diff --git "a/trainer_state.json" "b/trainer_state.json" new file mode 100644--- /dev/null +++ "b/trainer_state.json" @@ -0,0 +1,6352 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 11.162670109420306, + "eval_steps": 1000000, + "global_step": 527425, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.01, + "learning_rate": 5.000000000000001e-07, + "loss": 10.3109, + "step": 500 + }, + { + "epoch": 0.02, + "learning_rate": 1.0000000000000002e-06, + "loss": 10.1886, + "step": 1000 + }, + { + "epoch": 0.03, + "learning_rate": 1.5e-06, + "loss": 10.0674, + "step": 1500 + }, + { + "epoch": 0.04, + "learning_rate": 2.0000000000000003e-06, + "loss": 9.943, + "step": 2000 + }, + { + "epoch": 0.05, + "learning_rate": 2.5e-06, + "loss": 9.7902, + "step": 2500 + }, + { + "epoch": 0.06, + "learning_rate": 3e-06, + "loss": 9.6081, + "step": 3000 + }, + { + "epoch": 0.07, + "learning_rate": 3.5e-06, + "loss": 9.3983, + "step": 3500 + }, + { + "epoch": 0.08, + "learning_rate": 4.000000000000001e-06, + "loss": 9.1676, + "step": 4000 + }, + { + "epoch": 0.1, + "learning_rate": 4.5e-06, + "loss": 8.92, + "step": 4500 + }, + { + "epoch": 0.11, + "learning_rate": 5e-06, + "loss": 8.6684, + "step": 5000 + }, + { + "epoch": 0.12, + "learning_rate": 5.500000000000001e-06, + "loss": 8.4167, + "step": 5500 + }, + { + "epoch": 0.13, + "learning_rate": 6e-06, + "loss": 8.1706, + "step": 6000 + }, + { + "epoch": 0.14, + "learning_rate": 6.5000000000000004e-06, + "loss": 7.9414, + "step": 6500 + }, + { + "epoch": 0.15, + "learning_rate": 7e-06, + "loss": 7.7315, + "step": 7000 + }, + { + "epoch": 0.16, + "learning_rate": 7.500000000000001e-06, + "loss": 7.5484, + "step": 7500 + }, + { + "epoch": 0.17, + "learning_rate": 8.000000000000001e-06, + "loss": 7.3984, + "step": 8000 + }, + { + "epoch": 0.18, + "learning_rate": 8.5e-06, + "loss": 7.2891, + "step": 8500 + }, + { + "epoch": 0.19, + "learning_rate": 9e-06, + "loss": 7.2118, + "step": 9000 + }, + { + "epoch": 0.2, + "learning_rate": 9.5e-06, + "loss": 7.1472, + "step": 9500 + }, + { + "epoch": 0.21, + "learning_rate": 1e-05, + "loss": 7.1019, + "step": 10000 + }, + { + "epoch": 0.22, + "learning_rate": 9.998939532121573e-06, + "loss": 7.0535, + "step": 10500 + }, + { + "epoch": 0.23, + "learning_rate": 9.997879064243145e-06, + "loss": 7.0135, + "step": 11000 + }, + { + "epoch": 0.24, + "learning_rate": 9.996818596364717e-06, + "loss": 6.9804, + "step": 11500 + }, + { + "epoch": 0.25, + "learning_rate": 9.995758128486289e-06, + "loss": 6.9474, + "step": 12000 + }, + { + "epoch": 0.26, + "learning_rate": 9.994697660607861e-06, + "loss": 6.9246, + "step": 12500 + }, + { + "epoch": 0.28, + "learning_rate": 9.993637192729433e-06, + "loss": 6.8917, + "step": 13000 + }, + { + "epoch": 0.29, + "learning_rate": 9.992576724851005e-06, + "loss": 6.8755, + "step": 13500 + }, + { + "epoch": 0.3, + "learning_rate": 9.991516256972577e-06, + "loss": 6.8562, + "step": 14000 + }, + { + "epoch": 0.31, + "learning_rate": 9.99045578909415e-06, + "loss": 6.8341, + "step": 14500 + }, + { + "epoch": 0.32, + "learning_rate": 9.989395321215721e-06, + "loss": 6.8142, + "step": 15000 + }, + { + "epoch": 0.33, + "learning_rate": 9.988334853337293e-06, + "loss": 6.7961, + "step": 15500 + }, + { + "epoch": 0.34, + "learning_rate": 9.987274385458866e-06, + "loss": 6.7781, + "step": 16000 + }, + { + "epoch": 0.35, + "learning_rate": 9.986213917580438e-06, + "loss": 6.7628, + "step": 16500 + }, + { + "epoch": 0.36, + "learning_rate": 9.98515344970201e-06, + "loss": 6.7514, + "step": 17000 + }, + { + "epoch": 0.37, + "learning_rate": 9.984092981823582e-06, + "loss": 6.7342, + "step": 17500 + }, + { + "epoch": 0.38, + "learning_rate": 9.983032513945154e-06, + "loss": 6.7205, + "step": 18000 + }, + { + "epoch": 0.39, + "learning_rate": 9.981972046066726e-06, + "loss": 6.7145, + "step": 18500 + }, + { + "epoch": 0.4, + "learning_rate": 9.980911578188298e-06, + "loss": 6.6977, + "step": 19000 + }, + { + "epoch": 0.41, + "learning_rate": 9.97985111030987e-06, + "loss": 6.6897, + "step": 19500 + }, + { + "epoch": 0.42, + "learning_rate": 9.978790642431442e-06, + "loss": 6.6768, + "step": 20000 + }, + { + "epoch": 0.43, + "learning_rate": 9.977730174553012e-06, + "loss": 6.6635, + "step": 20500 + }, + { + "epoch": 0.44, + "learning_rate": 9.976669706674586e-06, + "loss": 6.6589, + "step": 21000 + }, + { + "epoch": 0.46, + "learning_rate": 9.975609238796158e-06, + "loss": 6.6457, + "step": 21500 + }, + { + "epoch": 0.47, + "learning_rate": 9.97454877091773e-06, + "loss": 6.6412, + "step": 22000 + }, + { + "epoch": 0.48, + "learning_rate": 9.973488303039302e-06, + "loss": 6.6333, + "step": 22500 + }, + { + "epoch": 0.49, + "learning_rate": 9.972427835160874e-06, + "loss": 6.6232, + "step": 23000 + }, + { + "epoch": 0.5, + "learning_rate": 9.971367367282446e-06, + "loss": 6.6168, + "step": 23500 + }, + { + "epoch": 0.51, + "learning_rate": 9.970306899404017e-06, + "loss": 6.6082, + "step": 24000 + }, + { + "epoch": 0.52, + "learning_rate": 9.96924643152559e-06, + "loss": 6.5968, + "step": 24500 + }, + { + "epoch": 0.53, + "learning_rate": 9.968185963647163e-06, + "loss": 6.5922, + "step": 25000 + }, + { + "epoch": 0.54, + "learning_rate": 9.967125495768733e-06, + "loss": 6.5922, + "step": 25500 + }, + { + "epoch": 0.55, + "learning_rate": 9.966065027890307e-06, + "loss": 6.5821, + "step": 26000 + }, + { + "epoch": 0.56, + "learning_rate": 9.965004560011879e-06, + "loss": 6.5706, + "step": 26500 + }, + { + "epoch": 0.57, + "learning_rate": 9.963944092133449e-06, + "loss": 6.5654, + "step": 27000 + }, + { + "epoch": 0.58, + "learning_rate": 9.962883624255023e-06, + "loss": 6.5614, + "step": 27500 + }, + { + "epoch": 0.59, + "learning_rate": 9.961823156376595e-06, + "loss": 6.5542, + "step": 28000 + }, + { + "epoch": 0.6, + "learning_rate": 9.960762688498167e-06, + "loss": 6.5505, + "step": 28500 + }, + { + "epoch": 0.61, + "learning_rate": 9.959702220619737e-06, + "loss": 6.544, + "step": 29000 + }, + { + "epoch": 0.62, + "learning_rate": 9.958641752741311e-06, + "loss": 6.5408, + "step": 29500 + }, + { + "epoch": 0.63, + "learning_rate": 9.957581284862883e-06, + "loss": 6.5316, + "step": 30000 + }, + { + "epoch": 0.65, + "learning_rate": 9.956520816984453e-06, + "loss": 6.524, + "step": 30500 + }, + { + "epoch": 0.66, + "learning_rate": 9.955460349106027e-06, + "loss": 6.5252, + "step": 31000 + }, + { + "epoch": 0.67, + "learning_rate": 9.9543998812276e-06, + "loss": 6.5142, + "step": 31500 + }, + { + "epoch": 0.68, + "learning_rate": 9.95333941334917e-06, + "loss": 6.5119, + "step": 32000 + }, + { + "epoch": 0.69, + "learning_rate": 9.952278945470742e-06, + "loss": 6.5057, + "step": 32500 + }, + { + "epoch": 0.7, + "learning_rate": 9.951218477592315e-06, + "loss": 6.4985, + "step": 33000 + }, + { + "epoch": 0.71, + "learning_rate": 9.950158009713886e-06, + "loss": 6.4913, + "step": 33500 + }, + { + "epoch": 0.72, + "learning_rate": 9.949097541835458e-06, + "loss": 6.4883, + "step": 34000 + }, + { + "epoch": 0.73, + "learning_rate": 9.948037073957032e-06, + "loss": 6.4872, + "step": 34500 + }, + { + "epoch": 0.74, + "learning_rate": 9.946976606078602e-06, + "loss": 6.4839, + "step": 35000 + }, + { + "epoch": 0.75, + "learning_rate": 9.945916138200174e-06, + "loss": 6.4753, + "step": 35500 + }, + { + "epoch": 0.76, + "learning_rate": 9.944855670321746e-06, + "loss": 6.4715, + "step": 36000 + }, + { + "epoch": 0.77, + "learning_rate": 9.94379520244332e-06, + "loss": 6.4699, + "step": 36500 + }, + { + "epoch": 0.78, + "learning_rate": 9.94273473456489e-06, + "loss": 6.4618, + "step": 37000 + }, + { + "epoch": 0.79, + "learning_rate": 9.941674266686462e-06, + "loss": 6.4564, + "step": 37500 + }, + { + "epoch": 0.8, + "learning_rate": 9.940613798808036e-06, + "loss": 6.4528, + "step": 38000 + }, + { + "epoch": 0.81, + "learning_rate": 9.939553330929606e-06, + "loss": 6.4518, + "step": 38500 + }, + { + "epoch": 0.83, + "learning_rate": 9.938492863051178e-06, + "loss": 6.4466, + "step": 39000 + }, + { + "epoch": 0.84, + "learning_rate": 9.937432395172752e-06, + "loss": 6.4427, + "step": 39500 + }, + { + "epoch": 0.85, + "learning_rate": 9.936371927294323e-06, + "loss": 6.4406, + "step": 40000 + }, + { + "epoch": 0.86, + "learning_rate": 9.935311459415895e-06, + "loss": 6.4353, + "step": 40500 + }, + { + "epoch": 0.87, + "learning_rate": 9.934250991537467e-06, + "loss": 6.4294, + "step": 41000 + }, + { + "epoch": 0.88, + "learning_rate": 9.933190523659039e-06, + "loss": 6.4352, + "step": 41500 + }, + { + "epoch": 0.89, + "learning_rate": 9.93213005578061e-06, + "loss": 6.4225, + "step": 42000 + }, + { + "epoch": 0.9, + "learning_rate": 9.931069587902183e-06, + "loss": 6.423, + "step": 42500 + }, + { + "epoch": 0.91, + "learning_rate": 9.930009120023757e-06, + "loss": 6.4175, + "step": 43000 + }, + { + "epoch": 0.92, + "learning_rate": 9.928948652145327e-06, + "loss": 6.4179, + "step": 43500 + }, + { + "epoch": 0.93, + "learning_rate": 9.927888184266899e-06, + "loss": 6.414, + "step": 44000 + }, + { + "epoch": 0.94, + "learning_rate": 9.926827716388471e-06, + "loss": 6.4103, + "step": 44500 + }, + { + "epoch": 0.95, + "learning_rate": 9.925767248510043e-06, + "loss": 6.4074, + "step": 45000 + }, + { + "epoch": 0.96, + "learning_rate": 9.924706780631615e-06, + "loss": 6.4042, + "step": 45500 + }, + { + "epoch": 0.97, + "learning_rate": 9.923646312753187e-06, + "loss": 6.3996, + "step": 46000 + }, + { + "epoch": 0.98, + "learning_rate": 9.92258584487476e-06, + "loss": 6.3965, + "step": 46500 + }, + { + "epoch": 0.99, + "learning_rate": 9.921525376996331e-06, + "loss": 6.3913, + "step": 47000 + }, + { + "epoch": 1.01, + "learning_rate": 9.920464909117903e-06, + "loss": 6.3885, + "step": 47500 + }, + { + "epoch": 1.02, + "learning_rate": 9.919404441239475e-06, + "loss": 6.3853, + "step": 48000 + }, + { + "epoch": 1.03, + "learning_rate": 9.918343973361048e-06, + "loss": 6.3805, + "step": 48500 + }, + { + "epoch": 1.04, + "learning_rate": 9.91728350548262e-06, + "loss": 6.3824, + "step": 49000 + }, + { + "epoch": 1.05, + "learning_rate": 9.916223037604192e-06, + "loss": 6.3738, + "step": 49500 + }, + { + "epoch": 1.06, + "learning_rate": 9.915162569725764e-06, + "loss": 6.3752, + "step": 50000 + }, + { + "epoch": 1.07, + "learning_rate": 9.914102101847336e-06, + "loss": 6.371, + "step": 50500 + }, + { + "epoch": 1.08, + "learning_rate": 9.913041633968908e-06, + "loss": 6.3703, + "step": 51000 + }, + { + "epoch": 1.09, + "learning_rate": 9.91198116609048e-06, + "loss": 6.3673, + "step": 51500 + }, + { + "epoch": 1.1, + "learning_rate": 9.910920698212052e-06, + "loss": 6.3654, + "step": 52000 + }, + { + "epoch": 1.11, + "learning_rate": 9.909860230333624e-06, + "loss": 6.3589, + "step": 52500 + }, + { + "epoch": 1.12, + "learning_rate": 9.908799762455196e-06, + "loss": 6.3579, + "step": 53000 + }, + { + "epoch": 1.13, + "learning_rate": 9.907739294576768e-06, + "loss": 6.3568, + "step": 53500 + }, + { + "epoch": 1.14, + "learning_rate": 9.90667882669834e-06, + "loss": 6.3551, + "step": 54000 + }, + { + "epoch": 1.15, + "learning_rate": 9.905618358819912e-06, + "loss": 6.3491, + "step": 54500 + }, + { + "epoch": 1.16, + "learning_rate": 9.904557890941484e-06, + "loss": 6.3458, + "step": 55000 + }, + { + "epoch": 1.17, + "learning_rate": 9.903497423063056e-06, + "loss": 6.3463, + "step": 55500 + }, + { + "epoch": 1.19, + "learning_rate": 9.902436955184628e-06, + "loss": 6.3419, + "step": 56000 + }, + { + "epoch": 1.2, + "learning_rate": 9.9013764873062e-06, + "loss": 6.3388, + "step": 56500 + }, + { + "epoch": 1.21, + "learning_rate": 9.900316019427772e-06, + "loss": 6.3372, + "step": 57000 + }, + { + "epoch": 1.22, + "learning_rate": 9.899255551549345e-06, + "loss": 6.3328, + "step": 57500 + }, + { + "epoch": 1.23, + "learning_rate": 9.898195083670917e-06, + "loss": 6.3311, + "step": 58000 + }, + { + "epoch": 1.24, + "learning_rate": 9.897134615792489e-06, + "loss": 6.3263, + "step": 58500 + }, + { + "epoch": 1.25, + "learning_rate": 9.89607414791406e-06, + "loss": 6.3276, + "step": 59000 + }, + { + "epoch": 1.26, + "learning_rate": 9.895013680035633e-06, + "loss": 6.3275, + "step": 59500 + }, + { + "epoch": 1.27, + "learning_rate": 9.893953212157205e-06, + "loss": 6.3239, + "step": 60000 + }, + { + "epoch": 1.28, + "learning_rate": 9.892892744278777e-06, + "loss": 6.3231, + "step": 60500 + }, + { + "epoch": 1.29, + "learning_rate": 9.891832276400349e-06, + "loss": 6.3238, + "step": 61000 + }, + { + "epoch": 1.3, + "learning_rate": 9.890771808521921e-06, + "loss": 6.3157, + "step": 61500 + }, + { + "epoch": 1.31, + "learning_rate": 9.889711340643493e-06, + "loss": 6.319, + "step": 62000 + }, + { + "epoch": 1.32, + "learning_rate": 9.888650872765065e-06, + "loss": 6.3093, + "step": 62500 + }, + { + "epoch": 1.33, + "learning_rate": 9.887590404886637e-06, + "loss": 6.3148, + "step": 63000 + }, + { + "epoch": 1.34, + "learning_rate": 9.88652993700821e-06, + "loss": 6.3089, + "step": 63500 + }, + { + "epoch": 1.35, + "learning_rate": 9.88546946912978e-06, + "loss": 6.3053, + "step": 64000 + }, + { + "epoch": 1.37, + "learning_rate": 9.884409001251353e-06, + "loss": 6.3072, + "step": 64500 + }, + { + "epoch": 1.38, + "learning_rate": 9.883348533372925e-06, + "loss": 6.2999, + "step": 65000 + }, + { + "epoch": 1.39, + "learning_rate": 9.882288065494497e-06, + "loss": 6.3008, + "step": 65500 + }, + { + "epoch": 1.4, + "learning_rate": 9.88122759761607e-06, + "loss": 6.3051, + "step": 66000 + }, + { + "epoch": 1.41, + "learning_rate": 