{ "best_metric": 1.4319051504135132, "best_model_checkpoint": "/content/drive/MyDrive/Graduation_Models/Question_Answering_Model/res/checkpoint-79622", "epoch": 5.0, "eval_steps": 500, "global_step": 199055, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 2e-05, "loss": 2.2451, "step": 100 }, { "epoch": 0.01, "learning_rate": 1.9999987533057874e-05, "loss": 1.9234, "step": 200 }, { "epoch": 0.01, "learning_rate": 1.9999951124629742e-05, "loss": 2.248, "step": 300 }, { "epoch": 0.01, "learning_rate": 1.999988928874841e-05, "loss": 2.1223, "step": 400 }, { "epoch": 0.01, "learning_rate": 1.9999802519258868e-05, "loss": 2.0712, "step": 500 }, { "epoch": 0.02, "learning_rate": 1.9999690816377467e-05, "loss": 2.3141, "step": 600 }, { "epoch": 0.02, "learning_rate": 1.9999554180382722e-05, "loss": 2.0641, "step": 700 }, { "epoch": 0.02, "learning_rate": 1.9999392611615324e-05, "loss": 2.0248, "step": 800 }, { "epoch": 0.02, "learning_rate": 1.9999206110478127e-05, "loss": 2.0396, "step": 900 }, { "epoch": 0.03, "learning_rate": 1.999899467743615e-05, "loss": 2.0182, "step": 1000 }, { "epoch": 0.03, "learning_rate": 1.9998758313016578e-05, "loss": 1.9715, "step": 1100 }, { "epoch": 0.03, "learning_rate": 1.9998497017808756e-05, "loss": 1.934, "step": 1200 }, { "epoch": 0.03, "learning_rate": 1.9998210792464193e-05, "loss": 2.0502, "step": 1300 }, { "epoch": 0.04, "learning_rate": 1.999789963769657e-05, "loss": 2.0179, "step": 1400 }, { "epoch": 0.04, "learning_rate": 1.9997563554281707e-05, "loss": 1.9943, "step": 1500 }, { "epoch": 0.04, "learning_rate": 1.999720254305759e-05, "loss": 2.0179, "step": 1600 }, { "epoch": 0.04, "learning_rate": 1.9996816604924373e-05, "loss": 1.9542, "step": 1700 }, { "epoch": 0.05, "learning_rate": 1.9996405740844334e-05, "loss": 2.0787, "step": 1800 }, { "epoch": 0.05, "learning_rate": 1.9995969951841926e-05, "loss": 2.1958, "step": 1900 }, { "epoch": 0.05, "learning_rate": 1.999550923900374e-05, "loss": 2.0362, "step": 2000 }, { "epoch": 0.05, "learning_rate": 1.9995023603478503e-05, "loss": 2.1523, "step": 2100 }, { "epoch": 0.06, "learning_rate": 1.9994513046477103e-05, "loss": 2.0725, "step": 2200 }, { "epoch": 0.06, "learning_rate": 1.9993977569272557e-05, "loss": 2.0911, "step": 2300 }, { "epoch": 0.06, "learning_rate": 1.9993422900504597e-05, "loss": 1.9009, "step": 2400 }, { "epoch": 0.06, "learning_rate": 1.9992837836128927e-05, "loss": 1.8365, "step": 2500 }, { "epoch": 0.07, "learning_rate": 1.9992227855727058e-05, "loss": 1.7446, "step": 2600 }, { "epoch": 0.07, "learning_rate": 1.9991592960819906e-05, "loss": 2.0005, "step": 2700 }, { "epoch": 0.07, "learning_rate": 1.9990933152990514e-05, "loss": 1.8915, "step": 2800 }, { "epoch": 0.07, "learning_rate": 1.9990248433884037e-05, "loss": 1.9823, "step": 2900 }, { "epoch": 0.08, "learning_rate": 1.9989538805207744e-05, "loss": 1.8206, "step": 3000 }, { "epoch": 0.08, "learning_rate": 1.998880426873102e-05, "loss": 1.811, "step": 3100 }, { "epoch": 0.08, "learning_rate": 1.998804482628535e-05, "loss": 1.7352, "step": 3200 }, { "epoch": 0.08, "learning_rate": 1.998726047976431e-05, "loss": 1.9674, "step": 3300 }, { "epoch": 0.09, "learning_rate": 1.998645123112359e-05, "loss": 1.7651, "step": 3400 }, { "epoch": 0.09, "learning_rate": 1.9985625547117113e-05, "loss": 1.9179, "step": 3500 }, { "epoch": 0.09, "learning_rate": 1.9984766749322143e-05, "loss": 1.7219, "step": 3600 }, { "epoch": 0.09, "learning_rate": 1.998388305562533e-05, "loss": 1.948, "step": 3700 }, { "epoch": 0.1, "learning_rate": 1.9982974468230066e-05, "loss": 1.6361, "step": 3800 }, { "epoch": 0.1, "learning_rate": 1.998204098940181e-05, "loss": 1.9303, "step": 3900 }, { "epoch": 0.1, "learning_rate": 1.9981082621468085e-05, "loss": 1.9764, "step": 4000 }, { "epoch": 0.1, "learning_rate": 1.998009936681848e-05, "loss": 2.0724, "step": 4100 }, { "epoch": 0.11, "learning_rate": 1.9979091227904628e-05, "loss": 1.8869, "step": 4200 }, { "epoch": 0.11, "learning_rate": 1.997805820724021e-05, "loss": 1.7824, "step": 4300 }, { "epoch": 0.11, "learning_rate": 1.9977000307400947e-05, "loss": 1.8222, "step": 4400 }, { "epoch": 0.11, "learning_rate": 1.9975917531024595e-05, "loss": 1.7731, "step": 4500 }, { "epoch": 0.12, "learning_rate": 1.9974809880810936e-05, "loss": 1.913, "step": 4600 }, { "epoch": 0.12, "learning_rate": 1.9973677359521774e-05, "loss": 1.8763, "step": 4700 }, { "epoch": 0.12, "learning_rate": 1.9972519969980926e-05, "loss": 1.8317, "step": 4800 }, { "epoch": 0.12, "learning_rate": 1.9971337715074207e-05, "loss": 2.1418, "step": 4900 }, { "epoch": 0.13, "learning_rate": 1.9970130597749446e-05, "loss": 1.701, "step": 5000 }, { "epoch": 0.13, "learning_rate": 1.9968898621016445e-05, "loss": 1.7664, "step": 5100 }, { "epoch": 0.13, "learning_rate": 1.9967641787947013e-05, "loss": 1.7309, "step": 5200 }, { "epoch": 0.13, "learning_rate": 1.996636010167491e-05, "loss": 1.8597, "step": 5300 }, { "epoch": 0.14, "learning_rate": 1.9965053565395893e-05, "loss": 1.9846, "step": 5400 }, { "epoch": 0.14, "learning_rate": 1.9963722182367647e-05, "loss": 1.9432, "step": 5500 }, { "epoch": 0.14, "learning_rate": 1.9962365955909842e-05, "loss": 1.7985, "step": 5600 }, { "epoch": 0.14, "learning_rate": 1.996098488940407e-05, "loss": 1.853, "step": 5700 }, { "epoch": 0.15, "learning_rate": 1.9959578986293865e-05, "loss": 1.8939, "step": 5800 }, { "epoch": 0.15, "learning_rate": 1.9958148250084695e-05, "loss": 2.0998, "step": 5900 }, { "epoch": 0.15, "learning_rate": 1.9956692684343935e-05, "loss": 1.9209, "step": 6000 }, { "epoch": 0.15, "learning_rate": 1.995521229270088e-05, "loss": 1.9265, "step": 6100 }, { "epoch": 0.16, "learning_rate": 1.9953707078846723e-05, "loss": 2.0443, "step": 6200 }, { "epoch": 0.16, "learning_rate": 1.995217704653454e-05, "loss": 1.9403, "step": 6300 }, { "epoch": 0.16, "learning_rate": 1.99506221995793e-05, "loss": 1.9593, "step": 6400 }, { "epoch": 0.16, "learning_rate": 1.9949042541857845e-05, "loss": 1.8659, "step": 6500 }, { "epoch": 0.17, "learning_rate": 1.9947438077308865e-05, "loss": 1.9453, "step": 6600 }, { "epoch": 0.17, "learning_rate": 1.9945808809932924e-05, "loss": 1.7745, "step": 6700 }, { "epoch": 0.17, "learning_rate": 1.994415474379241e-05, "loss": 2.004, "step": 6800 }, { "epoch": 0.17, "learning_rate": 1.9942475883011555e-05, "loss": 1.9436, "step": 6900 }, { "epoch": 0.18, "learning_rate": 1.9940772231776414e-05, "loss": 1.797, "step": 7000 }, { "epoch": 0.18, "learning_rate": 1.9939043794334848e-05, "loss": 1.9025, "step": 7100 }, { "epoch": 0.18, "learning_rate": 1.9937290574996525e-05, "loss": 1.7685, "step": 7200 }, { "epoch": 0.18, "learning_rate": 1.9935512578132897e-05, "loss": 1.989, "step": 7300 }, { "epoch": 0.19, "learning_rate": 1.993370980817721e-05, "loss": 1.8198, "step": 7400 }, { "epoch": 0.19, "learning_rate": 1.993188226962446e-05, "loss": 1.8176, "step": 7500 }, { "epoch": 0.19, "learning_rate": 1.9930029967031417e-05, "loss": 1.9733, "step": 7600 }, { "epoch": 0.19, "learning_rate": 1.9928152905016586e-05, "loss": 1.7749, "step": 7700 }, { "epoch": 0.2, "learning_rate": 1.992625108826022e-05, "loss": 1.8151, "step": 7800 }, { "epoch": 0.2, "learning_rate": 1.9924324521504275e-05, "loss": 2.0445, "step": 7900 }, { "epoch": 0.2, "learning_rate": 1.992237320955244e-05, "loss": 1.6274, "step": 8000 }, { "epoch": 0.2, "learning_rate": 1.992039715727009e-05, "loss": 1.716, "step": 8100 }, { "epoch": 0.21, "learning_rate": 1.9918396369584288e-05, "loss": 1.8435, "step": 8200 }, { "epoch": 0.21, "learning_rate": 1.9916370851483783e-05, "loss": 2.0033, "step": 8300 }, { "epoch": 0.21, "learning_rate": 1.9914320608018967e-05, "loss": 1.8912, "step": 8400 }, { "epoch": 0.21, "learning_rate": 1.9912245644301902e-05, "loss": 1.7367, "step": 8500 }, { "epoch": 0.22, "learning_rate": 1.9910145965506277e-05, "loss": 1.9486, "step": 8600 }, { "epoch": 0.22, "learning_rate": 1.9908021576867405e-05, "loss": 1.8735, "step": 8700 }, { "epoch": 0.22, "learning_rate": 1.9905872483682215e-05, "loss": 1.9792, "step": 8800 }, { "epoch": 0.22, "learning_rate": 1.9903698691309228e-05, "loss": 1.7321, "step": 8900 }, { "epoch": 0.23, "learning_rate": 1.990150020516855e-05, "loss": 1.8528, "step": 9000 }, { "epoch": 0.23, "learning_rate": 1.989927703074187e-05, "loss": 1.6462, "step": 9100 }, { "epoch": 0.23, "learning_rate": 1.9897029173572418e-05, "loss": 2.0644, "step": 9200 }, { "epoch": 0.23, "learning_rate": 1.9894756639264975e-05, "loss": 1.9923, "step": 9300 }, { "epoch": 0.24, "learning_rate": 1.9892459433485856e-05, "loss": 1.8272, "step": 9400 }, { "epoch": 0.24, "learning_rate": 1.9890137561962883e-05, "loss": 1.8618, "step": 9500 }, { "epoch": 0.24, "learning_rate": 1.9887791030485388e-05, "loss": 1.8634, "step": 9600 }, { "epoch": 0.24, "learning_rate": 1.9885419844904184e-05, "loss": 1.7906, "step": 9700 }, { "epoch": 0.25, "learning_rate": 1.9883024011131553e-05, "loss": 1.782, "step": 9800 }, { "epoch": 0.25, "learning_rate": 1.988062786186036e-05, "loss": 1.7883, "step": 9900 }, { "epoch": 0.25, "learning_rate": 1.987818299601931e-05, "loss": 1.7629, "step": 10000 }, { "epoch": 0.25, "learning_rate": 1.987571350003111e-05, "loss": 1.8477, "step": 10100 }, { "epoch": 0.26, "learning_rate": 1.9873219380053173e-05, "loss": 1.6919, "step": 10200 }, { "epoch": 0.26, "learning_rate": 1.9870700642304314e-05, "loss": 1.8721, "step": 10300 }, { "epoch": 0.26, "learning_rate": 1.9868157293064722e-05, "loss": 1.8195, "step": 10400 }, { "epoch": 0.26, "learning_rate": 1.986558933867595e-05, "loss": 1.7368, "step": 10500 }, { "epoch": 0.27, "learning_rate": 1.9862996785540912e-05, "loss": 1.8397, "step": 10600 }, { "epoch": 0.27, "learning_rate": 1.986037964012385e-05, "loss": 1.9547, "step": 10700 }, { "epoch": 0.27, "learning_rate": 1.9857737908950316e-05, "loss": 1.777, "step": 10800 }, { "epoch": 0.27, "learning_rate": 1.985507159860718e-05, "loss": 1.7939, "step": 10900 }, { "epoch": 0.28, "learning_rate": 1.9852380715742588e-05, "loss": 1.7406, "step": 11000 }, { "epoch": 0.28, "learning_rate": 1.9849665267065953e-05, "loss": 1.9234, "step": 11100 }, { "epoch": 0.28, "learning_rate": 1.9846925259347946e-05, "loss": 1.9835, "step": 11200 }, { "epoch": 0.28, "learning_rate": 1.984416069942047e-05, "loss": 1.5539, "step": 11300 }, { "epoch": 0.29, "learning_rate": 1.9841371594176645e-05, "loss": 1.7954, "step": 11400 }, { "epoch": 0.29, "learning_rate": 1.9838557950570798e-05, "loss": 1.76, "step": 11500 }, { "epoch": 0.29, "learning_rate": 1.9835719775618433e-05, "loss": 1.7775, "step": 11600 }, { "epoch": 0.29, "learning_rate": 1.983285707639622e-05, "loss": 1.8909, "step": 11700 }, { "epoch": 0.3, "learning_rate": 1.982996986004198e-05, "loss": 1.7236, "step": 11800 }, { "epoch": 0.3, "learning_rate": 1.982705813375467e-05, "loss": 1.9102, "step": 11900 }, { "epoch": 0.3, "learning_rate": 1.9824121904794356e-05, "loss": 1.8857, "step": 12000 }, { "epoch": 0.3, "learning_rate": 1.9821161180482188e-05, "loss": 1.897, "step": 12100 }, { "epoch": 0.31, "learning_rate": 1.9818175968200412e-05, "loss": 1.8742, "step": 12200 }, { "epoch": 0.31, "learning_rate": 1.981516627539231e-05, "loss": 1.6836, "step": 12300 }, { "epoch": 0.31, "learning_rate": 1.9812132109562225e-05, "loss": 1.7452, "step": 12400 }, { "epoch": 0.31, "learning_rate": 1.9809073478275506e-05, "loss": 1.8008, "step": 12500 }, { "epoch": 0.32, "learning_rate": 1.9805990389158512e-05, "loss": 1.7817, "step": 12600 }, { "epoch": 0.32, "learning_rate": 1.9802882849898582e-05, "loss": 1.8683, "step": 12700 }, { "epoch": 0.32, "learning_rate": 1.9799750868244017e-05, "loss": 1.6916, "step": 12800 }, { "epoch": 0.32, "learning_rate": 1.9796594452004058e-05, "loss": 1.7314, "step": 12900 }, { "epoch": 0.33, "learning_rate": 1.9793413609048888e-05, "loss": 1.8981, "step": 13000 }, { "epoch": 0.33, "learning_rate": 1.9790208347309578e-05, "loss": 1.749, "step": 13100 }, { "epoch": 0.33, "learning_rate": 1.978697867477809e-05, "loss": 1.8379, "step": 13200 }, { "epoch": 0.33, "learning_rate": 1.978372459950725e-05, "loss": 1.6974, "step": 13300 }, { "epoch": 0.34, "learning_rate": 1.978044612961074e-05, "loss": 1.8546, "step": 13400 }, { "epoch": 0.34, "learning_rate": 1.977714327326305e-05, "loss": 1.8717, "step": 13500 }, { "epoch": 0.34, "learning_rate": 1.9773816038699486e-05, "loss": 1.8475, "step": 13600 }, { "epoch": 0.34, "learning_rate": 1.9770498070864685e-05, "loss": 2.0507, "step": 13700 }, { "epoch": 0.35, "learning_rate": 1.976712234839247e-05, "loss": 1.842, "step": 13800 }, { "epoch": 0.35, "learning_rate": 1.9763722272690438e-05, "loss": 1.9577, "step": 13900 }, { "epoch": 0.35, "learning_rate": 1.9760297852236304e-05, "loss": 1.6966, "step": 14000 }, { "epoch": 0.35, "learning_rate": 1.9756849095568472e-05, "loss": 1.8043, "step": 14100 }, { "epoch": 0.36, "learning_rate": 1.9753376011286037e-05, "loss": 1.7529, "step": 14200 }, { "epoch": 0.36, "learning_rate": 1.9749878608048742e-05, "loss": 1.649, "step": 14300 }, { "epoch": 0.36, "learning_rate": 1.9746392232018573e-05, "loss": 1.8301, "step": 14400 }, { "epoch": 0.36, "learning_rate": 1.974284646006421e-05, "loss": 1.7945, "step": 14500 }, { "epoch": 0.37, "learning_rate": 1.9739276395409247e-05, "loss": 1.6606, "step": 14600 }, { "epoch": 0.37, "learning_rate": 1.9735682046955243e-05, "loss": 1.5654, "step": 14700 }, { "epoch": 0.37, "learning_rate": 1.973206342366431e-05, "loss": 1.625, "step": 14800 }, { "epoch": 0.37, "learning_rate": 1.972842053455908e-05, "loss": 1.7698, "step": 14900 }, { "epoch": 0.38, "learning_rate": 1.9724753388722694e-05, "loss": 1.7372, "step": 15000 }, { "epoch": 0.38, "learning_rate": 1.9721061995298763e-05, "loss": 1.6598, "step": 15100 }, { "epoch": 0.38, "learning_rate": 1.9717346363491366e-05, "loss": 1.7066, "step": 15200 }, { "epoch": 0.38, "learning_rate": 1.9713606502565024e-05, "loss": 1.9579, "step": 15300 }, { "epoch": 0.39, "learning_rate": 1.9709842421844655e-05, "loss": 1.9298, "step": 15400 }, { "epoch": 0.39, "learning_rate": 1.970605413071558e-05, "loss": 1.6692, "step": 15500 }, { "epoch": 0.39, "learning_rate": 1.9702241638623477e-05, "loss": 1.9984, "step": 15600 }, { "epoch": 0.39, "learning_rate": 1.969840495507437e-05, "loss": 1.7592, "step": 15700 }, { "epoch": 0.4, "learning_rate": 1.9694544089634598e-05, "loss": 1.777, "step": 15800 }, { "epoch": 0.4, "learning_rate": 1.9690659051930806e-05, "loss": 1.7379, "step": 15900 }, { "epoch": 0.4, "learning_rate": 1.9686749851649893e-05, "loss": 1.701, "step": 16000 }, { "epoch": 0.4, "learning_rate": 1.968281649853902e-05, "loss": 1.7452, "step": 16100 }, { "epoch": 0.41, "learning_rate": 1.9678859002405567e-05, "loss": 1.7393, "step": 16200 }, { "epoch": 0.41, "learning_rate": 1.96748773731171e-05, "loss": 1.6563, "step": 16300 }, { "epoch": 0.41, "learning_rate": 1.967087162060137e-05, "loss": 1.6847, "step": 16400 }, { "epoch": 0.41, "learning_rate": 1.966684175484628e-05, "loss": 1.6423, "step": 16500 }, { "epoch": 0.42, "learning_rate": 1.966278778589985e-05, "loss": 1.8873, "step": 16600 }, { "epoch": 0.42, "learning_rate": 1.9658709723870193e-05, "loss": 1.8384, "step": 16700 }, { "epoch": 0.42, "learning_rate": 1.9654648719551844e-05, "loss": 1.649, "step": 16800 }, { "epoch": 0.42, "learning_rate": 1.9650522742596405e-05, "loss": 1.8725, "step": 16900 }, { "epoch": 0.43, "learning_rate": 1.9646372703139257e-05, "loss": 1.6924, "step": 17000 }, { "epoch": 0.43, "learning_rate": 1.9642198611528065e-05, "loss": 1.7959, "step": 17100 }, { "epoch": 0.43, "learning_rate": 1.9638000478170455e-05, "loss": 1.7103, "step": 17200 }, { "epoch": 0.43, "learning_rate": 1.9633778313534007e-05, "loss": 1.8419, "step": 17300 }, { "epoch": 0.44, "learning_rate": 1.9629532128146222e-05, "loss": 1.6359, "step": 17400 }, { "epoch": 0.44, "learning_rate": 1.9625261932594483e-05, "loss": 1.7761, "step": 17500 }, { "epoch": 0.44, "learning_rate": 1.9620967737526048e-05, "loss": 1.7868, "step": 17600 }, { "epoch": 0.44, "learning_rate": 1.961664955364801e-05, "loss": 1.6477, "step": 17700 }, { "epoch": 0.45, "learning_rate": 1.9612307391727284e-05, "loss": 1.832, "step": 17800 }, { "epoch": 0.45, "learning_rate": 1.9607941262590566e-05, "loss": 1.8558, "step": 17900 }, { "epoch": 0.45, "learning_rate": 1.9603551177124312e-05, "loss": 1.7138, "step": 18000 }, { "epoch": 0.45, "learning_rate": 1.9599137146274704e-05, "loss": 1.865, "step": 18100 }, { "epoch": 0.46, "learning_rate": 1.9594699181047642e-05, "loss": 1.6553, "step": 18200 }, { "epoch": 0.46, "learning_rate": 1.95902372925087e-05, "loss": 1.898, "step": 18300 }, { "epoch": 0.46, "learning_rate": 1.9585751491783088e-05, "loss": 1.5566, "step": 18400 }, { "epoch": 0.46, "learning_rate": 1.9581241790055653e-05, "loss": 1.817, "step": 18500 }, { "epoch": 0.47, "learning_rate": 1.9576708198570846e-05, "loss": 1.8093, "step": 18600 }, { "epoch": 0.47, "learning_rate": 1.9572150728632654e-05, "loss": 1.832, "step": 18700 }, { "epoch": 0.47, "learning_rate": 1.956756939160463e-05, "loss": 1.68, "step": 18800 }, { "epoch": 0.47, "learning_rate": 1.956296419890982e-05, "loss": 1.7628, "step": 18900 }, { "epoch": 0.48, "learning_rate": 1.9558335162030767e-05, "loss": 1.8463, "step": 19000 }, { "epoch": 0.48, "learning_rate": 1.955368229250945e-05, "loss": 1.6305, "step": 19100 }, { "epoch": 0.48, "learning_rate": 1.954900560194729e-05, "loss": 1.7224, "step": 19200 }, { "epoch": 0.48, "learning_rate": 1.954430510200508e-05, "loss": 1.7883, "step": 19300 }, { "epoch": 0.49, "learning_rate": 1.9539580804403e-05, "loss": 1.6919, "step": 19400 }, { "epoch": 0.49, "learning_rate": 1.953483272092056e-05, "loss": 1.7098, "step": 19500 }, { "epoch": 0.49, "learning_rate": 1.953006086339657e-05, "loss": 1.7506, "step": 19600 }, { "epoch": 0.49, "learning_rate": 1.952526524372913e-05, "loss": 1.8997, "step": 19700 }, { "epoch": 0.5, "learning_rate": 1.9520445873875577e-05, "loss": 1.6932, "step": 19800 }, { "epoch": 0.5, "learning_rate": 1.951560276585248e-05, "loss": 1.7128, "step": 19900 }, { "epoch": 0.5, "learning_rate": 1.9510735931735587e-05, "loss": 1.8018, "step": 20000 }, { "epoch": 0.5, "learning_rate": 1.9505845383659798e-05, "loss": 1.6543, "step": 20100 }, { "epoch": 0.51, "learning_rate": 1.9500931133819154e-05, "loss": 1.9608, "step": 20200 }, { "epoch": 0.51, "learning_rate": 1.9495993194466793e-05, "loss": 1.5379, "step": 20300 }, { "epoch": 0.51, "learning_rate": 1.9491031577914908e-05, "loss": 1.661, "step": 20400 }, { "epoch": 0.51, "learning_rate": 1.948604629653474e-05, "loss": 1.6655, "step": 20500 }, { "epoch": 0.52, "learning_rate": 1.9481037362756534e-05, "loss": 1.7973, "step": 20600 }, { "epoch": 0.52, "learning_rate": 1.9476004789069502e-05, "loss": 1.6289, "step": 20700 }, { "epoch": 0.52, "learning_rate": 1.947094858802181e-05, "loss": 1.7458, "step": 20800 }, { "epoch": 0.52, "learning_rate": 1.946586877222053e-05, "loss": 1.4971, "step": 20900 }, { "epoch": 0.53, "learning_rate": 1.9460765354331615e-05, "loss": 1.7084, "step": 21000 }, { "epoch": 0.53, "learning_rate": 1.945563834707987e-05, "loss": 1.9127, "step": 21100 }, { "epoch": 0.53, "learning_rate": 1.945048776324891e-05, "loss": 1.7147, "step": 21200 }, { "epoch": 0.54, "learning_rate": 1.944536547375501e-05, "loss": 1.7273, "step": 21300 }, { "epoch": 0.54, "learning_rate": 1.9440168010795902e-05, "loss": 1.7247, "step": 21400 }, { "epoch": 0.54, "learning_rate": 1.9434947009831147e-05, "loss": 1.5706, "step": 21500 }, { "epoch": 0.54, "learning_rate": 1.9429702483878715e-05, "loss": 1.6378, "step": 21600 }, { "epoch": 0.55, "learning_rate": 1.9424434446015257e-05, "loss": 1.5879, "step": 21700 }, { "epoch": 0.55, "learning_rate": 1.9419142909376036e-05, "loss": 1.6355, "step": 21800 }, { "epoch": 0.55, "learning_rate": 1.94138278871549e-05, "loss": 1.7517, "step": 21900 }, { "epoch": 0.55, "learning_rate": 1.9408489392604273e-05, "loss": 1.6505, "step": 22000 }, { "epoch": 0.56, "learning_rate": 1.940312743903509e-05, "loss": 1.6221, "step": 22100 }, { "epoch": 0.56, "learning_rate": 1.939774203981679e-05, "loss": 1.6826, "step": 22200 }, { "epoch": 0.56, "learning_rate": 1.9392333208377262e-05, "loss": 1.6773, "step": 22300 }, { "epoch": 0.56, "learning_rate": 1.938690095820282e-05, "loss": 1.9732, "step": 22400 }, { "epoch": 0.57, "learning_rate": 1.938144530283818e-05, "loss": 1.9316, "step": 22500 }, { "epoch": 0.57, "learning_rate": 1.9375966255886403e-05, "loss": 1.7497, "step": 22600 }, { "epoch": 0.57, "learning_rate": 1.9370463831008885e-05, "loss": 1.5787, "step": 22700 }, { "epoch": 0.57, "learning_rate": 1.936493804192531e-05, "loss": 1.5613, "step": 22800 }, { "epoch": 0.58, "learning_rate": 1.9359388902413615e-05, "loss": 1.7014, "step": 22900 }, { "epoch": 0.58, "learning_rate": 1.935381642630996e-05, "loss": 1.9055, "step": 23000 }, { "epoch": 0.58, "learning_rate": 1.9348220627508692e-05, "loss": 1.6435, "step": 23100 }, { "epoch": 0.58, "learning_rate": 1.9342601519962314e-05, "loss": 1.853, "step": 23200 }, { "epoch": 0.59, "learning_rate": 1.9337015656967037e-05, "loss": 1.8849, "step": 23300 }, { "epoch": 0.59, "learning_rate": 1.9331350206757194e-05, "loss": 1.5938, "step": 23400 }, { "epoch": 0.59, "learning_rate": 1.9325661489866753e-05, "loss": 1.8399, "step": 23500 }, { "epoch": 0.59, "learning_rate": 1.931994952047989e-05, "loss": 1.679, "step": 23600 }, { "epoch": 0.6, "learning_rate": 1.9314214312838772e-05, "loss": 1.6732, "step": 23700 }, { "epoch": 0.6, "learning_rate": 1.9308455881243487e-05, "loss": 1.7741, "step": 23800 }, { "epoch": 0.6, "learning_rate": 1.930267424005205e-05, "loss": 1.8035, "step": 23900 }, { "epoch": 0.6, "learning_rate": 1.9296869403680334e-05, "loss": 1.7012, "step": 24000 }, { "epoch": 0.61, "learning_rate": 1.9291041386602054e-05, "loss": 1.6068, "step": 24100 }, { "epoch": 0.61, "learning_rate": 1.928519020334872e-05, "loss": 1.7894, "step": 24200 }, { "epoch": 0.61, "learning_rate": 1.92793158685096e-05, "loss": 1.7217, "step": 24300 }, { "epoch": 0.61, "learning_rate": 1.92734183967317e-05, "loss": 1.5664, "step": 24400 }, { "epoch": 0.62, "learning_rate": 1.9267497802719704e-05, "loss": 1.787, "step": 24500 }, { "epoch": 0.62, "learning_rate": 1.9261554101235954e-05, "loss": 1.6307, "step": 24600 }, { "epoch": 0.62, "learning_rate": 1.92555873071004e-05, "loss": 1.8638, "step": 24700 }, { "epoch": 0.62, "learning_rate": 1.9249597435190588e-05, "loss": 1.7258, "step": 24800 }, { "epoch": 0.63, "learning_rate": 1.9243584500441586e-05, "loss": 1.7605, "step": 24900 }, { "epoch": 0.63, "learning_rate": 1.923754851784598e-05, "loss": 1.7585, "step": 25000 }, { "epoch": 