": 1.5072976461561138e-06, "loss": 3.2844, "step": 1809500 }, { "epoch": 3.74, "learning_rate": 1.5066088640743664e-06, "loss": 3.2918, "step": 1810000 }, { "epoch": 3.74, "learning_rate": 1.505920081992619e-06, "loss": 3.2932, "step": 1810500 }, { "epoch": 3.74, "learning_rate": 1.5052312999108716e-06, "loss": 3.2879, "step": 1811000 }, { "epoch": 3.74, "learning_rate": 1.5045425178291243e-06, "loss": 3.2879, "step": 1811500 }, { "epoch": 3.74, "learning_rate": 1.5038537357473767e-06, "loss": 3.2911, "step": 1812000 }, { "epoch": 3.75, "learning_rate": 1.5031649536656293e-06, "loss": 3.2843, "step": 1812500 }, { "epoch": 3.75, "learning_rate": 1.502476171583882e-06, "loss": 3.2886, "step": 1813000 }, { "epoch": 3.75, "learning_rate": 1.5017873895021345e-06, "loss": 3.2889, "step": 1813500 }, { "epoch": 3.75, "learning_rate": 1.5010986074203872e-06, "loss": 3.2903, "step": 1814000 }, { "epoch": 3.75, "learning_rate": 1.5004098253386398e-06, "loss": 3.2854, "step": 1814500 }, { "epoch": 3.75, "learning_rate": 1.4997210432568924e-06, "loss": 3.292, "step": 1815000 }, { "epoch": 3.75, "learning_rate": 1.499032261175145e-06, "loss": 3.2951, "step": 1815500 }, { "epoch": 3.75, "learning_rate": 1.4983434790933972e-06, "loss": 3.2945, "step": 1816000 }, { "epoch": 3.75, "learning_rate": 1.4976546970116498e-06, "loss": 3.2895, "step": 1816500 }, { "epoch": 3.75, "learning_rate": 1.4969659149299025e-06, "loss": 3.2877, "step": 1817000 }, { "epoch": 3.76, "learning_rate": 1.496277132848155e-06, "loss": 3.2903, "step": 1817500 }, { "epoch": 3.76, "learning_rate": 1.4955883507664077e-06, "loss": 3.2897, "step": 1818000 }, { "epoch": 3.76, "learning_rate": 1.4948995686846603e-06, "loss": 3.2912, "step": 1818500 }, { "epoch": 3.76, "learning_rate": 1.494210786602913e-06, "loss": 3.2974, "step": 1819000 }, { "epoch": 3.76, "learning_rate": 1.4935220045211656e-06, "loss": 3.2828, "step": 1819500 }, { "epoch": 3.76, "learning_rate": 1.492833222439418e-06, "loss": 3.2901, "step": 1820000 }, { "epoch": 3.76, "learning_rate": 1.4921444403576706e-06, "loss": 3.289, "step": 1820500 }, { "epoch": 3.76, "learning_rate": 1.4914556582759232e-06, "loss": 3.2904, "step": 1821000 }, { "epoch": 3.76, "learning_rate": 1.4907668761941758e-06, "loss": 3.2828, "step": 1821500 }, { "epoch": 3.76, "learning_rate": 1.4900780941124285e-06, "loss": 3.2879, "step": 1822000 }, { "epoch": 3.77, "learning_rate": 1.489389312030681e-06, "loss": 3.2895, "step": 1822500 }, { "epoch": 3.77, "learning_rate": 1.4887005299489337e-06, "loss": 3.2883, "step": 1823000 }, { "epoch": 3.77, "learning_rate": 1.4880117478671863e-06, "loss": 3.2877, "step": 1823500 }, { "epoch": 3.77, "learning_rate": 1.4873229657854387e-06, "loss": 3.2895, "step": 1824000 }, { "epoch": 3.77, "learning_rate": 1.4866341837036914e-06, "loss": 3.2898, "step": 1824500 }, { "epoch": 3.77, "learning_rate": 1.485945401621944e-06, "loss": 3.2892, "step": 1825000 }, { "epoch": 3.77, "learning_rate": 1.4852566195401966e-06, "loss": 3.2843, "step": 1825500 }, { "epoch": 3.77, "learning_rate": 1.4845678374584492e-06, "loss": 3.2881, "step": 1826000 }, { "epoch": 3.77, "learning_rate": 1.4838790553767018e-06, "loss": 3.2859, "step": 1826500 }, { "epoch": 3.78, "learning_rate": 1.4831902732949545e-06, "loss": 3.2906, "step": 1827000 }, { "epoch": 3.78, "learning_rate": 1.482501491213207e-06, "loss": 3.2904, "step": 1827500 }, { "epoch": 3.78, "learning_rate": 1.4818127091314593e-06, "loss": 3.2858, "step": 1828000 }, { "epoch": 3.78, "learning_rate": 1.481123927049712e-06, "loss": 3.2912, "step": 1828500 }, { "epoch": 3.78, "learning_rate": 1.4804351449679645e-06, "loss": 3.288, "step": 1829000 }, { "epoch": 3.78, "learning_rate": 1.4797463628862172e-06, "loss": 3.29, "step": 1829500 }, { "epoch": 3.78, "learning_rate": 1.4790575808044698e-06, "loss": 3.2872, "step": 1830000 }, { "epoch": 3.78, "learning_rate": 1.4783687987227224e-06, "loss": 3.2876, "step": 1830500 }, { "epoch": 3.78, "learning_rate": 1.477680016640975e-06, "loss": 3.2881, "step": 1831000 }, { "epoch": 3.78, "learning_rate": 1.4769912345592276e-06, "loss": 3.2865, "step": 1831500 }, { "epoch": 3.79, "learning_rate": 1.4763024524774803e-06, "loss": 3.2846, "step": 1832000 }, { "epoch": 3.79, "learning_rate": 1.4756136703957327e-06, "loss": 3.2834, "step": 1832500 }, { "epoch": 3.79, "learning_rate": 1.4749248883139853e-06, "loss": 3.2906, "step": 1833000 }, { "epoch": 3.79, "learning_rate": 1.474236106232238e-06, "loss": 3.2809, "step": 1833500 }, { "epoch": 3.79, "learning_rate": 1.4735473241504905e-06, "loss": 3.2845, "step": 1834000 }, { "epoch": 3.79, "learning_rate": 1.4728585420687432e-06, "loss": 3.286, "step": 1834500 }, { "epoch": 3.79, "learning_rate": 1.4721697599869958e-06, "loss": 3.2918, "step": 1835000 }, { "epoch": 3.79, "learning_rate": 1.4714809779052484e-06, "loss": 3.286, "step": 1835500 }, { "epoch": 3.79, "learning_rate": 1.470792195823501e-06, "loss": 3.2925, "step": 1836000 }, { "epoch": 3.79, "learning_rate": 1.4701034137417534e-06, "loss": 3.2919, "step": 1836500 }, { "epoch": 3.8, "learning_rate": 1.469414631660006e-06, "loss": 3.2902, "step": 1837000 }, { "epoch": 3.8, "learning_rate": 1.4687258495782587e-06, "loss": 3.2888, "step": 1837500 }, { "epoch": 3.8, "learning_rate": 1.4680370674965113e-06, "loss": 3.2871, "step": 1838000 }, { "epoch": 3.8, "learning_rate": 1.467348285414764e-06, "loss": 3.2854, "step": 1838500 }, { "epoch": 3.8, "learning_rate": 1.4666595033330165e-06, "loss": 3.2912, "step": 1839000 }, { "epoch": 3.8, "learning_rate": 1.4659707212512692e-06, "loss": 3.2887, "step": 1839500 }, { "epoch": 3.8, "learning_rate": 1.4652819391695218e-06, "loss": 3.2882, "step": 1840000 }, { "epoch": 3.8, "learning_rate": 1.4645931570877742e-06, "loss": 3.282, "step": 1840500 }, { "epoch": 3.8, "learning_rate": 1.4639043750060266e-06, "loss": 3.2877, "step": 1841000 }, { "epoch": 3.81, "learning_rate": 1.4632155929242792e-06, "loss": 3.2885, "step": 1841500 }, { "epoch": 3.81, "learning_rate": 1.4625268108425318e-06, "loss": 3.287, "step": 1842000 }, { "epoch": 3.81, "learning_rate": 1.4618380287607845e-06, "loss": 3.2903, "step": 1842500 }, { "epoch": 3.81, "learning_rate": 1.461149246679037e-06, "loss": 3.2863, "step": 1843000 }, { "epoch": 3.81, "learning_rate": 1.4604604645972897e-06, "loss": 3.2876, "step": 1843500 }, { "epoch": 3.81, "learning_rate": 1.4597716825155423e-06, "loss": 3.2896, "step": 1844000 }, { "epoch": 3.81, "learning_rate": 1.4590829004337947e-06, "loss": 3.2873, "step": 1844500 }, { "epoch": 3.81, "learning_rate": 1.4583941183520474e-06, "loss": 3.287, "step": 1845000 }, { "epoch": 3.81, "learning_rate": 1.4577053362703e-06, "loss": 3.2924, "step": 1845500 }, { "epoch": 3.81, "learning_rate": 1.4570165541885526e-06, "loss": 3.2811, "step": 1846000 }, { "epoch": 3.82, "learning_rate": 1.4563277721068052e-06, "loss": 3.2863, "step": 1846500 }, { "epoch": 3.82, "learning_rate": 1.4556389900250578e-06, "loss": 3.2906, "step": 1847000 }, { "epoch": 3.82, "learning_rate": 1.4549502079433105e-06, "loss": 3.2806, "step": 1847500 }, { "epoch": 3.82, "learning_rate": 1.454261425861563e-06, "loss": 3.2829, "step": 1848000 }, { "epoch": 3.82, "learning_rate": 1.4535726437798157e-06, "loss": 3.2868, "step": 1848500 }, { "epoch": 3.82, "learning_rate": 1.4528838616980681e-06, "loss": 3.287, "step": 1849000 }, { "epoch": 3.82, "learning_rate": 1.4521950796163207e-06, "loss": 3.2818, "step": 1849500 }, { "epoch": 3.82, "learning_rate": 1.4515062975345734e-06, "loss": 3.2896, "step": 1850000 }, { "epoch": 3.82, "learning_rate": 1.450817515452826e-06, "loss": 3.2878, "step": 1850500 }, { "epoch": 3.82, "learning_rate": 1.4501287333710786e-06, "loss": 3.2857, "step": 1851000 }, { "epoch": 3.83, "learning_rate": 1.4494399512893312e-06, "loss": 3.2831, "step": 1851500 }, { "epoch": 3.83, "learning_rate": 1.4487511692075839e-06, "loss": 3.2838, "step": 1852000 }, { "epoch": 3.83, "learning_rate": 1.4480623871258365e-06, "loss": 3.2877, "step": 1852500 }, { "epoch": 3.83, "learning_rate": 1.4473736050440889e-06, "loss": 3.2897, "step": 1853000 }, { "epoch": 3.83, "learning_rate": 1.4466848229623415e-06, "loss": 3.2839, "step": 1853500 }, { "epoch": 3.83, "learning_rate": 1.445996040880594e-06, "loss": 3.2867, "step": 1854000 }, { "epoch": 3.83, "learning_rate": 1.4453072587988465e-06, "loss": 3.288, "step": 1854500 }, { "epoch": 3.83, "learning_rate": 1.4446184767170992e-06, "loss": 3.2821, "step": 1855000 }, { "epoch": 3.83, "learning_rate": 1.4439296946353518e-06, "loss": 3.2875, "step": 1855500 }, { "epoch": 3.84, "learning_rate": 1.4432409125536044e-06, "loss": 3.2851, "step": 1856000 }, { "epoch": 3.84, "learning_rate": 1.442552130471857e-06, "loss": 3.2855, "step": 1856500 }, { "epoch": 3.84, "learning_rate": 1.4418633483901094e-06, "loss": 3.2921, "step": 1857000 }, { "epoch": 3.84, "learning_rate": 1.441174566308362e-06, "loss": 3.2785, "step": 1857500 }, { "epoch": 3.84, "learning_rate": 1.4404857842266147e-06, "loss": 3.2875, "step": 1858000 }, { "epoch": 3.84, "learning_rate": 1.4397970021448673e-06, "loss": 3.2837, "step": 1858500 }, { "epoch": 3.84, "learning_rate": 1.43910822006312e-06, "loss": 3.2822, "step": 1859000 }, { "epoch": 3.84, "learning_rate": 1.4384194379813725e-06, "loss": 3.2866, "step": 1859500 }, { "epoch": 3.84, "learning_rate": 1.4377306558996252e-06, "loss": 3.2793, "step": 1860000 }, { "epoch": 3.84, "learning_rate": 1.4370418738178778e-06, "loss": 3.2851, "step": 1860500 }, { "epoch": 3.85, "learning_rate": 1.4363530917361302e-06, "loss": 3.2825, "step": 1861000 }, { "epoch": 3.85, "learning_rate": 1.4356643096543828e-06, "loss": 3.2857, "step": 1861500 }, { "epoch": 3.85, "learning_rate": 1.4349755275726354e-06, "loss": 3.2919, "step": 1862000 }, { "epoch": 3.85, "learning_rate": 1.434286745490888e-06, "loss": 3.2854, "step": 1862500 }, { "epoch": 3.85, "learning_rate": 1.4335979634091407e-06, "loss": 3.2806, "step": 1863000 }, { "epoch": 3.85, "learning_rate": 1.4329091813273933e-06, "loss": 3.2823, "step": 1863500 }, { "epoch": 3.85, "learning_rate": 1.432220399245646e-06, "loss": 3.2817, "step": 1864000 }, { "epoch": 3.85, "learning_rate": 1.4315316171638985e-06, "loss": 3.2854, "step": 1864500 }, { "epoch": 3.85, "learning_rate": 1.430842835082151e-06, "loss": 3.2788, "step": 1865000 }, { "epoch": 3.85, "learning_rate": 1.4301540530004036e-06, "loss": 3.2858, "step": 1865500 }, { "epoch": 3.86, "learning_rate": 1.4294652709186562e-06, "loss": 3.2931, "step": 1866000 }, { "epoch": 3.86, "learning_rate": 1.4287764888369086e-06, "loss": 3.289, "step": 1866500 }, { "epoch": 3.86, "learning_rate": 1.4280877067551612e-06, "loss": 3.2829, "step": 1867000 }, { "epoch": 3.86, "learning_rate": 1.4273989246734138e-06, "loss": 3.2847, "step": 1867500 }, { "epoch": 3.86, "learning_rate": 1.4267101425916665e-06, "loss": 3.2861, "step": 1868000 }, { "epoch": 3.86, "learning_rate": 1.426021360509919e-06, "loss": 3.2841, "step": 1868500 }, { "epoch": 3.86, "learning_rate": 1.4253325784281717e-06, "loss": 3.2861, "step": 1869000 }, { "epoch": 3.86, "learning_rate": 1.4246437963464241e-06, "loss": 3.2817, "step": 1869500 }, { "epoch": 3.86, "learning_rate": 1.4239550142646767e-06, "loss": 3.2881, "step": 1870000 }, { "epoch": 3.87, "learning_rate": 1.4232662321829294e-06, "loss": 3.2834, "step": 1870500 }, { "epoch": 3.87, "learning_rate": 1.422577450101182e-06, "loss": 3.2827, "step": 1871000 }, { "epoch": 3.87, "learning_rate": 1.4218886680194346e-06, "loss": 3.2857, "step": 1871500 }, { "epoch": 3.87, "learning_rate": 1.4211998859376872e-06, "loss": 3.2829, "step": 1872000 }, { "epoch": 3.87, "learning_rate": 1.4205111038559399e-06, "loss": 3.2803, "step": 1872500 }, { "epoch": 3.87, "learning_rate": 1.4198223217741925e-06, "loss": 3.2897, "step": 1873000 }, { "epoch": 3.87, "learning_rate": 1.4191335396924449e-06, "loss": 3.2799, "step": 1873500 }, { "epoch": 3.87, "learning_rate": 1.4184447576106975e-06, "loss": 3.2865, "step": 1874000 }, { "epoch": 3.87, "learning_rate": 1.4177559755289501e-06, "loss": 3.2826, "step": 1874500 }, { "epoch": 3.87, "learning_rate": 1.4170671934472027e-06, "loss": 3.2897, "step": 1875000 }, { "epoch": 3.88, "learning_rate": 1.4163784113654554e-06, "loss": 3.2766, "step": 1875500 }, { "epoch": 3.88, "learning_rate": 1.415689629283708e-06, "loss": 3.2816, "step": 1876000 }, { "epoch": 3.88, "learning_rate": 1.4150008472019606e-06, "loss": 3.2809, "step": 1876500 }, { "epoch": 3.88, "learning_rate": 1.4143120651202132e-06, "loss": 3.2872, "step": 1877000 }, { "epoch": 3.88, "learning_rate": 1.4136232830384656e-06, "loss": 3.2824, "step": 1877500 }, { "epoch": 3.88, "learning_rate": 1.4129345009567183e-06, "loss": 3.2798, "step": 1878000 }, { "epoch": 3.88, "learning_rate": 1.4122457188749709e-06, "loss": 3.2912, "step": 1878500 }, { "epoch": 3.88, "learning_rate": 1.4115569367932235e-06, "loss": 3.2751, "step": 1879000 }, { "epoch": 3.88, "learning_rate": 1.410868154711476e-06, "loss": 3.2776, "step": 1879500 }, { "epoch": 3.88, "learning_rate": 1.4101793726297285e-06, "loss": 3.2889, "step": 1880000 }, { "epoch": 3.89, "learning_rate": 1.4094905905479812e-06, "loss": 3.2841, "step": 1880500 }, { "epoch": 3.89, "learning_rate": 1.4088018084662338e-06, "loss": 3.2866, "step": 1881000 }, { "epoch": 3.89, "learning_rate": 1.4081130263844862e-06, "loss": 3.2823, "step": 1881500 }, { "epoch": 3.89, "learning_rate": 1.4074242443027388e-06, "loss": 3.2831, "step": 1882000 }, { "epoch": 3.89, "learning_rate": 1.4067354622209914e-06, "loss": 3.2793, "step": 1882500 }, { "epoch": 3.89, "learning_rate": 1.406046680139244e-06, "loss": 3.2846, "step": 1883000 }, { "epoch": 3.89, "learning_rate": 1.4053578980574967e-06, "loss": 3.2813, "step": 1883500 }, { "epoch": 3.89, "learning_rate": 1.4046691159757493e-06, "loss": 3.2817, "step": 1884000 }, { "epoch": 3.89, "learning_rate": 1.403980333894002e-06, "loss": 3.2878, "step": 1884500 }, { "epoch": 3.9, "learning_rate": 1.4032915518122545e-06, "loss": 3.2854, "step": 1885000 }, { "epoch": 3.9, "learning_rate": 1.402602769730507e-06, "loss": 3.288, "step": 1885500 }, { "epoch": 3.9, "learning_rate": 1.4019139876487596e-06, "loss": 3.2853, "step": 1886000 }, { "epoch": 3.9, "learning_rate": 1.4012252055670122e-06, "loss": 3.2777, "step": 1886500 }, { "epoch": 3.9, "learning_rate": 1.4005364234852648e-06, "loss": 3.2852, "step": 1887000 }, { "epoch": 3.9, "learning_rate": 1.3998476414035174e-06, "loss": 3.2811, "step": 1887500 }, { "epoch": 3.9, "learning_rate": 1.39915885932177e-06, "loss": 3.2803, "step": 1888000 }, { "epoch": 3.9, "learning_rate": 1.3984700772400227e-06, "loss": 3.2886, "step": 1888500 }, { "epoch": 3.9, "learning_rate": 1.3977812951582753e-06, "loss": 3.2786, "step": 1889000 }, { "epoch": 3.9, "learning_rate": 1.397092513076528e-06, "loss": 3.2917, "step": 1889500 }, { "epoch": 3.91, "learning_rate": 1.3964037309947803e-06, "loss": 3.2794, "step": 1890000 }, { "epoch": 3.91, "learning_rate": 1.395714948913033e-06, "loss": 3.2808, "step": 1890500 }, { "epoch": 3.91, "learning_rate": 1.3950261668312856e-06, "loss": 3.2833, "step": 1891000 }, { "epoch": 3.91, "learning_rate": 1.3943373847495382e-06, "loss": 3.2792, "step": 1891500 }, { "epoch": 3.91, "learning_rate": 1.3936486026677908e-06, "loss": 3.2817, "step": 1892000 }, { "epoch": 3.91, "learning_rate": 1.3929598205860432e-06, "loss": 3.2868, "step": 1892500 }, { "epoch": 3.91, "learning_rate": 1.3922710385042959e-06, "loss": 3.2839, "step": 1893000 }, { "epoch": 3.91, "learning_rate": 1.3915822564225485e-06, "loss": 3.281, "step": 1893500 }, { "epoch": 3.91, "learning_rate": 1.3908934743408009e-06, "loss": 3.2839, "step": 1894000 }, { "epoch": 3.91, "learning_rate": 1.3902046922590535e-06, "loss": 3.2818, "step": 1894500 }, { "epoch": 3.92, "learning_rate": 1.3895159101773061e-06, "loss": 3.2853, "step": 1895000 }, { "epoch": 3.92, "learning_rate": 1.3888271280955588e-06, "loss": 3.2884, "step": 1895500 }, { "epoch": 3.92, "learning_rate": 1.3881383460138114e-06, "loss": 3.28, "step": 1896000 }, { "epoch": 3.92, "learning_rate": 1.387449563932064e-06, "loss": 3.2886, "step": 1896500 }, { "epoch": 3.92, "learning_rate": 1.3867607818503166e-06, "loss": 3.2841, "step": 1897000 }, { "epoch": 3.92, "learning_rate": 1.3860719997685692e-06, "loss": 3.2865, "step": 1897500 }, { "epoch": 3.92, "learning_rate": 1.3853832176868216e-06, "loss": 3.2834, "step": 1898000 }, { "epoch": 3.92, "learning_rate": 1.3846944356050743e-06, "loss": 3.2784, "step": 1898500 }, { "epoch": 3.92, "learning_rate": 1.3840056535233269e-06, "loss": 3.2856, "step": 1899000 }, { "epoch": 3.93, "learning_rate": 1.3833168714415795e-06, "loss": 3.2804, "step": 1899500 }, { "epoch": 3.93, "learning_rate": 1.3826280893598321e-06, "loss": 3.281, "step": 1900000 }, { "epoch": 3.93, "learning_rate": 1.3819393072780848e-06, "loss": 3.2834, "step": 1900500 }, { "epoch": 3.93, "learning_rate": 1.3812505251963374e-06, "loss": 3.2795, "step": 1901000 }, { "epoch": 3.93, "learning_rate": 1.38056174311459e-06, "loss": 3.2832, "step": 1901500 }, { "epoch": 3.93, "learning_rate": 1.3798729610328424e-06, "loss": 3.2838, "step": 1902000 }, { "epoch": 3.93, "learning_rate": 1.379184178951095e-06, "loss": 3.2756, "step": 1902500 }, { "epoch": 3.93, "learning_rate": 1.3784953968693477e-06, "loss": 3.2853, "step": 1903000 }, { "epoch": 3.93, "learning_rate": 1.3778066147876003e-06, "loss": 3.2871, "step": 1903500 }, { "epoch": 3.93, "learning_rate": 1.3771178327058529e-06, "loss": 3.2906, "step": 1904000 }, { "epoch": 3.94, "learning_rate": 1.3764290506241055e-06, "loss": 3.2812, "step": 1904500 }, { "epoch": 3.94, "learning_rate": 1.375740268542358e-06, "loss": 3.2814, "step": 1905000 }, { "epoch": 3.94, "learning_rate": 1.3750514864606105e-06, "loss": 3.2781, "step": 1905500 }, { "epoch": 3.94, "learning_rate": 1.374362704378863e-06, "loss": 3.2891, "step": 1906000 }, { "epoch": 3.94, "learning_rate": 1.3736739222971156e-06, "loss": 3.283, "step": 1906500 }, { "epoch": 3.94, "learning_rate": 1.3729851402153682e-06, "loss": 3.2786, "step": 1907000 }, { "epoch": 3.94, "learning_rate": 1.3722963581336208e-06, "loss": 3.2861, "step": 1907500 }, { "epoch": 3.94, "learning_rate": 1.3716075760518734e-06, "loss": 3.2827, "step": 1908000 }, { "epoch": 3.94, "learning_rate": 1.370918793970126e-06, "loss": 3.2795, "step": 1908500 }, { "epoch": 3.94, "learning_rate": 1.3702300118883787e-06, "loss": 3.2804, "step": 1909000 }, { "epoch": 3.95, "learning_rate": 1.3695412298066313e-06, "loss": 3.2799, "step": 1909500 }, { "epoch": 3.95, "learning_rate": 1.368852447724884e-06, "loss": 3.2794, "step": 1910000 }, { "epoch": 3.95, "learning_rate": 1.3681636656431363e-06, "loss": 3.2821, "step": 1910500 }, { "epoch": 3.95, "learning_rate": 1.367474883561389e-06, "loss": 3.2856, "step": 1911000 }, { "epoch": 3.95, "learning_rate": 1.3667861014796416e-06, "loss": 3.2835, "step": 1911500 }, { "epoch": 3.95, "learning_rate": 1.3660973193978942e-06, "loss": 3.2854, "step": 1912000 }, { "epoch": 3.95, "learning_rate": 1.3654085373161468e-06, "loss": 3.2775, "step": 1912500 }, { "epoch": 3.95, "learning_rate": 1.3647197552343994e-06, "loss": 3.2861, "step": 1913000 }, { "epoch": 3.95, "learning_rate": 1.364030973152652e-06, "loss": 3.2882, "step": 1913500 }, { "epoch": 3.95, "learning_rate": 1.3633421910709047e-06, "loss": 3.2767, "step": 1914000 }, { "epoch": 3.96, "learning_rate": 1.362653408989157e-06, "loss": 3.2788, "step": 1914500 }, { "epoch": 3.96, "learning_rate": 1.3619646269074097e-06, "loss": 3.2828, "step": 1915000 }, { "epoch": 3.96, "learning_rate": 1.3612758448256623e-06, "loss": 3.2799, "step": 1915500 }, { "epoch": 3.96, "learning_rate": 1.360587062743915e-06, "loss": 3.2856, "step": 1916000 }, { "epoch": 3.96, "learning_rate": 1.3598982806621676e-06, "loss": 3.2899, "step": 1916500 }, { "epoch": 3.96, "learning_rate": 1.3592094985804202e-06, "loss": 3.2798, "step": 1917000 }, { "epoch": 3.96, "learning_rate": 1.3585207164986728e-06, "loss": 3.2756, "step": 1917500 }, { "epoch": 3.96, "learning_rate": 1.3578319344169252e-06, "loss": 3.282, "step": 1918000 }, { "epoch": 3.96, "learning_rate": 1.3571431523351776e-06, "loss": 3.2855, "step": 1918500 }, { "epoch": 3.97, "learning_rate": 1.3564543702534303e-06, "loss": 3.2811, "step": 1919000 }, { "epoch": 3.97, "learning_rate": 1.3557655881716829e-06, "loss": 3.2831, "step": 1919500 }, { "epoch": 3.97, "learning_rate": 1.3550768060899355e-06, "loss": 3.2885, "step": 1920000 }, { "epoch": 3.97, "learning_rate": 1.3543880240081881e-06, "loss": 3.2769, "step": 1920500 }, { "epoch": 3.97, "learning_rate": 1.3536992419264408e-06, "loss": 3.2788, "step": 1921000 }, { "epoch": 3.97, "learning_rate": 1.3530104598446934e-06, "loss": 3.2818, "step": 1921500 }, { "epoch": 3.97, "learning_rate": 1.352321677762946e-06, "loss": 3.2821, "step": 1922000 }, { "epoch": 3.97, "learning_rate": 1.3516328956811984e-06, "loss": 3.2791, "step": 1922500 }, { "epoch": 3.97, "learning_rate": 1.350944113599451e-06, "loss": 3.2792, "step": 1923000 }, { "epoch": 3.97, "learning_rate": 1.3502553315177037e-06, "loss": 3.2832, "step": 1923500 }, { "epoch": 3.98, "learning_rate": 1.3495665494359563e-06, "loss": 3.2765, "step": 1924000 }, { "epoch": 3.98, "learning_rate": 1.348877767354209e-06, "loss": 3.2844, "step": 1924500 }, { "epoch": 3.98, "learning_rate": 1.3481889852724615e-06, "loss": 3.2763, "step": 1925000 }, { "epoch": 3.98, "learning_rate": 1.3475002031907141e-06, "loss": 3.2829, "step": 1925500 }, { "epoch": 3.98, "learning_rate": 1.3468114211089668e-06, "loss": 3.2763, "step": 1926000 }, { "epoch": 3.98, "learning_rate": 1.3461226390272192e-06, "loss": 3.2813, "step": 1926500 }, { "epoch": 3.98, "learning_rate": 1.3454338569454718e-06, "loss": 3.2814, "step": 1927000 }, { "epoch": 3.98, "learning_rate": 1.3447450748637244e-06, "loss": 3.2789, "step": 1927500 }, { "epoch": 3.98, "learning_rate": 1.344056292781977e-06, "loss": 3.2796, "step": 1928000 }, { "epoch": 3.98, "learning_rate": 1.3433675107002297e-06, "loss": 3.2699, "step": 1928500 }, { "epoch": 3.99, "learning_rate": 1.3426787286184823e-06, "loss": 3.2863, "step": 1929000 }, { "epoch": 3.99, "learning_rate": 1.341989946536735e-06, "loss": 3.2805, "step": 1929500 }, { "epoch": 3.99, "learning_rate": 1.3413011644549875e-06, "loss": 3.2747, "step": 1930000 }, { "epoch": 3.99, "learning_rate": 1.3406123823732401e-06, "loss": 3.2777, "step": 1930500 }, { "epoch": 3.99, "learning_rate": 1.3399236002914923e-06, "loss": 3.284, "step": 1931000 }, { "epoch": 3.99, "learning_rate": 1.339234818209745e-06, "loss": 3.2781, "step": 1931500 }, { "epoch": 3.99, "learning_rate": 1.3385460361279976e-06, "loss": 3.2818, "step": 1932000 }, { "epoch": 3.99, "learning_rate": 1.3378572540462502e-06, "loss": 3.2748, "step": 1932500 }, { "epoch": 3.99, "learning_rate": 1.3371684719645028e-06, "loss": 3.277, "step": 1933000 }, { "epoch": 4.0, "learning_rate": 1.3364796898827554e-06, "loss": 3.2738, "step": 1933500 }, { "epoch": 4.0, "learning_rate": 1.335790907801008e-06, "loss": 3.2769, "step": 1934000 }, { "epoch": 4.0, "learning_rate": 1.3351021257192607e-06, "loss": 3.2745, "step": 1934500 }, { "epoch": 4.0, "learning_rate": 1.334413343637513e-06, "loss": 3.2781, "step": 1935000 }, { "epoch": 4.0, "learning_rate": 1.3337245615557657e-06, "loss": 3.2835, "step": 1935500 }, { "epoch": 4.0, "eval_loss": 3.2754366397857666, "eval_runtime": 22239.8882, "eval_samples_per_second": 154.739, "eval_steps_per_second": 2.418, "step": 1935784 }, { "epoch": 4.0, "learning_rate": 1.3330357794740183e-06, "loss": 3.2711, "step": 1936000 }, { "epoch": 4.0, "learning_rate": 1.332346997392271e-06, "loss": 3.2661, "step": 1936500 }, { "epoch": 4.0, "learning_rate": 1.3316582153105236e-06, "loss": 3.2717, "step": 1937000 }, { "epoch": 4.0, "learning_rate": 1.3309694332287762e-06, "loss": 3.268, "step": 1937500 }, { "epoch": 4.0, "learning_rate": 1.3302806511470288e-06, "loss": 3.2643, "step": 1938000 }, { "epoch": 4.01, "learning_rate": 1.3295918690652815e-06, "loss": 3.266, "step": 1938500 }, { "epoch": 4.01, "learning_rate": 1.3289030869835339e-06, "loss": 3.2667, "step": 1939000 }, { "epoch": 4.01, "learning_rate": 1.3282143049017865e-06, "loss": 3.2584, "step": 1939500 }, { "epoch": 4.01, "learning_rate": 1.327525522820039e-06, "loss": 3.2654, "step": 1940000 }, { "epoch": 4.01, "learning_rate": 1.3268367407382917e-06, "loss": 3.2568, "step": 1940500 }, { "epoch": 4.01, "learning_rate": 1.3261479586565443e-06, "loss": 3.2585, "step": 1941000 }, { "epoch": 4.01, "learning_rate": 1.325459176574797e-06, "loss": 3.2634, "step": 1941500 }, { "epoch": 4.01, "learning_rate": 1.3247703944930496e-06, "loss": 3.2593, "step": 1942000 }, { "epoch": 4.01, "learning_rate": 1.3240816124113022e-06, "loss": 3.2608, "step": 1942500 }, { "epoch": 4.01, "learning_rate": 1.3233928303295544e-06, "loss": 3.2638, "step": 1943000 }, { "epoch": 4.02, "learning_rate": 1.322704048247807e-06, "loss": 3.2688, "step": 1943500 }, { "epoch": 4.02, "learning_rate": 1.3220152661660597e-06, "loss": 3.264, "step": 1944000 }, { "epoch": 4.02, "learning_rate": 1.3213264840843123e-06, "loss": 