{ "best_metric": null, "best_model_checkpoint": null, "epoch": 10.0, "eval_steps": 500, "global_step": 584800, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, "learning_rate": 4.99577633378933e-05, "loss": 8.4265, "step": 500 }, { "epoch": 0.02, "learning_rate": 4.9915013679890566e-05, "loss": 7.7803, "step": 1000 }, { "epoch": 0.03, "learning_rate": 4.987226402188783e-05, "loss": 7.4779, "step": 1500 }, { "epoch": 0.03, "learning_rate": 4.9829514363885096e-05, "loss": 7.2649, "step": 2000 }, { "epoch": 0.04, "learning_rate": 4.978676470588236e-05, "loss": 7.0404, "step": 2500 }, { "epoch": 0.05, "learning_rate": 4.974401504787962e-05, "loss": 6.9479, "step": 3000 }, { "epoch": 0.06, "learning_rate": 4.970126538987688e-05, "loss": 6.8169, "step": 3500 }, { "epoch": 0.07, "learning_rate": 4.965851573187415e-05, "loss": 6.6874, "step": 4000 }, { "epoch": 0.08, "learning_rate": 4.961576607387141e-05, "loss": 6.6356, "step": 4500 }, { "epoch": 0.09, "learning_rate": 4.957301641586867e-05, "loss": 6.578, "step": 5000 }, { "epoch": 0.09, "learning_rate": 4.953026675786594e-05, "loss": 6.4661, "step": 5500 }, { "epoch": 0.1, "learning_rate": 4.94875170998632e-05, "loss": 6.3675, "step": 6000 }, { "epoch": 0.11, "learning_rate": 4.944485294117647e-05, "loss": 6.3715, "step": 6500 }, { "epoch": 0.12, "learning_rate": 4.940218878248974e-05, "loss": 6.3238, "step": 7000 }, { "epoch": 0.13, "learning_rate": 4.9359439124487e-05, "loss": 6.2349, "step": 7500 }, { "epoch": 0.14, "learning_rate": 4.931668946648427e-05, "loss": 6.1865, "step": 8000 }, { "epoch": 0.15, "learning_rate": 4.927393980848153e-05, "loss": 6.1535, "step": 8500 }, { "epoch": 0.15, "learning_rate": 4.92311901504788e-05, "loss": 6.0428, "step": 9000 }, { "epoch": 0.16, "learning_rate": 4.9188525991792064e-05, "loss": 6.0053, "step": 9500 }, { "epoch": 0.17, "learning_rate": 4.914586183310534e-05, "loss": 5.9903, "step": 10000 }, { "epoch": 0.18, "learning_rate": 4.91031121751026e-05, "loss": 6.0044, "step": 10500 }, { "epoch": 0.19, "learning_rate": 4.906036251709987e-05, "loss": 5.9116, "step": 11000 }, { "epoch": 0.2, "learning_rate": 4.901761285909713e-05, "loss": 5.8578, "step": 11500 }, { "epoch": 0.21, "learning_rate": 4.897486320109439e-05, "loss": 5.8959, "step": 12000 }, { "epoch": 0.21, "learning_rate": 4.8932113543091655e-05, "loss": 5.8711, "step": 12500 }, { "epoch": 0.22, "learning_rate": 4.888936388508892e-05, "loss": 5.809, "step": 13000 }, { "epoch": 0.23, "learning_rate": 4.8846614227086185e-05, "loss": 5.7566, "step": 13500 }, { "epoch": 0.24, "learning_rate": 4.880386456908345e-05, "loss": 5.6893, "step": 14000 }, { "epoch": 0.25, "learning_rate": 4.8761200410396716e-05, "loss": 5.6636, "step": 14500 }, { "epoch": 0.26, "learning_rate": 4.8718450752393984e-05, "loss": 5.6148, "step": 15000 }, { "epoch": 0.27, "learning_rate": 4.8675701094391246e-05, "loss": 5.6467, "step": 15500 }, { "epoch": 0.27, "learning_rate": 4.8632951436388514e-05, "loss": 5.5868, "step": 16000 }, { "epoch": 0.28, "learning_rate": 4.8590201778385776e-05, "loss": 5.5777, "step": 16500 }, { "epoch": 0.29, "learning_rate": 4.8547452120383044e-05, "loss": 5.5658, "step": 17000 }, { "epoch": 0.3, "learning_rate": 4.8504702462380306e-05, "loss": 5.5476, "step": 17500 }, { "epoch": 0.31, "learning_rate": 4.846195280437757e-05, "loss": 5.4681, "step": 18000 }, { "epoch": 0.32, "learning_rate": 4.841928864569084e-05, "loss": 5.4999, "step": 18500 }, { "epoch": 0.32, "learning_rate": 4.8376538987688105e-05, "loss": 5.4484, "step": 19000 }, { "epoch": 0.33, "learning_rate": 4.833378932968537e-05, "loss": 5.43, "step": 19500 }, { "epoch": 0.34, "learning_rate": 4.829103967168263e-05, "loss": 5.3776, "step": 20000 }, { "epoch": 0.35, "learning_rate": 4.824829001367989e-05, "loss": 5.3485, "step": 20500 }, { "epoch": 0.36, "learning_rate": 4.8205625854993166e-05, "loss": 5.3793, "step": 21000 }, { "epoch": 0.37, "learning_rate": 4.816287619699043e-05, "loss": 5.3071, "step": 21500 }, { "epoch": 0.38, "learning_rate": 4.81202120383037e-05, "loss": 5.3121, "step": 22000 }, { "epoch": 0.38, "learning_rate": 4.807746238030096e-05, "loss": 5.2851, "step": 22500 }, { "epoch": 0.39, "learning_rate": 4.803471272229823e-05, "loss": 5.296, "step": 23000 }, { "epoch": 0.4, "learning_rate": 4.799196306429549e-05, "loss": 5.2854, "step": 23500 }, { "epoch": 0.41, "learning_rate": 4.794921340629275e-05, "loss": 5.2706, "step": 24000 }, { "epoch": 0.42, "learning_rate": 4.790646374829001e-05, "loss": 5.278, "step": 24500 }, { "epoch": 0.43, "learning_rate": 4.786371409028728e-05, "loss": 5.2171, "step": 25000 }, { "epoch": 0.44, "learning_rate": 4.782096443228454e-05, "loss": 5.2034, "step": 25500 }, { "epoch": 0.44, "learning_rate": 4.777830027359781e-05, "loss": 5.196, "step": 26000 }, { "epoch": 0.45, "learning_rate": 4.773555061559507e-05, "loss": 5.1717, "step": 26500 }, { "epoch": 0.46, "learning_rate": 4.769288645690835e-05, "loss": 5.1113, "step": 27000 }, { "epoch": 0.47, "learning_rate": 4.765013679890561e-05, "loss": 5.1481, "step": 27500 }, { "epoch": 0.48, "learning_rate": 4.760738714090288e-05, "loss": 5.0527, "step": 28000 }, { "epoch": 0.49, "learning_rate": 4.7564637482900134e-05, "loss": 5.1138, "step": 28500 }, { "epoch": 0.5, "learning_rate": 4.75218878248974e-05, "loss": 5.1183, "step": 29000 }, { "epoch": 0.5, "learning_rate": 4.7479138166894664e-05, "loss": 5.098, "step": 29500 }, { "epoch": 0.51, "learning_rate": 4.743647400820794e-05, "loss": 5.0963, "step": 30000 }, { "epoch": 0.52, "learning_rate": 4.73938098495212e-05, "loss": 5.0569, "step": 30500 }, { "epoch": 0.53, "learning_rate": 4.735106019151847e-05, "loss": 5.0201, "step": 31000 }, { "epoch": 0.54, "learning_rate": 4.730831053351573e-05, "loss": 5.0116, "step": 31500 }, { "epoch": 0.55, "learning_rate": 4.7265560875513e-05, "loss": 5.0433, "step": 32000 }, { "epoch": 0.56, "learning_rate": 4.722281121751026e-05, "loss": 5.0234, "step": 32500 }, { "epoch": 0.56, "learning_rate": 4.7180061559507524e-05, "loss": 4.9659, "step": 33000 }, { "epoch": 0.57, "learning_rate": 4.7137311901504786e-05, "loss": 4.9612, "step": 33500 }, { "epoch": 0.58, "learning_rate": 4.7094562243502054e-05, "loss": 4.9943, "step": 34000 }, { "epoch": 0.59, "learning_rate": 4.7051898084815324e-05, "loss": 4.9673, "step": 34500 }, { "epoch": 0.6, "learning_rate": 4.7009148426812585e-05, "loss": 4.8833, "step": 35000 }, { "epoch": 0.61, "learning_rate": 4.696639876880985e-05, "loss": 4.9569, "step": 35500 }, { "epoch": 0.62, "learning_rate": 4.6923649110807115e-05, "loss": 4.933, "step": 36000 }, { "epoch": 0.62, "learning_rate": 4.688089945280438e-05, "loss": 4.8907, "step": 36500 }, { "epoch": 0.63, "learning_rate": 4.6838149794801645e-05, "loss": 4.9273, "step": 37000 }, { "epoch": 0.64, "learning_rate": 4.679540013679891e-05, "loss": 4.8889, "step": 37500 }, { "epoch": 0.65, "learning_rate": 4.6752650478796175e-05, "loss": 4.9151, "step": 38000 }, { "epoch": 0.66, "learning_rate": 4.670990082079344e-05, "loss": 4.9004, "step": 38500 }, { "epoch": 0.67, "learning_rate": 4.66671511627907e-05, "loss": 4.8357, "step": 39000 }, { "epoch": 0.68, "learning_rate": 4.662440150478796e-05, "loss": 4.8494, "step": 39500 }, { "epoch": 0.68, "learning_rate": 4.658165184678523e-05, "loss": 4.8046, "step": 40000 }, { "epoch": 0.69, "learning_rate": 4.653890218878249e-05, "loss": 4.8581, "step": 40500 }, { "epoch": 0.7, "learning_rate": 4.649615253077976e-05, "loss": 4.814, "step": 41000 }, { "epoch": 0.71, "learning_rate": 4.645340287277702e-05, "loss": 4.7839, "step": 41500 }, { "epoch": 0.72, "learning_rate": 4.641073871409029e-05, "loss": 4.8091, "step": 42000 }, { "epoch": 0.73, "learning_rate": 4.636798905608755e-05, "loss": 4.8198, "step": 42500 }, { "epoch": 0.74, "learning_rate": 4.632523939808482e-05, "loss": 4.7321, "step": 43000 }, { "epoch": 0.74, "learning_rate": 4.628248974008208e-05, "loss": 4.7552, "step": 43500 }, { "epoch": 0.75, "learning_rate": 4.623974008207935e-05, "loss": 4.7621, "step": 44000 }, { "epoch": 0.76, "learning_rate": 4.619699042407661e-05, "loss": 4.7516, "step": 44500 }, { "epoch": 0.77, "learning_rate": 4.615424076607387e-05, "loss": 4.7157, "step": 45000 }, { "epoch": 0.78, "learning_rate": 4.6111491108071134e-05, "loss": 4.6958, "step": 45500 }, { "epoch": 0.79, "learning_rate": 4.60687414500684e-05, "loss": 4.7013, "step": 46000 }, { "epoch": 0.8, "learning_rate": 4.6025991792065664e-05, "loss": 4.6959, "step": 46500 }, { "epoch": 0.8, "learning_rate": 4.598324213406293e-05, "loss": 4.7148, "step": 47000 }, { "epoch": 0.81, "learning_rate": 4.5940492476060194e-05, "loss": 4.7094, "step": 47500 }, { "epoch": 0.82, "learning_rate": 4.589774281805746e-05, "loss": 4.6568, "step": 48000 }, { "epoch": 0.83, "learning_rate": 4.5854993160054724e-05, "loss": 4.671, "step": 48500 }, { "epoch": 0.84, "learning_rate": 4.5812243502051985e-05, "loss": 4.6499, "step": 49000 }, { "epoch": 0.85, "learning_rate": 4.576949384404925e-05, "loss": 4.6552, "step": 49500 }, { "epoch": 0.85, "learning_rate": 4.5726915184678524e-05, "loss": 4.6251, "step": 50000 }, { "epoch": 0.86, "learning_rate": 4.5684165526675786e-05, "loss": 4.6063, "step": 50500 }, { "epoch": 0.87, "learning_rate": 4.564150136798906e-05, "loss": 4.6095, "step": 51000 }, { "epoch": 0.88, "learning_rate": 4.5598751709986324e-05, "loss": 4.6453, "step": 51500 }, { "epoch": 0.89, "learning_rate": 