0.63, "learning_rate": 1.9231489502453822e-05, "loss": 1.7886, "step": 25100 }, { "epoch": 0.63, "learning_rate": 1.9225407469372584e-05, "loss": 1.7991, "step": 25200 }, { "epoch": 0.64, "learning_rate": 1.9219302433767144e-05, "loss": 1.8049, "step": 25300 }, { "epoch": 0.64, "learning_rate": 1.921317441085972e-05, "loss": 1.6537, "step": 25400 }, { "epoch": 0.64, "learning_rate": 1.920702341592986e-05, "loss": 1.6834, "step": 25500 }, { "epoch": 0.64, "learning_rate": 1.9200849464314383e-05, "loss": 1.6623, "step": 25600 }, { "epoch": 0.65, "learning_rate": 1.9194652571407342e-05, "loss": 1.7102, "step": 25700 }, { "epoch": 0.65, "learning_rate": 1.918849506427951e-05, "loss": 1.6298, "step": 25800 }, { "epoch": 0.65, "learning_rate": 1.9182252564226664e-05, "loss": 1.631, "step": 25900 }, { "epoch": 0.65, "learning_rate": 1.9175987169251547e-05, "loss": 1.5952, "step": 26000 }, { "epoch": 0.66, "learning_rate": 1.9169698894976237e-05, "loss": 1.6925, "step": 26100 }, { "epoch": 0.66, "learning_rate": 1.9163387757079832e-05, "loss": 1.7845, "step": 26200 }, { "epoch": 0.66, "learning_rate": 1.9157053771298452e-05, "loss": 1.8064, "step": 26300 }, { "epoch": 0.66, "learning_rate": 1.9150696953425193e-05, "loss": 1.8842, "step": 26400 }, { "epoch": 0.67, "learning_rate": 1.9144317319310058e-05, "loss": 1.6494, "step": 26500 }, { "epoch": 0.67, "learning_rate": 1.913791488485996e-05, "loss": 1.8896, "step": 26600 }, { "epoch": 0.67, "learning_rate": 1.9131489666038657e-05, "loss": 1.8155, "step": 26700 }, { "epoch": 0.67, "learning_rate": 1.912504167886671e-05, "loss": 1.7773, "step": 26800 }, { "epoch": 0.68, "learning_rate": 1.911857093942146e-05, "loss": 1.716, "step": 26900 }, { "epoch": 0.68, "learning_rate": 1.9112077463836973e-05, "loss": 1.8483, "step": 27000 }, { "epoch": 0.68, "learning_rate": 1.9105561268304004e-05, "loss": 1.645, "step": 27100 }, { "epoch": 0.68, "learning_rate": 1.9099022369069956e-05, "loss": 1.6047, "step": 27200 }, { "epoch": 0.69, "learning_rate": 1.9092460782438853e-05, "loss": 1.5195, "step": 27300 }, { "epoch": 0.69, "learning_rate": 1.9085876524771277e-05, "loss": 1.8467, "step": 27400 }, { "epoch": 0.69, "learning_rate": 1.907926961248433e-05, "loss": 1.758, "step": 27500 }, { "epoch": 0.69, "learning_rate": 1.907264006205163e-05, "loss": 1.6981, "step": 27600 }, { "epoch": 0.7, "learning_rate": 1.90659878900032e-05, "loss": 1.7911, "step": 27700 }, { "epoch": 0.7, "learning_rate": 1.9059313112925505e-05, "loss": 1.592, "step": 27800 }, { "epoch": 0.7, "learning_rate": 1.9052615747461347e-05, "loss": 1.676, "step": 27900 }, { "epoch": 0.7, "learning_rate": 1.9045895810309864e-05, "loss": 1.6252, "step": 28000 }, { "epoch": 0.71, "learning_rate": 1.903915331822647e-05, "loss": 1.5912, "step": 28100 }, { "epoch": 0.71, "learning_rate": 1.903238828802281e-05, "loss": 1.7809, "step": 28200 }, { "epoch": 0.71, "learning_rate": 1.9025600736566742e-05, "loss": 1.6081, "step": 28300 }, { "epoch": 0.71, "learning_rate": 1.9018790680782265e-05, "loss": 1.6445, "step": 28400 }, { "epoch": 0.72, "learning_rate": 1.901195813764949e-05, "loss": 1.7395, "step": 28500 }, { "epoch": 0.72, "learning_rate": 1.9005103124204602e-05, "loss": 1.6988, "step": 28600 }, { "epoch": 0.72, "learning_rate": 1.899822565753981e-05, "loss": 1.9785, "step": 28700 }, { "epoch": 0.72, "learning_rate": 1.8991325754803318e-05, "loss": 1.7892, "step": 28800 }, { "epoch": 0.73, "learning_rate": 1.8984403433199255e-05, "loss": 1.8251, "step": 28900 }, { "epoch": 0.73, "learning_rate": 1.8977458709987662e-05, "loss": 1.6021, "step": 29000 }, { "epoch": 0.73, "learning_rate": 1.8970491602484435e-05, "loss": 1.6548, "step": 29100 }, { "epoch": 0.73, "learning_rate": 1.896350212806127e-05, "loss": 1.6622, "step": 29200 }, { "epoch": 0.74, "learning_rate": 1.8956490304145645e-05, "loss": 1.8714, "step": 29300 }, { "epoch": 0.74, "learning_rate": 1.8949456148220762e-05, "loss": 1.8197, "step": 29400 }, { "epoch": 0.74, "learning_rate": 1.894239967782551e-05, "loss": 1.8665, "step": 29500 }, { "epoch": 0.74, "learning_rate": 1.8935320910554397e-05, "loss": 1.5248, "step": 29600 }, { "epoch": 0.75, "learning_rate": 1.8928219864057552e-05, "loss": 1.7115, "step": 29700 }, { "epoch": 0.75, "learning_rate": 1.8921167899257056e-05, "loss": 1.6827, "step": 29800 }, { "epoch": 0.75, "learning_rate": 1.891409413317403e-05, "loss": 1.6721, "step": 29900 }, { "epoch": 0.75, "learning_rate": 1.8906926799799837e-05, "loss": 1.6201, "step": 30000 }, { "epoch": 0.76, "learning_rate": 1.889973725799746e-05, "loss": 1.65, "step": 30100 }, { "epoch": 0.76, "learning_rate": 1.8892525525693212e-05, "loss": 1.6597, "step": 30200 }, { "epoch": 0.76, "learning_rate": 1.888529162086874e-05, "loss": 1.6628, "step": 30300 }, { "epoch": 0.76, "learning_rate": 1.8878035561560984e-05, "loss": 1.7191, "step": 30400 }, { "epoch": 0.77, "learning_rate": 1.887075736586212e-05, "loss": 1.6925, "step": 30500 }, { "epoch": 0.77, "learning_rate": 1.886345705191951e-05, "loss": 1.531, "step": 30600 }, { "epoch": 0.77, "learning_rate": 1.8856134637935678e-05, "loss": 1.8038, "step": 30700 }, { "epoch": 0.77, "learning_rate": 1.8848790142168243e-05, "loss": 1.5675, "step": 30800 }, { "epoch": 0.78, "learning_rate": 1.884142358292989e-05, "loss": 1.7986, "step": 30900 }, { "epoch": 0.78, "learning_rate": 1.883403497858831e-05, "loss": 1.8275, "step": 31000 }, { "epoch": 0.78, "learning_rate": 1.882662434756616e-05, "loss": 1.856, "step": 31100 }, { "epoch": 0.78, "learning_rate": 1.881919170834103e-05, "loss": 1.7041, "step": 31200 }, { "epoch": 0.79, "learning_rate": 1.8811737079445368e-05, "loss": 1.6605, "step": 31300 }, { "epoch": 0.79, "learning_rate": 1.8804260479466462e-05, "loss": 1.611, "step": 31400 }, { "epoch": 0.79, "learning_rate": 1.8796761927046382e-05, "loss": 1.7808, "step": 31500 }, { "epoch": 0.79, "learning_rate": 1.8789241440881928e-05, "loss": 1.4411, "step": 31600 }, { "epoch": 0.8, "learning_rate": 1.87816990397246e-05, "loss": 1.7663, "step": 31700 }, { "epoch": 0.8, "learning_rate": 1.877413474238053e-05, "loss": 1.7196, "step": 31800 }, { "epoch": 0.8, "learning_rate": 1.876654856771044e-05, "loss": 1.6364, "step": 31900 }, { "epoch": 0.8, "learning_rate": 1.875894053462963e-05, "loss": 1.5694, "step": 32000 }, { "epoch": 0.81, "learning_rate": 1.8751310662107866e-05, "loss": 1.9001, "step": 32100 }, { "epoch": 0.81, "learning_rate": 1.8743658969169386e-05, "loss": 1.6115, "step": 32200 }, { "epoch": 0.81, "learning_rate": 1.873598547489284e-05, "loss": 1.8114, "step": 32300 }, { "epoch": 0.81, "learning_rate": 1.8728367258934995e-05, "loss": 1.8317, "step": 32400 }, { "epoch": 0.82, "learning_rate": 1.8720650436970645e-05, "loss": 1.627, "step": 32500 }, { "epoch": 0.82, "learning_rate": 1.8712911871037432e-05, "loss": 1.7334, "step": 32600 }, { "epoch": 0.82, "learning_rate": 1.8705151580430605e-05, "loss": 1.7104, "step": 32700 }, { "epoch": 0.82, "learning_rate": 1.8697369584499588e-05, "loss": 1.6504, "step": 32800 }, { "epoch": 0.83, "learning_rate": 1.868956590264791e-05, "loss": 1.5123, "step": 32900 }, { "epoch": 0.83, "learning_rate": 1.868174055433319e-05, "loss": 1.6737, "step": 33000 }, { "epoch": 0.83, "learning_rate": 1.867389355906706e-05, "loss": 1.7757, "step": 33100 }, { "epoch": 0.83, "learning_rate": 1.8666024936415123e-05, "loss": 1.8082, "step": 33200 }, { "epoch": 0.84, "learning_rate": 1.8658134705996916e-05, "loss": 1.6834, "step": 33300 }, { "epoch": 0.84, "learning_rate": 1.865022288748584e-05, "loss": 1.686, "step": 33400 }, { "epoch": 0.84, "learning_rate": 1.8642289500609143e-05, "loss": 1.777, "step": 33500 }, { "epoch": 0.84, "learning_rate": 1.8634334565147835e-05, "loss": 1.7536, "step": 33600 }, { "epoch": 0.85, "learning_rate": 1.8626358100936658e-05, "loss": 1.8103, "step": 33700 }, { "epoch": 0.85, "learning_rate": 1.861836012786404e-05, "loss": 1.5488, "step": 33800 }, { "epoch": 0.85, "learning_rate": 1.8610340665872027e-05, "loss": 1.7121, "step": 33900 }, { "epoch": 0.85, "learning_rate": 1.860229973495626e-05, "loss": 1.4662, "step": 34000 }, { "epoch": 0.86, "learning_rate": 1.85942373551659e-05, "loss": 1.9445, "step": 34100 }, { "epoch": 0.86, "learning_rate": 1.85862344906955e-05, "loss": 1.7745, "step": 34200 }, { "epoch": 0.86, "learning_rate": 1.8578129487503528e-05, "loss": 1.8254, "step": 34300 }, { "epoch": 0.86, "learning_rate": 1.857000309570278e-05, "loss": 1.749, "step": 34400 }, { "epoch": 0.87, "learning_rate": 1.856185533555551e-05, "loss": 1.8468, "step": 34500 }, { "epoch": 0.87, "learning_rate": 1.855368622737724e-05, "loss": 1.7578, "step": 34600 }, { "epoch": 0.87, "learning_rate": 1.8545495791536735e-05, "loss": 1.6632, "step": 34700 }, { "epoch": 0.87, "learning_rate": 1.8537284048455935e-05, "loss": 1.6868, "step": 34800 }, { "epoch": 0.88, "learning_rate": 1.85290510186099e-05, "loss": 1.6239, "step": 34900 }, { "epoch": 0.88, "learning_rate": 1.8520796722526778e-05, "loss": 1.5998, "step": 35000 }, { "epoch": 0.88, "learning_rate": 1.8512521180787727e-05, "loss": 1.7554, "step": 35100 }, { "epoch": 0.88, "learning_rate": 1.8504224414026896e-05, "loss": 1.9675, "step": 35200 }, { "epoch": 0.89, "learning_rate": 1.8495906442931336e-05, "loss": 1.9078, "step": 35300 }, { "epoch": 0.89, "learning_rate": 1.8487567288240994e-05, "loss": 1.6755, "step": 35400 }, { "epoch": 0.89, "learning_rate": 1.8479206970748608e-05, "loss": 1.5819, "step": 35500 }, { "epoch": 0.89, "learning_rate": 1.8470825511299707e-05, "loss": 1.5667, "step": 35600 }, { "epoch": 0.9, "learning_rate": 1.846242293079252e-05, "loss": 1.6201, "step": 35700 }, { "epoch": 0.9, "learning_rate": 1.8453999250177944e-05, "loss": 1.7056, "step": 35800 }, { "epoch": 0.9, "learning_rate": 1.844555449045949e-05, "loss": 1.8987, "step": 35900 }, { "epoch": 0.9, "learning_rate": 1.843708867269322e-05, "loss": 1.8683, "step": 36000 }, { "epoch": 0.91, "learning_rate": 1.8428601817987708e-05, "loss": 1.6787, "step": 36100 }, { "epoch": 0.91, "learning_rate": 1.842009394750398e-05, "loss": 1.5664, "step": 36200 }, { "epoch": 0.91, "learning_rate": 1.841156508245546e-05, "loss": 1.9259, "step": 36300 }, { "epoch": 0.91, "learning_rate": 1.8403015244107923e-05, "loss": 1.6442, "step": 36400 }, { "epoch": 0.92, "learning_rate": 1.8394444453779438e-05, "loss": 1.8566, "step": 36500 }, { "epoch": 0.92, "learning_rate": 1.8385852732840314e-05, "loss": 1.8008, "step": 36600 }, { "epoch": 0.92, "learning_rate": 1.837724010271304e-05, "loss": 1.5996, "step": 36700 }, { "epoch": 0.92, "learning_rate": 1.8368606584872264e-05, "loss": 1.6382, "step": 36800 }, { "epoch": 0.93, "learning_rate": 1.8359952200844687e-05, "loss": 1.6781, "step": 36900 }, { "epoch": 0.93, "learning_rate": 1.8351276972209054e-05, "loss": 1.7243, "step": 37000 }, { "epoch": 0.93, "learning_rate": 1.834258092059608e-05, "loss": 1.7199, "step": 37100 }, { "epoch": 0.93, "learning_rate": 1.83338640676884e-05, "loss": 1.8002, "step": 37200 }, { "epoch": 0.94, "learning_rate": 1.8325126435220514e-05, "loss": 1.5906, "step": 37300 }, { "epoch": 0.94, "learning_rate": 1.831636804497873e-05, "loss": 1.7027, "step": 37400 }, { "epoch": 0.94, "learning_rate": 1.8307588918801122e-05, "loss": 1.7599, "step": 37500 }, { "epoch": 0.94, "learning_rate": 1.829878907857746e-05, "loss": 1.6626, "step": 37600 }, { "epoch": 0.95, "learning_rate": 1.828996854624916e-05, "loss": 1.4791, "step": 37700 }, { "epoch": 0.95, "learning_rate": 1.828112734380924e-05, "loss": 1.6516, "step": 37800 }, { "epoch": 0.95, "learning_rate": 1.8272265493302253e-05, "loss": 1.4912, "step": 37900 }, { "epoch": 0.95, "learning_rate": 1.826338301682423e-05, "loss": 1.8356, "step": 38000 }, { "epoch": 0.96, "learning_rate": 1.8254479936522634e-05, "loss": 1.49, "step": 38100 }, { "epoch": 0.96, "learning_rate": 1.8245556274596308e-05, "loss": 1.7719, "step": 38200 }, { "epoch": 0.96, "learning_rate": 1.8236612053295405e-05, "loss": 1.6282, "step": 38300 }, { "epoch": 0.96, "learning_rate": 1.822773704409024e-05, "loss": 1.7773, "step": 38400 }, { "epoch": 0.97, "learning_rate": 1.8218751976032035e-05, "loss": 1.7018, "step": 38500 }, { "epoch": 0.97, "learning_rate": 1.820974641543278e-05, "loss": 1.726, "step": 38600 }, { "epoch": 0.97, "learning_rate": 1.8200720384746832e-05, "loss": 1.5169, "step": 38700 }, { "epoch": 0.97, "learning_rate": 1.81916739064796e-05, "loss": 1.6333, "step": 38800 }, { "epoch": 0.98, "learning_rate": 1.818260700318746e-05, "loss": 1.884, "step": 38900 }, { "epoch": 0.98, "learning_rate": 1.8173519697477727e-05, "loss": 1.6378, "step": 39000 }, { "epoch": 0.98, "learning_rate": 1.8164412012008587e-05, "loss": 1.7932, "step": 39100 }, { "epoch": 0.98, "learning_rate": 1.815528396948903e-05, "loss": 1.6671, "step": 39200 }, { "epoch": 0.99, "learning_rate": 1.814613559267882e-05, "loss": 1.7175, "step": 39300 }, { "epoch": 0.99, "learning_rate": 1.813696690438841e-05, "loss": 1.7527, "step": 39400 }, { "epoch": 0.99, "learning_rate": 1.8127777927478902e-05, "loss": 1.6946, "step": 39500 }, { "epoch": 0.99, "learning_rate": 1.8118568684861983e-05, "loss": 1.6551, "step": 39600 }, { "epoch": 1.0, "learning_rate": 1.8109339199499874e-05, "loss": 1.5853, "step": 39700 }, { "epoch": 1.0, "learning_rate": 1.8100089494405264e-05, "loss": 1.7403, "step": 39800 }, { "epoch": 1.0, "eval_loss": 1.4650893211364746, "eval_runtime": 105.1973, "eval_samples_per_second": 75.696, "eval_steps_per_second": 9.468, "step": 39811 }, { "epoch": 1.0, "learning_rate": 1.8090819592641264e-05, "loss": 1.4215, "step": 39900 }, { "epoch": 1.0, "learning_rate": 1.8081529517321336e-05, "loss": 1.7474, "step": 40000 }, { "epoch": 1.01, "learning_rate": 1.807221929160925e-05, "loss": 1.7123, "step": 40100 }, { "epoch": 1.01, "learning_rate": 1.80629823418011e-05, "loss": 1.864, "step": 40200 }, { "epoch": 1.01, "learning_rate": 1.805363208592073e-05, "loss": 1.5812, "step": 40300 }, { "epoch": 1.01, "learning_rate": 1.8044261749207323e-05, "loss": 1.63, "step": 40400 }, { "epoch": 1.02, "learning_rate": 1.8034871355024783e-05, "loss": 1.5077, "step": 40500 }, { "epoch": 1.02, "learning_rate": 1.8025460926787004e-05, "loss": 1.5994, "step": 40600 }, { "epoch": 1.02, "learning_rate": 1.8016030487957843e-05, "loss": 1.6769, "step": 40700 }, { "epoch": 1.02, "learning_rate": 1.8006580062051042e-05, "loss": 1.6441, "step": 40800 }, { "epoch": 1.03, "learning_rate": 1.7997204475266296e-05, "loss": 1.6812, "step": 40900 }, { "epoch": 1.03, "learning_rate": 1.7987714345226705e-05, "loss": 1.8061, "step": 41000 }, { "epoch": 1.03, "learning_rate": 1.7978204298712614e-05, "loss": 1.6677, "step": 41100 }, { "epoch": 1.03, "learning_rate": 1.7968674359436268e-05, "loss": 1.7225, "step": 41200 }, { "epoch": 1.04, "learning_rate": 1.7959124551159512e-05, "loss": 1.6024, "step": 41300 }, { "epoch": 1.04, "learning_rate": 1.7949554897693716e-05, "loss": 1.8078, "step": 41400 }, { "epoch": 1.04, "learning_rate": 1.7939965422899754e-05, "loss": 1.6088, "step": 41500 }, { "epoch": 1.04, "learning_rate": 1.7930356150687907e-05, "loss": 1.7393, "step": 41600 }, { "epoch": 1.05, "learning_rate": 1.792072710501782e-05, "loss": 1.6075, "step": 41700 }, { "epoch": 1.05, "learning_rate": 1.7911078309898447e-05, "loss": 1.7143, "step": 41800 }, { "epoch": 1.05, "learning_rate": 1.7901409789387987e-05, "loss": 1.779, "step": 41900 }, { "epoch": 1.05, "learning_rate": 1.789172156759381e-05, "loss": 1.5551, "step": 42000 }, { "epoch": 1.06, "learning_rate": 1.788201366867242e-05, "loss": 1.8168, "step": 42100 }, { "epoch": 1.06, "learning_rate": 1.7872286116829377e-05, "loss": 1.6811, "step": 42200 }, { "epoch": 1.06, "learning_rate": 1.7862538936319247e-05, "loss": 1.5401, "step": 42300 }, { "epoch": 1.07, "learning_rate": 1.7852772151445537e-05, "loss": 1.6055, "step": 42400 }, { "epoch": 1.07, "learning_rate": 1.7842985786560637e-05, "loss": 1.6392, "step": 42500 }, { "epoch": 1.07, "learning_rate": 1.7833179866065754e-05, "loss": 1.6091, "step": 42600 }, { "epoch": 1.07, "learning_rate": 1.782335441441086e-05, "loss": 1.5879, "step": 42700 }, { "epoch": 1.08, "learning_rate": 1.7813509456094617e-05, "loss": 1.6446, "step": 42800 }, { "epoch": 1.08, "learning_rate": 1.7803645015664333e-05, "loss": 1.5454, "step": 42900 }, { "epoch": 1.08, "learning_rate": 1.779376111771589e-05, "loss": 1.5753, "step": 43000 }, { "epoch": 1.08, "learning_rate": 1.7783857786893686e-05, "loss": 1.5995, "step": 43100 }, { "epoch": 1.09, "learning_rate": 1.777393504789057e-05, "loss": 1.6661, "step": 43200 }, { "epoch": 1.09, "learning_rate": 1.776399292544778e-05, "loss": 2.0914, "step": 43300 }, { "epoch": 1.09, "learning_rate": 1.7754031444354898e-05, "loss": 1.7128, "step": 43400 }, { "epoch": 1.09, "learning_rate": 1.774405062944976e-05, "loss": 1.7939, "step": 43500 }, { "epoch": 1.1, "learning_rate": 1.7734050505618415e-05, "loss": 1.5976, "step": 43600 }, { "epoch": 1.1, "learning_rate": 1.772403109779506e-05, "loss": 1.8864, "step": 43700 }, { "epoch": 1.1, "learning_rate": 1.7713992430961963e-05, "loss": 1.6491, "step": 43800 }, { "epoch": 1.1, "learning_rate": 1.7703934530149426e-05, "loss": 1.6283, "step": 43900 }, { "epoch": 1.11, "learning_rate": 1.7693857420435695e-05, "loss": 1.5285, "step": 44000 }, { "epoch": 1.11, "learning_rate": 1.7683761126946927e-05, "loss": 1.6802, "step": 44100 }, { "epoch": 1.11, "learning_rate": 1.76736456748571e-05, "loss": 1.7112, "step": 44200 }, { "epoch": 1.11, "learning_rate": 1.7663511089387968e-05, "loss": 1.8106, "step": 44300 }, { "epoch": 1.12, "learning_rate": 1.7653357395808984e-05, "loss": 1.646, "step": 44400 }, { "epoch": 1.12, "learning_rate": 1.7643184619437255e-05, "loss": 1.4939, "step": 44500 }, { "epoch": 1.12, "learning_rate": 1.763299278563746e-05, "loss": 1.5154, "step": 44600 }, { "epoch": 1.12, "learning_rate": 1.76227819198218e-05, "loss": 1.7225, "step": 44700 }, { "epoch": 1.13, "learning_rate": 1.761255204744993e-05, "loss": 1.8143, "step": 44800 }, { "epoch": 1.13, "learning_rate": 1.7602303194028896e-05, "loss": 1.5512, "step": 44900 }, { "epoch": 1.13, "learning_rate": 1.759203538511307e-05, "loss": 1.8718, "step": 45000 }, { "epoch": 1.13, "learning_rate": 1.758174864630409e-05, "loss": 1.7409, "step": 45100 }, { "epoch": 1.14, "learning_rate": 1.7571443003250787e-05, "loss": 1.695, "step": 45200 }, { "epoch": 1.14, "learning_rate": 1.7561118481649137e-05, "loss": 1.583, "step": 45300 }, { "epoch": 1.14, "learning_rate": 1.755077510724218e-05, "loss": 1.6148, "step": 45400 }, { "epoch": 1.14, "learning_rate": 1.7540412905819966e-05, "loss": 1.752, "step": 45500 }, { "epoch": 1.15, "learning_rate": 1.753003190321949e-05, "loss": 1.613, "step": 45600 }, { "epoch": 1.15, "learning_rate": 1.7519632125324618e-05, "loss": 1.724, "step": 45700 }, { "epoch": 1.15, "learning_rate": 1.7509213598066044e-05, "loss": 1.7039, "step": 45800 }, { "epoch": 1.15, "learning_rate": 1.74987763474212e-05, "loss": 1.6811, "step": 45900 }, { "epoch": 1.16, "learning_rate": 1.7488320399414203e-05, "loss": 1.676, "step": 46000 }, { "epoch": 1.16, "learning_rate": 1.7477845780115796e-05, "loss": 1.8192, "step": 46100 }, { "epoch": 1.16, "learning_rate": 1.7467352515643274e-05, "loss": 1.7483, "step": 46200 }, { "epoch": 1.16, "learning_rate": 1.745684063216042e-05, "loss": 1.7146, "step": 46300 }, { "epoch": 1.17, "learning_rate": 1.744631015587744e-05, "loss": 1.6719, "step": 46400 }, { "epoch": 1.17, "learning_rate": 1.7435761113050906e-05, "loss": 1.7145, "step": 46500 }, { "epoch": 1.17, "learning_rate": 1.7425193529983678e-05, "loss": 1.7036, "step": 46600 }, { "epoch": 1.17, "learning_rate": 1.7414607433024842e-05, "loss": 1.7418, "step": 46700 }, { "epoch": 1.18, "learning_rate": 1.740400284856965e-05, "loss": 1.5501, "step": 46800 }, { "epoch": 1.18, "learning_rate": 1.7393379803059457e-05, "loss": 1.6983, "step": 46900 }, { "epoch": 1.18, "learning_rate": 1.7382738322981638e-05, "loss": 1.4834, "step": 47000 }, { "epoch": 1.18, "learning_rate": 1.7372078434869533e-05, "loss": 1.6422, "step": 47100 }, { "epoch": 1.19, "learning_rate": 1.7361507038898876e-05, "loss": 1.6846, "step": 47200 }, { "epoch": 1.19, "learning_rate": 1.7350810597918115e-05, "loss": 1.4663, "step": 47300 }, { "epoch": 1.19, "learning_rate": 1.734009582851129e-05, "loss": 1.6254, "step": 47400 }, { "epoch": 1.19, "learning_rate": 1.732936275739449e-05, "loss": 1.6724, "step": 47500 }, { "epoch": 1.2, "learning_rate": 1.731861141132942e-05, "loss": 1.6673, "step": 47600 }, { "epoch": 1.2, "learning_rate": 1.7307841817123363e-05, "loss": 1.6335, "step": 47700 }, { "epoch": 1.2, "learning_rate": 1.7297054001629107e-05, "loss": 1.8172, "step": 47800 }, { "epoch": 1.2, "learning_rate": 1.7286247991744863e-05, "loss": 1.6739, "step": 47900 }, { "epoch": 1.21, "learning_rate": 1.7275423814414207e-05, "loss": 1.7223, "step": 48000 }, { "epoch": 1.21, "learning_rate": 1.7264581496626024e-05, "loss": 1.639, "step": 48100 }, { "epoch": 1.21, "learning_rate": 1.7253721065414418e-05, "loss": 1.7626, "step": 48200 }, { "epoch": 1.21, "learning_rate": 1.7242842547858666e-05, "loss": 1.5735, "step": 48300 }, { "epoch": 1.22, "learning_rate": 1.7231945971083138e-05, "loss": 1.7126, "step": 48400 }, { "epoch": 1.22, "learning_rate": 1.722103136225723e-05, "loss": 1.5057, "step": 48500 }, { "epoch": 1.22, "learning_rate": 1.7210098748595302e-05, "loss": 1.7282, "step": 48600 }, { "epoch": 1.22, "learning_rate": 1.719914815735661e-05, "loss": 1.5201, "step": 48700 }, { "epoch": 1.23, "learning_rate": 1.718817961584523e-05, "loss": 1.6772, "step": 48800 }, { "epoch": 1.23, "learning_rate": 1.717719315140999e-05, "loss": 1.6784, "step": 48900 }, { "epoch": 1.23, "learning_rate": 1.716618879144442e-05, "loss": 1.7472, "step": 49000 }, { "epoch": 1.23, "learning_rate": 1.7155276874024092e-05, "loss": 1.8064, "step": 49100 }, { "epoch": 1.24, "learning_rate": 1.714423698362675e-05, "loss": 1.8315, "step": 49200 }, { "epoch": 1.24, "learning_rate": 1.7133179279871605e-05, "loss": 1.6508, "step": 49300 }, { "epoch": 1.24, "learning_rate": 1.712210379032981e-05, "loss": 1.6248, "step": 49400 }, { "epoch": 1.24, "learning_rate": 1.711101054261685e-05, "loss": 1.8541, "step": 49500 }, { "epoch": 1.25, "learning_rate": 1.7099899564392513e-05, "loss": 1.7817, "step": 49600 }, { "epoch": 1.25, "learning_rate": 1.708877088336078e-05, "loss": 1.6701, "step": 49700 }, { "epoch": 1.25, "learning_rate": 1.7077624527269776e-05, "loss": 1.626, "step": 49800 }, { "epoch": 1.25, "learning_rate": 1.706646052391169e-05, "loss": 1.6845, "step": 49900 }, { "epoch": 1.26, "learning_rate": 1.705527890112273e-05, "loss": 