{ "best_metric": null, "best_model_checkpoint": null, "epoch": 10.0, "global_step": 177010, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.03, "learning_rate": 4.985876504152308e-05, "loss": 3.3413, "step": 500 }, { "epoch": 0.06, "learning_rate": 4.971753008304616e-05, "loss": 3.2871, "step": 1000 }, { "epoch": 0.08, "learning_rate": 4.9576295124569234e-05, "loss": 3.2263, "step": 1500 }, { "epoch": 0.11, "learning_rate": 4.943506016609231e-05, "loss": 3.2316, "step": 2000 }, { "epoch": 0.14, "learning_rate": 4.929382520761539e-05, "loss": 3.1903, "step": 2500 }, { "epoch": 0.17, "learning_rate": 4.915259024913847e-05, "loss": 3.1967, "step": 3000 }, { "epoch": 0.2, "learning_rate": 4.901135529066155e-05, "loss": 3.181, "step": 3500 }, { "epoch": 0.23, "learning_rate": 4.8870120332184624e-05, "loss": 3.1665, "step": 4000 }, { "epoch": 0.25, "learning_rate": 4.87288853737077e-05, "loss": 3.1597, "step": 4500 }, { "epoch": 0.28, "learning_rate": 4.8587650415230776e-05, "loss": 3.1482, "step": 5000 }, { "epoch": 0.31, "learning_rate": 4.8446415456753855e-05, "loss": 3.1244, "step": 5500 }, { "epoch": 0.34, "learning_rate": 4.8305180498276935e-05, "loss": 3.1668, "step": 6000 }, { "epoch": 0.37, "learning_rate": 4.8163945539800014e-05, "loss": 3.1144, "step": 6500 }, { "epoch": 0.4, "learning_rate": 4.8022710581323093e-05, "loss": 3.1353, "step": 7000 }, { "epoch": 0.42, "learning_rate": 4.7881475622846166e-05, "loss": 3.1212, "step": 7500 }, { "epoch": 0.45, "learning_rate": 4.7740240664369245e-05, "loss": 3.0918, "step": 8000 }, { "epoch": 0.48, "learning_rate": 4.7599005705892325e-05, "loss": 3.1366, "step": 8500 }, { "epoch": 0.51, "learning_rate": 4.7457770747415404e-05, "loss": 3.1026, "step": 9000 }, { "epoch": 0.54, "learning_rate": 4.7316535788938484e-05, "loss": 3.0913, "step": 9500 }, { "epoch": 0.56, "learning_rate": 4.717530083046156e-05, "loss": 3.0663, "step": 10000 }, { "epoch": 0.59, "learning_rate": 4.7034065871984636e-05, "loss": 3.0958, "step": 10500 }, { "epoch": 0.62, "learning_rate": 4.6892830913507715e-05, "loss": 3.0529, "step": 11000 }, { "epoch": 0.65, "learning_rate": 4.6751595955030794e-05, "loss": 3.0909, "step": 11500 }, { "epoch": 0.68, "learning_rate": 4.661036099655387e-05, "loss": 3.0962, "step": 12000 }, { "epoch": 0.71, "learning_rate": 4.6469126038076946e-05, "loss": 3.0731, "step": 12500 }, { "epoch": 0.73, "learning_rate": 4.632789107960002e-05, "loss": 3.0736, "step": 13000 }, { "epoch": 0.76, "learning_rate": 4.61866561211231e-05, "loss": 3.0786, "step": 13500 }, { "epoch": 0.79, "learning_rate": 4.604542116264618e-05, "loss": 3.0708, "step": 14000 }, { "epoch": 0.82, "learning_rate": 4.590418620416926e-05, "loss": 3.0641, "step": 14500 }, { "epoch": 0.85, "learning_rate": 4.5762951245692336e-05, "loss": 3.0344, "step": 15000 }, { "epoch": 0.88, "learning_rate": 4.5621716287215416e-05, "loss": 3.061, "step": 15500 }, { "epoch": 0.9, "learning_rate": 4.548048132873849e-05, "loss": 3.0766, "step": 16000 }, { "epoch": 0.93, "learning_rate": 4.533924637026157e-05, "loss": 3.0682, "step": 16500 }, { "epoch": 0.96, "learning_rate": 4.519801141178465e-05, "loss": 3.0431, "step": 17000 }, { "epoch": 0.99, "learning_rate": 4.5056776453307727e-05, "loss": 3.064, "step": 17500 }, { "epoch": 1.02, "learning_rate": 4.4915541494830806e-05, "loss": 2.8743, "step": 18000 }, { "epoch": 1.05, "learning_rate": 4.4774306536353885e-05, "loss": 2.75, "step": 18500 }, { "epoch": 1.07, "learning_rate": 4.463307157787696e-05, "loss": 2.7833, "step": 19000 }, { "epoch": 1.1, "learning_rate": 4.449183661940004e-05, "loss": 2.7679, "step": 19500 }, { "epoch": 1.13, "learning_rate": 4.435060166092312e-05, "loss": 2.7905, "step": 20000 }, { "epoch": 1.16, "learning_rate": 4.420936670244619e-05, "loss": 2.7913, "step": 20500 }, { "epoch": 1.19, "learning_rate": 4.406813174396927e-05, "loss": 2.8132, "step": 21000 }, { "epoch": 1.21, "learning_rate": 4.392689678549235e-05, "loss": 2.7929, "step": 21500 }, { "epoch": 1.24, "learning_rate": 4.378566182701542e-05, "loss": 2.7994, "step": 