4.5556002051983585e-05, "loss": 4.5956, "step": 52000 }, { "epoch": 0.9, "learning_rate": 4.551325239398085e-05, "loss": 4.5697, "step": 52500 }, { "epoch": 0.91, "learning_rate": 4.5470502735978115e-05, "loss": 4.6187, "step": 53000 }, { "epoch": 0.91, "learning_rate": 4.542775307797538e-05, "loss": 4.6015, "step": 53500 }, { "epoch": 0.92, "learning_rate": 4.5385003419972645e-05, "loss": 4.5628, "step": 54000 }, { "epoch": 0.93, "learning_rate": 4.534225376196991e-05, "loss": 4.5632, "step": 54500 }, { "epoch": 0.94, "learning_rate": 4.5299504103967175e-05, "loss": 4.5841, "step": 55000 }, { "epoch": 0.95, "learning_rate": 4.525675444596443e-05, "loss": 4.5934, "step": 55500 }, { "epoch": 0.96, "learning_rate": 4.52140047879617e-05, "loss": 4.5902, "step": 56000 }, { "epoch": 0.97, "learning_rate": 4.517125512995896e-05, "loss": 4.56, "step": 56500 }, { "epoch": 0.97, "learning_rate": 4.512850547195623e-05, "loss": 4.6091, "step": 57000 }, { "epoch": 0.98, "learning_rate": 4.508575581395349e-05, "loss": 4.5518, "step": 57500 }, { "epoch": 0.99, "learning_rate": 4.504300615595076e-05, "loss": 4.5324, "step": 58000 }, { "epoch": 1.0, "learning_rate": 4.500025649794802e-05, "loss": 4.5271, "step": 58500 }, { "epoch": 1.01, "learning_rate": 4.495750683994529e-05, "loss": 4.5211, "step": 59000 }, { "epoch": 1.02, "learning_rate": 4.491475718194254e-05, "loss": 4.5261, "step": 59500 }, { "epoch": 1.03, "learning_rate": 4.487209302325582e-05, "loss": 4.5172, "step": 60000 }, { "epoch": 1.03, "learning_rate": 4.482942886456908e-05, "loss": 4.5021, "step": 60500 }, { "epoch": 1.04, "learning_rate": 4.478667920656635e-05, "loss": 4.5054, "step": 61000 }, { "epoch": 1.05, "learning_rate": 4.474392954856361e-05, "loss": 4.4886, "step": 61500 }, { "epoch": 1.06, "learning_rate": 4.470117989056088e-05, "loss": 4.487, "step": 62000 }, { "epoch": 1.07, "learning_rate": 4.465860123119015e-05, "loss": 4.5001, "step": 62500 }, { "epoch": 1.08, "learning_rate": 4.461585157318742e-05, "loss": 4.5064, "step": 63000 }, { "epoch": 1.09, "learning_rate": 4.457310191518468e-05, "loss": 4.4453, "step": 63500 }, { "epoch": 1.09, "learning_rate": 4.453035225718194e-05, "loss": 4.4815, "step": 64000 }, { "epoch": 1.1, "learning_rate": 4.4487602599179204e-05, "loss": 4.4853, "step": 64500 }, { "epoch": 1.11, "learning_rate": 4.444485294117647e-05, "loss": 4.4796, "step": 65000 }, { "epoch": 1.12, "learning_rate": 4.4402103283173734e-05, "loss": 4.4877, "step": 65500 }, { "epoch": 1.13, "learning_rate": 4.4359353625171e-05, "loss": 4.4423, "step": 66000 }, { "epoch": 1.14, "learning_rate": 4.4316603967168264e-05, "loss": 4.4397, "step": 66500 }, { "epoch": 1.15, "learning_rate": 4.427385430916553e-05, "loss": 4.4684, "step": 67000 }, { "epoch": 1.15, "learning_rate": 4.4231104651162794e-05, "loss": 4.4439, "step": 67500 }, { "epoch": 1.16, "learning_rate": 4.4188354993160055e-05, "loss": 4.4587, "step": 68000 }, { "epoch": 1.17, "learning_rate": 4.414560533515732e-05, "loss": 4.397, "step": 68500 }, { "epoch": 1.18, "learning_rate": 4.410294117647059e-05, "loss": 4.398, "step": 69000 }, { "epoch": 1.19, "learning_rate": 4.4060191518467855e-05, "loss": 4.3962, "step": 69500 }, { "epoch": 1.2, "learning_rate": 4.4017441860465116e-05, "loss": 4.4318, "step": 70000 }, { "epoch": 1.21, "learning_rate": 4.397469220246238e-05, "loss": 4.4008, "step": 70500 }, { "epoch": 1.21, "learning_rate": 4.3931942544459646e-05, "loss": 4.3997, "step": 71000 }, { "epoch": 1.22, "learning_rate": 4.388919288645691e-05, "loss": 4.3974, "step": 71500 }, { "epoch": 1.23, "learning_rate": 4.3846443228454176e-05, "loss": 4.4154, "step": 72000 }, { "epoch": 1.24, "learning_rate": 4.380369357045144e-05, "loss": 4.3971, "step": 72500 }, { "epoch": 1.25, "learning_rate": 4.3760943912448706e-05, "loss": 4.3549, "step": 73000 }, { "epoch": 1.26, "learning_rate": 4.371819425444597e-05, "loss": 4.3565, "step": 73500 }, { "epoch": 1.27, "learning_rate": 4.3675615595075245e-05, "loss": 4.3663, "step": 74000 }, { "epoch": 1.27, "learning_rate": 4.363286593707251e-05, "loss": 4.3174, "step": 74500 }, { "epoch": 1.28, "learning_rate": 4.359011627906977e-05, "loss": 4.3624, "step": 75000 }, { "epoch": 1.29, "learning_rate": 4.354736662106703e-05, "loss": 4.3694, "step": 75500 }, { "epoch": 1.3, "learning_rate": 4.35046169630643e-05, "loss": 4.3345, "step": 76000 }, { "epoch": 1.31, "learning_rate": 4.346195280437757e-05, "loss": 4.3558, "step": 76500 }, { "epoch": 1.32, "learning_rate": 4.341928864569084e-05, "loss": 4.3529, "step": 77000 }, { "epoch": 1.33, "learning_rate": 4.33765389876881e-05, "loss": 4.3293, "step": 77500 }, { "epoch": 1.33, "learning_rate": 4.333378932968537e-05, "loss": 4.3166, "step": 78000 }, { "epoch": 1.34, "learning_rate": 4.329103967168263e-05, "loss": 4.3186, "step": 78500 }, { "epoch": 1.35, "learning_rate": 4.32483755129959e-05, "loss": 4.372, "step": 79000 }, { "epoch": 1.36, "learning_rate": 4.3205625854993167e-05, "loss": 4.2791, "step": 79500 }, { "epoch": 1.37, "learning_rate": 4.316296169630643e-05, "loss": 4.3088, "step": 80000 }, { "epoch": 1.38, "learning_rate": 4.31202120383037e-05, "loss": 4.3065, "step": 80500 }, { "epoch": 1.39, "learning_rate": 4.307746238030096e-05, "loss": 4.3327, "step": 81000 }, { "epoch": 1.39, "learning_rate": 4.303471272229823e-05, "loss": 4.2718, "step": 81500 }, { "epoch": 1.4, "learning_rate": 4.299196306429549e-05, "loss": 4.2324, "step": 82000 }, { "epoch": 1.41, "learning_rate": 4.294921340629276e-05, "loss": 4.2851, "step": 82500 }, { "epoch": 1.42, "learning_rate": 4.290654924760602e-05, "loss": 4.2606, "step": 83000 }, { "epoch": 1.43, "learning_rate": 4.286379958960329e-05, "loss": 4.2524, "step": 83500 }, { "epoch": 1.44, "learning_rate": 4.282104993160055e-05, "loss": 4.2853, "step": 84000 }, { "epoch": 1.44, "learning_rate": 4.277830027359782e-05, "loss": 4.274, "step": 84500 }, { "epoch": 1.45, "learning_rate": 4.273555061559508e-05, "loss": 4.2519, "step": 85000 }, { "epoch": 1.46, "learning_rate": 4.269280095759234e-05, "loss": 4.2295, "step": 85500 }, { "epoch": 1.47, "learning_rate": 4.26500512995896e-05, "loss": 4.27, "step": 86000 }, { "epoch": 1.48, "learning_rate": 4.260730164158687e-05, "loss": 4.2542, "step": 86500 }, { "epoch": 1.49, "learning_rate": 4.256455198358413e-05, "loss": 4.1816, "step": 87000 }, { "epoch": 1.5, "learning_rate": 4.2521802325581395e-05, "loss": 4.2759, "step": 87500 }, { "epoch": 1.5, "learning_rate": 4.247905266757866e-05, "loss": 4.2383, "step": 88000 }, { "epoch": 1.51, "learning_rate": 4.2436303009575925e-05, "loss": 4.2417, "step": 88500 }, { "epoch": 1.52, "learning_rate": 4.2393553351573186e-05, "loss": 4.2522, "step": 89000 }, { "epoch": 1.53, "learning_rate": 4.235080369357045e-05, "loss": 4.2286, "step": 89500 }, { "epoch": 1.54, "learning_rate": 4.2308054035567716e-05, "loss": 4.213, "step": 90000 }, { "epoch": 1.55, "learning_rate": 4.226530437756498e-05, "loss": 4.2361, "step": 90500 }, { "epoch": 1.56, "learning_rate": 4.2222554719562246e-05, "loss": 4.2226, "step": 91000 }, { "epoch": 1.56, "learning_rate": 4.2179976060191524e-05, "loss": 4.2126, "step": 91500 }, { "epoch": 1.57, "learning_rate": 4.2137226402188785e-05, "loss": 4.2679, "step": 92000 }, { "epoch": 1.58, "learning_rate": 4.2094476744186054e-05, "loss": 4.2176, "step": 92500 }, { "epoch": 1.59, "learning_rate": 4.2051727086183315e-05, "loss": 4.2451, "step": 93000 }, { "epoch": 1.6, "learning_rate": 4.200897742818058e-05, "loss": 4.2348, "step": 93500 }, { "epoch": 1.61, "learning_rate": 4.196622777017784e-05, "loss": 4.1622, "step": 94000 }, { "epoch": 1.62, "learning_rate": 4.19234781121751e-05, "loss": 4.2212, "step": 94500 }, { "epoch": 1.62, "learning_rate": 4.188089945280438e-05, "loss": 4.1774, "step": 95000 }, { "epoch": 1.63, "learning_rate": 4.1838149794801646e-05, "loss": 4.1855, "step": 95500 }, { "epoch": 1.64, "learning_rate": 4.179540013679891e-05, "loss": 4.1997, "step": 96000 }, { "epoch": 1.65, "learning_rate": 4.1752650478796176e-05, "loss": 4.1479, "step": 96500 }, { "epoch": 1.66, "learning_rate": 4.170990082079344e-05, "loss": 4.1943, "step": 97000 }, { "epoch": 1.67, "learning_rate": 4.16671511627907e-05, "loss": 4.1743, "step": 97500 }, { "epoch": 1.68, "learning_rate": 4.162440150478796e-05, "loss": 4.1654, "step": 98000 }, { "epoch": 1.68, "learning_rate": 4.158165184678523e-05, "loss": 4.1624, "step": 98500 }, { "epoch": 1.69, "learning_rate": 4.153890218878249e-05, "loss": 4.204, "step": 99000 }, { "epoch": 1.7, "learning_rate": 4.149615253077976e-05, "loss": 4.0859, "step": 99500 }, { "epoch": 1.71, "learning_rate": 4.145340287277702e-05, "loss": 4.1537, "step": 100000 }, { "epoch": 1.72, "learning_rate": 4.141065321477429e-05, "loss": 4.172, "step": 100500 }, { "epoch": 1.73, "learning_rate": 4.136790355677155e-05, "loss": 4.1576, "step": 101000 }, { "epoch": 1.74, "learning_rate": 4.132523939808482e-05, "loss": 4.1124, "step": 101500 }, { "epoch": 1.74, "learning_rate": 4.128248974008208e-05, "loss": 4.1375, "step": 102000 }, { "epoch": 1.75, "learning_rate": 4.123982558139535e-05, "loss": 4.1307, "step": 102500 }, { "epoch": 1.76, "learning_rate": 4.119707592339261e-05, "loss": 4.1423, "step": 103000 }, { "epoch": 1.77, "learning_rate": 4.115432626538988e-05, "loss": 4.1378, "step": 103500 }, { "epoch": 1.78, "learning_rate": 4.111157660738714e-05, "loss": 4.0877, "step": 104000 }, { "epoch": 