1.6834, "step": 50000 }, { "epoch": 1.26, "learning_rate": 1.7044079686783015e-05, "loss": 1.6578, "step": 50100 }, { "epoch": 1.26, "learning_rate": 1.703286290881654e-05, "loss": 1.8281, "step": 50200 }, { "epoch": 1.26, "learning_rate": 1.7021628595191092e-05, "loss": 1.5931, "step": 50300 }, { "epoch": 1.27, "learning_rate": 1.7010376773918175e-05, "loss": 1.5499, "step": 50400 }, { "epoch": 1.27, "learning_rate": 1.6999107473052953e-05, "loss": 1.6587, "step": 50500 }, { "epoch": 1.27, "learning_rate": 1.6987820720694163e-05, "loss": 1.6193, "step": 50600 }, { "epoch": 1.27, "learning_rate": 1.697651654498407e-05, "loss": 1.706, "step": 50700 }, { "epoch": 1.28, "learning_rate": 1.6965194974108376e-05, "loss": 1.6819, "step": 50800 }, { "epoch": 1.28, "learning_rate": 1.695385603629615e-05, "loss": 1.8728, "step": 50900 }, { "epoch": 1.28, "learning_rate": 1.6942499759819768e-05, "loss": 1.7289, "step": 51000 }, { "epoch": 1.28, "learning_rate": 1.6931126172994844e-05, "loss": 1.7831, "step": 51100 }, { "epoch": 1.29, "learning_rate": 1.6919735304180142e-05, "loss": 1.6022, "step": 51200 }, { "epoch": 1.29, "learning_rate": 1.6908327181777525e-05, "loss": 1.5742, "step": 51300 }, { "epoch": 1.29, "learning_rate": 1.689690183423187e-05, "loss": 1.5363, "step": 51400 }, { "epoch": 1.29, "learning_rate": 1.688545929003101e-05, "loss": 1.6747, "step": 51500 }, { "epoch": 1.3, "learning_rate": 1.6873999577705657e-05, "loss": 1.4892, "step": 51600 }, { "epoch": 1.3, "learning_rate": 1.6862522725829316e-05, "loss": 1.6908, "step": 51700 }, { "epoch": 1.3, "learning_rate": 1.6851028763018238e-05, "loss": 1.5501, "step": 51800 }, { "epoch": 1.3, "learning_rate": 1.6839517717931343e-05, "loss": 1.6753, "step": 51900 }, { "epoch": 1.31, "learning_rate": 1.682798961927013e-05, "loss": 1.5969, "step": 52000 }, { "epoch": 1.31, "learning_rate": 1.681656003119197e-05, "loss": 1.6019, "step": 52100 }, { "epoch": 1.31, "learning_rate": 1.680499808147447e-05, "loss": 1.8769, "step": 52200 }, { "epoch": 1.31, "learning_rate": 1.679341916425352e-05, "loss": 1.5716, "step": 52300 }, { "epoch": 1.32, "learning_rate": 1.6781823308399846e-05, "loss": 1.5338, "step": 52400 }, { "epoch": 1.32, "learning_rate": 1.6770210542826436e-05, "loss": 1.7512, "step": 52500 }, { "epoch": 1.32, "learning_rate": 1.675858089648842e-05, "loss": 1.4335, "step": 52600 }, { "epoch": 1.32, "learning_rate": 1.6746934398383024e-05, "loss": 1.6627, "step": 52700 }, { "epoch": 1.33, "learning_rate": 1.673527107754949e-05, "loss": 1.6009, "step": 52800 }, { "epoch": 1.33, "learning_rate": 1.672359096306901e-05, "loss": 1.5058, "step": 52900 }, { "epoch": 1.33, "learning_rate": 1.6711894084064644e-05, "loss": 1.7135, "step": 53000 }, { "epoch": 1.33, "learning_rate": 1.6700180469701252e-05, "loss": 1.618, "step": 53100 }, { "epoch": 1.34, "learning_rate": 1.668845014918543e-05, "loss": 1.7835, "step": 53200 }, { "epoch": 1.34, "learning_rate": 1.667670315176542e-05, "loss": 1.6558, "step": 53300 }, { "epoch": 1.34, "learning_rate": 1.6664939506731054e-05, "loss": 1.6903, "step": 53400 }, { "epoch": 1.34, "learning_rate": 1.665315924341366e-05, "loss": 1.6888, "step": 53500 }, { "epoch": 1.35, "learning_rate": 1.6641362391186014e-05, "loss": 1.6561, "step": 53600 }, { "epoch": 1.35, "learning_rate": 1.6629548979462254e-05, "loss": 1.7988, "step": 53700 }, { "epoch": 1.35, "learning_rate": 1.6617719037697805e-05, "loss": 1.7562, "step": 53800 }, { "epoch": 1.35, "learning_rate": 1.66058725953893e-05, "loss": 1.7014, "step": 53900 }, { "epoch": 1.36, "learning_rate": 1.6594009682074526e-05, "loss": 1.6283, "step": 54000 }, { "epoch": 1.36, "learning_rate": 1.6582130327332332e-05, "loss": 1.7115, "step": 54100 }, { "epoch": 1.36, "learning_rate": 1.6570353599589153e-05, "loss": 1.8219, "step": 54200 }, { "epoch": 1.36, "learning_rate": 1.6558441614567092e-05, "loss": 1.5507, "step": 54300 }, { "epoch": 1.37, "learning_rate": 1.654651327680262e-05, "loss": 1.6835, "step": 54400 }, { "epoch": 1.37, "learning_rate": 1.6534568616037713e-05, "loss": 1.7691, "step": 54500 }, { "epoch": 1.37, "learning_rate": 1.6522607662055055e-05, "loss": 1.5614, "step": 54600 }, { "epoch": 1.37, "learning_rate": 1.6510630444677948e-05, "loss": 1.7597, "step": 54700 }, { "epoch": 1.38, "learning_rate": 1.649863699377024e-05, "loss": 1.6361, "step": 54800 }, { "epoch": 1.38, "learning_rate": 1.648662733923628e-05, "loss": 1.5732, "step": 54900 }, { "epoch": 1.38, "learning_rate": 1.6474601511020787e-05, "loss": 1.6991, "step": 55000 }, { "epoch": 1.38, "learning_rate": 1.646255953910883e-05, "loss": 1.5766, "step": 55100 }, { "epoch": 1.39, "learning_rate": 1.6450501453525713e-05, "loss": 1.7388, "step": 55200 }, { "epoch": 1.39, "learning_rate": 1.6438427284336935e-05, "loss": 1.5538, "step": 55300 }, { "epoch": 1.39, "learning_rate": 1.6426337061648085e-05, "loss": 1.685, "step": 55400 }, { "epoch": 1.39, "learning_rate": 1.641423081560479e-05, "loss": 1.6507, "step": 55500 }, { "epoch": 1.4, "learning_rate": 1.640210857639262e-05, "loss": 1.4541, "step": 55600 }, { "epoch": 1.4, "learning_rate": 1.6389970374237024e-05, "loss": 1.6886, "step": 55700 }, { "epoch": 1.4, "learning_rate": 1.6377816239403262e-05, "loss": 1.8045, "step": 55800 }, { "epoch": 1.4, "learning_rate": 1.6365646202196303e-05, "loss": 1.512, "step": 55900 }, { "epoch": 1.41, "learning_rate": 1.6353460292960784e-05, "loss": 1.8086, "step": 56000 }, { "epoch": 1.41, "learning_rate": 1.6341258542080907e-05, "loss": 1.7012, "step": 56100 }, { "epoch": 1.41, "learning_rate": 1.632904097998038e-05, "loss": 1.69, "step": 56200 }, { "epoch": 1.41, "learning_rate": 1.6316807637122325e-05, "loss": 1.7214, "step": 56300 }, { "epoch": 1.42, "learning_rate": 1.6304558544009226e-05, "loss": 1.4842, "step": 56400 }, { "epoch": 1.42, "learning_rate": 1.6292293731182822e-05, "loss": 1.6042, "step": 56500 }, { "epoch": 1.42, "learning_rate": 1.628001322922406e-05, "loss": 1.6462, "step": 56600 }, { "epoch": 1.42, "learning_rate": 1.6267717068752993e-05, "loss": 1.5979, "step": 56700 }, { "epoch": 1.43, "learning_rate": 1.625540528042874e-05, "loss": 1.6199, "step": 56800 }, { "epoch": 1.43, "learning_rate": 1.624307789494936e-05, "loss": 1.5126, "step": 56900 }, { "epoch": 1.43, "learning_rate": 1.623073494305182e-05, "loss": 1.5222, "step": 57000 }, { "epoch": 1.43, "learning_rate": 1.6218376455511888e-05, "loss": 1.5933, "step": 57100 }, { "epoch": 1.44, "learning_rate": 1.6206002463144072e-05, "loss": 1.6143, "step": 57200 }, { "epoch": 1.44, "learning_rate": 1.6193612996801552e-05, "loss": 1.661, "step": 57300 }, { "epoch": 1.44, "learning_rate": 1.618120808737607e-05, "loss": 1.5564, "step": 57400 }, { "epoch": 1.44, "learning_rate": 1.616891204520217e-05, "loss": 1.62, "step": 57500 }, { "epoch": 1.45, "learning_rate": 1.6156476496098393e-05, "loss": 1.6057, "step": 57600 }, { "epoch": 1.45, "learning_rate": 1.6144150181386295e-05, "loss": 1.6121, "step": 57700 }, { "epoch": 1.45, "learning_rate": 1.6131684115393595e-05, "loss": 1.8013, "step": 57800 }, { "epoch": 1.45, "learning_rate": 1.6119202760730693e-05, "loss": 1.7516, "step": 57900 }, { "epoch": 1.46, "learning_rate": 1.610670614851845e-05, "loss": 1.4714, "step": 58000 }, { "epoch": 1.46, "learning_rate": 1.6094194309915782e-05, "loss": 1.7001, "step": 58100 }, { "epoch": 1.46, "learning_rate": 1.608166727611956e-05, "loss": 1.4094, "step": 58200 }, { "epoch": 1.46, "learning_rate": 1.606912507836454e-05, "loss": 1.8002, "step": 58300 }, { "epoch": 1.47, "learning_rate": 1.6056567747923297e-05, "loss": 1.6507, "step": 58400 }, { "epoch": 1.47, "learning_rate": 1.6043995316106134e-05, "loss": 1.7155, "step": 58500 }, { "epoch": 1.47, "learning_rate": 1.6031407814261005e-05, "loss": 1.6369, "step": 58600 }, { "epoch": 1.47, "learning_rate": 1.6018805273773443e-05, "loss": 1.6602, "step": 58700 }, { "epoch": 1.48, "learning_rate": 1.600618772606647e-05, "loss": 1.8279, "step": 58800 }, { "epoch": 1.48, "learning_rate": 1.5993555202600543e-05, "loss": 1.6221, "step": 58900 }, { "epoch": 1.48, "learning_rate": 1.598090773487345e-05, "loss": 1.5228, "step": 59000 }, { "epoch": 1.48, "learning_rate": 1.5968245354420232e-05, "loss": 1.7752, "step": 59100 }, { "epoch": 1.49, "learning_rate": 1.5955568092813123e-05, "loss": 1.6846, "step": 59200 }, { "epoch": 1.49, "learning_rate": 1.594287598166147e-05, "loss": 1.4935, "step": 59300 }, { "epoch": 1.49, "learning_rate": 1.5930169052611626e-05, "loss": 1.6476, "step": 59400 }, { "epoch": 1.49, "learning_rate": 1.5917447337346904e-05, "loss": 1.6163, "step": 59500 }, { "epoch": 1.5, "learning_rate": 1.5904710867587484e-05, "loss": 1.7478, "step": 59600 }, { "epoch": 1.5, "learning_rate": 1.5891959675090332e-05, "loss": 1.7003, "step": 59700 }, { "epoch": 1.5, "learning_rate": 1.5879193791649118e-05, "loss": 1.7968, "step": 59800 }, { "epoch": 1.5, "learning_rate": 1.5866413249094158e-05, "loss": 1.7259, "step": 59900 }, { "epoch": 1.51, "learning_rate": 1.5853618079292295e-05, "loss": 1.6437, "step": 60000 }, { "epoch": 1.51, "learning_rate": 1.5840808314146872e-05, "loss": 1.5891, "step": 60100 }, { "epoch": 1.51, "learning_rate": 1.58279839855976e-05, "loss": 1.6291, "step": 60200 }, { "epoch": 1.51, "learning_rate": 1.5815145125620516e-05, "loss": 1.5988, "step": 60300 }, { "epoch": 1.52, "learning_rate": 1.5802291766227876e-05, "loss": 1.6975, "step": 60400 }, { "epoch": 1.52, "learning_rate": 1.5789423939468112e-05, "loss": 1.6146, "step": 60500 }, { "epoch": 1.52, "learning_rate": 1.5776541677425705e-05, "loss": 1.6627, "step": 60600 }, { "epoch": 1.52, "learning_rate": 1.5763645012221136e-05, "loss": 1.5154, "step": 60700 }, { "epoch": 1.53, "learning_rate": 1.575073397601081e-05, "loss": 1.3921, "step": 60800 }, { "epoch": 1.53, "learning_rate": 1.5737808600986944e-05, "loss": 1.5418, "step": 60900 }, { "epoch": 1.53, "learning_rate": 1.5724868919377528e-05, "loss": 1.7312, "step": 61000 }, { "epoch": 1.53, "learning_rate": 1.5711914963446207e-05, "loss": 1.5306, "step": 61100 }, { "epoch": 1.54, "learning_rate": 1.5698946765492232e-05, "loss": 1.6496, "step": 61200 }, { "epoch": 1.54, "learning_rate": 1.5685964357850353e-05, "loss": 1.5414, "step": 61300 }, { "epoch": 1.54, "learning_rate": 1.567296777289075e-05, "loss": 1.8149, "step": 61400 }, { "epoch": 1.54, "learning_rate": 1.5659957043018975e-05, "loss": 1.643, "step": 61500 }, { "epoch": 1.55, "learning_rate": 1.5646932200675812e-05, "loss": 1.6405, "step": 61600 }, { "epoch": 1.55, "learning_rate": 1.563389327833726e-05, "loss": 1.6376, "step": 61700 }, { "epoch": 1.55, "learning_rate": 1.562084030851442e-05, "loss": 1.6154, "step": 61800 }, { "epoch": 1.55, "learning_rate": 1.560777332375341e-05, "loss": 1.6542, "step": 61900 }, { "epoch": 1.56, "learning_rate": 1.55946923566353e-05, "loss": 1.6935, "step": 62000 }, { "epoch": 1.56, "learning_rate": 1.558159743977603e-05, "loss": 1.5964, "step": 62100 }, { "epoch": 1.56, "learning_rate": 1.55684886058263e-05, "loss": 1.7399, "step": 62200 }, { "epoch": 1.56, "learning_rate": 1.5555365887471538e-05, "loss": 1.4878, "step": 62300 }, { "epoch": 1.57, "learning_rate": 1.5542229317431768e-05, "loss": 1.6529, "step": 62400 }, { "epoch": 1.57, "learning_rate": 1.5529078928461565e-05, "loss": 1.6528, "step": 62500 }, { "epoch": 1.57, "learning_rate": 1.551591475334996e-05, "loss": 1.5646, "step": 62600 }, { "epoch": 1.57, "learning_rate": 1.5502736824920354e-05, "loss": 1.6046, "step": 62700 }, { "epoch": 1.58, "learning_rate": 1.548954517603044e-05, "loss": 1.705, "step": 62800 }, { "epoch": 1.58, "learning_rate": 1.547633983957212e-05, "loss": 1.5444, "step": 62900 }, { "epoch": 1.58, "learning_rate": 1.5463253105864722e-05, "loss": 1.509, "step": 63000 }, { "epoch": 1.58, "learning_rate": 1.5450020629135298e-05, "loss": 1.6404, "step": 63100 }, { "epoch": 1.59, "learning_rate": 1.5436774563387522e-05, "loss": 1.4361, "step": 63200 }, { "epoch": 1.59, "learning_rate": 1.5423514941648978e-05, "loss": 1.7006, "step": 63300 }, { "epoch": 1.59, "learning_rate": 1.5410241796981048e-05, "loss": 1.6002, "step": 63400 }, { "epoch": 1.6, "learning_rate": 1.5396955162478845e-05, "loss": 1.544, "step": 63500 }, { "epoch": 1.6, "learning_rate": 1.5383655071271104e-05, "loss": 1.7422, "step": 63600 }, { "epoch": 1.6, "learning_rate": 1.5370341556520124e-05, "loss": 1.4425, "step": 63700 }, { "epoch": 1.6, "learning_rate": 1.5357014651421663e-05, "loss": 1.4881, "step": 63800 }, { "epoch": 1.61, "learning_rate": 1.5343674389204876e-05, "loss": 1.6319, "step": 63900 }, { "epoch": 1.61, "learning_rate": 1.5330320803132215e-05, "loss": 1.5717, "step": 64000 }, { "epoch": 1.61, "learning_rate": 1.5316953926499363e-05, "loss": 1.5976, "step": 64100 }, { "epoch": 1.61, "learning_rate": 1.5303573792635126e-05, "loss": 1.7077, "step": 64200 }, { "epoch": 1.62, "learning_rate": 1.5290180434901386e-05, "loss": 1.5682, "step": 64300 }, { "epoch": 1.62, "learning_rate": 1.5276773886692977e-05, "loss": 1.7105, "step": 64400 }, { "epoch": 1.62, "learning_rate": 1.5263354181437636e-05, "loss": 1.5934, "step": 64500 }, { "epoch": 1.62, "learning_rate": 1.5249921352595896e-05, "loss": 1.6659, "step": 64600 }, { "epoch": 1.63, "learning_rate": 1.5236475433661024e-05, "loss": 1.667, "step": 64700 }, { "epoch": 1.63, "learning_rate": 1.5223016458158912e-05, "loss": 1.67, "step": 64800 }, { "epoch": 1.63, "learning_rate": 1.5209544459648019e-05, "loss": 1.8044, "step": 64900 }, { "epoch": 1.63, "learning_rate": 1.5196059471719267e-05, "loss": 1.6084, "step": 65000 }, { "epoch": 1.64, "learning_rate": 1.518256152799597e-05, "loss": 1.4102, "step": 65100 }, { "epoch": 1.64, "learning_rate": 1.5169185834646367e-05, "loss": 1.7695, "step": 65200 }, { "epoch": 1.64, "learning_rate": 1.5155662209050697e-05, "loss": 1.836, "step": 65300 }, { "epoch": 1.64, "learning_rate": 1.5142125728386552e-05, "loss": 1.5216, "step": 65400 }, { "epoch": 1.65, "learning_rate": 1.5128576426405632e-05, "loss": 1.6375, "step": 65500 }, { "epoch": 1.65, "learning_rate": 1.5115014336891612e-05, "loss": 1.7208, "step": 65600 }, { "epoch": 1.65, "learning_rate": 1.5101439493660044e-05, "loss": 1.6194, "step": 65700 }, { "epoch": 1.65, "learning_rate": 1.5087851930558293e-05, "loss": 1.7472, "step": 65800 }, { "epoch": 1.66, "learning_rate": 1.5074251681465426e-05, "loss": 1.6213, "step": 65900 }, { "epoch": 1.66, "learning_rate": 1.5060638780292147e-05, "loss": 1.6214, "step": 66000 }, { "epoch": 1.66, "learning_rate": 1.5047013260980708e-05, "loss": 1.694, "step": 66100 }, { "epoch": 1.66, "learning_rate": 1.5033375157504817e-05, "loss": 1.7412, "step": 66200 }, { "epoch": 1.67, "learning_rate": 1.5019724503869575e-05, "loss": 1.813, "step": 66300 }, { "epoch": 1.67, "learning_rate": 1.5006061334111347e-05, "loss": 1.5533, "step": 66400 }, { "epoch": 1.67, "learning_rate": 1.4992385682297734e-05, "loss": 1.4578, "step": 66500 }, { "epoch": 1.67, "learning_rate": 1.4978697582527446e-05, "loss": 1.7334, "step": 66600 }, { "epoch": 1.68, "learning_rate": 1.496499706893023e-05, "loss": 1.633, "step": 66700 }, { "epoch": 1.68, "learning_rate": 1.495128417566679e-05, "loss": 1.8807, "step": 66800 }, { "epoch": 1.68, "learning_rate": 1.4937558936928694e-05, "loss": 1.5315, "step": 66900 }, { "epoch": 1.68, "learning_rate": 1.4923821386938293e-05, "loss": 1.66, "step": 67000 }, { "epoch": 1.69, "learning_rate": 1.4910071559948638e-05, "loss": 1.6738, "step": 67100 }, { "epoch": 1.69, "learning_rate": 1.4896309490243386e-05, "loss": 1.5716, "step": 67200 }, { "epoch": 1.69, "learning_rate": 1.4882535212136721e-05, "loss": 1.7525, "step": 67300 }, { "epoch": 1.69, "learning_rate": 1.4868748759973275e-05, "loss": 1.6295, "step": 67400 }, { "epoch": 1.7, "learning_rate": 1.485495016812802e-05, "loss": 1.7672, "step": 67500 }, { "epoch": 1.7, "learning_rate": 1.484113947100621e-05, "loss": 1.5538, "step": 67600 }, { "epoch": 1.7, "learning_rate": 1.4827316703043277e-05, "loss": 1.6398, "step": 67700 }, { "epoch": 1.7, "learning_rate": 1.4813481898704752e-05, "loss": 1.6656, "step": 67800 }, { "epoch": 1.71, "learning_rate": 1.4799773619844324e-05, "loss": 1.668, "step": 67900 }, { "epoch": 1.71, "learning_rate": 1.4785914965773704e-05, "loss": 1.6209, "step": 68000 }, { "epoch": 1.71, "learning_rate": 1.4772044378558102e-05, "loss": 1.6242, "step": 68100 }, { "epoch": 1.71, "learning_rate": 1.4758161892782281e-05, "loss": 1.4472, "step": 68200 }, { "epoch": 1.72, "learning_rate": 1.4744267543060668e-05, "loss": 1.6373, "step": 68300 }, { "epoch": 1.72, "learning_rate": 1.4730361364037278e-05, "loss": 1.5845, "step": 68400 }, { "epoch": 1.72, "learning_rate": 1.4716443390385613e-05, "loss": 1.7273, "step": 68500 }, { "epoch": 1.72, "learning_rate": 1.4702513656808588e-05, "loss": 1.6112, "step": 68600 }, { "epoch": 1.73, "learning_rate": 1.4688572198038441e-05, "loss": 1.4885, "step": 68700 }, { "epoch": 1.73, "learning_rate": 1.4674619048836642e-05, "loss": 1.7485, "step": 68800 }, { "epoch": 1.73, "learning_rate": 1.4660654243993813e-05, "loss": 1.7285, "step": 68900 }, { "epoch": 1.73, "learning_rate": 1.4646817639994944e-05, "loss": 1.8137, "step": 69000 }, { "epoch": 1.74, "learning_rate": 1.4632829744045207e-05, "loss": 1.7656, "step": 69100 }, { "epoch": 1.74, "learning_rate": 1.4618830296651411e-05, "loss": 1.7004, "step": 69200 }, { "epoch": 1.74, "learning_rate": 1.4604819332719614e-05, "loss": 1.5771, "step": 69300 }, { "epoch": 1.74, "learning_rate": 1.459079688718459e-05, "loss": 1.5787, "step": 69400 }, { "epoch": 1.75, "learning_rate": 1.457676299500974e-05, "loss": 1.5543, "step": 69500 }, { "epoch": 1.75, "learning_rate": 1.4562717691187018e-05, "loss": 1.6373, "step": 69600 }, { "epoch": 1.75, "learning_rate": 1.454866101073681e-05, "loss": 1.6135, "step": 69700 }, { "epoch": 1.75, "learning_rate": 1.4534592988707893e-05, "loss": 1.6989, "step": 69800 }, { "epoch": 1.76, "learning_rate": 1.4520513660177296e-05, "loss": 1.6014, "step": 69900 }, { "epoch": 1.76, "learning_rate": 1.4506423060250265e-05, "loss": 1.5499, "step": 70000 }, { "epoch": 1.76, "learning_rate": 1.4492321224060133e-05, "loss": 1.6784, "step": 70100 }, { "epoch": 1.76, "learning_rate": 1.447820818676826e-05, "loss": 1.674, "step": 70200 }, { "epoch": 1.77, "learning_rate": 1.4464083983563924e-05, "loss": 1.6557, "step": 70300 }, { "epoch": 1.77, "learning_rate": 1.4449948649664252e-05, "loss": 1.548, "step": 70400 }, { "epoch": 1.77, "learning_rate": 1.4435802220314124e-05, "loss": 1.6148, "step": 70500 }, { "epoch": 1.77, "learning_rate": 1.4421644730786079e-05, "loss": 1.6385, "step": 70600 }, { "epoch": 1.78, "learning_rate": 1.4407476216380245e-05, "loss": 1.6862, "step": 70700 }, { "epoch": 1.78, "learning_rate": 1.4393296712424225e-05, "loss": 1.6091, "step": 70800 }, { "epoch": 1.78, "learning_rate": 1.4379106254273032e-05, "loss": 1.7291, "step": 70900 }, { "epoch": 1.78, "learning_rate": 1.436490487730899e-05, "loss": 1.5063, "step": 71000 }, { "epoch": 1.79, "learning_rate": 1.4350692616941649e-05, "loss": 1.4312, "step": 71100 }, { "epoch": 1.79, "learning_rate": 1.4336469508607692e-05, "loss": 1.5163, "step": 71200 }, { "epoch": 1.79, "learning_rate": 1.4322235587770854e-05, "loss": 1.8072, "step": 71300 }, { "epoch": 1.79, "learning_rate": 1.430799088992183e-05, "loss": 1.6612, "step": 71400 }, { "epoch": 1.8, "learning_rate": 1.4293735450578183e-05, "loss": 1.4452, "step": 71500 }, { "epoch": 1.8, "learning_rate": 1.4279469305284264e-05, "loss": 1.7496, "step": 71600 }, { "epoch": 1.8, "learning_rate": 1.4265192489611108e-05, "loss": 1.4869, "step": 71700 }, { "epoch": 1.8, "learning_rate": 1.4250905039156368e-05, "loss": 1.6697, "step": 71800 }, { "epoch": 1.81, "learning_rate": 1.4236606989544204e-05, "loss": 1.7116, "step": 71900 }, { "epoch": 1.81, "learning_rate": 1.422229837642521e-05, "loss": 1.8197, "step": 72000 }, { "epoch": 1.81, "learning_rate": 1.420797923547631e-05, "loss": 1.7444, "step": 72100 }, { "epoch": 1.81, "learning_rate": 1.4193649602400696e-05, "loss": 1.8146, "step": 72200 }, { "epoch": 1.82, "learning_rate": 1.4179309512927697e-05, "loss": 1.4516, "step": 72300 }, { "epoch": 1.82, "learning_rate": 1.4164959002812734e-05, "loss": 1.7425, "step": 72400 }, { "epoch": 1.82, "learning_rate": 1.4150598107837202e-05, "loss": 1.6935, "step": 72500 }, { "epoch": 1.82, "learning_rate": 1.4136226863808384e-05, "loss": 1.6986, "step": 72600 }, { "epoch": 1.83, "learning_rate": 1.4121845306559383e-05, "loss": 1.6139, "step": 72700 }, { "epoch": 1.83, "learning_rate": 1.4107453471948999e-05, "loss": 1.7356, "step": 72800 }, { "epoch": 1.83, "learning_rate": 1.4093051395861673e-05, "loss": 1.639, "step": 72900 }, { "epoch": 1.83, "learning_rate": 1.4078639114207371e-05, "loss": 1.6989, "step": 73000 }, { "epoch": 1.84, "learning_rate": 1.4064216662921509e-05, "loss": 1.4938, "step": 73100 }, { "epoch": 1.84, "learning_rate": 1.4049928453857955e-05, "loss": 1.654, "step": 73200 }, { "epoch": 1.84, "learning_rate": 1.4035485872015193e-05, "loss": 1.6631, "step": 73300 }, { "epoch": 1.84, "learning_rate": 1.4021033228138667e-05, "loss": 1.4672, "step": 73400 }, { "epoch": 1.85, "learning_rate": 1.4006570558264432e-05, "loss": 1.6349, "step": 73500 }, { "epoch": 1.85, "learning_rate": 1.3992097898453539e-05, "loss": 1.69, "step": 73600 }, { "epoch": 1.85, "learning_rate": 1.3977615284791953e-05, "loss": 1.6285, "step": 73700 }, { "epoch": 1.85, "learning_rate": 1.3963122753390455e-05, "loss": 1.7005, "step": 73800 }, { "epoch": 1.86, "learning_rate": 1.394862034038455e-05, "loss": 1.4793, "step": 73900 }, { "epoch": 1.86, "learning_rate": 1.3934108081934396e-05, "loss": 1.7438, "step": 74000 }, { "epoch": 1.86, "learning_rate": 1.3919586014224685e-05, "loss": 1.4409, "step": 74100 }, { "epoch": 1.86, "learning_rate": 1.3905054173464571e-05, "loss": 1.5435, "step": 74200 }, { "epoch": 1.87, "learning_rate": 1.3890512595887585e-05, "loss": 1.5822, "step": 74300 }, { "epoch": 1.87, "learning_rate": 1.3875961317751519e-05, "loss": 1.7633, "step": 74400 }, { "epoch": 1.87, "learning_rate": 1.3861400375338364e-05, "loss": 1.5942, "step": 74500 }, { "epoch": 1.87, "learning_rate": 1.3846829804954209e-05, "loss": 1.5557, "step": 74600 }, { "epoch": 1.88, "learning_rate": 1.383224964292914e-05, "loss": 1.661, "step": 74700 }, { "epoch": 1.88, "learning_rate": 1.381765992561717e-05, "loss": 1.7335, "step": 74800 }, { "epoch": 1.88, "learning_rate": 1.380306068939613e-05, "loss": 1.6817, "step": 74900 }, { "epoch": 1.88, "learning_rate": 1.3788451970667582e-05, "loss": 1.6671, "step": 75000 }, { "epoch": 1.89, "learning_rate": 1.3773833805856745e-05, "loss": 