3.2577, "step": 1944500 }, { "epoch": 4.02, "learning_rate": 1.320637702002565e-06, "loss": 3.2654, "step": 1945000 }, { "epoch": 4.02, "learning_rate": 1.3199489199208175e-06, "loss": 3.2669, "step": 1945500 }, { "epoch": 4.02, "learning_rate": 1.3192601378390701e-06, "loss": 3.2644, "step": 1946000 }, { "epoch": 4.02, "learning_rate": 1.3185713557573228e-06, "loss": 3.26, "step": 1946500 }, { "epoch": 4.02, "learning_rate": 1.3178825736755752e-06, "loss": 3.2657, "step": 1947000 }, { "epoch": 4.02, "learning_rate": 1.3171937915938278e-06, "loss": 3.266, "step": 1947500 }, { "epoch": 4.03, "learning_rate": 1.3165050095120804e-06, "loss": 3.2683, "step": 1948000 }, { "epoch": 4.03, "learning_rate": 1.315816227430333e-06, "loss": 3.2598, "step": 1948500 }, { "epoch": 4.03, "learning_rate": 1.3151274453485857e-06, "loss": 3.264, "step": 1949000 }, { "epoch": 4.03, "learning_rate": 1.3144386632668383e-06, "loss": 3.2618, "step": 1949500 }, { "epoch": 4.03, "learning_rate": 1.313749881185091e-06, "loss": 3.2643, "step": 1950000 }, { "epoch": 4.03, "learning_rate": 1.3130610991033435e-06, "loss": 3.2608, "step": 1950500 }, { "epoch": 4.03, "learning_rate": 1.3123723170215961e-06, "loss": 3.2716, "step": 1951000 }, { "epoch": 4.03, "learning_rate": 1.3116835349398486e-06, "loss": 3.2622, "step": 1951500 }, { "epoch": 4.03, "learning_rate": 1.3109947528581012e-06, "loss": 3.2574, "step": 1952000 }, { "epoch": 4.03, "learning_rate": 1.3103059707763538e-06, "loss": 3.2577, "step": 1952500 }, { "epoch": 4.04, "learning_rate": 1.3096171886946064e-06, "loss": 3.2644, "step": 1953000 }, { "epoch": 4.04, "learning_rate": 1.308928406612859e-06, "loss": 3.2635, "step": 1953500 }, { "epoch": 4.04, "learning_rate": 1.3082396245311117e-06, "loss": 3.2684, "step": 1954000 }, { "epoch": 4.04, "learning_rate": 1.3075508424493643e-06, "loss": 3.2616, "step": 1954500 }, { "epoch": 4.04, "learning_rate": 1.306862060367617e-06, "loss": 3.2631, "step": 1955000 }, { "epoch": 4.04, "learning_rate": 1.306173278285869e-06, "loss": 3.2656, "step": 1955500 }, { "epoch": 4.04, "learning_rate": 1.3054844962041217e-06, "loss": 3.265, "step": 1956000 }, { "epoch": 4.04, "learning_rate": 1.3047957141223743e-06, "loss": 3.2643, "step": 1956500 }, { "epoch": 4.04, "learning_rate": 1.304106932040627e-06, "loss": 3.2578, "step": 1957000 }, { "epoch": 4.04, "learning_rate": 1.3034181499588796e-06, "loss": 3.268, "step": 1957500 }, { "epoch": 4.05, "learning_rate": 1.3027293678771322e-06, "loss": 3.2657, "step": 1958000 }, { "epoch": 4.05, "learning_rate": 1.3020405857953848e-06, "loss": 3.2603, "step": 1958500 }, { "epoch": 4.05, "learning_rate": 1.3013518037136375e-06, "loss": 3.257, "step": 1959000 }, { "epoch": 4.05, "learning_rate": 1.3006630216318899e-06, "loss": 3.2626, "step": 1959500 }, { "epoch": 4.05, "learning_rate": 1.2999742395501425e-06, "loss": 3.2651, "step": 1960000 }, { "epoch": 4.05, "learning_rate": 1.299285457468395e-06, "loss": 3.2633, "step": 1960500 }, { "epoch": 4.05, "learning_rate": 1.2985966753866477e-06, "loss": 3.2611, "step": 1961000 }, { "epoch": 4.05, "learning_rate": 1.2979078933049003e-06, "loss": 3.2606, "step": 1961500 }, { "epoch": 4.05, "learning_rate": 1.297219111223153e-06, "loss": 3.2648, "step": 1962000 }, { "epoch": 4.06, "learning_rate": 1.2965303291414056e-06, "loss": 3.2645, "step": 1962500 }, { "epoch": 4.06, "learning_rate": 1.2958415470596582e-06, "loss": 3.2594, "step": 1963000 }, { "epoch": 4.06, "learning_rate": 1.2951527649779106e-06, "loss": 3.2637, "step": 1963500 }, { "epoch": 4.06, "learning_rate": 1.2944639828961632e-06, "loss": 3.2646, "step": 1964000 }, { "epoch": 4.06, "learning_rate": 1.2937752008144159e-06, "loss": 3.2607, "step": 1964500 }, { "epoch": 4.06, "learning_rate": 1.2930864187326685e-06, "loss": 3.2648, "step": 1965000 }, { "epoch": 4.06, "learning_rate": 1.2923976366509211e-06, "loss": 3.2634, "step": 1965500 }, { "epoch": 4.06, "learning_rate": 1.2917088545691737e-06, "loss": 3.2596, "step": 1966000 }, { "epoch": 4.06, "learning_rate": 1.2910200724874264e-06, "loss": 3.2599, "step": 1966500 }, { "epoch": 4.06, "learning_rate": 1.290331290405679e-06, "loss": 3.2665, "step": 1967000 }, { "epoch": 4.07, "learning_rate": 1.2896425083239314e-06, "loss": 3.258, "step": 1967500 }, { "epoch": 4.07, "learning_rate": 1.288953726242184e-06, "loss": 3.2597, "step": 1968000 }, { "epoch": 4.07, "learning_rate": 1.2882649441604364e-06, "loss": 3.2669, "step": 1968500 }, { "epoch": 4.07, "learning_rate": 1.287576162078689e-06, "loss": 3.2572, "step": 1969000 }, { "epoch": 4.07, "learning_rate": 1.2868873799969417e-06, "loss": 3.2679, "step": 1969500 }, { "epoch": 4.07, "learning_rate": 1.2861985979151943e-06, "loss": 3.2714, "step": 1970000 }, { "epoch": 4.07, "learning_rate": 1.285509815833447e-06, "loss": 3.267, "step": 1970500 }, { "epoch": 4.07, "learning_rate": 1.2848210337516995e-06, "loss": 3.264, "step": 1971000 }, { "epoch": 4.07, "learning_rate": 1.2841322516699521e-06, "loss": 3.2608, "step": 1971500 }, { "epoch": 4.07, "learning_rate": 1.2834434695882046e-06, "loss": 3.2606, "step": 1972000 }, { "epoch": 4.08, "learning_rate": 1.2827546875064572e-06, "loss": 3.2634, "step": 1972500 }, { "epoch": 4.08, "learning_rate": 1.2820659054247098e-06, "loss": 3.2576, "step": 1973000 }, { "epoch": 4.08, "learning_rate": 1.2813771233429624e-06, "loss": 3.2649, "step": 1973500 }, { "epoch": 4.08, "learning_rate": 1.280688341261215e-06, "loss": 3.2639, "step": 1974000 }, { "epoch": 4.08, "learning_rate": 1.2799995591794677e-06, "loss": 3.2657, "step": 1974500 }, { "epoch": 4.08, "learning_rate": 1.2793107770977203e-06, "loss": 3.2623, "step": 1975000 }, { "epoch": 4.08, "learning_rate": 1.278621995015973e-06, "loss": 3.2676, "step": 1975500 }, { "epoch": 4.08, "learning_rate": 1.2779332129342253e-06, "loss": 3.2664, "step": 1976000 }, { "epoch": 4.08, "learning_rate": 1.277244430852478e-06, "loss": 3.2602, "step": 1976500 }, { "epoch": 4.09, "learning_rate": 1.2765556487707306e-06, "loss": 3.2617, "step": 1977000 }, { "epoch": 4.09, "learning_rate": 1.2758668666889832e-06, "loss": 3.2629, "step": 1977500 }, { "epoch": 4.09, "learning_rate": 1.2751780846072358e-06, "loss": 3.2637, "step": 1978000 }, { "epoch": 4.09, "learning_rate": 1.2744893025254884e-06, "loss": 3.2639, "step": 1978500 }, { "epoch": 4.09, "learning_rate": 1.273800520443741e-06, "loss": 3.267, "step": 1979000 }, { "epoch": 4.09, "learning_rate": 1.2731117383619937e-06, "loss": 3.2672, "step": 1979500 }, { "epoch": 4.09, "learning_rate": 1.272422956280246e-06, "loss": 3.2616, "step": 1980000 }, { "epoch": 4.09, "learning_rate": 1.2717341741984987e-06, "loss": 3.2712, "step": 1980500 }, { "epoch": 4.09, "learning_rate": 1.2710453921167513e-06, "loss": 3.2599, "step": 1981000 }, { "epoch": 4.09, "learning_rate": 1.2703566100350037e-06, "loss": 3.2586, "step": 1981500 }, { "epoch": 4.1, "learning_rate": 1.2696678279532564e-06, "loss": 3.2647, "step": 1982000 }, { "epoch": 4.1, "learning_rate": 1.268979045871509e-06, "loss": 3.267, "step": 1982500 }, { "epoch": 4.1, "learning_rate": 1.2682902637897616e-06, "loss": 3.2615, "step": 1983000 }, { "epoch": 4.1, "learning_rate": 1.2676014817080142e-06, "loss": 3.2701, "step": 1983500 }, { "epoch": 4.1, "learning_rate": 1.2669126996262666e-06, "loss": 3.2692, "step": 1984000 }, { "epoch": 4.1, "learning_rate": 1.2662239175445192e-06, "loss": 3.2576, "step": 1984500 }, { "epoch": 4.1, "learning_rate": 1.2655351354627719e-06, "loss": 3.262, "step": 1985000 }, { "epoch": 4.1, "learning_rate": 1.2648463533810245e-06, "loss": 3.2608, "step": 1985500 }, { "epoch": 4.1, "learning_rate": 1.2641575712992771e-06, "loss": 3.2572, "step": 1986000 }, { "epoch": 4.1, "learning_rate": 1.2634687892175297e-06, "loss": 3.2639, "step": 1986500 }, { "epoch": 4.11, "learning_rate": 1.2627800071357824e-06, "loss": 3.2627, "step": 1987000 }, { "epoch": 4.11, "learning_rate": 1.262091225054035e-06, "loss": 3.2592, "step": 1987500 }, { "epoch": 4.11, "learning_rate": 1.2614024429722876e-06, "loss": 3.2615, "step": 1988000 }, { "epoch": 4.11, "learning_rate": 1.26071366089054e-06, "loss": 3.2648, "step": 1988500 }, { "epoch": 4.11, "learning_rate": 1.2600248788087926e-06, "loss": 3.264, "step": 1989000 }, { "epoch": 4.11, "learning_rate": 1.2593360967270452e-06, "loss": 3.2584, "step": 1989500 }, { "epoch": 4.11, "learning_rate": 1.2586473146452979e-06, "loss": 3.2585, "step": 1990000 }, { "epoch": 4.11, "learning_rate": 1.2579585325635505e-06, "loss": 3.2652, "step": 1990500 }, { "epoch": 4.11, "learning_rate": 1.2572697504818031e-06, "loss": 3.2677, "step": 1991000 }, { "epoch": 4.12, "learning_rate": 1.2565809684000557e-06, "loss": 3.261, "step": 1991500 }, { "epoch": 4.12, "learning_rate": 1.2558921863183084e-06, "loss": 3.2661, "step": 1992000 }, { "epoch": 4.12, "learning_rate": 1.2552034042365608e-06, "loss": 3.2646, "step": 1992500 }, { "epoch": 4.12, "learning_rate": 1.2545146221548134e-06, "loss": 3.2653, "step": 1993000 }, { "epoch": 4.12, "learning_rate": 1.253825840073066e-06, "loss": 3.27, "step": 1993500 }, { "epoch": 4.12, "learning_rate": 1.2531370579913184e-06, "loss": 3.2594, "step": 1994000 }, { "epoch": 4.12, "learning_rate": 1.252448275909571e-06, "loss": 3.2605, "step": 1994500 }, { "epoch": 4.12, "learning_rate": 1.2517594938278237e-06, "loss": 3.2627, "step": 1995000 }, { "epoch": 4.12, "learning_rate": 1.2510707117460763e-06, "loss": 3.2636, "step": 1995500 }, { "epoch": 4.12, "learning_rate": 1.250381929664329e-06, "loss": 3.2586, "step": 1996000 }, { "epoch": 4.13, "learning_rate": 1.2496931475825813e-06, "loss": 3.2645, "step": 1996500 }, { "epoch": 4.13, "learning_rate": 1.249004365500834e-06, "loss": 3.2638, "step": 1997000 }, { "epoch": 4.13, "learning_rate": 1.2483155834190866e-06, "loss": 3.2635, "step": 1997500 }, { "epoch": 4.13, "learning_rate": 1.2476268013373392e-06, "loss": 3.2584, "step": 1998000 }, { "epoch": 4.13, "learning_rate": 1.2469380192555918e-06, "loss": 3.2613, "step": 1998500 }, { "epoch": 4.13, "learning_rate": 1.2462492371738444e-06, "loss": 3.2621, "step": 1999000 }, { "epoch": 4.13, "learning_rate": 1.245560455092097e-06, "loss": 3.2621, "step": 1999500 }, { "epoch": 4.13, "learning_rate": 1.2448716730103497e-06, "loss": 3.2625, "step": 2000000 }, { "epoch": 4.13, "learning_rate": 1.244182890928602e-06, "loss": 3.2623, "step": 2000500 }, { "epoch": 4.13, "learning_rate": 1.2434941088468547e-06, "loss": 3.2671, "step": 2001000 }, { "epoch": 4.14, "learning_rate": 1.2428053267651073e-06, "loss": 3.2559, "step": 2001500 }, { "epoch": 4.14, "learning_rate": 1.24211654468336e-06, "loss": 3.265, "step": 2002000 }, { "epoch": 4.14, "learning_rate": 1.2414277626016126e-06, "loss": 3.2618, "step": 2002500 }, { "epoch": 4.14, "learning_rate": 1.2407389805198652e-06, "loss": 3.266, "step": 2003000 }, { "epoch": 4.14, "learning_rate": 1.2400501984381178e-06, "loss": 3.2663, "step": 2003500 }, { "epoch": 4.14, "learning_rate": 1.2393614163563704e-06, "loss": 3.2579, "step": 2004000 }, { "epoch": 4.14, "learning_rate": 1.2386726342746228e-06, "loss": 3.2609, "step": 2004500 }, { "epoch": 4.14, "learning_rate": 1.2379838521928755e-06, "loss": 3.2674, "step": 2005000 }, { "epoch": 4.14, "learning_rate": 1.237295070111128e-06, "loss": 3.2616, "step": 2005500 }, { "epoch": 4.15, "learning_rate": 1.2366062880293807e-06, "loss": 3.2623, "step": 2006000 }, { "epoch": 4.15, "learning_rate": 1.2359175059476333e-06, "loss": 3.2614, "step": 2006500 }, { "epoch": 4.15, "learning_rate": 1.2352287238658857e-06, "loss": 3.2596, "step": 2007000 }, { "epoch": 4.15, "learning_rate": 1.2345399417841384e-06, "loss": 3.265, "step": 2007500 }, { "epoch": 4.15, "learning_rate": 1.233851159702391e-06, "loss": 3.2662, "step": 2008000 }, { "epoch": 4.15, "learning_rate": 1.2331623776206436e-06, "loss": 3.26, "step": 2008500 }, { "epoch": 4.15, "learning_rate": 1.232473595538896e-06, "loss": 3.257, "step": 2009000 }, { "epoch": 4.15, "learning_rate": 1.2317848134571486e-06, "loss": 3.2582, "step": 2009500 }, { "epoch": 4.15, "learning_rate": 1.2310960313754013e-06, "loss": 3.2641, "step": 2010000 }, { "epoch": 4.15, "learning_rate": 1.2304072492936539e-06, "loss": 3.2639, "step": 2010500 }, { "epoch": 4.16, "learning_rate": 1.2297184672119065e-06, "loss": 3.2649, "step": 2011000 }, { "epoch": 4.16, "learning_rate": 1.2290296851301591e-06, "loss": 3.2609, "step": 2011500 }, { "epoch": 4.16, "learning_rate": 1.2283409030484117e-06, "loss": 3.2592, "step": 2012000 }, { "epoch": 4.16, "learning_rate": 1.2276521209666644e-06, "loss": 3.2658, "step": 2012500 }, { "epoch": 4.16, "learning_rate": 1.2269633388849168e-06, "loss": 3.2657, "step": 2013000 }, { "epoch": 4.16, "learning_rate": 1.2262745568031694e-06, "loss": 3.2639, "step": 2013500 }, { "epoch": 4.16, "learning_rate": 1.225585774721422e-06, "loss": 3.26, "step": 2014000 }, { "epoch": 4.16, "learning_rate": 1.2248969926396746e-06, "loss": 3.2608, "step": 2014500 }, { "epoch": 4.16, "learning_rate": 1.2242082105579273e-06, "loss": 3.2554, "step": 2015000 }, { "epoch": 4.16, "learning_rate": 1.2235194284761799e-06, "loss": 3.2616, "step": 2015500 }, { "epoch": 4.17, "learning_rate": 1.2228306463944325e-06, "loss": 3.26, "step": 2016000 }, { "epoch": 4.17, "learning_rate": 1.2221418643126851e-06, "loss": 3.265, "step": 2016500 }, { "epoch": 4.17, "learning_rate": 1.2214530822309375e-06, "loss": 3.2608, "step": 2017000 }, { "epoch": 4.17, "learning_rate": 1.2207643001491902e-06, "loss": 3.2592, "step": 2017500 }, { "epoch": 4.17, "learning_rate": 1.2200755180674428e-06, "loss": 3.26, "step": 2018000 }, { "epoch": 4.17, "learning_rate": 1.2193867359856954e-06, "loss": 3.257, "step": 2018500 }, { "epoch": 4.17, "learning_rate": 1.218697953903948e-06, "loss": 3.2621, "step": 2019000 }, { "epoch": 4.17, "learning_rate": 1.2180091718222006e-06, "loss": 3.2551, "step": 2019500 }, { "epoch": 4.17, "learning_rate": 1.217320389740453e-06, "loss": 3.2581, "step": 2020000 }, { "epoch": 4.18, "learning_rate": 1.2166316076587057e-06, "loss": 3.2578, "step": 2020500 }, { "epoch": 4.18, "learning_rate": 1.215942825576958e-06, "loss": 3.2599, "step": 2021000 }, { "epoch": 4.18, "learning_rate": 1.2152540434952107e-06, "loss": 3.2721, "step": 2021500 }, { "epoch": 4.18, "learning_rate": 1.2145652614134633e-06, "loss": 3.2656, "step": 2022000 }, { "epoch": 4.18, "learning_rate": 1.213876479331716e-06, "loss": 3.2601, "step": 2022500 }, { "epoch": 4.18, "learning_rate": 1.2131876972499686e-06, "loss": 3.254, "step": 2023000 }, { "epoch": 4.18, "learning_rate": 1.2124989151682212e-06, "loss": 3.2625, "step": 2023500 }, { "epoch": 4.18, "learning_rate": 1.2118101330864738e-06, "loss": 3.2575, "step": 2024000 }, { "epoch": 4.18, "learning_rate": 1.2111213510047264e-06, "loss": 3.2573, "step": 2024500 }, { "epoch": 4.18, "learning_rate": 1.2104325689229788e-06, "loss": 3.2612, "step": 2025000 }, { "epoch": 4.19, "learning_rate": 1.2097437868412315e-06, "loss": 3.2565, "step": 2025500 }, { "epoch": 4.19, "learning_rate": 1.209055004759484e-06, "loss": 3.2578, "step": 2026000 }, { "epoch": 4.19, "learning_rate": 1.2083662226777367e-06, "loss": 3.2604, "step": 2026500 }, { "epoch": 4.19, "learning_rate": 1.2076774405959893e-06, "loss": 3.2579, "step": 2027000 }, { "epoch": 4.19, "learning_rate": 1.206988658514242e-06, "loss": 3.2581, "step": 2027500 }, { "epoch": 4.19, "learning_rate": 1.2062998764324946e-06, "loss": 3.2665, "step": 2028000 }, { "epoch": 4.19, "learning_rate": 1.2056110943507472e-06, "loss": 3.2615, "step": 2028500 }, { "epoch": 4.19, "learning_rate": 1.2049223122689998e-06, "loss": 3.2625, "step": 2029000 }, { "epoch": 4.19, "learning_rate": 1.2042335301872522e-06, "loss": 3.2665, "step": 2029500 }, { "epoch": 4.19, "learning_rate": 1.2035447481055048e-06, "loss": 3.2642, "step": 2030000 }, { "epoch": 4.2, "learning_rate": 1.2028559660237575e-06, "loss": 3.2621, "step": 2030500 }, { "epoch": 4.2, "learning_rate": 1.20216718394201e-06, "loss": 3.2612, "step": 2031000 }, { "epoch": 4.2, "learning_rate": 1.2014784018602627e-06, "loss": 3.2562, "step": 2031500 }, { "epoch": 4.2, "learning_rate": 1.2007896197785153e-06, "loss": 3.2555, "step": 2032000 }, { "epoch": 4.2, "learning_rate": 1.2001008376967677e-06, "loss": 3.2579, "step": 2032500 }, { "epoch": 4.2, "learning_rate": 1.1994120556150204e-06, "loss": 3.2593, "step": 2033000 }, { "epoch": 4.2, "learning_rate": 1.1987232735332728e-06, "loss": 3.2573, "step": 2033500 }, { "epoch": 4.2, "learning_rate": 1.1980344914515254e-06, "loss": 3.2582, "step": 2034000 }, { "epoch": 4.2, "learning_rate": 1.197345709369778e-06, "loss": 3.255, "step": 2034500 }, { "epoch": 4.21, "learning_rate": 1.1966569272880306e-06, "loss": 3.2654, "step": 2035000 }, { "epoch": 4.21, "learning_rate": 1.1959681452062833e-06, "loss": 3.2584, "step": 2035500 }, { "epoch": 4.21, "learning_rate": 1.1952793631245359e-06, "loss": 3.2585, "step": 2036000 }, { "epoch": 4.21, "learning_rate": 1.1945905810427885e-06, "loss": 3.2619, "step": 2036500 }, { "epoch": 4.21, "learning_rate": 1.1939017989610411e-06, "loss": 3.2604, "step": 2037000 }, { "epoch": 4.21, "learning_rate": 1.1932130168792935e-06, "loss": 3.2672, "step": 2037500 }, { "epoch": 4.21, "learning_rate": 1.1925242347975462e-06, "loss": 3.2641, "step": 2038000 }, { "epoch": 4.21, "learning_rate": 1.1918354527157988e-06, "loss": 3.2558, "step": 2038500 }, { "epoch": 4.21, "learning_rate": 1.1911466706340514e-06, "loss": 3.2565, "step": 2039000 }, { "epoch": 4.21, "learning_rate": 1.190457888552304e-06, "loss": 3.2611, "step": 2039500 }, { "epoch": 4.22, "learning_rate": 1.1897691064705566e-06, "loss": 3.2628, "step": 2040000 }, { "epoch": 4.22, "learning_rate": 1.1890803243888093e-06, "loss": 3.2636, "step": 2040500 }, { "epoch": 4.22, "learning_rate": 1.1883915423070619e-06, "loss": 3.264, "step": 2041000 }, { "epoch": 4.22, "learning_rate": 1.1877027602253143e-06, "loss": 3.2633, "step": 2041500 }, { "epoch": 4.22, "learning_rate": 1.187013978143567e-06, "loss": 3.2582, "step": 2042000 }, { "epoch": 4.22, "learning_rate": 1.1863251960618195e-06, "loss": 3.2603, "step": 2042500 }, { "epoch": 4.22, "learning_rate": 1.1856364139800722e-06, "loss": 3.2569, "step": 2043000 }, { "epoch": 4.22, "learning_rate": 1.1849476318983248e-06, "loss": 3.2595, "step": 2043500 }, { "epoch": 4.22, "learning_rate": 1.1842588498165774e-06, "loss": 3.2604, "step": 2044000 }, { "epoch": 4.22, "learning_rate": 1.18357006773483e-06, "loss": 3.2603, "step": 2044500 }, { "epoch": 4.23, "learning_rate": 1.1828812856530826e-06, "loss": 3.2551, "step": 2045000 }, { "epoch": 4.23, "learning_rate": 1.1821925035713348e-06, "loss": 3.2632, "step": 2045500 }, { "epoch": 4.23, "learning_rate": 1.1815037214895875e-06, "loss": 3.2613, "step": 2046000 }, { "epoch": 4.23, "learning_rate": 1.18081493940784e-06, "loss": 3.2611, "step": 2046500 }, { "epoch": 4.23, "learning_rate": 1.1801261573260927e-06, "loss": 3.2641, "step": 2047000 }, { "epoch": 4.23, "learning_rate": 1.1794373752443453e-06, "loss": 3.2652, "step": 2047500 }, { "epoch": 4.23, "learning_rate": 1.178748593162598e-06, "loss": 3.2586, "step": 2048000 }, { "epoch": 4.23, "learning_rate": 1.1780598110808506e-06, "loss": 3.2604, "step": 2048500 }, { "epoch": 4.23, "learning_rate": 1.1773710289991032e-06, "loss": 3.2598, "step": 2049000 }, { "epoch": 4.23, "learning_rate": 1.1766822469173558e-06, "loss": 3.2559, "step": 2049500 }, { "epoch": 4.24, "learning_rate": 1.1759934648356082e-06, "loss": 3.2631, "step": 2050000 }, { "epoch": 4.24, "learning_rate": 1.1753046827538608e-06, "loss": 3.2552, "step": 2050500 }, { "epoch": 4.24, "learning_rate": 1.1746159006721135e-06, "loss": 3.2616, "step": 2051000 }, { "epoch": 4.24, "learning_rate": 1.173927118590366e-06, "loss": 3.2534, "step": 2051500 }, { "epoch": 4.24, "learning_rate": 1.1732383365086187e-06, "loss": 3.2598, "step": 2052000 }, { "epoch": 4.24, "learning_rate": 1.1725495544268713e-06, "loss": 3.2572, "step": 2052500 }, { "epoch": 4.24, "learning_rate": 1.171860772345124e-06, "loss": 3.2647, "step": 2053000 }, { "epoch": 4.24, "learning_rate": 1.1711719902633766e-06, "loss": 3.2643, "step": 2053500 }, { "epoch": 4.24, "learning_rate": 1.170483208181629e-06, "loss": 3.2611, "step": 2054000 }, { "epoch": 4.25, "learning_rate": 1.1697944260998816e-06, "loss": 3.2628, "step": 2054500 }, { "epoch": 4.25, "learning_rate": 1.1691056440181342e-06, "loss": 3.2598, "step": 2055000 }, { "epoch": 4.25, "learning_rate": 1.1684168619363868e-06, "loss": 3.2642, "step": 2055500 }, { "epoch": 4.25, "learning_rate": 1.1677280798546395e-06, "loss": 3.2564, "step": 2056000 }, { "epoch": 4.25, "learning_rate": 1.167039297772892e-06, "loss": 3.262, "step": 2056500 }, { "epoch": 4.25, "learning_rate": 1.1663505156911447e-06, "loss": 3.2586, "step": 2057000 }, { "epoch": 4.25, "learning_rate": 1.1656617336093973e-06, "loss": 3.2581, "step": 2057500 }, { "epoch": 4.25, "learning_rate": 1.1649729515276495e-06, "loss": 3.2593, "step": 2058000 }, { "epoch": 4.25, "learning_rate": 1.1642841694459022e-06, "loss": 3.2624, "step": 2058500 }, { "epoch": 4.25, "learning_rate": 1.1635953873641548e-06, "loss": 3.2593, "step": 2059000 }, { "epoch": 4.26, "learning_rate": 1.1629066052824074e-06, "loss": 3.2614, "step": 2059500 }, { "epoch": 4.26, "learning_rate": 1.16221782320066e-06, "loss": 3.2568, "step": 2060000 }, { "epoch": 4.26, "learning_rate": 1.1615290411189126e-06, "loss": 3.2578, "step": 2060500 }, { "epoch": 4.26, "learning_rate": 1.1608402590371653e-06, "loss": 3.2585, "step": 2061000 }, { "epoch": 4.26, "learning_rate": 1.1601514769554179e-06, "loss": 3.2665, "step": 2061500 }, { "epoch": 4.26, "learning_rate": 1.1594626948736703e-06, "loss": 3.2629, "step": 2062000 }, { "epoch": 4.26, "learning_rate": 1.158773912791923e-06, "loss": 3.2575, "step": 2062500 }, { "epoch": 4.26, "learning_rate": 1.1580851307101755e-06, "loss": 3.2602, "step": 2063000 }, { "epoch": 4.26, "learning_rate": 1.1573963486284282e-06, "loss": 3.259, "step": 2063500 }, { "epoch": 4.26, "learning_rate": 1.1567075665466808e-06, "loss": 3.2583, "step": 2064000 }, { "epoch": 4.27, "learning_rate": 1.1560187844649334e-06, "loss": 3.2603, "step": 2064500 }, { "epoch": 4.27, "learning_rate": 1.155330002383186e-06, "loss": 3.2565, "step": 2065000 }, { "epoch": 4.27, "learning_rate": 1.1546412203014386e-06, "loss": 3.2525, "step": 2065500 }, { "epoch": 4.27, "learning_rate": 1.153952438219691e-06, "loss": 3.2562, "step": 2066000 }, { "epoch": 4.27, "learning_rate": 1.1532636561379437e-06, "loss": 3.2555, "step": 2066500 }, { "epoch": 4.27, "learning_rate": 1.1525748740561963e-06, "loss": 3.2618, "step": 2067000 }, { "epoch": 4.27, "learning_rate": 1.151886091974449e-06, "loss": 3.2663, "step": 2067500 }, { "epoch": 4.27, "learning_rate": 1.1511973098927015e-06, "loss": 3.2612, "step": 2068000 }, { "epoch": 4.27, "learning_rate": 1.1505085278109542e-06, "loss": 3.2582, "step": 2068500 }, { "epoch": 4.28, "learning_rate": 1.1498197457292068e-06, "loss": 3.2614, "step": 2069000 }, { "epoch": 4.28, "learning_rate": 1.1491309636474594e-06, "loss": 3.2611, "step": 2069500 }, { "epoch": 4.28, "learning_rate": 1.148442181565712e-06, "loss": 3.2611, "step": 2070000 }, { "epoch": 4.28, "learning_rate": 1.1477533994839642e-06, "loss": 3.2536, "step": 2070500 }, { "epoch": 4.28, "learning_rate": 1.1470646174022168e-06, "loss": 3.2576, "step": 2071000 }, { "epoch": 4.28, "learning_rate": 1.1463758353204695e-06, "loss": 3.2578, "step": 2071500 }, { "epoch": 4.28, "learning_rate": 1.145687053238722e-06, "loss": 3.2514, "step": 2072000 }, { "epoch": 4.28, "learning_rate": 1.1449982711569747e-06, "loss": 3.258, "step": 2072500 }, { "epoch": 4.28, "learning_rate": 1.1443094890752273e-06, "loss": 3.2548, "step": 2073000 }, { "epoch": 4.28, "learning_rate": 1.14362070699348e-06, "loss": 3.2503, "step": 2073500 }, { "epoch": 4.29, "learning_rate": 1.1429319249117326e-06, "loss": 3.256, "step": 2074000 }, { "epoch": 4.29, "learning_rate": 1.142243142829985e-06, "loss": 3.2543, "step": 2074500 }, { "epoch": 4.29, "learning_rate": 1.1415543607482376e-06, "loss": 3.2635, "step": 2075000 }, { "epoch": 4.29, "learning_rate": 1.1408655786664902e-06, "loss": 3.2581, "step": 2075500 }, { "epoch": 4.29, "learning_rate": 1.1401767965847428e-06, "loss": 3.2559, "step": 2076000 }, { "epoch": 4.29, "learning_rate": 1.1394880145029955e-06, "loss": 3.2585, "step": 2076500 }, { "epoch": 4.29, "learning_rate": 1.138799232421248e-06, "loss": 3.2566, "step": 2077000 }, { "epoch": 4.29, "learning_rate": 1.1381104503395007e-06, "loss": 3.2522, "step": 2077500 }, { "epoch": 4.29, "learning_rate": 1.1374216682577533e-06, "loss": 3.2516, "step": 2078000 }, { "epoch": 4.29, "learning_rate": 1.1367328861760057e-06, "loss": 3.2645, "step": 2078500 }, { "epoch": 4.3, "learning_rate": 1.1360441040942584e-06, "loss": 3.2552, "step": 2079000 }, { "epoch": 4.3, "learning_rate": 1.135355322012511e-06, "loss": 3.2557, "step": 2079500 }, { "epoch": 4.3, "learning_rate": 1.1346665399307636e-06, "loss": 3.255, "step": 2080000 }, { "epoch": 4.3, "learning_rate": 1.1339777578490162e-06, "loss": 3.2592, "step": 