1.79, "learning_rate": 4.106882694938441e-05, "loss": 4.1337, "step": 104500 }, { "epoch": 1.8, "learning_rate": 4.102607729138167e-05, "loss": 4.1034, "step": 105000 }, { "epoch": 1.8, "learning_rate": 4.098332763337894e-05, "loss": 4.1387, "step": 105500 }, { "epoch": 1.81, "learning_rate": 4.0940577975376195e-05, "loss": 4.1397, "step": 106000 }, { "epoch": 1.82, "learning_rate": 4.0897828317373464e-05, "loss": 4.142, "step": 106500 }, { "epoch": 1.83, "learning_rate": 4.0855078659370725e-05, "loss": 4.1181, "step": 107000 }, { "epoch": 1.84, "learning_rate": 4.0812414500684e-05, "loss": 4.1161, "step": 107500 }, { "epoch": 1.85, "learning_rate": 4.0769750341997264e-05, "loss": 4.0865, "step": 108000 }, { "epoch": 1.86, "learning_rate": 4.0727086183310534e-05, "loss": 4.0692, "step": 108500 }, { "epoch": 1.86, "learning_rate": 4.0684336525307795e-05, "loss": 4.0814, "step": 109000 }, { "epoch": 1.87, "learning_rate": 4.0641586867305064e-05, "loss": 4.0752, "step": 109500 }, { "epoch": 1.88, "learning_rate": 4.0598837209302325e-05, "loss": 4.0893, "step": 110000 }, { "epoch": 1.89, "learning_rate": 4.0556087551299594e-05, "loss": 4.0941, "step": 110500 }, { "epoch": 1.9, "learning_rate": 4.0513337893296855e-05, "loss": 4.1135, "step": 111000 }, { "epoch": 1.91, "learning_rate": 4.0470588235294124e-05, "loss": 4.0911, "step": 111500 }, { "epoch": 1.92, "learning_rate": 4.0427924076607386e-05, "loss": 4.0741, "step": 112000 }, { "epoch": 1.92, "learning_rate": 4.0385174418604655e-05, "loss": 4.1022, "step": 112500 }, { "epoch": 1.93, "learning_rate": 4.0342424760601916e-05, "loss": 4.0507, "step": 113000 }, { "epoch": 1.94, "learning_rate": 4.0299675102599185e-05, "loss": 4.0823, "step": 113500 }, { "epoch": 1.95, "learning_rate": 4.0256925444596446e-05, "loss": 4.0645, "step": 114000 }, { "epoch": 1.96, "learning_rate": 4.021417578659371e-05, "loss": 4.0487, "step": 114500 }, { "epoch": 1.97, "learning_rate": 4.017142612859097e-05, "loss": 4.0594, "step": 115000 }, { "epoch": 1.98, "learning_rate": 4.012867647058824e-05, "loss": 4.0333, "step": 115500 }, { "epoch": 1.98, "learning_rate": 4.00859268125855e-05, "loss": 4.0575, "step": 116000 }, { "epoch": 1.99, "learning_rate": 4.004317715458277e-05, "loss": 4.0441, "step": 116500 }, { "epoch": 2.0, "learning_rate": 4.000042749658003e-05, "loss": 4.0541, "step": 117000 }, { "epoch": 2.01, "learning_rate": 3.99576778385773e-05, "loss": 4.0371, "step": 117500 }, { "epoch": 2.02, "learning_rate": 3.991492818057456e-05, "loss": 4.0368, "step": 118000 }, { "epoch": 2.03, "learning_rate": 3.987226402188783e-05, "loss": 4.0379, "step": 118500 }, { "epoch": 2.03, "learning_rate": 3.982951436388509e-05, "loss": 4.0413, "step": 119000 }, { "epoch": 2.04, "learning_rate": 3.978676470588236e-05, "loss": 3.9662, "step": 119500 }, { "epoch": 2.05, "learning_rate": 3.974401504787962e-05, "loss": 4.0108, "step": 120000 }, { "epoch": 2.06, "learning_rate": 3.970126538987688e-05, "loss": 4.0292, "step": 120500 }, { "epoch": 2.07, "learning_rate": 3.965851573187414e-05, "loss": 3.9768, "step": 121000 }, { "epoch": 2.08, "learning_rate": 3.961593707250342e-05, "loss": 4.01, "step": 121500 }, { "epoch": 2.09, "learning_rate": 3.957318741450068e-05, "loss": 4.0071, "step": 122000 }, { "epoch": 2.09, "learning_rate": 3.953043775649795e-05, "loss": 3.9862, "step": 122500 }, { "epoch": 2.1, "learning_rate": 3.948768809849521e-05, "loss": 4.0002, "step": 123000 }, { "epoch": 2.11, "learning_rate": 3.944493844049248e-05, "loss": 3.986, "step": 123500 }, { "epoch": 2.12, "learning_rate": 3.940218878248974e-05, "loss": 4.0122, "step": 124000 }, { "epoch": 2.13, "learning_rate": 3.935952462380301e-05, "loss": 4.0036, "step": 124500 }, { "epoch": 2.14, "learning_rate": 3.931677496580027e-05, "loss": 4.0221, "step": 125000 }, { "epoch": 2.15, "learning_rate": 3.927402530779754e-05, "loss": 3.9919, "step": 125500 }, { "epoch": 2.15, "learning_rate": 3.9231361149110804e-05, "loss": 3.9685, "step": 126000 }, { "epoch": 2.16, "learning_rate": 3.918861149110807e-05, "loss": 3.9836, "step": 126500 }, { "epoch": 2.17, "learning_rate": 3.914594733242134e-05, "loss": 3.9964, "step": 127000 }, { "epoch": 2.18, "learning_rate": 3.9103197674418604e-05, "loss": 3.9632, "step": 127500 }, { "epoch": 2.19, "learning_rate": 3.9060448016415865e-05, "loss": 4.0239, "step": 128000 }, { "epoch": 2.2, "learning_rate": 3.9017698358413134e-05, "loss": 3.9661, "step": 128500 }, { "epoch": 2.21, "learning_rate": 3.8974948700410395e-05, "loss": 4.0074, "step": 129000 }, { "epoch": 2.21, "learning_rate": 3.8932199042407664e-05, "loss": 3.9572, "step": 129500 }, { "epoch": 2.22, "learning_rate": 3.8889449384404925e-05, "loss": 4.0149, "step": 130000 }, { "epoch": 2.23, "learning_rate": 3.8846699726402194e-05, "loss": 3.9621, "step": 130500 }, { "epoch": 2.24, "learning_rate": 3.8803950068399455e-05, "loss": 3.9519, "step": 131000 }, { "epoch": 2.25, "learning_rate": 3.876120041039672e-05, "loss": 3.9366, "step": 131500 }, { "epoch": 2.26, "learning_rate": 3.871845075239398e-05, "loss": 3.9689, "step": 132000 }, { "epoch": 2.27, "learning_rate": 3.867570109439125e-05, "loss": 3.9984, "step": 132500 }, { "epoch": 2.27, "learning_rate": 3.863295143638851e-05, "loss": 3.9291, "step": 133000 }, { "epoch": 2.28, "learning_rate": 3.859020177838578e-05, "loss": 3.9921, "step": 133500 }, { "epoch": 2.29, "learning_rate": 3.854745212038304e-05, "loss": 3.9747, "step": 134000 }, { "epoch": 2.3, "learning_rate": 3.8504702462380307e-05, "loss": 3.9321, "step": 134500 }, { "epoch": 2.31, "learning_rate": 3.846195280437757e-05, "loss": 3.9596, "step": 135000 }, { "epoch": 2.32, "learning_rate": 3.841920314637483e-05, "loss": 3.9574, "step": 135500 }, { "epoch": 2.33, "learning_rate": 3.83765389876881e-05, "loss": 3.9476, "step": 136000 }, { "epoch": 2.33, "learning_rate": 3.833378932968537e-05, "loss": 3.937, "step": 136500 }, { "epoch": 2.34, "learning_rate": 3.829103967168263e-05, "loss": 3.9935, "step": 137000 }, { "epoch": 2.35, "learning_rate": 3.82483755129959e-05, "loss": 3.9308, "step": 137500 }, { "epoch": 2.36, "learning_rate": 3.820562585499316e-05, "loss": 3.9201, "step": 138000 }, { "epoch": 2.37, "learning_rate": 3.816287619699043e-05, "loss": 3.952, "step": 138500 }, { "epoch": 2.38, "learning_rate": 3.812021203830369e-05, "loss": 3.9014, "step": 139000 }, { "epoch": 2.39, "learning_rate": 3.807746238030096e-05, "loss": 3.9021, "step": 139500 }, { "epoch": 2.39, "learning_rate": 3.803471272229822e-05, "loss": 3.9358, "step": 140000 }, { "epoch": 2.4, "learning_rate": 3.799196306429549e-05, "loss": 3.9108, "step": 140500 }, { "epoch": 2.41, "learning_rate": 3.794921340629275e-05, "loss": 3.9362, "step": 141000 }, { "epoch": 2.42, "learning_rate": 3.790646374829002e-05, "loss": 3.9195, "step": 141500 }, { "epoch": 2.43, "learning_rate": 3.786371409028728e-05, "loss": 3.9143, "step": 142000 }, { "epoch": 2.44, "learning_rate": 3.782096443228454e-05, "loss": 3.8993, "step": 142500 }, { "epoch": 2.45, "learning_rate": 3.7778214774281804e-05, "loss": 3.8982, "step": 143000 }, { "epoch": 2.45, "learning_rate": 3.773546511627907e-05, "loss": 3.9135, "step": 143500 }, { "epoch": 2.46, "learning_rate": 3.7692715458276334e-05, "loss": 3.9076, "step": 144000 }, { "epoch": 2.47, "learning_rate": 3.76499658002736e-05, "loss": 3.9286, "step": 144500 }, { "epoch": 2.48, "learning_rate": 3.7607301641586865e-05, "loss": 3.8641, "step": 145000 }, { "epoch": 2.49, "learning_rate": 3.7564551983584134e-05, "loss": 3.9229, "step": 145500 }, { "epoch": 2.5, "learning_rate": 3.7521802325581395e-05, "loss": 3.9007, "step": 146000 }, { "epoch": 2.51, "learning_rate": 3.7479052667578664e-05, "loss": 3.8653, "step": 146500 }, { "epoch": 2.51, "learning_rate": 3.7436303009575925e-05, "loss": 3.9433, "step": 147000 }, { "epoch": 2.52, "learning_rate": 3.7393553351573194e-05, "loss": 3.934, "step": 147500 }, { "epoch": 2.53, "learning_rate": 3.7350803693570455e-05, "loss": 3.9171, "step": 148000 }, { "epoch": 2.54, "learning_rate": 3.730805403556772e-05, "loss": 3.8635, "step": 148500 }, { "epoch": 2.55, "learning_rate": 3.726530437756498e-05, "loss": 3.8977, "step": 149000 }, { "epoch": 2.56, "learning_rate": 3.722255471956225e-05, "loss": 3.931, "step": 149500 }, { "epoch": 2.56, "learning_rate": 3.7179890560875516e-05, "loss": 3.8653, "step": 150000 }, { "epoch": 2.57, "learning_rate": 3.713714090287278e-05, "loss": 3.875, "step": 150500 }, { "epoch": 2.58, "learning_rate": 3.709439124487004e-05, "loss": 3.8962, "step": 151000 }, { "epoch": 2.59, "learning_rate": 3.705164158686731e-05, "loss": 3.8875, "step": 151500 }, { "epoch": 2.6, "learning_rate": 3.700897742818058e-05, "loss": 3.8829, "step": 152000 }, { "epoch": 2.61, "learning_rate": 3.696622777017784e-05, "loss": 3.8708, "step": 152500 }, { "epoch": 2.62, "learning_rate": 3.69234781121751e-05, "loss": 3.8609, "step": 153000 }, { "epoch": 2.62, "learning_rate": 3.688072845417237e-05, "loss": 3.8731, "step": 153500 }, { "epoch": 2.63, "learning_rate": 3.683797879616963e-05, "loss": 3.8877, "step": 154000 }, { "epoch": 2.64, "learning_rate": 3.67952291381669e-05, "loss": 3.8592, "step": 154500 }, { "epoch": 2.65, "learning_rate": 3.675256497948016e-05, "loss": 3.8315, "step": 155000 }, { "epoch": 2.66, "learning_rate": 3.670981532147743e-05, "loss": 3.8739, "step": 155500 }, { "epoch": 2.67, "learning_rate": 3.666706566347469e-05, "loss": 3.8786, "step": 