22000 }, { "epoch": 1.27, "learning_rate": 4.36444268685385e-05, "loss": 2.7934, "step": 22500 }, { "epoch": 1.3, "learning_rate": 4.350319191006158e-05, "loss": 2.8068, "step": 23000 }, { "epoch": 1.33, "learning_rate": 4.336195695158466e-05, "loss": 2.7842, "step": 23500 }, { "epoch": 1.36, "learning_rate": 4.322072199310774e-05, "loss": 2.8079, "step": 24000 }, { "epoch": 1.38, "learning_rate": 4.307948703463082e-05, "loss": 2.7959, "step": 24500 }, { "epoch": 1.41, "learning_rate": 4.293825207615389e-05, "loss": 2.8159, "step": 25000 }, { "epoch": 1.44, "learning_rate": 4.279701711767697e-05, "loss": 2.8135, "step": 25500 }, { "epoch": 1.47, "learning_rate": 4.265578215920005e-05, "loss": 2.8063, "step": 26000 }, { "epoch": 1.5, "learning_rate": 4.251454720072313e-05, "loss": 2.8289, "step": 26500 }, { "epoch": 1.53, "learning_rate": 4.237331224224621e-05, "loss": 2.8124, "step": 27000 }, { "epoch": 1.55, "learning_rate": 4.223207728376928e-05, "loss": 2.8181, "step": 27500 }, { "epoch": 1.58, "learning_rate": 4.209084232529236e-05, "loss": 2.8284, "step": 28000 }, { "epoch": 1.61, "learning_rate": 4.194960736681543e-05, "loss": 2.8456, "step": 28500 }, { "epoch": 1.64, "learning_rate": 4.180837240833851e-05, "loss": 2.8413, "step": 29000 }, { "epoch": 1.67, "learning_rate": 4.166713744986159e-05, "loss": 2.7965, "step": 29500 }, { "epoch": 1.69, "learning_rate": 4.152590249138467e-05, "loss": 2.8385, "step": 30000 }, { "epoch": 1.72, "learning_rate": 4.138466753290774e-05, "loss": 2.8246, "step": 30500 }, { "epoch": 1.75, "learning_rate": 4.124343257443082e-05, "loss": 2.83, "step": 31000 }, { "epoch": 1.78, "learning_rate": 4.11021976159539e-05, "loss": 2.8387, "step": 31500 }, { "epoch": 1.81, "learning_rate": 4.096096265747698e-05, "loss": 2.8369, "step": 32000 }, { "epoch": 1.84, "learning_rate": 4.081972769900006e-05, "loss": 2.8197, "step": 32500 }, { "epoch": 1.86, "learning_rate": 4.067849274052314e-05, "loss": 2.8224, "step": 33000 }, { "epoch": 1.89, "learning_rate": 4.053725778204621e-05, "loss": 2.8123, "step": 33500 }, { "epoch": 1.92, "learning_rate": 4.039602282356929e-05, "loss": 2.8198, "step": 34000 }, { "epoch": 1.95, "learning_rate": 4.025478786509237e-05, "loss": 2.8318, "step": 34500 }, { "epoch": 1.98, "learning_rate": 4.011355290661545e-05, "loss": 2.8398, "step": 35000 }, { "epoch": 2.01, "learning_rate": 3.997231794813853e-05, "loss": 2.7405, "step": 35500 }, { "epoch": 2.03, "learning_rate": 3.98310829896616e-05, "loss": 2.5663, "step": 36000 }, { "epoch": 2.06, "learning_rate": 3.968984803118468e-05, "loss": 2.5434, "step": 36500 }, { "epoch": 2.09, "learning_rate": 3.9548613072707755e-05, "loss": 2.5603, "step": 37000 }, { "epoch": 2.12, "learning_rate": 3.9407378114230834e-05, "loss": 2.5647, "step": 37500 }, { "epoch": 2.15, "learning_rate": 3.9266143155753913e-05, "loss": 2.5591, "step": 38000 }, { "epoch": 2.18, "learning_rate": 3.912490819727699e-05, "loss": 2.557, "step": 38500 }, { "epoch": 2.2, "learning_rate": 3.8983673238800065e-05, "loss": 2.5874, "step": 39000 }, { "epoch": 2.23, "learning_rate": 3.8842438280323145e-05, "loss": 2.5848, "step": 39500 }, { "epoch": 2.26, "learning_rate": 3.8701203321846224e-05, "loss": 2.5693, "step": 40000 }, { "epoch": 2.29, "learning_rate": 3.8559968363369304e-05, "loss": 2.5997, "step": 40500 }, { "epoch": 2.32, "learning_rate": 3.841873340489238e-05, "loss": 2.5978, "step": 41000 }, { "epoch": 2.34, "learning_rate": 3.827749844641546e-05, "loss": 2.5705, "step": 41500 }, { "epoch": 2.37, "learning_rate": 3.8136263487938535e-05, "loss": 2.6125, "step": 42000 }, { "epoch": 2.4, "learning_rate": 3.7995028529461614e-05, "loss": 2.6105, "step": 42500 }, { "epoch": 2.43, "learning_rate": 3.7853793570984694e-05, "loss": 2.6086, "step": 43000 }, { "epoch": 2.46, "learning_rate": 3.771255861250777e-05, "loss": 2.6181, "step": 43500 }, { "epoch": 2.49, "learning_rate": 3.7571323654030846e-05, "loss": 2.5933, "step": 44000 }, { "epoch": 2.51, "learning_rate": 3.7430088695553925e-05, "loss": 2.6127, "step": 44500 }, { "epoch": 2.54, "learning_rate": 3.7288853737077e-05, "loss": 2.5906, "step": 45000 }, { "epoch": 2.57, "learning_rate": 3.714761877860008e-05, "loss": 2.6226, "step": 45500 }, { "epoch": 2.6, "learning_rate": 3.7006383820123157e-05, "loss": 2.6157, "step": 46000 }, { "epoch": 2.63, "learning_rate": 3.6865148861646236e-05, "loss": 2.6168, "step": 46500 }, { "epoch": 2.66, "learning_rate": 3.6723913903169315e-05, "loss": 2.6321, "step": 47000 }, { "epoch": 2.68, "learning_rate": 3.6582678944692395e-05, "loss": 2.631, "step": 47500 }, { "epoch": 2.71, "learning_rate": 3.644144398621547e-05, "loss": 2.6225, "step": 48000 }, { "epoch": 2.74, "learning_rate": 3.630020902773855e-05, "loss": 2.5985, "step": 48500 }, { "epoch": 2.77, "learning_rate": 3.6158974069261626e-05, "loss": 2.6194, "step": 49000 }, { "epoch": 2.8, "learning_rate": 3.6017739110784705e-05, "loss": 2.6228, "step": 49500 }, { "epoch": 2.82, "learning_rate": 3.5876504152307785e-05, "loss": 2.6266, "step": 50000 }, { "epoch": 2.85, "learning_rate": 3.5735269193830864e-05, "loss": 2.635, "step": 50500 }, { "epoch": 2.88, "learning_rate": 3.559403423535394e-05, "loss": 2.6387, "step": 51000 }, { "epoch": 2.91, "learning_rate": 3.5452799276877016e-05, "loss": 2.6477, "step": 51500 }, { "epoch": 2.94, "learning_rate": 3.531156431840009e-05, "loss": 2.637, "step": 52000 }, { "epoch": 2.97, "learning_rate": 3.517032935992317e-05, "loss": 2.6528, "step": 52500 }, { "epoch": 2.99, "learning_rate": 3.502909440144625e-05, "loss": 2.6596, "step": 53000 }, { "epoch": 3.02, "learning_rate": 3.488785944296932e-05, "loss": 2.4093, "step": 53500 }, { "epoch": 3.05, "learning_rate": 3.47466244844924e-05, "loss": 2.3596, "step": 54000 }, { "epoch": 3.08, "learning_rate": 3.460538952601548e-05, "loss": 2.3662, "step": 54500 }, { "epoch": 3.11, "learning_rate": 3.446415456753856e-05, "loss": 2.3709, "step": 55000 }, { "epoch": 3.14, "learning_rate": 3.432291960906164e-05, "loss": 2.3823, "step": 55500 }, { "epoch": 3.16, "learning_rate": 3.418168465058472e-05, "loss": 2.3749, "step": 56000 }, { "epoch": 3.19, "learning_rate": 3.404044969210779e-05, "loss": 2.3889, "step": 56500 }, { "epoch": 3.22, "learning_rate": 3.389921473363087e-05, "loss": 2.3777, "step": 57000 }, { "epoch": 3.25, "learning_rate": 3.375797977515395e-05, "loss": 2.4009, "step": 57500 }, { "epoch": 3.28, "learning_rate": 3.361674481667703e-05, "loss": 2.403, "step": 58000 }, { "epoch": 3.3, "learning_rate": 3.347550985820011e-05, "loss": 2.4091, "step": 58500 }, { "epoch": 3.33, "learning_rate": 3.3334274899723187e-05, "loss": 2.4504, "step": 59000 }, { "epoch": 3.36, "learning_rate": 3.319303994124626e-05, "loss": 2.4165, "step": 59500 }, { "epoch": 3.39, "learning_rate": 3.305180498276934e-05, "loss": 2.408, "step": 60000 }, { "epoch": 3.42, "learning_rate": 3.291057002429241e-05, "loss": 2.4213, "step": 60500 }, { "epoch": 3.45, "learning_rate": 3.276933506581549e-05, "loss": 2.4162, "step": 61000 }, { "epoch": 3.47, "learning_rate": 3.262810010733857e-05, "loss": 2.4156, "step": 61500 }, { "epoch": 3.5, "learning_rate": 3.248686514886165e-05, "loss": 2.4263, "step": 62000 }, { "epoch": 3.53, "learning_rate": 3.234563019038472e-05, "loss": 2.4268, "step": 62500 }, { "epoch": 3.56, "learning_rate": 3.22043952319078e-05, "loss": 2.4019, "step": 63000 }, { "epoch": 3.59, "learning_rate": 3.206316027343088e-05, "loss": 2.4252, "step": 63500 }, { "epoch": 3.62, "learning_rate": 3.192192531495396e-05, "loss": 2.442, "step": 64000 }, { "epoch": 3.64, "learning_rate": 3.178069035647704e-05, "loss": 2.4226, "step": 64500 }, { "epoch": 3.67, "learning_rate": 3.163945539800011e-05, "loss": 2.4471, "step": 65000 }, { "epoch": 3.7, "learning_rate": 3.149822043952319e-05, "loss": 2.4206, "step": 65500 }, { "epoch": 3.73, "learning_rate": 3.135698548104627e-05, "loss": 2.4499, "step": 66000 }, { "epoch": 3.76, "learning_rate": 3.121575052256935e-05, "loss": 2.446, "step": 66500 }, { "epoch": 3.79, "learning_rate": 3.107451556409243e-05, "loss": 2.4632, "step": 67000 }, { "epoch": 