{ "best_metric": null, "best_model_checkpoint": null, "epoch": 4.0, "global_step": 269968, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, "learning_rate": 4.990739643216974e-05, "loss": 2.8507, "step": 500 }, { "epoch": 0.01, "learning_rate": 4.9814792864339485e-05, "loss": 2.7365, "step": 1000 }, { "epoch": 0.02, "learning_rate": 4.972218929650922e-05, "loss": 2.7102, "step": 1500 }, { "epoch": 0.03, "learning_rate": 4.9629585728678954e-05, "loss": 2.7208, "step": 2000 }, { "epoch": 0.04, "learning_rate": 4.953698216084869e-05, "loss": 2.7067, "step": 2500 }, { "epoch": 0.04, "learning_rate": 4.9444378593018436e-05, "loss": 2.6698, "step": 3000 }, { "epoch": 0.05, "learning_rate": 4.9351775025188174e-05, "loss": 2.6546, "step": 3500 }, { "epoch": 0.06, "learning_rate": 4.925917145735791e-05, "loss": 2.6446, "step": 4000 }, { "epoch": 0.07, "learning_rate": 4.916656788952765e-05, "loss": 2.6289, "step": 4500 }, { "epoch": 0.07, "learning_rate": 4.9073964321697394e-05, "loss": 2.6532, "step": 5000 }, { "epoch": 0.08, "learning_rate": 4.8981360753867125e-05, "loss": 2.5513, "step": 5500 }, { "epoch": 0.09, "learning_rate": 4.888875718603686e-05, "loss": 2.5434, "step": 6000 }, { "epoch": 0.1, "learning_rate": 4.87961536182066e-05, "loss": 2.5836, "step": 6500 }, { "epoch": 0.1, "learning_rate": 4.8703550050376345e-05, "loss": 2.5433, "step": 7000 }, { "epoch": 0.11, "learning_rate": 4.861094648254608e-05, "loss": 2.5794, "step": 7500 }, { "epoch": 0.12, "learning_rate": 4.851834291471582e-05, "loss": 2.5457, "step": 8000 }, { "epoch": 0.13, "learning_rate": 4.842573934688556e-05, "loss": 2.5119, "step": 8500 }, { "epoch": 0.13, "learning_rate": 4.83331357790553e-05, "loss": 2.525, "step": 9000 }, { "epoch": 0.14, "learning_rate": 4.8240532211225034e-05, "loss": 2.5471, "step": 9500 }, { "epoch": 0.15, "learning_rate": 4.814792864339477e-05, "loss": 2.5862, "step": 10000 }, { "epoch": 0.16, "learning_rate": 4.805532507556451e-05, "loss": 2.5391, "step": 10500 }, { "epoch": 0.16, "learning_rate": 4.7962721507734254e-05, "loss": 2.5123, "step": 11000 }, { "epoch": 0.17, "learning_rate": 4.787011793990399e-05, "loss": 2.5144, "step": 11500 }, { "epoch": 0.18, "learning_rate": 4.777751437207373e-05, "loss": 2.5659, "step": 12000 }, { "epoch": 0.19, "learning_rate": 4.768491080424347e-05, "loss": 2.5536, "step": 12500 }, { "epoch": 0.19, "learning_rate": 4.7592307236413205e-05, "loss": 2.4725, "step": 13000 }, { "epoch": 0.2, "learning_rate": 4.749970366858294e-05, "loss": 2.4336, "step": 13500 }, { "epoch": 0.21, "learning_rate": 4.740710010075268e-05, "loss": 2.5392, "step": 14000 }, { "epoch": 0.21, "learning_rate": 4.7314496532922425e-05, "loss": 2.4867, "step": 14500 }, { "epoch": 0.22, "learning_rate": 4.722189296509216e-05, "loss": 2.4775, "step": 15000 }, { "epoch": 0.23, "learning_rate": 4.71292893972619e-05, "loss": 2.5399, "step": 15500 }, { "epoch": 0.24, "learning_rate": 4.703668582943164e-05, "loss": 2.4984, "step": 16000 }, { "epoch": 0.24, "learning_rate": 4.6944082261601376e-05, "loss": 2.5248, "step": 16500 }, { "epoch": 0.25, "learning_rate": 4.6851478693771114e-05, "loss": 2.4343, "step": 17000 }, { "epoch": 0.26, "learning_rate": 4.675887512594085e-05, "loss": 2.4473, "step": 17500 }, { "epoch": 0.27, "learning_rate": 4.666627155811059e-05, "loss": 2.455, "step": 18000 }, { "epoch": 0.27, "learning_rate": 4.6573667990280334e-05, "loss": 2.4335, "step": 18500 }, { "epoch": 0.28, "learning_rate": 4.648106442245007e-05, "loss": 2.4983, "step": 19000 }, { "epoch": 0.29, "learning_rate": 4.638846085461981e-05, "loss": 2.4334, "step": 19500 }, { "epoch": 0.3, "learning_rate": 4.629585728678955e-05, "loss": 2.4077, "step": 20000 }, { "epoch": 0.3, "learning_rate": 4.6203253718959285e-05, "loss": 2.4161, "step": 20500 }, { "epoch": 0.31, "learning_rate": 4.611065015112902e-05, "loss": 2.4169, "step": 21000 }, { "epoch": 0.32, "learning_rate": 4.601804658329876e-05, "loss": 2.4123, "step": 21500 }, { "epoch": 0.33, "learning_rate": 4.59254430154685e-05, "loss": 2.4486, "step": 22000 }, { "epoch": 0.33, "learning_rate": 4.583283944763824e-05, "loss": 2.3579, "step": 22500 }, { "epoch": 0.34, "learning_rate": 4.574023587980798e-05, "loss": 2.355, "step": 23000 }, { "epoch": 0.35, "learning_rate": 4.564763231197772e-05, "loss": 2.3947, "step": 23500 }, { "epoch": 0.36, "learning_rate": 4.555502874414746e-05, "loss": 2.4513, "step": 24000 }, { "epoch": 0.36, "learning_rate": 4.5462425176317195e-05, "loss": 2.4414, "step": 24500 }, { "epoch": 0.37, "learning_rate": 4.536982160848693e-05, "loss": 2.4163, "step": 25000 }, { "epoch": 0.38, "learning_rate": 4.527721804065667e-05, "loss": 2.4108, "step": 25500 }, { "epoch": 0.39, "learning_rate": 4.518461447282641e-05, "loss": 2.3692, "step": 26000 }, { "epoch": 0.39, "learning_rate": 4.509201090499615e-05, "loss": 2.4022, "step": 26500 }, { "epoch": 0.4, "learning_rate": 4.499940733716589e-05, "loss": 2.3209, "step": 27000 }, { "epoch": 0.41, "learning_rate": 4.490680376933563e-05, "loss": 2.4336, "step": 27500 }, { "epoch": 0.41, "learning_rate": 4.4814200201505366e-05, "loss": 2.3763, "step": 28000 }, { "epoch": 0.42, "learning_rate": 4.4721596633675104e-05, "loss": 2.4228, "step": 28500 }, { "epoch": 0.43, "learning_rate": 4.462899306584484e-05, "loss": 2.4199, "step": 29000 }, { "epoch": 0.44, "learning_rate": 4.453638949801458e-05, "loss": 2.3636, "step": 29500 }, { "epoch": 0.44, "learning_rate": 4.4443785930184324e-05, "loss": 2.4332, "step": 30000 }, { "epoch": 0.45, "learning_rate": 4.435118236235406e-05, "loss": 2.4513, "step": 30500 }, { "epoch": 0.46, "learning_rate": 4.42585787945238e-05, "loss": 2.3083, "step": 31000 }, { "epoch": 0.47, "learning_rate": 4.416597522669354e-05, "loss": 2.3773, "step": 31500 }, { "epoch": 0.47, "learning_rate": 4.4073371658863275e-05, "loss": 2.3017, "step": 32000 }, { "epoch": 0.48, "learning_rate": 4.398076809103301e-05, "loss": 2.3439, "step": 32500 }, { "epoch": 0.49, "learning_rate": 4.388816452320275e-05, "loss": 2.3497, "step": 33000 }, { "epoch": 0.5, "learning_rate": 4.379556095537249e-05, "loss": 2.3305, "step": 33500 }, { "epoch": 0.5, "learning_rate": 