1.6907, "step": 75100 }, { "epoch": 1.89, "learning_rate": 1.375920623141237e-05, "loss": 1.632, "step": 75200 }, { "epoch": 1.89, "learning_rate": 1.374456928380669e-05, "loss": 1.6096, "step": 75300 }, { "epoch": 1.89, "learning_rate": 1.37299229995353e-05, "loss": 1.5511, "step": 75400 }, { "epoch": 1.9, "learning_rate": 1.3715267415117075e-05, "loss": 1.6211, "step": 75500 }, { "epoch": 1.9, "learning_rate": 1.3700602567094077e-05, "loss": 1.6162, "step": 75600 }, { "epoch": 1.9, "learning_rate": 1.3685928492031475e-05, "loss": 1.7431, "step": 75700 }, { "epoch": 1.9, "learning_rate": 1.3671245226517429e-05, "loss": 1.7654, "step": 75800 }, { "epoch": 1.91, "learning_rate": 1.3656552807163031e-05, "loss": 1.656, "step": 75900 }, { "epoch": 1.91, "learning_rate": 1.3641851270602185e-05, "loss": 1.658, "step": 76000 }, { "epoch": 1.91, "learning_rate": 1.3627140653491531e-05, "loss": 1.5835, "step": 76100 }, { "epoch": 1.91, "learning_rate": 1.3612420992510358e-05, "loss": 1.675, "step": 76200 }, { "epoch": 1.92, "learning_rate": 1.359769232436049e-05, "loss": 1.6759, "step": 76300 }, { "epoch": 1.92, "learning_rate": 1.3582954685766224e-05, "loss": 1.453, "step": 76400 }, { "epoch": 1.92, "learning_rate": 1.3568208113474212e-05, "loss": 1.5264, "step": 76500 }, { "epoch": 1.92, "learning_rate": 1.3553600242864616e-05, "loss": 1.888, "step": 76600 }, { "epoch": 1.93, "learning_rate": 1.3538836001925289e-05, "loss": 1.4686, "step": 76700 }, { "epoch": 1.93, "learning_rate": 1.3524062937293238e-05, "loss": 1.4277, "step": 76800 }, { "epoch": 1.93, "learning_rate": 1.3509281085803446e-05, "loss": 1.8314, "step": 76900 }, { "epoch": 1.93, "learning_rate": 1.3494490484312813e-05, "loss": 1.5377, "step": 77000 }, { "epoch": 1.94, "learning_rate": 1.3479691169700054e-05, "loss": 1.445, "step": 77100 }, { "epoch": 1.94, "learning_rate": 1.3464883178865607e-05, "loss": 1.7339, "step": 77200 }, { "epoch": 1.94, "learning_rate": 1.3450066548731544e-05, "loss": 1.8655, "step": 77300 }, { "epoch": 1.94, "learning_rate": 1.343524131624148e-05, "loss": 1.3921, "step": 77400 }, { "epoch": 1.95, "learning_rate": 1.3420407518360486e-05, "loss": 1.6644, "step": 77500 }, { "epoch": 1.95, "learning_rate": 1.340556519207497e-05, "loss": 1.6924, "step": 77600 }, { "epoch": 1.95, "learning_rate": 1.3390714374392622e-05, "loss": 1.6703, "step": 77700 }, { "epoch": 1.95, "learning_rate": 1.3375855102342299e-05, "loss": 1.6915, "step": 77800 }, { "epoch": 1.96, "learning_rate": 1.3360987412973936e-05, "loss": 1.7154, "step": 77900 }, { "epoch": 1.96, "learning_rate": 1.3346111343358459e-05, "loss": 1.5393, "step": 78000 }, { "epoch": 1.96, "learning_rate": 1.333122693058769e-05, "loss": 1.5757, "step": 78100 }, { "epoch": 1.96, "learning_rate": 1.3316334211774249e-05, "loss": 1.5819, "step": 78200 }, { "epoch": 1.97, "learning_rate": 1.3301433224051468e-05, "loss": 1.4649, "step": 78300 }, { "epoch": 1.97, "learning_rate": 1.32865240045733e-05, "loss": 1.4907, "step": 78400 }, { "epoch": 1.97, "learning_rate": 1.3271606590514215e-05, "loss": 1.382, "step": 78500 }, { "epoch": 1.97, "learning_rate": 1.3256681019069128e-05, "loss": 1.6937, "step": 78600 }, { "epoch": 1.98, "learning_rate": 1.324174732745328e-05, "loss": 1.5817, "step": 78700 }, { "epoch": 1.98, "learning_rate": 1.3226805552902166e-05, "loss": 1.6214, "step": 78800 }, { "epoch": 1.98, "learning_rate": 1.321185573267144e-05, "loss": 1.5416, "step": 78900 }, { "epoch": 1.98, "learning_rate": 1.31968979040368e-05, "loss": 1.6649, "step": 79000 }, { "epoch": 1.99, "learning_rate": 1.3182081801625837e-05, "loss": 1.5701, "step": 79100 }, { "epoch": 1.99, "learning_rate": 1.3167108147243437e-05, "loss": 1.6784, "step": 79200 }, { "epoch": 1.99, "learning_rate": 1.315212659603024e-05, "loss": 1.5761, "step": 79300 }, { "epoch": 1.99, "learning_rate": 1.3137137185341073e-05, "loss": 1.4885, "step": 79400 }, { "epoch": 2.0, "learning_rate": 1.3122139952550358e-05, "loss": 1.6533, "step": 79500 }, { "epoch": 2.0, "learning_rate": 1.3107134935052024e-05, "loss": 1.7439, "step": 79600 }, { "epoch": 2.0, "eval_loss": 1.4319051504135132, "eval_runtime": 105.8268, "eval_samples_per_second": 75.246, "eval_steps_per_second": 9.412, "step": 79622 }, { "epoch": 2.0, "learning_rate": 1.3092122170259407e-05, "loss": 1.6398, "step": 79700 }, { "epoch": 2.0, "learning_rate": 1.3077101695605157e-05, "loss": 1.5117, "step": 79800 }, { "epoch": 2.01, "learning_rate": 1.3062073548541157e-05, "loss": 1.6524, "step": 79900 }, { "epoch": 2.01, "learning_rate": 1.304703776653841e-05, "loss": 1.699, "step": 80000 }, { "epoch": 2.01, "learning_rate": 1.3031994387086967e-05, "loss": 1.4589, "step": 80100 }, { "epoch": 2.01, "learning_rate": 1.3016943447695813e-05, "loss": 1.5964, "step": 80200 }, { "epoch": 2.02, "learning_rate": 1.3001884985892784e-05, "loss": 1.4429, "step": 80300 }, { "epoch": 2.02, "learning_rate": 1.2986819039224474e-05, "loss": 1.51, "step": 80400 }, { "epoch": 2.02, "learning_rate": 1.2971745645256146e-05, "loss": 1.7436, "step": 80500 }, { "epoch": 2.02, "learning_rate": 1.2956664841571622e-05, "loss": 1.6454, "step": 80600 }, { "epoch": 2.03, "learning_rate": 1.2941576665773203e-05, "loss": 1.4964, "step": 80700 }, { "epoch": 2.03, "learning_rate": 1.2926481155481573e-05, "loss": 1.5786, "step": 80800 }, { "epoch": 2.03, "learning_rate": 1.29113783483357e-05, "loss": 1.6244, "step": 80900 }, { "epoch": 2.03, "learning_rate": 1.2896268281992757e-05, "loss": 1.5288, "step": 81000 }, { "epoch": 2.04, "learning_rate": 1.2881150994127995e-05, "loss": 1.6195, "step": 81100 }, { "epoch": 2.04, "learning_rate": 1.2866026522434695e-05, "loss": 1.7562, "step": 81200 }, { "epoch": 2.04, "learning_rate": 1.2850894904624038e-05, "loss": 1.5659, "step": 81300 }, { "epoch": 2.04, "learning_rate": 1.2835756178425023e-05, "loss": 1.7103, "step": 81400 }, { "epoch": 2.05, "learning_rate": 1.2820610381584373e-05, "loss": 1.5271, "step": 81500 }, { "epoch": 2.05, "learning_rate": 1.2805457551866445e-05, "loss": 1.7134, "step": 81600 }, { "epoch": 2.05, "learning_rate": 1.2790449359802883e-05, "loss": 1.8355, "step": 81700 }, { "epoch": 2.05, "learning_rate": 1.277528264707931e-05, "loss": 1.482, "step": 81800 }, { "epoch": 2.06, "learning_rate": 1.2760109014498104e-05, "loss": 1.6014, "step": 81900 }, { "epoch": 2.06, "learning_rate": 1.2744928499893025e-05, "loss": 1.7941, "step": 82000 }, { "epoch": 2.06, "learning_rate": 1.2729741141115005e-05, "loss": 1.6198, "step": 82100 }, { "epoch": 2.06, "learning_rate": 1.2714546976032009e-05, "loss": 1.527, "step": 82200 }, { "epoch": 2.07, "learning_rate": 1.269949808524328e-05, "loss": 1.5099, "step": 82300 }, { "epoch": 2.07, "learning_rate": 1.2684290488339608e-05, "loss": 1.6182, "step": 82400 }, { "epoch": 2.07, "learning_rate": 1.2669076198457107e-05, "loss": 1.8505, "step": 82500 }, { "epoch": 2.07, "learning_rate": 1.2653855253530903e-05, "loss": 1.4598, "step": 82600 }, { "epoch": 2.08, "learning_rate": 1.2638627691512726e-05, "loss": 1.7607, "step": 82700 }, { "epoch": 2.08, "learning_rate": 1.2623393550370802e-05, "loss": 1.6954, "step": 82800 }, { "epoch": 2.08, "learning_rate": 1.2608152868089764e-05, "loss": 1.5318, "step": 82900 }, { "epoch": 2.08, "learning_rate": 1.2592905682670556e-05, "loss": 1.5393, "step": 83000 }, { "epoch": 2.09, "learning_rate": 1.257765203213033e-05, "loss": 1.6498, "step": 83100 }, { "epoch": 2.09, "learning_rate": 1.256239195450236e-05, "loss": 1.3822, "step": 83200 }, { "epoch": 2.09, "learning_rate": 1.2547125487835946e-05, "loss": 1.5836, "step": 83300 }, { "epoch": 2.09, "learning_rate": 1.253185267019633e-05, "loss": 1.501, "step": 83400 }, { "epoch": 2.1, "learning_rate": 1.2516573539664565e-05, "loss": 1.5387, "step": 83500 }, { "epoch": 2.1, "learning_rate": 1.2501288134337464e-05, "loss": 1.5213, "step": 83600 }, { "epoch": 2.1, "learning_rate": 1.2485996492327483e-05, "loss": 1.7316, "step": 83700 }, { "epoch": 2.1, "learning_rate": 1.247069865176262e-05, "loss": 1.7472, "step": 83800 }, { "epoch": 2.11, "learning_rate": 1.2455394650786336e-05, "loss": 1.6054, "step": 83900 }, { "epoch": 2.11, "learning_rate": 1.2440084527557448e-05, "loss": 1.3633, "step": 84000 }, { "epoch": 2.11, "learning_rate": 1.2424768320250043e-05, "loss": 1.5243, "step": 84100 }, { "epoch": 2.11, "learning_rate": 1.2409446067053374e-05, "loss": 1.8291, "step": 84200 }, { "epoch": 2.12, "learning_rate": 1.239411780617177e-05, "loss": 1.7671, "step": 84300 }, { "epoch": 2.12, "learning_rate": 1.2378783575824535e-05, "loss": 1.5681, "step": 84400 }, { "epoch": 2.12, "learning_rate": 1.2363443414245871e-05, "loss": 1.7331, "step": 84500 }, { "epoch": 2.13, "learning_rate": 1.2348097359684748e-05, "loss": 1.4652, "step": 84600 }, { "epoch": 2.13, "learning_rate": 1.2332745450404848e-05, "loss": 1.4714, "step": 84700 }, { "epoch": 2.13, "learning_rate": 1.2317387724684445e-05, "loss": 1.5197, "step": 84800 }, { "epoch": 2.13, "learning_rate": 1.2302024220816308e-05, "loss": 1.6178, "step": 84900 }, { "epoch": 2.14, "learning_rate": 1.2286654977107624e-05, "loss": 1.5859, "step": 85000 }, { "epoch": 2.14, "learning_rate": 1.2271280031879887e-05, "loss": 1.7483, "step": 85100 }, { "epoch": 2.14, "learning_rate": 1.2256053257459767e-05, "loss": 1.5365, "step": 85200 }, { "epoch": 2.14, "learning_rate": 1.2240667080273632e-05, "loss": 1.5326, "step": 85300 }, { "epoch": 2.15, "learning_rate": 1.2225275316234135e-05, "loss": 1.6538, "step": 85400 }, { "epoch": 2.15, "learning_rate": 1.220987800371892e-05, "loss": 1.5555, "step": 85500 }, { "epoch": 2.15, "learning_rate": 1.219447518111947e-05, "loss": 1.5809, "step": 85600 }, { "epoch": 2.15, "learning_rate": 1.2179066886841e-05, "loss": 1.5383, "step": 85700 }, { "epoch": 2.16, "learning_rate": 1.2163653159302382e-05, "loss": 1.6567, "step": 85800 }, { "epoch": 2.16, "learning_rate": 1.2148234036936013e-05, "loss": 1.5909, "step": 85900 }, { "epoch": 2.16, "learning_rate": 1.2132809558187763e-05, "loss": 1.647, "step": 86000 }, { "epoch": 2.16, "learning_rate": 1.211737976151685e-05, "loss": 1.7332, "step": 86100 }, { "epoch": 2.17, "learning_rate": 1.2101944685395743e-05, "loss": 1.7165, "step": 86200 }, { "epoch": 2.17, "learning_rate": 1.2086504368310088e-05, "loss": 1.4636, "step": 86300 }, { "epoch": 2.17, "learning_rate": 1.2071213329579867e-05, "loss": 1.4769, "step": 86400 }, { "epoch": 2.17, "learning_rate": 1.2055762697523075e-05, "loss": 1.6723, "step": 86500 }, { "epoch": 2.18, "learning_rate": 1.2040306939651367e-05, "loss": 1.5215, "step": 86600 }, { "epoch": 2.18, "learning_rate": 1.202484609450195e-05, "loss": 1.333, "step": 86700 }, { "epoch": 2.18, "learning_rate": 1.2009380200624716e-05, "loss": 1.9055, "step": 86800 }, { "epoch": 2.18, "learning_rate": 1.199390929658215e-05, "loss": 1.5719, "step": 86900 }, { "epoch": 2.19, "learning_rate": 1.197843342094922e-05, "loss": 1.5993, "step": 87000 }, { "epoch": 2.19, "learning_rate": 1.1962952612313302e-05, "loss": 1.6091, "step": 87100 }, { "epoch": 2.19, "learning_rate": 1.1947466909274055e-05, "loss": 1.5519, "step": 87200 }, { "epoch": 2.19, "learning_rate": 1.193197635044336e-05, "loss": 1.6367, "step": 87300 }, { "epoch": 2.2, "learning_rate": 1.1916480974445195e-05, "loss": 1.6784, "step": 87400 }, { "epoch": 2.2, "learning_rate": 1.1900980819915547e-05, "loss": 1.5687, "step": 87500 }, { "epoch": 2.2, "learning_rate": 1.1885475925502328e-05, "loss": 1.4682, "step": 87600 }, { "epoch": 2.2, "learning_rate": 1.1869966329865259e-05, "loss": 1.5661, "step": 87700 }, { "epoch": 2.21, "learning_rate": 1.1854452071675788e-05, "loss": 1.7014, "step": 87800 }, { "epoch": 2.21, "learning_rate": 1.1838933189616985e-05, "loss": 1.5735, "step": 87900 }, { "epoch": 2.21, "learning_rate": 1.1823409722383452e-05, "loss": 1.5651, "step": 88000 }, { "epoch": 2.21, "learning_rate": 1.1807881708681219e-05, "loss": 1.6123, "step": 88100 }, { "epoch": 2.22, "learning_rate": 1.1792349187227663e-05, "loss": 1.4021, "step": 88200 }, { "epoch": 2.22, "learning_rate": 1.1776812196751386e-05, "loss": 1.6754, "step": 88300 }, { "epoch": 2.22, "learning_rate": 1.1761270775992145e-05, "loss": 1.5927, "step": 88400 }, { "epoch": 2.22, "learning_rate": 1.1745724963700737e-05, "loss": 1.6039, "step": 88500 }, { "epoch": 2.23, "learning_rate": 1.1730174798638906e-05, "loss": 1.6661, "step": 88600 }, { "epoch": 2.23, "learning_rate": 1.1714620319579264e-05, "loss": 1.697, "step": 88700 }, { "epoch": 2.23, "learning_rate": 1.169906156530516e-05, "loss": 1.6109, "step": 88800 }, { "epoch": 2.23, "learning_rate": 1.1683654225360436e-05, "loss": 1.7661, "step": 88900 }, { "epoch": 2.24, "learning_rate": 1.1668087078834072e-05, "loss": 1.5345, "step": 89000 }, { "epoch": 2.24, "learning_rate": 1.1652515773118694e-05, "loss": 1.605, "step": 89100 }, { "epoch": 2.24, "learning_rate": 1.1636940347039612e-05, "loss": 1.7576, "step": 89200 }, { "epoch": 2.24, "learning_rate": 1.1621360839432418e-05, "loss": 1.7532, "step": 89300 }, { "epoch": 2.25, "learning_rate": 1.160577728914287e-05, "loss": 1.4063, "step": 89400 }, { "epoch": 2.25, "learning_rate": 1.1590189735026817e-05, "loss": 1.6403, "step": 89500 }, { "epoch": 2.25, "learning_rate": 1.1574598215950083e-05, "loss": 1.5833, "step": 89600 }, { "epoch": 2.25, "learning_rate": 1.1559002770788384e-05, "loss": 1.6362, "step": 89700 }, { "epoch": 2.26, "learning_rate": 1.1543403438427223e-05, "loss": 1.6122, "step": 89800 }, { "epoch": 2.26, "learning_rate": 1.1527800257761787e-05, "loss": 1.6909, "step": 89900 }, { "epoch": 2.26, "learning_rate": 1.1512193267696876e-05, "loss": 1.7437, "step": 90000 }, { "epoch": 2.26, "learning_rate": 1.1496582507146773e-05, "loss": 1.6401, "step": 90100 }, { "epoch": 2.27, "learning_rate": 1.148096801503517e-05, "loss": 1.4777, "step": 90200 }, { "epoch": 2.27, "learning_rate": 1.1465349830295059e-05, "loss": 1.6512, "step": 90300 }, { "epoch": 2.27, "learning_rate": 1.144972799186864e-05, "loss": 1.343, "step": 90400 }, { "epoch": 2.27, "learning_rate": 1.1434102538707225e-05, "loss": 1.5105, "step": 90500 }, { "epoch": 2.28, "learning_rate": 1.1418473509771143e-05, "loss": 1.5863, "step": 90600 }, { "epoch": 2.28, "learning_rate": 1.1402840944029627e-05, "loss": 1.5929, "step": 90700 }, { "epoch": 2.28, "learning_rate": 1.1387204880460736e-05, "loss": 1.606, "step": 90800 }, { "epoch": 2.28, "learning_rate": 1.1371565358051258e-05, "loss": 1.5751, "step": 90900 }, { "epoch": 2.29, "learning_rate": 1.1355922415796586e-05, "loss": 1.3173, "step": 91000 }, { "epoch": 2.29, "learning_rate": 1.134027609270066e-05, "loss": 1.7935, "step": 91100 }, { "epoch": 2.29, "learning_rate": 1.1324626427775836e-05, "loss": 1.67, "step": 91200 }, { "epoch": 2.29, "learning_rate": 1.1308973460042809e-05, "loss": 1.4579, "step": 91300 }, { "epoch": 2.3, "learning_rate": 1.1293317228530506e-05, "loss": 1.7644, "step": 91400 }, { "epoch": 2.3, "learning_rate": 1.1277657772275999e-05, "loss": 1.7796, "step": 91500 }, { "epoch": 2.3, "learning_rate": 1.1261995130324385e-05, "loss": 1.643, "step": 91600 }, { "epoch": 2.3, "learning_rate": 1.1246329341728726e-05, "loss": 1.5704, "step": 91700 }, { "epoch": 2.31, "learning_rate": 1.1230660445549906e-05, "loss": 1.6084, "step": 91800 }, { "epoch": 2.31, "learning_rate": 1.1214988480856576e-05, "loss": 1.5432, "step": 91900 }, { "epoch": 2.31, "learning_rate": 1.1199313486725034e-05, "loss": 1.5549, "step": 92000 }, { "epoch": 2.31, "learning_rate": 1.1183635502239123e-05, "loss": 1.6265, "step": 92100 }, { "epoch": 2.32, "learning_rate": 1.1167954566490153e-05, "loss": 1.4822, "step": 92200 }, { "epoch": 2.32, "learning_rate": 1.1152270718576784e-05, "loss": 1.6895, "step": 92300 }, { "epoch": 2.32, "learning_rate": 1.1136583997604942e-05, "loss": 1.55, "step": 92400 }, { "epoch": 2.32, "learning_rate": 1.1120894442687715e-05, "loss": 1.5429, "step": 92500 }, { "epoch": 2.33, "learning_rate": 1.110520209294526e-05, "loss": 1.5462, "step": 92600 }, { "epoch": 2.33, "learning_rate": 1.1089506987504697e-05, "loss": 1.6085, "step": 92700 }, { "epoch": 2.33, "learning_rate": 1.1073809165500025e-05, "loss": 1.5437, "step": 92800 }, { "epoch": 2.33, "learning_rate": 1.1058108666072002e-05, "loss": 1.5362, "step": 92900 }, { "epoch": 2.34, "learning_rate": 1.1042405528368083e-05, "loss": 1.4636, "step": 93000 }, { "epoch": 2.34, "learning_rate": 1.1026699791542284e-05, "loss": 1.6231, "step": 93100 }, { "epoch": 2.34, "learning_rate": 1.1010991494755106e-05, "loss": 1.7617, "step": 93200 }, { "epoch": 2.34, "learning_rate": 1.099528067717344e-05, "loss": 1.5536, "step": 93300 }, { "epoch": 2.35, "learning_rate": 1.0979567377970452e-05, "loss": 1.363, "step": 93400 }, { "epoch": 2.35, "learning_rate": 1.0963851636325502e-05, "loss": 1.5323, "step": 93500 }, { "epoch": 2.35, "learning_rate": 1.0948133491424038e-05, "loss": 1.5152, "step": 93600 }, { "epoch": 2.35, "learning_rate": 1.0932412982457502e-05, "loss": 1.4381, "step": 93700 }, { "epoch": 2.36, "learning_rate": 1.0916690148623224e-05, "loss": 1.3717, "step": 93800 }, { "epoch": 2.36, "learning_rate": 1.0900965029124342e-05, "loss": 1.518, "step": 93900 }, { "epoch": 2.36, "learning_rate": 1.0885237663169684e-05, "loss": 1.5327, "step": 94000 }, { "epoch": 2.36, "learning_rate": 1.0869508089973681e-05, "loss": 1.5696, "step": 94100 }, { "epoch": 2.37, "learning_rate": 1.0853776348756274e-05, "loss": 1.694, "step": 94200 }, { "epoch": 2.37, "learning_rate": 1.0838042478742798e-05, "loss": 1.7374, "step": 94300 }, { "epoch": 2.37, "learning_rate": 1.0822306519163908e-05, "loss": 1.6499, "step": 94400 }, { "epoch": 2.37, "learning_rate": 1.0806568509255458e-05, "loss": 1.7191, "step": 94500 }, { "epoch": 2.38, "learning_rate": 1.0790828488258424e-05, "loss": 1.5961, "step": 94600 }, { "epoch": 2.38, "learning_rate": 1.0775086495418791e-05, "loss": 1.6597, "step": 94700 }, { "epoch": 2.38, "learning_rate": 1.0759342569987461e-05, "loss": 1.6895, "step": 94800 }, { "epoch": 2.38, "learning_rate": 1.0743754218650935e-05, "loss": 1.6971, "step": 94900 }, { "epoch": 2.39, "learning_rate": 1.0728006564154498e-05, "loss": 1.7573, "step": 95000 }, { "epoch": 2.39, "learning_rate": 1.071225709445492e-05, "loss": 1.538, "step": 95100 }, { "epoch": 2.39, "learning_rate": 1.069650584882175e-05, "loss": 1.6128, "step": 95200 }, { "epoch": 2.39, "learning_rate": 1.0680752866528954e-05, "loss": 1.8315, "step": 95300 }, { "epoch": 2.4, "learning_rate": 1.066499818685484e-05, "loss": 1.7549, "step": 95400 }, { "epoch": 2.4, "learning_rate": 1.0649241849081945e-05, "loss": 1.5704, "step": 95500 }, { "epoch": 2.4, "learning_rate": 1.0633483892496938e-05, "loss": 1.5987, "step": 95600 }, { "epoch": 2.4, "learning_rate": 1.0617724356390528e-05, "loss": 1.5178, "step": 95700 }, { "epoch": 2.41, "learning_rate": 1.0601963280057354e-05, "loss": 1.6961, "step": 95800 }, { "epoch": 2.41, "learning_rate": 1.0586200702795908e-05, "loss": 1.5233, "step": 95900 }, { "epoch": 2.41, "learning_rate": 1.0570436663908412e-05, "loss": 1.5493, "step": 96000 }, { "epoch": 2.41, "learning_rate": 1.0554671202700742e-05, "loss": 1.5388, "step": 96100 }, { "epoch": 2.42, "learning_rate": 1.0539062033641323e-05, "loss": 1.5733, "step": 96200 }, { "epoch": 2.42, "learning_rate": 1.0523293858967374e-05, "loss": 1.4723, "step": 96300 }, { "epoch": 2.42, "learning_rate": 1.0507524379518575e-05, "loss": 1.6448, "step": 96400 }, { "epoch": 2.42, "learning_rate": 1.0491753634614362e-05, "loss": 1.6485, "step": 96500 }, { "epoch": 2.43, "learning_rate": 1.0475981663577328e-05, "loss": 1.7557, "step": 96600 }, { "epoch": 2.43, "learning_rate": 1.0460208505733122e-05, "loss": 1.7331, "step": 96700 }, { "epoch": 2.43, "learning_rate": 1.0444434200410358e-05, "loss": 1.6496, "step": 96800 }, { "epoch": 2.43, "learning_rate": 1.04286587869405e-05, "loss": 1.6028, "step": 96900 }, { "epoch": 2.44, "learning_rate": 1.0412882304657786e-05, "loss": 1.6282, "step": 97000 }, { "epoch": 2.44, "learning_rate": 1.039710479289911e-05, "loss": 1.6374, "step": 97100 }, { "epoch": 2.44, "learning_rate": 1.0381326291003944e-05, "loss": 1.522, "step": 97200 }, { "epoch": 2.44, "learning_rate": 1.0365546838314215e-05, "loss": 1.4434, "step": 97300 }, { "epoch": 2.45, "learning_rate": 1.034976647417423e-05, "loss": 1.5621, "step": 97400 }, { "epoch": 2.45, "learning_rate": 1.0333985237930566e-05, "loss": 1.578, "step": 97500 }, { "epoch": 2.45, "learning_rate": 1.0318203168931975e-05, "loss": 1.4662, "step": 97600 }, { "epoch": 2.45, "learning_rate": 1.0302420306529288e-05, "loss": 1.6144, "step": 97700 }, { "epoch": 2.46, "learning_rate": 1.0286794529843183e-05, "loss": 1.7074, "step": 97800 }, { "epoch": 2.46, "learning_rate": 1.027101020564475e-05, "loss": 1.5317, "step": 97900 }, { "epoch": 2.46, "learning_rate": 1.0255225205712608e-05, "loss": 1.6295, "step": 98000 }, { "epoch": 2.46, "learning_rate": 1.0239439569404896e-05, "loss": 1.6762, "step": 98100 }, { "epoch": 2.47, "learning_rate": 1.022365333608133e-05, "loss": 1.5155, "step": 98200 }, { "epoch": 2.47, "learning_rate": 1.0207866545103125e-05, "loss": 1.6692, "step": 98300 }, { "epoch": 2.47, "learning_rate": 1.0192079235832881e-05, "loss": 1.6259, "step": 98400 }, { "epoch": 2.47, "learning_rate": 1.0176291447634497e-05, "loss": 1.6242, "step": 98500 }, { "epoch": 2.48, "learning_rate": 1.0160503219873055e-05, "loss": 1.6459, "step": 98600 }, { "epoch": 2.48, "learning_rate": 1.0144714591914741e-05, "loss": 1.7056, "step": 98700 }, { "epoch": 2.48, "learning_rate": 1.0128925603126741e-05, "loss": 1.4721, "step": 98800 }, { "epoch": 2.48, "learning_rate": 1.0113136292877135e-05, "loss": 1.6886, "step": 98900 }, { "epoch": 2.49, "learning_rate": 1.0097346700534804e-05, "loss": 1.484, "step": 99000 }, { "epoch": 2.49, "learning_rate": 1.0081556865469336e-05, "loss": 1.5845, "step": 99100 }, { "epoch": 2.49, "learning_rate": 1.0065766827050926e-05, "loss": 1.8109, "step": 99200 }, { "epoch": 2.49, "learning_rate": 1.0049976624650269e-05, "loss": 1.5233, "step": 99300 }, { "epoch": 2.5, "learning_rate": 1.0034186297638475e-05, "loss": 1.5552, "step": 99400 }, { "epoch": 2.5, "learning_rate": 1.0018395885386962e-05, "loss": 1.7768, "step": 99500 }, { "epoch": 2.5, "learning_rate": 1.0002605427267363e-05, "loss": 1.557, "step": 99600 }, { "epoch": 2.5, "learning_rate": 9.98681496265142e-06, "loss": 1.5228, "step": 99700 }, { "epoch": 2.51, "learning_rate": 9.971024530910894e-06, "loss": 1.601, "step": 99800 }, { "epoch": 2.51, "learning_rate": 9.955234171417472e-06, "loss": 1.7041, "step": 99900 }, { "epoch": 2.51, "learning_rate": 9.93944392354265e-06, "loss": 