9.880167129737642e-06, + "loss": 6.2997, + "step": 66500 + }, + { + "epoch": 1.42, + "learning_rate": 9.879106661859214e-06, + "loss": 6.2996, + "step": 67000 + }, + { + "epoch": 1.43, + "learning_rate": 9.878046193980784e-06, + "loss": 6.293, + "step": 67500 + }, + { + "epoch": 1.44, + "learning_rate": 9.876985726102358e-06, + "loss": 6.2996, + "step": 68000 + }, + { + "epoch": 1.45, + "learning_rate": 9.87592525822393e-06, + "loss": 6.2954, + "step": 68500 + }, + { + "epoch": 1.46, + "learning_rate": 9.8748647903455e-06, + "loss": 6.2912, + "step": 69000 + }, + { + "epoch": 1.47, + "learning_rate": 9.873804322467074e-06, + "loss": 6.2855, + "step": 69500 + }, + { + "epoch": 1.48, + "learning_rate": 9.872743854588646e-06, + "loss": 6.2877, + "step": 70000 + }, + { + "epoch": 1.49, + "learning_rate": 9.871683386710216e-06, + "loss": 6.2817, + "step": 70500 + }, + { + "epoch": 1.5, + "learning_rate": 9.87062291883179e-06, + "loss": 6.28, + "step": 71000 + }, + { + "epoch": 1.51, + "learning_rate": 9.869562450953362e-06, + "loss": 6.2794, + "step": 71500 + }, + { + "epoch": 1.52, + "learning_rate": 9.868501983074934e-06, + "loss": 6.2766, + "step": 72000 + }, + { + "epoch": 1.53, + "learning_rate": 9.867441515196505e-06, + "loss": 6.2769, + "step": 72500 + }, + { + "epoch": 1.55, + "learning_rate": 9.866381047318078e-06, + "loss": 6.2815, + "step": 73000 + }, + { + "epoch": 1.56, + "learning_rate": 9.86532057943965e-06, + "loss": 6.2805, + "step": 73500 + }, + { + "epoch": 1.57, + "learning_rate": 9.86426011156122e-06, + "loss": 6.2726, + "step": 74000 + }, + { + "epoch": 1.58, + "learning_rate": 9.863199643682794e-06, + "loss": 6.274, + "step": 74500 + }, + { + "epoch": 1.59, + "learning_rate": 9.862139175804367e-06, + "loss": 6.2712, + "step": 75000 + }, + { + "epoch": 1.6, + "learning_rate": 9.861078707925937e-06, + "loss": 6.2738, + "step": 75500 + }, + { + "epoch": 1.61, + "learning_rate": 9.860018240047509e-06, + "loss": 6.2694, + "step": 76000 + }, + { + "epoch": 1.62, + "learning_rate": 9.858957772169083e-06, + "loss": 6.2672, + "step": 76500 + }, + { + "epoch": 1.63, + "learning_rate": 9.857897304290653e-06, + "loss": 6.2641, + "step": 77000 + }, + { + "epoch": 1.64, + "learning_rate": 9.856836836412225e-06, + "loss": 6.2667, + "step": 77500 + }, + { + "epoch": 1.65, + "learning_rate": 9.855776368533799e-06, + "loss": 6.2637, + "step": 78000 + }, + { + "epoch": 1.66, + "learning_rate": 9.85471590065537e-06, + "loss": 6.2598, + "step": 78500 + }, + { + "epoch": 1.67, + "learning_rate": 9.853655432776941e-06, + "loss": 6.2604, + "step": 79000 + }, + { + "epoch": 1.68, + "learning_rate": 9.852594964898515e-06, + "loss": 6.2604, + "step": 79500 + }, + { + "epoch": 1.69, + "learning_rate": 9.851534497020087e-06, + "loss": 6.2561, + "step": 80000 + }, + { + "epoch": 1.7, + "learning_rate": 9.850474029141657e-06, + "loss": 6.2531, + "step": 80500 + }, + { + "epoch": 1.71, + "learning_rate": 9.84941356126323e-06, + "loss": 6.2594, + "step": 81000 + }, + { + "epoch": 1.72, + "learning_rate": 9.848353093384803e-06, + "loss": 6.2522, + "step": 81500 + }, + { + "epoch": 1.74, + "learning_rate": 9.847292625506374e-06, + "loss": 6.2518, + "step": 82000 + }, + { + "epoch": 1.75, + "learning_rate": 9.846232157627946e-06, + "loss": 6.2498, + "step": 82500 + }, + { + "epoch": 1.76, + "learning_rate": 9.84517168974952e-06, + "loss": 6.2482, + "step": 83000 + }, + { + "epoch": 1.77, + "learning_rate": 9.84411122187109e-06, + "loss": 6.2519, + "step": 83500 + }, + { + "epoch": 1.78, + "learning_rate": 9.843050753992662e-06, + "loss": 6.2451, + "step": 84000 + }, + { + "epoch": 1.79, + "learning_rate": 9.841990286114234e-06, + "loss": 6.244, + "step": 84500 + }, + { + "epoch": 1.8, + "learning_rate": 9.840929818235806e-06, + "loss": 6.2417, + "step": 85000 + }, + { + "epoch": 1.81, + "learning_rate": 9.839869350357378e-06, + "loss": 6.2415, + "step": 85500 + }, + { + "epoch": 1.82, + "learning_rate": 9.83880888247895e-06, + "loss": 6.244, + "step": 86000 + }, + { + "epoch": 1.83, + "learning_rate": 9.837748414600524e-06, + "loss": 6.2417, + "step": 86500 + }, + { + "epoch": 1.84, + "learning_rate": 9.836687946722094e-06, + "loss": 6.2389, + "step": 87000 + }, + { + "epoch": 1.85, + "learning_rate": 9.835627478843666e-06, + "loss": 6.2405, + "step": 87500 + }, + { + "epoch": 1.86, + "learning_rate": 9.834567010965238e-06, + "loss": 6.2414, + "step": 88000 + }, + { + "epoch": 1.87, + "learning_rate": 9.83350654308681e-06, + "loss": 6.2382, + "step": 88500 + }, + { + "epoch": 1.88, + "learning_rate": 9.832446075208382e-06, + "loss": 6.2392, + "step": 89000 + }, + { + "epoch": 1.89, + "learning_rate": 9.831385607329954e-06, + "loss": 6.2284, + "step": 89500 + }, + { + "epoch": 1.9, + "learning_rate": 9.830325139451527e-06, + "loss": 6.2364, + "step": 90000 + }, + { + "epoch": 1.92, + "learning_rate": 9.829264671573099e-06, + "loss": 6.2323, + "step": 90500 + }, + { + "epoch": 1.93, + "learning_rate": 9.82820420369467e-06, + "loss": 6.2289, + "step": 91000 + }, + { + "epoch": 1.94, + "learning_rate": 9.827143735816243e-06, + "loss": 6.229, + "step": 91500 + }, + { + "epoch": 1.95, + "learning_rate": 9.826083267937815e-06, + "loss": 6.2273, + "step": 92000 + }, + { + "epoch": 1.96, + "learning_rate": 9.825022800059387e-06, + "loss": 6.2305, + "step": 92500 + }, + { + "epoch": 1.97, + "learning_rate": 9.823962332180959e-06, + "loss": 6.2271, + "step": 93000 + }, + { + "epoch": 1.98, + "learning_rate": 9.822901864302531e-06, + "loss": 6.2228, + "step": 93500 + }, + { + "epoch": 1.99, + "learning_rate": 9.821841396424103e-06, + "loss": 6.223, + "step": 94000 + }, + { + "epoch": 2.0, + "learning_rate": 9.820780928545675e-06, + "loss": 6.226, + "step": 94500 + }, + { + "epoch": 2.01, + "learning_rate": 9.819720460667247e-06, + "loss": 6.2238, + "step": 95000 + }, + { + "epoch": 2.02, + "learning_rate": 9.81865999278882e-06, + "loss": 6.2203, + "step": 95500 + }, + { + "epoch": 2.03, + "learning_rate": 9.817599524910391e-06, + "loss": 6.2188, + "step": 96000 + }, + { + "epoch": 2.04, + "learning_rate": 9.816539057031963e-06, + "loss": 6.222, + "step": 96500 + }, + { + "epoch": 2.05, + "learning_rate": 9.815478589153535e-06, + "loss": 6.2142, + "step": 97000 + }, + { + "epoch": 2.06, + "learning_rate": 9.814418121275107e-06, + "loss": 6.2172, + "step": 97500 + }, + { + "epoch": 2.07, + "learning_rate": 9.81335765339668e-06, + "loss": 6.2173, + "step": 98000 + }, + { + "epoch": 2.08, + "learning_rate": 9.812297185518252e-06, + "loss": 6.2145, + "step": 98500 + }, + { + "epoch": 2.1, + "learning_rate": 9.811236717639824e-06, + "loss": 6.2189, + "step": 99000 + }, + { + "epoch": 2.11, + "learning_rate": 9.810176249761396e-06, + "loss": 6.2149, + "step": 99500 + }, + { + "epoch": 2.12, + "learning_rate": 9.809115781882968e-06, + "loss": 6.2143, + "step": 100000 + }, + { + "epoch": 2.13, + "learning_rate": 9.80805531400454e-06, + "loss": 6.2135, + "step": 100500 + }, + { + "epoch": 2.14, + "learning_rate": 9.806994846126112e-06, + "loss": 6.212, + "step": 101000 + }, + { + "epoch": 2.15, + "learning_rate": 9.805934378247684e-06, + "loss": 6.21, + "step": 101500 + }, + { + "epoch": 2.16, + "learning_rate": 9.804873910369256e-06, + "loss": 6.2104, + "step": 102000 + }, + { + "epoch": 2.17, + "learning_rate": 9.803813442490828e-06, + "loss": 6.2088, + "step": 102500 + }, + { + "epoch": 2.18, + "learning_rate": 9.8027529746124e-06, + "loss": 6.2063, + "step": 103000 + }, + { + "epoch": 2.19, + "learning_rate": 9.801692506733972e-06, + "loss": 6.2057, + "step": 103500 + }, + { + "epoch": 2.2, + "learning_rate": 9.800632038855544e-06, + "loss": 6.2069, + "step": 104000 + }, + { + "epoch": 2.21, + "learning_rate": 9.799571570977116e-06, + "loss": 6.2071, + "step": 104500 + }, + { + "epoch": 2.22, + "learning_rate": 9.798511103098688e-06, + "loss": 6.2082, + "step": 105000 + }, + { + "epoch": 2.23, + "learning_rate": 9.79745063522026e-06, + "loss": 6.2063, + "step": 105500 + }, + { + "epoch": 2.24, + "learning_rate": 9.796390167341832e-06, + "loss": 6.2028, + "step": 106000 + }, + { + "epoch": 2.25, + "learning_rate": 9.795329699463404e-06, + "loss": 6.1995, + "step": 106500 + }, + { + "epoch": 2.26, + "learning_rate": 9.794269231584976e-06, + "loss": 6.1986, + "step": 107000 + }, + { + "epoch": 2.28, + "learning_rate": 9.793208763706547e-06, + "loss": 6.2024, + "step": 107500 + }, + { + "epoch": 2.29, + "learning_rate": 9.79214829582812e-06, + "loss": 6.2027, + "step": 108000 + }, + { + "epoch": 2.3, + "learning_rate": 9.791087827949693e-06, + "loss": 6.201, + "step": 108500 + }, + { + "epoch": 2.31, + "learning_rate": 9.790027360071265e-06, + "loss": 6.1984, + "step": 109000 + }, + { + "epoch": 2.32, + "learning_rate": 9.788966892192837e-06, + "loss": 6.1953, + "step": 109500 + }, + { + "epoch": 2.33, + "learning_rate": 9.787906424314409e-06, + "loss": 6.1976, + "step": 110000 + }, + { + "epoch": 2.34, + "learning_rate": 9.786845956435981e-06, + "loss": 6.2026, + "step": 110500 + }, + { + "epoch": 2.35, + "learning_rate": 9.785785488557551e-06, + "loss": 6.198, + "step": 111000 + }, + { + "epoch": 2.36, + "learning_rate": 9.784725020679125e-06, + "loss": 6.1939, + "step": 111500 + }, + { + "epoch": 2.37, + "learning_rate": 9.783664552800697e-06, + "loss": 6.1911, + "step": 112000 + }, + { + "epoch": 2.38, + "learning_rate": 9.782604084922267e-06, + "loss": 6.1924, + "step": 112500 + }, + { + "epoch": 2.39, + "learning_rate": 9.781543617043841e-06, + "loss": 6.1927, + "step": 113000 + }, + { + "epoch": 2.4, + "learning_rate": 9.780483149165413e-06, + "loss": 6.1915, + "step": 113500 + }, + { + "epoch": 2.41, + "learning_rate": 9.779422681286984e-06, + "loss": 6.1913, + "step": 114000 + }, + { + "epoch": 2.42, + "learning_rate": 9.778362213408557e-06, + "loss": 6.1912, + "step": 114500 + }, + { + "epoch": 2.43, + "learning_rate": 9.77730174553013e-06, + "loss": 6.1873, + "step": 115000 + }, + { + "epoch": 2.44, + "learning_rate": 9.776241277651701e-06, + "loss": 6.1892, + "step": 115500 + }, + { + "epoch": 2.46, + "learning_rate": 9.775180809773272e-06, + "loss": 6.189, + "step": 116000 + }, + { + "epoch": 2.47, + "learning_rate": 9.774120341894846e-06, + "loss": 6.1855, + "step": 116500 + }, + { + "epoch": 2.48, + "learning_rate": 9.773059874016418e-06, + "loss": 6.1875, + "step": 117000 + }, + { + "epoch": 2.49, + "learning_rate": 9.771999406137988e-06, + "loss": 6.1858, + "step": 117500 + }, + { + "epoch": 2.5, + "learning_rate": 9.770938938259562e-06, + "loss": 6.1885, + "step": 118000 + }, + { + "epoch": 2.51, + "learning_rate": 9.769878470381134e-06, + "loss": 6.1832, + "step": 118500 + }, + { + "epoch": 2.52, + "learning_rate": 9.768818002502704e-06, + "loss": 6.1777, + "step": 119000 + }, + { + "epoch": 2.53, + "learning_rate": 9.767757534624276e-06, + "loss": 6.1805, + "step": 119500 + }, + { + "epoch": 2.54, + "learning_rate": 9.76669706674585e-06, + "loss": 6.1814, + "step": 120000 + }, + { + "epoch": 2.55, + "learning_rate": 9.76563659886742e-06, + "loss": 6.1796, + "step": 120500 + }, + { + "epoch": 2.56, + "learning_rate": 9.764576130988992e-06, + "loss": 6.1805, + "step": 121000 + }, + { + "epoch": 2.57, + "learning_rate": 9.763515663110566e-06, + "loss": 6.1828, + "step": 121500 + }, + { + "epoch": 2.58, + "learning_rate": 9.762455195232136e-06, + "loss": 6.1781, + "step": 122000 + }, + { + "epoch": 2.59, + "learning_rate": 9.761394727353709e-06, + "loss": 6.1794, + "step": 122500 + }, + { + "epoch": 2.6, + "learning_rate": 9.760334259475282e-06, + "loss": 6.1756, + "step": 123000 + }, + { + "epoch": 2.61, + "learning_rate": 9.759273791596854e-06, + "loss": 6.1772, + "step": 123500 + }, + { + "epoch": 2.62, + "learning_rate": 9.758213323718425e-06, + "loss": 6.1746, + "step": 124000 + }, + { + "epoch": 2.63, + "learning_rate": 9.757152855839997e-06, + "loss": 6.1777, + "step": 124500 + }, + { + "epoch": 2.65, + "learning_rate": 9.75609238796157e-06, + "loss": 6.1711, + "step": 125000 + }, + { + "epoch": 2.66, + "learning_rate": 9.755031920083141e-06, + "loss": 6.171, + "step": 125500 + }, + { + "epoch": 2.67, + "learning_rate": 9.753971452204713e-06, + "loss": 6.1734, + "step": 126000 + }, + { + "epoch": 2.68, + "learning_rate": 9.752910984326287e-06, + "loss": 6.1725, + "step": 126500 + }, + { + "epoch": 2.69, + "learning_rate": 9.751850516447857e-06, + "loss": 6.1771, + "step": 127000 + }, + { + "epoch": 2.7, + "learning_rate": 9.750790048569429e-06, + "loss": 6.1717, + "step": 127500 + }, + { + "epoch": 2.71, + "learning_rate": 9.749729580691001e-06, + "loss": 6.1715, + "step": 128000 + }, + { + "epoch": 2.72, + "learning_rate": 9.748669112812573e-06, + "loss": 6.1701, + "step": 128500 + }, + { + "epoch": 2.73, + "learning_rate": 9.747608644934145e-06, + "loss": 6.1721, + "step": 129000 + }, + { + "epoch": 2.74, + "learning_rate": 9.746548177055717e-06, + "loss": 6.1693, + "step": 129500 + }, + { + "epoch": 2.75, + "learning_rate": 9.745487709177291e-06, + "loss": 6.169, + "step": 130000 + }, + { + "epoch": 2.76, + "learning_rate": 9.744427241298861e-06, + "loss": 6.1677, + "step": 130500 + }, + { + "epoch": 2.77, + "learning_rate": 9.743366773420434e-06, + "loss": 6.167, + "step": 131000 + }, + { + "epoch": 2.78, + "learning_rate": 9.742306305542006e-06, + "loss": 6.1649, + "step": 131500 + }, + { + "epoch": 2.79, + "learning_rate": 9.741245837663578e-06, + "loss": 6.1692, + "step": 132000 + }, + { + "epoch": 2.8, + "learning_rate": 9.74018536978515e-06, + "loss": 6.1672, + "step": 132500 + }, + { + "epoch": 2.81, + "learning_rate": 