3.81, "learning_rate": 3.09332806056155e-05, "loss": 2.462, "step": 67500 }, { "epoch": 3.84, "learning_rate": 3.079204564713858e-05, "loss": 2.4722, "step": 68000 }, { "epoch": 3.87, "learning_rate": 3.0650810688661654e-05, "loss": 2.4678, "step": 68500 }, { "epoch": 3.9, "learning_rate": 3.0509575730184737e-05, "loss": 2.4871, "step": 69000 }, { "epoch": 3.93, "learning_rate": 3.0368340771707816e-05, "loss": 2.4585, "step": 69500 }, { "epoch": 3.95, "learning_rate": 3.0227105813230892e-05, "loss": 2.4802, "step": 70000 }, { "epoch": 3.98, "learning_rate": 3.0085870854753972e-05, "loss": 2.4703, "step": 70500 }, { "epoch": 4.01, "learning_rate": 2.9944635896277044e-05, "loss": 2.3879, "step": 71000 }, { "epoch": 4.04, "learning_rate": 2.9803400937800124e-05, "loss": 2.2056, "step": 71500 }, { "epoch": 4.07, "learning_rate": 2.9662165979323203e-05, "loss": 2.209, "step": 72000 }, { "epoch": 4.1, "learning_rate": 2.9520931020846282e-05, "loss": 2.2496, "step": 72500 }, { "epoch": 4.12, "learning_rate": 2.9379696062369362e-05, "loss": 2.2075, "step": 73000 }, { "epoch": 4.15, "learning_rate": 2.9238461103892438e-05, "loss": 2.2253, "step": 73500 }, { "epoch": 4.18, "learning_rate": 2.9097226145415514e-05, "loss": 2.2405, "step": 74000 }, { "epoch": 4.21, "learning_rate": 2.895599118693859e-05, "loss": 2.2353, "step": 74500 }, { "epoch": 4.24, "learning_rate": 2.881475622846167e-05, "loss": 2.2074, "step": 75000 }, { "epoch": 4.27, "learning_rate": 2.867352126998475e-05, "loss": 2.2315, "step": 75500 }, { "epoch": 4.29, "learning_rate": 2.8532286311507828e-05, "loss": 2.2407, "step": 76000 }, { "epoch": 4.32, "learning_rate": 2.83910513530309e-05, "loss": 2.2213, "step": 76500 }, { "epoch": 4.35, "learning_rate": 2.824981639455398e-05, "loss": 2.2676, "step": 77000 }, { "epoch": 4.38, "learning_rate": 2.810858143607706e-05, "loss": 2.2671, "step": 77500 }, { "epoch": 4.41, "learning_rate": 2.7967346477600135e-05, "loss": 2.2482, "step": 78000 }, { "epoch": 4.43, "learning_rate": 2.7826111519123215e-05, "loss": 2.2563, "step": 78500 }, { "epoch": 4.46, "learning_rate": 2.7684876560646294e-05, "loss": 2.2629, "step": 79000 }, { "epoch": 4.49, "learning_rate": 2.7543641602169367e-05, "loss": 2.2547, "step": 79500 }, { "epoch": 4.52, "learning_rate": 2.7402406643692446e-05, "loss": 2.2762, "step": 80000 }, { "epoch": 4.55, "learning_rate": 2.7261171685215525e-05, "loss": 2.2484, "step": 80500 }, { "epoch": 4.58, "learning_rate": 2.7119936726738605e-05, "loss": 2.2779, "step": 81000 }, { "epoch": 4.6, "learning_rate": 2.6978701768261684e-05, "loss": 2.2956, "step": 81500 }, { "epoch": 4.63, "learning_rate": 2.683746680978476e-05, "loss": 2.2861, "step": 82000 }, { "epoch": 4.66, "learning_rate": 2.6696231851307836e-05, "loss": 2.2722, "step": 82500 }, { "epoch": 4.69, "learning_rate": 2.6554996892830912e-05, "loss": 2.2839, "step": 83000 }, { "epoch": 4.72, "learning_rate": 2.641376193435399e-05, "loss": 2.3063, "step": 83500 }, { "epoch": 4.75, "learning_rate": 2.627252697587707e-05, "loss": 2.2823, "step": 84000 }, { "epoch": 4.77, "learning_rate": 2.613129201740015e-05, "loss": 2.3072, "step": 84500 }, { "epoch": 4.8, "learning_rate": 2.599005705892323e-05, "loss": 2.2991, "step": 85000 }, { "epoch": 4.83, "learning_rate": 2.5848822100446302e-05, "loss": 2.3157, "step": 85500 }, { "epoch": 4.86, "learning_rate": 2.5707587141969382e-05, "loss": 2.2799, "step": 86000 }, { "epoch": 4.89, "learning_rate": 2.5566352183492458e-05, "loss": 2.2816, "step": 86500 }, { "epoch": 4.91, "learning_rate": 2.5425117225015537e-05, "loss": 2.2798, "step": 87000 }, { "epoch": 4.94, "learning_rate": 2.5283882266538617e-05, "loss": 2.307, "step": 87500 }, { "epoch": 4.97, "learning_rate": 2.5142647308061696e-05, "loss": 2.2899, "step": 88000 }, { "epoch": 5.0, "learning_rate": 2.500141234958477e-05, "loss": 2.3, "step": 88500 }, { "epoch": 5.03, "learning_rate": 2.4860177391107848e-05, "loss": 2.0441, "step": 89000 }, { "epoch": 5.06, "learning_rate": 2.4718942432630927e-05, "loss": 2.0678, "step": 89500 }, { "epoch": 