1.6165, "step": 100000 }, { "epoch": 2.51, "learning_rate": 9.923653826657642e-06, "loss": 1.4589, "step": 100100 }, { "epoch": 2.52, "learning_rate": 9.907863920133303e-06, "loss": 1.5414, "step": 100200 }, { "epoch": 2.52, "learning_rate": 9.892074243339996e-06, "loss": 1.633, "step": 100300 }, { "epoch": 2.52, "learning_rate": 9.876442728263133e-06, "loss": 1.7658, "step": 100400 }, { "epoch": 2.52, "learning_rate": 9.860653625761045e-06, "loss": 1.4471, "step": 100500 }, { "epoch": 2.53, "learning_rate": 9.844864870703592e-06, "loss": 1.5261, "step": 100600 }, { "epoch": 2.53, "learning_rate": 9.829076502458277e-06, "loss": 1.5347, "step": 100700 }, { "epoch": 2.53, "learning_rate": 9.813288560391635e-06, "loss": 1.5035, "step": 100800 }, { "epoch": 2.53, "learning_rate": 9.79750108386913e-06, "loss": 1.5075, "step": 100900 }, { "epoch": 2.54, "learning_rate": 9.781714112255083e-06, "loss": 1.5341, "step": 101000 }, { "epoch": 2.54, "learning_rate": 9.765927684912537e-06, "loss": 1.5804, "step": 101100 }, { "epoch": 2.54, "learning_rate": 9.750141841203193e-06, "loss": 1.6443, "step": 101200 }, { "epoch": 2.54, "learning_rate": 9.734356620487295e-06, "loss": 1.6232, "step": 101300 }, { "epoch": 2.55, "learning_rate": 9.718572062123523e-06, "loss": 1.4144, "step": 101400 }, { "epoch": 2.55, "learning_rate": 9.702788205468912e-06, "loss": 1.5492, "step": 101500 }, { "epoch": 2.55, "learning_rate": 9.68700508987875e-06, "loss": 1.6528, "step": 101600 }, { "epoch": 2.55, "learning_rate": 9.671222754706478e-06, "loss": 1.4979, "step": 101700 }, { "epoch": 2.56, "learning_rate": 9.655441239303578e-06, "loss": 1.6166, "step": 101800 }, { "epoch": 2.56, "learning_rate": 9.639660583019507e-06, "loss": 1.684, "step": 101900 }, { "epoch": 2.56, "learning_rate": 9.623880825201566e-06, "loss": 1.2842, "step": 102000 }, { "epoch": 2.56, "learning_rate": 9.608102005194823e-06, "loss": 1.522, "step": 102100 }, { "epoch": 2.57, "learning_rate": 9.592324162342008e-06, "loss": 1.6282, "step": 102200 }, { "epoch": 2.57, "learning_rate": 9.576547335983402e-06, "loss": 1.8509, "step": 102300 }, { "epoch": 2.57, "learning_rate": 9.560771565456772e-06, "loss": 1.5174, "step": 102400 }, { "epoch": 2.57, "learning_rate": 9.544996890097232e-06, "loss": 1.7027, "step": 102500 }, { "epoch": 2.58, "learning_rate": 9.529223349237186e-06, "loss": 1.6712, "step": 102600 }, { "epoch": 2.58, "learning_rate": 9.513450982206188e-06, "loss": 1.5752, "step": 102700 }, { "epoch": 2.58, "learning_rate": 9.497679828330878e-06, "loss": 1.5511, "step": 102800 }, { "epoch": 2.58, "learning_rate": 9.481909926934872e-06, "loss": 1.3991, "step": 102900 }, { "epoch": 2.59, "learning_rate": 9.46614131733866e-06, "loss": 1.6597, "step": 103000 }, { "epoch": 2.59, "learning_rate": 9.450374038859504e-06, "loss": 1.3541, "step": 103100 }, { "epoch": 2.59, "learning_rate": 9.434608130811362e-06, "loss": 1.5658, "step": 103200 }, { "epoch": 2.59, "learning_rate": 9.418843632504756e-06, "loss": 1.5591, "step": 103300 }, { "epoch": 2.6, "learning_rate": 9.403080583246716e-06, "loss": 1.5797, "step": 103400 }, { "epoch": 2.6, "learning_rate": 9.387319022340642e-06, "loss": 1.5591, "step": 103500 }, { "epoch": 2.6, "learning_rate": 9.37155898908622e-06, "loss": 1.6079, "step": 103600 }, { "epoch": 2.6, "learning_rate": 9.355800522779346e-06, "loss": 1.6908, "step": 103700 }, { "epoch": 2.61, "learning_rate": 9.340043662711988e-06, "loss": 1.5744, "step": 103800 }, { "epoch": 2.61, "learning_rate": 9.32428844817213e-06, "loss": 1.5306, "step": 103900 }, { "epoch": 2.61, "learning_rate": 9.308534918443627e-06, "loss": 1.6904, "step": 104000 }, { "epoch": 2.61, "learning_rate": 9.292783112806158e-06, "loss": 1.5853, "step": 104100 }, { "epoch": 2.62, "learning_rate": 9.277033070535088e-06, "loss": 1.4596, "step": 104200 }, { "epoch": 2.62, "learning_rate": 9.261284830901393e-06, "loss": 1.5564, "step": 104300 }, { "epoch": 2.62, "learning_rate": 9.245695887902507e-06, "loss": 1.5895, "step": 104400 }, { "epoch": 2.62, "learning_rate": 9.229951352332415e-06, "loss": 1.5223, "step": 104500 }, { "epoch": 2.63, "learning_rate": 9.214208736792706e-06, "loss": 1.4883, "step": 104600 }, { "epoch": 2.63, "learning_rate": 9.198468080535841e-06, "loss": 1.7945, "step": 104700 }, { "epoch": 2.63, "learning_rate": 9.182729422809388e-06, "loss": 1.6831, "step": 104800 }, { "epoch": 2.63, "learning_rate": 9.166992802855927e-06, "loss": 1.7584, "step": 104900 }, { "epoch": 2.64, "learning_rate": 9.151258259912975e-06, "loss": 1.5457, "step": 105000 }, { "epoch": 2.64, "learning_rate": 9.13552583321285e-06, "loss": 1.3621, "step": 105100 }, { "epoch": 2.64, "learning_rate": 9.119795561982611e-06, "loss": 1.6464, "step": 105200 }, { "epoch": 2.64, "learning_rate": 9.104067485443924e-06, "loss": 1.6196, "step": 105300 }, { "epoch": 2.65, "learning_rate": 9.088341642813003e-06, "loss": 1.6884, "step": 105400 }, { "epoch": 2.65, "learning_rate": 9.072618073300477e-06, "loss": 1.5198, "step": 105500 }, { "epoch": 2.65, "learning_rate": 9.056896816111314e-06, "loss": 1.4461, "step": 105600 }, { "epoch": 2.66, "learning_rate": 9.041177910444715e-06, "loss": 1.7175, "step": 105700 }, { "epoch": 2.66, "learning_rate": 9.025461395494013e-06, "loss": 1.5441, "step": 105800 }, { "epoch": 2.66, "learning_rate": 9.009747310446589e-06, "loss": 1.3573, "step": 105900 }, { "epoch": 2.66, "learning_rate": 8.994035694483758e-06, "loss": 1.4871, "step": 106000 }, { "epoch": 2.67, "learning_rate": 8.978326586780688e-06, "loss": 1.6274, "step": 106100 }, { "epoch": 2.67, "learning_rate": 8.962620026506277e-06, "loss": 1.4913, "step": 106200 }, { "epoch": 2.67, "learning_rate": 8.946916052823085e-06, "loss": 1.3965, "step": 106300 }, { "epoch": 2.67, "learning_rate": 8.931214704887219e-06, "loss": 1.5782, "step": 106400 }, { "epoch": 2.68, "learning_rate": 8.915516021848239e-06, "loss": 1.5163, "step": 106500 }, { "epoch": 2.68, "learning_rate": 8.899820042849054e-06, "loss": 1.6809, "step": 106600 }, { "epoch": 2.68, "learning_rate": 8.884126807025843e-06, "loss": 1.5843, "step": 106700 }, { "epoch": 2.68, "learning_rate": 8.868436353507933e-06, "loss": 1.5234, "step": 106800 }, { "epoch": 2.69, "learning_rate": 8.852748721417724e-06, "loss": 1.545, "step": 106900 }, { "epoch": 2.69, "learning_rate": 8.837063949870576e-06, "loss": 1.4704, "step": 107000 }, { "epoch": 2.69, "learning_rate": 8.821382077974713e-06, "loss": 1.4108, "step": 107100 }, { "epoch": 2.69, "learning_rate": 8.805703144831134e-06, "loss": 1.4453, "step": 107200 }, { "epoch": 2.7, "learning_rate": 8.790027189533511e-06, "loss": 1.5554, "step": 107300 }, { "epoch": 2.7, "learning_rate": 8.77435425116809e-06, "loss": 1.5883, "step": 107400 }, { "epoch": 2.7, "learning_rate": 8.758684368813594e-06, "loss": 1.3589, "step": 107500 }, { "epoch": 2.7, "learning_rate": 8.743017581541123e-06, "loss": 1.5977, "step": 107600 }, { "epoch": 2.71, "learning_rate": 8.727353928414066e-06, "loss": 1.5475, "step": 107700 }, { "epoch": 2.71, "learning_rate": 8.711693448487992e-06, "loss": 1.7158, "step": 107800 }, { "epoch": 2.71, "learning_rate": 8.696036180810566e-06, "loss": 1.4865, "step": 107900 }, { "epoch": 2.71, "learning_rate": 8.680382164421433e-06, "loss": 1.4768, "step": 108000 }, { "epoch": 2.72, "learning_rate": 8.664731438352134e-06, "loss": 1.447, "step": 108100 }, { "epoch": 2.72, "learning_rate": 8.649084041626014e-06, "loss": 1.5726, "step": 108200 }, { "epoch": 2.72, "learning_rate": 8.633440013258113e-06, "loss": 1.5929, "step": 108300 }, { "epoch": 2.72, "learning_rate": 8.617955781470574e-06, "loss": 1.6388, "step": 108400 }, { "epoch": 2.73, "learning_rate": 8.602318572173878e-06, "loss": 1.5383, "step": 108500 }, { "epoch": 2.73, "learning_rate": 8.586684847839875e-06, "loss": 1.6516, "step": 108600 }, { "epoch": 2.73, "learning_rate": 8.571054647449517e-06, "loss": 1.6333, "step": 108700 }, { "epoch": 2.73, "learning_rate": 8.55542800997496e-06, "loss": 1.6239, "step": 108800 }, { "epoch": 2.74, "learning_rate": 8.53980497437948e-06, "loss": 1.4631, "step": 108900 }, { "epoch": 2.74, "learning_rate": 8.52418557961738e-06, "loss": 1.5702, "step": 109000 }, { "epoch": 2.74, "learning_rate": 8.50856986463387e-06, "loss": 1.6284, "step": 109100 }, { "epoch": 2.74, "learning_rate": 8.492957868365002e-06, "loss": 1.5192, "step": 109200 }, { "epoch": 2.75, "learning_rate": 8.477349629737537e-06, "loss": 1.572, "step": 109300 }, { "epoch": 2.75, "learning_rate": 8.461745187668884e-06, "loss": 1.549, "step": 109400 }, { "epoch": 2.75, "learning_rate": 8.446144581066976e-06, "loss": 1.5624, "step": 109500 }, { "epoch": 2.75, "learning_rate": 8.430547848830185e-06, "loss": 1.5753, "step": 109600 }, { "epoch": 2.76, "learning_rate": 8.414955029847222e-06, "loss": 1.5821, "step": 109700 }, { "epoch": 2.76, "learning_rate": 8.399366162997039e-06, "loss": 1.4767, "step": 109800 }, { "epoch": 2.76, "learning_rate": 8.38378128714874e-06, "loss": 1.5977, "step": 109900 }, { "epoch": 2.76, "learning_rate": 8.368200441161473e-06, "loss": 1.4919, "step": 110000 }, { "epoch": 2.77, "learning_rate": 8.352623663884342e-06, "loss": 1.6945, "step": 110100 }, { "epoch": 2.77, "learning_rate": 8.337050994156297e-06, "loss": 1.6239, "step": 110200 }, { "epoch": 2.77, "learning_rate": 8.321482470806054e-06, "loss": 1.5393, "step": 110300 }, { "epoch": 2.77, "learning_rate": 8.305918132651994e-06, "loss": 1.782, "step": 110400 }, { "epoch": 2.78, "learning_rate": 8.290358018502054e-06, "loss": 1.6213, "step": 110500 }, { "epoch": 2.78, "learning_rate": 8.274802167153639e-06, "loss": 1.6894, "step": 110600 }, { "epoch": 2.78, "learning_rate": 8.259250617393535e-06, "loss": 1.7082, "step": 110700 }, { "epoch": 2.78, "learning_rate": 8.24370340799779e-06, "loss": 1.4983, "step": 110800 }, { "epoch": 2.79, "learning_rate": 8.228160577731645e-06, "loss": 1.6077, "step": 110900 }, { "epoch": 2.79, "learning_rate": 8.212622165349405e-06, "loss": 1.7997, "step": 111000 }, { "epoch": 2.79, "learning_rate": 8.197088209594368e-06, "loss": 1.5131, "step": 111100 }, { "epoch": 2.79, "learning_rate": 8.181558749198722e-06, "loss": 1.5432, "step": 111200 }, { "epoch": 2.8, "learning_rate": 8.166033822883443e-06, "loss": 1.5817, "step": 111300 }, { "epoch": 2.8, "learning_rate": 8.150513469358207e-06, "loss": 1.5234, "step": 111400 }, { "epoch": 2.8, "learning_rate": 8.134997727321277e-06, "loss": 1.4133, "step": 111500 }, { "epoch": 2.8, "learning_rate": 8.119486635459425e-06, "loss": 1.7276, "step": 111600 }, { "epoch": 2.81, "learning_rate": 8.103980232447834e-06, "loss": 1.4738, "step": 111700 }, { "epoch": 2.81, "learning_rate": 8.088478556949988e-06, "loss": 1.6447, "step": 111800 }, { "epoch": 2.81, "learning_rate": 8.072981647617576e-06, "loss": 1.5666, "step": 111900 }, { "epoch": 2.81, "learning_rate": 8.057489543090426e-06, "loss": 1.4757, "step": 112000 }, { "epoch": 2.82, "learning_rate": 8.042002281996361e-06, "loss": 1.525, "step": 112100 }, { "epoch": 2.82, "learning_rate": 8.026519902951146e-06, "loss": 1.3649, "step": 112200 }, { "epoch": 2.82, "learning_rate": 8.011042444558366e-06, "loss": 1.6476, "step": 112300 }, { "epoch": 2.82, "learning_rate": 7.99556994540933e-06, "loss": 1.4928, "step": 112400 }, { "epoch": 2.83, "learning_rate": 7.980102444082991e-06, "loss": 1.5354, "step": 112500 }, { "epoch": 2.83, "learning_rate": 7.96463997914584e-06, "loss": 1.5008, "step": 112600 }, { "epoch": 2.83, "learning_rate": 7.949182589151809e-06, "loss": 1.6191, "step": 112700 }, { "epoch": 2.83, "learning_rate": 7.933730312642172e-06, "loss": 1.5635, "step": 112800 }, { "epoch": 2.84, "learning_rate": 7.918283188145456e-06, "loss": 1.5259, "step": 112900 }, { "epoch": 2.84, "learning_rate": 7.902841254177342e-06, "loss": 1.687, "step": 113000 }, { "epoch": 2.84, "learning_rate": 7.88740454924058e-06, "loss": 1.5634, "step": 113100 }, { "epoch": 2.84, "learning_rate": 7.871973111824856e-06, "loss": 1.7412, "step": 113200 }, { "epoch": 2.85, "learning_rate": 7.856546980406743e-06, "loss": 1.6292, "step": 113300 }, { "epoch": 2.85, "learning_rate": 7.841126193449584e-06, "loss": 1.6738, "step": 113400 }, { "epoch": 2.85, "learning_rate": 7.825710789403383e-06, "loss": 1.4008, "step": 113500 }, { "epoch": 2.85, "learning_rate": 7.810300806704738e-06, "loss": 1.579, "step": 113600 }, { "epoch": 2.86, "learning_rate": 7.794896283776715e-06, "loss": 1.5167, "step": 113700 }, { "epoch": 2.86, "learning_rate": 7.779497259028771e-06, "loss": 1.5673, "step": 113800 }, { "epoch": 2.86, "learning_rate": 7.764103770856666e-06, "loss": 1.7227, "step": 113900 }, { "epoch": 2.86, "learning_rate": 7.74871585764234e-06, "loss": 1.5478, "step": 114000 }, { "epoch": 2.87, "learning_rate": 7.733333557753833e-06, "loss": 1.7847, "step": 114100 }, { "epoch": 2.87, "learning_rate": 7.7179569095452e-06, "loss": 1.4537, "step": 114200 }, { "epoch": 2.87, "learning_rate": 7.702585951356393e-06, "loss": 1.4885, "step": 114300 }, { "epoch": 2.87, "learning_rate": 7.6873743453305e-06, "loss": 1.5601, "step": 114400 }, { "epoch": 2.88, "learning_rate": 7.672014824288214e-06, "loss": 1.4256, "step": 114500 }, { "epoch": 2.88, "learning_rate": 7.656661107817215e-06, "loss": 1.4908, "step": 114600 }, { "epoch": 2.88, "learning_rate": 7.64131323420029e-06, "loss": 1.6016, "step": 114700 }, { "epoch": 2.88, "learning_rate": 7.625971241705643e-06, "loss": 1.5315, "step": 114800 }, { "epoch": 2.89, "learning_rate": 7.610635168586829e-06, "loss": 1.5234, "step": 114900 }, { "epoch": 2.89, "learning_rate": 7.595305053082628e-06, "loss": 1.5272, "step": 115000 }, { "epoch": 2.89, "learning_rate": 7.579980933416972e-06, "loss": 1.3622, "step": 115100 }, { "epoch": 2.89, "learning_rate": 7.564662847798848e-06, "loss": 1.5475, "step": 115200 }, { "epoch": 2.9, "learning_rate": 7.549350834422195e-06, "loss": 1.6402, "step": 115300 }, { "epoch": 2.9, "learning_rate": 7.534044931465802e-06, "loss": 1.6139, "step": 115400 }, { "epoch": 2.9, "learning_rate": 7.518745177093236e-06, "loss": 1.5802, "step": 115500 }, { "epoch": 2.9, "learning_rate": 7.503451609452725e-06, "loss": 1.4628, "step": 115600 }, { "epoch": 2.91, "learning_rate": 7.488164266677078e-06, "loss": 1.458, "step": 115700 }, { "epoch": 2.91, "learning_rate": 7.472883186883577e-06, "loss": 1.6286, "step": 115800 }, { "epoch": 2.91, "learning_rate": 7.457608408173883e-06, "loss": 1.4971, "step": 115900 }, { "epoch": 2.91, "learning_rate": 7.44233996863396e-06, "loss": 1.4621, "step": 116000 }, { "epoch": 2.92, "learning_rate": 7.427077906333953e-06, "loss": 1.5817, "step": 116100 }, { "epoch": 2.92, "learning_rate": 7.411822259328119e-06, "loss": 1.566, "step": 116200 }, { "epoch": 2.92, "learning_rate": 7.3965730656547044e-06, "loss": 1.4478, "step": 116300 }, { "epoch": 2.92, "learning_rate": 7.3814827581020496e-06, "loss": 1.6612, "step": 116400 }, { "epoch": 2.93, "learning_rate": 7.366246519662102e-06, "loss": 1.6283, "step": 116500 }, { "epoch": 2.93, "learning_rate": 7.351016848192598e-06, "loss": 1.5307, "step": 116600 }, { "epoch": 2.93, "learning_rate": 7.335945979513159e-06, "loss": 1.5192, "step": 116700 }, { "epoch": 2.93, "learning_rate": 7.32072948927169e-06, "loss": 1.5293, "step": 116800 }, { "epoch": 2.94, "learning_rate": 7.305519679492299e-06, "loss": 1.5403, "step": 116900 }, { "epoch": 2.94, "learning_rate": 7.2903165880989546e-06, "loss": 1.4596, "step": 117000 }, { "epoch": 2.94, "learning_rate": 7.275120252998869e-06, "loss": 1.4479, "step": 117100 }, { "epoch": 2.94, "learning_rate": 7.2599307120824e-06, "loss": 1.5635, "step": 117200 }, { "epoch": 2.95, "learning_rate": 7.2447480032229815e-06, "loss": 1.5154, "step": 117300 }, { "epoch": 2.95, "learning_rate": 7.229572164276999e-06, "loss": 1.7034, "step": 117400 }, { "epoch": 2.95, "learning_rate": 7.214403233083721e-06, "loss": 1.7147, "step": 117500 }, { "epoch": 2.95, "learning_rate": 7.1992412474651785e-06, "loss": 1.5747, "step": 117600 }, { "epoch": 2.96, "learning_rate": 7.184086245226089e-06, "loss": 1.5234, "step": 117700 }, { "epoch": 2.96, "learning_rate": 7.168938264153762e-06, "loss": 1.4865, "step": 117800 }, { "epoch": 2.96, "learning_rate": 7.153797342018003e-06, "loss": 1.5403, "step": 117900 }, { "epoch": 2.96, "learning_rate": 7.13866351657101e-06, "loss": 1.5328, "step": 118000 }, { "epoch": 2.97, "learning_rate": 7.123536825547283e-06, "loss": 1.4935, "step": 118100 }, { "epoch": 2.97, "learning_rate": 7.108417306663542e-06, "loss": 1.7492, "step": 118200 }, { "epoch": 2.97, "learning_rate": 7.09330499761862e-06, "loss": 1.6109, "step": 118300 }, { "epoch": 2.97, "learning_rate": 7.078199936093377e-06, "loss": 1.5259, "step": 118400 }, { "epoch": 2.98, "learning_rate": 7.063102159750592e-06, "loss": 1.5748, "step": 118500 }, { "epoch": 2.98, "learning_rate": 7.048011706234888e-06, "loss": 1.7565, "step": 118600 }, { "epoch": 2.98, "learning_rate": 7.032928613172632e-06, "loss": 1.5787, "step": 118700 }, { "epoch": 2.98, "learning_rate": 7.017852918171828e-06, "loss": 1.3929, "step": 118800 }, { "epoch": 2.99, "learning_rate": 7.00278465882204e-06, "loss": 1.4722, "step": 118900 }, { "epoch": 2.99, "learning_rate": 6.9877238726942945e-06, "loss": 1.7614, "step": 119000 }, { "epoch": 2.99, "learning_rate": 6.972670597340976e-06, "loss": 1.5873, "step": 119100 }, { "epoch": 2.99, "learning_rate": 6.9576248702957525e-06, "loss": 1.4601, "step": 119200 }, { "epoch": 3.0, "learning_rate": 6.942586729073466e-06, "loss": 1.6497, "step": 119300 }, { "epoch": 3.0, "learning_rate": 6.927556211170039e-06, "loss": 1.4774, "step": 119400 }, { "epoch": 3.0, "eval_loss": 1.4340847730636597, "eval_runtime": 105.0404, "eval_samples_per_second": 75.809, "eval_steps_per_second": 9.482, "step": 119433 }, { "epoch": 3.0, "learning_rate": 6.912533354062394e-06, "loss": 1.4746, "step": 119500 }, { "epoch": 3.0, "learning_rate": 6.897518195208346e-06, "loss": 1.7601, "step": 119600 }, { "epoch": 3.01, "learning_rate": 6.882660807863584e-06, "loss": 1.6917, "step": 119700 }, { "epoch": 3.01, "learning_rate": 6.867811038578836e-06, "loss": 1.5032, "step": 119800 }, { "epoch": 3.01, "learning_rate": 6.852819042463457e-06, "loss": 1.5407, "step": 119900 }, { "epoch": 3.01, "learning_rate": 6.8378348934926516e-06, "loss": 1.4122, "step": 120000 }, { "epoch": 3.02, "learning_rate": 6.822858629027727e-06, "loss": 1.6369, "step": 120100 }, { "epoch": 3.02, "learning_rate": 6.8078902864103165e-06, "loss": 1.6638, "step": 120200 }, { "epoch": 3.02, "learning_rate": 6.792929902962322e-06, "loss": 1.6569, "step": 120300 }, { "epoch": 3.02, "learning_rate": 6.7779775159857854e-06, "loss": 1.5367, "step": 120400 }, { "epoch": 3.03, "learning_rate": 6.7630331627628185e-06, "loss": 1.4767, "step": 120500 }, { "epoch": 3.03, "learning_rate": 6.7480968805555015e-06, "loss": 1.3931, "step": 120600 }, { "epoch": 3.03, "learning_rate": 6.733168706605777e-06, "loss": 1.5617, "step": 120700 }, { "epoch": 3.03, "learning_rate": 6.718248678135393e-06, "loss": 1.7781, "step": 120800 }, { "epoch": 3.04, "learning_rate": 6.703336832345766e-06, "loss": 1.6472, "step": 120900 }, { "epoch": 3.04, "learning_rate": 6.688433206417929e-06, "loss": 1.5311, "step": 121000 }, { "epoch": 3.04, "learning_rate": 6.673537837512404e-06, "loss": 1.7496, "step": 121100 }, { "epoch": 3.04, "learning_rate": 6.65865076276913e-06, "loss": 1.6498, "step": 121200 }, { "epoch": 3.05, "learning_rate": 6.643772019307373e-06, "loss": 1.5578, "step": 121300 }, { "epoch": 3.05, "learning_rate": 6.628901644225614e-06, "loss": 1.4269, "step": 121400 }, { "epoch": 3.05, "learning_rate": 6.614039674601481e-06, "loss": 1.5012, "step": 121500 }, { "epoch": 3.05, "learning_rate": 6.599186147491632e-06, "loss": 1.6889, "step": 121600 }, { "epoch": 3.06, "learning_rate": 6.584341099931677e-06, "loss": 1.4733, "step": 121700 }, { "epoch": 3.06, "learning_rate": 6.569504568936089e-06, "loss": 1.6292, "step": 121800 }, { "epoch": 3.06, "learning_rate": 6.554676591498109e-06, "loss": 1.4752, "step": 121900 }, { "epoch": 3.06, "learning_rate": 6.539857204589632e-06, "loss": 1.7536, "step": 122000 }, { "epoch": 3.07, "learning_rate": 6.5250464451611514e-06, "loss": 1.59, "step": 122100 }, { "epoch": 3.07, "learning_rate": 6.510244350141648e-06, "loss": 1.7886, "step": 122200 }, { "epoch": 3.07, "learning_rate": 6.495450956438491e-06, "loss": 1.4779, "step": 122300 }, { "epoch": 3.07, "learning_rate": 6.48066630093735e-06, "loss": 1.5565, "step": 122400 }, { "epoch": 3.08, "learning_rate": 6.465890420502126e-06, "loss": 1.7939, "step": 122500 }, { "epoch": 3.08, "learning_rate": 6.451123351974818e-06, "loss": 1.4665, "step": 122600 }, { "epoch": 3.08, "learning_rate": 6.436365132175468e-06, "loss": 1.6097, "step": 122700 }, { "epoch": 3.08, "learning_rate": 6.4216157979020554e-06, "loss": 1.3935, "step": 122800 }, { "epoch": 3.09, "learning_rate": 6.406875385930389e-06, "loss": 1.4542, "step": 122900 }, { "epoch": 3.09, "learning_rate": 6.39214393301405e-06, "loss": 1.7555, "step": 123000 }, { "epoch": 3.09, "learning_rate": 6.377421475884267e-06, "loss": 1.6864, "step": 123100 }, { "epoch": 3.09, "learning_rate": 6.362708051249851e-06, "loss": 1.2799, "step": 123200 }, { "epoch": 3.1, "learning_rate": 6.348003695797078e-06, "loss": 1.6323, "step": 123300 }, { "epoch": 3.1, "learning_rate": 6.333308446189619e-06, "loss": 1.5903, "step": 123400 }, { "epoch": 3.1, "learning_rate": 6.318622339068441e-06, "loss": 1.6682, "step": 123500 }, { "epoch": 3.1, "learning_rate": 6.303945411051712e-06, "loss": 1.5656, "step": 123600 }, { "epoch": 3.11, "learning_rate": 6.289277698734719e-06, "loss": 1.5184, "step": 123700 }, { "epoch": 3.11, "learning_rate": 6.274619238689761e-06, "loss": 1.433, "step": 123800 }, { "epoch": 3.11, "learning_rate": 6.259970067466072e-06, "loss": 1.3651, "step": 123900 }, { "epoch": 3.11, "learning_rate": 6.245330221589729e-06, "loss": 1.5621, "step": 124000 }, { "epoch": 3.12, "learning_rate": 6.230699737563557e-06, "loss": 1.6011, "step": 124100 }, { "epoch": 3.12, "learning_rate": 6.2160786518670266e-06, "loss": 1.5385, "step": 124200 }, { "epoch": 3.12, "learning_rate": 6.201467000956191e-06, "loss": 1.7246, "step": 124300 }, { "epoch": 3.12, "learning_rate": 6.186864821263568e-06, "loss": 1.3, "step": 124400 }, { "epoch": 3.13, "learning_rate": 6.172272149198068e-06, "loss": 1.5876, "step": 124500 }, { "epoch": 3.13, "learning_rate": 6.157689021144887e-06, "loss": 1.5561, "step": 124600 }, { "epoch": 3.13, "learning_rate": 6.143115473465425e-06, "loss": 1.395, "step": 124700 }, { "epoch": 3.13, "learning_rate": 6.128551542497203e-06, "loss": 1.6815, "step": 124800 }, { "epoch": 