4.370295738754223e-05, "loss": 2.3532, "step": 34000 }, { "epoch": 0.51, "learning_rate": 4.361035381971197e-05, "loss": 2.2562, "step": 34500 }, { "epoch": 0.52, "learning_rate": 4.351775025188171e-05, "loss": 2.3071, "step": 35000 }, { "epoch": 0.53, "learning_rate": 4.3425146684051446e-05, "loss": 2.3573, "step": 35500 }, { "epoch": 0.53, "learning_rate": 4.3332543116221184e-05, "loss": 2.3095, "step": 36000 }, { "epoch": 0.54, "learning_rate": 4.323993954839092e-05, "loss": 2.3321, "step": 36500 }, { "epoch": 0.55, "learning_rate": 4.314733598056066e-05, "loss": 2.2776, "step": 37000 }, { "epoch": 0.56, "learning_rate": 4.30547324127304e-05, "loss": 2.2757, "step": 37500 }, { "epoch": 0.56, "learning_rate": 4.296212884490014e-05, "loss": 2.3101, "step": 38000 }, { "epoch": 0.57, "learning_rate": 4.286952527706988e-05, "loss": 2.3099, "step": 38500 }, { "epoch": 0.58, "learning_rate": 4.277692170923962e-05, "loss": 2.3121, "step": 39000 }, { "epoch": 0.59, "learning_rate": 4.2684318141409355e-05, "loss": 2.3046, "step": 39500 }, { "epoch": 0.59, "learning_rate": 4.259171457357909e-05, "loss": 2.2414, "step": 40000 }, { "epoch": 0.6, "learning_rate": 4.249911100574883e-05, "loss": 2.2979, "step": 40500 }, { "epoch": 0.61, "learning_rate": 4.240650743791857e-05, "loss": 2.2733, "step": 41000 }, { "epoch": 0.61, "learning_rate": 4.2313903870088306e-05, "loss": 2.3319, "step": 41500 }, { "epoch": 0.62, "learning_rate": 4.222130030225805e-05, "loss": 2.3224, "step": 42000 }, { "epoch": 0.63, "learning_rate": 4.212869673442779e-05, "loss": 2.2873, "step": 42500 }, { "epoch": 0.64, "learning_rate": 4.2036093166597526e-05, "loss": 2.3584, "step": 43000 }, { "epoch": 0.64, "learning_rate": 4.1943489598767264e-05, "loss": 2.265, "step": 43500 }, { "epoch": 0.65, "learning_rate": 4.1850886030937e-05, "loss": 2.2914, "step": 44000 }, { "epoch": 0.66, "learning_rate": 4.175828246310674e-05, "loss": 2.2585, "step": 44500 }, { "epoch": 0.67, "learning_rate": 4.166567889527648e-05, "loss": 2.2645, "step": 45000 }, { "epoch": 0.67, "learning_rate": 4.157307532744622e-05, "loss": 2.3289, "step": 45500 }, { "epoch": 0.68, "learning_rate": 4.148047175961596e-05, "loss": 2.2665, "step": 46000 }, { "epoch": 0.69, "learning_rate": 4.13878681917857e-05, "loss": 2.2714, "step": 46500 }, { "epoch": 0.7, "learning_rate": 4.129526462395543e-05, "loss": 2.2622, "step": 47000 }, { "epoch": 0.7, "learning_rate": 4.120266105612517e-05, "loss": 2.2456, "step": 47500 }, { "epoch": 0.71, "learning_rate": 4.111005748829491e-05, "loss": 2.3016, "step": 48000 }, { "epoch": 0.72, "learning_rate": 4.101745392046465e-05, "loss": 2.2608, "step": 48500 }, { "epoch": 0.73, "learning_rate": 4.092485035263439e-05, "loss": 2.2983, "step": 49000 }, { "epoch": 0.73, "learning_rate": 4.083224678480413e-05, "loss": 2.2725, "step": 49500 }, { "epoch": 0.74, "learning_rate": 4.073964321697387e-05, "loss": 2.2304, "step": 50000 }, { "epoch": 0.75, "learning_rate": 4.064703964914361e-05, "loss": 2.3037, "step": 50500 }, { "epoch": 0.76, "learning_rate": 4.055443608131334e-05, "loss": 2.2449, "step": 51000 }, { "epoch": 0.76, "learning_rate": 4.046183251348308e-05, "loss": 2.256, "step": 51500 }, { "epoch": 0.77, "learning_rate": 4.036922894565282e-05, "loss": 2.3002, "step": 52000 }, { "epoch": 0.78, "learning_rate": 4.027662537782256e-05, "loss": 2.2611, "step": 52500 }, { "epoch": 0.79, "learning_rate": 4.0184021809992296e-05, "loss": 2.2351, "step": 53000 }, { "epoch": 0.79, "learning_rate": 4.009141824216204e-05, "loss": 2.2351, "step": 53500 }, { "epoch": 0.8, "learning_rate": 3.999881467433178e-05, "loss": 2.2658, "step": 54000 }, { "epoch": 0.81, "learning_rate": 3.990621110650151e-05, "loss": 2.2394, "step": 54500 }, { "epoch": 0.81, "learning_rate": 3.981360753867125e-05, "loss": 2.2527, "step": 55000 }, { "epoch": 0.82, "learning_rate": 3.972100397084099e-05, "loss": 2.2554, "step": 55500 }, { "epoch": 0.83, "learning_rate": 3.962840040301073e-05, "loss": 2.2116, "step": 56000 }, { "epoch": 0.84, "learning_rate": 3.953579683518047e-05, "loss": 2.2459, "step": 56500 }, { "epoch": 0.84, "learning_rate": 3.9443193267350205e-05, "loss": 2.2093, "step": 57000 }, { "epoch": 0.85, "learning_rate": 3.935058969951995e-05, "loss": 2.2384, "step": 57500 }, { "epoch": 0.86, "learning_rate": 3.925798613168968e-05, "loss": 2.222, "step": 58000 }, { "epoch": 0.87, "learning_rate": 3.916538256385942e-05, "loss": 2.1714, "step": 58500 }, { "epoch": 0.87, "learning_rate": 3.907277899602916e-05, "loss": 2.2678, "step": 59000 }, { "epoch": 0.88, "learning_rate": 3.89801754281989e-05, "loss": 2.259, "step": 59500 }, { "epoch": 0.89, "learning_rate": 3.888757186036864e-05, "loss": 2.1827, "step": 60000 }, { "epoch": 0.9, "learning_rate": 3.8794968292538376e-05, "loss": 2.2199, "step": 60500 }, { "epoch": 0.9, "learning_rate": 3.870236472470812e-05, "loss": 2.1635, "step": 61000 }, { "epoch": 0.91, "learning_rate": 3.860976115687786e-05, "loss": 2.126, "step": 61500 }, { "epoch": 0.92, "learning_rate": 3.851715758904759e-05, "loss": 2.277, "step": 62000 }, { "epoch": 0.93, "learning_rate": 3.842455402121733e-05, "loss": 2.1814, "step": 62500 }, { "epoch": 0.93, "learning_rate": 3.833195045338707e-05, "loss": 2.2185, "step": 63000 }, { "epoch": 0.94, "learning_rate": 3.823934688555681e-05, "loss": 2.1325, "step": 63500 }, { "epoch": 0.95, "learning_rate": 3.814674331772655e-05, "loss": 2.1752, "step": 64000 }, { "epoch": 0.96, "learning_rate": 3.8054139749896285e-05, "loss": 2.2558, "step": 64500 }, { "epoch": 0.96, "learning_rate": 3.796153618206603e-05, "loss": 2.1914, "step": 65000 }, { "epoch": 0.97, "learning_rate": 3.786893261423576e-05, "loss": 2.1828, "step": 65500 }, { "epoch": 0.98, "learning_rate": 3.77763290464055e-05, "loss": 2.1864, "step": 66000 }, { "epoch": 0.99, "learning_rate": 3.7683725478575236e-05, "loss": 2.2374, "step": 66500 }, { "epoch": 0.99, "learning_rate": 3.759112191074498e-05, "loss": 2.2294, "step": 67000 }, { "epoch": 1.0, "learning_rate": 3.749851834291472e-05, "loss": 2.1764, "step": 67500 }, { "epoch": 1.01, "learning_rate": 3.7405914775084456e-05, "loss": 1.8288, "step": 68000 }, { "epoch": 1.01, "learning_rate": 3.7313311207254194e-05, "loss": 1.8335, "step": 68500 }, { "epoch": 1.02, "learning_rate": 3.722070763942393e-05, "loss": 1.789, "step": 69000 }, { "epoch": 1.03, "learning_rate": 3.712810407159367e-05, "loss": 1.8011, "step": 69500 }, { "epoch": 1.04, "learning_rate": 3.703550050376341e-05, "loss": 1.8464, "step": 70000 }, { "epoch": 1.04, "learning_rate": 3.6942896935933145e-05, "loss": 1.9109, "step": 70500 }, { "epoch": 1.05, "learning_rate": 3.685029336810289e-05, "loss": 1.8988, "step": 71000 }, { "epoch": 1.06, "learning_rate": 3.675768980027263e-05, "loss": 1.8336, "step": 71500 }, { "epoch": 1.07, "learning_rate": 3.6665086232442365e-05, "loss": 1.8093, "step": 72000 }, { "epoch": 1.07, "learning_rate": 3.657248266461211e-05, "loss": 1.8718, "step": 72500 }, { "epoch": 1.08, "learning_rate": 3.647987909678184e-05, "loss": 1.8582, "step": 73000 }, { "epoch": 1.09, "learning_rate": 3.638727552895158e-05, "loss": 1.8773, "step": 73500 }, { "epoch": 1.1, "learning_rate": 3.6294671961121317e-05, "loss": 1.845, "step": 74000 }, { "epoch": 1.1, "learning_rate": 3.620206839329106e-05, "loss": 1.8208, "step": 74500 }, { "epoch": 1.11, "learning_rate": 3.61094648254608e-05, "loss": 1.866, "step": 75000 }, { "epoch": 1.12, "learning_rate": 3.601686125763054e-05, "loss": 1.8354, "step": 75500 }, { "epoch": 1.13, "learning_rate": 3.5924257689800274e-05, "loss": 1.874, "step": 76000 }, { "epoch": 1.13, "learning_rate": 3.583165412197001e-05, "loss": 1.8157, "step": 76500 }, { "epoch": 1.14, "learning_rate": 3.573905055413975e-05, "loss": 1.8941, "step": 77000 }, { "epoch": 1.15, "learning_rate": 3.564644698630949e-05, "loss": 1.7856, "step": 77500 }, { "epoch": 1.16, "learning_rate": 3.5553843418479226e-05, "loss": 1.8355, "step": 78000 }, { "epoch": 1.16, "learning_rate": 3.546123985064897e-05, "loss": 1.8542, "step": 78500 }, { "epoch": 1.17, "learning_rate": 3.536863628281871e-05, "loss": 1.8734, "step": 79000 }, { "epoch": 1.18, "learning_rate": 3.5276032714988446e-05, "loss": 1.8471, "step": 79500 }, { "epoch": 1.19, "learning_rate": 3.5183429147158183e-05, "loss": 1.8843, "step": 80000 }, { "epoch": 1.19, "learning_rate": 3.509082557932792e-05, "loss": 1.8549, "step": 80500 }, { "epoch": 1.2, "learning_rate": 3.499822201149766e-05, "loss": 1.8794, "step": 81000 }, { "epoch": 1.21, "learning_rate": 3.49056184436674e-05, "loss": 1.8123, "step": 81500 }, { "epoch": 1.21, "learning_rate": 3.4813014875837135e-05, "loss": 1.9222, "step": 82000 }, { "epoch": 1.22, "learning_rate": 3.472041130800688e-05, "loss": 1.8118, "step": 82500 }, { "epoch": 1.23, "learning_rate": 3.462780774017662e-05, "loss": 1.8444, "step": 83000 }, { "epoch": 1.24, "learning_rate": 3.4535204172346355e-05, "loss": 1.8205, "step": 83500 }, { "epoch": 1.24, "learning_rate": 3.444260060451609e-05, "loss": 1.832, "step": 84000 }, { "epoch": 1.25, "learning_rate": 3.434999703668583e-05, "loss": 1.8681, "step": 84500 }, { "epoch": 1.26, "learning_rate": 3.425739346885557e-05, "loss": 1.8315, "step": 85000 }, { "epoch": 1.27, "learning_rate": 3.4164789901025306e-05, "loss": 1.8455, "step": 85500 }, { "epoch": 1.27, "learning_rate": 3.407218633319505e-05, "loss": 1.8116, "step": 86000 }, { "epoch": 1.28, "learning_rate": 3.397958276536479e-05, "loss": 1.8428, "step": 86500 }, { "epoch": 1.29, "learning_rate": 3.3886979197534526e-05, "loss": 1.8807, "step": 87000 }, { "epoch": 1.3, "learning_rate": 3.3794375629704264e-05, "loss": 1.848, "step": 87500 }, { "epoch": 1.3, "learning_rate": 3.3701772061874e-05, "loss": 1.8763, "step": 88000 }, { "epoch": 1.31, "learning_rate": 3.360916849404374e-05, "loss": 1.8613, "step": 88500 }, { "epoch": 1.32, "learning_rate": 3.351656492621348e-05, "loss": 1.887, "step": 89000 }, { "epoch": 1.33, "learning_rate": 3.3423961358383215e-05, "loss": 1.8228, "step": 89500 }, { "epoch": 1.33, "learning_rate": 3.333135779055296e-05, "loss": 1.8495, "step": 90000 }, { "epoch": 1.34, "learning_rate": 3.32387542227227e-05, "loss": 1.8136, "step": 90500 }, { "epoch": 1.35, "learning_rate": 3.3146150654892435e-05, "loss": 1.8473, "step": 91000 }, { "epoch": 1.36, "learning_rate": 3.305354708706217e-05, "loss": 1.8911, "step": 91500 }, { "epoch": 1.36, "learning_rate": 3.296094351923191e-05, "loss": 1.8469, "step": 92000 }, { "epoch": 1.37, "learning_rate": 3.286833995140165e-05, "loss": 1.8637, "step": 92500 }, { "epoch": 1.38, "learning_rate": 3.2775736383571386e-05, "loss": 1.8833, "step": 93000 }, { "epoch": 1.39, "learning_rate": 3.2683132815741124e-05, "loss": 1.7691, "step": 93500 }, { "epoch": 1.39, "learning_rate": 3.259052924791087e-05, "loss": 1.8607, "step": 94000 }, { "epoch": 1.4, "learning_rate": 3.2497925680080606e-05, "loss": 1.8724, "step": 94500 }, { "epoch": 1.41, "learning_rate": 3.2405322112250344e-05, "loss": 1.857, "step": 95000 }, { "epoch": 1.41, "learning_rate": 3.231271854442008e-05, "loss": 1.8516, "step": 95500 }, { "epoch": 1.42, "learning_rate": 3.222011497658982e-05, "loss": 1.8776, "step": 96000 }, { "epoch": 1.43, "learning_rate": 3.212751140875956e-05, "loss": 1.856, "step": 96500 }, { "epoch": 1.44, "learning_rate": 3.2034907840929295e-05, "loss": 1.8006, "step": 97000 }, { "epoch": 1.44, "learning_rate": 3.194230427309903e-05, "loss": 1.8157, "step": 97500 }, { "epoch": 1.45, "learning_rate": 3.184970070526878e-05, "loss": 1.888, "step": 98000 }, { "epoch": 1.46, "learning_rate": 3.1757097137438515e-05, "loss": 1.7996, "step": 98500 }, { "epoch": 1.47, "learning_rate": 3.166449356960825e-05, "loss": 1.8884, "step": 99000 }, { "epoch": 1.47, "learning_rate": 3.1571890001777984e-05, "loss": 1.8581, "step": 99500 }, { "epoch": 1.48, "learning_rate": 3.147928643394773e-05, "loss": 1.8047, "step": 100000 }, { "epoch": 1.49, "learning_rate": 3.1386682866117467e-05, "loss": 1.782, "step": 100500 }, { "epoch": 1.5, "learning_rate": 3.1294079298287204e-05, "loss": 1.8976, "step": 101000 }, { "epoch": 1.5, "learning_rate": 3.120147573045695e-05, "loss": 1.8875, "step": 101500 }, { "epoch": 1.51, "learning_rate": 3.110887216262669e-05, "loss": 1.8775, "step": 102000 }, { "epoch": 1.52, "learning_rate": 