5.08, "learning_rate": 2.4577707474154003e-05, "loss": 2.074, "step": 90000 }, { "epoch": 5.11, "learning_rate": 2.443647251567708e-05, "loss": 2.0784, "step": 90500 }, { "epoch": 5.14, "learning_rate": 2.429523755720016e-05, "loss": 2.0702, "step": 91000 }, { "epoch": 5.17, "learning_rate": 2.4154002598723238e-05, "loss": 2.0951, "step": 91500 }, { "epoch": 5.2, "learning_rate": 2.4012767640246314e-05, "loss": 2.0874, "step": 92000 }, { "epoch": 5.23, "learning_rate": 2.3871532681769393e-05, "loss": 2.088, "step": 92500 }, { "epoch": 5.25, "learning_rate": 2.3730297723292473e-05, "loss": 2.102, "step": 93000 }, { "epoch": 5.28, "learning_rate": 2.358906276481555e-05, "loss": 2.0919, "step": 93500 }, { "epoch": 5.31, "learning_rate": 2.3447827806338625e-05, "loss": 2.1272, "step": 94000 }, { "epoch": 5.34, "learning_rate": 2.3306592847861704e-05, "loss": 2.0911, "step": 94500 }, { "epoch": 5.37, "learning_rate": 2.316535788938478e-05, "loss": 2.1141, "step": 95000 }, { "epoch": 5.4, "learning_rate": 2.302412293090786e-05, "loss": 2.1297, "step": 95500 }, { "epoch": 5.42, "learning_rate": 2.2882887972430936e-05, "loss": 2.1072, "step": 96000 }, { "epoch": 5.45, "learning_rate": 2.2741653013954015e-05, "loss": 2.1144, "step": 96500 }, { "epoch": 5.48, "learning_rate": 2.2600418055477094e-05, "loss": 2.1087, "step": 97000 }, { "epoch": 5.51, "learning_rate": 2.245918309700017e-05, "loss": 2.1283, "step": 97500 }, { "epoch": 5.54, "learning_rate": 2.231794813852325e-05, "loss": 2.1053, "step": 98000 }, { "epoch": 5.56, "learning_rate": 2.2176713180046326e-05, "loss": 2.1368, "step": 98500 }, { "epoch": 5.59, "learning_rate": 2.20354782215694e-05, "loss": 2.1244, "step": 99000 }, { "epoch": 5.62, "learning_rate": 2.189424326309248e-05, "loss": 2.1426, "step": 99500 }, { "epoch": 5.65, "learning_rate": 2.175300830461556e-05, "loss": 2.132, "step": 100000 }, { "epoch": 5.68, "learning_rate": 2.1611773346138636e-05, "loss": 2.1389, "step": 100500 }, { "epoch": 5.71, "learning_rate": 2.1470538387661716e-05, "loss": 2.13, "step": 101000 }, { "epoch": 5.73, "learning_rate": 2.1329303429184795e-05, "loss": 2.1177, "step": 101500 }, { "epoch": 5.76, "learning_rate": 2.118806847070787e-05, "loss": 2.1378, "step": 102000 }, { "epoch": 5.79, "learning_rate": 2.1046833512230947e-05, "loss": 2.1325, "step": 102500 }, { "epoch": 5.82, "learning_rate": 2.0905598553754027e-05, "loss": 2.139, "step": 103000 }, { "epoch": 5.85, "learning_rate": 2.0764363595277103e-05, "loss": 2.1274, "step": 103500 }, { "epoch": 5.88, "learning_rate": 2.0623128636800182e-05, "loss": 2.1305, "step": 104000 }, { "epoch": 5.9, "learning_rate": 2.048189367832326e-05, "loss": 2.127, "step": 104500 }, { "epoch": 5.93, "learning_rate": 2.0340658719846337e-05, "loss": 2.1525, "step": 105000 }, { "epoch": 5.96, "learning_rate": 2.0199423761369417e-05, "loss": 2.1471, "step": 105500 }, { "epoch": 5.99, "learning_rate": 2.0058188802892493e-05, "loss": 2.1616, "step": 106000 }, { "epoch": 6.02, "learning_rate": 1.991695384441557e-05, "loss": 2.0195, "step": 106500 }, { "epoch": 6.04, "learning_rate": 1.9775718885938648e-05, "loss": 1.9568, "step": 107000 }, { "epoch": 6.07, "learning_rate": 1.9634483927461727e-05, "loss": 1.9251, "step": 107500 }, { "epoch": 6.1, "learning_rate": 1.9493248968984803e-05, "loss": 1.9556, "step": 108000 }, { "epoch": 6.13, "learning_rate": 1.9352014010507883e-05, "loss": 1.9674, "step": 108500 }, { "epoch": 6.16, "learning_rate": 1.921077905203096e-05, "loss": 1.9599, "step": 109000 }, { "epoch": 6.19, "learning_rate": 1.9069544093554038e-05, "loss": 1.9753, "step": 109500 }, { "epoch": 6.21, "learning_rate": 1.8928309135077114e-05, "loss": 1.951, "step": 110000 }, { "epoch": 6.24, "learning_rate": 1.878707417660019e-05, "loss": 1.9851, "step": 110500 }, { "epoch": 6.27, "learning_rate": 1.864583921812327e-05, "loss": 1.9678, "step": 111000 }, { "epoch": 6.3, "learning_rate": 1.850460425964635e-05, "loss": 1.9631, "step": 111500 }, { "epoch": 6.33, "learning_rate": 1.8363369301169425e-05, "loss": 1.9813, "step": 112000 }, { "epoch": 6.36, "learning_rate": 1.8222134342692504e-05, "loss": 1.9736, "step": 112500 }, { "epoch": 6.38, "learning_rate": 1.8080899384215584e-05, "loss": 1.9931, "step": 113000 }, { "epoch": 6.41, "learning_rate": 1.793966442573866e-05, "loss": 1.9856, "step": 113500 }, { "epoch": 6.44, "learning_rate": 1.779842946726174e-05, "loss": 1.9701, "step": 114000 }, { "epoch": 6.47, "learning_rate": 1.7657194508784815e-05, "loss": 1.9627, "step": 114500 }, { "epoch": 6.5, "learning_rate": 1.751595955030789e-05, "loss": 1.9749, "step": 115000 }, { "epoch": 6.53, "learning_rate": 1.737472459183097e-05, "loss": 1.9957, "step": 115500 }, { "epoch": 6.55, "learning_rate": 1.723348963335405e-05, "loss": 1.9793, "step": 116000 }, { "epoch": 6.58, "learning_rate": 1.7092254674877126e-05, "loss": 1.9792, "step": 116500 }, { "epoch": 6.61, "learning_rate": 1.6951019716400205e-05, "loss": 1.9809, "step": 117000 }, { "epoch": 6.64, "learning_rate": 1.6809784757923285e-05, "loss": 1.984, "step": 117500 }, { "epoch": 6.67, "learning_rate": 1.666854979944636e-05, "loss": 1.9844, "step": 118000 }, { "epoch": 6.69, "learning_rate": 1.6527314840969437e-05, "loss": 1.9945, "step": 118500 }, { "epoch": 6.72, "learning_rate": 1.6386079882492516e-05, "loss": 2.0097, "step": 119000 }, { "epoch": 6.75, "learning_rate": 1.6244844924015592e-05, "loss": 2.0085, "step": 119500 }, { "epoch": 6.78, "learning_rate": 1.610360996553867e-05, "loss": 1.9903, "step": 120000 }, { "epoch": 6.81, "learning_rate": 1.596237500706175e-05, "loss": 1.9873, "step": 120500 }, { "epoch": 6.84, "learning_rate": 1.5821140048584827e-05, "loss": 2.0064, "step": 121000 }, { "epoch": 6.86, "learning_rate": 1.5679905090107906e-05, "loss": 1.9923, "step": 121500 }, { "epoch": 6.89, "learning_rate": 1.5538670131630982e-05, "loss": 2.0165, "step": 122000 }, { "epoch": 6.92, "learning_rate": 1.5397435173154058e-05, "loss": 1.9874, "step": 122500 }, { "epoch": 6.95, "learning_rate": 1.5256200214677137e-05, "loss": 2.0166, "step": 123000 }, { "epoch": 6.98, "learning_rate": 1.5114965256200213e-05, "loss": 1.9818, "step": 123500 }, { "epoch": 7.01, "learning_rate": 1.4973730297723293e-05, "loss": 1.9813, "step": 124000 }, { "epoch": 7.03, "learning_rate": 1.4832495339246372e-05, "loss": 1.8291, "step": 124500 }, { "epoch": 7.06, "learning_rate": 1.4691260380769448e-05, "loss": 1.8125, "step": 125000 }, { "epoch": 7.09, "learning_rate": 1.4550025422292526e-05, "loss": 1.8245, "step": 125500 }, { "epoch": 7.12, "learning_rate": 1.4408790463815605e-05, "loss": 1.8357, "step": 126000 }, { "epoch": 7.15, "learning_rate": 1.4267555505338681e-05, "loss": 1.8543, "step": 126500 }, { "epoch": 7.17, "learning_rate": 1.412632054686176e-05, "loss": 1.8331, "step": 127000 }, { "epoch": 7.2, "learning_rate": 1.3985085588384838e-05, "loss": 1.8727, "step": 127500 }, { "epoch": 7.23, "learning_rate": 1.3843850629907914e-05, "loss": 1.8471, "step": 128000 }, { "epoch": 7.26, "learning_rate": 1.3702615671430994e-05, "loss": 1.8413, "step": 128500 }, { "epoch": 7.29, "learning_rate": 1.3561380712954071e-05, "loss": 1.8588, "step": 129000 }, { "epoch": 7.32, "learning_rate": 1.3420145754477147e-05, "loss": 1.8544, "step": 129500 }, { "epoch": 7.34, "learning_rate": 1.3278910796000227e-05, "loss": 1.865, "step": 130000 }, { "epoch": 7.37, "learning_rate": 1.3137675837523306e-05, "loss": 1.8314, "step": 130500 }, { "epoch": 7.4, "learning_rate": 1.2996440879046382e-05, "loss": 1.8607, "step": 131000 }, { "epoch": 7.43, "learning_rate": 1.285520592056946e-05, "loss": 1.8674, "step": 131500 }, { "epoch": 7.46, "learning_rate": 1.271397096209254e-05, "loss": 1.8549, "step": 132000 }, { "epoch": 7.49, "learning_rate": 1.2572736003615615e-05, "loss": 1.8412, "step": 132500 }, { "epoch": 7.51, "learning_rate": 1.2431501045138693e-05, "loss": 1.8871, "step": 133000 }, { "epoch": 7.54, "learning_rate": 1.229026608666177e-05, "loss": 1.8812, "step": 133500 }, { "epoch": 7.57, "learning_rate": 1.2149031128184848e-05, "loss": 1.8689, "step": 134000 }, { "epoch": 7.6, "learning_rate": 