9.739124901906722e-06, + "loss": 6.1668, + "step": 133000 + }, + { + "epoch": 2.83, + "learning_rate": 9.738064434028294e-06, + "loss": 6.1674, + "step": 133500 + }, + { + "epoch": 2.84, + "learning_rate": 9.737003966149866e-06, + "loss": 6.1661, + "step": 134000 + }, + { + "epoch": 2.85, + "learning_rate": 9.735943498271438e-06, + "loss": 6.1641, + "step": 134500 + }, + { + "epoch": 2.86, + "learning_rate": 9.73488303039301e-06, + "loss": 6.1631, + "step": 135000 + }, + { + "epoch": 2.87, + "learning_rate": 9.733822562514582e-06, + "loss": 6.162, + "step": 135500 + }, + { + "epoch": 2.88, + "learning_rate": 9.732762094636154e-06, + "loss": 6.1612, + "step": 136000 + }, + { + "epoch": 2.89, + "learning_rate": 9.731701626757726e-06, + "loss": 6.1594, + "step": 136500 + }, + { + "epoch": 2.9, + "learning_rate": 9.730641158879298e-06, + "loss": 6.1585, + "step": 137000 + }, + { + "epoch": 2.91, + "learning_rate": 9.72958069100087e-06, + "loss": 6.1588, + "step": 137500 + }, + { + "epoch": 2.92, + "learning_rate": 9.728520223122442e-06, + "loss": 6.1591, + "step": 138000 + }, + { + "epoch": 2.93, + "learning_rate": 9.727459755244014e-06, + "loss": 6.1653, + "step": 138500 + }, + { + "epoch": 2.94, + "learning_rate": 9.726399287365586e-06, + "loss": 6.1589, + "step": 139000 + }, + { + "epoch": 2.95, + "learning_rate": 9.725338819487158e-06, + "loss": 6.1573, + "step": 139500 + }, + { + "epoch": 2.96, + "learning_rate": 9.72427835160873e-06, + "loss": 6.1585, + "step": 140000 + }, + { + "epoch": 2.97, + "learning_rate": 9.723217883730303e-06, + "loss": 6.1548, + "step": 140500 + }, + { + "epoch": 2.98, + "learning_rate": 9.722157415851875e-06, + "loss": 6.1572, + "step": 141000 + }, + { + "epoch": 2.99, + "learning_rate": 9.721096947973447e-06, + "loss": 6.1565, + "step": 141500 + }, + { + "epoch": 3.01, + "learning_rate": 9.720036480095019e-06, + "loss": 6.1538, + "step": 142000 + }, + { + "epoch": 3.02, + "learning_rate": 9.71897601221659e-06, + "loss": 6.1527, + "step": 142500 + }, + { + "epoch": 3.03, + "learning_rate": 9.717915544338163e-06, + "loss": 6.1537, + "step": 143000 + }, + { + "epoch": 3.04, + "learning_rate": 9.716855076459735e-06, + "loss": 6.1545, + "step": 143500 + }, + { + "epoch": 3.05, + "learning_rate": 9.715794608581307e-06, + "loss": 6.1535, + "step": 144000 + }, + { + "epoch": 3.06, + "learning_rate": 9.714734140702879e-06, + "loss": 6.1526, + "step": 144500 + }, + { + "epoch": 3.07, + "learning_rate": 9.713673672824451e-06, + "loss": 6.1523, + "step": 145000 + }, + { + "epoch": 3.08, + "learning_rate": 9.712613204946023e-06, + "loss": 6.1558, + "step": 145500 + }, + { + "epoch": 3.09, + "learning_rate": 9.711552737067595e-06, + "loss": 6.1498, + "step": 146000 + }, + { + "epoch": 3.1, + "learning_rate": 9.710492269189167e-06, + "loss": 6.15, + "step": 146500 + }, + { + "epoch": 3.11, + "learning_rate": 9.70943180131074e-06, + "loss": 6.1502, + "step": 147000 + }, + { + "epoch": 3.12, + "learning_rate": 9.708371333432311e-06, + "loss": 6.1498, + "step": 147500 + }, + { + "epoch": 3.13, + "learning_rate": 9.707310865553883e-06, + "loss": 6.1498, + "step": 148000 + }, + { + "epoch": 3.14, + "learning_rate": 9.706250397675456e-06, + "loss": 6.144, + "step": 148500 + }, + { + "epoch": 3.15, + "learning_rate": 9.705189929797028e-06, + "loss": 6.1476, + "step": 149000 + }, + { + "epoch": 3.16, + "learning_rate": 9.7041294619186e-06, + "loss": 6.1476, + "step": 149500 + }, + { + "epoch": 3.17, + "learning_rate": 9.703068994040172e-06, + "loss": 6.1488, + "step": 150000 + }, + { + "epoch": 3.19, + "learning_rate": 9.702008526161744e-06, + "loss": 6.1492, + "step": 150500 + }, + { + "epoch": 3.2, + "learning_rate": 9.700948058283314e-06, + "loss": 6.1497, + "step": 151000 + }, + { + "epoch": 3.21, + "learning_rate": 9.699887590404888e-06, + "loss": 6.1482, + "step": 151500 + }, + { + "epoch": 3.22, + "learning_rate": 9.69882712252646e-06, + "loss": 6.1472, + "step": 152000 + }, + { + "epoch": 3.23, + "learning_rate": 9.697766654648032e-06, + "loss": 6.1425, + "step": 152500 + }, + { + "epoch": 3.24, + "learning_rate": 9.696706186769604e-06, + "loss": 6.1406, + "step": 153000 + }, + { + "epoch": 3.25, + "learning_rate": 9.695645718891176e-06, + "loss": 6.1464, + "step": 153500 + }, + { + "epoch": 3.26, + "learning_rate": 9.694585251012748e-06, + "loss": 6.1416, + "step": 154000 + }, + { + "epoch": 3.27, + "learning_rate": 9.693524783134318e-06, + "loss": 6.142, + "step": 154500 + }, + { + "epoch": 3.28, + "learning_rate": 9.692464315255892e-06, + "loss": 6.141, + "step": 155000 + }, + { + "epoch": 3.29, + "learning_rate": 9.691403847377464e-06, + "loss": 6.1435, + "step": 155500 + }, + { + "epoch": 3.3, + "learning_rate": 9.690343379499035e-06, + "loss": 6.1477, + "step": 156000 + }, + { + "epoch": 3.31, + "learning_rate": 9.689282911620608e-06, + "loss": 6.1395, + "step": 156500 + }, + { + "epoch": 3.32, + "learning_rate": 9.68822244374218e-06, + "loss": 6.14, + "step": 157000 + }, + { + "epoch": 3.33, + "learning_rate": 9.68716197586375e-06, + "loss": 6.1425, + "step": 157500 + }, + { + "epoch": 3.34, + "learning_rate": 9.686101507985325e-06, + "loss": 6.1369, + "step": 158000 + }, + { + "epoch": 3.35, + "learning_rate": 9.685041040106897e-06, + "loss": 6.1405, + "step": 158500 + }, + { + "epoch": 3.37, + "learning_rate": 9.683980572228469e-06, + "loss": 6.1366, + "step": 159000 + }, + { + "epoch": 3.38, + "learning_rate": 9.682920104350039e-06, + "loss": 6.1395, + "step": 159500 + }, + { + "epoch": 3.39, + "learning_rate": 9.681859636471613e-06, + "loss": 6.1364, + "step": 160000 + }, + { + "epoch": 3.4, + "learning_rate": 9.680799168593185e-06, + "loss": 6.1373, + "step": 160500 + }, + { + "epoch": 3.41, + "learning_rate": 9.679738700714755e-06, + "loss": 6.139, + "step": 161000 + }, + { + "epoch": 3.42, + "learning_rate": 9.678678232836329e-06, + "loss": 6.1339, + "step": 161500 + }, + { + "epoch": 3.43, + "learning_rate": 9.677617764957901e-06, + "loss": 6.1375, + "step": 162000 + }, + { + "epoch": 3.44, + "learning_rate": 9.676557297079471e-06, + "loss": 6.1361, + "step": 162500 + }, + { + "epoch": 3.45, + "learning_rate": 9.675496829201043e-06, + "loss": 6.14, + "step": 163000 + }, + { + "epoch": 3.46, + "learning_rate": 9.674436361322617e-06, + "loss": 6.1351, + "step": 163500 + }, + { + "epoch": 3.47, + "learning_rate": 9.673375893444188e-06, + "loss": 6.1316, + "step": 164000 + }, + { + "epoch": 3.48, + "learning_rate": 9.67231542556576e-06, + "loss": 6.1307, + "step": 164500 + }, + { + "epoch": 3.49, + "learning_rate": 9.671254957687333e-06, + "loss": 6.138, + "step": 165000 + }, + { + "epoch": 3.5, + "learning_rate": 9.670194489808904e-06, + "loss": 6.1308, + "step": 165500 + }, + { + "epoch": 3.51, + "learning_rate": 9.669134021930476e-06, + "loss": 6.1315, + "step": 166000 + }, + { + "epoch": 3.52, + "learning_rate": 9.66807355405205e-06, + "loss": 6.131, + "step": 166500 + }, + { + "epoch": 3.53, + "learning_rate": 9.667013086173622e-06, + "loss": 6.1331, + "step": 167000 + }, + { + "epoch": 3.55, + "learning_rate": 9.665952618295192e-06, + "loss": 6.1346, + "step": 167500 + }, + { + "epoch": 3.56, + "learning_rate": 9.664892150416764e-06, + "loss": 6.1316, + "step": 168000 + }, + { + "epoch": 3.57, + "learning_rate": 9.663831682538338e-06, + "loss": 6.127, + "step": 168500 + }, + { + "epoch": 3.58, + "learning_rate": 9.662771214659908e-06, + "loss": 6.1312, + "step": 169000 + }, + { + "epoch": 3.59, + "learning_rate": 9.66171074678148e-06, + "loss": 6.1284, + "step": 169500 + }, + { + "epoch": 3.6, + "learning_rate": 9.660650278903054e-06, + "loss": 6.1241, + "step": 170000 + }, + { + "epoch": 3.61, + "learning_rate": 9.659589811024624e-06, + "loss": 6.128, + "step": 170500 + }, + { + "epoch": 3.62, + "learning_rate": 9.658529343146196e-06, + "loss": 6.1258, + "step": 171000 + }, + { + "epoch": 3.63, + "learning_rate": 9.657468875267768e-06, + "loss": 6.1239, + "step": 171500 + }, + { + "epoch": 3.64, + "learning_rate": 9.65640840738934e-06, + "loss": 6.1301, + "step": 172000 + }, + { + "epoch": 3.65, + "learning_rate": 9.655347939510913e-06, + "loss": 6.1253, + "step": 172500 + }, + { + "epoch": 3.66, + "learning_rate": 9.654287471632485e-06, + "loss": 6.1268, + "step": 173000 + }, + { + "epoch": 3.67, + "learning_rate": 9.653227003754057e-06, + "loss": 6.1238, + "step": 173500 + }, + { + "epoch": 3.68, + "learning_rate": 9.652166535875629e-06, + "loss": 6.1211, + "step": 174000 + }, + { + "epoch": 3.69, + "learning_rate": 9.6511060679972e-06, + "loss": 6.1242, + "step": 174500 + }, + { + "epoch": 3.7, + "learning_rate": 9.650045600118773e-06, + "loss": 6.1275, + "step": 175000 + }, + { + "epoch": 3.71, + "learning_rate": 9.648985132240345e-06, + "loss": 6.1241, + "step": 175500 + }, + { + "epoch": 3.72, + "learning_rate": 9.647924664361917e-06, + "loss": 6.1256, + "step": 176000 + }, + { + "epoch": 3.74, + "learning_rate": 9.646864196483489e-06, + "loss": 6.1242, + "step": 176500 + }, + { + "epoch": 3.75, + "learning_rate": 9.645803728605061e-06, + "loss": 6.1215, + "step": 177000 + }, + { + "epoch": 3.76, + "learning_rate": 9.644743260726633e-06, + "loss": 6.1216, + "step": 177500 + }, + { + "epoch": 3.77, + "learning_rate": 9.643682792848205e-06, + "loss": 6.1215, + "step": 178000 + }, + { + "epoch": 3.78, + "learning_rate": 9.642622324969777e-06, + "loss": 6.1219, + "step": 178500 + }, + { + "epoch": 3.79, + "learning_rate": 9.64156185709135e-06, + "loss": 6.1237, + "step": 179000 + }, + { + "epoch": 3.8, + "learning_rate": 9.640501389212921e-06, + "loss": 6.1176, + "step": 179500 + }, + { + "epoch": 3.81, + "learning_rate": 9.639440921334493e-06, + "loss": 6.1225, + "step": 180000 + }, + { + "epoch": 3.82, + "learning_rate": 9.638380453456065e-06, + "loss": 6.1212, + "step": 180500 + }, + { + "epoch": 3.83, + "learning_rate": 9.637319985577638e-06, + "loss": 6.1191, + "step": 181000 + }, + { + "epoch": 3.84, + "learning_rate": 9.63625951769921e-06, + "loss": 6.1215, + "step": 181500 + }, + { + "epoch": 3.85, + "learning_rate": 9.635199049820782e-06, + "loss": 6.1208, + "step": 182000 + }, + { + "epoch": 3.86, + "learning_rate": 9.634138581942354e-06, + "loss": 6.1227, + "step": 182500 + }, + { + "epoch": 3.87, + "learning_rate": 9.633078114063926e-06, + "loss": 6.1223, + "step": 183000 + }, + { + "epoch": 3.88, + "learning_rate": 9.632017646185498e-06, + "loss": 6.1157, + "step": 183500 + }, + { + "epoch": 3.89, + "learning_rate": 9.63095717830707e-06, + "loss": 6.1168, + "step": 184000 + }, + { + "epoch": 3.9, + "learning_rate": 9.629896710428642e-06, + "loss": 6.1113, + "step": 184500 + }, + { + "epoch": 3.92, + "learning_rate": 9.628836242550214e-06, + "loss": 6.1157, + "step": 185000 + }, + { + "epoch": 3.93, + "learning_rate": 9.627775774671786e-06, + "loss": 6.116, + "step": 185500 + }, + { + "epoch": 3.94, + "learning_rate": 9.626715306793358e-06, + "loss": 6.1159, + "step": 186000 + }, + { + "epoch": 3.95, + "learning_rate": 9.62565483891493e-06, + "loss": 6.1174, + "step": 186500 + }, + { + "epoch": 3.96, + "learning_rate": 9.624594371036502e-06, + "loss": 6.1192, + "step": 187000 + }, + { + "epoch": 3.97, + "learning_rate": 9.623533903158074e-06, + "loss": 6.1168, + "step": 187500 + }, + { + "epoch": 3.98, + "learning_rate": 9.622473435279646e-06, + "loss": 6.1163, + "step": 188000 + }, + { + "epoch": 3.99, + "learning_rate": 9.621412967401218e-06, + "loss": 6.1151, + "step": 188500 + }, + { + "epoch": 4.0, + "learning_rate": 9.62035249952279e-06, + "loss": 6.1141, + "step": 189000 + }, + { + "epoch": 4.01, + "learning_rate": 9.619292031644362e-06, + "loss": 6.1132, + "step": 189500 + }, + { + "epoch": 4.02, + "learning_rate": 9.618231563765935e-06, + "loss": 6.1142, + "step": 190000 + }, + { + "epoch": 4.03, + "learning_rate": 9.617171095887507e-06, + "loss": 6.113, + "step": 190500 + }, + { + "epoch": 4.04, + "learning_rate": 9.616110628009079e-06, + "loss": 6.1132, + "step": 191000 + }, + { + "epoch": 4.05, + "learning_rate": 9.61505016013065e-06, + "loss": 6.1126, + "step": 191500 + }, + { + "epoch": 4.06, + "learning_rate": 9.613989692252223e-06, + "loss": 6.1099, + "step": 192000 + }, + { + "epoch": 4.07, + "learning_rate": 9.612929224373795e-06, + "loss": 6.1111, + "step": 192500 + }, + { + "epoch": 4.08, + "learning_rate": 9.611868756495367e-06, + "loss": 6.1091, + "step": 193000 + }, + { + "epoch": 4.1, + "learning_rate": 9.610808288616939e-06, + "loss": 6.1123, + "step": 193500 + }, + { + "epoch": 4.11, + "learning_rate": 9.609747820738511e-06, + "loss": 6.1071, + "step": 194000 + }, + { + "epoch": 4.12, + "learning_rate": 9.608687352860081e-06, + "loss": 6.1103, + "step": 194500 + }, + { + "epoch": 4.13, + "learning_rate": 9.607626884981655e-06, + "loss": 6.1081, + "step": 195000 + }, + { + "epoch": 4.14, + "learning_rate": 9.606566417103227e-06, + "loss": 6.1079, + "step": 195500 + }, + { + "epoch": 4.15, + "learning_rate": 9.6055059492248e-06, + "loss": 6.1122, + "step": 196000 + }, + { + "epoch": 4.16, + "learning_rate": 9.604445481346371e-06, + "loss": 6.1103, + "step": 196500 + }, + { + "epoch": 4.17, + "learning_rate": 9.603385013467943e-06, + "loss": 6.1062, + "step": 197000 + }, + { + "epoch": 4.18, + "learning_rate": 9.602324545589515e-06, + "loss": 6.1043, + "step": 197500 + }, + { + "epoch": 4.19, + "learning_rate": 9.601264077711086e-06, + "loss": 6.1049, + "step": 198000 + }, + { + "epoch": 4.2, + "learning_rate": 9.60020360983266e-06, + "loss": 6.1062, + "step": 198500 + }, + { + "epoch": 4.21, + "learning_rate": 9.599143141954232e-06, + "loss": 6.1034, + "step": 