3.1016268594796424e-05, "loss": 1.8253, "step": 102500 }, { "epoch": 1.53, "learning_rate": 3.0923665026966155e-05, "loss": 1.8766, "step": 103000 }, { "epoch": 1.53, "learning_rate": 3.08310614591359e-05, "loss": 1.7809, "step": 103500 }, { "epoch": 1.54, "learning_rate": 3.073845789130564e-05, "loss": 1.8724, "step": 104000 }, { "epoch": 1.55, "learning_rate": 3.0645854323475376e-05, "loss": 1.87, "step": 104500 }, { "epoch": 1.56, "learning_rate": 3.055325075564511e-05, "loss": 1.888, "step": 105000 }, { "epoch": 1.56, "learning_rate": 3.0460647187814855e-05, "loss": 1.804, "step": 105500 }, { "epoch": 1.57, "learning_rate": 3.0368043619984592e-05, "loss": 1.8045, "step": 106000 }, { "epoch": 1.58, "learning_rate": 3.027544005215433e-05, "loss": 1.8211, "step": 106500 }, { "epoch": 1.59, "learning_rate": 3.0182836484324068e-05, "loss": 1.8786, "step": 107000 }, { "epoch": 1.59, "learning_rate": 3.009023291649381e-05, "loss": 1.863, "step": 107500 }, { "epoch": 1.6, "learning_rate": 2.9997629348663547e-05, "loss": 1.8576, "step": 108000 }, { "epoch": 1.61, "learning_rate": 2.9905025780833285e-05, "loss": 1.871, "step": 108500 }, { "epoch": 1.62, "learning_rate": 2.9812422213003022e-05, "loss": 1.8222, "step": 109000 }, { "epoch": 1.62, "learning_rate": 2.9719818645172764e-05, "loss": 1.8619, "step": 109500 }, { "epoch": 1.63, "learning_rate": 2.96272150773425e-05, "loss": 1.8899, "step": 110000 }, { "epoch": 1.64, "learning_rate": 2.953461150951224e-05, "loss": 1.8915, "step": 110500 }, { "epoch": 1.64, "learning_rate": 2.9442007941681977e-05, "loss": 1.8638, "step": 111000 }, { "epoch": 1.65, "learning_rate": 2.9349404373851718e-05, "loss": 1.8411, "step": 111500 }, { "epoch": 1.66, "learning_rate": 2.9256800806021456e-05, "loss": 1.8337, "step": 112000 }, { "epoch": 1.67, "learning_rate": 2.9164197238191194e-05, "loss": 1.8295, "step": 112500 }, { "epoch": 1.67, "learning_rate": 2.907159367036093e-05, "loss": 1.8165, "step": 113000 }, { "epoch": 1.68, "learning_rate": 2.8978990102530673e-05, "loss": 1.7852, "step": 113500 }, { "epoch": 1.69, "learning_rate": 2.888638653470041e-05, "loss": 1.806, "step": 114000 }, { "epoch": 1.7, "learning_rate": 2.8793782966870148e-05, "loss": 1.836, "step": 114500 }, { "epoch": 1.7, "learning_rate": 2.870117939903989e-05, "loss": 1.8174, "step": 115000 }, { "epoch": 1.71, "learning_rate": 2.8608575831209627e-05, "loss": 1.8736, "step": 115500 }, { "epoch": 1.72, "learning_rate": 2.8515972263379365e-05, "loss": 1.8421, "step": 116000 }, { "epoch": 1.73, "learning_rate": 2.8423368695549103e-05, "loss": 1.8666, "step": 116500 }, { "epoch": 1.73, "learning_rate": 2.8330765127718844e-05, "loss": 1.8455, "step": 117000 }, { "epoch": 1.74, "learning_rate": 2.8238161559888582e-05, "loss": 1.8277, "step": 117500 }, { "epoch": 1.75, "learning_rate": 2.814555799205832e-05, "loss": 1.7909, "step": 118000 }, { "epoch": 1.76, "learning_rate": 2.8052954424228057e-05, "loss": 1.7783, "step": 118500 }, { "epoch": 1.76, "learning_rate": 2.79603508563978e-05, "loss": 1.8208, "step": 119000 }, { "epoch": 1.77, "learning_rate": 2.7867747288567536e-05, "loss": 1.8484, "step": 119500 }, { "epoch": 1.78, "learning_rate": 2.7775143720737274e-05, "loss": 1.824, "step": 120000 }, { "epoch": 1.79, "learning_rate": 2.7682540152907012e-05, "loss": 1.8373, "step": 120500 }, { "epoch": 1.79, "learning_rate": 2.7589936585076753e-05, "loss": 1.8155, "step": 121000 }, { "epoch": 1.8, "learning_rate": 2.749733301724649e-05, "loss": 1.7846, "step": 121500 }, { "epoch": 1.81, "learning_rate": 2.740472944941623e-05, "loss": 1.8153, "step": 122000 }, { "epoch": 1.82, "learning_rate": 2.7312125881585966e-05, "loss": 1.8557, "step": 122500 }, { "epoch": 1.82, "learning_rate": 2.7219522313755708e-05, "loss": 1.8372, "step": 123000 }, { "epoch": 1.83, "learning_rate": 2.7126918745925445e-05, "loss": 1.8148, "step": 123500 }, { "epoch": 1.84, "learning_rate": 2.7034315178095183e-05, "loss": 1.7911, "step": 124000 }, { "epoch": 1.84, "learning_rate": 2.694171161026492e-05, "loss": 1.8467, "step": 124500 }, { "epoch": 1.85, "learning_rate": 2.6849108042434662e-05, "loss": 1.8121, "step": 125000 }, { "epoch": 1.86, "learning_rate": 2.67565044746044e-05, "loss": 1.8034, "step": 125500 }, { "epoch": 1.87, "learning_rate": 2.6663900906774138e-05, "loss": 1.7933, "step": 126000 }, { "epoch": 1.87, "learning_rate": 2.6571297338943872e-05, "loss": 1.8018, "step": 126500 }, { "epoch": 1.88, "learning_rate": 2.6478693771113617e-05, "loss": 1.7972, "step": 127000 }, { "epoch": 1.89, "learning_rate": 2.6386090203283354e-05, "loss": 1.8592, "step": 127500 }, { "epoch": 1.9, "learning_rate": 2.6293486635453092e-05, "loss": 1.8192, "step": 128000 }, { "epoch": 1.9, "learning_rate": 2.6200883067622833e-05, "loss": 1.828, "step": 128500 }, { "epoch": 1.91, "learning_rate": 2.610827949979257e-05, "loss": 1.8501, "step": 129000 }, { "epoch": 1.92, "learning_rate": 2.601567593196231e-05, "loss": 1.8408, "step": 129500 }, { "epoch": 1.93, "learning_rate": 2.5923072364132047e-05, "loss": 1.8387, "step": 130000 }, { "epoch": 1.93, "learning_rate": 2.5830468796301788e-05, "loss": 1.8467, "step": 130500 }, { "epoch": 1.94, "learning_rate": 2.5737865228471526e-05, "loss": 1.8348, "step": 131000 }, { "epoch": 1.95, "learning_rate": 2.5645261660641263e-05, "loss": 1.796, "step": 131500 }, { "epoch": 1.96, "learning_rate": 2.5552658092810998e-05, "loss": 1.804, "step": 132000 }, { "epoch": 1.96, "learning_rate": 2.5460054524980742e-05, "loss": 1.7959, "step": 132500 }, { "epoch": 1.97, "learning_rate": 2.536745095715048e-05, "loss": 1.8213, "step": 133000 }, { "epoch": 1.98, "learning_rate": 2.5274847389320218e-05, "loss": 1.7823, "step": 133500 }, { "epoch": 1.99, "learning_rate": 2.5182243821489952e-05, "loss": 1.7913, "step": 134000 }, { "epoch": 1.99, "learning_rate": 2.5089640253659697e-05, "loss": 1.7693, "step": 134500 }, { "epoch": 2.0, "learning_rate": 2.4997036685829435e-05, "loss": 1.797, "step": 135000 }, { "epoch": 2.01, "learning_rate": 2.4904433117999172e-05, "loss": 1.3749, "step": 135500 }, { "epoch": 2.02, "learning_rate": 2.481182955016891e-05, "loss": 1.3449, "step": 136000 }, { "epoch": 