2080500 }, { "epoch": 4.3, "learning_rate": 1.1332889757672689e-06, "loss": 3.2549, "step": 2081000 }, { "epoch": 4.3, "learning_rate": 1.1326001936855215e-06, "loss": 3.2568, "step": 2081500 }, { "epoch": 4.3, "learning_rate": 1.131911411603774e-06, "loss": 3.2638, "step": 2082000 }, { "epoch": 4.3, "learning_rate": 1.1312226295220265e-06, "loss": 3.257, "step": 2082500 }, { "epoch": 4.3, "learning_rate": 1.130533847440279e-06, "loss": 3.2585, "step": 2083000 }, { "epoch": 4.31, "learning_rate": 1.1298450653585315e-06, "loss": 3.2557, "step": 2083500 }, { "epoch": 4.31, "learning_rate": 1.1291562832767842e-06, "loss": 3.2617, "step": 2084000 }, { "epoch": 4.31, "learning_rate": 1.1284675011950368e-06, "loss": 3.2547, "step": 2084500 }, { "epoch": 4.31, "learning_rate": 1.1277787191132894e-06, "loss": 3.2562, "step": 2085000 }, { "epoch": 4.31, "learning_rate": 1.127089937031542e-06, "loss": 3.2605, "step": 2085500 }, { "epoch": 4.31, "learning_rate": 1.1264011549497946e-06, "loss": 3.2523, "step": 2086000 }, { "epoch": 4.31, "learning_rate": 1.125712372868047e-06, "loss": 3.26, "step": 2086500 }, { "epoch": 4.31, "learning_rate": 1.1250235907862997e-06, "loss": 3.2644, "step": 2087000 }, { "epoch": 4.31, "learning_rate": 1.1243348087045523e-06, "loss": 3.2554, "step": 2087500 }, { "epoch": 4.31, "learning_rate": 1.123646026622805e-06, "loss": 3.2555, "step": 2088000 }, { "epoch": 4.32, "learning_rate": 1.1229572445410575e-06, "loss": 3.2519, "step": 2088500 }, { "epoch": 4.32, "learning_rate": 1.1222684624593102e-06, "loss": 3.263, "step": 2089000 }, { "epoch": 4.32, "learning_rate": 1.1215796803775628e-06, "loss": 3.2609, "step": 2089500 }, { "epoch": 4.32, "learning_rate": 1.1208908982958154e-06, "loss": 3.2589, "step": 2090000 }, { "epoch": 4.32, "learning_rate": 1.120202116214068e-06, "loss": 3.2577, "step": 2090500 }, { "epoch": 4.32, "learning_rate": 1.1195133341323204e-06, "loss": 3.2561, "step": 2091000 }, { "epoch": 4.32, "learning_rate": 1.118824552050573e-06, "loss": 3.2576, "step": 2091500 }, { "epoch": 4.32, "learning_rate": 1.1181357699688257e-06, "loss": 3.2582, "step": 2092000 }, { "epoch": 4.32, "learning_rate": 1.1174469878870783e-06, "loss": 3.261, "step": 2092500 }, { "epoch": 4.32, "learning_rate": 1.116758205805331e-06, "loss": 3.2584, "step": 2093000 }, { "epoch": 4.33, "learning_rate": 1.1160694237235835e-06, "loss": 3.2636, "step": 2093500 }, { "epoch": 4.33, "learning_rate": 1.1153806416418362e-06, "loss": 3.2596, "step": 2094000 }, { "epoch": 4.33, "learning_rate": 1.1146918595600888e-06, "loss": 3.2559, "step": 2094500 }, { "epoch": 4.33, "learning_rate": 1.1140030774783412e-06, "loss": 3.2582, "step": 2095000 }, { "epoch": 4.33, "learning_rate": 1.1133142953965938e-06, "loss": 3.257, "step": 2095500 }, { "epoch": 4.33, "learning_rate": 1.1126255133148462e-06, "loss": 3.2598, "step": 2096000 }, { "epoch": 4.33, "learning_rate": 1.1119367312330989e-06, "loss": 3.2605, "step": 2096500 }, { "epoch": 4.33, "learning_rate": 1.1112479491513515e-06, "loss": 3.2564, "step": 2097000 }, { "epoch": 4.33, "learning_rate": 1.110559167069604e-06, "loss": 3.2592, "step": 2097500 }, { "epoch": 4.34, "learning_rate": 1.1098703849878567e-06, "loss": 3.2535, "step": 2098000 }, { "epoch": 4.34, "learning_rate": 1.1091816029061093e-06, "loss": 3.2551, "step": 2098500 }, { "epoch": 4.34, "learning_rate": 1.1084928208243617e-06, "loss": 3.2577, "step": 2099000 }, { "epoch": 4.34, "learning_rate": 1.1078040387426144e-06, "loss": 3.2474, "step": 2099500 }, { "epoch": 4.34, "learning_rate": 1.107115256660867e-06, "loss": 3.2471, "step": 2100000 }, { "epoch": 4.34, "learning_rate": 1.1064264745791196e-06, "loss": 3.2553, "step": 2100500 }, { "epoch": 4.34, "learning_rate": 1.1057376924973722e-06, "loss": 3.2552, "step": 2101000 }, { "epoch": 4.34, "learning_rate": 1.1050489104156249e-06, "loss": 3.2588, "step": 2101500 }, { "epoch": 4.34, "learning_rate": 1.1043601283338775e-06, "loss": 3.2631, "step": 2102000 }, { "epoch": 4.34, "learning_rate": 1.10367134625213e-06, "loss": 3.2544, "step": 2102500 }, { "epoch": 4.35, "learning_rate": 1.1029825641703825e-06, "loss": 3.2542, "step": 2103000 }, { "epoch": 4.35, "learning_rate": 1.1022937820886351e-06, "loss": 3.2521, "step": 2103500 }, { "epoch": 4.35, "learning_rate": 1.1016050000068878e-06, "loss": 3.2576, "step": 2104000 }, { "epoch": 4.35, "learning_rate": 1.1009162179251404e-06, "loss": 3.2564, "step": 2104500 }, { "epoch": 4.35, "learning_rate": 1.100227435843393e-06, "loss": 3.2511, "step": 2105000 }, { "epoch": 4.35, "learning_rate": 1.0995386537616456e-06, "loss": 3.2639, "step": 2105500 }, { "epoch": 4.35, "learning_rate": 1.0988498716798982e-06, "loss": 3.2592, "step": 2106000 }, { "epoch": 4.35, "learning_rate": 1.0981610895981509e-06, "loss": 3.2529, "step": 2106500 }, { "epoch": 4.35, "learning_rate": 1.0974723075164035e-06, "loss": 3.2616, "step": 2107000 }, { "epoch": 4.35, "learning_rate": 1.0967835254346559e-06, "loss": 3.2532, "step": 2107500 }, { "epoch": 4.36, "learning_rate": 1.0960947433529085e-06, "loss": 3.256, "step": 2108000 }, { "epoch": 4.36, "learning_rate": 1.0954059612711611e-06, "loss": 3.2609, "step": 2108500 }, { "epoch": 4.36, "learning_rate": 1.0947171791894135e-06, "loss": 3.2525, "step": 2109000 }, { "epoch": 4.36, "learning_rate": 1.0940283971076662e-06, "loss": 3.2572, "step": 2109500 }, { "epoch": 4.36, "learning_rate": 1.0933396150259188e-06, "loss": 3.2595, "step": 2110000 }, { "epoch": 4.36, "learning_rate": 1.0926508329441714e-06, "loss": 3.2538, "step": 2110500 }, { "epoch": 4.36, "learning_rate": 1.091962050862424e-06, "loss": 3.2592, "step": 2111000 }, { "epoch": 4.36, "learning_rate": 1.0912732687806764e-06, "loss": 3.2571, "step": 2111500 }, { "epoch": 4.36, "learning_rate": 1.090584486698929e-06, "loss": 3.2574, "step": 2112000 }, { "epoch": 4.37, "learning_rate": 1.0898957046171817e-06, "loss": 3.2581, "step": 2112500 }, { "epoch": 4.37, "learning_rate": 1.0892069225354343e-06, "loss": 3.2555, "step": 2113000 }, { "epoch": 4.37, "learning_rate": 1.088518140453687e-06, "loss": 3.2524, "step": 2113500 }, { "epoch": 4.37, "learning_rate": 1.0878293583719395e-06, "loss": 3.2623, "step": 2114000 }, { "epoch": 4.37, "learning_rate": 1.0871405762901922e-06, "loss": 3.2558, "step": 2114500 }, { "epoch": 4.37, "learning_rate": 1.0864517942084448e-06, "loss": 3.2604, "step": 2115000 }, { "epoch": 4.37, "learning_rate": 1.0857630121266972e-06, "loss": 3.2581, "step": 2115500 }, { "epoch": 4.37, "learning_rate": 1.0850742300449498e-06, "loss": 3.2581, "step": 2116000 }, { "epoch": 4.37, "learning_rate": 1.0843854479632024e-06, "loss": 3.2597, "step": 2116500 }, { "epoch": 4.37, "learning_rate": 1.083696665881455e-06, "loss": 3.2606, "step": 2117000 }, { "epoch": 4.38, "learning_rate": 1.0830078837997077e-06, "loss": 3.2629, "step": 2117500 }, { "epoch": 4.38, "learning_rate": 1.0823191017179603e-06, "loss": 3.2553, "step": 2118000 }, { "epoch": 4.38, "learning_rate": 1.081630319636213e-06, "loss": 3.2547, "step": 2118500 }, { "epoch": 4.38, "learning_rate": 1.0809415375544656e-06, "loss": 3.2563, "step": 2119000 }, { "epoch": 4.38, "learning_rate": 1.080252755472718e-06, "loss": 3.2601, "step": 2119500 }, { "epoch": 4.38, "learning_rate": 1.0795639733909706e-06, "loss": 3.255, "step": 2120000 }, { "epoch": 4.38, "learning_rate": 1.0788751913092232e-06, "loss": 3.2523, "step": 2120500 }, { "epoch": 4.38, "learning_rate": 1.0781864092274758e-06, "loss": 3.2606, "step": 2121000 }, { "epoch": 4.38, "learning_rate": 1.0774976271457282e-06, "loss": 3.256, "step": 2121500 }, { "epoch": 4.38, "learning_rate": 1.0768088450639809e-06, "loss": 3.2613, "step": 2122000 }, { "epoch": 4.39, "learning_rate": 1.0761200629822335e-06, "loss": 3.2575, "step": 2122500 }, { "epoch": 4.39, "learning_rate": 1.075431280900486e-06, "loss": 3.2583, "step": 2123000 }, { "epoch": 4.39, "learning_rate": 1.0747424988187385e-06, "loss": 3.2571, "step": 2123500 }, { "epoch": 4.39, "learning_rate": 1.0740537167369911e-06, "loss": 3.251, "step": 2124000 }, { "epoch": 4.39, "learning_rate": 1.0733649346552438e-06, "loss": 3.2595, "step": 2124500 }, { "epoch": 4.39, "learning_rate": 1.0726761525734964e-06, "loss": 3.2572, "step": 2125000 }, { "epoch": 4.39, "learning_rate": 1.071987370491749e-06, "loss": 3.252, "step": 2125500 }, { "epoch": 4.39, "learning_rate": 1.0712985884100016e-06, "loss": 3.2561, "step": 2126000 }, { "epoch": 4.39, "learning_rate": 1.0706098063282542e-06, "loss": 3.2542, "step": 2126500 }, { "epoch": 4.4, "learning_rate": 1.0699210242465069e-06, "loss": 3.2537, "step": 2127000 }, { "epoch": 4.4, "learning_rate": 1.0692322421647595e-06, "loss": 3.2557, "step": 2127500 }, { "epoch": 4.4, "learning_rate": 1.0685434600830119e-06, "loss": 3.2532, "step": 2128000 }, { "epoch": 4.4, "learning_rate": 1.0678546780012645e-06, "loss": 3.2618, "step": 2128500 }, { "epoch": 4.4, "learning_rate": 1.0671658959195171e-06, "loss": 3.2567, "step": 2129000 }, { "epoch": 4.4, "learning_rate": 1.0664771138377698e-06, "loss": 3.2593, "step": 2129500 }, { "epoch": 4.4, "learning_rate": 1.0657883317560224e-06, "loss": 3.2574, "step": 2130000 }, { "epoch": 4.4, "learning_rate": 1.065099549674275e-06, "loss": 3.2541, "step": 2130500 }, { "epoch": 4.4, "learning_rate": 1.0644107675925276e-06, "loss": 3.2567, "step": 2131000 }, { "epoch": 4.4, "learning_rate": 1.0637219855107802e-06, "loss": 3.2581, "step": 2131500 }, { "epoch": 4.41, "learning_rate": 1.0630332034290327e-06, "loss": 3.2494, "step": 2132000 }, { "epoch": 4.41, "learning_rate": 1.0623444213472853e-06, "loss": 3.25, "step": 2132500 }, { "epoch": 4.41, "learning_rate": 1.061655639265538e-06, "loss": 3.2501, "step": 2133000 }, { "epoch": 4.41, "learning_rate": 1.0609668571837905e-06, "loss": 3.2547, "step": 2133500 }, { "epoch": 4.41, "learning_rate": 1.0602780751020431e-06, "loss": 3.2599, "step": 2134000 }, { "epoch": 4.41, "learning_rate": 1.0595892930202955e-06, "loss": 3.254, "step": 2134500 }, { "epoch": 4.41, "learning_rate": 1.0589005109385482e-06, "loss": 3.2563, "step": 2135000 }, { "epoch": 4.41, "learning_rate": 1.0582117288568008e-06, "loss": 3.2541, "step": 2135500 }, { "epoch": 4.41, "learning_rate": 1.0575229467750532e-06, "loss": 3.2611, "step": 2136000 }, { "epoch": 4.41, "learning_rate": 1.0568341646933058e-06, "loss": 3.2564, "step": 2136500 }, { "epoch": 4.42, "learning_rate": 1.0561453826115584e-06, "loss": 3.2554, "step": 2137000 }, { "epoch": 4.42, "learning_rate": 1.055456600529811e-06, "loss": 3.2515, "step": 2137500 }, { "epoch": 4.42, "learning_rate": 1.0547678184480637e-06, "loss": 3.2532, "step": 2138000 }, { "epoch": 4.42, "learning_rate": 1.0540790363663163e-06, "loss": 3.2547, "step": 2138500 }, { "epoch": 4.42, "learning_rate": 1.053390254284569e-06, "loss": 3.2568, "step": 2139000 }, { "epoch": 4.42, "learning_rate": 1.0527014722028216e-06, "loss": 3.2553, "step": 2139500 }, { "epoch": 4.42, "learning_rate": 1.052012690121074e-06, "loss": 3.2533, "step": 2140000 }, { "epoch": 4.42, "learning_rate": 1.0513239080393266e-06, "loss": 3.259, "step": 2140500 }, { "epoch": 4.42, "learning_rate": 1.0506351259575792e-06, "loss": 3.2569, "step": 2141000 }, { "epoch": 4.43, "learning_rate": 1.0499463438758318e-06, "loss": 3.2515, "step": 2141500 }, { "epoch": 4.43, "learning_rate": 1.0492575617940844e-06, "loss": 3.2569, "step": 2142000 }, { "epoch": 4.43, "learning_rate": 1.048568779712337e-06, "loss": 3.2507, "step": 2142500 }, { "epoch": 4.43, "learning_rate": 1.0478799976305897e-06, "loss": 3.2506, "step": 2143000 }, { "epoch": 4.43, "learning_rate": 1.0471912155488423e-06, "loss": 3.2529, "step": 2143500 }, { "epoch": 4.43, "learning_rate": 1.0465024334670947e-06, "loss": 3.2514, "step": 2144000 }, { "epoch": 4.43, "learning_rate": 1.0458136513853473e-06, "loss": 3.26, "step": 2144500 }, { "epoch": 4.43, "learning_rate": 1.0451248693036e-06, "loss": 3.2542, "step": 2145000 }, { "epoch": 4.43, "learning_rate": 1.0444360872218526e-06, "loss": 3.2601, "step": 2145500 }, { "epoch": 4.43, "learning_rate": 1.0437473051401052e-06, "loss": 3.2532, "step": 2146000 }, { "epoch": 4.44, "learning_rate": 1.0430585230583578e-06, "loss": 3.2507, "step": 2146500 }, { "epoch": 4.44, "learning_rate": 1.0423697409766102e-06, "loss": 3.2605, "step": 2147000 }, { "epoch": 4.44, "learning_rate": 1.0416809588948629e-06, "loss": 3.2548, "step": 2147500 }, { "epoch": 4.44, "learning_rate": 1.0409921768131155e-06, "loss": 3.2552, "step": 2148000 }, { "epoch": 4.44, "learning_rate": 1.0403033947313679e-06, "loss": 3.2622, "step": 2148500 }, { "epoch": 4.44, "learning_rate": 1.0396146126496205e-06, "loss": 3.2516, "step": 2149000 }, { "epoch": 4.44, "learning_rate": 1.0389258305678731e-06, "loss": 3.2514, "step": 2149500 }, { "epoch": 4.44, "learning_rate": 1.0382370484861258e-06, "loss": 3.2562, "step": 2150000 }, { "epoch": 4.44, "learning_rate": 1.0375482664043784e-06, "loss": 3.256, "step": 2150500 }, { "epoch": 4.44, "learning_rate": 1.036859484322631e-06, "loss": 3.2459, "step": 2151000 }, { "epoch": 4.45, "learning_rate": 1.0361707022408836e-06, "loss": 3.2512, "step": 2151500 }, { "epoch": 4.45, "learning_rate": 1.0354819201591362e-06, "loss": 3.2597, "step": 2152000 }, { "epoch": 4.45, "learning_rate": 1.0347931380773887e-06, "loss": 3.26, "step": 2152500 }, { "epoch": 4.45, "learning_rate": 1.0341043559956413e-06, "loss": 3.2546, "step": 2153000 }, { "epoch": 4.45, "learning_rate": 1.033415573913894e-06, "loss": 3.2584, "step": 2153500 }, { "epoch": 4.45, "learning_rate": 1.0327267918321465e-06, "loss": 3.2486, "step": 2154000 }, { "epoch": 4.45, "learning_rate": 1.0320380097503991e-06, "loss": 3.2614, "step": 2154500 }, { "epoch": 4.45, "learning_rate": 1.0313492276686518e-06, "loss": 3.251, "step": 2155000 }, { "epoch": 4.45, "learning_rate": 1.0306604455869044e-06, "loss": 3.2502, "step": 2155500 }, { "epoch": 4.46, "learning_rate": 1.029971663505157e-06, "loss": 3.2555, "step": 2156000 }, { "epoch": 4.46, "learning_rate": 1.0292828814234094e-06, "loss": 3.2542, "step": 2156500 }, { "epoch": 4.46, "learning_rate": 1.028594099341662e-06, "loss": 3.2579, "step": 2157000 }, { "epoch": 4.46, "learning_rate": 1.0279053172599147e-06, "loss": 3.2536, "step": 2157500 }, { "epoch": 4.46, "learning_rate": 1.0272165351781673e-06, "loss": 3.2508, "step": 2158000 }, { "epoch": 4.46, "learning_rate": 1.02652775309642e-06, "loss": 3.2509, "step": 2158500 }, { "epoch": 4.46, "learning_rate": 1.0258389710146725e-06, "loss": 3.251, "step": 2159000 }, { "epoch": 4.46, "learning_rate": 1.0251501889329251e-06, "loss": 3.2513, "step": 2159500 }, { "epoch": 4.46, "learning_rate": 1.0244614068511776e-06, "loss": 3.2492, "step": 2160000 }, { "epoch": 4.46, "learning_rate": 1.02377262476943e-06, "loss": 3.2461, "step": 2160500 }, { "epoch": 4.47, "learning_rate": 1.0230838426876826e-06, "loss": 3.2518, "step": 2161000 }, { "epoch": 4.47, "learning_rate": 1.0223950606059352e-06, "loss": 3.2554, "step": 2161500 }, { "epoch": 4.47, "learning_rate": 1.0217062785241878e-06, "loss": 3.2587, "step": 2162000 }, { "epoch": 4.47, "learning_rate": 1.0210174964424404e-06, "loss": 3.255, "step": 2162500 }, { "epoch": 4.47, "learning_rate": 1.020328714360693e-06, "loss": 3.2521, "step": 2163000 }, { "epoch": 4.47, "learning_rate": 1.0196399322789457e-06, "loss": 3.2467, "step": 2163500 }, { "epoch": 4.47, "learning_rate": 1.0189511501971983e-06, "loss": 3.2516, "step": 2164000 }, { "epoch": 4.47, "learning_rate": 1.0182623681154507e-06, "loss": 3.2504, "step": 2164500 }, { "epoch": 4.47, "learning_rate": 1.0175735860337033e-06, "loss": 3.2456, "step": 2165000 }, { "epoch": 4.47, "learning_rate": 1.016884803951956e-06, "loss": 3.254, "step": 2165500 }, { "epoch": 4.48, "learning_rate": 1.0161960218702086e-06, "loss": 3.2552, "step": 2166000 }, { "epoch": 4.48, "learning_rate": 1.0155072397884612e-06, "loss": 3.2513, "step": 2166500 }, { "epoch": 4.48, "learning_rate": 1.0148184577067138e-06, "loss": 3.257, "step": 2167000 }, { "epoch": 4.48, "learning_rate": 1.0141296756249665e-06, "loss": 3.2485, "step": 2167500 }, { "epoch": 4.48, "learning_rate": 1.013440893543219e-06, "loss": 3.2579, "step": 2168000 }, { "epoch": 4.48, "learning_rate": 1.0127521114614717e-06, "loss": 3.2519, "step": 2168500 }, { "epoch": 4.48, "learning_rate": 1.0120633293797241e-06, "loss": 3.2559, "step": 2169000 }, { "epoch": 4.48, "learning_rate": 1.0113745472979767e-06, "loss": 3.2524, "step": 2169500 }, { "epoch": 4.48, "learning_rate": 1.0106857652162293e-06, "loss": 3.2523, "step": 2170000 }, { "epoch": 4.49, "learning_rate": 1.009996983134482e-06, "loss": 3.2577, "step": 2170500 }, { "epoch": 4.49, "learning_rate": 1.0093082010527346e-06, "loss": 3.2503, "step": 2171000 }, { "epoch": 4.49, "learning_rate": 1.0086194189709872e-06, "loss": 3.2554, "step": 2171500 }, { "epoch": 4.49, "learning_rate": 1.0079306368892398e-06, "loss": 3.2564, "step": 2172000 }, { "epoch": 4.49, "learning_rate": 1.0072418548074925e-06, "loss": 3.2539, "step": 2172500 }, { "epoch": 4.49, "learning_rate": 1.0065530727257447e-06, "loss": 3.255, "step": 2173000 }, { "epoch": 4.49, "learning_rate": 1.0058642906439973e-06, "loss": 3.2482, "step": 2173500 }, { "epoch": 4.49, "learning_rate": 1.00517550856225e-06, "loss": 3.2596, "step": 2174000 }, { "epoch": 4.49, "learning_rate": 1.0044867264805025e-06, "loss": 3.2557, "step": 2174500 }, { "epoch": 4.49, "learning_rate": 1.0037979443987551e-06, "loss": 3.265, "step": 2175000 }, { "epoch": 4.5, "learning_rate": 1.0031091623170078e-06, "loss": 3.2573, "step": 2175500 }, { "epoch": 4.5, "learning_rate": 1.0024203802352604e-06, "loss": 3.2444, "step": 2176000 }, { "epoch": 4.5, "learning_rate": 1.001731598153513e-06, "loss": 3.253, "step": 2176500 }, { "epoch": 4.5, "learning_rate": 1.0010428160717654e-06, "loss": 3.2482, "step": 2177000 }, { "epoch": 4.5, "learning_rate": 1.000354033990018e-06, "loss": 3.2518, "step": 2177500 }, { "epoch": 4.5, "learning_rate": 9.996652519082707e-07, "loss": 3.2473, "step": 2178000 }, { "epoch": 4.5, "learning_rate": 9.989764698265233e-07, "loss": 3.2521, "step": 2178500 }, { "epoch": 4.5, "learning_rate": 9.98287687744776e-07, "loss": 3.2544, "step": 2179000 }, { "epoch": 4.5, "learning_rate": 9.975989056630285e-07, "loss": 3.2528, "step": 2179500 }, { "epoch": 4.5, "learning_rate": 9.96910123581281e-07, "loss": 3.2576, "step": 2180000 }, { "epoch": 4.51, "learning_rate": 9.962213414995336e-07, "loss": 3.2572, "step": 2180500 }, { "epoch": 4.51, "learning_rate": 9.955325594177862e-07, "loss": 3.2611, "step": 2181000 }, { "epoch": 4.51, "learning_rate": 9.948437773360388e-07, "loss": 3.2536, "step": 2181500 }, { "epoch": 4.51, "learning_rate": 9.941549952542914e-07, "loss": 3.2531, "step": 2182000 }, { "epoch": 4.51, "learning_rate": 9.93466213172544e-07, "loss": 3.2535, "step": 2182500 }, { "epoch": 4.51, "learning_rate": 9.927774310907967e-07, "loss": 3.2519, "step": 2183000 }, { "epoch": 4.51, "learning_rate": 9.920886490090493e-07, "loss": 3.2482, "step": 2183500 }, { "epoch": 4.51, "learning_rate": 9.913998669273017e-07, "loss": 3.254, "step": 2184000 }, { "epoch": 4.51, "learning_rate": 9.907110848455543e-07, "loss": 3.2527, "step": 2184500 }, { "epoch": 4.51, "learning_rate": 9.90022302763807e-07, "loss": 3.251, "step": 2185000 }, { "epoch": 4.52, "learning_rate": 9.893335206820596e-07, "loss": 3.2522, "step": 2185500 }, { "epoch": 4.52, "learning_rate": 9.88644738600312e-07, "loss": 3.2527, "step": 2186000 }, { "epoch": 4.52, "learning_rate": 9.879559565185646e-07, "loss": 3.2552, "step": 2186500 }, { "epoch": 4.52, "learning_rate": 9.872671744368172e-07, "loss": 3.2587, "step": 2187000 }, { "epoch": 4.52, "learning_rate": 9.865783923550698e-07, "loss": 3.2507, "step": 2187500 }, { "epoch": 4.52, "learning_rate": 9.858896102733225e-07, "loss": 3.2503, "step": 2188000 }, { "epoch": 4.52, "learning_rate": 9.85200828191575e-07, "loss": 3.2505, "step": 2188500 }, { "epoch": 4.52, "learning_rate": 9.845120461098277e-07, "loss": 3.2584, "step": 2189000 }, { "epoch": 4.52, "learning_rate": 9.838232640280803e-07, "loss": 3.2503, "step": 2189500 }, { "epoch": 4.53, "learning_rate": 9.83134481946333e-07, "loss": 3.2441, "step": 2190000 }, { "epoch": 4.53, "learning_rate": 9.824456998645854e-07, "loss": 3.2527, "step": 2190500 }, { "epoch": 4.53, "learning_rate": 9.81756917782838e-07, "loss": 3.2513, "step": 2191000 }, { "epoch": 4.53, "learning_rate": 9.810681357010906e-07, "loss": 3.2516, "step": 2191500 }, { "epoch": 4.53, "learning_rate": 9.803793536193432e-07, "loss": 3.2466, "step": 2192000 }, { "epoch": 4.53, "learning_rate": 9.796905715375956e-07, "loss": 3.2497, "step": 2192500 }, { "epoch": 4.53, "learning_rate": 9.790017894558482e-07, "loss": 3.25, "step": 2193000 }, { "epoch": 4.53, "learning_rate": 9.783130073741009e-07, "loss": 3.2538, "step": 2193500 }, { "epoch": 4.53, "learning_rate": 9.776242252923535e-07, "loss": 3.2534, "step": 2194000 }, { "epoch": 4.53, "learning_rate": 9.769354432106061e-07, "loss": 3.2489, "step": 2194500 }, { "epoch": 4.54, "learning_rate": 9.762466611288587e-07, "loss": 3.2508, "step": 2195000 }, { "epoch": 4.54, "learning_rate": 9.755578790471114e-07, "loss": 3.2528, "step": 2195500 }, { "epoch": 4.54, "learning_rate": 9.74869096965364e-07, "loss": 3.25, "step": 2196000 }, { "epoch": 4.54, "learning_rate": 9.741803148836164e-07, "loss": 3.2516, "step": 2196500 }, { "epoch": 4.54, "learning_rate": 9.73491532801869e-07, "loss": 3.2517, "step": 2197000 }, { "epoch": 4.54, "learning_rate": 9.728027507201216e-07, "loss": 3.2432, "step": 2197500 }, { "epoch": 4.54, "learning_rate": 9.721139686383743e-07, "loss": 3.2501, "step": 2198000 }, { "epoch": 4.54, "learning_rate": 9.714251865566267e-07, "loss": 3.249, "step": 2198500 }, { "epoch": 4.54, "learning_rate": 9.707364044748793e-07, "loss": 3.2552, "step": 2199000 }, { "epoch": 4.54, "learning_rate": 9.70047622393132e-07, "loss": 3.2479, "step": 2199500 }, { "epoch": 4.55, "learning_rate": 9.693588403113845e-07, "loss": 3.2511, "step": 2200000 }, { "epoch": 4.55, "learning_rate": 9.686700582296371e-07, "loss": 3.2583, "step": 2200500 }, { "epoch": 4.55, "learning_rate": 9.679812761478898e-07, "loss": 3.2524, "step": 2201000 }, { "epoch": 4.55, "learning_rate": 9.672924940661424e-07, "loss": 3.2497, "step": 2201500 }, { "epoch": 4.55, "learning_rate": 9.66603711984395e-07, "loss": 3.2522, "step": 2202000 }, { "epoch": 4.55, "learning_rate": 9.659149299026474e-07, "loss": 3.255, "step": 2202500 }, { "epoch": 4.55, "learning_rate": 9.652261478209e-07, "loss": 3.2528, "step": 2203000 }, { "epoch": 4.55, "learning_rate": 9.645373657391527e-07, "loss": 3.2529, "step": 2203500 }, { "epoch": 4.55, "learning_rate": 9.638485836574053e-07, "loss": 3.2475, "step": 2204000 }, { "epoch": 4.56, "learning_rate": 9.631598015756577e-07, "loss": 3.2531, "step": 2204500 }, { "epoch": 4.56, "learning_rate": 9.624710194939103e-07, "loss": 3.2475, "step": 2205000 }, { "epoch": 4.56, "learning_rate": 9.61782237412163e-07, "loss": 3.2501, "step": 2205500 }, { "epoch": 4.56, "learning_rate": 9.610934553304156e-07, "loss": 3.244, "step": 2206000 }, { "epoch": 4.56, "learning_rate": 9.604046732486682e-07, "loss": 3.246, "step": 2206500 }, { "epoch": 4.56, "learning_rate": 9.597158911669208e-07, "loss": 3.2549, "step": 2207000 }, { "epoch": 4.56, "learning_rate": 9.590271090851734e-07, "loss": 3.2485, "step": 2207500 }, { "epoch": 4.56, "learning_rate": 9.58338327003426e-07, "loss": 3.2476, "step": 2208000 }, { "epoch": 4.56, "learning_rate": 9.576495449216787e-07, "loss": 3.2465, "step": 2208500 }, { "epoch": 4.56, "learning_rate": 9.56960762839931e-07, "loss": 3.2431, "step": 2209000 }, { "epoch": 4.57, "learning_rate": 9.562719807581837e-07, "loss": 3.2538, "step": 2209500 }, { "epoch": 4.57, "learning_rate": 9.555831986764363e-07, "loss": 3.255, "step": 2210000 }, { "epoch": 4.57, "learning_rate": 9.54894416594689e-07, "loss": 3.2557, "step": 2210500 }, { "epoch": 4.57, "learning_rate": 9.542056345129414e-07, "loss": 3.2486, "step": 2211000 }, { "epoch": 4.57, "learning_rate": 9.535168524311941e-07, "loss": 3.2478, "step": 2211500 }, { "epoch": 4.57, "learning_rate": 9.528280703494467e-07, "loss": 3.2429, "step": 2212000 }, { "epoch": 4.57, "learning_rate": 9.521392882676993e-07, "loss": 3.2499, "step": 2212500 }, { "epoch": 4.57, "learning_rate": 9.514505061859518e-07, "loss": 3.2509, "step": 2213000 }, { "epoch": 4.57, "learning_rate": 9.507617241042045e-07, "loss": 3.2519, "step": 2213500 }, { "epoch": 4.57, "learning_rate": 9.50072942022457e-07, "loss": 3.2483, "step": 2214000 }, { "epoch": 4.58, "learning_rate": 9.493841599407096e-07, "loss": 3.2534, "step": 2214500 }, { "epoch": 4.58, "learning_rate": 9.486953778589621e-07, "loss": 3.2467, "step": 2215000 }, { "epoch": 4.58, "learning_rate": 9.480065957772147e-07, "loss": 3.2549, "step": 2215500 }, { "epoch": 4.58, "learning_rate": 9.473178136954674e-07, "loss": 3.2473, "step": 2216000 }, { "epoch": 4.58, "learning_rate": 9.4662903161372e-07, "loss": 3.2476, "step": 2216500 }, { "epoch": 4.58, "learning_rate": 9.459402495319725e-07, "loss": 3.2442, "step": 2217000 }, { "epoch": 4.58, "learning_rate": 9.452514674502251e-07, "loss": 3.2534, "step": 2217500 }, { "epoch": 4.58, "learning_rate": 9.445626853684777e-07, "loss": 3.2549, "step": 2218000 }, { "epoch": 4.58, "learning_rate": 9.438739032867304e-07, "loss": 3.2559, "step": 2218500 }, { "epoch": 4.59, "learning_rate": 9.431851212049829e-07, "loss": 3.2521, "step": 2219000 }, { "epoch": 4.59, "learning_rate": 9.424963391232355e-07, "loss": 3.2499, "step": 2219500 }, { "epoch": 4.59, "learning_rate": 9.418075570414881e-07, "loss": 3.2469, "step": 2220000 }, { "epoch": 4.59, "learning_rate": 9.411187749597406e-07, "loss": 3.25, "step": 2220500 }, { "epoch": 4.59, "learning_rate": 9.404299928779931e-07, "loss": 3.2511, "step": 2221000 }, { "epoch": 4.59, "learning_rate": 9.397412107962458e-07, "loss": 3.2503, "step": 2221500 }, { "epoch": 4.59, "learning_rate": 9.390524287144984e-07, "loss": 3.2496, "step": 2222000 }, { "epoch": 4.59, "learning_rate": 9.38363646632751e-07, "loss": 3.2447, "step": 2222500 }, { "epoch": 4.59, "learning_rate": 9.376748645510035e-07, "loss": 3.2553, "step": 2223000 }, { "epoch": 4.59, "learning_rate": 9.369860824692561e-07, "loss": 3.2539, "step": 2223500 }, { "epoch": 4.6, "learning_rate": 9.362973003875088e-07, "loss": 3.2556, "step": 2224000 }, { "epoch": 4.6, "learning_rate": 9.356085183057614e-07, "loss": 3.2543, "step": 2224500 }, { "epoch": 4.6, "learning_rate": 9.349197362240139e-07, "loss": 3.2527, "step": 2225000 }, { "epoch": 4.6, "learning_rate": 9.342309541422665e-07, "loss": 3.2464, "step": 2225500 }, { "epoch": 4.6, "learning_rate": 9.335421720605192e-07, "loss": 3.2479, "step": 2226000 }, { "epoch": 4.6, "learning_rate": 9.328533899787718e-07, "loss": 3.2509, "step": 2226500 }, { "epoch": 4.6, "learning_rate": 9.321646078970243e-07, "loss": 3.2529, "step": 2227000 }, { "epoch": 4.6, "learning_rate": 9.314758258152768e-07, "loss": 3.2548, "step": 2227500 }, { "epoch": 4.6, "learning_rate": 9.307870437335294e-07, "loss": 3.2456, "step": 2228000 }, { "epoch": 4.6, "learning_rate": 9.30098261651782e-07, "loss": 3.247, "step": 2228500 }, { "epoch": 4.61, "learning_rate": 9.294094795700347e-07, "loss": 3.2524, "step": 2229000 }, { "epoch": 4.61, "learning_rate": 9.287206974882872e-07, "loss": 3.2535, "step": 2229500 }, { "epoch": 4.61, "learning_rate": 9.280319154065398e-07, "loss": 3.2479, "step": 2230000 }, { "epoch": 4.61, "learning_rate": 9.273431333247924e-07, "loss": 3.2514, "step": 2230500 }, { "epoch": 4.61, "learning_rate": 9.26654351243045e-07, "loss": 3.257, "step": 2231000 }, { "epoch": 4.61, "learning_rate": 9.259655691612976e-07, "loss": 3.2514, "step": 2231500 }, { "epoch": 4.61, "learning_rate": 9.252767870795502e-07, "loss": 3.2435, "step": 2232000 }, { "epoch": 4.61, "learning_rate": 9.245880049978028e-07, "loss": 3.2488, "step": 2232500 }, { "epoch": 4.61, "learning_rate": 9.238992229160553e-07, "loss": 3.2516, "step": 2233000 }, { "epoch": 4.62, "learning_rate": 9.232104408343078e-07, "loss": 3.2501, "step": 2233500 }, { "epoch": 4.62, "learning_rate": 9.225216587525605e-07, "loss": 3.2542, "step": 2234000 }, { "epoch": 4.62, "learning_rate": 9.218328766708131e-07, "loss": 3.2513, "step": 2234500 }, { "epoch": 4.62, "learning_rate": 9.211440945890657e-07, "loss": 3.247, "step": 2235000 }, { "epoch": 4.62, "learning_rate": 9.204553125073182e-07, "loss": 3.2478, "step": 2235500 }, { "epoch": 4.62, "learning_rate": 9.197665304255708e-07, "loss": 3.2502, "step": 2236000 }, { "epoch": 4.62, "learning_rate": 9.190777483438235e-07, "loss": 3.2502, "step": 2236500 }, { "epoch": 4.62, "learning_rate": 9.183889662620761e-07, "loss": 3.2508, "step": 2237000 }, { "epoch": 4.62, "learning_rate": 9.177001841803286e-07, "loss": 3.2475, "step": 2237500 }, { "epoch": 4.62, "learning_rate": 9.170114020985812e-07, "loss": 3.2527, "step": 2238000 }, { "epoch": 4.63, "learning_rate": 9.163226200168338e-07, "loss": 3.2495, "step": 2238500 }, { "epoch": 4.63, "learning_rate": 9.156338379350865e-07, "loss": 3.2403, "step": 2239000 }, { "epoch": 4.63, "learning_rate": 9.149450558533389e-07, "loss": 3.2482, "step": 2239500 }, { "epoch": 4.63, "learning_rate": 9.142562737715915e-07, "loss": 3.2441, "step": 2240000 }, { "epoch": 4.63, "learning_rate": 9.135674916898441e-07, "loss": 3.2495, "step": 2240500 }, { "epoch": 4.63, "learning_rate": 9.128787096080967e-07, "loss": 3.2437, "step": 2241000 }, { "epoch": 4.63, "learning_rate": 9.121899275263493e-07, "loss": 3.2513, "step": 2241500 }, { "epoch": 4.63, "learning_rate": 9.115011454446019e-07, "loss": 3.2521, "step": 2242000 }, { "epoch": 4.63, "learning_rate": 9.108123633628545e-07, "loss": 3.2471, "step": 2242500 }, { "epoch": 4.63, "learning_rate": 9.101235812811071e-07, "loss": 3.2545, "step": 2243000 }, { "epoch": 4.64, "learning_rate": 9.094347991993596e-07, "loss": 3.2521, "step": 2243500 }, { "epoch": 4.64, "learning_rate": 9.087460171176123e-07, "loss": 3.2479, "step": 2244000 }, { "epoch": 4.64, "learning_rate": 9.080572350358649e-07, "loss": 3.2519, "step": 2244500 }, { "epoch": 4.64, "learning_rate": 9.073684529541175e-07, "loss": 3.2472, "step": 2245000 }, { "epoch": 4.64, "learning_rate": 9.066796708723699e-07, "loss": 3.251, "step": 2245500 }, { "epoch": 4.64, "learning_rate": 9.059908887906225e-07, "loss": 3.2394, "step": 2246000 }, { "epoch": 4.64, "learning_rate": 9.053021067088752e-07, "loss": 3.2469, "step": 2246500 }, { "epoch": 4.64, "learning_rate": 9.046133246271278e-07, "loss": 3.249, "step": 2247000 }, { "epoch": 4.64, "learning_rate": 9.039245425453804e-07, "loss": 3.2551, "step": 2247500 }, { "epoch": 4.65, "learning_rate": 9.032357604636329e-07, "loss": 3.2463, "step": 2248000 }, { "epoch": 4.65, "learning_rate": 9.025469783818855e-07, "loss": 3.2467, "step": 2248500 }, { "epoch": 4.65, "learning_rate": 9.018581963001382e-07, "loss": 3.2508, "step": 2249000 }, { "epoch": 4.65, "learning_rate": 9.011694142183908e-07, "loss": 3.2489, "step": 2249500 }, { "epoch": 4.65, "learning_rate": 9.004806321366433e-07, "loss": 3.2484, "step": 2250000 }, { "epoch": 4.65, "learning_rate": 8.997918500548959e-07, "loss": 3.2459, "step": 2250500 }, { "epoch": 4.65, "learning_rate": 8.991030679731485e-07, "loss": 3.2453, "step": 2251000 }, { "epoch": 4.65, "learning_rate": 8.984142858914012e-07, "loss": 3.2523, "step": 2251500 }, { "epoch": 4.65, "learning_rate": 8.977255038096536e-07, "loss": 3.2481, "step": 2252000 }, { "epoch": 4.65, "learning_rate": 8.970367217279062e-07, "loss": 3.2496, "step": 2252500 }, { "epoch": 4.66, "learning_rate": 8.963479396461588e-07, "loss": 3.254, "step": 2253000 }, { "epoch": 4.66, "learning_rate": 8.956591575644114e-07, "loss": 3.2483, "step": 2253500 }, { "epoch": 4.66, "learning_rate": 8.94970375482664e-07, "loss": 3.2524, "step": 2254000 }, { "epoch": 4.66, "learning_rate": 8.942815934009166e-07, "loss": 3.249, "step": 2254500 }, { "epoch": 4.66, "learning_rate": 8.935928113191692e-07, "loss": 3.2464, "step": 2255000 }, { "epoch": 4.66, "learning_rate": 8.929040292374218e-07, "loss": 3.2563, "step": 2255500 }, { "epoch": 4.66, "learning_rate": 8.922152471556743e-07, "loss": 3.2497, "step": 2256000 }, { "epoch": 4.66, "learning_rate": 8.91526465073927e-07, "loss": 3.2473, "step": 2256500 }, { "epoch": 4.66, "learning_rate": 8.908376829921796e-07, "loss": 3.2477, "step": 2257000 }, { "epoch": 4.66, "learning_rate": 8.901489009104322e-07, "loss": 3.2463, "step": 2257500 }, { "epoch": 4.67, "learning_rate": 8.894601188286847e-07, "loss": 3.2514, "step": 2258000 }, { "epoch": 4.67, "learning_rate": 8.887713367469372e-07, "loss": 3.2497, "step": 2258500 }, { "epoch": 4.67, "learning_rate": 8.880825546651898e-07, "loss": 3.2483, "step": 2259000 }, { "epoch": 4.67, "learning_rate": 8.873937725834425e-07, "loss": 3.2486, "step": 2259500 }, { "epoch": 4.67, "learning_rate": 8.86704990501695e-07, "loss": 3.2434, "step": 2260000 }, { "epoch": 4.67, "learning_rate": 8.860162084199476e-07, "loss": 3.2506, "step": 2260500 }, { "epoch": 4.67, "learning_rate": 8.853274263382002e-07, "loss": 3.254, "step": 2261000 }, { "epoch": 4.67, "learning_rate": 8.846386442564528e-07, "loss": 3.2497, "step": 2261500 }, { "epoch": 4.67, "learning_rate": 8.839498621747054e-07, "loss": 3.2487, "step": 2262000 }, { "epoch": 4.68, "learning_rate": 8.83261080092958e-07, "loss": 3.2496, "step": 2262500 }, { "epoch": 4.68, "learning_rate": 8.825722980112106e-07, "loss": 3.2444, "step": 2263000 }, { "epoch": 4.68, "learning_rate": 8.818835159294632e-07, "loss": 3.2483, "step": 2263500 }, { "epoch": 4.68, "learning_rate": 8.811947338477157e-07, "loss": 3.2514, "step": 2264000 }, { "epoch": 4.68, "learning_rate": 8.805059517659684e-07, "loss": 3.2434, "step": 2264500 }, { "epoch": 4.68, "learning_rate": 8.798171696842209e-07, "loss": 3.2529, "step": 2265000 }, { "epoch": 4.68, "learning_rate": 8.791283876024735e-07, "loss": 3.2482, "step": 2265500 }, { "epoch": 4.68, "learning_rate": 8.784396055207261e-07, "loss": 3.2524, "step": 2266000 }, { "epoch": 4.68, "learning_rate": 8.777508234389786e-07, "loss": 3.2521, "step": 2266500 }, { "epoch": 4.68, "learning_rate": 8.770620413572313e-07, "loss": 3.243, "step": 2267000 }, { "epoch": 4.69, "learning_rate": 8.763732592754839e-07, "loss": 3.2467, "step": 2267500 }, { "epoch": 4.69, "learning_rate": 8.756844771937365e-07, "loss": 3.2499, "step": 2268000 }, { "epoch": 4.69, "learning_rate": 8.74995695111989e-07, "loss": 3.2523, "step": 2268500 }, { "epoch": 4.69, "learning_rate": 8.743069130302416e-07, "loss": 3.2462, "step": 2269000 }, { "epoch": 4.69, "learning_rate": 8.736181309484943e-07, "loss": 3.2456, "step": 2269500 }, { "epoch": 4.69, "learning_rate": 8.729293488667469e-07, "loss": 3.2427, "step": 2270000 }, { "epoch": 4.69, "learning_rate": 8.722405667849994e-07, "loss": 3.242, "step": 2270500 }, { "epoch": 4.69, "learning_rate": 8.71551784703252e-07, "loss": 3.2472, "step": 2271000 }, { "epoch": 4.69, "learning_rate": 8.708630026215045e-07, "loss": 3.2497, "step": 2271500 }, { "epoch": 4.69, "learning_rate": 8.701742205397572e-07, "loss": 3.2504, "step": 2272000 }, { "epoch": 4.7, "learning_rate": 8.694854384580097e-07, "loss": 3.2498, "step": 2272500 }, { "epoch": 4.7, "learning_rate": 8.687966563762623e-07, "loss": 3.2449, "step": 2273000 }, { "epoch": 4.7, "learning_rate": 8.681078742945149e-07, "loss": 3.2481, "step": 2273500 }, { "epoch": 4.7, "learning_rate": 8.674190922127675e-07, "loss": 3.2473, "step": 2274000 }, { "epoch": 4.7, "learning_rate": 8.667303101310201e-07, "loss": 3.2559, "step": 2274500 }, { "epoch": 4.7, "learning_rate": 8.660415280492727e-07, "loss": 3.2516, "step": 2275000 }, { "epoch": 4.7, "learning_rate": 8.653527459675253e-07, "loss": 3.2493, "step": 2275500 }, { "epoch": 4.7, "learning_rate": 8.646639638857779e-07, "loss": 3.2449, "step": 2276000 }, { "epoch": 4.7, "learning_rate": 8.639751818040304e-07, "loss": 3.244, "step": 2276500 }, { "epoch": 4.71, "learning_rate": 8.632863997222831e-07, "loss": 3.2484, "step": 2277000 }, { "epoch": 4.71, "learning_rate": 8.625976176405356e-07, "loss": 3.2518, "step": 2277500 }, { "epoch": 4.71, "learning_rate": 8.619088355587882e-07, "loss": 3.2472, "step": 2278000 }, { "epoch": 4.71, "learning_rate": 8.612200534770407e-07, "loss": 3.2485, "step": 2278500 }, { "epoch": 4.71, "learning_rate": 8.605312713952933e-07, "loss": 3.2512, "step": 2279000 }, { "epoch": 4.71, "learning_rate": 8.59842489313546e-07, "loss": 3.2467, "step": 2279500 }, { "epoch": 4.71, "learning_rate": 8.591537072317986e-07, "loss": 3.2433, "step": 2280000 }, { "epoch": 4.71, "learning_rate": 8.584649251500511e-07, "loss": 3.251, "step": 2280500 }, { "epoch": 4.71, "learning_rate": 8.577761430683037e-07, "loss": 3.2494, "step": 2281000 }, { "epoch": 4.71, "learning_rate": 8.570873609865563e-07, "loss": 3.2427, "step": 2281500 }, { "epoch": 4.72, "learning_rate": 8.56398578904809e-07, "loss": 3.2416, "step": 2282000 }, { "epoch": 4.72, "learning_rate": 8.557097968230615e-07, "loss": 3.2554, "step": 2282500 }, { "epoch": 4.72, "learning_rate": 8.550210147413141e-07, "loss": 3.2535, "step": 2283000 }, { "epoch": 4.72, "learning_rate": 8.543322326595667e-07, "loss": 3.2442, "step": 2283500 }, { "epoch": 4.72, "learning_rate": 8.536434505778192e-07, "loss": 3.245, "step": 2284000 }, { "epoch": 4.72, "learning_rate": 8.529546684960717e-07, "loss": 3.2429, "step": 2284500 }, { "epoch": 4.72, "learning_rate": 8.522658864143244e-07, "loss": 3.2497, "step": 2285000 }, { "epoch": 4.72, "learning_rate": 8.51577104332577e-07, "loss": 3.2514, "step": 2285500 }, { "epoch": 4.72, "learning_rate": 8.508883222508296e-07, "loss": 3.2508, "step": 2286000 }, { "epoch": 4.72, "learning_rate": 8.501995401690822e-07, "loss": 3.2457, "step": 2286500 }, { "epoch": 4.73, "learning_rate": 8.495107580873347e-07, "loss": 3.244, "step": 2287000 }, { "epoch": 4.73, "learning_rate": 8.488219760055874e-07, "loss": 3.2461, "step": 2287500 }, { "epoch": 4.73, "learning_rate": 8.4813319392384e-07, "loss": 3.2441, "step": 2288000 }, { "epoch": 4.73, "learning_rate": 8.474444118420926e-07, "loss": 3.249, "step": 2288500 }, { "epoch": 4.73, "learning_rate": 8.467556297603451e-07, "loss": 3.2515, "step": 2289000 }, { "epoch": 4.73, "learning_rate": 8.460668476785977e-07, "loss": 3.2494, "step": 2289500 }, { "epoch": 4.73, "learning_rate": 8.453780655968504e-07, "loss": 3.2448, "step": 2290000 }, { "epoch": 4.73, "learning_rate": 8.446892835151029e-07, "loss": 3.2487, "step": 2290500 }, { "epoch": 4.73, "learning_rate": 8.440005014333554e-07, "loss": 3.2444, "step": 2291000 }, { "epoch": 4.74, "learning_rate": 8.43311719351608e-07, "loss": 3.242, "step": 2291500 }, { "epoch": 4.74, "learning_rate": 8.426229372698606e-07, "loss": 3.2417, "step": 2292000 }, { "epoch": 4.74, "learning_rate": 8.419341551881133e-07, "loss": 3.2484, "step": 2292500 }, { "epoch": 4.74, "learning_rate": 8.412453731063658e-07, "loss": 3.2499, "step": 2293000 }, { "epoch": 4.74, "learning_rate": 8.405565910246184e-07, "loss": 3.2433, "step": 2293500 }, { "epoch": 4.74, "learning_rate": 8.39867808942871e-07, "loss": 3.2446, "step": 2294000 }, { "epoch": 4.74, "learning_rate": 8.391790268611236e-07, "loss": 3.2421, "step": 2294500 }, { "epoch": 4.74, "learning_rate": 8.384902447793762e-07, "loss": 3.247, "step": 2295000 }, { "epoch": 4.74, "learning_rate": 8.378014626976288e-07, "loss": 3.2419, "step": 2295500 }, { "epoch": 4.74, "learning_rate": 8.371126806158814e-07, "loss": 3.2468, "step": 2296000 }, { "epoch": 4.75, "learning_rate": 8.36423898534134e-07, "loss": 3.2483, "step": 2296500 }, { "epoch": 4.75, "learning_rate": 8.357351164523864e-07, "loss": 3.243, "step": 2297000 }, { "epoch": 4.75, "learning_rate": 8.350463343706391e-07, "loss": 3.2438, "step": 2297500 }, { "epoch": 4.75, "learning_rate": 8.343575522888917e-07, "loss": 3.2463, "step": 2298000 }, { "epoch": 4.75, "learning_rate": 8.336687702071443e-07, "loss": 3.25, "step": 2298500 }, { "epoch": 4.75, "learning_rate": 8.329799881253968e-07, "loss": 3.2378, "step": 2299000 }, { "epoch": 4.75, "learning_rate": 8.322912060436494e-07, "loss": 3.2411, "step": 2299500 }, { "epoch": 4.75, "learning_rate": 8.316024239619021e-07, "loss": 3.2479, "step": 2300000 }, { "epoch": 4.75, "learning_rate": 8.309136418801547e-07, "loss": 3.2502, "step": 2300500 }, { "epoch": 4.75, "learning_rate": 8.302248597984072e-07, "loss": 3.2478, "step": 2301000 }, { "epoch": 4.76, "learning_rate": 8.295360777166598e-07, "loss": 3.2464, "step": 2301500 }, { "epoch": 4.76, "learning_rate": 8.288472956349124e-07, "loss": 3.2467, "step": 2302000 }, { "epoch": 4.76, "learning_rate": 8.281585135531651e-07, "loss": 3.2413, "step": 2302500 }, { "epoch": 4.76, "learning_rate": 8.274697314714175e-07, "loss": 3.2493, "step": 2303000 }, { "epoch": 4.76, "learning_rate": 8.267809493896701e-07, "loss": 3.2462, "step": 2303500 }, { "epoch": 4.76, "learning_rate": 8.260921673079227e-07, "loss": 3.2422, "step": 2304000 }, { "epoch": 4.76, "learning_rate": 8.254033852261753e-07, "loss": 3.246, "step": 2304500 }, { "epoch": 4.76, "learning_rate": 8.247146031444279e-07, "loss": 3.2483, "step": 2305000 }, { "epoch": 4.76, "learning_rate": 8.240258210626805e-07, "loss": 3.246, "step": 2305500 }, { "epoch": 4.76, "learning_rate": 8.233370389809331e-07, "loss": 3.2436, "step": 2306000 }, { "epoch": 4.77, "learning_rate": 8.226482568991857e-07, "loss": 3.2428, "step": 2306500 }, { "epoch": 4.77, "learning_rate": 8.219594748174383e-07, "loss": 3.2463, "step": 2307000 }, { "epoch": 4.77, "learning_rate": 8.212706927356909e-07, "loss": 3.2417, "step": 2307500 }, { "epoch": 4.77, "learning_rate": 8.205819106539435e-07, "loss": 3.2403, "step": 2308000 }, { "epoch": 4.77, "learning_rate": 8.198931285721961e-07, "loss": 3.249, "step": 2308500 }, { "epoch": 4.77, "learning_rate": 8.192043464904487e-07, "loss": 3.2444, "step": 2309000 }, { "epoch": 4.77, "learning_rate": 8.185155644087011e-07, "loss": 3.246, "step": 2309500 }, { "epoch": 4.77, "learning_rate": 8.178267823269537e-07, "loss": 3.2451, "step": 2310000 }, { "epoch": 4.77, "learning_rate": 8.171380002452064e-07, "loss": 3.2399, "step": 2310500 }, { "epoch": 4.78, "learning_rate": 8.16449218163459e-07, "loss": 3.2435, "step": 2311000 }, { "epoch": 4.78, "learning_rate": 8.157604360817115e-07, "loss": 3.2391, "step": 2311500 }, { "epoch": 4.78, "learning_rate": 8.150716539999641e-07, "loss": 3.2447, "step": 2312000 }, { "epoch": 4.78, "learning_rate": 8.143828719182168e-07, "loss": 3.242, "step": 2312500 }, { "epoch": 4.78, "learning_rate": 8.136940898364694e-07, "loss": 3.2466, "step": 2313000 }, { "epoch": 4.78, "learning_rate": 8.130053077547219e-07, "loss": 3.2459, "step": 2313500 }, { "epoch": 4.78, "learning_rate": 8.123165256729745e-07, "loss": 3.2532, "step": 2314000 }, { "epoch": 4.78, "learning_rate": 8.116277435912271e-07, "loss": 3.2523, "step": 2314500 }, { "epoch": 4.78, "learning_rate": 8.109389615094798e-07, "loss": 3.2452, "step": 2315000 }, { "epoch": 4.78, "learning_rate": 8.102501794277323e-07, "loss": 3.2471, "step": 2315500 }, { "epoch": 4.79, "learning_rate": 8.095613973459848e-07, "loss": 3.2414, "step": 2316000 }, { "epoch": 4.79, "learning_rate": 8.088726152642374e-07, "loss": 3.2413, "step": 2316500 }, { "epoch": 4.79, "learning_rate": 8.0818383318249e-07, "loss": 3.2413, "step": 2317000 }, { "epoch": 4.79, "learning_rate": 8.074950511007425e-07, "loss": 3.246, "step": 2317500 }, { "epoch": 4.79, "learning_rate": 8.068062690189952e-07, "loss": 3.2508, "step": 2318000 }, { "epoch": 4.79, "learning_rate": 8.061174869372478e-07, "loss": 3.2475, "step": 2318500 }, { "epoch": 4.79, "learning_rate": 8.054287048555004e-07, "loss": 3.2419, "step": 2319000 }, { "epoch": 4.79, "learning_rate": 8.047399227737529e-07, "loss": 3.247, "step": 2319500 }, { "epoch": 4.79, "learning_rate": 8.040511406920055e-07, "loss": 3.2472, "step": 2320000 }, { "epoch": 4.79, "learning_rate": 8.033623586102582e-07, "loss": 3.242, "step": 2320500 }, { "epoch": 4.8, "learning_rate": 8.026735765285108e-07, "loss": 3.2452, "step": 2321000 }, { "epoch": 4.8, "learning_rate": 8.019847944467633e-07, "loss": 3.2492, "step": 2321500 }, { "epoch": 4.8, "learning_rate": 8.012960123650158e-07, "loss": 3.2421, "step": 2322000 }, { "epoch": 4.8, "learning_rate": 8.006072302832684e-07, "loss": 3.2451, "step": 2322500 }, { "epoch": 4.8, "learning_rate": 7.999184482015211e-07, "loss": 3.2508, "step": 2323000 }, { "epoch": 4.8, "learning_rate": 7.992296661197736e-07, "loss": 3.2466, "step": 2323500 }, { "epoch": 4.8, "learning_rate": 7.985408840380262e-07, "loss": 3.2509, "step": 2324000 }, { "epoch": 4.8, "learning_rate": 7.978521019562788e-07, "loss": 3.2496, "step": 2324500 }, { "epoch": 4.8, "learning_rate": 7.971633198745314e-07, "loss": 3.2449, "step": 2325000 }, { "epoch": 4.81, "learning_rate": 7.964745377927841e-07, "loss": 3.2507, "step": 2325500 }, { "epoch": 4.81, "learning_rate": 7.957857557110366e-07, "loss": 3.2457, "step": 2326000 }, { "epoch": 4.81, "learning_rate": 7.950969736292892e-07, "loss": 3.2422, "step": 2326500 }, { "epoch": 4.81, "learning_rate": 7.944081915475418e-07, "loss": 3.2415, "step": 2327000 }, { "epoch": 4.81, "learning_rate": 7.937194094657944e-07, "loss": 3.244, "step": 2327500 }, { "epoch": 4.81, "learning_rate": 7.93030627384047e-07, "loss": 3.2477, "step": 2328000 }, { "epoch": 4.81, "learning_rate": 7.923418453022995e-07, "loss": 3.2485, "step": 2328500 }, { "epoch": 4.81, "learning_rate": 7.916530632205521e-07, "loss": 3.2381, "step": 2329000 }, { "epoch": 4.81, "learning_rate": 7.909642811388047e-07, "loss": 3.2373, "step": 2329500 }, { "epoch": 4.81, "learning_rate": 7.902754990570572e-07, "loss": 3.2432, "step": 2330000 }, { "epoch": 4.82, "learning_rate": 7.895867169753099e-07, "loss": 3.2494, "step": 2330500 }, { "epoch": 4.82, "learning_rate": 7.888979348935625e-07, "loss": 3.2396, "step": 2331000 }, { "epoch": 4.82, "learning_rate": 7.882091528118151e-07, "loss": 3.2501, "step": 2331500 }, { "epoch": 4.82, "learning_rate": 7.875203707300676e-07, "loss": 3.2467, "step": 2332000 }, { "epoch": 4.82, "learning_rate": 7.868315886483202e-07, "loss": 3.2469, "step": 2332500 }, { "epoch": 4.82, "learning_rate": 7.861428065665729e-07, "loss": 3.2454, "step": 2333000 }, { "epoch": 4.82, "learning_rate": 7.854540244848255e-07, "loss": 3.2367, "step": 2333500 }, { "epoch": 4.82, "learning_rate": 7.84765242403078e-07, "loss": 3.2486, "step": 2334000 }, { "epoch": 4.82, "learning_rate": 7.840764603213306e-07, "loss": 3.2416, "step": 2334500 }, { "epoch": 4.82, "learning_rate": 7.833876782395831e-07, "loss": 3.2506, "step": 2335000 }, { "epoch": 4.83, "learning_rate": 7.826988961578358e-07, "loss": 3.2468, "step": 2335500 }, { "epoch": 4.83, "learning_rate": 7.820101140760883e-07, "loss": 3.2454, "step": 2336000 }, { "epoch": 4.83, "learning_rate": 7.813213319943409e-07, "loss": 3.248, "step": 2336500 }, { "epoch": 4.83, "learning_rate": 7.806325499125935e-07, "loss": 3.2457, "step": 2337000 }, { "epoch": 4.83, "learning_rate": 7.799437678308461e-07, "loss": 3.2437, "step": 2337500 }, { "epoch": 4.83, "learning_rate": 7.792549857490987e-07, "loss": 3.243, "step": 2338000 }, { "epoch": 4.83, "learning_rate": 7.785662036673513e-07, "loss": 3.2418, "step": 2338500 }, { "epoch": 4.83, "learning_rate": 7.778774215856039e-07, "loss": 3.2461, "step": 2339000 }, { "epoch": 4.83, "learning_rate": 7.771886395038565e-07, "loss": 3.2458, "step": 2339500 }, { "epoch": 4.84, "learning_rate": 7.76499857422109e-07, "loss": 3.2455, "step": 2340000 }, { "epoch": 4.84, "learning_rate": 7.758110753403617e-07, "loss": 3.2438, "step": 2340500 }, { "epoch": 4.84, "learning_rate": 7.751222932586143e-07, "loss": 3.2404, "step": 2341000 }, { "epoch": 4.84, "learning_rate": 7.744335111768668e-07, "loss": 3.2379, "step": 2341500 }, { "epoch": 4.84, "learning_rate": 7.737447290951193e-07, "loss": 3.2435, "step": 2342000 }, { "epoch": 4.84, "learning_rate": 7.730559470133719e-07, "loss": 3.2458, "step": 2342500 }, { "epoch": 4.84, "learning_rate": 7.723671649316245e-07, "loss": 3.2408, "step": 2343000 }, { "epoch": 4.84, "learning_rate": 7.716783828498772e-07, "loss": 3.2432, "step": 2343500 }, { "epoch": 4.84, "learning_rate": 7.709896007681297e-07, "loss": 3.2431, "step": 2344000 }, { "epoch": 4.84, "learning_rate": 7.703008186863823e-07, "loss": 3.2466, "step": 2344500 }, { "epoch": 4.85, "learning_rate": 7.696120366046349e-07, "loss": 3.2459, "step": 2345000 }, { "epoch": 4.85, "learning_rate": 7.689232545228876e-07, "loss": 3.2381, "step": 2345500 }, { "epoch": 4.85, "learning_rate": 7.682344724411402e-07, "loss": 3.2431, "step": 2346000 }, { "epoch": 4.85, "learning_rate": 7.675456903593927e-07, "loss": 3.246, "step": 2346500 }, { "epoch": 4.85, "learning_rate": 7.668569082776453e-07, "loss": 3.2408, "step": 2347000 }, { "epoch": 4.85, "learning_rate": 7.661681261958979e-07, "loss": 3.2481, "step": 2347500 }, { "epoch": 4.85, "learning_rate": 7.654793441141504e-07, "loss": 3.2423, "step": 2348000 }, { "epoch": 4.85, "learning_rate": 7.64790562032403e-07, "loss": 3.2396, "step": 2348500 }, { "epoch": 4.85, "learning_rate": 7.641017799506556e-07, "loss": 3.2475, "step": 2349000 }, { "epoch": 4.85, "learning_rate": 7.634129978689082e-07, "loss": 3.2502, "step": 2349500 }, { "epoch": 4.86, "learning_rate": 7.627242157871608e-07, "loss": 3.2441, "step": 2350000 }, { "epoch": 4.86, "learning_rate": 7.620354337054133e-07, "loss": 3.2383, "step": 2350500 }, { "epoch": 4.86, "learning_rate": 7.61346651623666e-07, "loss": 3.249, "step": 2351000 }, { "epoch": 4.86, "learning_rate": 7.606578695419186e-07, "loss": 3.2484, "step": 2351500 }, { "epoch": 4.86, "learning_rate": 7.599690874601712e-07, "loss": 3.2436, "step": 2352000 }, { "epoch": 4.86, "learning_rate": 7.592803053784237e-07, "loss": 3.2499, "step": 2352500 }, { "epoch": 4.86, "learning_rate": 7.585915232966763e-07, "loss": 3.2487, "step": 2353000 }, { "epoch": 4.86, "learning_rate": 7.57902741214929e-07, "loss": 3.2505, "step": 2353500 }, { "epoch": 4.86, "learning_rate": 7.572139591331815e-07, "loss": 3.2369, "step": 2354000 }, { "epoch": 4.87, "learning_rate": 7.56525177051434e-07, "loss": 