199000 + }, + { + "epoch": 4.22, + "learning_rate": 9.598082674075802e-06, + "loss": 6.106, + "step": 199500 + }, + { + "epoch": 4.23, + "learning_rate": 9.597022206197376e-06, + "loss": 6.1077, + "step": 200000 + }, + { + "epoch": 4.24, + "learning_rate": 9.595961738318948e-06, + "loss": 6.1097, + "step": 200500 + }, + { + "epoch": 4.25, + "learning_rate": 9.594901270440518e-06, + "loss": 6.1048, + "step": 201000 + }, + { + "epoch": 4.26, + "learning_rate": 9.593840802562092e-06, + "loss": 6.1047, + "step": 201500 + }, + { + "epoch": 4.28, + "learning_rate": 9.592780334683664e-06, + "loss": 6.1031, + "step": 202000 + }, + { + "epoch": 4.29, + "learning_rate": 9.591719866805234e-06, + "loss": 6.1028, + "step": 202500 + }, + { + "epoch": 4.3, + "learning_rate": 9.590659398926806e-06, + "loss": 6.1061, + "step": 203000 + }, + { + "epoch": 4.31, + "learning_rate": 9.58959893104838e-06, + "loss": 6.1015, + "step": 203500 + }, + { + "epoch": 4.32, + "learning_rate": 9.588538463169952e-06, + "loss": 6.1068, + "step": 204000 + }, + { + "epoch": 4.33, + "learning_rate": 9.587477995291522e-06, + "loss": 6.1051, + "step": 204500 + }, + { + "epoch": 4.34, + "learning_rate": 9.586417527413096e-06, + "loss": 6.1022, + "step": 205000 + }, + { + "epoch": 4.35, + "learning_rate": 9.585357059534668e-06, + "loss": 6.1031, + "step": 205500 + }, + { + "epoch": 4.36, + "learning_rate": 9.584296591656239e-06, + "loss": 6.102, + "step": 206000 + }, + { + "epoch": 4.37, + "learning_rate": 9.58323612377781e-06, + "loss": 6.1018, + "step": 206500 + }, + { + "epoch": 4.38, + "learning_rate": 9.582175655899384e-06, + "loss": 6.1007, + "step": 207000 + }, + { + "epoch": 4.39, + "learning_rate": 9.581115188020955e-06, + "loss": 6.099, + "step": 207500 + }, + { + "epoch": 4.4, + "learning_rate": 9.580054720142527e-06, + "loss": 6.1037, + "step": 208000 + }, + { + "epoch": 4.41, + "learning_rate": 9.5789942522641e-06, + "loss": 6.1014, + "step": 208500 + }, + { + "epoch": 4.42, + "learning_rate": 9.577933784385671e-06, + "loss": 6.104, + "step": 209000 + }, + { + "epoch": 4.43, + "learning_rate": 9.576873316507243e-06, + "loss": 6.0975, + "step": 209500 + }, + { + "epoch": 4.44, + "learning_rate": 9.575812848628817e-06, + "loss": 6.0999, + "step": 210000 + }, + { + "epoch": 4.46, + "learning_rate": 9.574752380750389e-06, + "loss": 6.1014, + "step": 210500 + }, + { + "epoch": 4.47, + "learning_rate": 9.57369191287196e-06, + "loss": 6.0973, + "step": 211000 + }, + { + "epoch": 4.48, + "learning_rate": 9.572631444993531e-06, + "loss": 6.0998, + "step": 211500 + }, + { + "epoch": 4.49, + "learning_rate": 9.571570977115105e-06, + "loss": 6.1004, + "step": 212000 + }, + { + "epoch": 4.5, + "learning_rate": 9.570510509236675e-06, + "loss": 6.0983, + "step": 212500 + }, + { + "epoch": 4.51, + "learning_rate": 9.569450041358247e-06, + "loss": 6.101, + "step": 213000 + }, + { + "epoch": 4.52, + "learning_rate": 9.568389573479821e-06, + "loss": 6.0992, + "step": 213500 + }, + { + "epoch": 4.53, + "learning_rate": 9.567329105601392e-06, + "loss": 6.0954, + "step": 214000 + }, + { + "epoch": 4.54, + "learning_rate": 9.566268637722964e-06, + "loss": 6.0971, + "step": 214500 + }, + { + "epoch": 4.55, + "learning_rate": 9.565208169844536e-06, + "loss": 6.0984, + "step": 215000 + }, + { + "epoch": 4.56, + "learning_rate": 9.564147701966108e-06, + "loss": 6.0938, + "step": 215500 + }, + { + "epoch": 4.57, + "learning_rate": 9.56308723408768e-06, + "loss": 6.0977, + "step": 216000 + }, + { + "epoch": 4.58, + "learning_rate": 9.562026766209252e-06, + "loss": 6.0938, + "step": 216500 + }, + { + "epoch": 4.59, + "learning_rate": 9.560966298330824e-06, + "loss": 6.0977, + "step": 217000 + }, + { + "epoch": 4.6, + "learning_rate": 9.559905830452396e-06, + "loss": 6.1002, + "step": 217500 + }, + { + "epoch": 4.61, + "learning_rate": 9.558845362573968e-06, + "loss": 6.0988, + "step": 218000 + }, + { + "epoch": 4.62, + "learning_rate": 9.557784894695542e-06, + "loss": 6.0937, + "step": 218500 + }, + { + "epoch": 4.64, + "learning_rate": 9.556724426817112e-06, + "loss": 6.0947, + "step": 219000 + }, + { + "epoch": 4.65, + "learning_rate": 9.555663958938684e-06, + "loss": 6.0983, + "step": 219500 + }, + { + "epoch": 4.66, + "learning_rate": 9.554603491060256e-06, + "loss": 6.0932, + "step": 220000 + }, + { + "epoch": 4.67, + "learning_rate": 9.553543023181828e-06, + "loss": 6.0947, + "step": 220500 + }, + { + "epoch": 4.68, + "learning_rate": 9.5524825553034e-06, + "loss": 6.0914, + "step": 221000 + }, + { + "epoch": 4.69, + "learning_rate": 9.551422087424972e-06, + "loss": 6.0919, + "step": 221500 + }, + { + "epoch": 4.7, + "learning_rate": 9.550361619546544e-06, + "loss": 6.0892, + "step": 222000 + }, + { + "epoch": 4.71, + "learning_rate": 9.549301151668117e-06, + "loss": 6.0967, + "step": 222500 + }, + { + "epoch": 4.72, + "learning_rate": 9.548240683789689e-06, + "loss": 6.0933, + "step": 223000 + }, + { + "epoch": 4.73, + "learning_rate": 9.54718021591126e-06, + "loss": 6.0907, + "step": 223500 + }, + { + "epoch": 4.74, + "learning_rate": 9.546119748032833e-06, + "loss": 6.0939, + "step": 224000 + }, + { + "epoch": 4.75, + "learning_rate": 9.545059280154405e-06, + "loss": 6.0929, + "step": 224500 + }, + { + "epoch": 4.76, + "learning_rate": 9.543998812275977e-06, + "loss": 6.092, + "step": 225000 + }, + { + "epoch": 4.77, + "learning_rate": 9.542938344397549e-06, + "loss": 6.0886, + "step": 225500 + }, + { + "epoch": 4.78, + "learning_rate": 9.541877876519121e-06, + "loss": 6.092, + "step": 226000 + }, + { + "epoch": 4.79, + "learning_rate": 9.540817408640693e-06, + "loss": 6.0931, + "step": 226500 + }, + { + "epoch": 4.8, + "learning_rate": 9.539756940762265e-06, + "loss": 6.0888, + "step": 227000 + }, + { + "epoch": 4.81, + "learning_rate": 9.538696472883837e-06, + "loss": 6.0948, + "step": 227500 + }, + { + "epoch": 4.83, + "learning_rate": 9.53763600500541e-06, + "loss": 6.0864, + "step": 228000 + }, + { + "epoch": 4.84, + "learning_rate": 9.536575537126981e-06, + "loss": 6.0931, + "step": 228500 + }, + { + "epoch": 4.85, + "learning_rate": 9.535515069248553e-06, + "loss": 6.0899, + "step": 229000 + }, + { + "epoch": 4.86, + "learning_rate": 9.534454601370125e-06, + "loss": 6.0895, + "step": 229500 + }, + { + "epoch": 4.87, + "learning_rate": 9.533394133491697e-06, + "loss": 6.0884, + "step": 230000 + }, + { + "epoch": 4.88, + "learning_rate": 9.53233366561327e-06, + "loss": 6.0865, + "step": 230500 + }, + { + "epoch": 4.89, + "learning_rate": 9.531273197734842e-06, + "loss": 6.0839, + "step": 231000 + }, + { + "epoch": 4.9, + "learning_rate": 9.530212729856414e-06, + "loss": 6.0905, + "step": 231500 + }, + { + "epoch": 4.91, + "learning_rate": 9.529152261977986e-06, + "loss": 6.088, + "step": 232000 + }, + { + "epoch": 4.92, + "learning_rate": 9.528091794099558e-06, + "loss": 6.0807, + "step": 232500 + }, + { + "epoch": 4.93, + "learning_rate": 9.52703132622113e-06, + "loss": 6.0859, + "step": 233000 + }, + { + "epoch": 4.94, + "learning_rate": 9.525970858342702e-06, + "loss": 6.0859, + "step": 233500 + }, + { + "epoch": 4.95, + "learning_rate": 9.524910390464274e-06, + "loss": 6.0898, + "step": 234000 + }, + { + "epoch": 4.96, + "learning_rate": 9.523849922585846e-06, + "loss": 6.0895, + "step": 234500 + }, + { + "epoch": 4.97, + "learning_rate": 9.522789454707418e-06, + "loss": 6.0845, + "step": 235000 + }, + { + "epoch": 4.98, + "learning_rate": 9.52172898682899e-06, + "loss": 6.0878, + "step": 235500 + }, + { + "epoch": 4.99, + "learning_rate": 9.520668518950562e-06, + "loss": 6.0921, + "step": 236000 + }, + { + "epoch": 5.01, + "learning_rate": 9.519608051072134e-06, + "loss": 6.0861, + "step": 236500 + }, + { + "epoch": 5.02, + "learning_rate": 9.518547583193706e-06, + "loss": 6.0826, + "step": 237000 + }, + { + "epoch": 5.03, + "learning_rate": 9.517487115315278e-06, + "loss": 6.0903, + "step": 237500 + }, + { + "epoch": 5.04, + "learning_rate": 9.516426647436849e-06, + "loss": 6.0858, + "step": 238000 + }, + { + "epoch": 5.05, + "learning_rate": 9.515366179558422e-06, + "loss": 6.086, + "step": 238500 + }, + { + "epoch": 5.06, + "learning_rate": 9.514305711679994e-06, + "loss": 6.0843, + "step": 239000 + }, + { + "epoch": 5.07, + "learning_rate": 9.513245243801566e-06, + "loss": 6.0809, + "step": 239500 + }, + { + "epoch": 5.08, + "learning_rate": 9.512184775923139e-06, + "loss": 6.0834, + "step": 240000 + }, + { + "epoch": 5.09, + "learning_rate": 9.51112430804471e-06, + "loss": 6.0845, + "step": 240500 + }, + { + "epoch": 5.1, + "learning_rate": 9.510063840166283e-06, + "loss": 6.0806, + "step": 241000 + }, + { + "epoch": 5.11, + "learning_rate": 9.509003372287855e-06, + "loss": 6.0824, + "step": 241500 + }, + { + "epoch": 5.12, + "learning_rate": 9.507942904409427e-06, + "loss": 6.0835, + "step": 242000 + }, + { + "epoch": 5.13, + "learning_rate": 9.506882436530999e-06, + "loss": 6.0853, + "step": 242500 + }, + { + "epoch": 5.14, + "learning_rate": 9.50582196865257e-06, + "loss": 6.0797, + "step": 243000 + }, + { + "epoch": 5.15, + "learning_rate": 9.504761500774143e-06, + "loss": 6.0868, + "step": 243500 + }, + { + "epoch": 5.16, + "learning_rate": 9.503701032895715e-06, + "loss": 6.0839, + "step": 244000 + }, + { + "epoch": 5.17, + "learning_rate": 9.502640565017285e-06, + "loss": 6.0826, + "step": 244500 + }, + { + "epoch": 5.19, + "learning_rate": 9.501580097138859e-06, + "loss": 6.0807, + "step": 245000 + }, + { + "epoch": 5.2, + "learning_rate": 9.500519629260431e-06, + "loss": 6.0833, + "step": 245500 + }, + { + "epoch": 5.21, + "learning_rate": 9.499459161382002e-06, + "loss": 6.0807, + "step": 246000 + }, + { + "epoch": 5.22, + "learning_rate": 9.498398693503574e-06, + "loss": 6.0797, + "step": 246500 + }, + { + "epoch": 5.23, + "learning_rate": 9.497338225625147e-06, + "loss": 6.0797, + "step": 247000 + }, + { + "epoch": 5.24, + "learning_rate": 9.49627775774672e-06, + "loss": 6.0752, + "step": 247500 + }, + { + "epoch": 5.25, + "learning_rate": 9.49521728986829e-06, + "loss": 6.0783, + "step": 248000 + }, + { + "epoch": 5.26, + "learning_rate": 9.494156821989864e-06, + "loss": 6.0789, + "step": 248500 + }, + { + "epoch": 5.27, + "learning_rate": 9.493096354111436e-06, + "loss": 6.0786, + "step": 249000 + }, + { + "epoch": 5.28, + "learning_rate": 9.492035886233006e-06, + "loss": 6.0805, + "step": 249500 + }, + { + "epoch": 5.29, + "learning_rate": 9.490975418354578e-06, + "loss": 6.081, + "step": 250000 + }, + { + "epoch": 5.3, + "learning_rate": 9.489914950476152e-06, + "loss": 6.0789, + "step": 250500 + }, + { + "epoch": 5.31, + "learning_rate": 9.488854482597722e-06, + "loss": 6.077, + "step": 251000 + }, + { + "epoch": 5.32, + "learning_rate": 9.487794014719294e-06, + "loss": 6.081, + "step": 251500 + }, + { + "epoch": 5.33, + "learning_rate": 9.486733546840868e-06, + "loss": 6.0847, + "step": 252000 + }, + { + "epoch": 5.34, + "learning_rate": 9.485673078962438e-06, + "loss": 6.0784, + "step": 252500 + }, + { + "epoch": 5.35, + "learning_rate": 9.48461261108401e-06, + "loss": 6.08, + "step": 253000 + }, + { + "epoch": 5.37, + "learning_rate": 9.483552143205584e-06, + "loss": 6.0752, + "step": 253500 + }, + { + "epoch": 5.38, + "learning_rate": 9.482491675327156e-06, + "loss": 6.0791, + "step": 254000 + }, + { + "epoch": 5.39, + "learning_rate": 9.481431207448726e-06, + "loss": 6.0779, + "step": 254500 + }, + { + "epoch": 5.4, + "learning_rate": 9.480370739570299e-06, + "loss": 6.0758, + "step": 255000 + }, + { + "epoch": 5.41, + "learning_rate": 9.479310271691872e-06, + "loss": 6.0803, + "step": 255500 + }, + { + "epoch": 5.42, + "learning_rate": 9.478249803813443e-06, + "loss": 6.0752, + "step": 256000 + }, + { + "epoch": 5.43, + "learning_rate": 9.477189335935015e-06, + "loss": 6.0742, + "step": 256500 + }, + { + "epoch": 5.44, + "learning_rate": 9.476128868056588e-06, + "loss": 6.077, + "step": 257000 + }, + { + "epoch": 5.45, + "learning_rate": 9.475068400178159e-06, + "loss": 6.0734, + "step": 257500 + }, + { + "epoch": 5.46, + "learning_rate": 9.474007932299731e-06, + "loss": 6.0731, + "step": 258000 + }, + { + "epoch": 5.47, + "learning_rate": 9.472947464421303e-06, + "loss": 6.0787, + "step": 258500 + }, + { + "epoch": 5.48, + "learning_rate": 9.471886996542875e-06, + "loss": 6.073, + "step": 259000 + }, + { + "epoch": 5.49, + "learning_rate": 9.470826528664447e-06, + "loss": 6.073, + "step": 259500 + }, + { + "epoch": 5.5, + "learning_rate": 9.469766060786019e-06, + "loss": 6.0765, + "step": 260000 + }, + { + "epoch": 5.51, + "learning_rate": 9.468705592907591e-06, + "loss": 6.076, + "step": 260500 + }, + { + "epoch": 5.52, + "learning_rate": 9.467645125029163e-06, + "loss": 6.0721, + "step": 261000 + }, + { + "epoch": 5.53, + "learning_rate": 9.466584657150735e-06, + "loss": 6.0762, + "step": 261500 + }, + { + "epoch": 5.55, + "learning_rate": 9.465524189272309e-06, + "loss": 6.0719, + "step": 262000 + }, + { + "epoch": 5.56, + "learning_rate": 9.46446372139388e-06, + "loss": 6.0754, + "step": 262500 + }, + { + "epoch": 5.57, + "learning_rate": 9.463403253515451e-06, + "loss": 6.0737, + "step": 263000 + }, + { + "epoch": 5.58, + "learning_rate": 9.462342785637024e-06, + "loss": 6.072, + "step": 263500 + }, + { + "epoch": 5.59, + "learning_rate": 9.461282317758596e-06, + "loss": 6.0748, + "step": 264000 + }, + { + "epoch": 5.6, + "learning_rate": 9.460221849880168e-06, + "loss": 6.0811, + "step": 264500 + }, + { + "epoch": 5.61, + "learning_rate": 9.45916138200174e-06, + "loss": 6.0738, + "step": 265000 + }, + { + "epoch": 