2.02, "learning_rate": 2.4719225982338648e-05, "loss": 1.387, "step": 136500 }, { "epoch": 2.03, "learning_rate": 2.462662241450839e-05, "loss": 1.3564, "step": 137000 }, { "epoch": 2.04, "learning_rate": 2.4534018846678124e-05, "loss": 1.3306, "step": 137500 }, { "epoch": 2.04, "learning_rate": 2.4441415278847865e-05, "loss": 1.3972, "step": 138000 }, { "epoch": 2.05, "learning_rate": 2.4348811711017603e-05, "loss": 1.3669, "step": 138500 }, { "epoch": 2.06, "learning_rate": 2.4256208143187344e-05, "loss": 1.4143, "step": 139000 }, { "epoch": 2.07, "learning_rate": 2.4163604575357078e-05, "loss": 1.3784, "step": 139500 }, { "epoch": 2.07, "learning_rate": 2.407100100752682e-05, "loss": 1.3759, "step": 140000 }, { "epoch": 2.08, "learning_rate": 2.3978397439696557e-05, "loss": 1.3384, "step": 140500 }, { "epoch": 2.09, "learning_rate": 2.3885793871866298e-05, "loss": 1.3865, "step": 141000 }, { "epoch": 2.1, "learning_rate": 2.3793190304036033e-05, "loss": 1.3423, "step": 141500 }, { "epoch": 2.1, "learning_rate": 2.3700586736205774e-05, "loss": 1.3576, "step": 142000 }, { "epoch": 2.11, "learning_rate": 2.360798316837551e-05, "loss": 1.3832, "step": 142500 }, { "epoch": 2.12, "learning_rate": 2.351537960054525e-05, "loss": 1.3412, "step": 143000 }, { "epoch": 2.13, "learning_rate": 2.342277603271499e-05, "loss": 1.4008, "step": 143500 }, { "epoch": 2.13, "learning_rate": 2.333017246488473e-05, "loss": 1.4198, "step": 144000 }, { "epoch": 2.14, "learning_rate": 2.323756889705447e-05, "loss": 1.3535, "step": 144500 }, { "epoch": 2.15, "learning_rate": 2.3144965329224204e-05, "loss": 1.4097, "step": 145000 }, { "epoch": 2.16, "learning_rate": 2.3052361761393945e-05, "loss": 1.409, "step": 145500 }, { "epoch": 2.16, "learning_rate": 2.2959758193563683e-05, "loss": 1.4151, "step": 146000 }, { "epoch": 2.17, "learning_rate": 2.2867154625733424e-05, "loss": 1.4083, "step": 146500 }, { "epoch": 2.18, "learning_rate": 2.277455105790316e-05, "loss": 1.4173, "step": 147000 }, { "epoch": 2.19, "learning_rate": 2.26819474900729e-05, "loss": 1.463, "step": 147500 }, { "epoch": 2.19, "learning_rate": 2.2589343922242637e-05, "loss": 1.4193, "step": 148000 }, { "epoch": 2.2, "learning_rate": 2.2496740354412375e-05, "loss": 1.4219, "step": 148500 }, { "epoch": 2.21, "learning_rate": 2.2404136786582113e-05, "loss": 1.3641, "step": 149000 }, { "epoch": 2.22, "learning_rate": 2.2311533218751854e-05, "loss": 1.3905, "step": 149500 }, { "epoch": 2.22, "learning_rate": 2.2218929650921592e-05, "loss": 1.4293, "step": 150000 }, { "epoch": 2.23, "learning_rate": 2.212632608309133e-05, "loss": 1.4548, "step": 150500 }, { "epoch": 2.24, "learning_rate": 2.2033722515261068e-05, "loss": 1.4201, "step": 151000 }, { "epoch": 2.24, "learning_rate": 2.194111894743081e-05, "loss": 1.3813, "step": 151500 }, { "epoch": 2.25, "learning_rate": 2.1848515379600546e-05, "loss": 1.3631, "step": 152000 }, { "epoch": 2.26, "learning_rate": 2.1755911811770284e-05, "loss": 1.4613, "step": 152500 }, { "epoch": 2.27, "learning_rate": 2.1663308243940022e-05, "loss": 1.37, "step": 153000 }, { "epoch": 2.27, "learning_rate": 2.1570704676109763e-05, "loss": 1.4528, "step": 153500 }, { "epoch": 2.28, "learning_rate": 2.14781011082795e-05, "loss": 1.3796, "step": 154000 }, { "epoch": 2.29, "learning_rate": 2.138549754044924e-05, "loss": 1.4019, "step": 154500 }, { "epoch": 2.3, "learning_rate": 2.1292893972618977e-05, "loss": 1.3995, "step": 155000 }, { "epoch": 2.3, "learning_rate": 2.1200290404788718e-05, "loss": 1.3776, "step": 155500 }, { "epoch": 2.31, "learning_rate": 2.1107686836958456e-05, "loss": 1.4263, "step": 156000 }, { "epoch": 2.32, "learning_rate": 2.1015083269128193e-05, "loss": 1.395, "step": 156500 }, { "epoch": 2.33, "learning_rate": 2.092247970129793e-05, "loss": 1.3474, "step": 157000 }, { "epoch": 2.33, "learning_rate": 2.0829876133467672e-05, "loss": 1.3742, "step": 157500 }, { "epoch": 2.34, "learning_rate": 2.073727256563741e-05, "loss": 1.4322, "step": 158000 }, { "epoch": 2.35, "learning_rate": 2.0644668997807148e-05, "loss": 1.3475, "step": 158500 }, { "epoch": 2.36, "learning_rate": 2.055206542997689e-05, "loss": 1.3618, "step": 159000 }, { "epoch": 2.36, "learning_rate": 2.0459461862146627e-05, "loss": 1.3992, "step": 159500 }, { "epoch": 2.37, "learning_rate": 2.0366858294316365e-05, "loss": 1.4042, "step": 160000 }, { "epoch": 2.38, "learning_rate": 2.0274254726486102e-05, "loss": 1.4052, "step": 160500 }, { "epoch": 2.39, "learning_rate": 2.0181651158655844e-05, "loss": 1.4609, "step": 161000 }, { "epoch": 2.39, "learning_rate": 2.008904759082558e-05, "loss": 1.4281, "step": 161500 }, { "epoch": 2.4, "learning_rate": 1.999644402299532e-05, "loss": 1.4165, "step": 162000 }, { "epoch": 2.41, "learning_rate": 1.9903840455165057e-05, "loss": 1.383, "step": 162500 }, { "epoch": 2.42, "learning_rate": 1.9811236887334798e-05, "loss": 1.3725, "step": 163000 }, { "epoch": 2.42, "learning_rate": 1.9718633319504536e-05, "loss": 1.3656, "step": 163500 }, { "epoch": 2.43, "learning_rate": 1.9626029751674274e-05, "loss": 1.4094, "step": 164000 }, { "epoch": 2.44, "learning_rate": 1.953342618384401e-05, "loss": 1.4369, "step": 164500 }, { "epoch": 2.44, "learning_rate": 1.9440822616013753e-05, "loss": 1.4073, "step": 165000 }, { "epoch": 2.45, "learning_rate": 1.9348219048183487e-05, "loss": 1.3785, "step": 165500 }, { "epoch": 2.46, "learning_rate": 1.9255615480353228e-05, "loss": 1.4189, "step": 166000 }, { "epoch": 2.47, "learning_rate": 1.9163011912522966e-05, "loss": 1.3908, "step": 166500 }, { "epoch": 2.47, "learning_rate": 1.9070408344692707e-05, "loss": 1.414, "step": 167000 }, { "epoch": 2.48, "learning_rate": 1.897780477686244e-05, "loss": 1.3761, "step": 167500 }, { "epoch": 2.49, "learning_rate": 1.8885201209032183e-05, "loss": 1.4145, "step": 168000 }, { "epoch": 2.5, "learning_rate": 1.879259764120192e-05, "loss": 1.425, "step": 168500 }, { "epoch": 2.5, "learning_rate": 1.869999407337166e-05, "loss": 1.4359, "step": 169000 }, { "epoch": 2.51, "learning_rate": 1.8607390505541396e-05, "loss": 1.3791, "step": 169500 }, { "epoch": 2.52, "learning_rate": 1.8514786937711137e-05, "loss": 