3.14, "learning_rate": 6.1139972645537525e-06, "loss": 1.5594, "step": 124900 }, { "epoch": 3.14, "learning_rate": 6.0994526759245485e-06, "loss": 1.4238, "step": 125000 }, { "epoch": 3.14, "learning_rate": 6.084917812874893e-06, "loss": 1.5036, "step": 125100 }, { "epoch": 3.14, "learning_rate": 6.070392711645847e-06, "loss": 1.8192, "step": 125200 }, { "epoch": 3.15, "learning_rate": 6.055877408454132e-06, "loss": 1.4584, "step": 125300 }, { "epoch": 3.15, "learning_rate": 6.0413719394920375e-06, "loss": 1.7073, "step": 125400 }, { "epoch": 3.15, "learning_rate": 6.026876340927328e-06, "loss": 1.5449, "step": 125500 }, { "epoch": 3.15, "learning_rate": 6.012390648903164e-06, "loss": 1.7324, "step": 125600 }, { "epoch": 3.16, "learning_rate": 5.9979148995379995e-06, "loss": 1.5229, "step": 125700 }, { "epoch": 3.16, "learning_rate": 5.983593737118352e-06, "loss": 1.5682, "step": 125800 }, { "epoch": 3.16, "learning_rate": 5.969137881000641e-06, "loss": 1.5016, "step": 125900 }, { "epoch": 3.16, "learning_rate": 5.954692075387876e-06, "loss": 1.5098, "step": 126000 }, { "epoch": 3.17, "learning_rate": 5.94025635629907e-06, "loss": 1.4981, "step": 126100 }, { "epoch": 3.17, "learning_rate": 5.925830759728078e-06, "loss": 1.7784, "step": 126200 }, { "epoch": 3.17, "learning_rate": 5.911415321643514e-06, "loss": 1.769, "step": 126300 }, { "epoch": 3.18, "learning_rate": 5.897010077988661e-06, "loss": 1.6487, "step": 126400 }, { "epoch": 3.18, "learning_rate": 5.88261506468139e-06, "loss": 1.5276, "step": 126500 }, { "epoch": 3.18, "learning_rate": 5.8682303176140605e-06, "loss": 1.5772, "step": 126600 }, { "epoch": 3.18, "learning_rate": 5.85399956598991e-06, "loss": 1.3924, "step": 126700 }, { "epoch": 3.19, "learning_rate": 5.839635355420257e-06, "loss": 1.5139, "step": 126800 }, { "epoch": 3.19, "learning_rate": 5.825281518255652e-06, "loss": 1.653, "step": 126900 }, { "epoch": 3.19, "learning_rate": 5.810938090285789e-06, "loss": 1.5493, "step": 127000 }, { "epoch": 3.19, "learning_rate": 5.796605107274411e-06, "loss": 1.5735, "step": 127100 }, { "epoch": 3.2, "learning_rate": 5.782282604959206e-06, "loss": 1.6204, "step": 127200 }, { "epoch": 3.2, "learning_rate": 5.7679706190517325e-06, "loss": 1.5693, "step": 127300 }, { "epoch": 3.2, "learning_rate": 5.7536691852373335e-06, "loss": 1.6643, "step": 127400 }, { "epoch": 3.2, "learning_rate": 5.739378339175039e-06, "loss": 1.5999, "step": 127500 }, { "epoch": 3.21, "learning_rate": 5.725098116497485e-06, "loss": 1.663, "step": 127600 }, { "epoch": 3.21, "learning_rate": 5.710828552810805e-06, "loss": 1.6441, "step": 127700 }, { "epoch": 3.21, "learning_rate": 5.696569683694566e-06, "loss": 1.4993, "step": 127800 }, { "epoch": 3.21, "learning_rate": 5.682321544701665e-06, "loss": 1.5306, "step": 127900 }, { "epoch": 3.22, "learning_rate": 5.668084171358255e-06, "loss": 1.562, "step": 128000 }, { "epoch": 3.22, "learning_rate": 5.65385759916363e-06, "loss": 1.5874, "step": 128100 }, { "epoch": 3.22, "learning_rate": 5.639641863590166e-06, "loss": 1.5792, "step": 128200 }, { "epoch": 3.22, "learning_rate": 5.625437000083207e-06, "loss": 1.6469, "step": 128300 }, { "epoch": 3.23, "learning_rate": 5.611243044060999e-06, "loss": 1.6187, "step": 128400 }, { "epoch": 3.23, "learning_rate": 5.597060030914591e-06, "loss": 1.5667, "step": 128500 }, { "epoch": 3.23, "learning_rate": 5.5828879960077356e-06, "loss": 1.5001, "step": 128600 }, { "epoch": 3.23, "learning_rate": 5.5687269746768305e-06, "loss": 1.6853, "step": 128700 }, { "epoch": 3.24, "learning_rate": 5.554577002230794e-06, "loss": 1.414, "step": 128800 }, { "epoch": 3.24, "learning_rate": 5.54043811395101e-06, "loss": 1.3952, "step": 128900 }, { "epoch": 3.24, "learning_rate": 5.526310345091212e-06, "loss": 1.6372, "step": 129000 }, { "epoch": 3.24, "learning_rate": 5.51219373087742e-06, "loss": 1.6284, "step": 129100 }, { "epoch": 3.25, "learning_rate": 5.498088306507838e-06, "loss": 1.5459, "step": 129200 }, { "epoch": 3.25, "learning_rate": 5.483994107152761e-06, "loss": 1.3989, "step": 129300 }, { "epoch": 3.25, "learning_rate": 5.469911167954513e-06, "loss": 1.4371, "step": 129400 }, { "epoch": 3.25, "learning_rate": 5.455839524027322e-06, "loss": 1.4676, "step": 129500 }, { "epoch": 3.26, "learning_rate": 5.441779210457264e-06, "loss": 1.4694, "step": 129600 }, { "epoch": 3.26, "learning_rate": 5.4277302623021684e-06, "loss": 1.6514, "step": 129700 }, { "epoch": 3.26, "learning_rate": 5.413692714591516e-06, "loss": 1.5611, "step": 129800 }, { "epoch": 3.26, "learning_rate": 5.399666602326361e-06, "loss": 1.6673, "step": 129900 }, { "epoch": 3.27, "learning_rate": 5.385651960479253e-06, "loss": 1.493, "step": 130000 }, { "epoch": 3.27, "learning_rate": 5.371648823994139e-06, "loss": 1.3823, "step": 130100 }, { "epoch": 3.27, "learning_rate": 5.357657227786281e-06, "loss": 1.7226, "step": 130200 }, { "epoch": 3.27, "learning_rate": 5.343677206742154e-06, "loss": 1.595, "step": 130300 }, { "epoch": 3.28, "learning_rate": 5.329708795719389e-06, "loss": 1.5354, "step": 130400 }, { "epoch": 3.28, "learning_rate": 5.315891539452085e-06, "loss": 1.5617, "step": 130500 }, { "epoch": 3.28, "learning_rate": 5.301946335960362e-06, "loss": 1.4738, "step": 130600 }, { "epoch": 3.28, "learning_rate": 5.28801284654127e-06, "loss": 1.4278, "step": 130700 }, { "epoch": 3.29, "learning_rate": 5.274091105936408e-06, "loss": 1.4754, "step": 130800 }, { "epoch": 3.29, "learning_rate": 5.260181148858083e-06, "loss": 1.6935, "step": 130900 }, { "epoch": 3.29, "learning_rate": 5.246283009989219e-06, "loss": 1.5907, "step": 131000 }, { "epoch": 3.29, "learning_rate": 5.232396723983279e-06, "loss": 1.3946, "step": 131100 }, { "epoch": 3.3, "learning_rate": 5.218522325464162e-06, "loss": 1.6115, "step": 131200 }, { "epoch": 3.3, "learning_rate": 5.204659849026135e-06, "loss": 1.554, "step": 131300 }, { "epoch": 3.3, "learning_rate": 5.190809329233741e-06, "loss": 1.5957, "step": 131400 }, { "epoch": 3.3, "learning_rate": 5.176970800621699e-06, "loss": 1.6272, "step": 131500 }, { "epoch": 3.31, "learning_rate": 5.163144297694843e-06, "loss": 1.3648, "step": 131600 }, { "epoch": 3.31, "learning_rate": 5.149329854928007e-06, "loss": 1.3675, "step": 131700 }, { "epoch": 3.31, "learning_rate": 5.1355275067659675e-06, "loss": 1.5661, "step": 131800 }, { "epoch": 3.31, "learning_rate": 5.121737287623341e-06, "loss": 1.4997, "step": 131900 }, { "epoch": 3.32, "learning_rate": 5.107959231884501e-06, "loss": 1.4832, "step": 132000 }, { "epoch": 3.32, "learning_rate": 5.094193373903484e-06, "loss": 1.729, "step": 132100 }, { "epoch": 3.32, "learning_rate": 5.080439748003927e-06, "loss": 1.4502, "step": 132200 }, { "epoch": 3.32, "learning_rate": 5.066698388478961e-06, "loss": 1.6517, "step": 132300 }, { "epoch": 3.33, "learning_rate": 5.052969329591137e-06, "loss": 1.4246, "step": 132400 }, { "epoch": 3.33, "learning_rate": 5.039252605572329e-06, "loss": 1.5638, "step": 132500 }, { "epoch": 3.33, "learning_rate": 5.025548250623651e-06, "loss": 1.4579, "step": 132600 }, { "epoch": 3.33, "learning_rate": 5.011856298915389e-06, "loss": 1.3776, "step": 132700 }, { "epoch": 3.34, "learning_rate": 4.998176784586897e-06, "loss": 1.4769, "step": 132800 }, { "epoch": 3.34, "learning_rate": 4.98450974174652e-06, "loss": 1.6085, "step": 132900 }, { "epoch": 3.34, "learning_rate": 4.9708552044715016e-06, "loss": 1.6582, "step": 133000 }, { "epoch": 3.34, "learning_rate": 4.957213206807904e-06, "loss": 1.456, "step": 133100 }, { "epoch": 3.35, "learning_rate": 4.943583782770528e-06, "loss": 1.5786, "step": 133200 }, { "epoch": 3.35, "learning_rate": 4.929966966342827e-06, "loss": 1.6342, "step": 133300 }, { "epoch": 3.35, "learning_rate": 4.916362791476806e-06, "loss": 1.5134, "step": 133400 }, { "epoch": 3.35, "learning_rate": 4.902771292092964e-06, "loss": 1.4202, "step": 133500 }, { "epoch": 3.36, "learning_rate": 4.889192502080181e-06, "loss": 1.4385, "step": 133600 }, { "epoch": 3.36, "learning_rate": 4.875762052573432e-06, "loss": 1.5589, "step": 133700 }, { "epoch": 3.36, "learning_rate": 4.8622086549047295e-06, "loss": 1.5394, "step": 133800 }, { "epoch": 3.36, "learning_rate": 4.8486680677454976e-06, "loss": 1.5107, "step": 133900 }, { "epoch": 3.37, "learning_rate": 4.835140324857684e-06, "loss": 1.5208, "step": 134000 }, { "epoch": 3.37, "learning_rate": 4.821625459971202e-06, "loss": 1.7193, "step": 134100 }, { "epoch": 3.37, "learning_rate": 4.808123506783864e-06, "loss": 1.4764, "step": 134200 }, { "epoch": 3.37, "learning_rate": 4.7946344989612784e-06, "loss": 1.6334, "step": 134300 }, { "epoch": 3.38, "learning_rate": 4.781158470136783e-06, "loss": 1.5929, "step": 134400 }, { "epoch": 3.38, "learning_rate": 4.767695453911353e-06, "loss": 1.6574, "step": 134500 }, { "epoch": 3.38, "learning_rate": 4.754245483853521e-06, "loss": 1.552, "step": 134600 }, { "epoch": 3.38, "learning_rate": 4.740808593499284e-06, "loss": 1.6368, "step": 134700 }, { "epoch": 3.39, "learning_rate": 4.727384816352024e-06, "loss": 1.5964, "step": 134800 }, { "epoch": 3.39, "learning_rate": 4.713974185882435e-06, "loss": 1.5992, "step": 134900 }, { "epoch": 3.39, "learning_rate": 4.700576735528428e-06, "loss": 1.5626, "step": 135000 }, { "epoch": 3.39, "learning_rate": 4.687192498695054e-06, "loss": 1.5907, "step": 135100 }, { "epoch": 3.4, "learning_rate": 4.673821508754412e-06, "loss": 1.5929, "step": 135200 }, { "epoch": 3.4, "learning_rate": 4.660463799045569e-06, "loss": 1.5956, "step": 135300 }, { "epoch": 3.4, "learning_rate": 4.647119402874487e-06, "loss": 1.5373, "step": 135400 }, { "epoch": 3.4, "learning_rate": 4.633788353513933e-06, "loss": 1.4478, "step": 135500 }, { "epoch": 3.41, "learning_rate": 4.6204706842033845e-06, "loss": 1.5077, "step": 135600 }, { "epoch": 3.41, "learning_rate": 4.6071664281489705e-06, "loss": 1.7909, "step": 135700 }, { "epoch": 3.41, "learning_rate": 4.593875618523361e-06, "loss": 1.5342, "step": 135800 }, { "epoch": 3.41, "learning_rate": 4.580598288465712e-06, "loss": 1.5186, "step": 135900 }, { "epoch": 3.42, "learning_rate": 4.567334471081568e-06, "loss": 1.5761, "step": 136000 }, { "epoch": 3.42, "learning_rate": 4.55408419944277e-06, "loss": 1.5188, "step": 136100 }, { "epoch": 3.42, "learning_rate": 4.5408475065873995e-06, "loss": 1.7061, "step": 136200 }, { "epoch": 3.42, "learning_rate": 4.527624425519665e-06, "loss": 1.5379, "step": 136300 }, { "epoch": 3.43, "learning_rate": 4.514414989209853e-06, "loss": 1.591, "step": 136400 }, { "epoch": 3.43, "learning_rate": 4.501219230594211e-06, "loss": 1.5354, "step": 136500 }, { "epoch": 3.43, "learning_rate": 4.488037182574894e-06, "loss": 1.4201, "step": 136600 }, { "epoch": 3.43, "learning_rate": 4.4748688780198715e-06, "loss": 1.7105, "step": 136700 }, { "epoch": 3.44, "learning_rate": 4.461714349762838e-06, "loss": 1.4942, "step": 136800 }, { "epoch": 3.44, "learning_rate": 4.4485736306031395e-06, "loss": 1.5802, "step": 136900 }, { "epoch": 3.44, "learning_rate": 4.4354467533056955e-06, "loss": 1.5918, "step": 137000 }, { "epoch": 3.44, "learning_rate": 4.42233375060091e-06, "loss": 1.3691, "step": 137100 }, { "epoch": 3.45, "learning_rate": 4.40936557719041e-06, "loss": 1.542, "step": 137200 }, { "epoch": 3.45, "learning_rate": 4.396280282162643e-06, "loss": 1.5523, "step": 137300 }, { "epoch": 3.45, "learning_rate": 4.383208959384756e-06, "loss": 1.5435, "step": 137400 }, { "epoch": 3.45, "learning_rate": 4.37015164144864e-06, "loss": 1.4696, "step": 137500 }, { "epoch": 3.46, "learning_rate": 4.3571083609112575e-06, "loss": 1.6473, "step": 137600 }, { "epoch": 3.46, "learning_rate": 4.344079150294579e-06, "loss": 1.5965, "step": 137700 }, { "epoch": 3.46, "learning_rate": 4.331064042085483e-06, "loss": 1.4019, "step": 137800 }, { "epoch": 3.46, "learning_rate": 4.318063068735686e-06, "loss": 1.3499, "step": 137900 }, { "epoch": 3.47, "learning_rate": 4.305076262661669e-06, "loss": 1.387, "step": 138000 }, { "epoch": 3.47, "learning_rate": 4.292103656244586e-06, "loss": 1.4539, "step": 138100 }, { "epoch": 3.47, "learning_rate": 4.279145281830178e-06, "loss": 1.6603, "step": 138200 }, { "epoch": 3.47, "learning_rate": 4.266201171728712e-06, "loss": 1.4886, "step": 138300 }, { "epoch": 3.48, "learning_rate": 4.253271358214875e-06, "loss": 1.5638, "step": 138400 }, { "epoch": 3.48, "learning_rate": 4.240355873527718e-06, "loss": 1.6035, "step": 138500 }, { "epoch": 3.48, "learning_rate": 4.227454749870567e-06, "loss": 1.4951, "step": 138600 }, { "epoch": 3.48, "learning_rate": 4.214568019410923e-06, "loss": 1.5671, "step": 138700 }, { "epoch": 3.49, "learning_rate": 4.201695714280417e-06, "loss": 1.5289, "step": 138800 }, { "epoch": 3.49, "learning_rate": 4.188837866574709e-06, "loss": 1.5755, "step": 138900 }, { "epoch": 3.49, "learning_rate": 4.175994508353404e-06, "loss": 1.5877, "step": 139000 }, { "epoch": 3.49, "learning_rate": 4.163165671639977e-06, "loss": 1.5899, "step": 139100 }, { "epoch": 3.5, "learning_rate": 4.1503513884217084e-06, "loss": 1.5273, "step": 139200 }, { "epoch": 3.5, "learning_rate": 4.13755169064958e-06, "loss": 1.6695, "step": 139300 }, { "epoch": 3.5, "learning_rate": 4.124766610238216e-06, "loss": 1.6263, "step": 139400 }, { "epoch": 3.5, "learning_rate": 4.1119961790657835e-06, "loss": 1.7143, "step": 139500 }, { "epoch": 3.51, "learning_rate": 4.099240428973924e-06, "loss": 1.7138, "step": 139600 }, { "epoch": 3.51, "learning_rate": 4.086499391767681e-06, "loss": 1.4372, "step": 139700 }, { "epoch": 3.51, "learning_rate": 4.0737730992154104e-06, "loss": 1.586, "step": 139800 }, { "epoch": 3.51, "learning_rate": 4.061061583048704e-06, "loss": 1.5441, "step": 139900 }, { "epoch": 3.52, "learning_rate": 4.048364874962306e-06, "loss": 1.5327, "step": 140000 }, { "epoch": 3.52, "learning_rate": 4.035683006614039e-06, "loss": 1.6613, "step": 140100 }, { "epoch": 3.52, "learning_rate": 4.02301600962473e-06, "loss": 1.4873, "step": 140200 }, { "epoch": 3.52, "learning_rate": 4.010363915578127e-06, "loss": 1.477, "step": 140300 }, { "epoch": 3.53, "learning_rate": 3.997726756020806e-06, "loss": 1.3782, "step": 140400 }, { "epoch": 3.53, "learning_rate": 3.985104562462121e-06, "loss": 1.7356, "step": 140500 }, { "epoch": 3.53, "learning_rate": 3.9724973663740985e-06, "loss": 1.5755, "step": 140600 }, { "epoch": 3.53, "learning_rate": 3.9599051991913785e-06, "loss": 1.528, "step": 140700 }, { "epoch": 3.54, "learning_rate": 3.947328092311127e-06, "loss": 1.6104, "step": 140800 }, { "epoch": 3.54, "learning_rate": 3.93476607709295e-06, "loss": 1.6152, "step": 140900 }, { "epoch": 3.54, "learning_rate": 3.9222191848588385e-06, "loss": 1.5738, "step": 141000 }, { "epoch": 3.54, "learning_rate": 3.909687446893061e-06, "loss": 1.535, "step": 141100 }, { "epoch": 3.55, "learning_rate": 3.897295984695821e-06, "loss": 1.7467, "step": 141200 }, { "epoch": 3.55, "learning_rate": 3.884794496646734e-06, "loss": 1.6794, "step": 141300 }, { "epoch": 3.55, "learning_rate": 3.87230825618027e-06, "loss": 1.5785, "step": 141400 }, { "epoch": 3.55, "learning_rate": 3.859837294429479e-06, "loss": 1.4767, "step": 141500 }, { "epoch": 3.56, "learning_rate": 3.847381642489304e-06, "loss": 1.5417, "step": 141600 }, { "epoch": 3.56, "learning_rate": 3.834941331416533e-06, "loss": 1.5367, "step": 141700 }, { "epoch": 3.56, "learning_rate": 3.822640565428963e-06, "loss": 1.4965, "step": 141800 }, { "epoch": 3.56, "learning_rate": 3.8102308749263562e-06, "loss": 1.4044, "step": 141900 }, { "epoch": 3.57, "learning_rate": 3.7978366179224456e-06, "loss": 1.4994, "step": 142000 }, { "epoch": 3.57, "learning_rate": 3.785457825320925e-06, "loss": 1.2695, "step": 142100 }, { "epoch": 3.57, "learning_rate": 3.7730945279869303e-06, "loss": 1.5415, "step": 142200 }, { "epoch": 3.57, "learning_rate": 3.7607467567469658e-06, "loss": 1.6179, "step": 142300 }, { "epoch": 3.58, "learning_rate": 3.748414542388823e-06, "loss": 1.5967, "step": 142400 }, { "epoch": 3.58, "learning_rate": 3.736097915661505e-06, "loss": 1.5924, "step": 142500 }, { "epoch": 3.58, "learning_rate": 3.7237969072751423e-06, "loss": 1.5233, "step": 142600 }, { "epoch": 3.58, "learning_rate": 3.7115115479009246e-06, "loss": 1.5392, "step": 142700 }, { "epoch": 3.59, "learning_rate": 3.6992418681710286e-06, "loss": 1.6292, "step": 142800 }, { "epoch": 3.59, "learning_rate": 3.686987898678529e-06, "loss": 1.6106, "step": 142900 }, { "epoch": 3.59, "learning_rate": 3.6747496699773378e-06, "loss": 1.4183, "step": 143000 }, { "epoch": 3.59, "learning_rate": 3.6625272125821053e-06, "loss": 1.5874, "step": 143100 }, { "epoch": 3.6, "learning_rate": 3.650320556968171e-06, "loss": 1.6181, "step": 143200 }, { "epoch": 3.6, "learning_rate": 3.6381297335714636e-06, "loss": 1.6461, "step": 143300 }, { "epoch": 3.6, "learning_rate": 3.6259547727884457e-06, "loss": 1.5741, "step": 143400 }, { "epoch": 3.6, "learning_rate": 3.6137957049760197e-06, "loss": 1.4858, "step": 143500 }, { "epoch": 3.61, "learning_rate": 3.601652560451465e-06, "loss": 1.4613, "step": 143600 }, { "epoch": 3.61, "learning_rate": 3.5895253694923626e-06, "loss": 1.5194, "step": 143700 }, { "epoch": 3.61, "learning_rate": 3.5774141623365022e-06, "loss": 1.4293, "step": 143800 }, { "epoch": 3.61, "learning_rate": 3.5653189691818356e-06, "loss": 1.645, "step": 143900 }, { "epoch": 3.62, "learning_rate": 3.5532398201863703e-06, "loss": 1.7682, "step": 144000 }, { "epoch": 3.62, "learning_rate": 3.5411767454681203e-06, "loss": 1.6922, "step": 144100 }, { "epoch": 3.62, "learning_rate": 3.529129775105019e-06, "loss": 1.5515, "step": 144200 }, { "epoch": 3.62, "learning_rate": 3.51709893913484e-06, "loss": 1.6381, "step": 144300 }, { "epoch": 3.63, "learning_rate": 3.5050842675551254e-06, "loss": 1.6397, "step": 144400 }, { "epoch": 3.63, "learning_rate": 3.4930857903231253e-06, "loss": 1.4475, "step": 144500 }, { "epoch": 3.63, "learning_rate": 3.4811035373557e-06, "loss": 1.4943, "step": 144600 }, { "epoch": 3.63, "learning_rate": 3.469137538529267e-06, "loss": 1.728, "step": 144700 }, { "epoch": 3.64, "learning_rate": 3.4571878236797042e-06, "loss": 1.4894, "step": 144800 }, { "epoch": 3.64, "learning_rate": 3.4452544226022886e-06, "loss": 1.599, "step": 144900 }, { "epoch": 3.64, "learning_rate": 3.433337365051629e-06, "loss": 1.5652, "step": 145000 }, { "epoch": 3.64, "learning_rate": 3.4214366807415765e-06, "loss": 1.3636, "step": 145100 }, { "epoch": 3.65, "learning_rate": 3.409552399345166e-06, "loss": 1.6956, "step": 145200 }, { "epoch": 3.65, "learning_rate": 3.397684550494522e-06, "loss": 1.443, "step": 145300 }, { "epoch": 3.65, "learning_rate": 3.3858331637807983e-06, "loss": 1.5861, "step": 145400 }, { "epoch": 3.65, "learning_rate": 3.3739982687541095e-06, "loss": 1.3556, "step": 145500 }, { "epoch": 3.66, "learning_rate": 3.3621798949234475e-06, "loss": 1.5248, "step": 145600 }, { "epoch": 3.66, "learning_rate": 3.3503780717566036e-06, "loss": 1.6649, "step": 145700 }, { "epoch": 3.66, "learning_rate": 3.3387105989429103e-06, "loss": 1.5004, "step": 145800 }, { "epoch": 3.66, "learning_rate": 3.3269417991018802e-06, "loss": 1.5739, "step": 145900 }, { "epoch": 3.67, "learning_rate": 3.3151896377869343e-06, "loss": 1.3528, "step": 146000 }, { "epoch": 3.67, "learning_rate": 3.3034541443007686e-06, "loss": 1.5199, "step": 146100 }, { "epoch": 3.67, "learning_rate": 3.2917353479045323e-06, "loss": 1.6106, "step": 146200 }, { "epoch": 3.67, "learning_rate": 3.280033277817737e-06, "loss": 1.5067, "step": 146300 }, { "epoch": 3.68, "learning_rate": 3.268347963218185e-06, "loss": 1.7674, "step": 146400 }, { "epoch": 3.68, "learning_rate": 3.2566794332419096e-06, "loss": 1.5584, "step": 146500 }, { "epoch": 3.68, "learning_rate": 3.24514415082234e-06, "loss": 1.4041, "step": 146600 }, { "epoch": 3.68, "learning_rate": 3.23350910876185e-06, "loss": 1.7312, "step": 146700 }, { "epoch": 3.69, "learning_rate": 3.22189093819143e-06, "loss": 1.5527, "step": 146800 }, { "epoch": 3.69, "learning_rate": 3.210289668079698e-06, "loss": 1.4499, "step": 146900 }, { "epoch": 3.69, "learning_rate": 3.1987053273531144e-06, "loss": 1.5563, "step": 147000 }, { "epoch": 3.69, "learning_rate": 3.187137944895946e-06, "loss": 1.3889, "step": 147100 }, { "epoch": 3.7, "learning_rate": 3.175587549550171e-06, "loss": 1.5391, "step": 147200 }, { "epoch": 3.7, "learning_rate": 3.1640541701154115e-06, "loss": 1.5342, "step": 147300 }, { "epoch": 3.7, "learning_rate": 3.1525378353488658e-06, "loss": 1.5108, "step": 147400 }, { "epoch": 3.71, "learning_rate": 3.141038573965226e-06, "loss": 1.4814, "step": 147500 }, { "epoch": 3.71, "learning_rate": 3.129556414636613e-06, "loss": 1.4736, "step": 147600 }, { "epoch": 3.71, "learning_rate": 3.1180913859925153e-06, "loss": 1.4667, "step": 147700 }, { "epoch": 3.71, "learning_rate": 3.106643516619705e-06, "loss": 1.6876, "step": 147800 }, { "epoch": 3.72, "learning_rate": 3.09521283506216e-06, "loss": 1.5146, "step": 147900 }, { "epoch": 3.72, "learning_rate": 3.0837993698210165e-06, "loss": 1.6805, "step": 148000 }, { "epoch": 3.72, "learning_rate": 3.072403149354469e-06, "loss": 1.5928, "step": 148100 }, { "epoch": 3.72, "learning_rate": 3.0610242020777304e-06, "loss": 1.5288, "step": 148200 }, { "epoch": 3.73, "learning_rate": 3.049662556362929e-06, "loss": 1.7413, "step": 148300 }, { "epoch": 3.73, "learning_rate": 3.0383182405390622e-06, "loss": 1.6862, "step": 148400 }, { "epoch": 3.73, "learning_rate": 3.02699128289192e-06, "loss": 1.5638, "step": 148500 }, { "epoch": 3.73, "learning_rate": 3.0156817116640023e-06, "loss": 1.5577, "step": 148600 }, { "epoch": 3.74, "learning_rate": 3.004389555054468e-06, "loss": 1.6053, "step": 148700 }, { "epoch": 3.74, "learning_rate": 2.9931148412190437e-06, "loss": 1.3459, "step": 148800 }, { "epoch": 3.74, "learning_rate": 2.981857598269974e-06, "loss": 1.6425, "step": 148900 }, { "epoch": 3.74, "learning_rate": 2.97061785427594e-06, "loss": 1.4097, "step": 149000 }, { "epoch": 3.75, "learning_rate": 2.9593956372619883e-06, "loss": 1.5332, "step": 149100 }, { "epoch": 3.75, "learning_rate": 2.9481909752094594e-06, "loss": 1.3187, "step": 149200 }, { "epoch": 3.75, "learning_rate": 2.937003896055933e-06, "loss": 1.5284, "step": 149300 }, { "epoch": 3.75, "learning_rate": 2.925834427695142e-06, "loss": 1.4458, "step": 149400 }, { "epoch": 3.76, "learning_rate": 2.914794028871477e-06, "loss": 1.3389, "step": 149500 }, { "epoch": 3.76, "learning_rate": 2.9036596887996717e-06, "loss": 1.6144, "step": 149600 }, { "epoch": 3.76, "learning_rate": 2.892543042660658e-06, "loss": 1.5529, "step": 149700 }, { "epoch": 3.76, "learning_rate": 2.881444118172558e-06, "loss": 