156000 }, { "epoch": 2.68, "learning_rate": 3.662440150478796e-05, "loss": 3.8754, "step": 156500 }, { "epoch": 2.68, "learning_rate": 3.658165184678522e-05, "loss": 3.8909, "step": 157000 }, { "epoch": 2.69, "learning_rate": 3.653890218878249e-05, "loss": 3.8487, "step": 157500 }, { "epoch": 2.7, "learning_rate": 3.649615253077975e-05, "loss": 3.8285, "step": 158000 }, { "epoch": 2.71, "learning_rate": 3.645340287277702e-05, "loss": 3.8426, "step": 158500 }, { "epoch": 2.72, "learning_rate": 3.641065321477428e-05, "loss": 3.8324, "step": 159000 }, { "epoch": 2.73, "learning_rate": 3.636790355677155e-05, "loss": 3.8314, "step": 159500 }, { "epoch": 2.74, "learning_rate": 3.632515389876881e-05, "loss": 3.8827, "step": 160000 }, { "epoch": 2.74, "learning_rate": 3.6282404240766074e-05, "loss": 3.8093, "step": 160500 }, { "epoch": 2.75, "learning_rate": 3.6239654582763335e-05, "loss": 3.8147, "step": 161000 }, { "epoch": 2.76, "learning_rate": 3.619699042407661e-05, "loss": 3.8406, "step": 161500 }, { "epoch": 2.77, "learning_rate": 3.615424076607387e-05, "loss": 3.8308, "step": 162000 }, { "epoch": 2.78, "learning_rate": 3.611157660738714e-05, "loss": 3.8018, "step": 162500 }, { "epoch": 2.79, "learning_rate": 3.6068826949384404e-05, "loss": 3.845, "step": 163000 }, { "epoch": 2.8, "learning_rate": 3.602607729138167e-05, "loss": 3.8614, "step": 163500 }, { "epoch": 2.8, "learning_rate": 3.5983327633378934e-05, "loss": 3.8299, "step": 164000 }, { "epoch": 2.81, "learning_rate": 3.59405779753762e-05, "loss": 3.857, "step": 164500 }, { "epoch": 2.82, "learning_rate": 3.5897828317373464e-05, "loss": 3.8043, "step": 165000 }, { "epoch": 2.83, "learning_rate": 3.5855078659370726e-05, "loss": 3.8535, "step": 165500 }, { "epoch": 2.84, "learning_rate": 3.581232900136799e-05, "loss": 3.806, "step": 166000 }, { "epoch": 2.85, "learning_rate": 3.576983584131327e-05, "loss": 3.8039, "step": 166500 }, { "epoch": 2.86, "learning_rate": 3.5727086183310534e-05, "loss": 3.7829, "step": 167000 }, { "epoch": 2.86, "learning_rate": 3.5684336525307796e-05, "loss": 3.7712, "step": 167500 }, { "epoch": 2.87, "learning_rate": 3.5641586867305064e-05, "loss": 3.8275, "step": 168000 }, { "epoch": 2.88, "learning_rate": 3.5598922708618334e-05, "loss": 3.84, "step": 168500 }, { "epoch": 2.89, "learning_rate": 3.55561730506156e-05, "loss": 3.8221, "step": 169000 }, { "epoch": 2.9, "learning_rate": 3.551342339261286e-05, "loss": 3.817, "step": 169500 }, { "epoch": 2.91, "learning_rate": 3.5470673734610125e-05, "loss": 3.775, "step": 170000 }, { "epoch": 2.92, "learning_rate": 3.542792407660739e-05, "loss": 3.799, "step": 170500 }, { "epoch": 2.92, "learning_rate": 3.5385174418604655e-05, "loss": 3.7927, "step": 171000 }, { "epoch": 2.93, "learning_rate": 3.534242476060192e-05, "loss": 3.7902, "step": 171500 }, { "epoch": 2.94, "learning_rate": 3.5299675102599185e-05, "loss": 3.8066, "step": 172000 }, { "epoch": 2.95, "learning_rate": 3.525692544459645e-05, "loss": 3.7513, "step": 172500 }, { "epoch": 2.96, "learning_rate": 3.5214175786593715e-05, "loss": 3.7826, "step": 173000 }, { "epoch": 2.97, "learning_rate": 3.517142612859097e-05, "loss": 3.8108, "step": 173500 }, { "epoch": 2.98, "learning_rate": 3.512867647058823e-05, "loss": 3.837, "step": 174000 }, { "epoch": 2.98, "learning_rate": 3.508601231190151e-05, "loss": 3.779, "step": 174500 }, { "epoch": 2.99, "learning_rate": 3.504334815321478e-05, "loss": 3.7988, "step": 175000 }, { "epoch": 3.0, "learning_rate": 3.500059849521204e-05, "loss": 3.7856, "step": 175500 }, { "epoch": 3.01, "learning_rate": 3.495784883720931e-05, "loss": 3.78, "step": 176000 }, { "epoch": 3.02, "learning_rate": 3.491509917920657e-05, "loss": 3.7456, "step": 176500 }, { "epoch": 3.03, "learning_rate": 3.487234952120384e-05, "loss": 3.7645, "step": 177000 }, { "epoch": 3.04, "learning_rate": 3.48296853625171e-05, "loss": 3.7486, "step": 177500 }, { "epoch": 3.04, "learning_rate": 3.478693570451437e-05, "loss": 3.7541, "step": 178000 }, { "epoch": 3.05, "learning_rate": 3.474418604651163e-05, "loss": 3.7828, "step": 178500 }, { "epoch": 3.06, "learning_rate": 3.47014363885089e-05, "loss": 3.7786, "step": 179000 }, { "epoch": 3.07, "learning_rate": 3.465868673050616e-05, "loss": 3.7776, "step": 179500 }, { "epoch": 3.08, "learning_rate": 3.461593707250342e-05, "loss": 3.783, "step": 180000 }, { "epoch": 3.09, "learning_rate": 3.457318741450068e-05, "loss": 3.7366, "step": 180500 }, { "epoch": 3.1, "learning_rate": 3.453043775649795e-05, "loss": 3.7755, "step": 181000 }, { "epoch": 3.1, "learning_rate": 3.448768809849521e-05, "loss": 3.7732, "step": 181500 }, { "epoch": 3.11, "learning_rate": 3.444493844049248e-05, "loss": 3.7646, "step": 182000 }, { "epoch": 3.12, "learning_rate": 3.4402274281805744e-05, "loss": 3.7425, "step": 182500 }, { "epoch": 3.13, "learning_rate": 3.435952462380301e-05, "loss": 3.7511, "step": 183000 }, { "epoch": 3.14, "learning_rate": 3.4316774965800274e-05, "loss": 3.7502, "step": 183500 }, { "epoch": 3.15, "learning_rate": 3.427411080711354e-05, "loss": 3.7457, "step": 184000 }, { "epoch": 3.15, "learning_rate": 3.4231361149110805e-05, "loss": 3.7421, "step": 184500 }, { "epoch": 3.16, "learning_rate": 3.418861149110807e-05, "loss": 3.7374, "step": 185000 }, { "epoch": 3.17, "learning_rate": 3.4145861833105335e-05, "loss": 3.7469, "step": 185500 }, { "epoch": 3.18, "learning_rate": 3.41031121751026e-05, "loss": 3.7475, "step": 186000 }, { "epoch": 3.19, "learning_rate": 3.4060362517099865e-05, "loss": 3.76, "step": 186500 }, { "epoch": 3.2, "learning_rate": 3.401761285909713e-05, "loss": 3.7236, "step": 187000 }, { "epoch": 3.21, "learning_rate": 3.3974863201094395e-05, "loss": 3.7304, "step": 187500 }, { "epoch": 3.21, "learning_rate": 3.3932113543091656e-05, "loss": 3.7536, "step": 188000 }, { "epoch": 3.22, "learning_rate": 3.388936388508892e-05, "loss": 3.7591, "step": 188500 }, { "epoch": 3.23, "learning_rate": 3.3846699726402194e-05, "loss": 3.7331, "step": 189000 }, { "epoch": 3.24, "learning_rate": 3.3803950068399456e-05, "loss": 3.7429, "step": 189500 }, { "epoch": 3.25, "learning_rate": 3.376120041039672e-05, "loss": 3.7781, "step": 190000 }, { "epoch": 3.26, "learning_rate": 3.371845075239398e-05, "loss": 3.6779, "step": 190500 }, { "epoch": 3.27, "learning_rate": 3.367570109439125e-05, "loss": 3.7198, "step": 191000 }, { "epoch": 3.27, "learning_rate": 3.363295143638851e-05, "loss": 3.7508, "step": 191500 }, { "epoch": 3.28, "learning_rate": 3.3590287277701785e-05, "loss": 3.7314, "step": 192000 }, { "epoch": 3.29, "learning_rate": 3.354753761969904e-05, "loss": 3.7358, "step": 192500 }, { "epoch": 3.3, "learning_rate": 3.350478796169631e-05, "loss": 3.7569, "step": 193000 }, { "epoch": 3.31, "learning_rate": 3.346203830369357e-05, "loss": 3.7113, "step": 193500 }, { "epoch": 3.32, "learning_rate": 3.341928864569084e-05, "loss": 3.7133, "step": 194000 }, { "epoch": 3.33, "learning_rate": 3.33765389876881e-05, "loss": 3.703, "step": 194500 }, { "epoch": 3.33, "learning_rate": 3.333387482900137e-05, "loss": 3.7268, "step": 195000 }, { "epoch": 3.34, "learning_rate": 3.329112517099863e-05, "loss": 3.7187, "step": 195500 }, { "epoch": 3.35, "learning_rate": 3.32483755129959e-05, "loss": 3.7187, "step": 196000 }, { "epoch": 3.36, "learning_rate": 3.320562585499316e-05, "loss": 3.7223, "step": 196500 }, { "epoch": 3.37, "learning_rate": 3.316287619699043e-05, "loss": 3.698, "step": 197000 }, { "epoch": 3.38, "learning_rate": 3.312012653898769e-05, "loss": 3.6941, "step": 197500 }, { "epoch": 3.39, "learning_rate": 3.307746238030096e-05, "loss": 3.6822, "step": 198000 }, { "epoch": 3.39, "learning_rate": 3.303471272229822e-05, "loss": 3.7184, "step": 198500 }, { "epoch": 3.4, "learning_rate": 3.299196306429549e-05, "loss": 3.6901, "step": 199000 }, { "epoch": 3.41, "learning_rate": 3.294921340629275e-05, "loss": 3.669, "step": 199500 }, { "epoch": 3.42, "learning_rate": 3.290646374829002e-05, "loss": 3.7188, "step": 200000 }, { "epoch": 3.43, "learning_rate": 3.286371409028728e-05, "loss": 3.7266, "step": 200500 }, { "epoch": 3.44, "learning_rate": 3.282096443228454e-05, "loss": 3.6421, "step": 201000 }, { "epoch": 3.45, "learning_rate": 3.2778214774281805e-05, "loss": 3.7126, "step": 201500 }, { "epoch": 3.45, "learning_rate": 3.273555061559508e-05, "loss": 3.7324, "step": 202000 }, { "epoch": 3.46, "learning_rate": 3.269280095759234e-05, "loss": 3.7318, "step": 202500 }, { "epoch": 3.47, "learning_rate": 3.2650051299589604e-05, "loss": 3.7125, "step": 203000 }, { "epoch": 3.48, "learning_rate": 3.2607301641586866e-05, "loss": 3.7445, "step": 203500 }, { "epoch": 3.49, "learning_rate": 3.256463748290014e-05, "loss": 3.6906, "step": 204000 }, { "epoch": 3.5, "learning_rate": 3.2521973324213405e-05, "loss": 3.7217, "step": 204500 }, { "epoch": 3.51, "learning_rate": 3.247922366621067e-05, "loss": 3.7128, "step": 205000 }, { "epoch": 3.51, "learning_rate": 3.2436474008207935e-05, "loss": 3.66, "step": 205500 }, { "epoch": 3.52, "learning_rate": 3.23937243502052e-05, "loss": 3.6891, "step": 206000 }, { "epoch": 3.53, "learning_rate": 3.2351060191518466e-05, "loss": 3.6576, "step": 206500 }, { "epoch": 3.54, "learning_rate": 3.2308310533515734e-05, "loss": 3.6565, "step": 207000 }, { "epoch": 3.55, "learning_rate": 3.2265560875512996e-05, "loss": 3.6723, "step": 207500 }, { "epoch": 3.56, "learning_rate": 3.2222811217510264e-05, "loss": 