3.2484, "step": 2354500 }, { "epoch": 4.87, "learning_rate": 7.558363949696866e-07, "loss": 3.2397, "step": 2355000 }, { "epoch": 4.87, "learning_rate": 7.551476128879392e-07, "loss": 3.2449, "step": 2355500 }, { "epoch": 4.87, "learning_rate": 7.544588308061919e-07, "loss": 3.2402, "step": 2356000 }, { "epoch": 4.87, "learning_rate": 7.537700487244444e-07, "loss": 3.2396, "step": 2356500 }, { "epoch": 4.87, "learning_rate": 7.53081266642697e-07, "loss": 3.2386, "step": 2357000 }, { "epoch": 4.87, "learning_rate": 7.523924845609496e-07, "loss": 3.2371, "step": 2357500 }, { "epoch": 4.87, "learning_rate": 7.517037024792022e-07, "loss": 3.2486, "step": 2358000 }, { "epoch": 4.87, "learning_rate": 7.510149203974548e-07, "loss": 3.2457, "step": 2358500 }, { "epoch": 4.87, "learning_rate": 7.503261383157074e-07, "loss": 3.2431, "step": 2359000 }, { "epoch": 4.88, "learning_rate": 7.4963735623396e-07, "loss": 3.2407, "step": 2359500 }, { "epoch": 4.88, "learning_rate": 7.489485741522126e-07, "loss": 3.2444, "step": 2360000 }, { "epoch": 4.88, "learning_rate": 7.48259792070465e-07, "loss": 3.2405, "step": 2360500 }, { "epoch": 4.88, "learning_rate": 7.475710099887177e-07, "loss": 3.2422, "step": 2361000 }, { "epoch": 4.88, "learning_rate": 7.468822279069703e-07, "loss": 3.24, "step": 2361500 }, { "epoch": 4.88, "learning_rate": 7.461934458252229e-07, "loss": 3.2411, "step": 2362000 }, { "epoch": 4.88, "learning_rate": 7.455046637434754e-07, "loss": 3.2415, "step": 2362500 }, { "epoch": 4.88, "learning_rate": 7.44815881661728e-07, "loss": 3.2423, "step": 2363000 }, { "epoch": 4.88, "learning_rate": 7.441270995799807e-07, "loss": 3.2377, "step": 2363500 }, { "epoch": 4.88, "learning_rate": 7.434383174982333e-07, "loss": 3.2412, "step": 2364000 }, { "epoch": 4.89, "learning_rate": 7.427495354164858e-07, "loss": 3.2499, "step": 2364500 }, { "epoch": 4.89, "learning_rate": 7.420607533347384e-07, "loss": 3.2436, "step": 2365000 }, { "epoch": 4.89, "learning_rate": 7.41371971252991e-07, "loss": 3.2438, "step": 2365500 }, { "epoch": 4.89, "learning_rate": 7.406831891712437e-07, "loss": 3.2445, "step": 2366000 }, { "epoch": 4.89, "learning_rate": 7.399944070894963e-07, "loss": 3.2447, "step": 2366500 }, { "epoch": 4.89, "learning_rate": 7.393056250077487e-07, "loss": 3.2469, "step": 2367000 }, { "epoch": 4.89, "learning_rate": 7.386168429260013e-07, "loss": 3.2478, "step": 2367500 }, { "epoch": 4.89, "learning_rate": 7.379280608442539e-07, "loss": 3.2416, "step": 2368000 }, { "epoch": 4.89, "learning_rate": 7.372392787625066e-07, "loss": 3.2498, "step": 2368500 }, { "epoch": 4.9, "learning_rate": 7.365504966807591e-07, "loss": 3.2443, "step": 2369000 }, { "epoch": 4.9, "learning_rate": 7.358617145990117e-07, "loss": 3.2466, "step": 2369500 }, { "epoch": 4.9, "learning_rate": 7.351729325172643e-07, "loss": 3.2449, "step": 2370000 }, { "epoch": 4.9, "learning_rate": 7.344841504355169e-07, "loss": 3.2474, "step": 2370500 }, { "epoch": 4.9, "learning_rate": 7.337953683537695e-07, "loss": 3.2397, "step": 2371000 }, { "epoch": 4.9, "learning_rate": 7.331065862720221e-07, "loss": 3.241, "step": 2371500 }, { "epoch": 4.9, "learning_rate": 7.324178041902747e-07, "loss": 3.2438, "step": 2372000 }, { "epoch": 4.9, "learning_rate": 7.317290221085273e-07, "loss": 3.2385, "step": 2372500 }, { "epoch": 4.9, "learning_rate": 7.310402400267797e-07, "loss": 3.2428, "step": 2373000 }, { "epoch": 4.9, "learning_rate": 7.303514579450323e-07, "loss": 3.2402, "step": 2373500 }, { "epoch": 4.91, "learning_rate": 7.29662675863285e-07, "loss": 3.2484, "step": 2374000 }, { "epoch": 4.91, "learning_rate": 7.289738937815376e-07, "loss": 3.2382, "step": 2374500 }, { "epoch": 4.91, "learning_rate": 7.282851116997901e-07, "loss": 3.2468, "step": 2375000 }, { "epoch": 4.91, "learning_rate": 7.275963296180427e-07, "loss": 3.2405, "step": 2375500 }, { "epoch": 4.91, "learning_rate": 7.269075475362953e-07, "loss": 3.2341, "step": 2376000 }, { "epoch": 4.91, "learning_rate": 7.26218765454548e-07, "loss": 3.2471, "step": 2376500 }, { "epoch": 4.91, "learning_rate": 7.255299833728005e-07, "loss": 3.2439, "step": 2377000 }, { "epoch": 4.91, "learning_rate": 7.248412012910531e-07, "loss": 3.2502, "step": 2377500 }, { "epoch": 4.91, "learning_rate": 7.241524192093057e-07, "loss": 3.2455, "step": 2378000 }, { "epoch": 4.91, "learning_rate": 7.234636371275584e-07, "loss": 3.2409, "step": 2378500 }, { "epoch": 4.92, "learning_rate": 7.227748550458109e-07, "loss": 3.2374, "step": 2379000 }, { "epoch": 4.92, "learning_rate": 7.220860729640634e-07, "loss": 3.2426, "step": 2379500 }, { "epoch": 4.92, "learning_rate": 7.21397290882316e-07, "loss": 3.2461, "step": 2380000 }, { "epoch": 4.92, "learning_rate": 7.207085088005686e-07, "loss": 3.2447, "step": 2380500 }, { "epoch": 4.92, "learning_rate": 7.200197267188211e-07, "loss": 3.2396, "step": 2381000 }, { "epoch": 4.92, "learning_rate": 7.193309446370738e-07, "loss": 3.2409, "step": 2381500 }, { "epoch": 4.92, "learning_rate": 7.186421625553264e-07, "loss": 3.2379, "step": 2382000 }, { "epoch": 4.92, "learning_rate": 7.17953380473579e-07, "loss": 3.2399, "step": 2382500 }, { "epoch": 4.92, "learning_rate": 7.172645983918315e-07, "loss": 3.2493, "step": 2383000 }, { "epoch": 4.93, "learning_rate": 7.165758163100841e-07, "loss": 3.2419, "step": 2383500 }, { "epoch": 4.93, "learning_rate": 7.158870342283368e-07, "loss": 3.2508, "step": 2384000 }, { "epoch": 4.93, "learning_rate": 7.151982521465894e-07, "loss": 3.2414, "step": 2384500 }, { "epoch": 4.93, "learning_rate": 7.14509470064842e-07, "loss": 3.2387, "step": 2385000 }, { "epoch": 4.93, "learning_rate": 7.138206879830945e-07, "loss": 3.2454, "step": 2385500 }, { "epoch": 4.93, "learning_rate": 7.13131905901347e-07, "loss": 3.2425, "step": 2386000 }, { "epoch": 4.93, "learning_rate": 7.124431238195997e-07, "loss": 3.2534, "step": 2386500 }, { "epoch": 4.93, "learning_rate": 7.117543417378523e-07, "loss": 3.2397, "step": 2387000 }, { "epoch": 4.93, "learning_rate": 7.110655596561048e-07, "loss": 3.2398, "step": 2387500 }, { "epoch": 4.93, "learning_rate": 7.103767775743574e-07, "loss": 3.2437, "step": 2388000 }, { "epoch": 4.94, "learning_rate": 7.0968799549261e-07, "loss": 3.2402, "step": 2388500 }, { "epoch": 4.94, "learning_rate": 7.089992134108627e-07, "loss": 3.2419, "step": 2389000 }, { "epoch": 4.94, "learning_rate": 7.083104313291152e-07, "loss": 3.2449, "step": 2389500 }, { "epoch": 4.94, "learning_rate": 7.076216492473678e-07, "loss": 3.2473, "step": 2390000 }, { "epoch": 4.94, "learning_rate": 7.069328671656204e-07, "loss": 3.2429, "step": 2390500 }, { "epoch": 4.94, "learning_rate": 7.06244085083873e-07, "loss": 3.2444, "step": 2391000 }, { "epoch": 4.94, "learning_rate": 7.055553030021256e-07, "loss": 3.2468, "step": 2391500 }, { "epoch": 4.94, "learning_rate": 7.048665209203782e-07, "loss": 3.2376, "step": 2392000 }, { "epoch": 4.94, "learning_rate": 7.041777388386307e-07, "loss": 3.2382, "step": 2392500 }, { "epoch": 4.94, "learning_rate": 7.034889567568833e-07, "loss": 3.2471, "step": 2393000 }, { "epoch": 4.95, "learning_rate": 7.028001746751358e-07, "loss": 3.241, "step": 2393500 }, { "epoch": 4.95, "learning_rate": 7.021113925933885e-07, "loss": 3.2426, "step": 2394000 }, { "epoch": 4.95, "learning_rate": 7.014226105116411e-07, "loss": 3.2406, "step": 2394500 }, { "epoch": 4.95, "learning_rate": 7.007338284298937e-07, "loss": 3.2358, "step": 2395000 }, { "epoch": 4.95, "learning_rate": 7.000450463481462e-07, "loss": 3.2453, "step": 2395500 }, { "epoch": 4.95, "learning_rate": 6.993562642663988e-07, "loss": 3.2381, "step": 2396000 }, { "epoch": 4.95, "learning_rate": 6.986674821846515e-07, "loss": 3.2394, "step": 2396500 }, { "epoch": 4.95, "learning_rate": 6.979787001029041e-07, "loss": 3.243, "step": 2397000 }, { "epoch": 4.95, "learning_rate": 6.972899180211566e-07, "loss": 3.247, "step": 2397500 }, { "epoch": 4.96, "learning_rate": 6.966011359394092e-07, "loss": 3.2396, "step": 2398000 }, { "epoch": 4.96, "learning_rate": 6.959123538576617e-07, "loss": 3.2425, "step": 2398500 }, { "epoch": 4.96, "learning_rate": 6.952235717759144e-07, "loss": 3.2467, "step": 2399000 }, { "epoch": 4.96, "learning_rate": 6.945347896941669e-07, "loss": 3.2472, "step": 2399500 }, { "epoch": 4.96, "learning_rate": 6.938460076124195e-07, "loss": 3.2411, "step": 2400000 }, { "epoch": 4.96, "learning_rate": 6.931572255306721e-07, "loss": 3.2416, "step": 2400500 }, { "epoch": 4.96, "learning_rate": 6.924684434489247e-07, "loss": 3.2409, "step": 2401000 }, { "epoch": 4.96, "learning_rate": 6.917796613671772e-07, "loss": 3.2393, "step": 2401500 }, { "epoch": 4.96, "learning_rate": 6.910908792854299e-07, "loss": 3.2393, "step": 2402000 }, { "epoch": 4.96, "learning_rate": 6.904020972036825e-07, "loss": 3.2462, "step": 2402500 }, { "epoch": 4.97, "learning_rate": 6.897133151219351e-07, "loss": 3.2358, "step": 2403000 }, { "epoch": 4.97, "learning_rate": 6.890245330401876e-07, "loss": 3.2377, "step": 2403500 }, { "epoch": 4.97, "learning_rate": 6.883357509584402e-07, "loss": 3.2418, "step": 2404000 }, { "epoch": 4.97, "learning_rate": 6.876469688766929e-07, "loss": 3.2446, "step": 2404500 }, { "epoch": 4.97, "learning_rate": 6.869581867949454e-07, "loss": 3.2408, "step": 2405000 }, { "epoch": 4.97, "learning_rate": 6.86269404713198e-07, "loss": 3.2418, "step": 2405500 }, { "epoch": 4.97, "learning_rate": 6.855806226314505e-07, "loss": 3.2322, "step": 2406000 }, { "epoch": 4.97, "learning_rate": 6.848918405497031e-07, "loss": 3.2396, "step": 2406500 }, { "epoch": 4.97, "learning_rate": 6.842030584679558e-07, "loss": 3.2443, "step": 2407000 }, { "epoch": 4.97, "learning_rate": 6.835142763862084e-07, "loss": 3.2415, "step": 2407500 }, { "epoch": 4.98, "learning_rate": 6.828254943044609e-07, "loss": 3.2458, "step": 2408000 }, { "epoch": 4.98, "learning_rate": 6.821367122227135e-07, "loss": 3.237, "step": 2408500 }, { "epoch": 4.98, "learning_rate": 6.814479301409661e-07, "loss": 3.2386, "step": 2409000 }, { "epoch": 4.98, "learning_rate": 6.807591480592188e-07, "loss": 3.2412, "step": 2409500 }, { "epoch": 4.98, "learning_rate": 6.800703659774713e-07, "loss": 3.2369, "step": 2410000 }, { "epoch": 4.98, "learning_rate": 6.793815838957239e-07, "loss": 3.2465, "step": 2410500 }, { "epoch": 4.98, "learning_rate": 6.786928018139765e-07, "loss": 3.2463, "step": 2411000 }, { "epoch": 4.98, "learning_rate": 6.78004019732229e-07, "loss": 3.2409, "step": 2411500 }, { "epoch": 4.98, "learning_rate": 6.773152376504816e-07, "loss": 3.2416, "step": 2412000 }, { "epoch": 4.99, "learning_rate": 6.766264555687342e-07, "loss": 3.2392, "step": 2412500 }, { "epoch": 4.99, "learning_rate": 6.759376734869868e-07, "loss": 3.2426, "step": 2413000 }, { "epoch": 4.99, "learning_rate": 6.752488914052394e-07, "loss": 3.2403, "step": 2413500 }, { "epoch": 4.99, "learning_rate": 6.745601093234919e-07, "loss": 3.2361, "step": 2414000 }, { "epoch": 4.99, "learning_rate": 6.738713272417446e-07, "loss": 3.2363, "step": 2414500 }, { "epoch": 4.99, "learning_rate": 6.731825451599972e-07, "loss": 3.2369, "step": 2415000 }, { "epoch": 4.99, "learning_rate": 6.724937630782498e-07, "loss": 3.2386, "step": 2415500 }, { "epoch": 4.99, "learning_rate": 6.718049809965023e-07, "loss": 3.2411, "step": 2416000 }, { "epoch": 4.99, "learning_rate": 6.711161989147549e-07, "loss": 3.2354, "step": 2416500 }, { "epoch": 4.99, "learning_rate": 6.704274168330076e-07, "loss": 3.2367, "step": 2417000 }, { "epoch": 5.0, "learning_rate": 6.697386347512602e-07, "loss": 3.2325, "step": 2417500 }, { "epoch": 5.0, "learning_rate": 6.690498526695126e-07, "loss": 3.2436, "step": 2418000 }, { "epoch": 5.0, "learning_rate": 6.683610705877652e-07, "loss": 3.2415, "step": 2418500 }, { "epoch": 5.0, "learning_rate": 6.676722885060178e-07, "loss": 3.2336, "step": 2419000 }, { "epoch": 5.0, "learning_rate": 6.669835064242705e-07, "loss": 3.2452, "step": 2419500 }, { "epoch": 5.0, "eval_loss": 3.2417044639587402, "eval_runtime": 23108.1645, "eval_samples_per_second": 148.925, "eval_steps_per_second": 2.327, "step": 2419730 }, { "epoch": 5.0, "learning_rate": 6.66294724342523e-07, "loss": 3.2284, "step": 2420000 }, { "epoch": 5.0, "learning_rate": 6.656059422607756e-07, "loss": 3.2326, "step": 2420500 }, { "epoch": 5.0, "learning_rate": 6.649171601790282e-07, "loss": 3.2284, "step": 2421000 }, { "epoch": 5.0, "learning_rate": 6.642283780972808e-07, "loss": 3.2286, "step": 2421500 }, { "epoch": 5.0, "learning_rate": 6.635395960155334e-07, "loss": 3.2281, "step": 2422000 }, { "epoch": 5.01, "learning_rate": 6.62850813933786e-07, "loss": 3.2301, "step": 2422500 }, { "epoch": 5.01, "learning_rate": 6.621620318520386e-07, "loss": 3.2342, "step": 2423000 }, { "epoch": 5.01, "learning_rate": 6.614732497702912e-07, "loss": 3.2259, "step": 2423500 }, { "epoch": 5.01, "learning_rate": 6.607844676885436e-07, "loss": 3.2265, "step": 2424000 }, { "epoch": 5.01, "learning_rate": 6.600956856067963e-07, "loss": 3.2296, "step": 2424500 }, { "epoch": 5.01, "learning_rate": 6.594069035250489e-07, "loss": 3.2298, "step": 2425000 }, { "epoch": 5.01, "learning_rate": 6.587181214433015e-07, "loss": 3.2315, "step": 2425500 }, { "epoch": 5.01, "learning_rate": 6.580293393615541e-07, "loss": 3.2349, "step": 2426000 }, { "epoch": 5.01, "learning_rate": 6.573405572798066e-07, "loss": 3.2296, "step": 2426500 }, { "epoch": 5.02, "learning_rate": 6.566517751980593e-07, "loss": 3.2325, "step": 2427000 }, { "epoch": 5.02, "learning_rate": 6.559629931163119e-07, "loss": 3.2315, "step": 2427500 }, { "epoch": 5.02, "learning_rate": 6.552742110345645e-07, "loss": 3.2321, "step": 2428000 }, { "epoch": 5.02, "learning_rate": 6.54585428952817e-07, "loss": 3.2257, "step": 2428500 }, { "epoch": 5.02, "learning_rate": 6.538966468710696e-07, "loss": 3.23, "step": 2429000 }, { "epoch": 5.02, "learning_rate": 6.532078647893223e-07, "loss": 3.2307, "step": 2429500 }, { "epoch": 5.02, "learning_rate": 6.525190827075749e-07, "loss": 3.2285, "step": 2430000 }, { "epoch": 5.02, "learning_rate": 6.518303006258273e-07, "loss": 3.2275, "step": 2430500 }, { "epoch": 5.02, "learning_rate": 6.511415185440799e-07, "loss": 3.2278, "step": 2431000 }, { "epoch": 5.02, "learning_rate": 6.504527364623325e-07, "loss": 3.2298, "step": 2431500 }, { "epoch": 5.03, "learning_rate": 6.497639543805852e-07, "loss": 3.2317, "step": 2432000 }, { "epoch": 5.03, "learning_rate": 6.490751722988377e-07, "loss": 3.2309, "step": 2432500 }, { "epoch": 5.03, "learning_rate": 6.483863902170903e-07, "loss": 3.2277, "step": 2433000 }, { "epoch": 5.03, "learning_rate": 6.476976081353429e-07, "loss": 3.2267, "step": 2433500 }, { "epoch": 5.03, "learning_rate": 6.470088260535955e-07, "loss": 3.2271, "step": 2434000 }, { "epoch": 5.03, "learning_rate": 6.46320043971848e-07, "loss": 3.2274, "step": 2434500 }, { "epoch": 5.03, "learning_rate": 6.456312618901007e-07, "loss": 3.2254, "step": 2435000 }, { "epoch": 5.03, "learning_rate": 6.449424798083533e-07, "loss": 3.2224, "step": 2435500 }, { "epoch": 5.03, "learning_rate": 6.442536977266059e-07, "loss": 3.2287, "step": 2436000 }, { "epoch": 5.03, "learning_rate": 6.435649156448584e-07, "loss": 3.2304, "step": 2436500 }, { "epoch": 5.04, "learning_rate": 6.428761335631109e-07, "loss": 3.2311, "step": 2437000 }, { "epoch": 5.04, "learning_rate": 6.421873514813636e-07, "loss": 3.2279, "step": 2437500 }, { "epoch": 5.04, "learning_rate": 6.414985693996162e-07, "loss": 3.2267, "step": 2438000 }, { "epoch": 5.04, "learning_rate": 6.408097873178687e-07, "loss": 3.2382, "step": 2438500 }, { "epoch": 5.04, "learning_rate": 6.401210052361213e-07, "loss": 3.226, "step": 2439000 }, { "epoch": 5.04, "learning_rate": 6.394322231543739e-07, "loss": 3.2276, "step": 2439500 }, { "epoch": 5.04, "learning_rate": 6.387434410726266e-07, "loss": 3.2321, "step": 2440000 }, { "epoch": 5.04, "learning_rate": 6.380546589908791e-07, "loss": 3.2312, "step": 2440500 }, { "epoch": 5.04, "learning_rate": 6.373658769091317e-07, "loss": 3.2215, "step": 2441000 }, { "epoch": 5.04, "learning_rate": 6.366770948273843e-07, "loss": 3.2303, "step": 2441500 }, { "epoch": 5.05, "learning_rate": 6.359883127456369e-07, "loss": 3.231, "step": 2442000 }, { "epoch": 5.05, "learning_rate": 6.352995306638895e-07, "loss": 3.2287, "step": 2442500 }, { "epoch": 5.05, "learning_rate": 6.34610748582142e-07, "loss": 3.2292, "step": 2443000 }, { "epoch": 5.05, "learning_rate": 6.339219665003946e-07, "loss": 3.2298, "step": 2443500 }, { "epoch": 5.05, "learning_rate": 6.332331844186472e-07, "loss": 3.2298, "step": 2444000 }, { "epoch": 5.05, "learning_rate": 6.325444023368997e-07, "loss": 3.2282, "step": 2444500 }, { "epoch": 5.05, "learning_rate": 6.318556202551524e-07, "loss": 3.235, "step": 2445000 }, { "epoch": 5.05, "learning_rate": 6.31166838173405e-07, "loss": 3.2291, "step": 2445500 }, { "epoch": 5.05, "learning_rate": 6.304780560916576e-07, "loss": 3.2327, "step": 2446000 }, { "epoch": 5.06, "learning_rate": 6.297892740099102e-07, "loss": 3.2313, "step": 2446500 }, { "epoch": 5.06, "learning_rate": 6.291004919281627e-07, "loss": 3.2317, "step": 2447000 }, { "epoch": 5.06, "learning_rate": 6.284117098464154e-07, "loss": 3.2283, "step": 2447500 }, { "epoch": 5.06, "learning_rate": 6.27722927764668e-07, "loss": 3.2274, "step": 2448000 }, { "epoch": 5.06, "learning_rate": 6.270341456829206e-07, "loss": 3.2273, "step": 2448500 }, { "epoch": 5.06, "learning_rate": 6.263453636011731e-07, "loss": 3.2302, "step": 2449000 }, { "epoch": 5.06, "learning_rate": 6.256565815194256e-07, "loss": 3.2261, "step": 2449500 }, { "epoch": 5.06, "learning_rate": 6.249677994376783e-07, "loss": 3.226, "step": 2450000 }, { "epoch": 5.06, "learning_rate": 6.242790173559309e-07, "loss": 3.2275, "step": 2450500 }, { "epoch": 5.06, "learning_rate": 6.235902352741834e-07, "loss": 3.2372, "step": 2451000 }, { "epoch": 5.07, "learning_rate": 6.22901453192436e-07, "loss": 3.2325, "step": 2451500 }, { "epoch": 5.07, "learning_rate": 6.222126711106886e-07, "loss": 3.229, "step": 2452000 }, { "epoch": 5.07, "learning_rate": 6.215238890289413e-07, "loss": 3.2267, "step": 2452500 }, { "epoch": 5.07, "learning_rate": 6.208351069471938e-07, "loss": 3.2282, "step": 2453000 }, { "epoch": 5.07, "learning_rate": 6.201463248654464e-07, "loss": 3.2308, "step": 2453500 }, { "epoch": 5.07, "learning_rate": 6.19457542783699e-07, "loss": 3.2278, "step": 2454000 }, { "epoch": 5.07, "learning_rate": 6.187687607019516e-07, "loss": 3.2318, "step": 2454500 }, { "epoch": 5.07, "learning_rate": 6.180799786202042e-07, "loss": 3.2278, "step": 2455000 }, { "epoch": 5.07, "learning_rate": 6.173911965384568e-07, "loss": 3.2253, "step": 2455500 }, { "epoch": 5.07, "learning_rate": 6.167024144567093e-07, "loss": 3.2334, "step": 2456000 }, { "epoch": 5.08, "learning_rate": 6.160136323749619e-07, "loss": 3.2268, "step": 2456500 }, { "epoch": 5.08, "learning_rate": 6.153248502932144e-07, "loss": 3.2277, "step": 2457000 }, { "epoch": 5.08, "learning_rate": 6.14636068211467e-07, "loss": 3.2325, "step": 2457500 }, { "epoch": 5.08, "learning_rate": 6.139472861297197e-07, "loss": 3.224, "step": 2458000 }, { "epoch": 5.08, "learning_rate": 6.132585040479723e-07, "loss": 3.2296, "step": 2458500 }, { "epoch": 5.08, "learning_rate": 6.125697219662248e-07, "loss": 3.2311, "step": 2459000 }, { "epoch": 5.08, "learning_rate": 6.118809398844774e-07, "loss": 3.2277, "step": 2459500 }, { "epoch": 5.08, "learning_rate": 6.1119215780273e-07, "loss": 3.2268, "step": 2460000 }, { "epoch": 5.08, "learning_rate": 6.105033757209827e-07, "loss": 3.2239, "step": 2460500 }, { "epoch": 5.09, "learning_rate": 6.098145936392352e-07, "loss": 3.2258, "step": 2461000 }, { "epoch": 5.09, "learning_rate": 6.091258115574878e-07, "loss": 3.2296, "step": 2461500 }, { "epoch": 5.09, "learning_rate": 6.084370294757404e-07, "loss": 3.2284, "step": 2462000 }, { "epoch": 5.09, "learning_rate": 6.07748247393993e-07, "loss": 3.225, "step": 2462500 }, { "epoch": 5.09, "learning_rate": 6.070594653122455e-07, "loss": 3.2336, "step": 2463000 }, { "epoch": 5.09, "learning_rate": 6.063706832304981e-07, "loss": 3.2292, "step": 2463500 }, { "epoch": 5.09, "learning_rate": 6.056819011487507e-07, "loss": 3.2268, "step": 2464000 }, { "epoch": 5.09, "learning_rate": 6.049931190670033e-07, "loss": 3.2294, "step": 2464500 }, { "epoch": 5.09, "learning_rate": 6.04304336985256e-07, "loss": 3.2236, "step": 2465000 }, { "epoch": 5.09, "learning_rate": 6.036155549035085e-07, "loss": 3.2317, "step": 2465500 }, { "epoch": 5.1, "learning_rate": 6.029267728217611e-07, "loss": 3.2315, "step": 2466000 }, { "epoch": 5.1, "learning_rate": 6.022379907400137e-07, "loss": 3.2277, "step": 2466500 }, { "epoch": 5.1, "learning_rate": 6.015492086582663e-07, "loss": 3.2248, "step": 2467000 }, { "epoch": 5.1, "learning_rate": 6.008604265765188e-07, "loss": 3.2264, "step": 2467500 }, { "epoch": 5.1, "learning_rate": 6.001716444947715e-07, "loss": 3.2317, "step": 2468000 }, { "epoch": 5.1, "learning_rate": 5.994828624130241e-07, "loss": 3.2345, "step": 2468500 }, { "epoch": 5.1, "learning_rate": 5.987940803312766e-07, "loss": 3.2272, "step": 2469000 }, { "epoch": 5.1, "learning_rate": 5.981052982495291e-07, "loss": 3.2256, "step": 2469500 }, { "epoch": 5.1, "learning_rate": 5.974165161677817e-07, "loss": 3.2254, "step": 2470000 }, { "epoch": 5.1, "learning_rate": 5.967277340860344e-07, "loss": 3.2233, "step": 2470500 }, { "epoch": 5.11, "learning_rate": 5.96038952004287e-07, "loss": 3.2325, "step": 2471000 }, { "epoch": 5.11, "learning_rate": 5.953501699225395e-07, "loss": 3.2334, "step": 2471500 }, { "epoch": 5.11, "learning_rate": 5.946613878407921e-07, "loss": 3.2296, "step": 2472000 }, { "epoch": 5.11, "learning_rate": 5.939726057590447e-07, "loss": 3.2326, "step": 2472500 }, { "epoch": 5.11, "learning_rate": 5.932838236772974e-07, "loss": 3.2314, "step": 2473000 }, { "epoch": 5.11, "learning_rate": 5.925950415955499e-07, "loss": 3.2302, "step": 2473500 }, { "epoch": 5.11, "learning_rate": 5.919062595138025e-07, "loss": 3.2195, "step": 2474000 }, { "epoch": 5.11, "learning_rate": 5.912174774320551e-07, "loss": 3.2224, "step": 2474500 }, { "epoch": 5.11, "learning_rate": 5.905286953503077e-07, "loss": 3.225, "step": 2475000 }, { "epoch": 5.12, "learning_rate": 5.898399132685602e-07, "loss": 3.2239, "step": 2475500 }, { "epoch": 5.12, "learning_rate": 5.891511311868128e-07, "loss": 3.2328, "step": 2476000 }, { "epoch": 5.12, "learning_rate": 5.884623491050654e-07, "loss": 3.2315, "step": 2476500 }, { "epoch": 5.12, "learning_rate": 5.87773567023318e-07, "loss": 3.2303, "step": 2477000 }, { "epoch": 5.12, "learning_rate": 5.870847849415705e-07, "loss": 3.2282, "step": 2477500 }, { "epoch": 5.12, "learning_rate": 5.863960028598232e-07, "loss": 3.2267, "step": 2478000 }, { "epoch": 5.12, "learning_rate": 5.857072207780758e-07, "loss": 3.226, "step": 2478500 }, { "epoch": 5.12, "learning_rate": 5.850184386963284e-07, "loss": 3.2361, "step": 2479000 }, { "epoch": 5.12, "learning_rate": 5.843296566145809e-07, "loss": 3.2273, "step": 2479500 }, { "epoch": 5.12, "learning_rate": 5.836408745328335e-07, "loss": 3.2285, "step": 2480000 }, { "epoch": 5.13, "learning_rate": 5.829520924510862e-07, "loss": 3.225, "step": 2480500 }, { "epoch": 5.13, "learning_rate": 5.822633103693388e-07, "loss": 3.2211, "step": 2481000 }, { "epoch": 5.13, "learning_rate": 5.815745282875912e-07, "loss": 3.2261, "step": 2481500 }, { "epoch": 5.13, "learning_rate": 5.808857462058438e-07, "loss": 3.2199, "step": 2482000 }, { "epoch": 5.13, "learning_rate": 5.801969641240964e-07, "loss": 3.232, "step": 2482500 }, { "epoch": 5.13, "learning_rate": 5.795081820423491e-07, "loss": 3.2278, "step": 2483000 }, { "epoch": 5.13, "learning_rate": 5.788193999606016e-07, "loss": 3.228, "step": 2483500 }, { "epoch": 5.13, "learning_rate": 5.781306178788542e-07, "loss": 3.2276, "step": 2484000 }, { "epoch": 5.13, "learning_rate": 5.774418357971068e-07, "loss": 3.2239, "step": 2484500 }, { "epoch": 5.13, "learning_rate": 5.767530537153594e-07, "loss": 3.2254, "step": 2485000 }, { "epoch": 5.14, "learning_rate": 5.760642716336121e-07, "loss": 3.2279, "step": 2485500 }, { "epoch": 5.14, "learning_rate": 5.753754895518646e-07, "loss": 3.2323, "step": 2486000 }, { "epoch": 5.14, "learning_rate": 5.746867074701172e-07, "loss": 3.2309, "step": 2486500 }, { "epoch": 5.14, "learning_rate": 5.739979253883698e-07, "loss": 3.2241, "step": 2487000 }, { "epoch": 5.14, "learning_rate": 5.733091433066224e-07, "loss": 3.2254, "step": 2487500 }, { "epoch": 5.14, "learning_rate": 5.726203612248748e-07, "loss": 3.229, "step": 2488000 }, { "epoch": 5.14, "learning_rate": 5.719315791431275e-07, "loss": 3.2337, "step": 2488500 }, { "epoch": 5.14, "learning_rate": 5.712427970613801e-07, "loss": 3.2266, "step": 2489000 }, { "epoch": 5.14, "learning_rate": 5.705540149796327e-07, "loss": 3.228, "step": 2489500 }, { "epoch": 5.15, "learning_rate": 5.698652328978852e-07, "loss": 3.2274, "step": 2490000 }, { "epoch": 5.15, "learning_rate": 5.691764508161378e-07, "loss": 3.2379, "step": 2490500 }, { "epoch": 5.15, "learning_rate": 5.684876687343905e-07, "loss": 