1.2007796169707928e-05, "loss": 1.8721, "step": 134500 }, { "epoch": 7.63, "learning_rate": 1.1866561211231005e-05, "loss": 1.8857, "step": 135000 }, { "epoch": 7.65, "learning_rate": 1.1725326252754081e-05, "loss": 1.8846, "step": 135500 }, { "epoch": 7.68, "learning_rate": 1.158409129427716e-05, "loss": 1.8804, "step": 136000 }, { "epoch": 7.71, "learning_rate": 1.1442856335800238e-05, "loss": 1.892, "step": 136500 }, { "epoch": 7.74, "learning_rate": 1.1301621377323316e-05, "loss": 1.8921, "step": 137000 }, { "epoch": 7.77, "learning_rate": 1.1160386418846392e-05, "loss": 1.8881, "step": 137500 }, { "epoch": 7.8, "learning_rate": 1.1019151460369472e-05, "loss": 1.9009, "step": 138000 }, { "epoch": 7.82, "learning_rate": 1.087791650189255e-05, "loss": 1.9004, "step": 138500 }, { "epoch": 7.85, "learning_rate": 1.0736681543415627e-05, "loss": 1.8725, "step": 139000 }, { "epoch": 7.88, "learning_rate": 1.0595446584938705e-05, "loss": 1.8726, "step": 139500 }, { "epoch": 7.91, "learning_rate": 1.0454211626461782e-05, "loss": 1.8767, "step": 140000 }, { "epoch": 7.94, "learning_rate": 1.031297666798486e-05, "loss": 1.858, "step": 140500 }, { "epoch": 7.97, "learning_rate": 1.0171741709507938e-05, "loss": 1.8896, "step": 141000 }, { "epoch": 7.99, "learning_rate": 1.0030506751031015e-05, "loss": 1.8879, "step": 141500 }, { "epoch": 8.02, "learning_rate": 9.889271792554093e-06, "loss": 1.7842, "step": 142000 }, { "epoch": 8.05, "learning_rate": 9.748036834077172e-06, "loss": 1.7351, "step": 142500 }, { "epoch": 8.08, "learning_rate": 9.606801875600248e-06, "loss": 1.7494, "step": 143000 }, { "epoch": 8.11, "learning_rate": 9.465566917123326e-06, "loss": 1.7528, "step": 143500 }, { "epoch": 8.14, "learning_rate": 9.324331958646404e-06, "loss": 1.7742, "step": 144000 }, { "epoch": 8.16, "learning_rate": 9.183097000169483e-06, "loss": 1.7612, "step": 144500 }, { "epoch": 8.19, "learning_rate": 9.041862041692561e-06, "loss": 1.7453, "step": 145000 }, { "epoch": 8.22, "learning_rate": 8.900627083215637e-06, "loss": 1.7342, "step": 145500 }, { "epoch": 8.25, "learning_rate": 8.759392124738716e-06, "loss": 1.7353, "step": 146000 }, { "epoch": 8.28, "learning_rate": 8.618157166261794e-06, "loss": 1.7624, "step": 146500 }, { "epoch": 8.3, "learning_rate": 8.476922207784872e-06, "loss": 1.7459, "step": 147000 }, { "epoch": 8.33, "learning_rate": 8.33568724930795e-06, "loss": 1.7687, "step": 147500 }, { "epoch": 8.36, "learning_rate": 8.194452290831027e-06, "loss": 1.7511, "step": 148000 }, { "epoch": 8.39, "learning_rate": 8.053217332354105e-06, "loss": 1.7673, "step": 148500 }, { "epoch": 8.42, "learning_rate": 7.911982373877182e-06, "loss": 1.7693, "step": 149000 }, { "epoch": 8.45, "learning_rate": 7.77074741540026e-06, "loss": 1.7681, "step": 149500 }, { "epoch": 8.47, "learning_rate": 7.629512456923338e-06, "loss": 1.7464, "step": 150000 }, { "epoch": 8.5, "learning_rate": 7.4882774984464154e-06, "loss": 1.7448, "step": 150500 }, { "epoch": 8.53, "learning_rate": 7.347042539969494e-06, "loss": 1.7741, "step": 151000 }, { "epoch": 8.56, "learning_rate": 7.205807581492572e-06, "loss": 1.7667, "step": 151500 }, { "epoch": 8.59, "learning_rate": 7.0645726230156485e-06, "loss": 1.753, "step": 152000 }, { "epoch": 8.62, "learning_rate": 6.923337664538727e-06, "loss": 1.7807, "step": 152500 }, { "epoch": 8.64, "learning_rate": 6.782102706061805e-06, "loss": 1.7919, "step": 153000 }, { "epoch": 8.67, "learning_rate": 6.640867747584882e-06, "loss": 1.763, "step": 153500 }, { "epoch": 8.7, "learning_rate": 6.499632789107961e-06, "loss": 1.7789, "step": 154000 }, { "epoch": 8.73, "learning_rate": 6.358397830631039e-06, "loss": 1.7715, "step": 154500 }, { "epoch": 8.76, "learning_rate": 6.2171628721541155e-06, "loss": 1.761, "step": 155000 }, { "epoch": 8.78, "learning_rate": 6.075927913677194e-06, "loss": 1.797, "step": 155500 }, { "epoch": 8.81, "learning_rate": 5.934692955200272e-06, "loss": 1.7882, "step": 156000 }, { "epoch": 8.84, "learning_rate": 5.793457996723349e-06, "loss": 1.777, "step": 156500 }, { "epoch": 8.87, "learning_rate": 5.652223038246427e-06, "loss": 1.7599, "step": 157000 }, { "epoch": 8.9, "learning_rate": 5.510988079769505e-06, "loss": 1.7721, "step": 157500 }, { "epoch": 8.93, "learning_rate": 5.3697531212925825e-06, "loss": 1.7702, "step": 158000 }, { "epoch": 8.95, "learning_rate": 5.22851816281566e-06, "loss": 1.7694, "step": 158500 }, { "epoch": 8.98, "learning_rate": 5.087283204338738e-06, "loss": 1.7717, "step": 159000 }, { "epoch": 9.01, "learning_rate": 4.946048245861816e-06, "loss": 1.7488, "step": 159500 }, { "epoch": 9.04, "learning_rate": 4.804813287384894e-06, "loss": 1.6852, "step": 160000 }, { "epoch": 9.07, "learning_rate": 4.663578328907972e-06, "loss": 1.6784, "step": 160500 }, { "epoch": 9.1, "learning_rate": 4.5223433704310494e-06, "loss": 1.6848, "step": 161000 }, { "epoch": 9.12, "learning_rate": 4.381108411954127e-06, "loss": 1.6925, "step": 161500 }, { "epoch": 9.15, "learning_rate": 4.239873453477205e-06, "loss": 1.6813, "step": 162000 }, { "epoch": 9.18, "learning_rate": 4.0986384950002825e-06, "loss": 1.6906, "step": 162500 }, { "epoch": 9.21, "learning_rate": 3.95740353652336e-06, "loss": 1.6695, "step": 163000 }, { "epoch": 9.24, "learning_rate": 3.816168578046439e-06, "loss": 1.6827, "step": 163500 }, { "epoch": 9.27, "learning_rate": 3.6749336195695156e-06, "loss": 1.6993, "step": 164000 }, { "epoch": 9.29, "learning_rate": 3.5336986610925937e-06, "loss": 1.6758, "step": 164500 }, { "epoch": 9.32, "learning_rate": 3.3924637026156718e-06, "loss": 1.6987, "step": 165000 }, { "epoch": 9.35, "learning_rate": 3.251228744138749e-06, "loss": 1.6765, "step": 165500 }, { "epoch": 9.38, "learning_rate": 3.109993785661827e-06, "loss": 1.6728, "step": 166000 }, { "epoch": 9.41, "learning_rate": 2.968758827184905e-06, "loss": 1.6944, "step": 166500 }, { "epoch": 9.43, "learning_rate": 2.8275238687079825e-06, "loss": 1.6823, "step": 167000 }, { "epoch": 9.46, "learning_rate": 2.6862889102310607e-06, "loss": 1.6906, "step": 167500 }, { "epoch": 9.49, "learning_rate": 2.5450539517541383e-06, "loss": 1.7025, "step": 168000 }, { "epoch": 9.52, "learning_rate": 2.403818993277216e-06, "loss": 1.71, "step": 168500 }, { "epoch": 9.55, "learning_rate": 2.2625840348002937e-06, "loss": 1.6926, "step": 169000 }, { "epoch": 9.58, "learning_rate": 2.121349076323372e-06, "loss": 1.6908, "step": 169500 }, { "epoch": 9.6, "learning_rate": 1.9801141178464495e-06, "loss": 1.7204, "step": 170000 }, { "epoch": 9.63, "learning_rate": 1.8388791593695272e-06, "loss": 1.7023, "step": 170500 }, { "epoch": 9.66, "learning_rate": 1.697644200892605e-06, "loss": 1.6624, "step": 171000 }, { "epoch": 9.69, "learning_rate": 1.5564092424156828e-06, "loss": 1.6915, "step": 171500 }, { "epoch": 9.72, "learning_rate": 1.4151742839387605e-06, "loss": 1.7074, "step": 172000 }, { "epoch": 9.75, "learning_rate": 1.2739393254618384e-06, "loss": 1.6899, "step": 172500 }, { "epoch": 9.77, "learning_rate": 1.132704366984916e-06, "loss": 1.7185, "step": 173000 }, { "epoch": 9.8, "learning_rate": 9.91469408507994e-07, "loss": 1.6943, "step": 173500 }, { "epoch": 9.83, "learning_rate": 8.502344500310717e-07, "loss": 1.6682, "step": 174000 }, { "epoch": 9.86, "learning_rate": 7.089994915541495e-07, "loss": 1.6977, "step": 174500 }, { "epoch": 9.89, "learning_rate": 5.677645330772273e-07, "loss": 1.6837, "step": 175000 }, { "epoch": 9.91, "learning_rate": 4.265295746003051e-07, "loss": 1.694, "step": 175500 }, { "epoch": 9.94, "learning_rate": 2.852946161233829e-07, "loss": 1.7053, "step": 176000 }, { "epoch": 9.97, "learning_rate": 1.4405965764646066e-07, "loss": 1.7092, "step": 176500 }, { "epoch": 10.0, "learning_rate": 2.824699169538444e-09, "loss": 1.6876, "step": 177000 }, { "epoch": 10.0, "step": 177010, "total_flos": 7.956896853814272e+16, "train_loss": 2.263988757942984, "train_runtime": 19136.7963, "train_samples_per_second": 36.998, "train_steps_per_second": 9.25 } ], "max_steps": 177010, "num_train_epochs": 10, "total_flos": 7.956896853814272e+16, "trial_name": null, "trial_params": null }