3.6781, "step": 208000 }, { "epoch": 3.57, "learning_rate": 3.2180061559507526e-05, "loss": 3.6858, "step": 208500 }, { "epoch": 3.57, "learning_rate": 3.2137397400820795e-05, "loss": 3.6536, "step": 209000 }, { "epoch": 3.58, "learning_rate": 3.2094733242134065e-05, "loss": 3.6654, "step": 209500 }, { "epoch": 3.59, "learning_rate": 3.2051983584131326e-05, "loss": 3.6439, "step": 210000 }, { "epoch": 3.6, "learning_rate": 3.200923392612859e-05, "loss": 3.6517, "step": 210500 }, { "epoch": 3.61, "learning_rate": 3.1966484268125856e-05, "loss": 3.6792, "step": 211000 }, { "epoch": 3.62, "learning_rate": 3.192373461012312e-05, "loss": 3.6649, "step": 211500 }, { "epoch": 3.63, "learning_rate": 3.1880984952120386e-05, "loss": 3.6359, "step": 212000 }, { "epoch": 3.63, "learning_rate": 3.183823529411765e-05, "loss": 3.6567, "step": 212500 }, { "epoch": 3.64, "learning_rate": 3.1795485636114916e-05, "loss": 3.6573, "step": 213000 }, { "epoch": 3.65, "learning_rate": 3.175273597811218e-05, "loss": 3.6925, "step": 213500 }, { "epoch": 3.66, "learning_rate": 3.170998632010944e-05, "loss": 3.6791, "step": 214000 }, { "epoch": 3.67, "learning_rate": 3.16672366621067e-05, "loss": 3.6442, "step": 214500 }, { "epoch": 3.68, "learning_rate": 3.162465800273598e-05, "loss": 3.7027, "step": 215000 }, { "epoch": 3.69, "learning_rate": 3.158190834473324e-05, "loss": 3.6328, "step": 215500 }, { "epoch": 3.69, "learning_rate": 3.153915868673051e-05, "loss": 3.6454, "step": 216000 }, { "epoch": 3.7, "learning_rate": 3.149649452804378e-05, "loss": 3.652, "step": 216500 }, { "epoch": 3.71, "learning_rate": 3.145374487004104e-05, "loss": 3.65, "step": 217000 }, { "epoch": 3.72, "learning_rate": 3.141099521203831e-05, "loss": 3.6305, "step": 217500 }, { "epoch": 3.73, "learning_rate": 3.136824555403557e-05, "loss": 3.6276, "step": 218000 }, { "epoch": 3.74, "learning_rate": 3.132549589603284e-05, "loss": 3.6349, "step": 218500 }, { "epoch": 3.74, "learning_rate": 3.12827462380301e-05, "loss": 3.6308, "step": 219000 }, { "epoch": 3.75, "learning_rate": 3.123999658002736e-05, "loss": 3.6472, "step": 219500 }, { "epoch": 3.76, "learning_rate": 3.119724692202462e-05, "loss": 3.6328, "step": 220000 }, { "epoch": 3.77, "learning_rate": 3.1154497264021884e-05, "loss": 3.639, "step": 220500 }, { "epoch": 3.78, "learning_rate": 3.111174760601915e-05, "loss": 3.6443, "step": 221000 }, { "epoch": 3.79, "learning_rate": 3.1068997948016414e-05, "loss": 3.6169, "step": 221500 }, { "epoch": 3.8, "learning_rate": 3.102624829001368e-05, "loss": 3.5953, "step": 222000 }, { "epoch": 3.8, "learning_rate": 3.0983498632010944e-05, "loss": 3.6557, "step": 222500 }, { "epoch": 3.81, "learning_rate": 3.094074897400821e-05, "loss": 3.6413, "step": 223000 }, { "epoch": 3.82, "learning_rate": 3.0897999316005474e-05, "loss": 3.6051, "step": 223500 }, { "epoch": 3.83, "learning_rate": 3.0855249658002735e-05, "loss": 3.6098, "step": 224000 }, { "epoch": 3.84, "learning_rate": 3.08125e-05, "loss": 3.6039, "step": 224500 }, { "epoch": 3.85, "learning_rate": 3.076983584131327e-05, "loss": 3.6379, "step": 225000 }, { "epoch": 3.86, "learning_rate": 3.072717168262654e-05, "loss": 3.6024, "step": 225500 }, { "epoch": 3.86, "learning_rate": 3.0684422024623804e-05, "loss": 3.6483, "step": 226000 }, { "epoch": 3.87, "learning_rate": 3.0641672366621066e-05, "loss": 3.6347, "step": 226500 }, { "epoch": 3.88, "learning_rate": 3.0598922708618334e-05, "loss": 3.6107, "step": 227000 }, { "epoch": 3.89, "learning_rate": 3.0556173050615596e-05, "loss": 3.584, "step": 227500 }, { "epoch": 3.9, "learning_rate": 3.051342339261286e-05, "loss": 3.6444, "step": 228000 }, { "epoch": 3.91, "learning_rate": 3.0470844733242138e-05, "loss": 3.5928, "step": 228500 }, { "epoch": 3.92, "learning_rate": 3.04280950752394e-05, "loss": 3.6176, "step": 229000 }, { "epoch": 3.92, "learning_rate": 3.0385345417236665e-05, "loss": 3.6444, "step": 229500 }, { "epoch": 3.93, "learning_rate": 3.0342595759233926e-05, "loss": 3.6084, "step": 230000 }, { "epoch": 3.94, "learning_rate": 3.0299846101231195e-05, "loss": 3.6357, "step": 230500 }, { "epoch": 3.95, "learning_rate": 3.0257096443228456e-05, "loss": 3.6135, "step": 231000 }, { "epoch": 3.96, "learning_rate": 3.0214432284541726e-05, "loss": 3.6289, "step": 231500 }, { "epoch": 3.97, "learning_rate": 3.0171682626538987e-05, "loss": 3.5722, "step": 232000 }, { "epoch": 3.98, "learning_rate": 3.0128932968536256e-05, "loss": 3.5999, "step": 232500 }, { "epoch": 3.98, "learning_rate": 3.0086183310533517e-05, "loss": 3.6273, "step": 233000 }, { "epoch": 3.99, "learning_rate": 3.0043433652530782e-05, "loss": 3.6238, "step": 233500 }, { "epoch": 4.0, "learning_rate": 3.0000683994528044e-05, "loss": 3.6198, "step": 234000 }, { "epoch": 4.01, "learning_rate": 2.9957934336525312e-05, "loss": 3.5947, "step": 234500 }, { "epoch": 4.02, "learning_rate": 2.9915184678522574e-05, "loss": 3.5988, "step": 235000 }, { "epoch": 4.03, "learning_rate": 2.9872520519835846e-05, "loss": 3.6401, "step": 235500 }, { "epoch": 4.04, "learning_rate": 2.9829770861833105e-05, "loss": 3.5982, "step": 236000 }, { "epoch": 4.04, "learning_rate": 2.9787021203830373e-05, "loss": 3.6065, "step": 236500 }, { "epoch": 4.05, "learning_rate": 2.9744271545827635e-05, "loss": 3.5934, "step": 237000 }, { "epoch": 4.06, "learning_rate": 2.9701521887824903e-05, "loss": 3.6165, "step": 237500 }, { "epoch": 4.07, "learning_rate": 2.965877222982216e-05, "loss": 3.6021, "step": 238000 }, { "epoch": 4.08, "learning_rate": 2.9616108071135434e-05, "loss": 3.5716, "step": 238500 }, { "epoch": 4.09, "learning_rate": 2.9573358413132696e-05, "loss": 3.586, "step": 239000 }, { "epoch": 4.1, "learning_rate": 2.9530608755129964e-05, "loss": 3.5593, "step": 239500 }, { "epoch": 4.1, "learning_rate": 2.9487859097127226e-05, "loss": 3.5961, "step": 240000 }, { "epoch": 4.11, "learning_rate": 2.944510943912449e-05, "loss": 3.6181, "step": 240500 }, { "epoch": 4.12, "learning_rate": 2.9402359781121752e-05, "loss": 3.5566, "step": 241000 }, { "epoch": 4.13, "learning_rate": 2.935961012311902e-05, "loss": 3.6061, "step": 241500 }, { "epoch": 4.14, "learning_rate": 2.9316860465116282e-05, "loss": 3.5411, "step": 242000 }, { "epoch": 4.15, "learning_rate": 2.9274281805745556e-05, "loss": 3.611, "step": 242500 }, { "epoch": 4.16, "learning_rate": 2.9231532147742818e-05, "loss": 3.5573, "step": 243000 }, { "epoch": 4.16, "learning_rate": 2.9188782489740086e-05, "loss": 3.5306, "step": 243500 }, { "epoch": 4.17, "learning_rate": 2.9146032831737348e-05, "loss": 3.5944, "step": 244000 }, { "epoch": 4.18, "learning_rate": 2.9103283173734613e-05, "loss": 3.5923, "step": 244500 }, { "epoch": 4.19, "learning_rate": 2.9060533515731874e-05, "loss": 3.5753, "step": 245000 }, { "epoch": 4.2, "learning_rate": 2.9017783857729142e-05, "loss": 3.5432, "step": 245500 }, { "epoch": 4.21, "learning_rate": 2.8975034199726404e-05, "loss": 3.5776, "step": 246000 }, { "epoch": 4.22, "learning_rate": 2.8932370041039674e-05, "loss": 3.5678, "step": 246500 }, { "epoch": 4.22, "learning_rate": 2.8889620383036935e-05, "loss": 3.6039, "step": 247000 }, { "epoch": 4.23, "learning_rate": 2.8846870725034204e-05, "loss": 3.5598, "step": 247500 }, { "epoch": 4.24, "learning_rate": 2.8804121067031465e-05, "loss": 3.5603, "step": 248000 }, { "epoch": 4.25, "learning_rate": 2.876137140902873e-05, "loss": 3.5818, "step": 248500 }, { "epoch": 4.26, "learning_rate": 2.871862175102599e-05, "loss": 3.5812, "step": 249000 }, { "epoch": 4.27, "learning_rate": 2.867587209302326e-05, "loss": 3.5672, "step": 249500 }, { "epoch": 4.27, "learning_rate": 2.863312243502052e-05, "loss": 3.5282, "step": 250000 }, { "epoch": 4.28, "learning_rate": 2.8590372777017787e-05, "loss": 3.5677, "step": 250500 }, { "epoch": 4.29, "learning_rate": 2.8547623119015048e-05, "loss": 3.5776, "step": 251000 }, { "epoch": 4.3, "learning_rate": 2.8504873461012316e-05, "loss": 3.5628, "step": 251500 }, { "epoch": 4.31, "learning_rate": 2.8462123803009578e-05, "loss": 3.5765, "step": 252000 }, { "epoch": 4.32, "learning_rate": 2.8419374145006843e-05, "loss": 3.5115, "step": 252500 }, { "epoch": 4.33, "learning_rate": 2.8376624487004105e-05, "loss": 3.5378, "step": 253000 }, { "epoch": 4.33, "learning_rate": 2.8333960328317378e-05, "loss": 3.5737, "step": 253500 }, { "epoch": 4.34, "learning_rate": 2.8291296169630644e-05, "loss": 3.5697, "step": 254000 }, { "epoch": 4.35, "learning_rate": 2.824854651162791e-05, "loss": 3.5255, "step": 254500 }, { "epoch": 4.36, "learning_rate": 2.820579685362517e-05, "loss": 3.5434, "step": 255000 }, { "epoch": 4.37, "learning_rate": 2.816304719562244e-05, "loss": 3.5507, "step": 255500 }, { "epoch": 4.38, "learning_rate": 2.8120383036935705e-05, "loss": 3.5848, "step": 256000 }, { "epoch": 4.39, "learning_rate": 2.8077633378932973e-05, "loss": 3.5669, "step": 256500 }, { "epoch": 4.39, "learning_rate": 2.803488372093023e-05, "loss": 3.5171, "step": 257000 }, { "epoch": 4.4, "learning_rate": 2.79921340629275e-05, "loss": 3.5614, "step": 257500 }, { "epoch": 4.41, "learning_rate": 2.794938440492476e-05, "loss": 3.5958, "step": 258000 }, { "epoch": 4.42, "learning_rate": 2.790663474692203e-05, "loss": 3.5079, "step": 258500 }, { "epoch": 4.43, "learning_rate": 2.7863885088919288e-05, "loss": 3.5361, "step": 259000 }, { "epoch": 4.44, "learning_rate": 2.7821135430916556e-05, "loss": 3.4883, "step": 