5.62, + "learning_rate": 9.458100914123312e-06, + "loss": 6.0744, + "step": 265500 + }, + { + "epoch": 5.63, + "learning_rate": 9.457040446244884e-06, + "loss": 6.0679, + "step": 266000 + }, + { + "epoch": 5.64, + "learning_rate": 9.455979978366456e-06, + "loss": 6.0702, + "step": 266500 + }, + { + "epoch": 5.65, + "learning_rate": 9.454919510488028e-06, + "loss": 6.074, + "step": 267000 + }, + { + "epoch": 5.66, + "learning_rate": 9.4538590426096e-06, + "loss": 6.0722, + "step": 267500 + }, + { + "epoch": 5.67, + "learning_rate": 9.452798574731172e-06, + "loss": 6.0746, + "step": 268000 + }, + { + "epoch": 5.68, + "learning_rate": 9.451738106852744e-06, + "loss": 6.0718, + "step": 268500 + }, + { + "epoch": 5.69, + "learning_rate": 9.450677638974316e-06, + "loss": 6.0693, + "step": 269000 + }, + { + "epoch": 5.7, + "learning_rate": 9.449617171095888e-06, + "loss": 6.0674, + "step": 269500 + }, + { + "epoch": 5.71, + "learning_rate": 9.44855670321746e-06, + "loss": 6.074, + "step": 270000 + }, + { + "epoch": 5.72, + "learning_rate": 9.447496235339032e-06, + "loss": 6.067, + "step": 270500 + }, + { + "epoch": 5.74, + "learning_rate": 9.446435767460604e-06, + "loss": 6.0681, + "step": 271000 + }, + { + "epoch": 5.75, + "learning_rate": 9.445375299582176e-06, + "loss": 6.0684, + "step": 271500 + }, + { + "epoch": 5.76, + "learning_rate": 9.444314831703748e-06, + "loss": 6.0698, + "step": 272000 + }, + { + "epoch": 5.77, + "learning_rate": 9.44325436382532e-06, + "loss": 6.0707, + "step": 272500 + }, + { + "epoch": 5.78, + "learning_rate": 9.442193895946893e-06, + "loss": 6.0692, + "step": 273000 + }, + { + "epoch": 5.79, + "learning_rate": 9.441133428068465e-06, + "loss": 6.0664, + "step": 273500 + }, + { + "epoch": 5.8, + "learning_rate": 9.440072960190037e-06, + "loss": 6.068, + "step": 274000 + }, + { + "epoch": 5.81, + "learning_rate": 9.439012492311609e-06, + "loss": 6.0643, + "step": 274500 + }, + { + "epoch": 5.82, + "learning_rate": 9.43795202443318e-06, + "loss": 6.0694, + "step": 275000 + }, + { + "epoch": 5.83, + "learning_rate": 9.436891556554753e-06, + "loss": 6.0711, + "step": 275500 + }, + { + "epoch": 5.84, + "learning_rate": 9.435831088676325e-06, + "loss": 6.0665, + "step": 276000 + }, + { + "epoch": 5.85, + "learning_rate": 9.434770620797897e-06, + "loss": 6.0709, + "step": 276500 + }, + { + "epoch": 5.86, + "learning_rate": 9.433710152919469e-06, + "loss": 6.0698, + "step": 277000 + }, + { + "epoch": 5.87, + "learning_rate": 9.432649685041041e-06, + "loss": 6.0655, + "step": 277500 + }, + { + "epoch": 5.88, + "learning_rate": 9.431589217162613e-06, + "loss": 6.0645, + "step": 278000 + }, + { + "epoch": 5.89, + "learning_rate": 9.430528749284185e-06, + "loss": 6.0697, + "step": 278500 + }, + { + "epoch": 5.9, + "learning_rate": 9.429468281405757e-06, + "loss": 6.0675, + "step": 279000 + }, + { + "epoch": 5.92, + "learning_rate": 9.42840781352733e-06, + "loss": 6.0662, + "step": 279500 + }, + { + "epoch": 5.93, + "learning_rate": 9.427347345648901e-06, + "loss": 6.0694, + "step": 280000 + }, + { + "epoch": 5.94, + "learning_rate": 9.426286877770473e-06, + "loss": 6.066, + "step": 280500 + }, + { + "epoch": 5.95, + "learning_rate": 9.425226409892046e-06, + "loss": 6.065, + "step": 281000 + }, + { + "epoch": 5.96, + "learning_rate": 9.424165942013616e-06, + "loss": 6.0678, + "step": 281500 + }, + { + "epoch": 5.97, + "learning_rate": 9.42310547413519e-06, + "loss": 6.0673, + "step": 282000 + }, + { + "epoch": 5.98, + "learning_rate": 9.422045006256762e-06, + "loss": 6.0649, + "step": 282500 + }, + { + "epoch": 5.99, + "learning_rate": 9.420984538378334e-06, + "loss": 6.0694, + "step": 283000 + }, + { + "epoch": 6.0, + "learning_rate": 9.419924070499906e-06, + "loss": 6.0675, + "step": 283500 + }, + { + "epoch": 6.01, + "learning_rate": 9.418863602621478e-06, + "loss": 6.0672, + "step": 284000 + }, + { + "epoch": 6.02, + "learning_rate": 9.41780313474305e-06, + "loss": 6.0634, + "step": 284500 + }, + { + "epoch": 6.03, + "learning_rate": 9.416742666864622e-06, + "loss": 6.0635, + "step": 285000 + }, + { + "epoch": 6.04, + "learning_rate": 9.415682198986194e-06, + "loss": 6.0639, + "step": 285500 + }, + { + "epoch": 6.05, + "learning_rate": 9.414621731107766e-06, + "loss": 6.0667, + "step": 286000 + }, + { + "epoch": 6.06, + "learning_rate": 9.413561263229336e-06, + "loss": 6.0664, + "step": 286500 + }, + { + "epoch": 6.07, + "learning_rate": 9.41250079535091e-06, + "loss": 6.0652, + "step": 287000 + }, + { + "epoch": 6.08, + "learning_rate": 9.411440327472482e-06, + "loss": 6.0621, + "step": 287500 + }, + { + "epoch": 6.1, + "learning_rate": 9.410379859594053e-06, + "loss": 6.0647, + "step": 288000 + }, + { + "epoch": 6.11, + "learning_rate": 9.409319391715626e-06, + "loss": 6.0656, + "step": 288500 + }, + { + "epoch": 6.12, + "learning_rate": 9.408258923837198e-06, + "loss": 6.0653, + "step": 289000 + }, + { + "epoch": 6.13, + "learning_rate": 9.407198455958769e-06, + "loss": 6.0674, + "step": 289500 + }, + { + "epoch": 6.14, + "learning_rate": 9.40613798808034e-06, + "loss": 6.0615, + "step": 290000 + }, + { + "epoch": 6.15, + "learning_rate": 9.405077520201915e-06, + "loss": 6.0582, + "step": 290500 + }, + { + "epoch": 6.16, + "learning_rate": 9.404017052323487e-06, + "loss": 6.0651, + "step": 291000 + }, + { + "epoch": 6.17, + "learning_rate": 9.402956584445057e-06, + "loss": 6.0615, + "step": 291500 + }, + { + "epoch": 6.18, + "learning_rate": 9.40189611656663e-06, + "loss": 6.0647, + "step": 292000 + }, + { + "epoch": 6.19, + "learning_rate": 9.400835648688203e-06, + "loss": 6.0625, + "step": 292500 + }, + { + "epoch": 6.2, + "learning_rate": 9.399775180809773e-06, + "loss": 6.0656, + "step": 293000 + }, + { + "epoch": 6.21, + "learning_rate": 9.398714712931345e-06, + "loss": 6.0581, + "step": 293500 + }, + { + "epoch": 6.22, + "learning_rate": 9.397654245052919e-06, + "loss": 6.0623, + "step": 294000 + }, + { + "epoch": 6.23, + "learning_rate": 9.39659377717449e-06, + "loss": 6.0596, + "step": 294500 + }, + { + "epoch": 6.24, + "learning_rate": 9.395533309296061e-06, + "loss": 6.059, + "step": 295000 + }, + { + "epoch": 6.25, + "learning_rate": 9.394472841417635e-06, + "loss": 6.0585, + "step": 295500 + }, + { + "epoch": 6.26, + "learning_rate": 9.393412373539206e-06, + "loss": 6.0623, + "step": 296000 + }, + { + "epoch": 6.28, + "learning_rate": 9.392351905660778e-06, + "loss": 6.061, + "step": 296500 + }, + { + "epoch": 6.29, + "learning_rate": 9.391291437782351e-06, + "loss": 6.0608, + "step": 297000 + }, + { + "epoch": 6.3, + "learning_rate": 9.390230969903923e-06, + "loss": 6.06, + "step": 297500 + }, + { + "epoch": 6.31, + "learning_rate": 9.389170502025494e-06, + "loss": 6.0609, + "step": 298000 + }, + { + "epoch": 6.32, + "learning_rate": 9.388110034147066e-06, + "loss": 6.0622, + "step": 298500 + }, + { + "epoch": 6.33, + "learning_rate": 9.38704956626864e-06, + "loss": 6.0582, + "step": 299000 + }, + { + "epoch": 6.34, + "learning_rate": 9.38598909839021e-06, + "loss": 6.0594, + "step": 299500 + }, + { + "epoch": 6.35, + "learning_rate": 9.384928630511782e-06, + "loss": 6.0631, + "step": 300000 + }, + { + "epoch": 6.36, + "learning_rate": 9.383868162633356e-06, + "loss": 6.0592, + "step": 300500 + }, + { + "epoch": 6.37, + "learning_rate": 9.382807694754926e-06, + "loss": 6.0599, + "step": 301000 + }, + { + "epoch": 6.38, + "learning_rate": 9.381747226876498e-06, + "loss": 6.0597, + "step": 301500 + }, + { + "epoch": 6.39, + "learning_rate": 9.38068675899807e-06, + "loss": 6.0559, + "step": 302000 + }, + { + "epoch": 6.4, + "learning_rate": 9.379626291119642e-06, + "loss": 6.0567, + "step": 302500 + }, + { + "epoch": 6.41, + "learning_rate": 9.378565823241214e-06, + "loss": 6.0587, + "step": 303000 + }, + { + "epoch": 6.42, + "learning_rate": 9.377505355362786e-06, + "loss": 6.0551, + "step": 303500 + }, + { + "epoch": 6.43, + "learning_rate": 9.376444887484358e-06, + "loss": 6.0579, + "step": 304000 + }, + { + "epoch": 6.44, + "learning_rate": 9.37538441960593e-06, + "loss": 6.0615, + "step": 304500 + }, + { + "epoch": 6.46, + "learning_rate": 9.374323951727503e-06, + "loss": 6.0557, + "step": 305000 + }, + { + "epoch": 6.47, + "learning_rate": 9.373263483849076e-06, + "loss": 6.0593, + "step": 305500 + }, + { + "epoch": 6.48, + "learning_rate": 9.372203015970647e-06, + "loss": 6.0559, + "step": 306000 + }, + { + "epoch": 6.49, + "learning_rate": 9.371142548092219e-06, + "loss": 6.0567, + "step": 306500 + }, + { + "epoch": 6.5, + "learning_rate": 9.37008208021379e-06, + "loss": 6.0615, + "step": 307000 + }, + { + "epoch": 6.51, + "learning_rate": 9.369021612335363e-06, + "loss": 6.0561, + "step": 307500 + }, + { + "epoch": 6.52, + "learning_rate": 9.367961144456935e-06, + "loss": 6.0598, + "step": 308000 + }, + { + "epoch": 6.53, + "learning_rate": 9.366900676578507e-06, + "loss": 6.0552, + "step": 308500 + }, + { + "epoch": 6.54, + "learning_rate": 9.365840208700079e-06, + "loss": 6.0561, + "step": 309000 + }, + { + "epoch": 6.55, + "learning_rate": 9.364779740821651e-06, + "loss": 6.0529, + "step": 309500 + }, + { + "epoch": 6.56, + "learning_rate": 9.363719272943223e-06, + "loss": 6.057, + "step": 310000 + }, + { + "epoch": 6.57, + "learning_rate": 9.362658805064795e-06, + "loss": 6.0573, + "step": 310500 + }, + { + "epoch": 6.58, + "learning_rate": 9.361598337186367e-06, + "loss": 6.0555, + "step": 311000 + }, + { + "epoch": 6.59, + "learning_rate": 9.36053786930794e-06, + "loss": 6.0545, + "step": 311500 + }, + { + "epoch": 6.6, + "learning_rate": 9.359477401429511e-06, + "loss": 6.0576, + "step": 312000 + }, + { + "epoch": 6.61, + "learning_rate": 9.358416933551083e-06, + "loss": 6.0544, + "step": 312500 + }, + { + "epoch": 6.62, + "learning_rate": 9.357356465672655e-06, + "loss": 6.0562, + "step": 313000 + }, + { + "epoch": 6.64, + "learning_rate": 9.356295997794228e-06, + "loss": 6.0562, + "step": 313500 + }, + { + "epoch": 6.65, + "learning_rate": 9.3552355299158e-06, + "loss": 6.0529, + "step": 314000 + }, + { + "epoch": 6.66, + "learning_rate": 9.354175062037372e-06, + "loss": 6.054, + "step": 314500 + }, + { + "epoch": 6.67, + "learning_rate": 9.353114594158944e-06, + "loss": 6.0565, + "step": 315000 + }, + { + "epoch": 6.68, + "learning_rate": 9.352054126280516e-06, + "loss": 6.0547, + "step": 315500 + }, + { + "epoch": 6.69, + "learning_rate": 9.350993658402088e-06, + "loss": 6.0537, + "step": 316000 + }, + { + "epoch": 6.7, + "learning_rate": 9.34993319052366e-06, + "loss": 6.0554, + "step": 316500 + }, + { + "epoch": 6.71, + "learning_rate": 9.348872722645232e-06, + "loss": 6.0527, + "step": 317000 + }, + { + "epoch": 6.72, + "learning_rate": 9.347812254766804e-06, + "loss": 6.0558, + "step": 317500 + }, + { + "epoch": 6.73, + "learning_rate": 9.346751786888376e-06, + "loss": 6.0516, + "step": 318000 + }, + { + "epoch": 6.74, + "learning_rate": 9.345691319009948e-06, + "loss": 6.056, + "step": 318500 + }, + { + "epoch": 6.75, + "learning_rate": 9.34463085113152e-06, + "loss": 6.0512, + "step": 319000 + }, + { + "epoch": 6.76, + "learning_rate": 9.343570383253092e-06, + "loss": 6.0525, + "step": 319500 + }, + { + "epoch": 6.77, + "learning_rate": 9.342509915374664e-06, + "loss": 6.0522, + "step": 320000 + }, + { + "epoch": 6.78, + "learning_rate": 9.341449447496236e-06, + "loss": 6.0532, + "step": 320500 + }, + { + "epoch": 6.79, + "learning_rate": 9.340388979617808e-06, + "loss": 6.0535, + "step": 321000 + }, + { + "epoch": 6.8, + "learning_rate": 9.33932851173938e-06, + "loss": 6.0527, + "step": 321500 + }, + { + "epoch": 6.81, + "learning_rate": 9.338268043860952e-06, + "loss": 6.0538, + "step": 322000 + }, + { + "epoch": 6.83, + "learning_rate": 9.337207575982525e-06, + "loss": 6.0545, + "step": 322500 + }, + { + "epoch": 6.84, + "learning_rate": 9.336147108104097e-06, + "loss": 6.0547, + "step": 323000 + }, + { + "epoch": 6.85, + "learning_rate": 9.335086640225669e-06, + "loss": 6.0502, + "step": 323500 + }, + { + "epoch": 6.86, + "learning_rate": 9.33402617234724e-06, + "loss": 6.0517, + "step": 324000 + }, + { + "epoch": 6.87, + "learning_rate": 9.332965704468813e-06, + "loss": 6.0525, + "step": 324500 + }, + { + "epoch": 6.88, + "learning_rate": 9.331905236590383e-06, + "loss": 6.0511, + "step": 325000 + }, + { + "epoch": 6.89, + "learning_rate": 9.330844768711957e-06, + "loss": 6.0487, + "step": 325500 + }, + { + "epoch": 6.9, + "learning_rate": 9.329784300833529e-06, + "loss": 6.0495, + "step": 326000 + }, + { + "epoch": 6.91, + "learning_rate": 9.328723832955101e-06, + "loss": 6.0491, + "step": 326500 + }, + { + "epoch": 6.92, + "learning_rate": 9.327663365076673e-06, + "loss": 6.0576, + "step": 327000 + }, + { + "epoch": 6.93, + "learning_rate": 9.326602897198245e-06, + "loss": 6.0479, + "step": 327500 + }, + { + "epoch": 6.94, + "learning_rate": 9.325542429319817e-06, + "loss": 6.0481, + "step": 328000 + }, + { + "epoch": 6.95, + "learning_rate": 9.32448196144139e-06, + "loss": 6.0501, + "step": 328500 + }, + { + "epoch": 6.96, + "learning_rate": 9.323421493562961e-06, + "loss": 6.0509, + "step": 329000 + }, + { + "epoch": 6.97, + "learning_rate": 9.322361025684533e-06, + "loss": 6.052, + "step": 329500 + }, + { + "epoch": 6.98, + "learning_rate": 9.321300557806104e-06, + "loss": 6.0504, + "step": 330000 + }, + { + "epoch": 6.99, + "learning_rate": 9.320240089927677e-06, + "loss": 6.0465, + "step": 330500 + }, + { + "epoch": 7.01, + "learning_rate": 9.31917962204925e-06, + "loss": 6.045, + "step": 331000 + }, + { + "epoch": 7.02, + "learning_rate": 