1.5885, "step": 149800 }, { "epoch": 3.77, "learning_rate": 2.8703629430092996e-06, "loss": 1.6247, "step": 149900 }, { "epoch": 3.77, "learning_rate": 2.8592995448005613e-06, "loss": 1.5383, "step": 150000 }, { "epoch": 3.77, "learning_rate": 2.8482539511316885e-06, "loss": 1.4166, "step": 150100 }, { "epoch": 3.77, "learning_rate": 2.8372261895436335e-06, "loss": 1.5869, "step": 150200 }, { "epoch": 3.78, "learning_rate": 2.8262162875328926e-06, "loss": 1.4532, "step": 150300 }, { "epoch": 3.78, "learning_rate": 2.81522427255143e-06, "loss": 1.6201, "step": 150400 }, { "epoch": 3.78, "learning_rate": 2.8042501720066052e-06, "loss": 1.5262, "step": 150500 }, { "epoch": 3.78, "learning_rate": 2.7932940132611163e-06, "loss": 1.5183, "step": 150600 }, { "epoch": 3.79, "learning_rate": 2.7823558236329197e-06, "loss": 1.5647, "step": 150700 }, { "epoch": 3.79, "learning_rate": 2.771435630395172e-06, "loss": 1.3284, "step": 150800 }, { "epoch": 3.79, "learning_rate": 2.760533460776159e-06, "loss": 1.4737, "step": 150900 }, { "epoch": 3.79, "learning_rate": 2.7496493419592195e-06, "loss": 1.3799, "step": 151000 }, { "epoch": 3.8, "learning_rate": 2.7387833010826927e-06, "loss": 1.6415, "step": 151100 }, { "epoch": 3.8, "learning_rate": 2.7279353652398412e-06, "loss": 1.6409, "step": 151200 }, { "epoch": 3.8, "learning_rate": 2.71710556147878e-06, "loss": 1.3556, "step": 151300 }, { "epoch": 3.8, "learning_rate": 2.706293916802414e-06, "loss": 1.547, "step": 151400 }, { "epoch": 3.81, "learning_rate": 2.6955004581683754e-06, "loss": 1.4547, "step": 151500 }, { "epoch": 3.81, "learning_rate": 2.684725212488948e-06, "loss": 1.5956, "step": 151600 }, { "epoch": 3.81, "learning_rate": 2.6739682066310093e-06, "loss": 1.5417, "step": 151700 }, { "epoch": 3.81, "learning_rate": 2.66322946741595e-06, "loss": 1.504, "step": 151800 }, { "epoch": 3.82, "learning_rate": 2.6525090216196148e-06, "loss": 1.3977, "step": 151900 }, { "epoch": 3.82, "learning_rate": 2.641806895972241e-06, "loss": 1.6131, "step": 152000 }, { "epoch": 3.82, "learning_rate": 2.631229864042193e-06, "loss": 1.6511, "step": 152100 }, { "epoch": 3.82, "learning_rate": 2.6205642748342353e-06, "loss": 1.5025, "step": 152200 }, { "epoch": 3.83, "learning_rate": 2.609917085425903e-06, "loss": 1.4286, "step": 152300 }, { "epoch": 3.83, "learning_rate": 2.59928832236477e-06, "loss": 1.5923, "step": 152400 }, { "epoch": 3.83, "learning_rate": 2.588678012152476e-06, "loss": 1.4728, "step": 152500 }, { "epoch": 3.83, "learning_rate": 2.5780861812446465e-06, "loss": 1.4967, "step": 152600 }, { "epoch": 3.84, "learning_rate": 2.5675128560508254e-06, "loss": 1.6518, "step": 152700 }, { "epoch": 3.84, "learning_rate": 2.556958062934426e-06, "loss": 1.599, "step": 152800 }, { "epoch": 3.84, "learning_rate": 2.5464218282126407e-06, "loss": 1.5023, "step": 152900 }, { "epoch": 3.84, "learning_rate": 2.5359041781563977e-06, "loss": 1.4995, "step": 153000 }, { "epoch": 3.85, "learning_rate": 2.5254051389902868e-06, "loss": 1.5392, "step": 153100 }, { "epoch": 3.85, "learning_rate": 2.514924736892486e-06, "loss": 1.7157, "step": 153200 }, { "epoch": 3.85, "learning_rate": 2.5044629979947134e-06, "loss": 1.2383, "step": 153300 }, { "epoch": 3.85, "learning_rate": 2.4940199483821424e-06, "loss": 1.5985, "step": 153400 }, { "epoch": 3.86, "learning_rate": 2.4835956140933572e-06, "loss": 1.479, "step": 153500 }, { "epoch": 3.86, "learning_rate": 2.4731900211202664e-06, "loss": 1.5893, "step": 153600 }, { "epoch": 3.86, "learning_rate": 2.4628031954080588e-06, "loss": 1.6484, "step": 153700 }, { "epoch": 3.86, "learning_rate": 2.452435162855129e-06, "loss": 1.4607, "step": 153800 }, { "epoch": 3.87, "learning_rate": 2.4420859493130046e-06, "loss": 1.6967, "step": 153900 }, { "epoch": 3.87, "learning_rate": 2.4317555805862925e-06, "loss": 1.4226, "step": 154000 }, { "epoch": 3.87, "learning_rate": 2.421444082432618e-06, "loss": 1.5822, "step": 154100 }, { "epoch": 3.87, "learning_rate": 2.4111514805625502e-06, "loss": 1.5887, "step": 154200 }, { "epoch": 3.88, "learning_rate": 2.4008778006395485e-06, "loss": 1.4663, "step": 154300 }, { "epoch": 3.88, "learning_rate": 2.3906230682798824e-06, "loss": 1.5252, "step": 154400 }, { "epoch": 3.88, "learning_rate": 2.380387309052581e-06, "loss": 1.5531, "step": 154500 }, { "epoch": 3.88, "learning_rate": 2.3701705484793703e-06, "loss": 1.4509, "step": 154600 }, { "epoch": 3.89, "learning_rate": 2.3599728120346033e-06, "loss": 1.658, "step": 154700 }, { "epoch": 3.89, "learning_rate": 2.3497941251452006e-06, "loss": 1.4495, "step": 154800 }, { "epoch": 3.89, "learning_rate": 2.3396345131905796e-06, "loss": 1.495, "step": 154900 }, { "epoch": 3.89, "learning_rate": 2.329494001502596e-06, "loss": 1.6249, "step": 155000 }, { "epoch": 3.9, "learning_rate": 2.3193726153654884e-06, "loss": 1.6054, "step": 155100 }, { "epoch": 3.9, "learning_rate": 2.309270380015801e-06, "loss": 1.4863, "step": 155200 }, { "epoch": 3.9, "learning_rate": 2.2991873206423365e-06, "loss": 1.6314, "step": 155300 }, { "epoch": 3.9, "learning_rate": 2.2891234623860713e-06, "loss": 1.5616, "step": 155400 }, { "epoch": 3.91, "learning_rate": 2.279078830340118e-06, "loss": 1.5619, "step": 155500 }, { "epoch": 3.91, "learning_rate": 2.269053449549642e-06, "loss": 1.4417, "step": 155600 }, { "epoch": 3.91, "learning_rate": 2.2590473450118165e-06, "loss": 1.685, "step": 155700 }, { "epoch": 3.91, "learning_rate": 2.2490605416757405e-06, "loss": 1.6451, "step": 155800 }, { "epoch": 3.92, "learning_rate": 2.239093064442397e-06, "loss": 1.4431, "step": 155900 }, { "epoch": 3.92, "learning_rate": 2.2291449381645825e-06, "loss": 1.4962, "step": 156000 }, { "epoch": 3.92, "learning_rate": 2.2192161876468344e-06, "loss": 1.4627, "step": 156100 }, { "epoch": 3.92, "learning_rate": 2.209405835031675e-06, "loss": 1.3706, "step": 156200 }, { "epoch": 3.93, "learning_rate": 2.1995157158799963e-06, "loss": 1.565, "step": 156300 }, { "epoch": 3.93, "learning_rate": 2.189645046365545e-06, "loss": 1.4955, "step": 156400 }, { "epoch": 3.93, "learning_rate": 2.1797938510997387e-06, "loss": 1.7505, "step": 156500 }, { "epoch": 3.93, "learning_rate": 2.1699621546454286e-06, "loss": 1.5703, "step": 156600 }, { "epoch": 3.94, "learning_rate": 2.1601499815168513e-06, "loss": 1.5258, "step": 156700 }, { "epoch": 3.94, "learning_rate": 2.150357356179569e-06, "loss": 1.653, "step": 156800 }, { "epoch": 3.94, "learning_rate": 2.140584303050399e-06, "loss": 1.5409, "step": 156900 }, { "epoch": 3.94, "learning_rate": 2.130830846497363e-06, "loss": 1.7147, "step": 157000 }, { "epoch": 3.95, "learning_rate": 2.1210970108396124e-06, "loss": 1.7227, "step": 157100 }, { "epoch": 3.95, "learning_rate": 2.1113828203473785e-06, "loss": 1.7082, "step": 157200 }, { "epoch": 3.95, "learning_rate": 2.1016882992419153e-06, "loss": 1.6203, "step": 157300 }, { "epoch": 3.95, "learning_rate": 2.0920134716954275e-06, "loss": 1.4667, "step": 157400 }, { "epoch": 3.96, "learning_rate": 2.0823583618310217e-06, "loss": 1.6821, "step": 157500 }, { "epoch": 3.96, "learning_rate": 2.0727229937226347e-06, "loss": 1.5006, "step": 157600 }, { "epoch": 3.96, "learning_rate": 2.0631073913949783e-06, "loss": 1.475, "step": 157700 }, { "epoch": 3.96, "learning_rate": 2.0535115788234873e-06, "loss": 1.4134, "step": 157800 }, { "epoch": 3.97, "learning_rate": 2.043935579934252e-06, "loss": 1.5919, "step": 157900 }, { "epoch": 3.97, "learning_rate": 2.0343794186039523e-06, "loss": 1.5557, "step": 158000 }, { "epoch": 3.97, "learning_rate": 2.0248431186598162e-06, "loss": 1.5963, "step": 158100 }, { "epoch": 3.97, "learning_rate": 2.015421769517826e-06, "loss": 1.4157, "step": 158200 }, { "epoch": 3.98, "learning_rate": 2.0059250644233174e-06, "loss": 1.5198, "step": 158300 }, { "epoch": 3.98, "learning_rate": 1.9964482916627224e-06, "loss": 1.5329, "step": 158400 }, { "epoch": 3.98, "learning_rate": 1.9869914748653216e-06, "loss": 1.5922, "step": 158500 }, { "epoch": 3.98, "learning_rate": 1.9775546376106345e-06, "loss": 1.5048, "step": 158600 }, { "epoch": 3.99, "learning_rate": 1.9682318726778314e-06, "loss": 1.5929, "step": 158700 }, { "epoch": 3.99, "learning_rate": 1.9588348646662092e-06, "loss": 1.4685, "step": 158800 }, { "epoch": 3.99, "learning_rate": 1.9494579064026597e-06, "loss": 1.5276, "step": 158900 }, { "epoch": 3.99, "learning_rate": 1.9401010212675862e-06, "loss": 1.5696, "step": 159000 }, { "epoch": 4.0, "learning_rate": 1.93076423259134e-06, "loss": 1.6802, "step": 159100 }, { "epoch": 4.0, "learning_rate": 1.9214475636541595e-06, "loss": 1.4646, "step": 159200 }, { "epoch": 4.0, "eval_loss": 1.4440454244613647, "eval_runtime": 103.1424, "eval_samples_per_second": 77.204, "eval_steps_per_second": 9.657, "step": 159244 }, { "epoch": 4.0, "learning_rate": 1.9121510376861164e-06, "loss": 1.5084, "step": 159300 }, { "epoch": 4.0, "learning_rate": 1.9028746778670638e-06, "loss": 1.6679, "step": 159400 }, { "epoch": 4.01, "learning_rate": 1.89361850732657e-06, "loss": 1.6483, "step": 159500 }, { "epoch": 4.01, "learning_rate": 1.884382549143866e-06, "loss": 1.5903, "step": 159600 }, { "epoch": 4.01, "learning_rate": 1.8751668263477784e-06, "loss": 1.3774, "step": 159700 }, { "epoch": 4.01, "learning_rate": 1.8659713619166874e-06, "loss": 1.4299, "step": 159800 }, { "epoch": 4.02, "learning_rate": 1.8567961787784538e-06, "loss": 1.4425, "step": 159900 }, { "epoch": 4.02, "learning_rate": 1.8476412998103743e-06, "loss": 1.5328, "step": 160000 }, { "epoch": 4.02, "learning_rate": 1.8385067478391228e-06, "loss": 1.625, "step": 160100 }, { "epoch": 4.02, "learning_rate": 1.8293925456406781e-06, "loss": 1.4713, "step": 160200 }, { "epoch": 4.03, "learning_rate": 1.820298715940293e-06, "loss": 1.6285, "step": 160300 }, { "epoch": 4.03, "learning_rate": 1.8112252814124121e-06, "loss": 1.4577, "step": 160400 }, { "epoch": 4.03, "learning_rate": 1.8021722646806361e-06, "loss": 1.4164, "step": 160500 }, { "epoch": 4.03, "learning_rate": 1.7931396883176477e-06, "loss": 1.4023, "step": 160600 }, { "epoch": 4.04, "learning_rate": 1.7841275748451704e-06, "loss": 1.3796, "step": 160700 }, { "epoch": 4.04, "learning_rate": 1.775135946733907e-06, "loss": 1.49, "step": 160800 }, { "epoch": 4.04, "learning_rate": 1.7661648264034736e-06, "loss": 1.4929, "step": 160900 }, { "epoch": 4.04, "learning_rate": 1.757214236222362e-06, "loss": 1.6413, "step": 161000 }, { "epoch": 4.05, "learning_rate": 1.7482841985078658e-06, "loss": 1.4188, "step": 161100 }, { "epoch": 4.05, "learning_rate": 1.7393747355260405e-06, "loss": 1.468, "step": 161200 }, { "epoch": 4.05, "learning_rate": 1.7305746561242788e-06, "loss": 1.3213, "step": 161300 }, { "epoch": 4.05, "learning_rate": 1.7217062029000485e-06, "loss": 1.4919, "step": 161400 }, { "epoch": 4.06, "learning_rate": 1.712858390677753e-06, "loss": 1.4601, "step": 161500 }, { "epoch": 4.06, "learning_rate": 1.7040312415184268e-06, "loss": 1.6281, "step": 161600 }, { "epoch": 4.06, "learning_rate": 1.6952247774315822e-06, "loss": 1.5309, "step": 161700 }, { "epoch": 4.06, "learning_rate": 1.6864390203751568e-06, "loss": 1.7237, "step": 161800 }, { "epoch": 4.07, "learning_rate": 1.677673992255453e-06, "loss": 1.6465, "step": 161900 }, { "epoch": 4.07, "learning_rate": 1.6689297149270888e-06, "loss": 1.4827, "step": 162000 }, { "epoch": 4.07, "learning_rate": 1.6602062101929461e-06, "loss": 1.4682, "step": 162100 }, { "epoch": 4.07, "learning_rate": 1.6515904239046976e-06, "loss": 1.5363, "step": 162200 }, { "epoch": 4.08, "learning_rate": 1.6429083212927233e-06, "loss": 1.526, "step": 162300 }, { "epoch": 4.08, "learning_rate": 1.6342470561564116e-06, "loss": 1.5124, "step": 162400 }, { "epoch": 4.08, "learning_rate": 1.625606650091659e-06, "loss": 1.5101, "step": 162500 }, { "epoch": 4.08, "learning_rate": 1.616987124642355e-06, "loss": 1.4727, "step": 162600 }, { "epoch": 4.09, "learning_rate": 1.6083885013003298e-06, "loss": 1.6189, "step": 162700 }, { "epoch": 4.09, "learning_rate": 1.5998108015052848e-06, "loss": 1.5487, "step": 162800 }, { "epoch": 4.09, "learning_rate": 1.5912540466447624e-06, "loss": 1.4809, "step": 162900 }, { "epoch": 4.09, "learning_rate": 1.5828035120870156e-06, "loss": 1.571, "step": 163000 }, { "epoch": 4.1, "learning_rate": 1.5742885010684894e-06, "loss": 1.6463, "step": 163100 }, { "epoch": 4.1, "learning_rate": 1.565794498621489e-06, "loss": 1.3679, "step": 163200 }, { "epoch": 4.1, "learning_rate": 1.5573215259248642e-06, "loss": 1.8497, "step": 163300 }, { "epoch": 4.1, "learning_rate": 1.54886960410503e-06, "loss": 1.5575, "step": 163400 }, { "epoch": 4.11, "learning_rate": 1.5404387542359068e-06, "loss": 1.3959, "step": 163500 }, { "epoch": 4.11, "learning_rate": 1.5320289973388803e-06, "loss": 1.6716, "step": 163600 }, { "epoch": 4.11, "learning_rate": 1.5236403543827384e-06, "loss": 1.4972, "step": 163700 }, { "epoch": 4.11, "learning_rate": 1.5152728462836263e-06, "loss": 1.4674, "step": 163800 }, { "epoch": 4.12, "learning_rate": 1.5069264939049954e-06, "loss": 1.5557, "step": 163900 }, { "epoch": 4.12, "learning_rate": 1.4986013180575454e-06, "loss": 1.5359, "step": 164000 }, { "epoch": 4.12, "learning_rate": 1.490297339499166e-06, "loss": 1.49, "step": 164100 }, { "epoch": 4.12, "learning_rate": 1.4820145789349062e-06, "loss": 1.5324, "step": 164200 }, { "epoch": 4.13, "learning_rate": 1.4737530570169034e-06, "loss": 1.4554, "step": 164300 }, { "epoch": 4.13, "learning_rate": 1.4655127943443426e-06, "loss": 1.7141, "step": 164400 }, { "epoch": 4.13, "learning_rate": 1.4572938114634006e-06, "loss": 1.6873, "step": 164500 }, { "epoch": 4.13, "learning_rate": 1.4490961288671912e-06, "loss": 1.7279, "step": 164600 }, { "epoch": 4.14, "learning_rate": 1.4409197669957209e-06, "loss": 1.5814, "step": 164700 }, { "epoch": 4.14, "learning_rate": 1.4327647462358374e-06, "loss": 1.4079, "step": 164800 }, { "epoch": 4.14, "learning_rate": 1.4246310869211765e-06, "loss": 1.7057, "step": 164900 }, { "epoch": 4.14, "learning_rate": 1.4165188093321069e-06, "loss": 1.6384, "step": 165000 }, { "epoch": 4.15, "learning_rate": 1.4084279336956908e-06, "loss": 1.7167, "step": 165100 }, { "epoch": 4.15, "learning_rate": 1.4003584801856206e-06, "loss": 1.6443, "step": 165200 }, { "epoch": 4.15, "learning_rate": 1.3923104689221822e-06, "loss": 1.6051, "step": 165300 }, { "epoch": 4.15, "learning_rate": 1.384283919972189e-06, "loss": 1.6322, "step": 165400 }, { "epoch": 4.16, "learning_rate": 1.376278853348948e-06, "loss": 1.5969, "step": 165500 }, { "epoch": 4.16, "learning_rate": 1.3682952890122014e-06, "loss": 1.6706, "step": 165600 }, { "epoch": 4.16, "learning_rate": 1.3603332468680718e-06, "loss": 1.3971, "step": 165700 }, { "epoch": 4.16, "learning_rate": 1.352392746769029e-06, "loss": 1.7085, "step": 165800 }, { "epoch": 4.17, "learning_rate": 1.3444738085138164e-06, "loss": 1.6672, "step": 165900 }, { "epoch": 4.17, "learning_rate": 1.3365764518474277e-06, "loss": 1.5532, "step": 166000 }, { "epoch": 4.17, "learning_rate": 1.3287006964610416e-06, "loss": 1.5312, "step": 166100 }, { "epoch": 4.17, "learning_rate": 1.3208465619919742e-06, "loss": 1.5525, "step": 166200 }, { "epoch": 4.18, "learning_rate": 1.3130140680236303e-06, "loss": 1.5711, "step": 166300 }, { "epoch": 4.18, "learning_rate": 1.3052032340854615e-06, "loss": 1.6363, "step": 166400 }, { "epoch": 4.18, "learning_rate": 1.2974140796529123e-06, "loss": 1.5198, "step": 166500 }, { "epoch": 4.18, "learning_rate": 1.2896466241473726e-06, "loss": 1.6119, "step": 166600 }, { "epoch": 4.19, "learning_rate": 1.2819008869361215e-06, "loss": 1.6668, "step": 166700 }, { "epoch": 4.19, "learning_rate": 1.27417688733229e-06, "loss": 1.6585, "step": 166800 }, { "epoch": 4.19, "learning_rate": 1.2664746445948117e-06, "loss": 1.6193, "step": 166900 }, { "epoch": 4.19, "learning_rate": 1.2587941779283696e-06, "loss": 1.6603, "step": 167000 }, { "epoch": 4.2, "learning_rate": 1.251135506483351e-06, "loss": 1.4718, "step": 167100 }, { "epoch": 4.2, "learning_rate": 1.2434986493557976e-06, "loss": 1.6091, "step": 167200 }, { "epoch": 4.2, "learning_rate": 1.2358836255873586e-06, "loss": 1.6819, "step": 167300 }, { "epoch": 4.2, "learning_rate": 1.2282904541652473e-06, "loss": 1.7092, "step": 167400 }, { "epoch": 4.21, "learning_rate": 1.220719154022193e-06, "loss": 1.5284, "step": 167500 }, { "epoch": 4.21, "learning_rate": 1.213169744036382e-06, "loss": 1.4091, "step": 167600 }, { "epoch": 4.21, "learning_rate": 1.2056422430314319e-06, "loss": 1.373, "step": 167700 }, { "epoch": 4.21, "learning_rate": 1.1981366697763209e-06, "loss": 1.5889, "step": 167800 }, { "epoch": 4.22, "learning_rate": 1.1906530429853602e-06, "loss": 1.5643, "step": 167900 }, { "epoch": 4.22, "learning_rate": 1.1831913813181417e-06, "loss": 1.5899, "step": 168000 }, { "epoch": 4.22, "learning_rate": 1.1757517033794808e-06, "loss": 1.4954, "step": 168100 }, { "epoch": 4.22, "learning_rate": 1.1683340277193878e-06, "loss": 1.5553, "step": 168200 }, { "epoch": 4.23, "learning_rate": 1.1609383728330104e-06, "loss": 1.54, "step": 168300 }, { "epoch": 4.23, "learning_rate": 1.153564757160588e-06, "loss": 1.7796, "step": 168400 }, { "epoch": 4.23, "learning_rate": 1.1462131990874047e-06, "loss": 1.5182, "step": 168500 }, { "epoch": 4.24, "learning_rate": 1.138883716943754e-06, "loss": 1.456, "step": 168600 }, { "epoch": 4.24, "learning_rate": 1.1315763290048799e-06, "loss": 1.3536, "step": 168700 }, { "epoch": 4.24, "learning_rate": 1.1242910534909435e-06, "loss": 1.4555, "step": 168800 }, { "epoch": 4.24, "learning_rate": 1.1170279085669622e-06, "loss": 1.3692, "step": 168900 }, { "epoch": 4.25, "learning_rate": 1.1098592126096264e-06, "loss": 1.6945, "step": 169000 }, { "epoch": 4.25, "learning_rate": 1.1026401613831216e-06, "loss": 1.4664, "step": 169100 }, { "epoch": 4.25, "learning_rate": 1.095443294730656e-06, "loss": 1.645, "step": 169200 }, { "epoch": 4.25, "learning_rate": 1.088268630596817e-06, "loss": 1.7037, "step": 169300 }, { "epoch": 4.26, "learning_rate": 1.0811161868708265e-06, "loss": 1.4568, "step": 169400 }, { "epoch": 4.26, "learning_rate": 1.0739859813865016e-06, "loss": 1.4757, "step": 169500 }, { "epoch": 4.26, "learning_rate": 1.0668780319222183e-06, "loss": 1.6425, "step": 169600 }, { "epoch": 4.26, "learning_rate": 1.059792356200856e-06, "loss": 1.472, "step": 169700 }, { "epoch": 4.27, "learning_rate": 1.0527289718897527e-06, "loss": 1.5863, "step": 169800 }, { "epoch": 4.27, "learning_rate": 1.0456878966006733e-06, "loss": 1.4315, "step": 169900 }, { "epoch": 4.27, "learning_rate": 1.0386691478897504e-06, "loss": 1.4882, "step": 170000 }, { "epoch": 4.27, "learning_rate": 1.0316727432574513e-06, "loss": 1.7307, "step": 170100 }, { "epoch": 4.28, "learning_rate": 1.0246987001485332e-06, "loss": 1.5676, "step": 170200 }, { "epoch": 4.28, "learning_rate": 1.0177470359519893e-06, "loss": 1.5912, "step": 170300 }, { "epoch": 4.28, "learning_rate": 1.0108177680010245e-06, "loss": 1.3868, "step": 170400 }, { "epoch": 4.28, "learning_rate": 1.0039109135729895e-06, "loss": 1.6063, "step": 170500 }, { "epoch": 4.29, "learning_rate": 9.97026489889361e-07, "loss": 1.4688, "step": 170600 }, { "epoch": 4.29, "learning_rate": 9.901645141156758e-07, "loss": 1.5994, "step": 170700 }, { "epoch": 4.29, "learning_rate": 9.833250033615072e-07, "loss": 1.5419, "step": 170800 }, { "epoch": 4.29, "learning_rate": 9.765079746804152e-07, "loss": 1.5621, "step": 170900 }, { "epoch": 4.3, "learning_rate": 9.697812789399286e-07, "loss": 1.559, "step": 171000 }, { "epoch": 4.3, "learning_rate": 9.630766509770995e-07, "loss": 1.5576, "step": 171100 }, { "epoch": 4.3, "learning_rate": 9.563267194527337e-07, "loss": 1.2647, "step": 171200 }, { "epoch": 4.3, "learning_rate": 9.495993373186507e-07, "loss": 1.7894, "step": 171300 }, { "epoch": 4.31, "learning_rate": 9.428945213488283e-07, "loss": 1.584, "step": 171400 }, { "epoch": 4.31, "learning_rate": 9.362122882609759e-07, "loss": 1.6641, "step": 171500 }, { "epoch": 4.31, "learning_rate": 9.295526547164946e-07, "loss": 1.4268, "step": 171600 }, { "epoch": 4.31, "learning_rate": 9.229156373204385e-07, "loss": 1.5775, "step": 171700 }, { "epoch": 4.32, "learning_rate": 9.163012526214699e-07, "loss": 1.4871, "step": 171800 }, { "epoch": 4.32, "learning_rate": 9.097095171118209e-07, "loss": 1.5337, "step": 171900 }, { "epoch": 4.32, "learning_rate": 9.031404472272476e-07, "loss": 1.4827, "step": 172000 }, { "epoch": 4.32, "learning_rate": 8.965940593469902e-07, "loss": 1.4905, "step": 172100 }, { "epoch": 4.33, "learning_rate": 8.900703697937385e-07, "loss": 1.5499, "step": 172200 }, { "epoch": 4.33, "learning_rate": 8.835693948335855e-07, "loss": 1.5598, "step": 172300 }, { "epoch": 4.33, "learning_rate": 8.770911506759861e-07, "loss": 1.3765, "step": 172400 }, { "epoch": 4.33, "learning_rate": 8.706356534737181e-07, "loss": 1.6377, "step": 172500 }, { "epoch": 4.34, "learning_rate": 8.642029193228474e-07, "loss": 1.4915, "step": 172600 }, { "epoch": 4.34, "learning_rate": 8.577929642626737e-07, "loss": 1.6407, "step": 172700 }, { "epoch": 4.34, "learning_rate": 8.514058042757078e-07, "loss": 1.4478, "step": 172800 }, { "epoch": 4.34, "learning_rate": 8.450414552876197e-07, "loss": 1.7031, "step": 172900 }, { "epoch": 4.35, "learning_rate": 8.386999331672018e-07, "loss": 1.4492, "step": 173000 }, { "epoch": 4.35, "learning_rate": 8.323812537263365e-07, "loss": 1.5874, "step": 173100 }, { "epoch": 4.35, "learning_rate": 8.26085432719943e-07, "loss": 1.5022, "step": 173200 }, { "epoch": 4.35, "learning_rate": 8.198124858459477e-07, "loss": 1.6878, "step": 173300 }, { "epoch": 4.36, "learning_rate": 8.135624287452448e-07, "loss": 1.4548, "step": 173400 }, { "epoch": 4.36, "learning_rate": 8.073352770016529e-07, "loss": 1.4942, "step": 173500 }, { "epoch": 4.36, "learning_rate": 8.011310461418853e-07, "loss": 1.6136, "step": 173600 }, { "epoch": 4.36, "learning_rate": 7.949497516354943e-07, "loss": 1.3589, "step": 173700 }, { "epoch": 4.37, "learning_rate": 7.887914088948479e-07, "loss": 1.5114, "step": 173800 }, { "epoch": 4.37, "learning_rate": 7.826560332750876e-07, "loss": 1.6357, "step": 173900 }, { "epoch": 4.37, "learning_rate": 7.765436400740889e-07, "loss": 1.5171, "step": 174000 }, { "epoch": 4.37, "learning_rate": 7.705150245995252e-07, "loss": 1.517, "step": 174100 }, { "epoch": 4.38, "learning_rate": 7.644484116970252e-07, "loss": 1.3948, "step": 174200 }, { "epoch": 4.38, "learning_rate": 7.584048266119582e-07, "loss": 1.4937, "step": 174300 }, { "epoch": 4.38, "learning_rate": 7.523842844133312e-07, "loss": 1.5807, "step": 174400 }, { "epoch": 4.38, "learning_rate": 