1.3784, "step": 170000 }, { "epoch": 2.53, "learning_rate": 1.8422183369880875e-05, "loss": 1.4094, "step": 170500 }, { "epoch": 2.53, "learning_rate": 1.8329579802050613e-05, "loss": 1.4048, "step": 171000 }, { "epoch": 2.54, "learning_rate": 1.8236976234220354e-05, "loss": 1.4183, "step": 171500 }, { "epoch": 2.55, "learning_rate": 1.8144372666390092e-05, "loss": 1.3787, "step": 172000 }, { "epoch": 2.56, "learning_rate": 1.8051769098559833e-05, "loss": 1.4246, "step": 172500 }, { "epoch": 2.56, "learning_rate": 1.7959165530729567e-05, "loss": 1.3803, "step": 173000 }, { "epoch": 2.57, "learning_rate": 1.786656196289931e-05, "loss": 1.4329, "step": 173500 }, { "epoch": 2.58, "learning_rate": 1.7773958395069046e-05, "loss": 1.3802, "step": 174000 }, { "epoch": 2.59, "learning_rate": 1.7681354827238787e-05, "loss": 1.3925, "step": 174500 }, { "epoch": 2.59, "learning_rate": 1.7588751259408522e-05, "loss": 1.3817, "step": 175000 }, { "epoch": 2.6, "learning_rate": 1.7496147691578263e-05, "loss": 1.3918, "step": 175500 }, { "epoch": 2.61, "learning_rate": 1.7403544123748e-05, "loss": 1.4201, "step": 176000 }, { "epoch": 2.62, "learning_rate": 1.731094055591774e-05, "loss": 1.4103, "step": 176500 }, { "epoch": 2.62, "learning_rate": 1.7218336988087476e-05, "loss": 1.4312, "step": 177000 }, { "epoch": 2.63, "learning_rate": 1.7125733420257218e-05, "loss": 1.3746, "step": 177500 }, { "epoch": 2.64, "learning_rate": 1.7033129852426955e-05, "loss": 1.4273, "step": 178000 }, { "epoch": 2.64, "learning_rate": 1.6940526284596693e-05, "loss": 1.3886, "step": 178500 }, { "epoch": 2.65, "learning_rate": 1.684792271676643e-05, "loss": 1.3741, "step": 179000 }, { "epoch": 2.66, "learning_rate": 1.6755319148936172e-05, "loss": 1.3609, "step": 179500 }, { "epoch": 2.67, "learning_rate": 1.666271558110591e-05, "loss": 1.3623, "step": 180000 }, { "epoch": 2.67, "learning_rate": 1.6570112013275648e-05, "loss": 1.3889, "step": 180500 }, { "epoch": 2.68, "learning_rate": 1.6477508445445385e-05, "loss": 1.448, "step": 181000 }, { "epoch": 2.69, "learning_rate": 1.6384904877615127e-05, "loss": 1.3549, "step": 181500 }, { "epoch": 2.7, "learning_rate": 1.6292301309784864e-05, "loss": 1.4019, "step": 182000 }, { "epoch": 2.7, "learning_rate": 1.6199697741954602e-05, "loss": 1.3859, "step": 182500 }, { "epoch": 2.71, "learning_rate": 1.610709417412434e-05, "loss": 1.3908, "step": 183000 }, { "epoch": 2.72, "learning_rate": 1.601449060629408e-05, "loss": 1.3679, "step": 183500 }, { "epoch": 2.73, "learning_rate": 1.592188703846382e-05, "loss": 1.359, "step": 184000 }, { "epoch": 2.73, "learning_rate": 1.5829283470633557e-05, "loss": 1.3884, "step": 184500 }, { "epoch": 2.74, "learning_rate": 1.5736679902803294e-05, "loss": 1.3703, "step": 185000 }, { "epoch": 2.75, "learning_rate": 1.5644076334973036e-05, "loss": 1.3434, "step": 185500 }, { "epoch": 2.76, "learning_rate": 1.5551472767142773e-05, "loss": 1.3662, "step": 186000 }, { "epoch": 2.76, "learning_rate": 1.545886919931251e-05, "loss": 1.4051, "step": 186500 }, { "epoch": 2.77, "learning_rate": 1.5366265631482252e-05, "loss": 1.4064, "step": 187000 }, { "epoch": 2.78, "learning_rate": 1.527366206365199e-05, "loss": 1.3615, "step": 187500 }, { "epoch": 2.79, "learning_rate": 1.518105849582173e-05, "loss": 1.3496, "step": 188000 }, { "epoch": 2.79, "learning_rate": 1.5088454927991466e-05, "loss": 1.4558, "step": 188500 }, { "epoch": 2.8, "learning_rate": 1.4995851360161205e-05, "loss": 1.3331, "step": 189000 }, { "epoch": 2.81, "learning_rate": 1.4903247792330943e-05, "loss": 1.3776, "step": 189500 }, { "epoch": 2.82, "learning_rate": 1.4810644224500682e-05, "loss": 1.3912, "step": 190000 }, { "epoch": 2.82, "learning_rate": 1.471804065667042e-05, "loss": 1.3816, "step": 190500 }, { "epoch": 2.83, "learning_rate": 1.462543708884016e-05, "loss": 1.3897, "step": 191000 }, { "epoch": 2.84, "learning_rate": 1.4532833521009898e-05, "loss": 1.3831, "step": 191500 }, { "epoch": 2.84, "learning_rate": 1.4440229953179637e-05, "loss": 1.3954, "step": 192000 }, { "epoch": 2.85, "learning_rate": 1.4347626385349375e-05, "loss": 1.383, "step": 192500 }, { "epoch": 2.86, "learning_rate": 1.4255022817519114e-05, "loss": 1.3408, "step": 193000 }, { "epoch": 2.87, "learning_rate": 1.4162419249688852e-05, "loss": 1.3996, "step": 193500 }, { "epoch": 2.87, "learning_rate": 1.4069815681858592e-05, "loss": 1.3653, "step": 194000 }, { "epoch": 2.88, "learning_rate": 1.397721211402833e-05, "loss": 1.4181, "step": 194500 }, { "epoch": 2.89, "learning_rate": 1.3884608546198069e-05, "loss": 1.3542, "step": 195000 }, { "epoch": 2.9, "learning_rate": 1.3792004978367807e-05, "loss": 1.3785, "step": 195500 }, { "epoch": 2.9, "learning_rate": 1.3699401410537546e-05, "loss": 1.4211, "step": 196000 }, { "epoch": 2.91, "learning_rate": 1.3606797842707284e-05, "loss": 1.3833, "step": 196500 }, { "epoch": 2.92, "learning_rate": 1.3514194274877023e-05, "loss": 1.3677, "step": 197000 }, { "epoch": 2.93, "learning_rate": 1.3421590707046761e-05, "loss": 1.4014, "step": 197500 }, { "epoch": 2.93, "learning_rate": 1.33289871392165e-05, "loss": 1.408, "step": 198000 }, { "epoch": 2.94, "learning_rate": 1.3236383571386238e-05, "loss": 1.3761, "step": 198500 }, { "epoch": 2.95, "learning_rate": 1.3143780003555978e-05, "loss": 1.412, "step": 199000 }, { "epoch": 2.96, "learning_rate": 1.3051176435725716e-05, "loss": 1.3706, "step": 199500 }, { "epoch": 2.96, "learning_rate": 1.2958572867895455e-05, "loss": 1.3831, "step": 200000 }, { "epoch": 2.97, "learning_rate": 1.2865969300065195e-05, "loss": 1.3469, "step": 200500 }, { "epoch": 2.98, "learning_rate": 1.2773365732234932e-05, "loss": 1.3403, "step": 201000 }, { "epoch": 2.99, "learning_rate": 1.2680762164404672e-05, "loss": 1.3783, "step": 201500 }, { "epoch": 2.99, "learning_rate": 1.258815859657441e-05, "loss": 1.3897, "step": 202000 }, { "epoch": 3.0, "learning_rate": 1.2495555028744147e-05, "loss": 1.3974, "step": 202500 }, { "epoch": 3.01, "learning_rate": 1.2402951460913887e-05, "loss": 0.9791, "step": 203000 }, { "epoch": 3.02, "learning_rate": 1.2310347893083625e-05, "loss": 0.9923, "step": 203500 }, { "epoch": 3.02, "learning_rate": 1.2217744325253364e-05, "loss": 0.9658, "step": 204000 }, { "epoch": 3.03, "learning_rate": 1.2125140757423102e-05, "loss": 1.0327, "step": 204500 }, { "epoch": 3.04, "learning_rate": 1.2032537189592841e-05, "loss": 0.9956, "step": 205000 }, { "epoch": 3.04, "learning_rate": 1.193993362176258e-05, "loss": 0.9618, "step": 205500 }, { "epoch": 3.05, "learning_rate": 1.1847330053932319e-05, "loss": 0.9582, "step": 206000 }, { "epoch": 3.06, "learning_rate": 1.1754726486102056e-05, "loss": 1.002, "step": 206500 }, { "epoch": 3.07, "learning_rate": 1.1662122918271796e-05, "loss": 0.959, "step": 207000 }, { "epoch": 3.07, "learning_rate": 1.1569519350441535e-05, "loss": 0.9495, "step": 207500 }, { "epoch": 3.08, "learning_rate": 1.1476915782611273e-05, "loss": 1.016, "step": 208000 }, { "epoch": 3.09, "learning_rate": 1.1384312214781013e-05, "loss": 1.0179, "step": 208500 }, { "epoch": 3.1, "learning_rate": 1.129170864695075e-05, "loss": 0.9873, "step": 209000 }, { "epoch": 3.1, "learning_rate": 1.119910507912049e-05, "loss": 1.0094, "step": 209500 }, { "epoch": 3.11, "learning_rate": 1.1106501511290228e-05, "loss": 0.9773, "step": 210000 }, { "epoch": 3.12, "learning_rate": 1.1013897943459967e-05, "loss": 1.004, "step": 210500 }, { "epoch": 3.13, "learning_rate": 1.0921294375629705e-05, "loss": 0.9712, "step": 211000 }, { "epoch": 3.13, "learning_rate": 1.0828690807799444e-05, "loss": 0.9503, "step": 211500 }, { "epoch": 3.14, "learning_rate": 1.0736087239969182e-05, "loss": 1.0044, "step": 212000 }, { "epoch": 3.15, "learning_rate": 1.064348367213892e-05, "loss": 0.9697, "step": 212500 }, { "epoch": 3.16, "learning_rate": 1.055088010430866e-05, "loss": 0.9893, "step": 213000 }, { "epoch": 3.16, "learning_rate": 1.0458276536478397e-05, "loss": 1.028, "step": 213500 }, { "epoch": 3.17, "learning_rate": 1.0365672968648137e-05, "loss": 0.972, "step": 214000 }, { "epoch": 3.18, "learning_rate": 1.0273069400817875e-05, "loss": 0.975, "step": 214500 }, { "epoch": 3.19, "learning_rate": 1.0180465832987614e-05, "loss": 0.9553, "step": 215000 }, { "epoch": 3.19, "learning_rate": 1.0087862265157352e-05, "loss": 0.9977, "step": 215500 }, { "epoch": 3.2, "learning_rate": 9.995258697327091e-06, "loss": 1.0038, "step": 216000 }, { "epoch": 3.21, "learning_rate": 9.902655129496829e-06, "loss": 0.9956, "step": 216500 }, { "epoch": 3.22, "learning_rate": 9.810051561666569e-06, "loss": 0.975, "step": 217000 }, { "epoch": 3.22, "learning_rate": 9.717447993836306e-06, "loss": 0.9638, "step": 217500 }, { "epoch": 3.23, "learning_rate": 9.624844426006046e-06, "loss": 0.9551, "step": 218000 }, { "epoch": 3.24, "learning_rate": 9.532240858175784e-06, "loss": 0.9791, "step": 218500 }, { "epoch": 3.24, "learning_rate": 9.439637290345523e-06, "loss": 1.015, "step": 219000 }, { "epoch": 3.25, "learning_rate": 9.347033722515261e-06, "loss": 0.9465, "step": 219500 }, { "epoch": 3.26, "learning_rate": 9.254430154685e-06, "loss": 0.9856, "step": 220000 }, { "epoch": 3.27, "learning_rate": 9.161826586854738e-06, "loss": 0.9704, "step": 220500 }, { "epoch": 3.27, "learning_rate": 9.069223019024476e-06, "loss": 0.9467, "step": 221000 }, { "epoch": 3.28, "learning_rate": 8.976619451194217e-06, "loss": 0.9747, "step": 221500 }, { "epoch": 3.29, "learning_rate": 8.884015883363955e-06, "loss": 0.9979, "step": 222000 }, { "epoch": 3.3, "learning_rate": 8.791412315533694e-06, "loss": 0.9839, "step": 222500 }, { "epoch": 3.3, "learning_rate": 8.698808747703432e-06, "loss": 0.9905, "step": 223000 }, { "epoch": 3.31, "learning_rate": 8.606205179873172e-06, "loss": 1.0233, "step": 223500 }, { "epoch": 3.32, "learning_rate": 8.51360161204291e-06, "loss": 1.0214, "step": 224000 }, { "epoch": 3.33, "learning_rate": 8.420998044212649e-06, "loss": 0.9928, "step": 224500 }, { "epoch": 3.33, "learning_rate": 8.328394476382387e-06, "loss": 0.98, "step": 225000 }, { "epoch": 3.34, "learning_rate": 8.235790908552126e-06, "loss": 0.9924, "step": 225500 }, { "epoch": 3.35, "learning_rate": 8.143187340721864e-06, "loss": 1.0215, "step": 226000 }, { "epoch": 3.36, "learning_rate": 8.050583772891602e-06, "loss": 0.957, "step": 226500 }, { "epoch": 3.36, "learning_rate": 7.957980205061341e-06, "loss": 0.988, "step": 227000 }, { "epoch": 3.37, "learning_rate": 7.865376637231079e-06, "loss": 0.9771, "step": 227500 }, { "epoch": 3.38, "learning_rate": 7.772773069400818e-06, "loss": 0.9663, "step": 228000 }, { "epoch": 3.39, "learning_rate": 7.680169501570556e-06, "loss": 0.9971, "step": 228500 }, { "epoch": 3.39, "learning_rate": 7.587565933740296e-06, "loss": 0.9708, "step": 229000 }, { "epoch": 3.4, "learning_rate": 7.494962365910034e-06, "loss": 0.9741, "step": 229500 }, { "epoch": 3.41, "learning_rate": 7.402358798079773e-06, "loss": 0.9427, "step": 230000 }, { "epoch": 3.42, "learning_rate": 7.309755230249511e-06, "loss": 1.0002, "step": 230500 }, { "epoch": 3.42, "learning_rate": 7.2171516624192494e-06, "loss": 0.9685, "step": 231000 }, { "epoch": 3.43, "learning_rate": 7.124548094588988e-06, "loss": 0.9676, "step": 231500 }, { "epoch": 3.44, "learning_rate": 7.031944526758727e-06, "loss": 0.9527, "step": 232000 }, { "epoch": 3.44, "learning_rate": 6.939340958928465e-06, "loss": 0.9675, "step": 232500 }, { "epoch": 3.45, "learning_rate": 6.846737391098204e-06, "loss": 0.9852, "step": 233000 }, { "epoch": 3.46, "learning_rate": 6.754133823267943e-06, "loss": 0.9607, "step": 233500 }, { "epoch": 3.47, "learning_rate": 6.661530255437681e-06, "loss": 0.9526, "step": 234000 }, { "epoch": 3.47, "learning_rate": 6.56892668760742e-06, "loss": 0.9592, "step": 234500 }, { "epoch": 3.48, "learning_rate": 6.4763231197771585e-06, "loss": 0.9227, "step": 235000 }, { "epoch": 3.49, "learning_rate": 6.383719551946897e-06, "loss": 0.9842, "step": 235500 }, { "epoch": 3.5, "learning_rate": 6.291115984116637e-06, "loss": 0.9649, "step": 236000 }, { "epoch": 3.5, "learning_rate": 6.198512416286375e-06, "loss": 0.9231, "step": 236500 }, { "epoch": 3.51, "learning_rate": 6.105908848456114e-06, "loss": 0.9331, "step": 237000 }, { "epoch": 3.52, "learning_rate": 6.013305280625852e-06, "loss": 0.9748, "step": 