259500 }, { "epoch": 4.45, "learning_rate": 2.7778385772913818e-05, "loss": 3.5404, "step": 260000 }, { "epoch": 4.45, "learning_rate": 2.7735636114911086e-05, "loss": 3.5473, "step": 260500 }, { "epoch": 4.46, "learning_rate": 2.7692886456908344e-05, "loss": 3.5328, "step": 261000 }, { "epoch": 4.47, "learning_rate": 2.765030779753762e-05, "loss": 3.5019, "step": 261500 }, { "epoch": 4.48, "learning_rate": 2.7607558139534883e-05, "loss": 3.5022, "step": 262000 }, { "epoch": 4.49, "learning_rate": 2.756480848153215e-05, "loss": 3.5488, "step": 262500 }, { "epoch": 4.5, "learning_rate": 2.7522058823529413e-05, "loss": 3.5467, "step": 263000 }, { "epoch": 4.51, "learning_rate": 2.7479309165526678e-05, "loss": 3.5505, "step": 263500 }, { "epoch": 4.51, "learning_rate": 2.743655950752394e-05, "loss": 3.5297, "step": 264000 }, { "epoch": 4.52, "learning_rate": 2.7393809849521208e-05, "loss": 3.5056, "step": 264500 }, { "epoch": 4.53, "learning_rate": 2.735106019151847e-05, "loss": 3.5086, "step": 265000 }, { "epoch": 4.54, "learning_rate": 2.7308310533515735e-05, "loss": 3.5174, "step": 265500 }, { "epoch": 4.55, "learning_rate": 2.7265646374829e-05, "loss": 3.5264, "step": 266000 }, { "epoch": 4.56, "learning_rate": 2.7223067715458278e-05, "loss": 3.5034, "step": 266500 }, { "epoch": 4.57, "learning_rate": 2.718031805745554e-05, "loss": 3.4838, "step": 267000 }, { "epoch": 4.57, "learning_rate": 2.7137568399452805e-05, "loss": 3.4903, "step": 267500 }, { "epoch": 4.58, "learning_rate": 2.7094818741450066e-05, "loss": 3.5118, "step": 268000 }, { "epoch": 4.59, "learning_rate": 2.7052069083447335e-05, "loss": 3.5055, "step": 268500 }, { "epoch": 4.6, "learning_rate": 2.7009319425444596e-05, "loss": 3.5211, "step": 269000 }, { "epoch": 4.61, "learning_rate": 2.696656976744186e-05, "loss": 3.5344, "step": 269500 }, { "epoch": 4.62, "learning_rate": 2.6923820109439123e-05, "loss": 3.514, "step": 270000 }, { "epoch": 4.63, "learning_rate": 2.688107045143639e-05, "loss": 3.473, "step": 270500 }, { "epoch": 4.63, "learning_rate": 2.6838320793433653e-05, "loss": 3.4917, "step": 271000 }, { "epoch": 4.64, "learning_rate": 2.6795571135430918e-05, "loss": 3.5179, "step": 271500 }, { "epoch": 4.65, "learning_rate": 2.675282147742818e-05, "loss": 3.5437, "step": 272000 }, { "epoch": 4.66, "learning_rate": 2.6710157318741452e-05, "loss": 3.5061, "step": 272500 }, { "epoch": 4.67, "learning_rate": 2.6667407660738714e-05, "loss": 3.4961, "step": 273000 }, { "epoch": 4.68, "learning_rate": 2.6624743502051986e-05, "loss": 3.5111, "step": 273500 }, { "epoch": 4.69, "learning_rate": 2.6582079343365256e-05, "loss": 3.4927, "step": 274000 }, { "epoch": 4.69, "learning_rate": 2.6539329685362518e-05, "loss": 3.4917, "step": 274500 }, { "epoch": 4.7, "learning_rate": 2.649658002735978e-05, "loss": 3.5134, "step": 275000 }, { "epoch": 4.71, "learning_rate": 2.6453830369357048e-05, "loss": 3.5344, "step": 275500 }, { "epoch": 4.72, "learning_rate": 2.641108071135431e-05, "loss": 3.5493, "step": 276000 }, { "epoch": 4.73, "learning_rate": 2.6368331053351574e-05, "loss": 3.4894, "step": 276500 }, { "epoch": 4.74, "learning_rate": 2.6325581395348836e-05, "loss": 3.4784, "step": 277000 }, { "epoch": 4.75, "learning_rate": 2.6282831737346104e-05, "loss": 3.4885, "step": 277500 }, { "epoch": 4.75, "learning_rate": 2.6240082079343366e-05, "loss": 3.5024, "step": 278000 }, { "epoch": 4.76, "learning_rate": 2.6197417920656635e-05, "loss": 3.5195, "step": 278500 }, { "epoch": 4.77, "learning_rate": 2.6154668262653897e-05, "loss": 3.4709, "step": 279000 }, { "epoch": 4.78, "learning_rate": 2.6111918604651165e-05, "loss": 3.4902, "step": 279500 }, { "epoch": 4.79, "learning_rate": 2.6069168946648427e-05, "loss": 3.4905, "step": 280000 }, { "epoch": 4.8, "learning_rate": 2.602641928864569e-05, "loss": 3.5166, "step": 280500 }, { "epoch": 4.81, "learning_rate": 2.5983669630642953e-05, "loss": 3.5104, "step": 281000 }, { "epoch": 4.81, "learning_rate": 2.594091997264022e-05, "loss": 3.495, "step": 281500 }, { "epoch": 4.82, "learning_rate": 2.5898170314637483e-05, "loss": 3.4946, "step": 282000 }, { "epoch": 4.83, "learning_rate": 2.5855506155950753e-05, "loss": 3.4997, "step": 282500 }, { "epoch": 4.84, "learning_rate": 2.5812756497948014e-05, "loss": 3.5034, "step": 283000 }, { "epoch": 4.85, "learning_rate": 2.5770006839945283e-05, "loss": 3.5261, "step": 283500 }, { "epoch": 4.86, "learning_rate": 2.5727342681258555e-05, "loss": 3.4806, "step": 284000 }, { "epoch": 4.86, "learning_rate": 2.568467852257182e-05, "loss": 3.4998, "step": 284500 }, { "epoch": 4.87, "learning_rate": 2.5641928864569086e-05, "loss": 3.5056, "step": 285000 }, { "epoch": 4.88, "learning_rate": 2.5599179206566348e-05, "loss": 3.4693, "step": 285500 }, { "epoch": 4.89, "learning_rate": 2.5556429548563616e-05, "loss": 3.4825, "step": 286000 }, { "epoch": 4.9, "learning_rate": 2.5513679890560878e-05, "loss": 3.4755, "step": 286500 }, { "epoch": 4.91, "learning_rate": 2.5470930232558143e-05, "loss": 3.4791, "step": 287000 }, { "epoch": 4.92, "learning_rate": 2.5428180574555405e-05, "loss": 3.4761, "step": 287500 }, { "epoch": 4.92, "learning_rate": 2.5385430916552666e-05, "loss": 3.4529, "step": 288000 }, { "epoch": 4.93, "learning_rate": 2.5342681258549934e-05, "loss": 3.5147, "step": 288500 }, { "epoch": 4.94, "learning_rate": 2.5299931600547193e-05, "loss": 3.4524, "step": 289000 }, { "epoch": 4.95, "learning_rate": 2.525718194254446e-05, "loss": 3.4681, "step": 289500 }, { "epoch": 4.96, "learning_rate": 2.5214432284541723e-05, "loss": 3.4865, "step": 290000 }, { "epoch": 4.97, "learning_rate": 2.517168262653899e-05, "loss": 3.5144, "step": 290500 }, { "epoch": 4.98, "learning_rate": 2.512893296853625e-05, "loss": 3.4747, "step": 291000 }, { "epoch": 4.98, "learning_rate": 2.5086183310533518e-05, "loss": 3.4518, "step": 291500 }, { "epoch": 4.99, "learning_rate": 2.504343365253078e-05, "loss": 3.5175, "step": 292000 }, { "epoch": 5.0, "learning_rate": 2.5000683994528044e-05, "loss": 3.4788, "step": 292500 }, { "epoch": 5.01, "learning_rate": 2.495793433652531e-05, "loss": 3.4503, "step": 293000 }, { "epoch": 5.02, "learning_rate": 2.491527017783858e-05, "loss": 3.4625, "step": 293500 }, { "epoch": 5.03, "learning_rate": 2.4872520519835844e-05, "loss": 3.4698, "step": 294000 }, { "epoch": 5.04, "learning_rate": 2.482977086183311e-05, "loss": 3.4249, "step": 294500 }, { "epoch": 5.04, "learning_rate": 2.478702120383037e-05, "loss": 3.4456, "step": 295000 }, { "epoch": 5.05, "learning_rate": 2.4744271545827635e-05, "loss": 3.4807, "step": 295500 }, { "epoch": 5.06, "learning_rate": 2.4701607387140905e-05, "loss": 3.4461, "step": 296000 }, { "epoch": 5.07, "learning_rate": 2.465885772913817e-05, "loss": 3.4426, "step": 296500 }, { "epoch": 5.08, "learning_rate": 2.461619357045144e-05, "loss": 3.4572, "step": 297000 }, { "epoch": 5.09, "learning_rate": 2.4573529411764705e-05, "loss": 3.4423, "step": 297500 }, { "epoch": 5.1, "learning_rate": 2.453077975376197e-05, "loss": 3.4409, "step": 298000 }, { "epoch": 5.1, "learning_rate": 2.4488030095759235e-05, "loss": 3.4681, "step": 298500 }, { "epoch": 5.11, "learning_rate": 2.44452804377565e-05, "loss": 3.4573, "step": 299000 }, { "epoch": 5.12, "learning_rate": 2.4402616279069766e-05, "loss": 3.4584, "step": 299500 }, { "epoch": 5.13, "learning_rate": 2.435986662106703e-05, "loss": 3.4655, "step": 300000 }, { "epoch": 5.14, "learning_rate": 2.4317116963064296e-05, "loss": 3.4626, "step": 300500 }, { "epoch": 5.15, "learning_rate": 2.427436730506156e-05, "loss": 3.475, "step": 301000 }, { "epoch": 5.16, "learning_rate": 2.4231617647058823e-05, "loss": 3.4343, "step": 301500 }, { "epoch": 5.16, "learning_rate": 2.4188867989056088e-05, "loss": 3.4596, "step": 302000 }, { "epoch": 5.17, "learning_rate": 2.4146118331053353e-05, "loss": 3.419, "step": 302500 }, { "epoch": 5.18, "learning_rate": 2.4103368673050618e-05, "loss": 3.4769, "step": 303000 }, { "epoch": 5.19, "learning_rate": 2.4060704514363887e-05, "loss": 3.4209, "step": 303500 }, { "epoch": 5.2, "learning_rate": 2.401795485636115e-05, "loss": 3.4429, "step": 304000 }, { "epoch": 5.21, "learning_rate": 2.3975205198358414e-05, "loss": 3.4464, "step": 304500 }, { "epoch": 5.22, "learning_rate": 2.393245554035568e-05, "loss": 3.4602, "step": 305000 }, { "epoch": 5.22, "learning_rate": 2.3889705882352943e-05, "loss": 3.465, "step": 305500 }, { "epoch": 5.23, "learning_rate": 2.3846956224350205e-05, "loss": 3.4138, "step": 306000 }, { "epoch": 5.24, "learning_rate": 2.380420656634747e-05, "loss": 3.4305, "step": 306500 }, { "epoch": 5.25, "learning_rate": 2.3761456908344735e-05, "loss": 3.4451, "step": 307000 }, { "epoch": 5.26, "learning_rate": 2.3718707250341997e-05, "loss": 3.4466, "step": 307500 }, { "epoch": 5.27, "learning_rate": 2.367595759233926e-05, "loss": 3.471, "step": 308000 }, { "epoch": 5.28, "learning_rate": 2.363329343365253e-05, "loss": 3.4632, "step": 308500 }, { "epoch": 5.28, "learning_rate": 2.3590543775649796e-05, "loss": 3.4416, "step": 309000 }, { "epoch": 5.29, "learning_rate": 2.354779411764706e-05, "loss": 3.4338, "step": 309500 }, { "epoch": 5.3, "learning_rate": 2.3505129958960327e-05, "loss": 3.391, "step": 310000 }, { "epoch": 5.31, "learning_rate": 2.3462380300957592e-05, "loss": 3.4299, "step": 310500 }, { "epoch": 5.32, "learning_rate": 2.3419630642954857e-05, "loss": 3.4384, "step": 311000 }, { "epoch": 5.33, "learning_rate": 2.3376880984952122e-05, "loss": 3.414, "step": 311500 }, { "epoch": 5.34, "learning_rate": 2.3334131326949384e-05, "loss": 3.378, "step": 312000 }, { "epoch": 5.34, "learning_rate": 2.329138166894665e-05, "loss": 3.4163, "step": 312500 }, { "epoch": 5.35, "learning_rate": 2.3248632010943914e-05, "loss": 3.4059, "step": 313000 }, { "epoch": 5.36, "learning_rate": 2.3205967852257183e-05, "loss": 3.4266, "step": 313500 }, { "epoch": 5.37, "learning_rate": 2.3163218194254445e-05, "loss": 3.4346, "step": 314000 }, { "epoch": 5.38, "learning_rate": 2.312046853625171e-05, "loss": 3.4367, "step": 314500 }, { "epoch": 5.39, "learning_rate": 2.3077718878248975e-05, "loss": 3.4176, "step": 315000 }, { "epoch": 5.4, "learning_rate": 2.303496922024624e-05, "loss": 3.4402, "step": 315500 }, { "epoch": 5.4, "learning_rate": 2.29922195622435e-05, "loss": 3.4373, "step": 316000 }, { "epoch": 5.41, "learning_rate": 2.2949469904240766e-05, "loss": 3.3886, "step": 316500 }, { "epoch": 5.42, "learning_rate": 2.290672024623803e-05, "loss": 3.3978, "step": 317000 }, { "epoch": 5.43, "learning_rate": 2.2863970588235296e-05, "loss": 3.407, "step": 317500 }, { "epoch": 5.44, "learning_rate": 2.2821220930232558e-05, "loss": 3.4255, "step": 318000 }, { "epoch": 5.45, "learning_rate": 2.2778471272229823e-05, "loss": 3.4385, "step": 318500 }, { "epoch": 5.45, "learning_rate": 2.2735807113543092e-05, "loss": 3.403, "step": 319000 }, { "epoch": 5.46, "learning_rate": 2.269314295485636e-05, "loss": 3.4244, "step": 319500 }, { "epoch": 5.47, "learning_rate": 2.2650393296853627e-05, "loss": 3.4243, "step": 320000 }, { "epoch": 5.48, "learning_rate": 2.2607643638850888e-05, "loss": 3.427, "step": 320500 }, { "epoch": 5.49, "learning_rate": 2.2564893980848153e-05, "loss": 3.4355, "step": 321000 }, { "epoch": 5.5, "learning_rate": 2.2522144322845418e-05, "loss": 3.4011, "step": 321500 }, { "epoch": 5.51, "learning_rate": 2.2479394664842683e-05, "loss": 3.3819, "step": 322000 }, { "epoch": 5.51, "learning_rate": 2.2436645006839945e-05, "loss": 3.4081, "step": 322500 }, { "epoch": 5.52, "learning_rate": 2.239389534883721e-05, "loss": 3.3752, "step": 323000 }, { "epoch": 5.53, "learning_rate": 2.2351145690834475e-05, "loss": 3.4235, "step": 323500 }, { "epoch": 5.54, "learning_rate": 2.2308481532147744e-05, "loss": 3.4504, "step": 324000 }, { "epoch": 5.55, "learning_rate": 2.2265731874145006e-05, "loss": 3.4153, "step": 324500 }, { "epoch": 5.56, "learning_rate": 2.2223067715458275e-05, "loss": 3.4146, "step": 325000 }, { "epoch": 5.57, "learning_rate": 2.218031805745554e-05, "loss": 3.3772, "step": 325500 }, { "epoch": 5.57, "learning_rate": 2.2137568399452805e-05, "loss": 3.4264, "step": 326000 }, { "epoch": 5.58, "learning_rate": 2.209481874145007e-05, "loss": 3.3695, "step": 326500 }, { "epoch": 5.59, "learning_rate": 2.205206908344733e-05, "loss": 3.3935, "step": 327000 }, { "epoch": 5.6, "learning_rate": 2.2009319425444597e-05, "loss": 3.4186, "step": 327500 }, { "epoch": 5.61, "learning_rate": 2.196656976744186e-05, "loss": 3.4184, "step": 328000 }, { "epoch": 5.62, "learning_rate": 2.1923820109439126e-05, "loss": 3.4167, "step": 328500 }, { "epoch": 5.63, "learning_rate": 2.1881070451436388e-05, "loss": 3.397, "step": 329000 }, { "epoch": 5.63, "learning_rate": 2.1838320793433653e-05, "loss": 3.3996, "step": 329500 }, { "epoch": 5.64, "learning_rate": 2.1795571135430918e-05, "loss": 3.3878, "step": 330000 }, { "epoch": 5.65, "learning_rate": 2.1752821477428183e-05, "loss": 3.43, "step": 330500 }, { "epoch": 5.66, "learning_rate": 2.1710071819425445e-05, "loss": 3.4278, "step": 331000 }, { "epoch": 5.67, "learning_rate": 2.1667407660738714e-05, "loss": 3.3853, "step": 331500 }, { "epoch": 5.68, "learning_rate": 2.162465800273598e-05, "loss": 3.4041, "step": 332000 }, { "epoch": 5.69, "learning_rate": 2.1581908344733244e-05, "loss": 3.4038, "step": 332500 }, { "epoch": 5.69, "learning_rate": 2.153924418604651e-05, "loss": 3.3846, "step": 333000 }, { "epoch": 5.7, "learning_rate": 2.1496494528043775e-05, "loss": 3.3813, "step": 333500 }, { "epoch": 5.71, "learning_rate": 2.145374487004104e-05, "loss": 3.3934, "step": 334000 }, { "epoch": 5.72, "learning_rate": 2.1410995212038305e-05, "loss": 3.3566, "step": 334500 }, { "epoch": 5.73, "learning_rate": 2.1368331053351574e-05, "loss": 3.3997, "step": 335000 }, { "epoch": 5.74, "learning_rate": 2.1325581395348836e-05, "loss": 3.4148, "step": 335500 }, { "epoch": 5.75, "learning_rate": 2.12828317373461e-05, "loss": 3.3976, "step": 336000 }, { "epoch": 5.75, "learning_rate": 2.1240082079343366e-05, "loss": 3.3818, "step": 336500 }, { "epoch": 5.76, "learning_rate": 2.119733242134063e-05, "loss": 3.3871, "step": 337000 }, { "epoch": 5.77, "learning_rate": 2.1154582763337893e-05, "loss": 3.3902, "step": 337500 }, { "epoch": 5.78, "learning_rate": 2.1111833105335158e-05, "loss": 3.4124, "step": 338000 }, { "epoch": 5.79, "learning_rate": 2.1069083447332423e-05, "loss": 3.3734, "step": 338500 }, { "epoch": 5.8, "learning_rate": 2.1026333789329684e-05, "loss": 3.3685, "step": 339000 }, { "epoch": 5.81, "learning_rate": 2.0983669630642954e-05, "loss": 3.3705, "step": 339500 }, { "epoch": 5.81, "learning_rate": 2.094091997264022e-05, "loss": 3.4106, "step": 340000 }, { "epoch": 5.82, "learning_rate": 2.0898170314637484e-05, "loss": 3.353, "step": 340500 }, { "epoch": 5.83, "learning_rate": 2.085542065663475e-05, "loss": 3.3443, "step": 341000 }, { "epoch": 5.84, "learning_rate": 2.081267099863201e-05, "loss": 3.3696, "step": 341500 }, { "epoch": 5.85, "learning_rate": 2.0769921340629275e-05, "loss": 3.3473, "step": 342000 }, { "epoch": 5.86, "learning_rate": 2.0727257181942545e-05, "loss": 3.3947, "step": 342500 }, { "epoch": 5.87, "learning_rate": 2.068450752393981e-05, "loss": 3.3491, "step": 343000 }, { "epoch": 5.87, "learning_rate": 2.064175786593707e-05, "loss": 3.3899, "step": 343500 }, { "epoch": 5.88, "learning_rate": 2.0599093707250344e-05, "loss": 3.3883, "step": 344000 }, { "epoch": 5.89, "learning_rate": 2.055634404924761e-05, "loss": 3.3623, "step": 344500 }, { "epoch": 5.9, "learning_rate": 2.051359439124487e-05, "loss": 3.3721, "step": 345000 }, { "epoch": 5.91, "learning_rate": 2.0470844733242135e-05, "loss": 3.3933, "step": 345500 }, { "epoch": 5.92, "learning_rate": 2.0428095075239397e-05, "loss": 3.3948, "step": 346000 }, { "epoch": 5.93, "learning_rate": 2.0385345417236662e-05, "loss": 3.3827, "step": 346500 }, { "epoch": 5.93, "learning_rate": 2.0342681258549935e-05, "loss": 3.367, "step": 347000 }, { "epoch": 5.94, "learning_rate": 2.0299931600547197e-05, "loss": 3.3329, "step": 347500 }, { "epoch": 5.95, "learning_rate": 2.025718194254446e-05, "loss": 3.3715, "step": 348000 }, { "epoch": 5.96, "learning_rate": 2.0214432284541723e-05, "loss": 3.356, "step": 348500 }, { "epoch": 5.97, "learning_rate": 2.0171682626538988e-05, "loss": 3.3729, "step": 349000 }, { "epoch": 5.98, "learning_rate": 2.0128932968536253e-05, "loss": 3.4025, "step": 349500 }, { "epoch": 5.98, "learning_rate": 2.0086268809849522e-05, "loss": 3.3937, "step": 350000 }, { "epoch": 5.99, "learning_rate": 2.0043519151846787e-05, "loss": 3.3799, "step": 350500 }, { "epoch": 6.0, "learning_rate": 2.0000854993160057e-05, "loss": 3.3702, "step": 351000 }, { "epoch": 6.01, "learning_rate": 1.9958105335157322e-05, "loss": 3.3405, "step": 351500 }, { "epoch": 6.02, "learning_rate": 1.9915441176470588e-05, "loss": 3.3531, "step": 352000 }, { "epoch": 6.03, "learning_rate": 1.9872691518467853e-05, "loss": 3.3501, "step": 352500 }, { "epoch": 6.04, "learning_rate": 1.9829941860465118e-05, "loss": 3.3631, "step": 353000 }, { "epoch": 6.04, "learning_rate": 1.9787192202462383e-05, "loss": 3.3329, "step": 353500 }, { "epoch": 6.05, "learning_rate": 1.9744442544459645e-05, "loss": 3.3577, "step": 354000 }, { "epoch": 6.06, "learning_rate": 1.970169288645691e-05, "loss": 3.3682, "step": 354500 }, { "epoch": 6.07, "learning_rate": 1.9658943228454174e-05, "loss": 3.3475, "step": 355000 }, { "epoch": 6.08, "learning_rate": 1.961619357045144e-05, "loss": 3.3654, "step": 355500 }, { "epoch": 6.09, "learning_rate": 1.95734439124487e-05, "loss": 3.3688, "step": 356000 }, { "epoch": 6.1, "learning_rate": 1.9530694254445966e-05, "loss": 3.3577, "step": 356500 }, { "epoch": 6.1, "learning_rate": 1.948794459644323e-05, "loss": 3.3702, "step": 357000 }, { "epoch": 6.11, "learning_rate": 1.9445194938440496e-05, "loss": 3.3792, "step": 357500 }, { "epoch": 6.12, "learning_rate": 1.9402445280437758e-05, "loss": 3.3318, "step": 358000 }, { "epoch": 6.13, "learning_rate": 1.935969562243502e-05, "loss": 3.3837, "step": 358500 }, { "epoch": 6.14, "learning_rate": 1.9316945964432284e-05, "loss": 3.3358, "step": 359000 }, { "epoch": 6.15, "learning_rate": 1.927419630642955e-05, "loss": 3.3344, "step": 359500 }, { "epoch": 6.16, "learning_rate": 1.9231446648426814e-05, "loss": 3.3393, "step": 360000 }, { "epoch": 6.16, "learning_rate": 1.9188696990424076e-05, "loss": 3.3408, "step": 360500 }, { "epoch": 6.17, "learning_rate": 1.914603283173735e-05, "loss": 3.3467, "step": 361000 }, { "epoch": 6.18, "learning_rate": 1.9103368673050618e-05, "loss": 3.3644, "step": 361500 }, { "epoch": 6.19, "learning_rate": 1.9060619015047883e-05, "loss": 3.3719, "step": 362000 }, { "epoch": 6.2, "learning_rate": 1.9017869357045144e-05, "loss": 3.3658, "step": 362500 }, { "epoch": 