7.46386800112694e-07, "loss": 1.7896, "step": 174500 }, { "epoch": 4.39, "learning_rate": 7.404123886641024e-07, "loss": 1.5806, "step": 174600 }, { "epoch": 4.39, "learning_rate": 7.344610649640893e-07, "loss": 1.526, "step": 174700 }, { "epoch": 4.39, "learning_rate": 7.285328438516104e-07, "loss": 1.5681, "step": 174800 }, { "epoch": 4.39, "learning_rate": 7.226277401080284e-07, "loss": 1.5797, "step": 174900 }, { "epoch": 4.4, "learning_rate": 7.167457684570589e-07, "loss": 1.4911, "step": 175000 }, { "epoch": 4.4, "learning_rate": 7.108869435647414e-07, "loss": 1.6196, "step": 175100 }, { "epoch": 4.4, "learning_rate": 7.050512800394038e-07, "loss": 1.5085, "step": 175200 }, { "epoch": 4.4, "learning_rate": 6.992387924316202e-07, "loss": 1.6151, "step": 175300 }, { "epoch": 4.41, "learning_rate": 6.934494952341809e-07, "loss": 1.8216, "step": 175400 }, { "epoch": 4.41, "learning_rate": 6.876834028820511e-07, "loss": 1.4565, "step": 175500 }, { "epoch": 4.41, "learning_rate": 6.819405297523407e-07, "loss": 1.2823, "step": 175600 }, { "epoch": 4.41, "learning_rate": 6.76220890164263e-07, "loss": 1.4467, "step": 175700 }, { "epoch": 4.42, "learning_rate": 6.705244983790982e-07, "loss": 1.5485, "step": 175800 }, { "epoch": 4.42, "learning_rate": 6.64851368600169e-07, "loss": 1.5262, "step": 175900 }, { "epoch": 4.42, "learning_rate": 6.59201514972786e-07, "loss": 1.5118, "step": 176000 }, { "epoch": 4.42, "learning_rate": 6.535749515842304e-07, "loss": 1.4475, "step": 176100 }, { "epoch": 4.43, "learning_rate": 6.479716924637136e-07, "loss": 1.4996, "step": 176200 }, { "epoch": 4.43, "learning_rate": 6.423917515823341e-07, "loss": 1.5263, "step": 176300 }, { "epoch": 4.43, "learning_rate": 6.368351428530506e-07, "loss": 1.595, "step": 176400 }, { "epoch": 4.43, "learning_rate": 6.313018801306481e-07, "loss": 1.5355, "step": 176500 }, { "epoch": 4.44, "learning_rate": 6.257919772117016e-07, "loss": 1.5553, "step": 176600 }, { "epoch": 4.44, "learning_rate": 6.203054478345394e-07, "loss": 1.539, "step": 176700 }, { "epoch": 4.44, "learning_rate": 6.148423056792064e-07, "loss": 1.4515, "step": 176800 }, { "epoch": 4.44, "learning_rate": 6.094025643674428e-07, "loss": 1.6645, "step": 176900 }, { "epoch": 4.45, "learning_rate": 6.039862374626337e-07, "loss": 1.5689, "step": 177000 }, { "epoch": 4.45, "learning_rate": 5.98647151447349e-07, "loss": 1.638, "step": 177100 }, { "epoch": 4.45, "learning_rate": 5.932774593331026e-07, "loss": 1.4937, "step": 177200 }, { "epoch": 4.45, "learning_rate": 5.8793122183196e-07, "loss": 1.5431, "step": 177300 }, { "epoch": 4.46, "learning_rate": 5.826084522741715e-07, "loss": 1.7241, "step": 177400 }, { "epoch": 4.46, "learning_rate": 5.773091639314655e-07, "loss": 1.4206, "step": 177500 }, { "epoch": 4.46, "learning_rate": 5.720333700170289e-07, "loss": 1.4897, "step": 177600 }, { "epoch": 4.46, "learning_rate": 5.667810836854626e-07, "loss": 1.5602, "step": 177700 }, { "epoch": 4.47, "learning_rate": 5.615523180327587e-07, "loss": 1.7545, "step": 177800 }, { "epoch": 4.47, "learning_rate": 5.563470860962617e-07, "loss": 1.4327, "step": 177900 }, { "epoch": 4.47, "learning_rate": 5.511654008546341e-07, "loss": 1.506, "step": 178000 }, { "epoch": 4.47, "learning_rate": 5.460072752278334e-07, "loss": 1.6394, "step": 178100 }, { "epoch": 4.48, "learning_rate": 5.408727220770649e-07, "loss": 1.4444, "step": 178200 }, { "epoch": 4.48, "learning_rate": 5.357617542047688e-07, "loss": 1.6138, "step": 178300 }, { "epoch": 4.48, "learning_rate": 5.306743843545725e-07, "loss": 1.5016, "step": 178400 }, { "epoch": 4.48, "learning_rate": 5.256106252112636e-07, "loss": 1.7845, "step": 178500 }, { "epoch": 4.49, "learning_rate": 5.205704894007601e-07, "loss": 1.5807, "step": 178600 }, { "epoch": 4.49, "learning_rate": 5.155539894900797e-07, "loss": 1.4029, "step": 178700 }, { "epoch": 4.49, "learning_rate": 5.105611379873043e-07, "loss": 1.434, "step": 178800 }, { "epoch": 4.49, "learning_rate": 5.055919473415549e-07, "loss": 1.4766, "step": 178900 }, { "epoch": 4.5, "learning_rate": 5.006464299429515e-07, "loss": 1.496, "step": 179000 }, { "epoch": 4.5, "learning_rate": 4.957245981225889e-07, "loss": 1.5863, "step": 179100 }, { "epoch": 4.5, "learning_rate": 4.908264641525063e-07, "loss": 1.6271, "step": 179200 }, { "epoch": 4.5, "learning_rate": 4.859520402456541e-07, "loss": 1.5103, "step": 179300 }, { "epoch": 4.51, "learning_rate": 4.811013385558683e-07, "loss": 1.5417, "step": 179400 }, { "epoch": 4.51, "learning_rate": 4.7627437117782725e-07, "loss": 1.6677, "step": 179500 }, { "epoch": 4.51, "learning_rate": 4.7147115014703705e-07, "loss": 1.4833, "step": 179600 }, { "epoch": 4.51, "learning_rate": 4.666916874397942e-07, "loss": 1.5465, "step": 179700 }, { "epoch": 4.52, "learning_rate": 4.619359949731561e-07, "loss": 1.3877, "step": 179800 }, { "epoch": 4.52, "learning_rate": 4.5720408460490973e-07, "loss": 1.559, "step": 179900 }, { "epoch": 4.52, "learning_rate": 4.5249596813354723e-07, "loss": 1.647, "step": 180000 }, { "epoch": 4.52, "learning_rate": 4.478116572982294e-07, "loss": 1.3878, "step": 180100 }, { "epoch": 4.53, "learning_rate": 4.4315116377876445e-07, "loss": 1.7022, "step": 180200 }, { "epoch": 4.53, "learning_rate": 4.3851449919557365e-07, "loss": 1.6196, "step": 180300 }, { "epoch": 4.53, "learning_rate": 4.339016751096614e-07, "loss": 1.4097, "step": 180400 }, { "epoch": 4.53, "learning_rate": 4.2931270302258966e-07, "loss": 1.6341, "step": 180500 }, { "epoch": 4.54, "learning_rate": 4.247475943764512e-07, "loss": 1.7311, "step": 180600 }, { "epoch": 4.54, "learning_rate": 4.20206360553832e-07, "loss": 1.5251, "step": 180700 }, { "epoch": 4.54, "learning_rate": 4.156890128777913e-07, "loss": 1.4356, "step": 180800 }, { "epoch": 4.54, "learning_rate": 4.111955626118336e-07, "loss": 1.6762, "step": 180900 }, { "epoch": 4.55, "learning_rate": 4.0677059799211326e-07, "loss": 1.5081, "step": 181000 }, { "epoch": 4.55, "learning_rate": 4.0232473684590713e-07, "loss": 1.5602, "step": 181100 }, { "epoch": 4.55, "learning_rate": 3.9790280643211444e-07, "loss": 1.7396, "step": 181200 }, { "epoch": 4.55, "learning_rate": 3.9350481777632457e-07, "loss": 1.6306, "step": 181300 }, { "epoch": 4.56, "learning_rate": 3.891307818444323e-07, "loss": 1.5819, "step": 181400 }, { "epoch": 4.56, "learning_rate": 3.8478070954260815e-07, "loss": 1.4591, "step": 181500 }, { "epoch": 4.56, "learning_rate": 3.804546117172736e-07, "loss": 1.5852, "step": 181600 }, { "epoch": 4.56, "learning_rate": 3.7615249915506913e-07, "loss": 1.6243, "step": 181700 }, { "epoch": 4.57, "learning_rate": 3.718743825828319e-07, "loss": 1.6762, "step": 181800 }, { "epoch": 4.57, "learning_rate": 3.6762027266756815e-07, "loss": 1.5482, "step": 181900 }, { "epoch": 4.57, "learning_rate": 3.633901800164297e-07, "loss": 1.4134, "step": 182000 }, { "epoch": 4.57, "learning_rate": 3.5918411517667616e-07, "loss": 1.5288, "step": 182100 }, { "epoch": 4.58, "learning_rate": 3.5500208863566423e-07, "loss": 1.6338, "step": 182200 }, { "epoch": 4.58, "learning_rate": 3.508441108208083e-07, "loss": 1.4722, "step": 182300 }, { "epoch": 4.58, "learning_rate": 3.46710192099563e-07, "loss": 1.5872, "step": 182400 }, { "epoch": 4.58, "learning_rate": 3.426003427793945e-07, "loss": 1.5954, "step": 182500 }, { "epoch": 4.59, "learning_rate": 3.3851457310775217e-07, "loss": 1.4441, "step": 182600 }, { "epoch": 4.59, "learning_rate": 3.34452893272047e-07, "loss": 1.5035, "step": 182700 }, { "epoch": 4.59, "learning_rate": 3.3041531339962354e-07, "loss": 1.4736, "step": 182800 }, { "epoch": 4.59, "learning_rate": 3.2640184355773983e-07, "loss": 1.5524, "step": 182900 }, { "epoch": 4.6, "learning_rate": 3.2241249375353113e-07, "loss": 1.4109, "step": 183000 }, { "epoch": 4.6, "learning_rate": 3.184472739339983e-07, "loss": 1.7207, "step": 183100 }, { "epoch": 4.6, "learning_rate": 3.1450619398597503e-07, "loss": 1.5648, "step": 183200 }, { "epoch": 4.6, "learning_rate": 3.105892637361041e-07, "loss": 1.5573, "step": 183300 }, { "epoch": 4.61, "learning_rate": 3.0669649295081205e-07, "loss": 1.5346, "step": 183400 }, { "epoch": 4.61, "learning_rate": 3.0282789133629034e-07, "loss": 1.5947, "step": 183500 }, { "epoch": 4.61, "learning_rate": 2.9898346853846517e-07, "loss": 1.4348, "step": 183600 }, { "epoch": 4.61, "learning_rate": 2.9516323414297666e-07, "loss": 1.6258, "step": 183700 }, { "epoch": 4.62, "learning_rate": 2.9136719767515307e-07, "loss": 1.5198, "step": 183800 }, { "epoch": 4.62, "learning_rate": 2.875953685999855e-07, "loss": 1.4458, "step": 183900 }, { "epoch": 4.62, "learning_rate": 2.838477563221098e-07, "loss": 1.4127, "step": 184000 }, { "epoch": 4.62, "learning_rate": 2.8012437018578034e-07, "loss": 1.6128, "step": 184100 }, { "epoch": 4.63, "learning_rate": 2.7642521947484404e-07, "loss": 1.6197, "step": 184200 }, { "epoch": 4.63, "learning_rate": 2.7275031341272186e-07, "loss": 1.3585, "step": 184300 }, { "epoch": 4.63, "learning_rate": 2.6909966116237975e-07, "loss": 1.5263, "step": 184400 }, { "epoch": 4.63, "learning_rate": 2.654732718263131e-07, "loss": 1.3267, "step": 184500 }, { "epoch": 4.64, "learning_rate": 2.6187115444651803e-07, "loss": 1.525, "step": 184600 }, { "epoch": 4.64, "learning_rate": 2.5829331800447555e-07, "loss": 1.5453, "step": 184700 }, { "epoch": 4.64, "learning_rate": 2.547397714211175e-07, "loss": 1.5968, "step": 184800 }, { "epoch": 4.64, "learning_rate": 2.512105235568185e-07, "loss": 1.6909, "step": 184900 }, { "epoch": 4.65, "learning_rate": 2.4770558321136284e-07, "loss": 1.4658, "step": 185000 }, { "epoch": 4.65, "learning_rate": 2.4425964497078014e-07, "loss": 1.5876, "step": 185100 }, { "epoch": 4.65, "learning_rate": 2.4080310252779016e-07, "loss": 1.4124, "step": 185200 }, { "epoch": 4.65, "learning_rate": 2.3737089355338695e-07, "loss": 1.5184, "step": 185300 }, { "epoch": 4.66, "learning_rate": 2.339630266054016e-07, "loss": 1.4806, "step": 185400 }, { "epoch": 4.66, "learning_rate": 2.3057951018096937e-07, "loss": 1.5421, "step": 185500 }, { "epoch": 4.66, "learning_rate": 2.2722035271651067e-07, "loss": 1.6232, "step": 185600 }, { "epoch": 4.66, "learning_rate": 2.238855625877101e-07, "loss": 1.5913, "step": 185700 }, { "epoch": 4.67, "learning_rate": 2.2057514810949532e-07, "loss": 1.4531, "step": 185800 }, { "epoch": 4.67, "learning_rate": 2.172891175360148e-07, "loss": 1.4164, "step": 185900 }, { "epoch": 4.67, "learning_rate": 2.1402747906062004e-07, "loss": 1.7549, "step": 186000 }, { "epoch": 4.67, "learning_rate": 2.1079024081584132e-07, "loss": 1.584, "step": 186100 }, { "epoch": 4.68, "learning_rate": 2.075774108733719e-07, "loss": 1.7102, "step": 186200 }, { "epoch": 4.68, "learning_rate": 2.0438899724404383e-07, "loss": 1.5705, "step": 186300 }, { "epoch": 4.68, "learning_rate": 2.012250078778122e-07, "loss": 1.627, "step": 186400 }, { "epoch": 4.68, "learning_rate": 1.9808545066373087e-07, "loss": 1.432, "step": 186500 }, { "epoch": 4.69, "learning_rate": 1.9497033342993465e-07, "loss": 1.7212, "step": 186600 }, { "epoch": 4.69, "learning_rate": 1.9187966394362156e-07, "loss": 1.5345, "step": 186700 }, { "epoch": 4.69, "learning_rate": 1.8881344991103169e-07, "loss": 1.5824, "step": 186800 }, { "epoch": 4.69, "learning_rate": 1.857716989774261e-07, "loss": 1.5104, "step": 186900 }, { "epoch": 4.7, "learning_rate": 1.8275441872707355e-07, "loss": 1.5922, "step": 187000 }, { "epoch": 4.7, "learning_rate": 1.7979142351198687e-07, "loss": 1.5801, "step": 187100 }, { "epoch": 4.7, "learning_rate": 1.7682286224343314e-07, "loss": 1.5187, "step": 187200 }, { "epoch": 4.7, "learning_rate": 1.7387879397105735e-07, "loss": 1.5425, "step": 187300 }, { "epoch": 4.71, "learning_rate": 1.7095922603556526e-07, "loss": 1.5001, "step": 187400 }, { "epoch": 4.71, "learning_rate": 1.680641657165738e-07, "loss": 1.538, "step": 187500 }, { "epoch": 4.71, "learning_rate": 1.65193620232591e-07, "loss": 1.3748, "step": 187600 }, { "epoch": 4.71, "learning_rate": 1.6234759674100487e-07, "loss": 1.6239, "step": 187700 }, { "epoch": 4.72, "learning_rate": 1.5952610233805455e-07, "loss": 1.7261, "step": 187800 }, { "epoch": 4.72, "learning_rate": 1.5675699216485374e-07, "loss": 1.5511, "step": 187900 }, { "epoch": 4.72, "learning_rate": 1.53984331517949e-07, "loss": 1.5148, "step": 188000 }, { "epoch": 4.72, "learning_rate": 1.5123622081255063e-07, "loss": 1.5834, "step": 188100 }, { "epoch": 4.73, "learning_rate": 1.4851266690076415e-07, "loss": 1.6786, "step": 188200 }, { "epoch": 4.73, "learning_rate": 1.4581367657346857e-07, "loss": 1.5605, "step": 188300 }, { "epoch": 4.73, "learning_rate": 1.4313925656029514e-07, "loss": 1.4843, "step": 188400 }, { "epoch": 4.73, "learning_rate": 1.404894135296131e-07, "loss": 1.5488, "step": 188500 }, { "epoch": 4.74, "learning_rate": 1.3786415408850952e-07, "loss": 1.5413, "step": 188600 }, { "epoch": 4.74, "learning_rate": 1.3526348478277385e-07, "loss": 1.4308, "step": 188700 }, { "epoch": 4.74, "learning_rate": 1.3268741209688796e-07, "loss": 1.4389, "step": 188800 }, { "epoch": 4.74, "learning_rate": 1.301359424539994e-07, "loss": 1.6397, "step": 188900 }, { "epoch": 4.75, "learning_rate": 1.2760908221591483e-07, "loss": 1.6472, "step": 189000 }, { "epoch": 4.75, "learning_rate": 1.2510683768307662e-07, "loss": 1.357, "step": 189100 }, { "epoch": 4.75, "learning_rate": 1.2262921509455296e-07, "loss": 1.4893, "step": 189200 }, { "epoch": 4.75, "learning_rate": 1.2017622062801993e-07, "loss": 1.5907, "step": 189300 }, { "epoch": 4.76, "learning_rate": 1.1774786039974506e-07, "loss": 1.5199, "step": 189400 }, { "epoch": 4.76, "learning_rate": 1.1534414046457388e-07, "loss": 1.3608, "step": 189500 }, { "epoch": 4.76, "learning_rate": 1.1296506681591324e-07, "loss": 1.5448, "step": 189600 }, { "epoch": 4.77, "learning_rate": 1.1061064538571808e-07, "loss": 1.6065, "step": 189700 }, { "epoch": 4.77, "learning_rate": 1.0828088204447584e-07, "loss": 1.3494, "step": 189800 }, { "epoch": 4.77, "learning_rate": 1.0597578260119201e-07, "loss": 1.4815, "step": 189900 }, { "epoch": 4.77, "learning_rate": 1.0371803496788568e-07, "loss": 1.7397, "step": 190000 }, { "epoch": 4.78, "learning_rate": 1.014620337202732e-07, "loss": 1.697, "step": 190100 }, { "epoch": 4.78, "learning_rate": 9.923071337265555e-08, "loss": 1.7665, "step": 190200 }, { "epoch": 4.78, "learning_rate": 9.702407948858127e-08, "loss": 1.4968, "step": 190300 }, { "epoch": 4.78, "learning_rate": 9.484213757004479e-08, "loss": 1.4011, "step": 190400 }, { "epoch": 4.79, "learning_rate": 9.268489305747752e-08, "loss": 1.3825, "step": 190500 }, { "epoch": 4.79, "learning_rate": 9.055235132972572e-08, "loss": 1.4756, "step": 190600 }, { "epoch": 4.79, "learning_rate": 8.844451770404494e-08, "loss": 1.449, "step": 190700 }, { "epoch": 4.79, "learning_rate": 8.636139743608329e-08, "loss": 1.4827, "step": 190800 }, { "epoch": 4.8, "learning_rate": 8.430299571986933e-08, "loss": 1.5371, "step": 190900 }, { "epoch": 4.8, "learning_rate": 8.226931768779534e-08, "loss": 1.4967, "step": 191000 }, { "epoch": 4.8, "learning_rate": 8.026036841061402e-08, "loss": 1.4925, "step": 191100 }, { "epoch": 4.8, "learning_rate": 7.82761528974152e-08, "loss": 1.4443, "step": 191200 }, { "epoch": 4.81, "learning_rate": 7.631667609561799e-08, "loss": 1.6004, "step": 191300 }, { "epoch": 4.81, "learning_rate": 7.43819428909598e-08, "loss": 1.6799, "step": 191400 }, { "epoch": 4.81, "learning_rate": 7.247195810748175e-08, "loss": 1.6054, "step": 191500 }, { "epoch": 4.81, "learning_rate": 7.058672650751774e-08, "loss": 1.3827, "step": 191600 }, { "epoch": 4.82, "learning_rate": 6.872625279168321e-08, "loss": 1.5442, "step": 191700 }, { "epoch": 4.82, "learning_rate": 6.689054159886077e-08, "loss": 1.6056, "step": 191800 }, { "epoch": 4.82, "learning_rate": 6.50795975061913e-08, "loss": 1.7632, "step": 191900 }, { "epoch": 4.82, "learning_rate": 6.329342502906288e-08, "loss": 1.55, "step": 192000 }, { "epoch": 4.83, "learning_rate": 6.153202862109741e-08, "loss": 1.4425, "step": 192100 }, { "epoch": 4.83, "learning_rate": 5.979541267413957e-08, "loss": 1.6685, "step": 192200 }, { "epoch": 4.83, "learning_rate": 5.808358151824678e-08, "loss": 1.3299, "step": 192300 }, { "epoch": 4.83, "learning_rate": 5.639653942168033e-08, "loss": 1.4752, "step": 192400 }, { "epoch": 4.84, "learning_rate": 5.473429059089097e-08, "loss": 1.5503, "step": 192500 }, { "epoch": 4.84, "learning_rate": 5.3096839170511114e-08, "loss": 1.3986, "step": 192600 }, { "epoch": 4.84, "learning_rate": 5.148418924334264e-08, "loss": 1.5912, "step": 192700 }, { "epoch": 4.84, "learning_rate": 4.9896344830347996e-08, "loss": 1.6343, "step": 192800 }, { "epoch": 4.85, "learning_rate": 4.8333309890640224e-08, "loss": 1.4908, "step": 192900 }, { "epoch": 4.85, "learning_rate": 4.679508832147295e-08, "loss": 1.5983, "step": 193000 }, { "epoch": 4.85, "learning_rate": 4.52816839582304e-08, "loss": 1.7203, "step": 193100 }, { "epoch": 4.85, "learning_rate": 4.3793100574416325e-08, "loss": 1.5248, "step": 193200 }, { "epoch": 4.86, "learning_rate": 4.232934188164839e-08, "loss": 1.584, "step": 193300 }, { "epoch": 4.86, "learning_rate": 4.0890411529644904e-08, "loss": 1.6542, "step": 193400 }, { "epoch": 4.86, "learning_rate": 3.9476313106218136e-08, "loss": 1.4137, "step": 193500 }, { "epoch": 4.86, "learning_rate": 3.808705013726433e-08, "loss": 1.69, "step": 193600 }, { "epoch": 4.87, "learning_rate": 3.672262608675703e-08, "loss": 1.4444, "step": 193700 }, { "epoch": 4.87, "learning_rate": 3.5383044356734895e-08, "loss": 1.5438, "step": 193800 }, { "epoch": 4.87, "learning_rate": 3.406830828729502e-08, "loss": 1.7066, "step": 193900 }, { "epoch": 4.87, "learning_rate": 3.277842115658514e-08, "loss": 1.4615, "step": 194000 }, { "epoch": 4.88, "learning_rate": 3.1525913501978534e-08, "loss": 1.5115, "step": 194100 }, { "epoch": 4.88, "learning_rate": 3.028548526682995e-08, "loss": 1.4969, "step": 194200 }, { "epoch": 4.88, "learning_rate": 2.9069915402459848e-08, "loss": 1.6788, "step": 194300 }, { "epoch": 4.88, "learning_rate": 2.7879206939753767e-08, "loss": 1.5609, "step": 194400 }, { "epoch": 4.89, "learning_rate": 2.671336284761239e-08, "loss": 1.2681, "step": 194500 }, { "epoch": 4.89, "learning_rate": 2.55723860329371e-08, "loss": 1.6237, "step": 194600 }, { "epoch": 4.89, "learning_rate": 2.4456279340625555e-08, "loss": 1.3887, "step": 194700 }, { "epoch": 4.89, "learning_rate": 2.3365045553566113e-08, "loss": 1.3611, "step": 194800 }, { "epoch": 4.9, "learning_rate": 2.229868739262897e-08, "loss": 1.5573, "step": 194900 }, { "epoch": 4.9, "learning_rate": 2.1257207516658383e-08, "loss": 1.5116, "step": 195000 }, { "epoch": 4.9, "learning_rate": 2.024060852246712e-08, "loss": 1.4603, "step": 195100 }, { "epoch": 4.9, "learning_rate": 1.924889294483423e-08, "loss": 1.5969, "step": 195200 }, { "epoch": 4.91, "learning_rate": 1.8282063256489512e-08, "loss": 1.4309, "step": 195300 }, { "epoch": 4.91, "learning_rate": 1.7340121868114622e-08, "loss": 1.5426, "step": 195400 }, { "epoch": 4.91, "learning_rate": 1.642307112833752e-08, "loss": 1.4415, "step": 195500 }, { "epoch": 4.91, "learning_rate": 1.5530913323721365e-08, "loss": 1.5152, "step": 195600 }, { "epoch": 4.92, "learning_rate": 1.4663650678760077e-08, "loss": 1.6264, "step": 195700 }, { "epoch": 4.92, "learning_rate": 1.3821285355877235e-08, "loss": 1.5322, "step": 195800 }, { "epoch": 4.92, "learning_rate": 1.3003819455418287e-08, "loss": 1.4464, "step": 195900 }, { "epoch": 4.92, "learning_rate": 1.2211255015641687e-08, "loss": 1.5836, "step": 196000 }, { "epoch": 4.93, "learning_rate": 1.1451147344400116e-08, "loss": 1.46, "step": 196100 }, { "epoch": 4.93, "learning_rate": 1.0708142629628493e-08, "loss": 1.6158, "step": 196200 }, { "epoch": 4.93, "learning_rate": 9.990045099553814e-09, "loss": 1.4556, "step": 196300 }, { "epoch": 4.93, "learning_rate": 9.296856544671607e-09, "loss": 1.5495, "step": 196400 }, { "epoch": 4.94, "learning_rate": 8.628578693370416e-09, "loss": 1.3709, "step": 196500 }, { "epoch": 4.94, "learning_rate": 7.985213211927356e-09, "loss": 1.4993, "step": 196600 }, { "epoch": 4.94, "learning_rate": 7.366761704501457e-09, "loss": 1.5032, "step": 196700 }, { "epoch": 4.94, "learning_rate": 6.7732257131336574e-09, "loss": 1.3548, "step": 196800 }, { "epoch": 4.95, "learning_rate": 6.204606717739037e-09, "loss": 1.5984, "step": 196900 }, { "epoch": 4.95, "learning_rate": 5.660906136104593e-09, "loss": 1.6287, "step": 197000 }, { "epoch": 4.95, "learning_rate": 5.147189774853401e-09, "loss": 1.6333, "step": 197100 }, { "epoch": 4.95, "learning_rate": 4.6530808087486e-09, "loss": 1.7158, "step": 197200 }, { "epoch": 4.96, "learning_rate": 4.183894124962784e-09, "loss": 1.8098, "step": 197300 }, { "epoch": 4.96, "learning_rate": 3.739630893359047e-09, "loss": 1.4564, "step": 197400 }, { "epoch": 4.96, "learning_rate": 3.3202922216579726e-09, "loss": 1.5274, "step": 197500 }, { "epoch": 4.96, "learning_rate": 2.925879155435407e-09, "loss": 1.5423, "step": 197600 }, { "epoch": 4.97, "learning_rate": 2.556392678114694e-09, "loss": 1.7297, "step": 197700 }, { "epoch": 4.97, "learning_rate": 2.2118337109700016e-09, "loss": 1.8108, "step": 197800 }, { "epoch": 4.97, "learning_rate": 1.892203113120772e-09, "loss": 1.4071, "step": 197900 }, { "epoch": 4.97, "learning_rate": 1.5975016815295007e-09, "loss": 1.5121, "step": 198000 }, { "epoch": 4.98, "learning_rate": 1.3277301510017382e-09, "loss": 1.5412, "step": 198100 }, { "epoch": 4.98, "learning_rate": 1.082889194182757e-09, "loss": 1.5034, "step": 198200 }, { "epoch": 4.98, "learning_rate": 8.629794215564424e-10, "loss": 1.6926, "step": 198300 }, { "epoch": 4.98, "learning_rate": 6.68001381443073e-10, "loss": 1.5571, "step": 198400 }, { "epoch": 4.99, "learning_rate": 4.979555599982089e-10, "loss": 1.3386, "step": 198500 }, { "epoch": 4.99, "learning_rate": 3.528423812126924e-10, "loss": 1.4871, "step": 198600 }, { "epoch": 4.99, "learning_rate": 2.3266220691042786e-10, "loss": 1.504, "step": 198700 }, { "epoch": 4.99, "learning_rate": 1.3741533674505036e-10, "loss": 1.5957, "step": 198800 }, { "epoch": 5.0, "learning_rate": 6.710200820658764e-11, "loss": 1.4233, "step": 198900 }, { "epoch": 5.0, "learning_rate": 2.1722396612577912e-11, "loss": 1.5864, "step": 199000 }, { "epoch": 5.0, "eval_loss": 1.468190312385559, "eval_runtime": 108.9768, "eval_samples_per_second": 73.071, "eval_steps_per_second": 9.14, "step": 199055 } ], "logging_steps": 100, "max_steps": 199055, "num_train_epochs": 5, "save_steps": 500, "total_flos": 4.621562918731776e+16, "trial_name": null, "trial_params": null }