3.2325, "step": 2491000 }, { "epoch": 5.15, "learning_rate": 5.677988866526431e-07, "loss": 3.2266, "step": 2491500 }, { "epoch": 5.15, "learning_rate": 5.671101045708956e-07, "loss": 3.224, "step": 2492000 }, { "epoch": 5.15, "learning_rate": 5.664213224891482e-07, "loss": 3.233, "step": 2492500 }, { "epoch": 5.15, "learning_rate": 5.657325404074009e-07, "loss": 3.2277, "step": 2493000 }, { "epoch": 5.15, "learning_rate": 5.650437583256535e-07, "loss": 3.2278, "step": 2493500 }, { "epoch": 5.15, "learning_rate": 5.643549762439059e-07, "loss": 3.2281, "step": 2494000 }, { "epoch": 5.15, "learning_rate": 5.636661941621585e-07, "loss": 3.2309, "step": 2494500 }, { "epoch": 5.16, "learning_rate": 5.629774120804111e-07, "loss": 3.2318, "step": 2495000 }, { "epoch": 5.16, "learning_rate": 5.622886299986637e-07, "loss": 3.2282, "step": 2495500 }, { "epoch": 5.16, "learning_rate": 5.615998479169163e-07, "loss": 3.2295, "step": 2496000 }, { "epoch": 5.16, "learning_rate": 5.609110658351689e-07, "loss": 3.2194, "step": 2496500 }, { "epoch": 5.16, "learning_rate": 5.602222837534215e-07, "loss": 3.2315, "step": 2497000 }, { "epoch": 5.16, "learning_rate": 5.595335016716741e-07, "loss": 3.2258, "step": 2497500 }, { "epoch": 5.16, "learning_rate": 5.588447195899266e-07, "loss": 3.2278, "step": 2498000 }, { "epoch": 5.16, "learning_rate": 5.581559375081793e-07, "loss": 3.2328, "step": 2498500 }, { "epoch": 5.16, "learning_rate": 5.574671554264319e-07, "loss": 3.233, "step": 2499000 }, { "epoch": 5.16, "learning_rate": 5.567783733446845e-07, "loss": 3.2261, "step": 2499500 }, { "epoch": 5.17, "learning_rate": 5.56089591262937e-07, "loss": 3.2338, "step": 2500000 }, { "epoch": 5.17, "learning_rate": 5.554008091811895e-07, "loss": 3.2259, "step": 2500500 }, { "epoch": 5.17, "learning_rate": 5.547120270994422e-07, "loss": 3.224, "step": 2501000 }, { "epoch": 5.17, "learning_rate": 5.540232450176948e-07, "loss": 3.2296, "step": 2501500 }, { "epoch": 5.17, "learning_rate": 5.533344629359473e-07, "loss": 3.2261, "step": 2502000 }, { "epoch": 5.17, "learning_rate": 5.526456808541999e-07, "loss": 3.2352, "step": 2502500 }, { "epoch": 5.17, "learning_rate": 5.519568987724525e-07, "loss": 3.2285, "step": 2503000 }, { "epoch": 5.17, "learning_rate": 5.512681166907052e-07, "loss": 3.2227, "step": 2503500 }, { "epoch": 5.17, "learning_rate": 5.505793346089577e-07, "loss": 3.2294, "step": 2504000 }, { "epoch": 5.18, "learning_rate": 5.498905525272103e-07, "loss": 3.2278, "step": 2504500 }, { "epoch": 5.18, "learning_rate": 5.492017704454629e-07, "loss": 3.2217, "step": 2505000 }, { "epoch": 5.18, "learning_rate": 5.485129883637155e-07, "loss": 3.2266, "step": 2505500 }, { "epoch": 5.18, "learning_rate": 5.478242062819682e-07, "loss": 3.2272, "step": 2506000 }, { "epoch": 5.18, "learning_rate": 5.471354242002207e-07, "loss": 3.2269, "step": 2506500 }, { "epoch": 5.18, "learning_rate": 5.464466421184732e-07, "loss": 3.2336, "step": 2507000 }, { "epoch": 5.18, "learning_rate": 5.457578600367258e-07, "loss": 3.229, "step": 2507500 }, { "epoch": 5.18, "learning_rate": 5.450690779549784e-07, "loss": 3.2231, "step": 2508000 }, { "epoch": 5.18, "learning_rate": 5.44380295873231e-07, "loss": 3.2264, "step": 2508500 }, { "epoch": 5.18, "learning_rate": 5.436915137914836e-07, "loss": 3.2229, "step": 2509000 }, { "epoch": 5.19, "learning_rate": 5.430027317097362e-07, "loss": 3.2302, "step": 2509500 }, { "epoch": 5.19, "learning_rate": 5.423139496279888e-07, "loss": 3.2254, "step": 2510000 }, { "epoch": 5.19, "learning_rate": 5.416251675462413e-07, "loss": 3.2281, "step": 2510500 }, { "epoch": 5.19, "learning_rate": 5.40936385464494e-07, "loss": 3.2237, "step": 2511000 }, { "epoch": 5.19, "learning_rate": 5.402476033827466e-07, "loss": 3.2344, "step": 2511500 }, { "epoch": 5.19, "learning_rate": 5.395588213009992e-07, "loss": 3.2275, "step": 2512000 }, { "epoch": 5.19, "learning_rate": 5.388700392192517e-07, "loss": 3.2297, "step": 2512500 }, { "epoch": 5.19, "learning_rate": 5.381812571375043e-07, "loss": 3.2252, "step": 2513000 }, { "epoch": 5.19, "learning_rate": 5.374924750557569e-07, "loss": 3.23, "step": 2513500 }, { "epoch": 5.19, "learning_rate": 5.368036929740095e-07, "loss": 3.2249, "step": 2514000 }, { "epoch": 5.2, "learning_rate": 5.36114910892262e-07, "loss": 3.2292, "step": 2514500 }, { "epoch": 5.2, "learning_rate": 5.354261288105146e-07, "loss": 3.2307, "step": 2515000 }, { "epoch": 5.2, "learning_rate": 5.347373467287672e-07, "loss": 3.2303, "step": 2515500 }, { "epoch": 5.2, "learning_rate": 5.340485646470199e-07, "loss": 3.2316, "step": 2516000 }, { "epoch": 5.2, "learning_rate": 5.333597825652724e-07, "loss": 3.2246, "step": 2516500 }, { "epoch": 5.2, "learning_rate": 5.32671000483525e-07, "loss": 3.2252, "step": 2517000 }, { "epoch": 5.2, "learning_rate": 5.319822184017776e-07, "loss": 3.2228, "step": 2517500 }, { "epoch": 5.2, "learning_rate": 5.312934363200302e-07, "loss": 3.2302, "step": 2518000 }, { "epoch": 5.2, "learning_rate": 5.306046542382828e-07, "loss": 3.2268, "step": 2518500 }, { "epoch": 5.21, "learning_rate": 5.299158721565354e-07, "loss": 3.2299, "step": 2519000 }, { "epoch": 5.21, "learning_rate": 5.29227090074788e-07, "loss": 3.2305, "step": 2519500 }, { "epoch": 5.21, "learning_rate": 5.285383079930405e-07, "loss": 3.2315, "step": 2520000 }, { "epoch": 5.21, "learning_rate": 5.27849525911293e-07, "loss": 3.2239, "step": 2520500 }, { "epoch": 5.21, "learning_rate": 5.271607438295456e-07, "loss": 3.2236, "step": 2521000 }, { "epoch": 5.21, "learning_rate": 5.264719617477983e-07, "loss": 3.2261, "step": 2521500 }, { "epoch": 5.21, "learning_rate": 5.257831796660509e-07, "loss": 3.2278, "step": 2522000 }, { "epoch": 5.21, "learning_rate": 5.250943975843034e-07, "loss": 3.2257, "step": 2522500 }, { "epoch": 5.21, "learning_rate": 5.24405615502556e-07, "loss": 3.2245, "step": 2523000 }, { "epoch": 5.21, "learning_rate": 5.237168334208086e-07, "loss": 3.2309, "step": 2523500 }, { "epoch": 5.22, "learning_rate": 5.230280513390613e-07, "loss": 3.221, "step": 2524000 }, { "epoch": 5.22, "learning_rate": 5.223392692573139e-07, "loss": 3.2251, "step": 2524500 }, { "epoch": 5.22, "learning_rate": 5.216504871755664e-07, "loss": 3.2276, "step": 2525000 }, { "epoch": 5.22, "learning_rate": 5.20961705093819e-07, "loss": 3.233, "step": 2525500 }, { "epoch": 5.22, "learning_rate": 5.202729230120715e-07, "loss": 3.2224, "step": 2526000 }, { "epoch": 5.22, "learning_rate": 5.195841409303242e-07, "loss": 3.23, "step": 2526500 }, { "epoch": 5.22, "learning_rate": 5.188953588485767e-07, "loss": 3.2299, "step": 2527000 }, { "epoch": 5.22, "learning_rate": 5.182065767668293e-07, "loss": 3.2248, "step": 2527500 }, { "epoch": 5.22, "learning_rate": 5.175177946850819e-07, "loss": 3.2221, "step": 2528000 }, { "epoch": 5.22, "learning_rate": 5.168290126033345e-07, "loss": 3.2304, "step": 2528500 }, { "epoch": 5.23, "learning_rate": 5.161402305215871e-07, "loss": 3.233, "step": 2529000 }, { "epoch": 5.23, "learning_rate": 5.154514484398397e-07, "loss": 3.2244, "step": 2529500 }, { "epoch": 5.23, "learning_rate": 5.147626663580923e-07, "loss": 3.2209, "step": 2530000 }, { "epoch": 5.23, "learning_rate": 5.140738842763449e-07, "loss": 3.2232, "step": 2530500 }, { "epoch": 5.23, "learning_rate": 5.133851021945974e-07, "loss": 3.2319, "step": 2531000 }, { "epoch": 5.23, "learning_rate": 5.126963201128501e-07, "loss": 3.2268, "step": 2531500 }, { "epoch": 5.23, "learning_rate": 5.120075380311027e-07, "loss": 3.2227, "step": 2532000 }, { "epoch": 5.23, "learning_rate": 5.113187559493552e-07, "loss": 3.2208, "step": 2532500 }, { "epoch": 5.23, "learning_rate": 5.106299738676077e-07, "loss": 3.2274, "step": 2533000 }, { "epoch": 5.24, "learning_rate": 5.099411917858603e-07, "loss": 3.2281, "step": 2533500 }, { "epoch": 5.24, "learning_rate": 5.09252409704113e-07, "loss": 3.2356, "step": 2534000 }, { "epoch": 5.24, "learning_rate": 5.085636276223656e-07, "loss": 3.2339, "step": 2534500 }, { "epoch": 5.24, "learning_rate": 5.078748455406181e-07, "loss": 3.2193, "step": 2535000 }, { "epoch": 5.24, "learning_rate": 5.071860634588707e-07, "loss": 3.2259, "step": 2535500 }, { "epoch": 5.24, "learning_rate": 5.064972813771233e-07, "loss": 3.2245, "step": 2536000 }, { "epoch": 5.24, "learning_rate": 5.05808499295376e-07, "loss": 3.2306, "step": 2536500 }, { "epoch": 5.24, "learning_rate": 5.051197172136285e-07, "loss": 3.2234, "step": 2537000 }, { "epoch": 5.24, "learning_rate": 5.044309351318811e-07, "loss": 3.2206, "step": 2537500 }, { "epoch": 5.24, "learning_rate": 5.037421530501337e-07, "loss": 3.2213, "step": 2538000 }, { "epoch": 5.25, "learning_rate": 5.030533709683863e-07, "loss": 3.2297, "step": 2538500 }, { "epoch": 5.25, "learning_rate": 5.023645888866388e-07, "loss": 3.2265, "step": 2539000 }, { "epoch": 5.25, "learning_rate": 5.016758068048914e-07, "loss": 3.23, "step": 2539500 }, { "epoch": 5.25, "learning_rate": 5.00987024723144e-07, "loss": 3.2286, "step": 2540000 }, { "epoch": 5.25, "learning_rate": 5.002982426413966e-07, "loss": 3.2269, "step": 2540500 }, { "epoch": 5.25, "learning_rate": 4.996094605596492e-07, "loss": 3.2249, "step": 2541000 }, { "epoch": 5.25, "learning_rate": 4.989206784779018e-07, "loss": 3.2231, "step": 2541500 }, { "epoch": 5.25, "learning_rate": 4.982318963961544e-07, "loss": 3.2235, "step": 2542000 }, { "epoch": 5.25, "learning_rate": 4.975431143144069e-07, "loss": 3.2253, "step": 2542500 }, { "epoch": 5.25, "learning_rate": 4.968543322326595e-07, "loss": 3.2312, "step": 2543000 }, { "epoch": 5.26, "learning_rate": 4.961655501509121e-07, "loss": 3.2264, "step": 2543500 }, { "epoch": 5.26, "learning_rate": 4.954767680691648e-07, "loss": 3.2257, "step": 2544000 }, { "epoch": 5.26, "learning_rate": 4.947879859874174e-07, "loss": 3.223, "step": 2544500 }, { "epoch": 5.26, "learning_rate": 4.940992039056699e-07, "loss": 3.2288, "step": 2545000 }, { "epoch": 5.26, "learning_rate": 4.934104218239225e-07, "loss": 3.2265, "step": 2545500 }, { "epoch": 5.26, "learning_rate": 4.92721639742175e-07, "loss": 3.2292, "step": 2546000 }, { "epoch": 5.26, "learning_rate": 4.920328576604277e-07, "loss": 3.2292, "step": 2546500 }, { "epoch": 5.26, "learning_rate": 4.913440755786803e-07, "loss": 3.2293, "step": 2547000 }, { "epoch": 5.26, "learning_rate": 4.906552934969329e-07, "loss": 3.2267, "step": 2547500 }, { "epoch": 5.27, "learning_rate": 4.899665114151854e-07, "loss": 3.2255, "step": 2548000 }, { "epoch": 5.27, "learning_rate": 4.89277729333438e-07, "loss": 3.2229, "step": 2548500 }, { "epoch": 5.27, "learning_rate": 4.885889472516905e-07, "loss": 3.2245, "step": 2549000 }, { "epoch": 5.27, "learning_rate": 4.879001651699432e-07, "loss": 3.2314, "step": 2549500 }, { "epoch": 5.27, "learning_rate": 4.872113830881958e-07, "loss": 3.2217, "step": 2550000 }, { "epoch": 5.27, "learning_rate": 4.865226010064484e-07, "loss": 3.2219, "step": 2550500 }, { "epoch": 5.27, "learning_rate": 4.858338189247009e-07, "loss": 3.2236, "step": 2551000 }, { "epoch": 5.27, "learning_rate": 4.851450368429535e-07, "loss": 3.2276, "step": 2551500 }, { "epoch": 5.27, "learning_rate": 4.844562547612061e-07, "loss": 3.2263, "step": 2552000 }, { "epoch": 5.27, "learning_rate": 4.837674726794587e-07, "loss": 3.2302, "step": 2552500 }, { "epoch": 5.28, "learning_rate": 4.830786905977113e-07, "loss": 3.2279, "step": 2553000 }, { "epoch": 5.28, "learning_rate": 4.823899085159639e-07, "loss": 3.2221, "step": 2553500 }, { "epoch": 5.28, "learning_rate": 4.817011264342164e-07, "loss": 3.2233, "step": 2554000 }, { "epoch": 5.28, "learning_rate": 4.810123443524691e-07, "loss": 3.2245, "step": 2554500 }, { "epoch": 5.28, "learning_rate": 4.803235622707216e-07, "loss": 3.227, "step": 2555000 }, { "epoch": 5.28, "learning_rate": 4.796347801889742e-07, "loss": 3.2284, "step": 2555500 }, { "epoch": 5.28, "learning_rate": 4.789459981072268e-07, "loss": 3.2245, "step": 2556000 }, { "epoch": 5.28, "learning_rate": 4.782572160254794e-07, "loss": 3.2297, "step": 2556500 }, { "epoch": 5.28, "learning_rate": 4.77568433943732e-07, "loss": 3.2264, "step": 2557000 }, { "epoch": 5.28, "learning_rate": 4.768796518619846e-07, "loss": 3.2299, "step": 2557500 }, { "epoch": 5.29, "learning_rate": 4.7619086978023715e-07, "loss": 3.2279, "step": 2558000 }, { "epoch": 5.29, "learning_rate": 4.755020876984898e-07, "loss": 3.2271, "step": 2558500 }, { "epoch": 5.29, "learning_rate": 4.7481330561674234e-07, "loss": 3.2283, "step": 2559000 }, { "epoch": 5.29, "learning_rate": 4.741245235349949e-07, "loss": 3.2241, "step": 2559500 }, { "epoch": 5.29, "learning_rate": 4.734357414532475e-07, "loss": 3.2321, "step": 2560000 }, { "epoch": 5.29, "learning_rate": 4.727469593715001e-07, "loss": 3.2254, "step": 2560500 }, { "epoch": 5.29, "learning_rate": 4.7205817728975267e-07, "loss": 3.2265, "step": 2561000 }, { "epoch": 5.29, "learning_rate": 4.713693952080053e-07, "loss": 3.224, "step": 2561500 }, { "epoch": 5.29, "learning_rate": 4.7068061312625786e-07, "loss": 3.2251, "step": 2562000 }, { "epoch": 5.3, "learning_rate": 4.6999183104451043e-07, "loss": 3.234, "step": 2562500 }, { "epoch": 5.3, "learning_rate": 4.69303048962763e-07, "loss": 3.2299, "step": 2563000 }, { "epoch": 5.3, "learning_rate": 4.686142668810156e-07, "loss": 3.2204, "step": 2563500 }, { "epoch": 5.3, "learning_rate": 4.6792548479926824e-07, "loss": 3.2306, "step": 2564000 }, { "epoch": 5.3, "learning_rate": 4.672367027175208e-07, "loss": 3.227, "step": 2564500 }, { "epoch": 5.3, "learning_rate": 4.6654792063577343e-07, "loss": 3.2297, "step": 2565000 }, { "epoch": 5.3, "learning_rate": 4.65859138554026e-07, "loss": 3.2361, "step": 2565500 }, { "epoch": 5.3, "learning_rate": 4.6517035647227857e-07, "loss": 3.2236, "step": 2566000 }, { "epoch": 5.3, "learning_rate": 4.6448157439053114e-07, "loss": 3.2275, "step": 2566500 }, { "epoch": 5.3, "learning_rate": 4.6379279230878376e-07, "loss": 3.2285, "step": 2567000 }, { "epoch": 5.31, "learning_rate": 4.6310401022703633e-07, "loss": 3.2337, "step": 2567500 }, { "epoch": 5.31, "learning_rate": 4.6241522814528895e-07, "loss": 3.2237, "step": 2568000 }, { "epoch": 5.31, "learning_rate": 4.617264460635415e-07, "loss": 3.2264, "step": 2568500 }, { "epoch": 5.31, "learning_rate": 4.610376639817941e-07, "loss": 3.2235, "step": 2569000 }, { "epoch": 5.31, "learning_rate": 4.6034888190004666e-07, "loss": 3.2243, "step": 2569500 }, { "epoch": 5.31, "learning_rate": 4.596600998182993e-07, "loss": 3.2267, "step": 2570000 }, { "epoch": 5.31, "learning_rate": 4.5897131773655185e-07, "loss": 3.2256, "step": 2570500 }, { "epoch": 5.31, "learning_rate": 4.5828253565480447e-07, "loss": 3.2237, "step": 2571000 }, { "epoch": 5.31, "learning_rate": 4.5759375357305704e-07, "loss": 3.2241, "step": 2571500 }, { "epoch": 5.31, "learning_rate": 4.5690497149130966e-07, "loss": 3.2255, "step": 2572000 }, { "epoch": 5.32, "learning_rate": 4.5621618940956217e-07, "loss": 3.2294, "step": 2572500 }, { "epoch": 5.32, "learning_rate": 4.555274073278148e-07, "loss": 3.2258, "step": 2573000 }, { "epoch": 5.32, "learning_rate": 4.5483862524606736e-07, "loss": 3.223, "step": 2573500 }, { "epoch": 5.32, "learning_rate": 4.5414984316432e-07, "loss": 3.2202, "step": 2574000 }, { "epoch": 5.32, "learning_rate": 4.5346106108257255e-07, "loss": 3.2247, "step": 2574500 }, { "epoch": 5.32, "learning_rate": 4.527722790008252e-07, "loss": 3.2244, "step": 2575000 }, { "epoch": 5.32, "learning_rate": 4.520834969190777e-07, "loss": 3.2202, "step": 2575500 }, { "epoch": 5.32, "learning_rate": 4.513947148373303e-07, "loss": 3.2226, "step": 2576000 }, { "epoch": 5.32, "learning_rate": 4.507059327555829e-07, "loss": 3.2234, "step": 2576500 }, { "epoch": 5.32, "learning_rate": 4.500171506738355e-07, "loss": 3.2254, "step": 2577000 }, { "epoch": 5.33, "learning_rate": 4.4932836859208807e-07, "loss": 3.2272, "step": 2577500 }, { "epoch": 5.33, "learning_rate": 4.486395865103407e-07, "loss": 3.2319, "step": 2578000 }, { "epoch": 5.33, "learning_rate": 4.479508044285932e-07, "loss": 3.2171, "step": 2578500 }, { "epoch": 5.33, "learning_rate": 4.4726202234684583e-07, "loss": 3.2222, "step": 2579000 }, { "epoch": 5.33, "learning_rate": 4.465732402650984e-07, "loss": 3.2289, "step": 2579500 }, { "epoch": 5.33, "learning_rate": 4.45884458183351e-07, "loss": 3.2249, "step": 2580000 }, { "epoch": 5.33, "learning_rate": 4.451956761016036e-07, "loss": 3.2208, "step": 2580500 }, { "epoch": 5.33, "learning_rate": 4.445068940198562e-07, "loss": 3.2266, "step": 2581000 }, { "epoch": 5.33, "learning_rate": 4.438181119381088e-07, "loss": 3.2297, "step": 2581500 }, { "epoch": 5.34, "learning_rate": 4.4312932985636135e-07, "loss": 3.2262, "step": 2582000 }, { "epoch": 5.34, "learning_rate": 4.424405477746139e-07, "loss": 3.2217, "step": 2582500 }, { "epoch": 5.34, "learning_rate": 4.4175176569286654e-07, "loss": 3.2253, "step": 2583000 }, { "epoch": 5.34, "learning_rate": 4.410629836111191e-07, "loss": 3.2328, "step": 2583500 }, { "epoch": 5.34, "learning_rate": 4.4037420152937173e-07, "loss": 3.2264, "step": 2584000 }, { "epoch": 5.34, "learning_rate": 4.3968541944762435e-07, "loss": 3.2218, "step": 2584500 }, { "epoch": 5.34, "learning_rate": 4.3899663736587686e-07, "loss": 3.2232, "step": 2585000 }, { "epoch": 5.34, "learning_rate": 4.383078552841295e-07, "loss": 3.2295, "step": 2585500 }, { "epoch": 5.34, "learning_rate": 4.3761907320238205e-07, "loss": 3.2254, "step": 2586000 }, { "epoch": 5.34, "learning_rate": 4.369302911206347e-07, "loss": 3.2304, "step": 2586500 }, { "epoch": 5.35, "learning_rate": 4.3624150903888724e-07, "loss": 3.2277, "step": 2587000 }, { "epoch": 5.35, "learning_rate": 4.3555272695713987e-07, "loss": 3.2258, "step": 2587500 }, { "epoch": 5.35, "learning_rate": 4.348639448753924e-07, "loss": 3.2222, "step": 2588000 }, { "epoch": 5.35, "learning_rate": 4.34175162793645e-07, "loss": 3.2273, "step": 2588500 }, { "epoch": 5.35, "learning_rate": 4.3348638071189757e-07, "loss": 3.2225, "step": 2589000 }, { "epoch": 5.35, "learning_rate": 4.327975986301502e-07, "loss": 3.2282, "step": 2589500 }, { "epoch": 5.35, "learning_rate": 4.3210881654840276e-07, "loss": 3.2211, "step": 2590000 }, { "epoch": 5.35, "learning_rate": 4.314200344666554e-07, "loss": 3.2209, "step": 2590500 }, { "epoch": 5.35, "learning_rate": 4.3073125238490795e-07, "loss": 3.2238, "step": 2591000 }, { "epoch": 5.35, "learning_rate": 4.300424703031605e-07, "loss": 3.2258, "step": 2591500 }, { "epoch": 5.36, "learning_rate": 4.293536882214131e-07, "loss": 3.2245, "step": 2592000 }, { "epoch": 5.36, "learning_rate": 4.286649061396657e-07, "loss": 3.223, "step": 2592500 }, { "epoch": 5.36, "learning_rate": 4.279761240579183e-07, "loss": 3.2223, "step": 2593000 }, { "epoch": 5.36, "learning_rate": 4.272873419761709e-07, "loss": 3.2251, "step": 2593500 }, { "epoch": 5.36, "learning_rate": 4.2659855989442347e-07, "loss": 3.2259, "step": 2594000 }, { "epoch": 5.36, "learning_rate": 4.2590977781267604e-07, "loss": 3.2235, "step": 2594500 }, { "epoch": 5.36, "learning_rate": 4.252209957309286e-07, "loss": 3.2222, "step": 2595000 }, { "epoch": 5.36, "learning_rate": 4.2453221364918123e-07, "loss": 3.2244, "step": 2595500 }, { "epoch": 5.36, "learning_rate": 4.238434315674338e-07, "loss": 3.2262, "step": 2596000 }, { "epoch": 5.37, "learning_rate": 4.231546494856864e-07, "loss": 3.2279, "step": 2596500 }, { "epoch": 5.37, "learning_rate": 4.22465867403939e-07, "loss": 3.2311, "step": 2597000 }, { "epoch": 5.37, "learning_rate": 4.217770853221916e-07, "loss": 3.2258, "step": 2597500 }, { "epoch": 5.37, "learning_rate": 4.210883032404441e-07, "loss": 3.2223, "step": 2598000 }, { "epoch": 5.37, "learning_rate": 4.2039952115869675e-07, "loss": 3.2306, "step": 2598500 }, { "epoch": 5.37, "learning_rate": 4.197107390769493e-07, "loss": 3.2253, "step": 2599000 }, { "epoch": 5.37, "learning_rate": 4.1902195699520194e-07, "loss": 3.2201, "step": 2599500 }, { "epoch": 5.37, "learning_rate": 4.183331749134545e-07, "loss": 3.2202, "step": 2600000 }, { "epoch": 5.37, "learning_rate": 4.1764439283170713e-07, "loss": 3.2246, "step": 2600500 }, { "epoch": 5.37, "learning_rate": 4.1695561074995964e-07, "loss": 3.2267, "step": 2601000 }, { "epoch": 5.38, "learning_rate": 4.1626682866821226e-07, "loss": 3.2273, "step": 2601500 }, { "epoch": 5.38, "learning_rate": 4.1557804658646483e-07, "loss": 3.2192, "step": 2602000 }, { "epoch": 5.38, "learning_rate": 4.1488926450471745e-07, "loss": 3.2182, "step": 2602500 }, { "epoch": 5.38, "learning_rate": 4.1420048242297e-07, "loss": 3.2234, "step": 2603000 }, { "epoch": 5.38, "learning_rate": 4.1351170034122264e-07, "loss": 3.2278, "step": 2603500 }, { "epoch": 5.38, "learning_rate": 4.128229182594752e-07, "loss": 3.2253, "step": 2604000 }, { "epoch": 5.38, "learning_rate": 4.121341361777278e-07, "loss": 3.2274, "step": 2604500 }, { "epoch": 5.38, "learning_rate": 4.114453540959804e-07, "loss": 3.2239, "step": 2605000 }, { "epoch": 5.38, "learning_rate": 4.1075657201423297e-07, "loss": 3.2208, "step": 2605500 }, { "epoch": 5.38, "learning_rate": 4.100677899324856e-07, "loss": 3.2207, "step": 2606000 }, { "epoch": 5.39, "learning_rate": 4.0937900785073816e-07, "loss": 3.22, "step": 2606500 }, { "epoch": 5.39, "learning_rate": 4.086902257689908e-07, "loss": 3.2289, "step": 2607000 }, { "epoch": 5.39, "learning_rate": 4.080014436872433e-07, "loss": 3.2277, "step": 2607500 }, { "epoch": 5.39, "learning_rate": 4.073126616054959e-07, "loss": 3.2223, "step": 2608000 }, { "epoch": 5.39, "learning_rate": 4.066238795237485e-07, "loss": 3.2293, "step": 2608500 }, { "epoch": 5.39, "learning_rate": 4.059350974420011e-07, "loss": 3.2291, "step": 2609000 }, { "epoch": 5.39, "learning_rate": 4.052463153602537e-07, "loss": 3.2285, "step": 2609500 }, { "epoch": 5.39, "learning_rate": 4.045575332785063e-07, "loss": 3.2204, "step": 2610000 }, { "epoch": 5.39, "learning_rate": 4.038687511967588e-07, "loss": 3.2211, "step": 2610500 }, { "epoch": 5.4, "learning_rate": 4.0317996911501144e-07, "loss": 3.2233, "step": 2611000 }, { "epoch": 5.4, "learning_rate": 4.02491187033264e-07, "loss": 3.2276, "step": 2611500 }, { "epoch": 5.4, "learning_rate": 4.0180240495151663e-07, "loss": 3.2231, "step": 2612000 }, { "epoch": 5.4, "learning_rate": 4.011136228697692e-07, "loss": 3.2289, "step": 2612500 }, { "epoch": 5.4, "learning_rate": 4.004248407880218e-07, "loss": 3.2277, "step": 2613000 }, { "epoch": 5.4, "learning_rate": 3.9973605870627433e-07, "loss": 3.2267, "step": 2613500 }, { "epoch": 5.4, "learning_rate": 3.9904727662452696e-07, "loss": 3.2314, "step": 2614000 }, { "epoch": 5.4, "learning_rate": 3.983584945427795e-07, "loss": 3.2249, "step": 2614500 }, { "epoch": 5.4, "learning_rate": 3.9766971246103215e-07, "loss": 3.2261, "step": 2615000 }, { "epoch": 5.4, "learning_rate": 3.969809303792847e-07, "loss": 3.2277, "step": 2615500 }, { "epoch": 5.41, "learning_rate": 3.9629214829753734e-07, "loss": 3.2184, "step": 2616000 }, { "epoch": 5.41, "learning_rate": 3.956033662157899e-07, "loss": 3.2303, "step": 2616500 }, { "epoch": 5.41, "learning_rate": 3.9491458413404247e-07, "loss": 3.2268, "step": 2617000 }, { "epoch": 5.41, "learning_rate": 3.9422580205229504e-07, "loss": 3.2218, "step": 2617500 }, { "epoch": 5.41, "learning_rate": 3.9353701997054766e-07, "loss": 3.2214, "step": 2618000 }, { "epoch": 5.41, "learning_rate": 3.9284823788880023e-07, "loss": 3.2277, "step": 2618500 }, { "epoch": 5.41, "learning_rate": 3.9215945580705285e-07, "loss": 3.2241, "step": 2619000 }, { "epoch": 5.41, "learning_rate": 3.914706737253054e-07, "loss": 3.2224, "step": 2619500 }, { "epoch": 5.41, "learning_rate": 3.90781891643558e-07, "loss": 3.2221, "step": 2620000 }, { "epoch": 5.41, "learning_rate": 3.9009310956181056e-07, "loss": 3.223, "step": 2620500 }, { "epoch": 5.42, "learning_rate": 3.894043274800632e-07, "loss": 3.2243, "step": 2621000 }, { "epoch": 5.42, "learning_rate": 3.8871554539831575e-07, "loss": 3.2261, "step": 2621500 }, { "epoch": 5.42, "learning_rate": 3.8802676331656837e-07, "loss": 3.2188, "step": 2622000 }, { "epoch": 5.42, "learning_rate": 3.8733798123482094e-07, "loss": 3.2249, "step": 2622500 }, { "epoch": 5.42, "learning_rate": 3.8664919915307356e-07, "loss": 3.2238, "step": 2623000 }, { "epoch": 5.42, "learning_rate": 3.8596041707132613e-07, "loss": 3.2235, "step": 2623500 }, { "epoch": 5.42, "learning_rate": 3.852716349895787e-07, "loss": 3.2197, "step": 2624000 }, { "epoch": 5.42, "learning_rate": 3.845828529078313e-07, "loss": 3.2244, "step": 2624500 }, { "epoch": 5.42, "learning_rate": 3.838940708260839e-07, "loss": 3.2209, "step": 2625000 }, { "epoch": 5.43, "learning_rate": 3.832052887443365e-07, "loss": 3.2234, "step": 2625500 }, { "epoch": 5.43, "learning_rate": 3.825165066625891e-07, "loss": 3.2206, "step": 2626000 }, { "epoch": 5.43, "learning_rate": 3.8182772458084165e-07, "loss": 3.23, "step": 2626500 }, { "epoch": 5.43, "learning_rate": 3.811389424990942e-07, "loss": 3.2236, "step": 2627000 }, { "epoch": 5.43, "learning_rate": 3.8045016041734684e-07, "loss": 3.2222, "step": 2627500 }, { "epoch": 5.43, "learning_rate": 3.797613783355994e-07, "loss": 