{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.6095727721406646, "global_step": 590000, "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 } ], "max_steps": 5807346, "num_train_epochs": 6, "total_flos": 1.0271547457536e+19, "trial_name": null, "trial_params": null }