9.31811915417082e-06, + "loss": 6.0477, + "step": 331500 + }, + { + "epoch": 7.03, + "learning_rate": 9.317058686292394e-06, + "loss": 6.05, + "step": 332000 + }, + { + "epoch": 7.04, + "learning_rate": 9.315998218413966e-06, + "loss": 6.0477, + "step": 332500 + }, + { + "epoch": 7.05, + "learning_rate": 9.314937750535536e-06, + "loss": 6.0528, + "step": 333000 + }, + { + "epoch": 7.06, + "learning_rate": 9.313877282657108e-06, + "loss": 6.0502, + "step": 333500 + }, + { + "epoch": 7.07, + "learning_rate": 9.312816814778682e-06, + "loss": 6.0497, + "step": 334000 + }, + { + "epoch": 7.08, + "learning_rate": 9.311756346900254e-06, + "loss": 6.0525, + "step": 334500 + }, + { + "epoch": 7.09, + "learning_rate": 9.310695879021824e-06, + "loss": 6.0471, + "step": 335000 + }, + { + "epoch": 7.1, + "learning_rate": 9.309635411143398e-06, + "loss": 6.0471, + "step": 335500 + }, + { + "epoch": 7.11, + "learning_rate": 9.30857494326497e-06, + "loss": 6.0459, + "step": 336000 + }, + { + "epoch": 7.12, + "learning_rate": 9.30751447538654e-06, + "loss": 6.0491, + "step": 336500 + }, + { + "epoch": 7.13, + "learning_rate": 9.306454007508113e-06, + "loss": 6.0453, + "step": 337000 + }, + { + "epoch": 7.14, + "learning_rate": 9.305393539629686e-06, + "loss": 6.0439, + "step": 337500 + }, + { + "epoch": 7.15, + "learning_rate": 9.304333071751257e-06, + "loss": 6.0489, + "step": 338000 + }, + { + "epoch": 7.16, + "learning_rate": 9.303272603872829e-06, + "loss": 6.0489, + "step": 338500 + }, + { + "epoch": 7.17, + "learning_rate": 9.302212135994402e-06, + "loss": 6.0445, + "step": 339000 + }, + { + "epoch": 7.19, + "learning_rate": 9.301151668115973e-06, + "loss": 6.0477, + "step": 339500 + }, + { + "epoch": 7.2, + "learning_rate": 9.300091200237545e-06, + "loss": 6.0484, + "step": 340000 + }, + { + "epoch": 7.21, + "learning_rate": 9.299030732359119e-06, + "loss": 6.0416, + "step": 340500 + }, + { + "epoch": 7.22, + "learning_rate": 9.29797026448069e-06, + "loss": 6.0491, + "step": 341000 + }, + { + "epoch": 7.23, + "learning_rate": 9.296909796602261e-06, + "loss": 6.0433, + "step": 341500 + }, + { + "epoch": 7.24, + "learning_rate": 9.295849328723833e-06, + "loss": 6.0388, + "step": 342000 + }, + { + "epoch": 7.25, + "learning_rate": 9.294788860845407e-06, + "loss": 6.0434, + "step": 342500 + }, + { + "epoch": 7.26, + "learning_rate": 9.293728392966977e-06, + "loss": 6.0488, + "step": 343000 + }, + { + "epoch": 7.27, + "learning_rate": 9.29266792508855e-06, + "loss": 6.043, + "step": 343500 + }, + { + "epoch": 7.28, + "learning_rate": 9.291607457210123e-06, + "loss": 6.0425, + "step": 344000 + }, + { + "epoch": 7.29, + "learning_rate": 9.290546989331693e-06, + "loss": 6.0431, + "step": 344500 + }, + { + "epoch": 7.3, + "learning_rate": 9.289486521453265e-06, + "loss": 6.0466, + "step": 345000 + }, + { + "epoch": 7.31, + "learning_rate": 9.288426053574837e-06, + "loss": 6.0426, + "step": 345500 + }, + { + "epoch": 7.32, + "learning_rate": 9.28736558569641e-06, + "loss": 6.0413, + "step": 346000 + }, + { + "epoch": 7.33, + "learning_rate": 9.286305117817982e-06, + "loss": 6.0478, + "step": 346500 + }, + { + "epoch": 7.34, + "learning_rate": 9.285244649939554e-06, + "loss": 6.0431, + "step": 347000 + }, + { + "epoch": 7.35, + "learning_rate": 9.284184182061126e-06, + "loss": 6.0441, + "step": 347500 + }, + { + "epoch": 7.37, + "learning_rate": 9.283123714182698e-06, + "loss": 6.0422, + "step": 348000 + }, + { + "epoch": 7.38, + "learning_rate": 9.28206324630427e-06, + "loss": 6.0494, + "step": 348500 + }, + { + "epoch": 7.39, + "learning_rate": 9.281002778425844e-06, + "loss": 6.0447, + "step": 349000 + }, + { + "epoch": 7.4, + "learning_rate": 9.279942310547414e-06, + "loss": 6.0454, + "step": 349500 + }, + { + "epoch": 7.41, + "learning_rate": 9.278881842668986e-06, + "loss": 6.0414, + "step": 350000 + }, + { + "epoch": 7.42, + "learning_rate": 9.277821374790558e-06, + "loss": 6.043, + "step": 350500 + }, + { + "epoch": 7.43, + "learning_rate": 9.27676090691213e-06, + "loss": 6.0447, + "step": 351000 + }, + { + "epoch": 7.44, + "learning_rate": 9.275700439033702e-06, + "loss": 6.0434, + "step": 351500 + }, + { + "epoch": 7.45, + "learning_rate": 9.274639971155274e-06, + "loss": 6.0461, + "step": 352000 + }, + { + "epoch": 7.46, + "learning_rate": 9.273579503276846e-06, + "loss": 6.0484, + "step": 352500 + }, + { + "epoch": 7.47, + "learning_rate": 9.272519035398418e-06, + "loss": 6.0459, + "step": 353000 + }, + { + "epoch": 7.48, + "learning_rate": 9.27145856751999e-06, + "loss": 6.0462, + "step": 353500 + }, + { + "epoch": 7.49, + "learning_rate": 9.270398099641562e-06, + "loss": 6.0465, + "step": 354000 + }, + { + "epoch": 7.5, + "learning_rate": 9.269337631763134e-06, + "loss": 6.0414, + "step": 354500 + }, + { + "epoch": 7.51, + "learning_rate": 9.268277163884707e-06, + "loss": 6.0391, + "step": 355000 + }, + { + "epoch": 7.52, + "learning_rate": 9.267216696006279e-06, + "loss": 6.0469, + "step": 355500 + }, + { + "epoch": 7.53, + "learning_rate": 9.26615622812785e-06, + "loss": 6.0432, + "step": 356000 + }, + { + "epoch": 7.55, + "learning_rate": 9.265095760249423e-06, + "loss": 6.0416, + "step": 356500 + }, + { + "epoch": 7.56, + "learning_rate": 9.264035292370995e-06, + "loss": 6.0477, + "step": 357000 + }, + { + "epoch": 7.57, + "learning_rate": 9.262974824492567e-06, + "loss": 6.0441, + "step": 357500 + }, + { + "epoch": 7.58, + "learning_rate": 9.261914356614139e-06, + "loss": 6.0412, + "step": 358000 + }, + { + "epoch": 7.59, + "learning_rate": 9.260853888735711e-06, + "loss": 6.044, + "step": 358500 + }, + { + "epoch": 7.6, + "learning_rate": 9.259793420857283e-06, + "loss": 6.0427, + "step": 359000 + }, + { + "epoch": 7.61, + "learning_rate": 9.258732952978855e-06, + "loss": 6.0431, + "step": 359500 + }, + { + "epoch": 7.62, + "learning_rate": 9.257672485100427e-06, + "loss": 6.0415, + "step": 360000 + }, + { + "epoch": 7.63, + "learning_rate": 9.256612017222e-06, + "loss": 6.0387, + "step": 360500 + }, + { + "epoch": 7.64, + "learning_rate": 9.255551549343571e-06, + "loss": 6.0421, + "step": 361000 + }, + { + "epoch": 7.65, + "learning_rate": 9.254491081465143e-06, + "loss": 6.0408, + "step": 361500 + }, + { + "epoch": 7.66, + "learning_rate": 9.253430613586715e-06, + "loss": 6.0408, + "step": 362000 + }, + { + "epoch": 7.67, + "learning_rate": 9.252370145708287e-06, + "loss": 6.039, + "step": 362500 + }, + { + "epoch": 7.68, + "learning_rate": 9.25130967782986e-06, + "loss": 6.0395, + "step": 363000 + }, + { + "epoch": 7.69, + "learning_rate": 9.250249209951432e-06, + "loss": 6.0388, + "step": 363500 + }, + { + "epoch": 7.7, + "learning_rate": 9.249188742073004e-06, + "loss": 6.0412, + "step": 364000 + }, + { + "epoch": 7.71, + "learning_rate": 9.248128274194576e-06, + "loss": 6.0398, + "step": 364500 + }, + { + "epoch": 7.73, + "learning_rate": 9.247067806316148e-06, + "loss": 6.0381, + "step": 365000 + }, + { + "epoch": 7.74, + "learning_rate": 9.24600733843772e-06, + "loss": 6.0389, + "step": 365500 + }, + { + "epoch": 7.75, + "learning_rate": 9.244946870559292e-06, + "loss": 6.0383, + "step": 366000 + }, + { + "epoch": 7.76, + "learning_rate": 9.243886402680864e-06, + "loss": 6.0423, + "step": 366500 + }, + { + "epoch": 7.77, + "learning_rate": 9.242825934802436e-06, + "loss": 6.0423, + "step": 367000 + }, + { + "epoch": 7.78, + "learning_rate": 9.241765466924008e-06, + "loss": 6.0385, + "step": 367500 + }, + { + "epoch": 7.79, + "learning_rate": 9.24070499904558e-06, + "loss": 6.0365, + "step": 368000 + }, + { + "epoch": 7.8, + "learning_rate": 9.23964453116715e-06, + "loss": 6.0376, + "step": 368500 + }, + { + "epoch": 7.81, + "learning_rate": 9.238584063288724e-06, + "loss": 6.0404, + "step": 369000 + }, + { + "epoch": 7.82, + "learning_rate": 9.237523595410296e-06, + "loss": 6.0381, + "step": 369500 + }, + { + "epoch": 7.83, + "learning_rate": 9.236463127531868e-06, + "loss": 6.0401, + "step": 370000 + }, + { + "epoch": 7.84, + "learning_rate": 9.23540265965344e-06, + "loss": 6.0372, + "step": 370500 + }, + { + "epoch": 7.85, + "learning_rate": 9.234342191775012e-06, + "loss": 6.0392, + "step": 371000 + }, + { + "epoch": 7.86, + "learning_rate": 9.233281723896584e-06, + "loss": 6.0373, + "step": 371500 + }, + { + "epoch": 7.87, + "learning_rate": 9.232221256018156e-06, + "loss": 6.0373, + "step": 372000 + }, + { + "epoch": 7.88, + "learning_rate": 9.231160788139729e-06, + "loss": 6.037, + "step": 372500 + }, + { + "epoch": 7.89, + "learning_rate": 9.2301003202613e-06, + "loss": 6.0372, + "step": 373000 + }, + { + "epoch": 7.9, + "learning_rate": 9.229039852382871e-06, + "loss": 6.0364, + "step": 373500 + }, + { + "epoch": 7.92, + "learning_rate": 9.227979384504445e-06, + "loss": 6.0365, + "step": 374000 + }, + { + "epoch": 7.93, + "learning_rate": 9.226918916626017e-06, + "loss": 6.0362, + "step": 374500 + }, + { + "epoch": 7.94, + "learning_rate": 9.225858448747587e-06, + "loss": 6.0356, + "step": 375000 + }, + { + "epoch": 7.95, + "learning_rate": 9.224797980869161e-06, + "loss": 6.038, + "step": 375500 + }, + { + "epoch": 7.96, + "learning_rate": 9.223737512990733e-06, + "loss": 6.0385, + "step": 376000 + }, + { + "epoch": 7.97, + "learning_rate": 9.222677045112303e-06, + "loss": 6.0382, + "step": 376500 + }, + { + "epoch": 7.98, + "learning_rate": 9.221616577233875e-06, + "loss": 6.0364, + "step": 377000 + }, + { + "epoch": 7.99, + "learning_rate": 9.220556109355449e-06, + "loss": 6.0379, + "step": 377500 + }, + { + "epoch": 8.0, + "learning_rate": 9.219495641477021e-06, + "loss": 6.0407, + "step": 378000 + }, + { + "epoch": 8.01, + "learning_rate": 9.218435173598592e-06, + "loss": 6.0372, + "step": 378500 + }, + { + "epoch": 8.02, + "learning_rate": 9.217374705720165e-06, + "loss": 6.0367, + "step": 379000 + }, + { + "epoch": 8.03, + "learning_rate": 9.216314237841737e-06, + "loss": 6.0362, + "step": 379500 + }, + { + "epoch": 8.04, + "learning_rate": 9.215253769963308e-06, + "loss": 6.0324, + "step": 380000 + }, + { + "epoch": 8.05, + "learning_rate": 9.214193302084881e-06, + "loss": 6.0333, + "step": 380500 + }, + { + "epoch": 8.06, + "learning_rate": 9.213132834206454e-06, + "loss": 6.0324, + "step": 381000 + }, + { + "epoch": 8.07, + "learning_rate": 9.212072366328024e-06, + "loss": 6.035, + "step": 381500 + }, + { + "epoch": 8.08, + "learning_rate": 9.211011898449596e-06, + "loss": 6.037, + "step": 382000 + }, + { + "epoch": 8.1, + "learning_rate": 9.20995143057117e-06, + "loss": 6.0343, + "step": 382500 + }, + { + "epoch": 8.11, + "learning_rate": 9.20889096269274e-06, + "loss": 6.0347, + "step": 383000 + }, + { + "epoch": 8.12, + "learning_rate": 9.207830494814312e-06, + "loss": 6.0349, + "step": 383500 + }, + { + "epoch": 8.13, + "learning_rate": 9.206770026935886e-06, + "loss": 6.0339, + "step": 384000 + }, + { + "epoch": 8.14, + "learning_rate": 9.205709559057458e-06, + "loss": 6.0342, + "step": 384500 + }, + { + "epoch": 8.15, + "learning_rate": 9.204649091179028e-06, + "loss": 6.0344, + "step": 385000 + }, + { + "epoch": 8.16, + "learning_rate": 9.2035886233006e-06, + "loss": 6.0336, + "step": 385500 + }, + { + "epoch": 8.17, + "learning_rate": 9.202528155422174e-06, + "loss": 6.0388, + "step": 386000 + }, + { + "epoch": 8.18, + "learning_rate": 9.201467687543744e-06, + "loss": 6.0316, + "step": 386500 + }, + { + "epoch": 8.19, + "learning_rate": 9.200407219665316e-06, + "loss": 6.0341, + "step": 387000 + }, + { + "epoch": 8.2, + "learning_rate": 9.19934675178689e-06, + "loss": 6.0345, + "step": 387500 + }, + { + "epoch": 8.21, + "learning_rate": 9.19828628390846e-06, + "loss": 6.0363, + "step": 388000 + }, + { + "epoch": 8.22, + "learning_rate": 9.197225816030033e-06, + "loss": 6.036, + "step": 388500 + }, + { + "epoch": 8.23, + "learning_rate": 9.196165348151605e-06, + "loss": 6.0343, + "step": 389000 + }, + { + "epoch": 8.24, + "learning_rate": 9.195104880273177e-06, + "loss": 6.0325, + "step": 389500 + }, + { + "epoch": 8.25, + "learning_rate": 9.194044412394749e-06, + "loss": 6.0355, + "step": 390000 + }, + { + "epoch": 8.26, + "learning_rate": 9.192983944516321e-06, + "loss": 6.0325, + "step": 390500 + }, + { + "epoch": 8.28, + "learning_rate": 9.191923476637893e-06, + "loss": 6.0352, + "step": 391000 + }, + { + "epoch": 8.29, + "learning_rate": 9.190863008759465e-06, + "loss": 6.0333, + "step": 391500 + }, + { + "epoch": 8.3, + "learning_rate": 9.189802540881037e-06, + "loss": 6.0359, + "step": 392000 + }, + { + "epoch": 8.31, + "learning_rate": 9.18874207300261e-06, + "loss": 6.0377, + "step": 392500 + }, + { + "epoch": 8.32, + "learning_rate": 9.187681605124181e-06, + "loss": 6.0348, + "step": 393000 + }, + { + "epoch": 8.33, + "learning_rate": 9.186621137245753e-06, + "loss": 6.0316, + "step": 393500 + }, + { + "epoch": 8.34, + "learning_rate": 9.185560669367325e-06, + "loss": 6.0305, + "step": 394000 + }, + { + "epoch": 8.35, + "learning_rate": 9.184500201488897e-06, + "loss": 6.035, + "step": 394500 + }, + { + "epoch": 8.36, + "learning_rate": 9.18343973361047e-06, + "loss": 6.0386, + "step": 395000 + }, + { + "epoch": 8.37, + "learning_rate": 9.182379265732041e-06, + "loss": 6.0312, + "step": 395500 + }, + { + "epoch": 8.38, + "learning_rate": 9.181318797853614e-06, + "loss": 6.0271, + "step": 396000 + }, + { + "epoch": 8.39, + "learning_rate": 9.180258329975186e-06, + "loss": 6.0297, + "step": 396500 + }, + { + "epoch": 8.4, + "learning_rate": 9.179197862096758e-06, + "loss": 6.0327, + "step": 397000 + }, + { + "epoch": 8.41, + "learning_rate": 9.17813739421833e-06, + "loss": 