3.2239, "step": 2628000 }, { "epoch": 5.43, "learning_rate": 3.7907259625385203e-07, "loss": 3.2191, "step": 2628500 }, { "epoch": 5.43, "learning_rate": 3.783838141721046e-07, "loss": 3.228, "step": 2629000 }, { "epoch": 5.43, "learning_rate": 3.7769503209035717e-07, "loss": 3.2274, "step": 2629500 }, { "epoch": 5.43, "learning_rate": 3.7700625000860973e-07, "loss": 3.2278, "step": 2630000 }, { "epoch": 5.44, "learning_rate": 3.7631746792686236e-07, "loss": 3.2283, "step": 2630500 }, { "epoch": 5.44, "learning_rate": 3.756286858451149e-07, "loss": 3.2267, "step": 2631000 }, { "epoch": 5.44, "learning_rate": 3.7493990376336755e-07, "loss": 3.2228, "step": 2631500 }, { "epoch": 5.44, "learning_rate": 3.742511216816201e-07, "loss": 3.227, "step": 2632000 }, { "epoch": 5.44, "learning_rate": 3.7356233959987274e-07, "loss": 3.2222, "step": 2632500 }, { "epoch": 5.44, "learning_rate": 3.7287355751812525e-07, "loss": 3.2222, "step": 2633000 }, { "epoch": 5.44, "learning_rate": 3.7218477543637787e-07, "loss": 3.2264, "step": 2633500 }, { "epoch": 5.44, "learning_rate": 3.7149599335463044e-07, "loss": 3.231, "step": 2634000 }, { "epoch": 5.44, "learning_rate": 3.7080721127288306e-07, "loss": 3.2296, "step": 2634500 }, { "epoch": 5.44, "learning_rate": 3.7011842919113563e-07, "loss": 3.2271, "step": 2635000 }, { "epoch": 5.45, "learning_rate": 3.6942964710938825e-07, "loss": 3.2226, "step": 2635500 }, { "epoch": 5.45, "learning_rate": 3.6874086502764077e-07, "loss": 3.2251, "step": 2636000 }, { "epoch": 5.45, "learning_rate": 3.680520829458934e-07, "loss": 3.2254, "step": 2636500 }, { "epoch": 5.45, "learning_rate": 3.6736330086414596e-07, "loss": 3.2235, "step": 2637000 }, { "epoch": 5.45, "learning_rate": 3.666745187823986e-07, "loss": 3.2218, "step": 2637500 }, { "epoch": 5.45, "learning_rate": 3.6598573670065115e-07, "loss": 3.225, "step": 2638000 }, { "epoch": 5.45, "learning_rate": 3.6529695461890377e-07, "loss": 3.2175, "step": 2638500 }, { "epoch": 5.45, "learning_rate": 3.646081725371563e-07, "loss": 3.2284, "step": 2639000 }, { "epoch": 5.45, "learning_rate": 3.639193904554089e-07, "loss": 3.2278, "step": 2639500 }, { "epoch": 5.46, "learning_rate": 3.632306083736615e-07, "loss": 3.2232, "step": 2640000 }, { "epoch": 5.46, "learning_rate": 3.625418262919141e-07, "loss": 3.2216, "step": 2640500 }, { "epoch": 5.46, "learning_rate": 3.6185304421016667e-07, "loss": 3.2286, "step": 2641000 }, { "epoch": 5.46, "learning_rate": 3.611642621284193e-07, "loss": 3.2226, "step": 2641500 }, { "epoch": 5.46, "learning_rate": 3.6047548004667186e-07, "loss": 3.2265, "step": 2642000 }, { "epoch": 5.46, "learning_rate": 3.597866979649244e-07, "loss": 3.223, "step": 2642500 }, { "epoch": 5.46, "learning_rate": 3.59097915883177e-07, "loss": 3.2205, "step": 2643000 }, { "epoch": 5.46, "learning_rate": 3.584091338014296e-07, "loss": 3.2236, "step": 2643500 }, { "epoch": 5.46, "learning_rate": 3.5772035171968224e-07, "loss": 3.2258, "step": 2644000 }, { "epoch": 5.46, "learning_rate": 3.570315696379348e-07, "loss": 3.2261, "step": 2644500 }, { "epoch": 5.47, "learning_rate": 3.5634278755618743e-07, "loss": 3.2213, "step": 2645000 }, { "epoch": 5.47, "learning_rate": 3.5565400547443994e-07, "loss": 3.2279, "step": 2645500 }, { "epoch": 5.47, "learning_rate": 3.5496522339269256e-07, "loss": 3.2271, "step": 2646000 }, { "epoch": 5.47, "learning_rate": 3.5427644131094513e-07, "loss": 3.2169, "step": 2646500 }, { "epoch": 5.47, "learning_rate": 3.5358765922919776e-07, "loss": 3.2219, "step": 2647000 }, { "epoch": 5.47, "learning_rate": 3.528988771474503e-07, "loss": 3.2257, "step": 2647500 }, { "epoch": 5.47, "learning_rate": 3.5221009506570295e-07, "loss": 3.2256, "step": 2648000 }, { "epoch": 5.47, "learning_rate": 3.5152131298395546e-07, "loss": 3.2209, "step": 2648500 }, { "epoch": 5.47, "learning_rate": 3.508325309022081e-07, "loss": 3.2205, "step": 2649000 }, { "epoch": 5.47, "learning_rate": 3.5014374882046065e-07, "loss": 3.2248, "step": 2649500 }, { "epoch": 5.48, "learning_rate": 3.4945496673871327e-07, "loss": 3.2278, "step": 2650000 }, { "epoch": 5.48, "learning_rate": 3.4876618465696584e-07, "loss": 3.2229, "step": 2650500 }, { "epoch": 5.48, "learning_rate": 3.4807740257521846e-07, "loss": 3.2297, "step": 2651000 }, { "epoch": 5.48, "learning_rate": 3.4738862049347103e-07, "loss": 3.2301, "step": 2651500 }, { "epoch": 5.48, "learning_rate": 3.466998384117236e-07, "loss": 3.2213, "step": 2652000 }, { "epoch": 5.48, "learning_rate": 3.4601105632997617e-07, "loss": 3.2156, "step": 2652500 }, { "epoch": 5.48, "learning_rate": 3.453222742482288e-07, "loss": 3.226, "step": 2653000 }, { "epoch": 5.48, "learning_rate": 3.4463349216648136e-07, "loss": 3.2244, "step": 2653500 }, { "epoch": 5.48, "learning_rate": 3.43944710084734e-07, "loss": 3.2228, "step": 2654000 }, { "epoch": 5.49, "learning_rate": 3.4325592800298655e-07, "loss": 3.2326, "step": 2654500 }, { "epoch": 5.49, "learning_rate": 3.425671459212391e-07, "loss": 3.2195, "step": 2655000 }, { "epoch": 5.49, "learning_rate": 3.418783638394917e-07, "loss": 3.2175, "step": 2655500 }, { "epoch": 5.49, "learning_rate": 3.411895817577443e-07, "loss": 3.2321, "step": 2656000 }, { "epoch": 5.49, "learning_rate": 3.405007996759969e-07, "loss": 3.222, "step": 2656500 }, { "epoch": 5.49, "learning_rate": 3.398120175942495e-07, "loss": 3.2207, "step": 2657000 }, { "epoch": 5.49, "learning_rate": 3.3912323551250207e-07, "loss": 3.226, "step": 2657500 }, { "epoch": 5.49, "learning_rate": 3.384344534307547e-07, "loss": 3.2192, "step": 2658000 }, { "epoch": 5.49, "learning_rate": 3.377456713490072e-07, "loss": 3.2245, "step": 2658500 }, { "epoch": 5.49, "learning_rate": 3.370568892672598e-07, "loss": 3.2314, "step": 2659000 }, { "epoch": 5.5, "learning_rate": 3.363681071855124e-07, "loss": 3.2286, "step": 2659500 }, { "epoch": 5.5, "learning_rate": 3.35679325103765e-07, "loss": 3.2203, "step": 2660000 }, { "epoch": 5.5, "learning_rate": 3.349905430220176e-07, "loss": 3.2211, "step": 2660500 }, { "epoch": 5.5, "learning_rate": 3.343017609402702e-07, "loss": 3.226, "step": 2661000 }, { "epoch": 5.5, "learning_rate": 3.336129788585227e-07, "loss": 3.226, "step": 2661500 }, { "epoch": 5.5, "learning_rate": 3.3292419677677534e-07, "loss": 3.2233, "step": 2662000 }, { "epoch": 5.5, "learning_rate": 3.322354146950279e-07, "loss": 3.2284, "step": 2662500 }, { "epoch": 5.5, "learning_rate": 3.3154663261328053e-07, "loss": 3.2188, "step": 2663000 }, { "epoch": 5.5, "learning_rate": 3.3085785053153315e-07, "loss": 3.2224, "step": 2663500 }, { "epoch": 5.5, "learning_rate": 3.301690684497857e-07, "loss": 3.2269, "step": 2664000 }, { "epoch": 5.51, "learning_rate": 3.294802863680383e-07, "loss": 3.22, "step": 2664500 }, { "epoch": 5.51, "learning_rate": 3.2879150428629086e-07, "loss": 3.2278, "step": 2665000 }, { "epoch": 5.51, "learning_rate": 3.281027222045435e-07, "loss": 3.2192, "step": 2665500 }, { "epoch": 5.51, "learning_rate": 3.2741394012279605e-07, "loss": 3.2198, "step": 2666000 }, { "epoch": 5.51, "learning_rate": 3.2672515804104867e-07, "loss": 3.2219, "step": 2666500 }, { "epoch": 5.51, "learning_rate": 3.2603637595930124e-07, "loss": 3.2161, "step": 2667000 }, { "epoch": 5.51, "learning_rate": 3.2534759387755386e-07, "loss": 3.2262, "step": 2667500 }, { "epoch": 5.51, "learning_rate": 3.246588117958064e-07, "loss": 3.2201, "step": 2668000 }, { "epoch": 5.51, "learning_rate": 3.23970029714059e-07, "loss": 3.2149, "step": 2668500 }, { "epoch": 5.52, "learning_rate": 3.2328124763231157e-07, "loss": 3.2212, "step": 2669000 }, { "epoch": 5.52, "learning_rate": 3.225924655505642e-07, "loss": 3.2299, "step": 2669500 }, { "epoch": 5.52, "learning_rate": 3.2190368346881676e-07, "loss": 3.2257, "step": 2670000 }, { "epoch": 5.52, "learning_rate": 3.212149013870694e-07, "loss": 3.2232, "step": 2670500 }, { "epoch": 5.52, "learning_rate": 3.205261193053219e-07, "loss": 3.2268, "step": 2671000 }, { "epoch": 5.52, "learning_rate": 3.198373372235745e-07, "loss": 3.2236, "step": 2671500 }, { "epoch": 5.52, "learning_rate": 3.191485551418271e-07, "loss": 3.2205, "step": 2672000 }, { "epoch": 5.52, "learning_rate": 3.184597730600797e-07, "loss": 3.2278, "step": 2672500 }, { "epoch": 5.52, "learning_rate": 3.177709909783323e-07, "loss": 3.2213, "step": 2673000 }, { "epoch": 5.52, "learning_rate": 3.170822088965849e-07, "loss": 3.2202, "step": 2673500 }, { "epoch": 5.53, "learning_rate": 3.163934268148374e-07, "loss": 3.2243, "step": 2674000 }, { "epoch": 5.53, "learning_rate": 3.1570464473309003e-07, "loss": 3.2215, "step": 2674500 }, { "epoch": 5.53, "learning_rate": 3.150158626513426e-07, "loss": 3.22, "step": 2675000 }, { "epoch": 5.53, "learning_rate": 3.143270805695952e-07, "loss": 3.2189, "step": 2675500 }, { "epoch": 5.53, "learning_rate": 3.136382984878478e-07, "loss": 3.2195, "step": 2676000 }, { "epoch": 5.53, "learning_rate": 3.129495164061004e-07, "loss": 3.2299, "step": 2676500 }, { "epoch": 5.53, "learning_rate": 3.12260734324353e-07, "loss": 3.225, "step": 2677000 }, { "epoch": 5.53, "learning_rate": 3.1157195224260555e-07, "loss": 3.2206, "step": 2677500 }, { "epoch": 5.53, "learning_rate": 3.108831701608581e-07, "loss": 3.2204, "step": 2678000 }, { "epoch": 5.53, "learning_rate": 3.1019438807911074e-07, "loss": 3.2243, "step": 2678500 }, { "epoch": 5.54, "learning_rate": 3.095056059973633e-07, "loss": 3.2146, "step": 2679000 }, { "epoch": 5.54, "learning_rate": 3.0881682391561593e-07, "loss": 3.2188, "step": 2679500 }, { "epoch": 5.54, "learning_rate": 3.081280418338685e-07, "loss": 3.2238, "step": 2680000 }, { "epoch": 5.54, "learning_rate": 3.0743925975212107e-07, "loss": 3.2224, "step": 2680500 }, { "epoch": 5.54, "learning_rate": 3.0675047767037364e-07, "loss": 3.2241, "step": 2681000 }, { "epoch": 5.54, "learning_rate": 3.0606169558862626e-07, "loss": 3.2173, "step": 2681500 }, { "epoch": 5.54, "learning_rate": 3.0537291350687883e-07, "loss": 3.227, "step": 2682000 }, { "epoch": 5.54, "learning_rate": 3.0468413142513145e-07, "loss": 3.2225, "step": 2682500 }, { "epoch": 5.54, "learning_rate": 3.0399534934338407e-07, "loss": 3.2262, "step": 2683000 }, { "epoch": 5.55, "learning_rate": 3.0330656726163664e-07, "loss": 3.2131, "step": 2683500 }, { "epoch": 5.55, "learning_rate": 3.026177851798892e-07, "loss": 3.2252, "step": 2684000 }, { "epoch": 5.55, "learning_rate": 3.019290030981418e-07, "loss": 3.2314, "step": 2684500 }, { "epoch": 5.55, "learning_rate": 3.012402210163944e-07, "loss": 3.2271, "step": 2685000 }, { "epoch": 5.55, "learning_rate": 3.0055143893464697e-07, "loss": 3.2208, "step": 2685500 }, { "epoch": 5.55, "learning_rate": 2.998626568528996e-07, "loss": 3.2139, "step": 2686000 }, { "epoch": 5.55, "learning_rate": 2.9917387477115216e-07, "loss": 3.2233, "step": 2686500 }, { "epoch": 5.55, "learning_rate": 2.9848509268940473e-07, "loss": 3.2234, "step": 2687000 }, { "epoch": 5.55, "learning_rate": 2.977963106076573e-07, "loss": 3.2274, "step": 2687500 }, { "epoch": 5.55, "learning_rate": 2.971075285259099e-07, "loss": 3.2207, "step": 2688000 }, { "epoch": 5.56, "learning_rate": 2.964187464441625e-07, "loss": 3.2195, "step": 2688500 }, { "epoch": 5.56, "learning_rate": 2.957299643624151e-07, "loss": 3.2225, "step": 2689000 }, { "epoch": 5.56, "learning_rate": 2.950411822806677e-07, "loss": 3.2258, "step": 2689500 }, { "epoch": 5.56, "learning_rate": 2.9435240019892024e-07, "loss": 3.2276, "step": 2690000 }, { "epoch": 5.56, "learning_rate": 2.936636181171728e-07, "loss": 3.2295, "step": 2690500 }, { "epoch": 5.56, "learning_rate": 2.9297483603542543e-07, "loss": 3.2273, "step": 2691000 }, { "epoch": 5.56, "learning_rate": 2.92286053953678e-07, "loss": 3.218, "step": 2691500 }, { "epoch": 5.56, "learning_rate": 2.915972718719306e-07, "loss": 3.2283, "step": 2692000 }, { "epoch": 5.56, "learning_rate": 2.909084897901832e-07, "loss": 3.2222, "step": 2692500 }, { "epoch": 5.56, "learning_rate": 2.902197077084358e-07, "loss": 3.219, "step": 2693000 }, { "epoch": 5.57, "learning_rate": 2.8953092562668833e-07, "loss": 3.2229, "step": 2693500 }, { "epoch": 5.57, "learning_rate": 2.8884214354494095e-07, "loss": 3.2234, "step": 2694000 }, { "epoch": 5.57, "learning_rate": 2.881533614631935e-07, "loss": 3.2239, "step": 2694500 }, { "epoch": 5.57, "learning_rate": 2.8746457938144614e-07, "loss": 3.2252, "step": 2695000 }, { "epoch": 5.57, "learning_rate": 2.867757972996987e-07, "loss": 3.2236, "step": 2695500 }, { "epoch": 5.57, "learning_rate": 2.8608701521795133e-07, "loss": 3.2242, "step": 2696000 }, { "epoch": 5.57, "learning_rate": 2.8539823313620385e-07, "loss": 3.2209, "step": 2696500 }, { "epoch": 5.57, "learning_rate": 2.8470945105445647e-07, "loss": 3.2177, "step": 2697000 }, { "epoch": 5.57, "learning_rate": 2.8402066897270904e-07, "loss": 3.2264, "step": 2697500 }, { "epoch": 5.58, "learning_rate": 2.8333188689096166e-07, "loss": 3.2243, "step": 2698000 }, { "epoch": 5.58, "learning_rate": 2.8264310480921423e-07, "loss": 3.2204, "step": 2698500 }, { "epoch": 5.58, "learning_rate": 2.8195432272746685e-07, "loss": 3.2261, "step": 2699000 }, { "epoch": 5.58, "learning_rate": 2.8126554064571937e-07, "loss": 3.2196, "step": 2699500 }, { "epoch": 5.58, "learning_rate": 2.80576758563972e-07, "loss": 3.2252, "step": 2700000 }, { "epoch": 5.58, "learning_rate": 2.7988797648222456e-07, "loss": 3.2269, "step": 2700500 }, { "epoch": 5.58, "learning_rate": 2.791991944004772e-07, "loss": 3.2168, "step": 2701000 }, { "epoch": 5.58, "learning_rate": 2.7851041231872975e-07, "loss": 3.2193, "step": 2701500 }, { "epoch": 5.58, "learning_rate": 2.7782163023698237e-07, "loss": 3.2258, "step": 2702000 }, { "epoch": 5.58, "learning_rate": 2.7713284815523494e-07, "loss": 3.2288, "step": 2702500 }, { "epoch": 5.59, "learning_rate": 2.764440660734875e-07, "loss": 3.2241, "step": 2703000 }, { "epoch": 5.59, "learning_rate": 2.757552839917401e-07, "loss": 3.2188, "step": 2703500 }, { "epoch": 5.59, "learning_rate": 2.750665019099927e-07, "loss": 3.2244, "step": 2704000 }, { "epoch": 5.59, "learning_rate": 2.743777198282453e-07, "loss": 3.221, "step": 2704500 }, { "epoch": 5.59, "learning_rate": 2.736889377464979e-07, "loss": 3.2237, "step": 2705000 }, { "epoch": 5.59, "learning_rate": 2.730001556647505e-07, "loss": 3.2226, "step": 2705500 }, { "epoch": 5.59, "learning_rate": 2.72311373583003e-07, "loss": 3.2208, "step": 2706000 }, { "epoch": 5.59, "learning_rate": 2.7162259150125564e-07, "loss": 3.2164, "step": 2706500 }, { "epoch": 5.59, "learning_rate": 2.709338094195082e-07, "loss": 3.2282, "step": 2707000 }, { "epoch": 5.59, "learning_rate": 2.7024502733776083e-07, "loss": 3.2234, "step": 2707500 }, { "epoch": 5.6, "learning_rate": 2.695562452560134e-07, "loss": 3.2262, "step": 2708000 }, { "epoch": 5.6, "learning_rate": 2.68867463174266e-07, "loss": 3.2189, "step": 2708500 }, { "epoch": 5.6, "learning_rate": 2.6817868109251854e-07, "loss": 3.2281, "step": 2709000 }, { "epoch": 5.6, "learning_rate": 2.6748989901077116e-07, "loss": 3.2234, "step": 2709500 }, { "epoch": 5.6, "learning_rate": 2.6680111692902373e-07, "loss": 3.2155, "step": 2710000 }, { "epoch": 5.6, "learning_rate": 2.6611233484727635e-07, "loss": 3.2193, "step": 2710500 }, { "epoch": 5.6, "learning_rate": 2.654235527655289e-07, "loss": 3.2225, "step": 2711000 }, { "epoch": 5.6, "learning_rate": 2.6473477068378154e-07, "loss": 3.2189, "step": 2711500 }, { "epoch": 5.6, "learning_rate": 2.640459886020341e-07, "loss": 3.2265, "step": 2712000 }, { "epoch": 5.6, "learning_rate": 2.633572065202867e-07, "loss": 3.2214, "step": 2712500 }, { "epoch": 5.61, "learning_rate": 2.6266842443853925e-07, "loss": 3.2227, "step": 2713000 }, { "epoch": 5.61, "learning_rate": 2.6197964235679187e-07, "loss": 3.2181, "step": 2713500 }, { "epoch": 5.61, "learning_rate": 2.6129086027504444e-07, "loss": 3.2262, "step": 2714000 }, { "epoch": 5.61, "learning_rate": 2.6060207819329706e-07, "loss": 3.2203, "step": 2714500 }, { "epoch": 5.61, "learning_rate": 2.5991329611154963e-07, "loss": 3.2204, "step": 2715000 }, { "epoch": 5.61, "learning_rate": 2.592245140298022e-07, "loss": 3.2232, "step": 2715500 }, { "epoch": 5.61, "learning_rate": 2.5853573194805477e-07, "loss": 3.225, "step": 2716000 }, { "epoch": 5.61, "learning_rate": 2.578469498663074e-07, "loss": 3.2176, "step": 2716500 }, { "epoch": 5.61, "learning_rate": 2.5715816778455996e-07, "loss": 3.2253, "step": 2717000 }, { "epoch": 5.62, "learning_rate": 2.564693857028126e-07, "loss": 3.222, "step": 2717500 }, { "epoch": 5.62, "learning_rate": 2.5578060362106515e-07, "loss": 3.218, "step": 2718000 }, { "epoch": 5.62, "learning_rate": 2.5509182153931777e-07, "loss": 3.2236, "step": 2718500 }, { "epoch": 5.62, "learning_rate": 2.544030394575703e-07, "loss": 3.2266, "step": 2719000 }, { "epoch": 5.62, "learning_rate": 2.537142573758229e-07, "loss": 3.2277, "step": 2719500 }, { "epoch": 5.62, "learning_rate": 2.5302547529407547e-07, "loss": 3.2245, "step": 2720000 }, { "epoch": 5.62, "learning_rate": 2.523366932123281e-07, "loss": 3.2186, "step": 2720500 }, { "epoch": 5.62, "learning_rate": 2.5164791113058066e-07, "loss": 3.2219, "step": 2721000 }, { "epoch": 5.62, "learning_rate": 2.509591290488333e-07, "loss": 3.222, "step": 2721500 }, { "epoch": 5.62, "learning_rate": 2.502703469670858e-07, "loss": 3.2274, "step": 2722000 }, { "epoch": 5.63, "learning_rate": 2.495815648853384e-07, "loss": 3.2175, "step": 2722500 }, { "epoch": 5.63, "learning_rate": 2.4889278280359104e-07, "loss": 3.2218, "step": 2723000 }, { "epoch": 5.63, "learning_rate": 2.482040007218436e-07, "loss": 3.2277, "step": 2723500 }, { "epoch": 5.63, "learning_rate": 2.475152186400962e-07, "loss": 3.2237, "step": 2724000 }, { "epoch": 5.63, "learning_rate": 2.468264365583488e-07, "loss": 3.2285, "step": 2724500 }, { "epoch": 5.63, "learning_rate": 2.4613765447660137e-07, "loss": 3.2205, "step": 2725000 }, { "epoch": 5.63, "learning_rate": 2.4544887239485394e-07, "loss": 3.2213, "step": 2725500 }, { "epoch": 5.63, "learning_rate": 2.4476009031310656e-07, "loss": 3.2196, "step": 2726000 }, { "epoch": 5.63, "learning_rate": 2.4407130823135913e-07, "loss": 3.2228, "step": 2726500 }, { "epoch": 5.63, "learning_rate": 2.433825261496117e-07, "loss": 3.2223, "step": 2727000 }, { "epoch": 5.64, "learning_rate": 2.426937440678643e-07, "loss": 3.2247, "step": 2727500 }, { "epoch": 5.64, "learning_rate": 2.420049619861169e-07, "loss": 3.2229, "step": 2728000 }, { "epoch": 5.64, "learning_rate": 2.4131617990436946e-07, "loss": 3.2253, "step": 2728500 }, { "epoch": 5.64, "learning_rate": 2.406273978226221e-07, "loss": 3.2192, "step": 2729000 }, { "epoch": 5.64, "learning_rate": 2.3993861574087465e-07, "loss": 3.2163, "step": 2729500 }, { "epoch": 5.64, "learning_rate": 2.392498336591272e-07, "loss": 3.2256, "step": 2730000 }, { "epoch": 5.64, "learning_rate": 2.3856105157737984e-07, "loss": 3.2232, "step": 2730500 }, { "epoch": 5.64, "learning_rate": 2.378722694956324e-07, "loss": 3.2202, "step": 2731000 }, { "epoch": 5.64, "learning_rate": 2.37183487413885e-07, "loss": 3.2223, "step": 2731500 }, { "epoch": 5.65, "learning_rate": 2.364947053321376e-07, "loss": 3.2207, "step": 2732000 }, { "epoch": 5.65, "learning_rate": 2.3580592325039016e-07, "loss": 3.2255, "step": 2732500 }, { "epoch": 5.65, "learning_rate": 2.3511714116864279e-07, "loss": 3.222, "step": 2733000 }, { "epoch": 5.65, "learning_rate": 2.3442835908689538e-07, "loss": 3.2214, "step": 2733500 }, { "epoch": 5.65, "learning_rate": 2.3373957700514795e-07, "loss": 3.22, "step": 2734000 }, { "epoch": 5.65, "learning_rate": 2.3305079492340055e-07, "loss": 3.2217, "step": 2734500 }, { "epoch": 5.65, "learning_rate": 2.3236201284165314e-07, "loss": 3.2209, "step": 2735000 }, { "epoch": 5.65, "learning_rate": 2.316732307599057e-07, "loss": 3.2218, "step": 2735500 }, { "epoch": 5.65, "learning_rate": 2.309844486781583e-07, "loss": 3.2203, "step": 2736000 }, { "epoch": 5.65, "learning_rate": 2.302956665964109e-07, "loss": 3.2223, "step": 2736500 }, { "epoch": 5.66, "learning_rate": 2.2960688451466347e-07, "loss": 3.2204, "step": 2737000 }, { "epoch": 5.66, "learning_rate": 2.2891810243291606e-07, "loss": 3.2243, "step": 2737500 }, { "epoch": 5.66, "learning_rate": 2.2822932035116866e-07, "loss": 3.222, "step": 2738000 }, { "epoch": 5.66, "learning_rate": 2.2754053826942123e-07, "loss": 3.2226, "step": 2738500 }, { "epoch": 5.66, "learning_rate": 2.2685175618767382e-07, "loss": 3.221, "step": 2739000 }, { "epoch": 5.66, "learning_rate": 2.2616297410592642e-07, "loss": 3.2168, "step": 2739500 }, { "epoch": 5.66, "learning_rate": 2.25474192024179e-07, "loss": 3.2185, "step": 2740000 }, { "epoch": 5.66, "learning_rate": 2.2478540994243158e-07, "loss": 3.2214, "step": 2740500 }, { "epoch": 5.66, "learning_rate": 2.2409662786068418e-07, "loss": 3.2252, "step": 2741000 }, { "epoch": 5.66, "learning_rate": 2.2340784577893677e-07, "loss": 3.2251, "step": 2741500 }, { "epoch": 5.67, "learning_rate": 2.2271906369718934e-07, "loss": 3.2247, "step": 2742000 }, { "epoch": 5.67, "learning_rate": 2.2203028161544193e-07, "loss": 3.2214, "step": 2742500 }, { "epoch": 5.67, "learning_rate": 2.2134149953369453e-07, "loss": 3.2165, "step": 2743000 }, { "epoch": 5.67, "learning_rate": 2.206527174519471e-07, "loss": 3.2234, "step": 2743500 }, { "epoch": 5.67, "learning_rate": 2.199639353701997e-07, "loss": 3.2197, "step": 2744000 }, { "epoch": 5.67, "learning_rate": 2.192751532884523e-07, "loss": 3.2179, "step": 2744500 }, { "epoch": 5.67, "learning_rate": 2.1858637120670486e-07, "loss": 3.2261, "step": 2745000 }, { "epoch": 5.67, "learning_rate": 2.1789758912495745e-07, "loss": 3.2226, "step": 2745500 }, { "epoch": 5.67, "learning_rate": 2.1720880704321005e-07, "loss": 3.2202, "step": 2746000 }, { "epoch": 5.68, "learning_rate": 2.1652002496146262e-07, "loss": 3.2261, "step": 2746500 }, { "epoch": 5.68, "learning_rate": 2.158312428797152e-07, "loss": 3.2141, "step": 2747000 }, { "epoch": 5.68, "learning_rate": 2.151424607979678e-07, "loss": 3.221, "step": 2747500 }, { "epoch": 5.68, "learning_rate": 2.144536787162204e-07, "loss": 3.227, "step": 2748000 }, { "epoch": 5.68, "learning_rate": 2.1376489663447297e-07, "loss": 3.2206, "step": 2748500 }, { "epoch": 5.68, "learning_rate": 2.1307611455272556e-07, "loss": 3.2207, "step": 2749000 }, { "epoch": 5.68, "learning_rate": 2.1238733247097816e-07, "loss": 3.2169, "step": 2749500 }, { "epoch": 5.68, "learning_rate": 2.1169855038923073e-07, "loss": 3.2204, "step": 2750000 }, { "epoch": 5.68, "learning_rate": 2.1100976830748332e-07, "loss": 3.2233, "step": 2750500 }, { "epoch": 5.68, "learning_rate": 2.1032098622573592e-07, "loss": 3.2216, "step": 2751000 }, { "epoch": 5.69, "learning_rate": 2.096322041439885e-07, "loss": 3.2253, "step": 2751500 }, { "epoch": 5.69, "learning_rate": 2.0894342206224108e-07, "loss": 3.2158, "step": 2752000 }, { "epoch": 5.69, "learning_rate": 2.0825463998049368e-07, "loss": 3.2223, "step": 2752500 }, { "epoch": 5.69, "learning_rate": 2.0756585789874627e-07, "loss": 3.2167, "step": 2753000 }, { "epoch": 5.69, "learning_rate": 2.0687707581699887e-07, "loss": 3.2253, "step": 2753500 }, { "epoch": 5.69, "learning_rate": 2.0618829373525146e-07, "loss": 3.2254, "step": 2754000 }, { "epoch": 5.69, "learning_rate": 2.0549951165350403e-07, "loss": 3.2242, "step": 2754500 }, { "epoch": 5.69, "learning_rate": 2.0481072957175663e-07, "loss": 3.2165, "step": 2755000 }, { "epoch": 5.69, "learning_rate": 2.0412194749000922e-07, "loss": 3.2276, "step": 2755500 }, { "epoch": 5.69, "learning_rate": 2.0343316540826182e-07, "loss": 3.2244, "step": 2756000 }, { "epoch": 5.7, "learning_rate": 2.0274438332651438e-07, "loss": 3.2183, "step": 2756500 }, { "epoch": 5.7, "learning_rate": 2.0205560124476698e-07, "loss": 3.2193, "step": 2757000 }, { "epoch": 5.7, "learning_rate": 2.0136681916301957e-07, "loss": 3.2207, "step": 2757500 }, { "epoch": 5.7, "learning_rate": 2.0067803708127214e-07, "loss": 3.2159, "step": 2758000 }, { "epoch": 5.7, "learning_rate": 1.9998925499952474e-07, "loss": 3.2202, "step": 2758500 }, { "epoch": 5.7, "learning_rate": 1.9930047291777733e-07, "loss": 3.2106, "step": 2759000 }, { "epoch": 5.7, "learning_rate": 1.986116908360299e-07, "loss": 3.2316, "step": 2759500 }, { "epoch": 5.7, "learning_rate": 1.979229087542825e-07, "loss": 3.2196, "step": 2760000 }, { "epoch": 5.7, "learning_rate": 1.972341266725351e-07, "loss": 3.2264, "step": 2760500 }, { "epoch": 5.71, "learning_rate": 1.9654534459078766e-07, "loss": 3.2232, "step": 2761000 }, { "epoch": 5.71, "learning_rate": 1.9585656250904026e-07, "loss": 3.2205, "step": 2761500 }, { "epoch": 5.71, "learning_rate": 1.9516778042729285e-07, "loss": 3.22, "step": 2762000 }, { "epoch": 5.71, "learning_rate": 1.9447899834554542e-07, "loss": 3.2294, "step": 2762500 }, { "epoch": 5.71, "learning_rate": 1.9379021626379801e-07, "loss": 3.2243, "step": 2763000 }, { "epoch": 5.71, "learning_rate": 1.931014341820506e-07, "loss": 3.2226, "step": 2763500 }, { "epoch": 5.71, "learning_rate": 1.9241265210030318e-07, "loss": 3.2199, "step": 2764000 }, { "epoch": 5.71, "learning_rate": 