237500 }, { "epoch": 3.53, "learning_rate": 5.92070171279559e-06, "loss": 0.9471, "step": 238000 }, { "epoch": 3.53, "learning_rate": 5.828098144965329e-06, "loss": 0.9819, "step": 238500 }, { "epoch": 3.54, "learning_rate": 5.7354945771350676e-06, "loss": 0.9898, "step": 239000 }, { "epoch": 3.55, "learning_rate": 5.642891009304807e-06, "loss": 0.9692, "step": 239500 }, { "epoch": 3.56, "learning_rate": 5.550287441474546e-06, "loss": 0.9939, "step": 240000 }, { "epoch": 3.56, "learning_rate": 5.457683873644284e-06, "loss": 0.9903, "step": 240500 }, { "epoch": 3.57, "learning_rate": 5.365080305814023e-06, "loss": 0.9671, "step": 241000 }, { "epoch": 3.58, "learning_rate": 5.2724767379837616e-06, "loss": 0.9527, "step": 241500 }, { "epoch": 3.59, "learning_rate": 5.1798731701535e-06, "loss": 0.9644, "step": 242000 }, { "epoch": 3.59, "learning_rate": 5.087269602323239e-06, "loss": 0.9809, "step": 242500 }, { "epoch": 3.6, "learning_rate": 4.9946660344929775e-06, "loss": 0.9401, "step": 243000 }, { "epoch": 3.61, "learning_rate": 4.902062466662716e-06, "loss": 0.9661, "step": 243500 }, { "epoch": 3.62, "learning_rate": 4.809458898832455e-06, "loss": 0.9696, "step": 244000 }, { "epoch": 3.62, "learning_rate": 4.7168553310021925e-06, "loss": 0.959, "step": 244500 }, { "epoch": 3.63, "learning_rate": 4.624251763171931e-06, "loss": 0.9661, "step": 245000 }, { "epoch": 3.64, "learning_rate": 4.53164819534167e-06, "loss": 0.9654, "step": 245500 }, { "epoch": 3.64, "learning_rate": 4.439044627511408e-06, "loss": 0.9804, "step": 246000 }, { "epoch": 3.65, "learning_rate": 4.346441059681148e-06, "loss": 0.9792, "step": 246500 }, { "epoch": 3.66, "learning_rate": 4.2538374918508865e-06, "loss": 0.8952, "step": 247000 }, { "epoch": 3.67, "learning_rate": 4.161233924020625e-06, "loss": 0.9645, "step": 247500 }, { "epoch": 3.67, "learning_rate": 4.068630356190364e-06, "loss": 0.9889, "step": 248000 }, { "epoch": 3.68, "learning_rate": 3.976026788360102e-06, "loss": 0.9172, "step": 248500 }, { "epoch": 3.69, "learning_rate": 3.883423220529841e-06, "loss": 0.9503, "step": 249000 }, { "epoch": 3.7, "learning_rate": 3.7908196526995792e-06, "loss": 0.9454, "step": 249500 }, { "epoch": 3.7, "learning_rate": 3.698216084869318e-06, "loss": 0.9557, "step": 250000 }, { "epoch": 3.71, "learning_rate": 3.6056125170390565e-06, "loss": 0.9833, "step": 250500 }, { "epoch": 3.72, "learning_rate": 3.513008949208795e-06, "loss": 0.9378, "step": 251000 }, { "epoch": 3.73, "learning_rate": 3.4204053813785338e-06, "loss": 0.9718, "step": 251500 }, { "epoch": 3.73, "learning_rate": 3.3278018135482724e-06, "loss": 0.9639, "step": 252000 }, { "epoch": 3.74, "learning_rate": 3.235198245718011e-06, "loss": 0.9254, "step": 252500 }, { "epoch": 3.75, "learning_rate": 3.1425946778877497e-06, "loss": 1.0007, "step": 253000 }, { "epoch": 3.76, "learning_rate": 3.0499911100574883e-06, "loss": 0.968, "step": 253500 }, { "epoch": 3.76, "learning_rate": 2.957387542227227e-06, "loss": 0.9663, "step": 254000 }, { "epoch": 3.77, "learning_rate": 2.8647839743969656e-06, "loss": 0.9838, "step": 254500 }, { "epoch": 3.78, "learning_rate": 2.772180406566704e-06, "loss": 0.9547, "step": 255000 }, { "epoch": 3.79, "learning_rate": 2.6795768387364432e-06, "loss": 0.9677, "step": 255500 }, { "epoch": 3.79, "learning_rate": 2.586973270906182e-06, "loss": 0.9753, "step": 256000 }, { "epoch": 3.8, "learning_rate": 2.49436970307592e-06, "loss": 0.9834, "step": 256500 }, { "epoch": 3.81, "learning_rate": 2.4017661352456587e-06, "loss": 0.9809, "step": 257000 }, { "epoch": 3.82, "learning_rate": 2.3091625674153974e-06, "loss": 0.9584, "step": 257500 }, { "epoch": 3.82, "learning_rate": 2.216558999585136e-06, "loss": 0.9321, "step": 258000 }, { "epoch": 3.83, "learning_rate": 2.1239554317548746e-06, "loss": 0.944, "step": 258500 }, { "epoch": 3.84, "learning_rate": 2.0313518639246137e-06, "loss": 0.9592, "step": 259000 }, { "epoch": 3.84, "learning_rate": 1.9387482960943523e-06, "loss": 0.96, "step": 259500 }, { "epoch": 3.85, "learning_rate": 1.8461447282640907e-06, "loss": 0.9804, "step": 260000 }, { "epoch": 3.86, "learning_rate": 1.7535411604338294e-06, "loss": 0.9617, "step": 260500 }, { "epoch": 3.87, "learning_rate": 1.6609375926035678e-06, "loss": 0.9234, "step": 261000 }, { "epoch": 3.87, "learning_rate": 1.5683340247733064e-06, "loss": 0.965, "step": 261500 }, { "epoch": 3.88, "learning_rate": 1.4757304569430452e-06, "loss": 0.9286, "step": 262000 }, { "epoch": 3.89, "learning_rate": 1.3831268891127839e-06, "loss": 0.9899, "step": 262500 }, { "epoch": 3.9, "learning_rate": 1.2905233212825223e-06, "loss": 0.9527, "step": 263000 }, { "epoch": 3.9, "learning_rate": 1.1979197534522611e-06, "loss": 0.9387, "step": 263500 }, { "epoch": 3.91, "learning_rate": 1.1053161856219998e-06, "loss": 0.9385, "step": 264000 }, { "epoch": 3.92, "learning_rate": 1.0127126177917382e-06, "loss": 0.976, "step": 264500 }, { "epoch": 3.93, "learning_rate": 9.20109049961477e-07, "loss": 0.9702, "step": 265000 }, { "epoch": 3.93, "learning_rate": 8.275054821312157e-07, "loss": 0.9343, "step": 265500 }, { "epoch": 3.94, "learning_rate": 7.349019143009542e-07, "loss": 0.9258, "step": 266000 }, { "epoch": 3.95, "learning_rate": 6.422983464706928e-07, "loss": 0.9513, "step": 266500 }, { "epoch": 3.96, "learning_rate": 5.496947786404315e-07, "loss": 0.9689, "step": 267000 }, { "epoch": 3.96, "learning_rate": 4.5709121081017015e-07, "loss": 0.9296, "step": 267500 }, { "epoch": 3.97, "learning_rate": 3.644876429799088e-07, "loss": 0.9628, "step": 268000 }, { "epoch": 3.98, "learning_rate": 2.7188407514964736e-07, "loss": 0.9392, "step": 268500 }, { "epoch": 3.99, "learning_rate": 1.7928050731938602e-07, "loss": 0.9467, "step": 269000 }, { "epoch": 3.99, "learning_rate": 8.667693948912465e-08, "loss": 0.9457, "step": 269500 }, { "epoch": 4.0, "step": 269968, "total_flos": 2.914340112407593e+17, "train_loss": 1.6431024962071243, "train_runtime": 97099.2276, "train_samples_per_second": 2.78, "train_steps_per_second": 2.78 } ], "max_steps": 269968, "num_train_epochs": 4, "total_flos": 2.914340112407593e+17, "trial_name": null, "trial_params": null }