6.0309, + "step": 397500 + }, + { + "epoch": 8.42, + "learning_rate": 9.177076926339902e-06, + "loss": 6.032, + "step": 398000 + }, + { + "epoch": 8.43, + "learning_rate": 9.176016458461474e-06, + "loss": 6.0291, + "step": 398500 + }, + { + "epoch": 8.44, + "learning_rate": 9.174955990583046e-06, + "loss": 6.0302, + "step": 399000 + }, + { + "epoch": 8.46, + "learning_rate": 9.173895522704618e-06, + "loss": 6.0347, + "step": 399500 + }, + { + "epoch": 8.47, + "learning_rate": 9.17283505482619e-06, + "loss": 6.0309, + "step": 400000 + }, + { + "epoch": 8.48, + "learning_rate": 9.171774586947762e-06, + "loss": 6.033, + "step": 400500 + }, + { + "epoch": 8.49, + "learning_rate": 9.170714119069334e-06, + "loss": 6.0328, + "step": 401000 + }, + { + "epoch": 8.5, + "learning_rate": 9.169653651190906e-06, + "loss": 6.0347, + "step": 401500 + }, + { + "epoch": 8.51, + "learning_rate": 9.168593183312478e-06, + "loss": 6.0281, + "step": 402000 + }, + { + "epoch": 8.52, + "learning_rate": 9.16753271543405e-06, + "loss": 6.0292, + "step": 402500 + }, + { + "epoch": 8.53, + "learning_rate": 9.166472247555622e-06, + "loss": 6.03, + "step": 403000 + }, + { + "epoch": 8.54, + "learning_rate": 9.165411779677194e-06, + "loss": 6.0273, + "step": 403500 + }, + { + "epoch": 8.55, + "learning_rate": 9.164351311798766e-06, + "loss": 6.0329, + "step": 404000 + }, + { + "epoch": 8.56, + "learning_rate": 9.163290843920338e-06, + "loss": 6.0296, + "step": 404500 + }, + { + "epoch": 8.57, + "learning_rate": 9.16223037604191e-06, + "loss": 6.0303, + "step": 405000 + }, + { + "epoch": 8.58, + "learning_rate": 9.161169908163483e-06, + "loss": 6.0318, + "step": 405500 + }, + { + "epoch": 8.59, + "learning_rate": 9.160109440285055e-06, + "loss": 6.0308, + "step": 406000 + }, + { + "epoch": 8.6, + "learning_rate": 9.159048972406627e-06, + "loss": 6.0237, + "step": 406500 + }, + { + "epoch": 8.61, + "learning_rate": 9.157988504528199e-06, + "loss": 6.0308, + "step": 407000 + }, + { + "epoch": 8.62, + "learning_rate": 9.15692803664977e-06, + "loss": 6.0298, + "step": 407500 + }, + { + "epoch": 8.64, + "learning_rate": 9.155867568771343e-06, + "loss": 6.0314, + "step": 408000 + }, + { + "epoch": 8.65, + "learning_rate": 9.154807100892915e-06, + "loss": 6.0284, + "step": 408500 + }, + { + "epoch": 8.66, + "learning_rate": 9.153746633014487e-06, + "loss": 6.0326, + "step": 409000 + }, + { + "epoch": 8.67, + "learning_rate": 9.152686165136059e-06, + "loss": 6.0329, + "step": 409500 + }, + { + "epoch": 8.68, + "learning_rate": 9.151625697257631e-06, + "loss": 6.0276, + "step": 410000 + }, + { + "epoch": 8.69, + "learning_rate": 9.150565229379203e-06, + "loss": 6.032, + "step": 410500 + }, + { + "epoch": 8.7, + "learning_rate": 9.149504761500775e-06, + "loss": 6.0287, + "step": 411000 + }, + { + "epoch": 8.71, + "learning_rate": 9.148444293622347e-06, + "loss": 6.0267, + "step": 411500 + }, + { + "epoch": 8.72, + "learning_rate": 9.147383825743918e-06, + "loss": 6.0255, + "step": 412000 + }, + { + "epoch": 8.73, + "learning_rate": 9.146323357865491e-06, + "loss": 6.0271, + "step": 412500 + }, + { + "epoch": 8.74, + "learning_rate": 9.145262889987063e-06, + "loss": 6.0259, + "step": 413000 + }, + { + "epoch": 8.75, + "learning_rate": 9.144202422108636e-06, + "loss": 6.0308, + "step": 413500 + }, + { + "epoch": 8.76, + "learning_rate": 9.143141954230208e-06, + "loss": 6.0305, + "step": 414000 + }, + { + "epoch": 8.77, + "learning_rate": 9.14208148635178e-06, + "loss": 6.0263, + "step": 414500 + }, + { + "epoch": 8.78, + "learning_rate": 9.141021018473352e-06, + "loss": 6.0284, + "step": 415000 + }, + { + "epoch": 8.79, + "learning_rate": 9.139960550594924e-06, + "loss": 6.0256, + "step": 415500 + }, + { + "epoch": 8.8, + "learning_rate": 9.138900082716496e-06, + "loss": 6.0315, + "step": 416000 + }, + { + "epoch": 8.82, + "learning_rate": 9.137839614838068e-06, + "loss": 6.0295, + "step": 416500 + }, + { + "epoch": 8.83, + "learning_rate": 9.136779146959638e-06, + "loss": 6.0257, + "step": 417000 + }, + { + "epoch": 8.84, + "learning_rate": 9.135718679081212e-06, + "loss": 6.0268, + "step": 417500 + }, + { + "epoch": 8.85, + "learning_rate": 9.134658211202784e-06, + "loss": 6.0312, + "step": 418000 + }, + { + "epoch": 8.86, + "learning_rate": 9.133597743324354e-06, + "loss": 6.0263, + "step": 418500 + }, + { + "epoch": 8.87, + "learning_rate": 9.132537275445928e-06, + "loss": 6.0255, + "step": 419000 + }, + { + "epoch": 8.88, + "learning_rate": 9.1314768075675e-06, + "loss": 6.0262, + "step": 419500 + }, + { + "epoch": 8.89, + "learning_rate": 9.13041633968907e-06, + "loss": 6.0235, + "step": 420000 + }, + { + "epoch": 8.9, + "learning_rate": 9.129355871810643e-06, + "loss": 6.0297, + "step": 420500 + }, + { + "epoch": 8.91, + "learning_rate": 9.128295403932216e-06, + "loss": 6.0231, + "step": 421000 + }, + { + "epoch": 8.92, + "learning_rate": 9.127234936053788e-06, + "loss": 6.0269, + "step": 421500 + }, + { + "epoch": 8.93, + "learning_rate": 9.126174468175359e-06, + "loss": 6.0246, + "step": 422000 + }, + { + "epoch": 8.94, + "learning_rate": 9.125114000296933e-06, + "loss": 6.0248, + "step": 422500 + }, + { + "epoch": 8.95, + "learning_rate": 9.124053532418505e-06, + "loss": 6.0216, + "step": 423000 + }, + { + "epoch": 8.96, + "learning_rate": 9.122993064540075e-06, + "loss": 6.0235, + "step": 423500 + }, + { + "epoch": 8.97, + "learning_rate": 9.121932596661649e-06, + "loss": 6.0274, + "step": 424000 + }, + { + "epoch": 8.98, + "learning_rate": 9.12087212878322e-06, + "loss": 6.0247, + "step": 424500 + }, + { + "epoch": 8.99, + "learning_rate": 9.119811660904791e-06, + "loss": 6.0222, + "step": 425000 + }, + { + "epoch": 9.01, + "learning_rate": 9.118751193026363e-06, + "loss": 6.0278, + "step": 425500 + }, + { + "epoch": 9.02, + "learning_rate": 9.117690725147937e-06, + "loss": 6.0266, + "step": 426000 + }, + { + "epoch": 9.03, + "learning_rate": 9.116630257269507e-06, + "loss": 6.0227, + "step": 426500 + }, + { + "epoch": 9.04, + "learning_rate": 9.11556978939108e-06, + "loss": 6.0205, + "step": 427000 + }, + { + "epoch": 9.05, + "learning_rate": 9.114509321512653e-06, + "loss": 6.0257, + "step": 427500 + }, + { + "epoch": 9.06, + "learning_rate": 9.113448853634225e-06, + "loss": 6.0231, + "step": 428000 + }, + { + "epoch": 9.07, + "learning_rate": 9.112388385755796e-06, + "loss": 6.025, + "step": 428500 + }, + { + "epoch": 9.08, + "learning_rate": 9.111327917877368e-06, + "loss": 6.0185, + "step": 429000 + }, + { + "epoch": 9.09, + "learning_rate": 9.110267449998941e-06, + "loss": 6.0234, + "step": 429500 + }, + { + "epoch": 9.1, + "learning_rate": 9.109206982120512e-06, + "loss": 6.0257, + "step": 430000 + }, + { + "epoch": 9.11, + "learning_rate": 9.108146514242084e-06, + "loss": 6.0191, + "step": 430500 + }, + { + "epoch": 9.12, + "learning_rate": 9.107086046363658e-06, + "loss": 6.0204, + "step": 431000 + }, + { + "epoch": 9.13, + "learning_rate": 9.106025578485228e-06, + "loss": 6.0248, + "step": 431500 + }, + { + "epoch": 9.14, + "learning_rate": 9.1049651106068e-06, + "loss": 6.0223, + "step": 432000 + }, + { + "epoch": 9.15, + "learning_rate": 9.103904642728372e-06, + "loss": 6.0281, + "step": 432500 + }, + { + "epoch": 9.16, + "learning_rate": 9.102844174849944e-06, + "loss": 6.0255, + "step": 433000 + }, + { + "epoch": 9.17, + "learning_rate": 9.101783706971516e-06, + "loss": 6.0223, + "step": 433500 + }, + { + "epoch": 9.19, + "learning_rate": 9.100723239093088e-06, + "loss": 6.0256, + "step": 434000 + }, + { + "epoch": 9.2, + "learning_rate": 9.09966277121466e-06, + "loss": 6.0239, + "step": 434500 + }, + { + "epoch": 9.21, + "learning_rate": 9.098602303336232e-06, + "loss": 6.0227, + "step": 435000 + }, + { + "epoch": 9.22, + "learning_rate": 9.097541835457804e-06, + "loss": 6.0183, + "step": 435500 + }, + { + "epoch": 9.23, + "learning_rate": 9.096481367579378e-06, + "loss": 6.0258, + "step": 436000 + }, + { + "epoch": 9.24, + "learning_rate": 9.095420899700948e-06, + "loss": 6.0231, + "step": 436500 + }, + { + "epoch": 9.25, + "learning_rate": 9.09436043182252e-06, + "loss": 6.0232, + "step": 437000 + }, + { + "epoch": 9.26, + "learning_rate": 9.093299963944093e-06, + "loss": 6.0208, + "step": 437500 + }, + { + "epoch": 9.27, + "learning_rate": 9.092239496065665e-06, + "loss": 6.0211, + "step": 438000 + }, + { + "epoch": 9.28, + "learning_rate": 9.091179028187237e-06, + "loss": 6.0197, + "step": 438500 + }, + { + "epoch": 9.29, + "learning_rate": 9.090118560308809e-06, + "loss": 6.0237, + "step": 439000 + }, + { + "epoch": 9.3, + "learning_rate": 9.08905809243038e-06, + "loss": 6.0208, + "step": 439500 + }, + { + "epoch": 9.31, + "learning_rate": 9.087997624551953e-06, + "loss": 6.0215, + "step": 440000 + }, + { + "epoch": 9.32, + "learning_rate": 9.086937156673525e-06, + "loss": 6.0204, + "step": 440500 + }, + { + "epoch": 9.33, + "learning_rate": 9.085876688795097e-06, + "loss": 6.0219, + "step": 441000 + }, + { + "epoch": 9.34, + "learning_rate": 9.084816220916669e-06, + "loss": 6.0222, + "step": 441500 + }, + { + "epoch": 9.35, + "learning_rate": 9.083755753038241e-06, + "loss": 6.0221, + "step": 442000 + }, + { + "epoch": 9.37, + "learning_rate": 9.082695285159813e-06, + "loss": 6.0184, + "step": 442500 + }, + { + "epoch": 9.38, + "learning_rate": 9.081634817281385e-06, + "loss": 6.018, + "step": 443000 + }, + { + "epoch": 9.39, + "learning_rate": 9.080574349402957e-06, + "loss": 6.019, + "step": 443500 + }, + { + "epoch": 9.4, + "learning_rate": 9.07951388152453e-06, + "loss": 6.0176, + "step": 444000 + }, + { + "epoch": 9.41, + "learning_rate": 9.078453413646101e-06, + "loss": 6.0192, + "step": 444500 + }, + { + "epoch": 9.42, + "learning_rate": 9.077392945767673e-06, + "loss": 6.0221, + "step": 445000 + }, + { + "epoch": 9.43, + "learning_rate": 9.076332477889245e-06, + "loss": 6.0223, + "step": 445500 + }, + { + "epoch": 9.44, + "learning_rate": 9.075272010010818e-06, + "loss": 6.0215, + "step": 446000 + }, + { + "epoch": 9.45, + "learning_rate": 9.07421154213239e-06, + "loss": 6.0222, + "step": 446500 + }, + { + "epoch": 9.46, + "learning_rate": 9.073151074253962e-06, + "loss": 6.0205, + "step": 447000 + }, + { + "epoch": 9.47, + "learning_rate": 9.072090606375534e-06, + "loss": 6.0181, + "step": 447500 + }, + { + "epoch": 9.48, + "learning_rate": 9.071030138497106e-06, + "loss": 6.0178, + "step": 448000 + }, + { + "epoch": 9.49, + "learning_rate": 9.069969670618678e-06, + "loss": 6.0239, + "step": 448500 + }, + { + "epoch": 9.5, + "learning_rate": 9.06890920274025e-06, + "loss": 6.0262, + "step": 449000 + }, + { + "epoch": 9.51, + "learning_rate": 9.067848734861822e-06, + "loss": 6.018, + "step": 449500 + }, + { + "epoch": 9.52, + "learning_rate": 9.066788266983394e-06, + "loss": 6.0219, + "step": 450000 + }, + { + "epoch": 9.53, + "learning_rate": 9.065727799104966e-06, + "loss": 6.0179, + "step": 450500 + }, + { + "epoch": 9.55, + "learning_rate": 9.064667331226538e-06, + "loss": 6.0201, + "step": 451000 + }, + { + "epoch": 9.56, + "learning_rate": 9.06360686334811e-06, + "loss": 6.0213, + "step": 451500 + }, + { + "epoch": 9.57, + "learning_rate": 9.062546395469682e-06, + "loss": 6.0203, + "step": 452000 + }, + { + "epoch": 9.58, + "learning_rate": 9.061485927591254e-06, + "loss": 6.0161, + "step": 452500 + }, + { + "epoch": 9.59, + "learning_rate": 9.060425459712826e-06, + "loss": 6.0171, + "step": 453000 + }, + { + "epoch": 9.6, + "learning_rate": 9.059364991834398e-06, + "loss": 6.0205, + "step": 453500 + }, + { + "epoch": 9.61, + "learning_rate": 9.05830452395597e-06, + "loss": 6.0209, + "step": 454000 + }, + { + "epoch": 9.62, + "learning_rate": 9.057244056077542e-06, + "loss": 6.0198, + "step": 454500 + }, + { + "epoch": 9.63, + "learning_rate": 9.056183588199115e-06, + "loss": 6.0154, + "step": 455000 + }, + { + "epoch": 9.64, + "learning_rate": 9.055123120320685e-06, + "loss": 6.0165, + "step": 455500 + }, + { + "epoch": 9.65, + "learning_rate": 9.054062652442259e-06, + "loss": 6.0154, + "step": 456000 + }, + { + "epoch": 9.66, + "learning_rate": 9.05300218456383e-06, + "loss": 6.0178, + "step": 456500 + }, + { + "epoch": 9.67, + "learning_rate": 9.051941716685403e-06, + "loss": 6.015, + "step": 457000 + }, + { + "epoch": 9.68, + "learning_rate": 9.050881248806975e-06, + "loss": 6.0154, + "step": 457500 + }, + { + "epoch": 9.69, + "learning_rate": 9.049820780928547e-06, + "loss": 6.0189, + "step": 458000 + }, + { + "epoch": 9.7, + "learning_rate": 9.048760313050119e-06, + "loss": 6.0187, + "step": 458500 + }, + { + "epoch": 9.71, + "learning_rate": 9.047699845171691e-06, + "loss": 6.0191, + "step": 459000 + }, + { + "epoch": 9.73, + "learning_rate": 9.046639377293263e-06, + "loss": 6.0168, + "step": 459500 + }, + { + "epoch": 9.74, + "learning_rate": 9.045578909414835e-06, + "loss": 6.0174, + "step": 460000 + }, + { + "epoch": 9.75, + "learning_rate": 9.044518441536405e-06, + "loss": 6.0153, + "step": 460500 + }, + { + "epoch": 9.76, + "learning_rate": 9.04345797365798e-06, + "loss": 6.0162, + "step": 461000 + }, + { + "epoch": 9.77, + "learning_rate": 9.042397505779551e-06, + "loss": 6.0147, + "step": 461500 + }, + { + "epoch": 9.78, + "learning_rate": 9.041337037901122e-06, + "loss": 6.0142, + "step": 462000 + }, + { + "epoch": 9.79, + "learning_rate": 9.040276570022695e-06, + "loss": 6.0129, + "step": 462500 + }, + { + "epoch": 9.8, + "learning_rate": 9.039216102144267e-06, + "loss": 6.0172, + "step": 463000 + }, + { + "epoch": 9.81, + "learning_rate": 9.038155634265838e-06, + "loss": 6.0161, + "step": 