1.9172387001855577e-07, "loss": 3.2142, "step": 2764500 }, { "epoch": 5.71, "learning_rate": 1.9103508793680837e-07, "loss": 3.2254, "step": 2765000 }, { "epoch": 5.71, "learning_rate": 1.9034630585506096e-07, "loss": 3.2178, "step": 2765500 }, { "epoch": 5.72, "learning_rate": 1.8965752377331353e-07, "loss": 3.2217, "step": 2766000 }, { "epoch": 5.72, "learning_rate": 1.8896874169156613e-07, "loss": 3.2225, "step": 2766500 }, { "epoch": 5.72, "learning_rate": 1.8827995960981872e-07, "loss": 3.2197, "step": 2767000 }, { "epoch": 5.72, "learning_rate": 1.875911775280713e-07, "loss": 3.2198, "step": 2767500 }, { "epoch": 5.72, "learning_rate": 1.8690239544632389e-07, "loss": 3.2304, "step": 2768000 }, { "epoch": 5.72, "learning_rate": 1.8621361336457648e-07, "loss": 3.2259, "step": 2768500 }, { "epoch": 5.72, "learning_rate": 1.8552483128282905e-07, "loss": 3.2183, "step": 2769000 }, { "epoch": 5.72, "learning_rate": 1.8483604920108165e-07, "loss": 3.2237, "step": 2769500 }, { "epoch": 5.72, "learning_rate": 1.8414726711933424e-07, "loss": 3.2207, "step": 2770000 }, { "epoch": 5.72, "learning_rate": 1.834584850375868e-07, "loss": 3.2221, "step": 2770500 }, { "epoch": 5.73, "learning_rate": 1.827697029558394e-07, "loss": 3.225, "step": 2771000 }, { "epoch": 5.73, "learning_rate": 1.82080920874092e-07, "loss": 3.2153, "step": 2771500 }, { "epoch": 5.73, "learning_rate": 1.8139213879234457e-07, "loss": 3.2201, "step": 2772000 }, { "epoch": 5.73, "learning_rate": 1.807033567105972e-07, "loss": 3.2231, "step": 2772500 }, { "epoch": 5.73, "learning_rate": 1.8001457462884978e-07, "loss": 3.2263, "step": 2773000 }, { "epoch": 5.73, "learning_rate": 1.7932579254710238e-07, "loss": 3.2205, "step": 2773500 }, { "epoch": 5.73, "learning_rate": 1.7863701046535495e-07, "loss": 3.2229, "step": 2774000 }, { "epoch": 5.73, "learning_rate": 1.7794822838360754e-07, "loss": 3.22, "step": 2774500 }, { "epoch": 5.73, "learning_rate": 1.7725944630186014e-07, "loss": 3.2178, "step": 2775000 }, { "epoch": 5.74, "learning_rate": 1.765706642201127e-07, "loss": 3.2159, "step": 2775500 }, { "epoch": 5.74, "learning_rate": 1.758818821383653e-07, "loss": 3.2227, "step": 2776000 }, { "epoch": 5.74, "learning_rate": 1.751931000566179e-07, "loss": 3.2196, "step": 2776500 }, { "epoch": 5.74, "learning_rate": 1.7450431797487047e-07, "loss": 3.2201, "step": 2777000 }, { "epoch": 5.74, "learning_rate": 1.7381553589312306e-07, "loss": 3.2191, "step": 2777500 }, { "epoch": 5.74, "learning_rate": 1.7312675381137566e-07, "loss": 3.2249, "step": 2778000 }, { "epoch": 5.74, "learning_rate": 1.7243797172962822e-07, "loss": 3.2213, "step": 2778500 }, { "epoch": 5.74, "learning_rate": 1.7174918964788082e-07, "loss": 3.2198, "step": 2779000 }, { "epoch": 5.74, "learning_rate": 1.7106040756613341e-07, "loss": 3.2193, "step": 2779500 }, { "epoch": 5.74, "learning_rate": 1.7037162548438598e-07, "loss": 3.2267, "step": 2780000 }, { "epoch": 5.75, "learning_rate": 1.6968284340263858e-07, "loss": 3.2184, "step": 2780500 }, { "epoch": 5.75, "learning_rate": 1.6899406132089117e-07, "loss": 3.2317, "step": 2781000 }, { "epoch": 5.75, "learning_rate": 1.6830527923914374e-07, "loss": 3.2222, "step": 2781500 }, { "epoch": 5.75, "learning_rate": 1.6761649715739634e-07, "loss": 3.2288, "step": 2782000 }, { "epoch": 5.75, "learning_rate": 1.6692771507564893e-07, "loss": 3.213, "step": 2782500 }, { "epoch": 5.75, "learning_rate": 1.6623893299390153e-07, "loss": 3.2189, "step": 2783000 }, { "epoch": 5.75, "learning_rate": 1.655501509121541e-07, "loss": 3.224, "step": 2783500 }, { "epoch": 5.75, "learning_rate": 1.648613688304067e-07, "loss": 3.2251, "step": 2784000 }, { "epoch": 5.75, "learning_rate": 1.6417258674865929e-07, "loss": 3.219, "step": 2784500 }, { "epoch": 5.75, "learning_rate": 1.6348380466691185e-07, "loss": 3.2154, "step": 2785000 }, { "epoch": 5.76, "learning_rate": 1.6279502258516445e-07, "loss": 3.223, "step": 2785500 }, { "epoch": 5.76, "learning_rate": 1.6210624050341704e-07, "loss": 3.2198, "step": 2786000 }, { "epoch": 5.76, "learning_rate": 1.6141745842166961e-07, "loss": 3.2219, "step": 2786500 }, { "epoch": 5.76, "learning_rate": 1.607286763399222e-07, "loss": 3.2122, "step": 2787000 }, { "epoch": 5.76, "learning_rate": 1.600398942581748e-07, "loss": 3.219, "step": 2787500 }, { "epoch": 5.76, "learning_rate": 1.5935111217642737e-07, "loss": 3.222, "step": 2788000 }, { "epoch": 5.76, "learning_rate": 1.5866233009467997e-07, "loss": 3.2225, "step": 2788500 }, { "epoch": 5.76, "learning_rate": 1.5797354801293256e-07, "loss": 3.2179, "step": 2789000 }, { "epoch": 5.76, "learning_rate": 1.5728476593118513e-07, "loss": 3.2206, "step": 2789500 }, { "epoch": 5.77, "learning_rate": 1.5659598384943773e-07, "loss": 3.2142, "step": 2790000 }, { "epoch": 5.77, "learning_rate": 1.5590720176769032e-07, "loss": 3.2208, "step": 2790500 }, { "epoch": 5.77, "learning_rate": 1.552184196859429e-07, "loss": 3.2193, "step": 2791000 }, { "epoch": 5.77, "learning_rate": 1.5452963760419548e-07, "loss": 3.2226, "step": 2791500 }, { "epoch": 5.77, "learning_rate": 1.5384085552244808e-07, "loss": 3.2252, "step": 2792000 }, { "epoch": 5.77, "learning_rate": 1.531520734407007e-07, "loss": 3.2176, "step": 2792500 }, { "epoch": 5.77, "learning_rate": 1.5246329135895327e-07, "loss": 3.2215, "step": 2793000 }, { "epoch": 5.77, "learning_rate": 1.5177450927720587e-07, "loss": 3.2185, "step": 2793500 }, { "epoch": 5.77, "learning_rate": 1.5108572719545846e-07, "loss": 3.2234, "step": 2794000 }, { "epoch": 5.77, "learning_rate": 1.5039694511371103e-07, "loss": 3.2181, "step": 2794500 }, { "epoch": 5.78, "learning_rate": 1.4970816303196362e-07, "loss": 3.2282, "step": 2795000 }, { "epoch": 5.78, "learning_rate": 1.4901938095021622e-07, "loss": 3.2176, "step": 2795500 }, { "epoch": 5.78, "learning_rate": 1.483305988684688e-07, "loss": 3.2202, "step": 2796000 }, { "epoch": 5.78, "learning_rate": 1.4764181678672138e-07, "loss": 3.2176, "step": 2796500 }, { "epoch": 5.78, "learning_rate": 1.4695303470497398e-07, "loss": 3.2241, "step": 2797000 }, { "epoch": 5.78, "learning_rate": 1.4626425262322655e-07, "loss": 3.2231, "step": 2797500 }, { "epoch": 5.78, "learning_rate": 1.4557547054147914e-07, "loss": 3.2222, "step": 2798000 }, { "epoch": 5.78, "learning_rate": 1.4488668845973174e-07, "loss": 3.225, "step": 2798500 }, { "epoch": 5.78, "learning_rate": 1.4419790637798433e-07, "loss": 3.2272, "step": 2799000 }, { "epoch": 5.78, "learning_rate": 1.435091242962369e-07, "loss": 3.226, "step": 2799500 }, { "epoch": 5.79, "learning_rate": 1.428203422144895e-07, "loss": 3.2171, "step": 2800000 }, { "epoch": 5.79, "learning_rate": 1.421315601327421e-07, "loss": 3.2234, "step": 2800500 }, { "epoch": 5.79, "learning_rate": 1.4144277805099466e-07, "loss": 3.2244, "step": 2801000 }, { "epoch": 5.79, "learning_rate": 1.4075399596924725e-07, "loss": 3.2162, "step": 2801500 }, { "epoch": 5.79, "learning_rate": 1.4006521388749985e-07, "loss": 3.2184, "step": 2802000 }, { "epoch": 5.79, "learning_rate": 1.3937643180575242e-07, "loss": 3.2298, "step": 2802500 }, { "epoch": 5.79, "learning_rate": 1.38687649724005e-07, "loss": 3.223, "step": 2803000 }, { "epoch": 5.79, "learning_rate": 1.379988676422576e-07, "loss": 3.2214, "step": 2803500 }, { "epoch": 5.79, "learning_rate": 1.3731008556051018e-07, "loss": 3.2187, "step": 2804000 }, { "epoch": 5.8, "learning_rate": 1.3662130347876277e-07, "loss": 3.2213, "step": 2804500 }, { "epoch": 5.8, "learning_rate": 1.3593252139701537e-07, "loss": 3.2149, "step": 2805000 }, { "epoch": 5.8, "learning_rate": 1.3524373931526794e-07, "loss": 3.2193, "step": 2805500 }, { "epoch": 5.8, "learning_rate": 1.3455495723352053e-07, "loss": 3.2182, "step": 2806000 }, { "epoch": 5.8, "learning_rate": 1.3386617515177313e-07, "loss": 3.2247, "step": 2806500 }, { "epoch": 5.8, "learning_rate": 1.331773930700257e-07, "loss": 3.2179, "step": 2807000 }, { "epoch": 5.8, "learning_rate": 1.324886109882783e-07, "loss": 3.2261, "step": 2807500 }, { "epoch": 5.8, "learning_rate": 1.3179982890653088e-07, "loss": 3.2257, "step": 2808000 }, { "epoch": 5.8, "learning_rate": 1.3111104682478348e-07, "loss": 3.2214, "step": 2808500 }, { "epoch": 5.8, "learning_rate": 1.3042226474303605e-07, "loss": 3.2188, "step": 2809000 }, { "epoch": 5.81, "learning_rate": 1.2973348266128864e-07, "loss": 3.2179, "step": 2809500 }, { "epoch": 5.81, "learning_rate": 1.2904470057954124e-07, "loss": 3.2192, "step": 2810000 }, { "epoch": 5.81, "learning_rate": 1.283559184977938e-07, "loss": 3.2246, "step": 2810500 }, { "epoch": 5.81, "learning_rate": 1.276671364160464e-07, "loss": 3.2242, "step": 2811000 }, { "epoch": 5.81, "learning_rate": 1.26978354334299e-07, "loss": 3.2178, "step": 2811500 }, { "epoch": 5.81, "learning_rate": 1.2628957225255157e-07, "loss": 3.2141, "step": 2812000 }, { "epoch": 5.81, "learning_rate": 1.256007901708042e-07, "loss": 3.2241, "step": 2812500 }, { "epoch": 5.81, "learning_rate": 1.2491200808905676e-07, "loss": 3.2196, "step": 2813000 }, { "epoch": 5.81, "learning_rate": 1.2422322600730935e-07, "loss": 3.2168, "step": 2813500 }, { "epoch": 5.81, "learning_rate": 1.2353444392556195e-07, "loss": 3.2177, "step": 2814000 }, { "epoch": 5.82, "learning_rate": 1.2284566184381451e-07, "loss": 3.2184, "step": 2814500 }, { "epoch": 5.82, "learning_rate": 1.221568797620671e-07, "loss": 3.2237, "step": 2815000 }, { "epoch": 5.82, "learning_rate": 1.214680976803197e-07, "loss": 3.2201, "step": 2815500 }, { "epoch": 5.82, "learning_rate": 1.2077931559857227e-07, "loss": 3.2215, "step": 2816000 }, { "epoch": 5.82, "learning_rate": 1.2009053351682487e-07, "loss": 3.2212, "step": 2816500 }, { "epoch": 5.82, "learning_rate": 1.1940175143507746e-07, "loss": 3.2146, "step": 2817000 }, { "epoch": 5.82, "learning_rate": 1.1871296935333006e-07, "loss": 3.2233, "step": 2817500 }, { "epoch": 5.82, "learning_rate": 1.1802418727158264e-07, "loss": 3.221, "step": 2818000 }, { "epoch": 5.82, "learning_rate": 1.1733540518983524e-07, "loss": 3.2143, "step": 2818500 }, { "epoch": 5.83, "learning_rate": 1.1664662310808782e-07, "loss": 3.2184, "step": 2819000 }, { "epoch": 5.83, "learning_rate": 1.159578410263404e-07, "loss": 3.2234, "step": 2819500 }, { "epoch": 5.83, "learning_rate": 1.15269058944593e-07, "loss": 3.2196, "step": 2820000 }, { "epoch": 5.83, "learning_rate": 1.1458027686284558e-07, "loss": 3.2224, "step": 2820500 }, { "epoch": 5.83, "learning_rate": 1.1389149478109816e-07, "loss": 3.2189, "step": 2821000 }, { "epoch": 5.83, "learning_rate": 1.1320271269935075e-07, "loss": 3.2231, "step": 2821500 }, { "epoch": 5.83, "learning_rate": 1.1251393061760334e-07, "loss": 3.2249, "step": 2822000 }, { "epoch": 5.83, "learning_rate": 1.1182514853585592e-07, "loss": 3.2112, "step": 2822500 }, { "epoch": 5.83, "learning_rate": 1.1113636645410851e-07, "loss": 3.2204, "step": 2823000 }, { "epoch": 5.83, "learning_rate": 1.104475843723611e-07, "loss": 3.219, "step": 2823500 }, { "epoch": 5.84, "learning_rate": 1.0975880229061369e-07, "loss": 3.22, "step": 2824000 }, { "epoch": 5.84, "learning_rate": 1.0907002020886627e-07, "loss": 3.2192, "step": 2824500 }, { "epoch": 5.84, "learning_rate": 1.0838123812711885e-07, "loss": 3.2196, "step": 2825000 }, { "epoch": 5.84, "learning_rate": 1.0769245604537145e-07, "loss": 3.2166, "step": 2825500 }, { "epoch": 5.84, "learning_rate": 1.0700367396362403e-07, "loss": 3.2173, "step": 2826000 }, { "epoch": 5.84, "learning_rate": 1.0631489188187661e-07, "loss": 3.2203, "step": 2826500 }, { "epoch": 5.84, "learning_rate": 1.056261098001292e-07, "loss": 3.224, "step": 2827000 }, { "epoch": 5.84, "learning_rate": 1.049373277183818e-07, "loss": 3.227, "step": 2827500 }, { "epoch": 5.84, "learning_rate": 1.042485456366344e-07, "loss": 3.2184, "step": 2828000 }, { "epoch": 5.84, "learning_rate": 1.0355976355488698e-07, "loss": 3.2199, "step": 2828500 }, { "epoch": 5.85, "learning_rate": 1.0287098147313956e-07, "loss": 3.2257, "step": 2829000 }, { "epoch": 5.85, "learning_rate": 1.0218219939139216e-07, "loss": 3.228, "step": 2829500 }, { "epoch": 5.85, "learning_rate": 1.0149341730964474e-07, "loss": 3.2223, "step": 2830000 }, { "epoch": 5.85, "learning_rate": 1.0080463522789732e-07, "loss": 3.2154, "step": 2830500 }, { "epoch": 5.85, "learning_rate": 1.0011585314614991e-07, "loss": 3.2256, "step": 2831000 }, { "epoch": 5.85, "learning_rate": 9.94270710644025e-08, "loss": 3.2265, "step": 2831500 }, { "epoch": 5.85, "learning_rate": 9.873828898265509e-08, "loss": 3.2215, "step": 2832000 }, { "epoch": 5.85, "learning_rate": 9.804950690090767e-08, "loss": 3.2174, "step": 2832500 }, { "epoch": 5.85, "learning_rate": 9.736072481916025e-08, "loss": 3.2239, "step": 2833000 }, { "epoch": 5.85, "learning_rate": 9.667194273741285e-08, "loss": 3.2161, "step": 2833500 }, { "epoch": 5.86, "learning_rate": 9.598316065566543e-08, "loss": 3.2239, "step": 2834000 }, { "epoch": 5.86, "learning_rate": 9.529437857391801e-08, "loss": 3.2237, "step": 2834500 }, { "epoch": 5.86, "learning_rate": 9.460559649217061e-08, "loss": 3.22, "step": 2835000 }, { "epoch": 5.86, "learning_rate": 9.391681441042319e-08, "loss": 3.2148, "step": 2835500 }, { "epoch": 5.86, "learning_rate": 9.322803232867579e-08, "loss": 3.2192, "step": 2836000 }, { "epoch": 5.86, "learning_rate": 9.253925024692837e-08, "loss": 3.2209, "step": 2836500 }, { "epoch": 5.86, "learning_rate": 9.185046816518095e-08, "loss": 3.2203, "step": 2837000 }, { "epoch": 5.86, "learning_rate": 9.116168608343356e-08, "loss": 3.2209, "step": 2837500 }, { "epoch": 5.86, "learning_rate": 9.047290400168614e-08, "loss": 3.2182, "step": 2838000 }, { "epoch": 5.87, "learning_rate": 8.978412191993872e-08, "loss": 3.2203, "step": 2838500 }, { "epoch": 5.87, "learning_rate": 8.909533983819132e-08, "loss": 3.2195, "step": 2839000 }, { "epoch": 5.87, "learning_rate": 8.84065577564439e-08, "loss": 3.2231, "step": 2839500 }, { "epoch": 5.87, "learning_rate": 8.77177756746965e-08, "loss": 3.2229, "step": 2840000 }, { "epoch": 5.87, "learning_rate": 8.702899359294908e-08, "loss": 3.2297, "step": 2840500 }, { "epoch": 5.87, "learning_rate": 8.634021151120166e-08, "loss": 3.2179, "step": 2841000 }, { "epoch": 5.87, "learning_rate": 8.565142942945425e-08, "loss": 3.2171, "step": 2841500 }, { "epoch": 5.87, "learning_rate": 8.496264734770683e-08, "loss": 3.2182, "step": 2842000 }, { "epoch": 5.87, "learning_rate": 8.427386526595942e-08, "loss": 3.2188, "step": 2842500 }, { "epoch": 5.87, "learning_rate": 8.358508318421201e-08, "loss": 3.2207, "step": 2843000 }, { "epoch": 5.88, "learning_rate": 8.289630110246459e-08, "loss": 3.2231, "step": 2843500 }, { "epoch": 5.88, "learning_rate": 8.220751902071717e-08, "loss": 3.223, "step": 2844000 }, { "epoch": 5.88, "learning_rate": 8.151873693896977e-08, "loss": 3.2238, "step": 2844500 }, { "epoch": 5.88, "learning_rate": 8.082995485722235e-08, "loss": 3.2248, "step": 2845000 }, { "epoch": 5.88, "learning_rate": 8.014117277547495e-08, "loss": 3.2225, "step": 2845500 }, { "epoch": 5.88, "learning_rate": 7.945239069372753e-08, "loss": 3.2243, "step": 2846000 }, { "epoch": 5.88, "learning_rate": 7.876360861198011e-08, "loss": 3.2184, "step": 2846500 }, { "epoch": 5.88, "learning_rate": 7.807482653023272e-08, "loss": 3.2199, "step": 2847000 }, { "epoch": 5.88, "learning_rate": 7.73860444484853e-08, "loss": 3.2235, "step": 2847500 }, { "epoch": 5.88, "learning_rate": 7.669726236673788e-08, "loss": 3.2204, "step": 2848000 }, { "epoch": 5.89, "learning_rate": 7.600848028499048e-08, "loss": 3.2209, "step": 2848500 }, { "epoch": 5.89, "learning_rate": 7.531969820324306e-08, "loss": 3.2144, "step": 2849000 }, { "epoch": 5.89, "learning_rate": 7.463091612149565e-08, "loss": 3.2201, "step": 2849500 }, { "epoch": 5.89, "learning_rate": 7.394213403974824e-08, "loss": 3.2153, "step": 2850000 }, { "epoch": 5.89, "learning_rate": 7.325335195800082e-08, "loss": 3.2112, "step": 2850500 }, { "epoch": 5.89, "learning_rate": 7.256456987625341e-08, "loss": 3.2105, "step": 2851000 }, { "epoch": 5.89, "learning_rate": 7.1875787794506e-08, "loss": 3.2128, "step": 2851500 }, { "epoch": 5.89, "learning_rate": 7.118700571275858e-08, "loss": 3.2188, "step": 2852000 }, { "epoch": 5.89, "learning_rate": 7.049822363101117e-08, "loss": 3.2178, "step": 2852500 }, { "epoch": 5.9, "learning_rate": 6.980944154926375e-08, "loss": 3.2171, "step": 2853000 }, { "epoch": 5.9, "learning_rate": 6.912065946751635e-08, "loss": 3.2195, "step": 2853500 }, { "epoch": 5.9, "learning_rate": 6.843187738576893e-08, "loss": 3.2184, "step": 2854000 }, { "epoch": 5.9, "learning_rate": 6.774309530402151e-08, "loss": 3.2201, "step": 2854500 }, { "epoch": 5.9, "learning_rate": 6.705431322227411e-08, "loss": 3.2244, "step": 2855000 }, { "epoch": 5.9, "learning_rate": 6.636553114052669e-08, "loss": 3.2106, "step": 2855500 }, { "epoch": 5.9, "learning_rate": 6.567674905877927e-08, "loss": 3.2231, "step": 2856000 }, { "epoch": 5.9, "learning_rate": 6.498796697703187e-08, "loss": 3.2211, "step": 2856500 }, { "epoch": 5.9, "learning_rate": 6.429918489528446e-08, "loss": 3.2197, "step": 2857000 }, { "epoch": 5.9, "learning_rate": 6.361040281353706e-08, "loss": 3.2203, "step": 2857500 }, { "epoch": 5.91, "learning_rate": 6.292162073178964e-08, "loss": 3.2154, "step": 2858000 }, { "epoch": 5.91, "learning_rate": 6.223283865004222e-08, "loss": 3.2221, "step": 2858500 }, { "epoch": 5.91, "learning_rate": 6.15440565682948e-08, "loss": 3.2205, "step": 2859000 }, { "epoch": 5.91, "learning_rate": 6.08552744865474e-08, "loss": 3.2161, "step": 2859500 }, { "epoch": 5.91, "learning_rate": 6.016649240479998e-08, "loss": 3.2265, "step": 2860000 }, { "epoch": 5.91, "learning_rate": 5.9477710323052574e-08, "loss": 3.2188, "step": 2860500 }, { "epoch": 5.91, "learning_rate": 5.8788928241305156e-08, "loss": 3.2179, "step": 2861000 }, { "epoch": 5.91, "learning_rate": 5.8100146159557745e-08, "loss": 3.2132, "step": 2861500 }, { "epoch": 5.91, "learning_rate": 5.741136407781033e-08, "loss": 3.214, "step": 2862000 }, { "epoch": 5.91, "learning_rate": 5.6722581996062915e-08, "loss": 3.2178, "step": 2862500 }, { "epoch": 5.92, "learning_rate": 5.6033799914315503e-08, "loss": 3.2149, "step": 2863000 }, { "epoch": 5.92, "learning_rate": 5.534501783256809e-08, "loss": 3.2233, "step": 2863500 }, { "epoch": 5.92, "learning_rate": 5.465623575082068e-08, "loss": 3.2235, "step": 2864000 }, { "epoch": 5.92, "learning_rate": 5.396745366907327e-08, "loss": 3.2237, "step": 2864500 }, { "epoch": 5.92, "learning_rate": 5.327867158732586e-08, "loss": 3.216, "step": 2865000 }, { "epoch": 5.92, "learning_rate": 5.2589889505578446e-08, "loss": 3.2174, "step": 2865500 }, { "epoch": 5.92, "learning_rate": 5.1901107423831034e-08, "loss": 3.2191, "step": 2866000 }, { "epoch": 5.92, "learning_rate": 5.1212325342083616e-08, "loss": 3.2183, "step": 2866500 }, { "epoch": 5.92, "learning_rate": 5.0523543260336205e-08, "loss": 3.2146, "step": 2867000 }, { "epoch": 5.93, "learning_rate": 4.983476117858879e-08, "loss": 3.2201, "step": 2867500 }, { "epoch": 5.93, "learning_rate": 4.914597909684138e-08, "loss": 3.2175, "step": 2868000 }, { "epoch": 5.93, "learning_rate": 4.8457197015093963e-08, "loss": 3.2164, "step": 2868500 }, { "epoch": 5.93, "learning_rate": 4.776841493334655e-08, "loss": 3.2238, "step": 2869000 }, { "epoch": 5.93, "learning_rate": 4.707963285159915e-08, "loss": 3.2195, "step": 2869500 }, { "epoch": 5.93, "learning_rate": 4.6390850769851735e-08, "loss": 3.2233, "step": 2870000 }, { "epoch": 5.93, "learning_rate": 4.570206868810432e-08, "loss": 3.2232, "step": 2870500 }, { "epoch": 5.93, "learning_rate": 4.5013286606356906e-08, "loss": 3.2164, "step": 2871000 }, { "epoch": 5.93, "learning_rate": 4.4324504524609494e-08, "loss": 3.2188, "step": 2871500 }, { "epoch": 5.93, "learning_rate": 4.363572244286208e-08, "loss": 3.2174, "step": 2872000 }, { "epoch": 5.94, "learning_rate": 4.2946940361114664e-08, "loss": 3.2276, "step": 2872500 }, { "epoch": 5.94, "learning_rate": 4.225815827936725e-08, "loss": 3.2242, "step": 2873000 }, { "epoch": 5.94, "learning_rate": 4.156937619761984e-08, "loss": 3.2163, "step": 2873500 }, { "epoch": 5.94, "learning_rate": 4.088059411587243e-08, "loss": 3.2208, "step": 2874000 }, { "epoch": 5.94, "learning_rate": 4.019181203412502e-08, "loss": 3.2149, "step": 2874500 }, { "epoch": 5.94, "learning_rate": 3.950302995237761e-08, "loss": 3.2159, "step": 2875000 }, { "epoch": 5.94, "learning_rate": 3.8814247870630195e-08, "loss": 3.2158, "step": 2875500 }, { "epoch": 5.94, "learning_rate": 3.8125465788882784e-08, "loss": 3.2198, "step": 2876000 }, { "epoch": 5.94, "learning_rate": 3.7436683707135366e-08, "loss": 3.218, "step": 2876500 }, { "epoch": 5.94, "learning_rate": 3.6747901625387954e-08, "loss": 3.2199, "step": 2877000 }, { "epoch": 5.95, "learning_rate": 3.605911954364054e-08, "loss": 3.2246, "step": 2877500 }, { "epoch": 5.95, "learning_rate": 3.537033746189313e-08, "loss": 3.2183, "step": 2878000 }, { "epoch": 5.95, "learning_rate": 3.468155538014571e-08, "loss": 3.2248, "step": 2878500 }, { "epoch": 5.95, "learning_rate": 3.39927732983983e-08, "loss": 3.2238, "step": 2879000 }, { "epoch": 5.95, "learning_rate": 3.3303991216650896e-08, "loss": 3.2191, "step": 2879500 }, { "epoch": 5.95, "learning_rate": 3.2615209134903485e-08, "loss": 3.2182, "step": 2880000 }, { "epoch": 5.95, "learning_rate": 3.192642705315607e-08, "loss": 3.2167, "step": 2880500 }, { "epoch": 5.95, "learning_rate": 3.1237644971408655e-08, "loss": 3.2207, "step": 2881000 }, { "epoch": 5.95, "learning_rate": 3.0548862889661244e-08, "loss": 3.2152, "step": 2881500 }, { "epoch": 5.96, "learning_rate": 2.986008080791383e-08, "loss": 3.2203, "step": 2882000 }, { "epoch": 5.96, "learning_rate": 2.9171298726166417e-08, "loss": 3.2192, "step": 2882500 }, { "epoch": 5.96, "learning_rate": 2.8482516644419006e-08, "loss": 3.2183, "step": 2883000 }, { "epoch": 5.96, "learning_rate": 2.7793734562671594e-08, "loss": 3.2212, "step": 2883500 }, { "epoch": 5.96, "learning_rate": 2.710495248092418e-08, "loss": 3.2212, "step": 2884000 }, { "epoch": 5.96, "learning_rate": 2.6416170399176765e-08, "loss": 3.221, "step": 2884500 }, { "epoch": 5.96, "learning_rate": 2.5727388317429353e-08, "loss": 3.2151, "step": 2885000 }, { "epoch": 5.96, "learning_rate": 2.503860623568194e-08, "loss": 3.221, "step": 2885500 }, { "epoch": 5.96, "learning_rate": 2.434982415393453e-08, "loss": 3.2225, "step": 2886000 }, { "epoch": 5.96, "learning_rate": 2.3661042072187115e-08, "loss": 3.2149, "step": 2886500 }, { "epoch": 5.97, "learning_rate": 2.2972259990439704e-08, "loss": 3.2189, "step": 2887000 }, { "epoch": 5.97, "learning_rate": 2.228347790869229e-08, "loss": 3.2218, "step": 2887500 }, { "epoch": 5.97, "learning_rate": 2.159469582694488e-08, "loss": 3.2259, "step": 2888000 }, { "epoch": 5.97, "learning_rate": 2.0905913745197466e-08, "loss": 3.2185, "step": 2888500 }, { "epoch": 5.97, "learning_rate": 2.0217131663450054e-08, "loss": 3.2189, "step": 2889000 }, { "epoch": 5.97, "learning_rate": 1.952834958170264e-08, "loss": 3.221, "step": 2889500 }, { "epoch": 5.97, "learning_rate": 1.8839567499955228e-08, "loss": 3.2243, "step": 2890000 }, { "epoch": 5.97, "learning_rate": 1.8150785418207816e-08, "loss": 3.2103, "step": 2890500 }, { "epoch": 5.97, "learning_rate": 1.7462003336460405e-08, "loss": 3.2165, "step": 2891000 }, { "epoch": 5.97, "learning_rate": 1.677322125471299e-08, "loss": 3.2171, "step": 2891500 }, { "epoch": 5.98, "learning_rate": 1.6084439172965578e-08, "loss": 3.2171, "step": 2892000 }, { "epoch": 5.98, "learning_rate": 1.5395657091218167e-08, "loss": 3.2171, "step": 2892500 }, { "epoch": 5.98, "learning_rate": 1.4706875009470754e-08, "loss": 3.2177, "step": 2893000 }, { "epoch": 5.98, "learning_rate": 1.4018092927723339e-08, "loss": 3.2201, "step": 2893500 }, { "epoch": 5.98, "learning_rate": 1.3329310845975929e-08, "loss": 3.2186, "step": 2894000 }, { "epoch": 5.98, "learning_rate": 1.2640528764228514e-08, "loss": 3.2248, "step": 2894500 }, { "epoch": 5.98, "learning_rate": 1.1951746682481103e-08, "loss": 3.2186, "step": 2895000 }, { "epoch": 5.98, "learning_rate": 1.126296460073369e-08, "loss": 3.2222, "step": 2895500 }, { "epoch": 5.98, "learning_rate": 1.0574182518986276e-08, "loss": 3.2133, "step": 2896000 }, { "epoch": 5.99, "learning_rate": 9.885400437238865e-09, "loss": 3.2252, "step": 2896500 }, { "epoch": 5.99, "learning_rate": 9.196618355491451e-09, "loss": 3.2152, "step": 2897000 }, { "epoch": 5.99, "learning_rate": 8.50783627374404e-09, "loss": 3.2165, "step": 2897500 }, { "epoch": 5.99, "learning_rate": 7.819054191996627e-09, "loss": 3.2156, "step": 2898000 }, { "epoch": 5.99, "learning_rate": 7.130272110249215e-09, "loss": 3.2222, "step": 2898500 }, { "epoch": 5.99, "learning_rate": 6.441490028501803e-09, "loss": 3.2237, "step": 2899000 }, { "epoch": 5.99, "learning_rate": 5.7527079467543904e-09, "loss": 3.2178, "step": 2899500 }, { "epoch": 5.99, "learning_rate": 5.0639258650069764e-09, "loss": 3.2146, "step": 2900000 } ], "max_steps": 2903676, "num_train_epochs": 6, "total_flos": 8.904896524175278e+19, "trial_name": null, "trial_params": null }