463500 + }, + { + "epoch": 9.82, + "learning_rate": 9.03709516638741e-06, + "loss": 6.0169, + "step": 464000 + }, + { + "epoch": 9.83, + "learning_rate": 9.036034698508984e-06, + "loss": 6.0168, + "step": 464500 + }, + { + "epoch": 9.84, + "learning_rate": 9.034974230630556e-06, + "loss": 6.008, + "step": 465000 + }, + { + "epoch": 9.85, + "learning_rate": 9.033913762752126e-06, + "loss": 6.0144, + "step": 465500 + }, + { + "epoch": 9.86, + "learning_rate": 9.0328532948737e-06, + "loss": 6.0143, + "step": 466000 + }, + { + "epoch": 9.87, + "learning_rate": 9.031792826995272e-06, + "loss": 6.0148, + "step": 466500 + }, + { + "epoch": 9.88, + "learning_rate": 9.030732359116842e-06, + "loss": 6.0109, + "step": 467000 + }, + { + "epoch": 9.89, + "learning_rate": 9.029671891238416e-06, + "loss": 6.0129, + "step": 467500 + }, + { + "epoch": 9.9, + "learning_rate": 9.028611423359988e-06, + "loss": 6.0178, + "step": 468000 + }, + { + "epoch": 9.92, + "learning_rate": 9.027550955481558e-06, + "loss": 6.0156, + "step": 468500 + }, + { + "epoch": 9.93, + "learning_rate": 9.02649048760313e-06, + "loss": 6.0119, + "step": 469000 + }, + { + "epoch": 9.94, + "learning_rate": 9.025430019724704e-06, + "loss": 6.0161, + "step": 469500 + }, + { + "epoch": 9.95, + "learning_rate": 9.024369551846275e-06, + "loss": 6.0108, + "step": 470000 + }, + { + "epoch": 9.96, + "learning_rate": 9.023309083967847e-06, + "loss": 6.0099, + "step": 470500 + }, + { + "epoch": 9.97, + "learning_rate": 9.02224861608942e-06, + "loss": 6.0153, + "step": 471000 + }, + { + "epoch": 9.98, + "learning_rate": 9.021188148210992e-06, + "loss": 6.0086, + "step": 471500 + }, + { + "epoch": 9.99, + "learning_rate": 9.020127680332563e-06, + "loss": 6.0108, + "step": 472000 + }, + { + "epoch": 10.0, + "learning_rate": 9.019067212454135e-06, + "loss": 6.0098, + "step": 472500 + }, + { + "epoch": 10.01, + "learning_rate": 9.018006744575709e-06, + "loss": 6.0068, + "step": 473000 + }, + { + "epoch": 10.02, + "learning_rate": 9.016946276697279e-06, + "loss": 6.0131, + "step": 473500 + }, + { + "epoch": 10.03, + "learning_rate": 9.015885808818851e-06, + "loss": 6.008, + "step": 474000 + }, + { + "epoch": 10.04, + "learning_rate": 9.014825340940425e-06, + "loss": 6.0108, + "step": 474500 + }, + { + "epoch": 10.05, + "learning_rate": 9.013764873061995e-06, + "loss": 6.0126, + "step": 475000 + }, + { + "epoch": 10.06, + "learning_rate": 9.012704405183567e-06, + "loss": 6.0092, + "step": 475500 + }, + { + "epoch": 10.07, + "learning_rate": 9.01164393730514e-06, + "loss": 6.0048, + "step": 476000 + }, + { + "epoch": 10.08, + "learning_rate": 9.010583469426711e-06, + "loss": 6.0082, + "step": 476500 + }, + { + "epoch": 10.1, + "learning_rate": 9.009523001548283e-06, + "loss": 6.0058, + "step": 477000 + }, + { + "epoch": 10.11, + "learning_rate": 9.008462533669855e-06, + "loss": 6.0048, + "step": 477500 + }, + { + "epoch": 10.12, + "learning_rate": 9.007402065791427e-06, + "loss": 6.0039, + "step": 478000 + }, + { + "epoch": 10.13, + "learning_rate": 9.006341597913e-06, + "loss": 6.0052, + "step": 478500 + }, + { + "epoch": 10.14, + "learning_rate": 9.005281130034572e-06, + "loss": 6.006, + "step": 479000 + }, + { + "epoch": 10.15, + "learning_rate": 9.004220662156145e-06, + "loss": 6.01, + "step": 479500 + }, + { + "epoch": 10.16, + "learning_rate": 9.003160194277716e-06, + "loss": 6.0052, + "step": 480000 + }, + { + "epoch": 10.17, + "learning_rate": 9.002099726399288e-06, + "loss": 6.0022, + "step": 480500 + }, + { + "epoch": 10.18, + "learning_rate": 9.00103925852086e-06, + "loss": 6.0026, + "step": 481000 + }, + { + "epoch": 10.19, + "learning_rate": 8.999978790642432e-06, + "loss": 6.0048, + "step": 481500 + }, + { + "epoch": 10.2, + "learning_rate": 8.998918322764004e-06, + "loss": 6.0032, + "step": 482000 + }, + { + "epoch": 10.21, + "learning_rate": 8.997857854885576e-06, + "loss": 6.0012, + "step": 482500 + }, + { + "epoch": 10.22, + "learning_rate": 8.996797387007148e-06, + "loss": 6.0052, + "step": 483000 + }, + { + "epoch": 10.23, + "learning_rate": 8.99573691912872e-06, + "loss": 6.0009, + "step": 483500 + }, + { + "epoch": 10.24, + "learning_rate": 8.994676451250292e-06, + "loss": 6.003, + "step": 484000 + }, + { + "epoch": 10.25, + "learning_rate": 8.993615983371864e-06, + "loss": 6.0032, + "step": 484500 + }, + { + "epoch": 10.26, + "learning_rate": 8.992555515493436e-06, + "loss": 6.0036, + "step": 485000 + }, + { + "epoch": 10.28, + "learning_rate": 8.991495047615008e-06, + "loss": 6.0009, + "step": 485500 + }, + { + "epoch": 10.29, + "learning_rate": 8.99043457973658e-06, + "loss": 6.0007, + "step": 486000 + }, + { + "epoch": 10.3, + "learning_rate": 8.989374111858152e-06, + "loss": 6.0021, + "step": 486500 + }, + { + "epoch": 10.31, + "learning_rate": 8.988313643979724e-06, + "loss": 5.9972, + "step": 487000 + }, + { + "epoch": 10.32, + "learning_rate": 8.987253176101297e-06, + "loss": 5.9948, + "step": 487500 + }, + { + "epoch": 10.33, + "learning_rate": 8.986192708222869e-06, + "loss": 5.997, + "step": 488000 + }, + { + "epoch": 10.34, + "learning_rate": 8.98513224034444e-06, + "loss": 5.9987, + "step": 488500 + }, + { + "epoch": 10.35, + "learning_rate": 8.984071772466013e-06, + "loss": 5.9978, + "step": 489000 + }, + { + "epoch": 10.36, + "learning_rate": 8.983011304587585e-06, + "loss": 5.9947, + "step": 489500 + }, + { + "epoch": 10.37, + "learning_rate": 8.981950836709157e-06, + "loss": 5.9994, + "step": 490000 + }, + { + "epoch": 10.38, + "learning_rate": 8.980890368830729e-06, + "loss": 5.9987, + "step": 490500 + }, + { + "epoch": 10.39, + "learning_rate": 8.979829900952301e-06, + "loss": 5.9907, + "step": 491000 + }, + { + "epoch": 10.4, + "learning_rate": 8.978769433073873e-06, + "loss": 5.9953, + "step": 491500 + }, + { + "epoch": 10.41, + "learning_rate": 8.977708965195445e-06, + "loss": 5.9967, + "step": 492000 + }, + { + "epoch": 10.42, + "learning_rate": 8.976648497317017e-06, + "loss": 5.9963, + "step": 492500 + }, + { + "epoch": 10.43, + "learning_rate": 8.97558802943859e-06, + "loss": 5.9926, + "step": 493000 + }, + { + "epoch": 10.44, + "learning_rate": 8.974527561560161e-06, + "loss": 5.9939, + "step": 493500 + }, + { + "epoch": 10.46, + "learning_rate": 8.973467093681733e-06, + "loss": 5.9936, + "step": 494000 + }, + { + "epoch": 10.47, + "learning_rate": 8.972406625803305e-06, + "loss": 5.9949, + "step": 494500 + }, + { + "epoch": 10.48, + "learning_rate": 8.971346157924877e-06, + "loss": 5.9926, + "step": 495000 + }, + { + "epoch": 10.49, + "learning_rate": 8.97028569004645e-06, + "loss": 5.9918, + "step": 495500 + }, + { + "epoch": 10.5, + "learning_rate": 8.969225222168022e-06, + "loss": 5.9883, + "step": 496000 + }, + { + "epoch": 10.51, + "learning_rate": 8.968164754289594e-06, + "loss": 5.9913, + "step": 496500 + }, + { + "epoch": 10.52, + "learning_rate": 8.967104286411166e-06, + "loss": 5.9921, + "step": 497000 + }, + { + "epoch": 10.53, + "learning_rate": 8.966043818532738e-06, + "loss": 5.9869, + "step": 497500 + }, + { + "epoch": 10.54, + "learning_rate": 8.96498335065431e-06, + "loss": 5.9932, + "step": 498000 + }, + { + "epoch": 10.55, + "learning_rate": 8.963922882775882e-06, + "loss": 5.9876, + "step": 498500 + }, + { + "epoch": 10.56, + "learning_rate": 8.962862414897452e-06, + "loss": 5.9893, + "step": 499000 + }, + { + "epoch": 10.57, + "learning_rate": 8.961801947019026e-06, + "loss": 5.9898, + "step": 499500 + }, + { + "epoch": 10.58, + "learning_rate": 8.960741479140598e-06, + "loss": 5.9863, + "step": 500000 + }, + { + "epoch": 10.59, + "learning_rate": 8.959681011262168e-06, + "loss": 5.9807, + "step": 500500 + }, + { + "epoch": 10.6, + "learning_rate": 8.958620543383742e-06, + "loss": 5.9903, + "step": 501000 + }, + { + "epoch": 10.61, + "learning_rate": 8.957560075505314e-06, + "loss": 5.9877, + "step": 501500 + }, + { + "epoch": 10.62, + "learning_rate": 8.956499607626886e-06, + "loss": 5.9869, + "step": 502000 + }, + { + "epoch": 10.64, + "learning_rate": 8.955439139748458e-06, + "loss": 5.9827, + "step": 502500 + }, + { + "epoch": 10.65, + "learning_rate": 8.95437867187003e-06, + "loss": 5.9815, + "step": 503000 + }, + { + "epoch": 10.66, + "learning_rate": 8.953318203991602e-06, + "loss": 5.9854, + "step": 503500 + }, + { + "epoch": 10.67, + "learning_rate": 8.952257736113173e-06, + "loss": 5.9806, + "step": 504000 + }, + { + "epoch": 10.68, + "learning_rate": 8.951197268234746e-06, + "loss": 5.9814, + "step": 504500 + }, + { + "epoch": 10.69, + "learning_rate": 8.950136800356319e-06, + "loss": 5.9785, + "step": 505000 + }, + { + "epoch": 10.7, + "learning_rate": 8.949076332477889e-06, + "loss": 5.9778, + "step": 505500 + }, + { + "epoch": 10.71, + "learning_rate": 8.948015864599463e-06, + "loss": 5.9821, + "step": 506000 + }, + { + "epoch": 10.72, + "learning_rate": 8.946955396721035e-06, + "loss": 5.9756, + "step": 506500 + }, + { + "epoch": 10.73, + "learning_rate": 8.945894928842605e-06, + "loss": 5.9784, + "step": 507000 + }, + { + "epoch": 10.74, + "learning_rate": 8.944834460964177e-06, + "loss": 5.9776, + "step": 507500 + }, + { + "epoch": 10.75, + "learning_rate": 8.943773993085751e-06, + "loss": 5.9706, + "step": 508000 + }, + { + "epoch": 10.76, + "learning_rate": 8.942713525207323e-06, + "loss": 5.9707, + "step": 508500 + }, + { + "epoch": 10.77, + "learning_rate": 8.941653057328893e-06, + "loss": 5.9735, + "step": 509000 + }, + { + "epoch": 10.78, + "learning_rate": 8.940592589450467e-06, + "loss": 5.9728, + "step": 509500 + }, + { + "epoch": 10.79, + "learning_rate": 8.939532121572039e-06, + "loss": 5.9704, + "step": 510000 + }, + { + "epoch": 10.8, + "learning_rate": 8.93847165369361e-06, + "loss": 5.9719, + "step": 510500 + }, + { + "epoch": 10.82, + "learning_rate": 8.937411185815183e-06, + "loss": 5.9691, + "step": 511000 + }, + { + "epoch": 10.83, + "learning_rate": 8.936350717936755e-06, + "loss": 5.9717, + "step": 511500 + }, + { + "epoch": 10.84, + "learning_rate": 8.935290250058326e-06, + "loss": 5.9672, + "step": 512000 + }, + { + "epoch": 10.85, + "learning_rate": 8.934229782179898e-06, + "loss": 5.9734, + "step": 512500 + }, + { + "epoch": 10.86, + "learning_rate": 8.933169314301471e-06, + "loss": 5.9691, + "step": 513000 + }, + { + "epoch": 10.87, + "learning_rate": 8.932108846423042e-06, + "loss": 5.9649, + "step": 513500 + }, + { + "epoch": 10.88, + "learning_rate": 8.931048378544614e-06, + "loss": 5.9612, + "step": 514000 + }, + { + "epoch": 10.89, + "learning_rate": 8.929987910666188e-06, + "loss": 5.9684, + "step": 514500 + }, + { + "epoch": 10.9, + "learning_rate": 8.928927442787758e-06, + "loss": 5.9662, + "step": 515000 + }, + { + "epoch": 10.91, + "learning_rate": 8.92786697490933e-06, + "loss": 5.962, + "step": 515500 + }, + { + "epoch": 10.92, + "learning_rate": 8.926806507030902e-06, + "loss": 5.9673, + "step": 516000 + }, + { + "epoch": 10.93, + "learning_rate": 8.925746039152476e-06, + "loss": 5.9616, + "step": 516500 + }, + { + "epoch": 10.94, + "learning_rate": 8.924685571274046e-06, + "loss": 5.9634, + "step": 517000 + }, + { + "epoch": 10.95, + "learning_rate": 8.923625103395618e-06, + "loss": 5.9636, + "step": 517500 + }, + { + "epoch": 10.96, + "learning_rate": 8.922564635517192e-06, + "loss": 5.961, + "step": 518000 + }, + { + "epoch": 10.97, + "learning_rate": 8.921504167638762e-06, + "loss": 5.9591, + "step": 518500 + }, + { + "epoch": 10.98, + "learning_rate": 8.920443699760334e-06, + "loss": 5.959, + "step": 519000 + }, + { + "epoch": 10.99, + "learning_rate": 8.919383231881908e-06, + "loss": 5.959, + "step": 519500 + }, + { + "epoch": 11.01, + "learning_rate": 8.918322764003479e-06, + "loss": 5.9626, + "step": 520000 + }, + { + "epoch": 11.02, + "learning_rate": 8.91726229612505e-06, + "loss": 5.9624, + "step": 520500 + }, + { + "epoch": 11.03, + "learning_rate": 8.916201828246623e-06, + "loss": 5.9615, + "step": 521000 + }, + { + "epoch": 11.04, + "learning_rate": 8.915141360368195e-06, + "loss": 5.9591, + "step": 521500 + }, + { + "epoch": 11.05, + "learning_rate": 8.914080892489767e-06, + "loss": 5.9551, + "step": 522000 + }, + { + "epoch": 11.06, + "learning_rate": 8.913020424611339e-06, + "loss": 5.954, + "step": 522500 + }, + { + "epoch": 11.07, + "learning_rate": 8.911959956732913e-06, + "loss": 5.9522, + "step": 523000 + }, + { + "epoch": 11.08, + "learning_rate": 8.910899488854483e-06, + "loss": 5.9594, + "step": 523500 + }, + { + "epoch": 11.09, + "learning_rate": 8.909839020976055e-06, + "loss": 5.9576, + "step": 524000 + }, + { + "epoch": 11.1, + "learning_rate": 8.908778553097627e-06, + "loss": 5.9569, + "step": 524500 + }, + { + "epoch": 11.11, + "learning_rate": 8.907718085219199e-06, + "loss": 5.9532, + "step": 525000 + }, + { + "epoch": 11.12, + "learning_rate": 8.906657617340771e-06, + "loss": 5.9511, + "step": 525500 + }, + { + "epoch": 11.13, + "learning_rate": 8.905597149462343e-06, + "loss": 5.9515, + "step": 526000 + }, + { + "epoch": 11.14, + "learning_rate": 8.904536681583915e-06, + "loss": 5.9519, + "step": 526500 + }, + { + "epoch": 11.15, + "learning_rate": 8.903476213705487e-06, + "loss": 5.9521, + "step": 527000 + }, + { + "epoch": 11.16, + "step": 527425, + "total_flos": 2.791879559002194e+17, + "train_loss": 6.172929247752939, + "train_runtime": 197999.0733, + "train_samples_per_second": 2958.983, + "train_steps_per_second": 23.863 + } + ], + "logging_steps": 500, + "max_steps": 4724900, + "num_train_epochs": 100, + "save_steps": 1000000, + "total_flos": 2.791879559002194e+17, + "trial_name": null, + "trial_params": null +}