6.21, "learning_rate": 1.897511969904241e-05, "loss": 3.313, "step": 363000 }, { "epoch": 6.22, "learning_rate": 1.893245554035568e-05, "loss": 3.3477, "step": 363500 }, { "epoch": 6.22, "learning_rate": 1.8889705882352944e-05, "loss": 3.3276, "step": 364000 }, { "epoch": 6.23, "learning_rate": 1.884704172366621e-05, "loss": 3.32, "step": 364500 }, { "epoch": 6.24, "learning_rate": 1.8804292065663475e-05, "loss": 3.3462, "step": 365000 }, { "epoch": 6.25, "learning_rate": 1.876154240766074e-05, "loss": 3.3172, "step": 365500 }, { "epoch": 6.26, "learning_rate": 1.8718792749658005e-05, "loss": 3.3422, "step": 366000 }, { "epoch": 6.27, "learning_rate": 1.8676043091655267e-05, "loss": 3.3399, "step": 366500 }, { "epoch": 6.28, "learning_rate": 1.863329343365253e-05, "loss": 3.3611, "step": 367000 }, { "epoch": 6.28, "learning_rate": 1.8590543775649796e-05, "loss": 3.3353, "step": 367500 }, { "epoch": 6.29, "learning_rate": 1.8547879616963066e-05, "loss": 3.3103, "step": 368000 }, { "epoch": 6.3, "learning_rate": 1.850512995896033e-05, "loss": 3.3291, "step": 368500 }, { "epoch": 6.31, "learning_rate": 1.8462380300957593e-05, "loss": 3.3194, "step": 369000 }, { "epoch": 6.32, "learning_rate": 1.8419630642954857e-05, "loss": 3.3426, "step": 369500 }, { "epoch": 6.33, "learning_rate": 1.8376880984952122e-05, "loss": 3.3213, "step": 370000 }, { "epoch": 6.34, "learning_rate": 1.8334131326949387e-05, "loss": 3.3214, "step": 370500 }, { "epoch": 6.34, "learning_rate": 1.829138166894665e-05, "loss": 3.3211, "step": 371000 }, { "epoch": 6.35, "learning_rate": 1.8248632010943914e-05, "loss": 3.3533, "step": 371500 }, { "epoch": 6.36, "learning_rate": 1.820588235294118e-05, "loss": 3.3376, "step": 372000 }, { "epoch": 6.37, "learning_rate": 1.8163132694938444e-05, "loss": 3.3151, "step": 372500 }, { "epoch": 6.38, "learning_rate": 1.812046853625171e-05, "loss": 3.3452, "step": 373000 }, { "epoch": 6.39, "learning_rate": 1.8077718878248975e-05, "loss": 3.2928, "step": 373500 }, { "epoch": 6.4, "learning_rate": 1.803496922024624e-05, "loss": 3.3321, "step": 374000 }, { "epoch": 6.4, "learning_rate": 1.7992219562243505e-05, "loss": 3.3356, "step": 374500 }, { "epoch": 6.41, "learning_rate": 1.7949469904240767e-05, "loss": 3.3358, "step": 375000 }, { "epoch": 6.42, "learning_rate": 1.790672024623803e-05, "loss": 3.3385, "step": 375500 }, { "epoch": 6.43, "learning_rate": 1.7863970588235296e-05, "loss": 3.3443, "step": 376000 }, { "epoch": 6.44, "learning_rate": 1.7821306429548566e-05, "loss": 3.3189, "step": 376500 }, { "epoch": 6.45, "learning_rate": 1.7778556771545828e-05, "loss": 3.3193, "step": 377000 }, { "epoch": 6.46, "learning_rate": 1.7735807113543092e-05, "loss": 3.3541, "step": 377500 }, { "epoch": 6.46, "learning_rate": 1.7693057455540357e-05, "loss": 3.3244, "step": 378000 }, { "epoch": 6.47, "learning_rate": 1.7650307797537622e-05, "loss": 3.3357, "step": 378500 }, { "epoch": 6.48, "learning_rate": 1.7607643638850892e-05, "loss": 3.3028, "step": 379000 }, { "epoch": 6.49, "learning_rate": 1.7564893980848154e-05, "loss": 3.2885, "step": 379500 }, { "epoch": 6.5, "learning_rate": 1.752214432284542e-05, "loss": 3.3094, "step": 380000 }, { "epoch": 6.51, "learning_rate": 1.7479394664842683e-05, "loss": 3.3171, "step": 380500 }, { "epoch": 6.52, "learning_rate": 1.743664500683995e-05, "loss": 3.3147, "step": 381000 }, { "epoch": 6.52, "learning_rate": 1.739389534883721e-05, "loss": 3.313, "step": 381500 }, { "epoch": 6.53, "learning_rate": 1.7351145690834475e-05, "loss": 3.3385, "step": 382000 }, { "epoch": 6.54, "learning_rate": 1.730839603283174e-05, "loss": 3.3173, "step": 382500 }, { "epoch": 6.55, "learning_rate": 1.726573187414501e-05, "loss": 3.3167, "step": 383000 }, { "epoch": 6.56, "learning_rate": 1.7223067715458276e-05, "loss": 3.2947, "step": 383500 }, { "epoch": 6.57, "learning_rate": 1.718031805745554e-05, "loss": 3.3185, "step": 384000 }, { "epoch": 6.57, "learning_rate": 1.7137568399452805e-05, "loss": 3.3438, "step": 384500 }, { "epoch": 6.58, "learning_rate": 1.709481874145007e-05, "loss": 3.3167, "step": 385000 }, { "epoch": 6.59, "learning_rate": 1.7052069083447332e-05, "loss": 3.3086, "step": 385500 }, { "epoch": 6.6, "learning_rate": 1.7009319425444597e-05, "loss": 3.3146, "step": 386000 }, { "epoch": 6.61, "learning_rate": 1.6966569767441862e-05, "loss": 3.3034, "step": 386500 }, { "epoch": 6.62, "learning_rate": 1.692390560875513e-05, "loss": 3.3163, "step": 387000 }, { "epoch": 6.63, "learning_rate": 1.6881155950752396e-05, "loss": 3.3306, "step": 387500 }, { "epoch": 6.63, "learning_rate": 1.6838406292749658e-05, "loss": 3.2904, "step": 388000 }, { "epoch": 6.64, "learning_rate": 1.6795656634746923e-05, "loss": 3.33, "step": 388500 }, { "epoch": 6.65, "learning_rate": 1.6752906976744188e-05, "loss": 3.2945, "step": 389000 }, { "epoch": 6.66, "learning_rate": 1.671015731874145e-05, "loss": 3.3257, "step": 389500 }, { "epoch": 6.67, "learning_rate": 1.6667407660738714e-05, "loss": 3.3196, "step": 390000 }, { "epoch": 6.68, "learning_rate": 1.662465800273598e-05, "loss": 3.3317, "step": 390500 }, { "epoch": 6.69, "learning_rate": 1.6581908344733244e-05, "loss": 3.2978, "step": 391000 }, { "epoch": 6.69, "learning_rate": 1.6539158686730506e-05, "loss": 3.3037, "step": 391500 }, { "epoch": 6.7, "learning_rate": 1.6496494528043776e-05, "loss": 3.2703, "step": 392000 }, { "epoch": 6.71, "learning_rate": 1.645374487004104e-05, "loss": 3.2918, "step": 392500 }, { "epoch": 6.72, "learning_rate": 1.6410995212038305e-05, "loss": 3.3257, "step": 393000 }, { "epoch": 6.73, "learning_rate": 1.636824555403557e-05, "loss": 3.2756, "step": 393500 }, { "epoch": 6.74, "learning_rate": 1.6325581395348837e-05, "loss": 3.3043, "step": 394000 }, { "epoch": 6.75, "learning_rate": 1.62828317373461e-05, "loss": 3.3169, "step": 394500 }, { "epoch": 6.75, "learning_rate": 1.6240082079343366e-05, "loss": 3.2976, "step": 395000 }, { "epoch": 6.76, "learning_rate": 1.619733242134063e-05, "loss": 3.2912, "step": 395500 }, { "epoch": 6.77, "learning_rate": 1.6154582763337893e-05, "loss": 3.2524, "step": 396000 }, { "epoch": 6.78, "learning_rate": 1.6111918604651163e-05, "loss": 3.293, "step": 396500 }, { "epoch": 6.79, "learning_rate": 1.6069168946648427e-05, "loss": 3.2664, "step": 397000 }, { "epoch": 6.8, "learning_rate": 1.6026419288645692e-05, "loss": 3.2705, "step": 397500 }, { "epoch": 6.81, "learning_rate": 1.5983669630642954e-05, "loss": 3.3202, "step": 398000 }, { "epoch": 6.81, "learning_rate": 1.594091997264022e-05, "loss": 3.3042, "step": 398500 }, { "epoch": 6.82, "learning_rate": 1.589825581395349e-05, "loss": 3.2975, "step": 399000 }, { "epoch": 6.83, "learning_rate": 1.5855506155950753e-05, "loss": 3.305, "step": 399500 }, { "epoch": 6.84, "learning_rate": 1.581275649794802e-05, "loss": 3.2572, "step": 400000 }, { "epoch": 6.85, "learning_rate": 1.5770092339261285e-05, "loss": 3.3046, "step": 400500 }, { "epoch": 6.86, "learning_rate": 1.572734268125855e-05, "loss": 3.2563, "step": 401000 }, { "epoch": 6.87, "learning_rate": 1.5684593023255814e-05, "loss": 3.2936, "step": 401500 }, { "epoch": 6.87, "learning_rate": 1.564184336525308e-05, "loss": 3.3103, "step": 402000 }, { "epoch": 6.88, "learning_rate": 1.559909370725034e-05, "loss": 3.2714, "step": 402500 }, { "epoch": 6.89, "learning_rate": 1.5556344049247606e-05, "loss": 3.3399, "step": 403000 }, { "epoch": 6.9, "learning_rate": 1.551359439124487e-05, "loss": 3.2546, "step": 403500 }, { "epoch": 6.91, "learning_rate": 1.5470844733242136e-05, "loss": 3.282, "step": 404000 }, { "epoch": 6.92, "learning_rate": 1.5428180574555402e-05, "loss": 3.2968, "step": 404500 }, { "epoch": 6.93, "learning_rate": 1.5385430916552667e-05, "loss": 3.2788, "step": 405000 }, { "epoch": 6.93, "learning_rate": 1.5342681258549932e-05, "loss": 3.2715, "step": 405500 }, { "epoch": 6.94, "learning_rate": 1.5299931600547197e-05, "loss": 3.261, "step": 406000 }, { "epoch": 6.95, "learning_rate": 1.525718194254446e-05, "loss": 3.2855, "step": 406500 }, { "epoch": 6.96, "learning_rate": 1.521451778385773e-05, "loss": 3.277, "step": 407000 }, { "epoch": 6.97, "learning_rate": 1.5171853625170997e-05, "loss": 3.3068, "step": 407500 }, { "epoch": 6.98, "learning_rate": 1.5129103967168262e-05, "loss": 3.2982, "step": 408000 }, { "epoch": 6.99, "learning_rate": 1.5086354309165526e-05, "loss": 3.2626, "step": 408500 }, { "epoch": 6.99, "learning_rate": 1.504360465116279e-05, "loss": 3.2685, "step": 409000 }, { "epoch": 7.0, "learning_rate": 1.5000854993160054e-05, "loss": 3.2705, "step": 409500 }, { "epoch": 7.01, "learning_rate": 1.4958105335157319e-05, "loss": 3.3044, "step": 410000 }, { "epoch": 7.02, "learning_rate": 1.4915355677154582e-05, "loss": 3.2707, "step": 410500 }, { "epoch": 7.03, "learning_rate": 1.4872606019151847e-05, "loss": 3.2798, "step": 411000 }, { "epoch": 7.04, "learning_rate": 1.482985636114911e-05, "loss": 3.2493, "step": 411500 }, { "epoch": 7.05, "learning_rate": 1.4787106703146375e-05, "loss": 3.2597, "step": 412000 }, { "epoch": 7.05, "learning_rate": 1.4744357045143639e-05, "loss": 3.275, "step": 412500 }, { "epoch": 7.06, "learning_rate": 1.4701692886456908e-05, "loss": 3.2734, "step": 413000 }, { "epoch": 7.07, "learning_rate": 1.465902872777018e-05, "loss": 3.2437, "step": 413500 }, { "epoch": 7.08, "learning_rate": 1.4616279069767441e-05, "loss": 3.2447, "step": 414000 }, { "epoch": 7.09, "learning_rate": 1.4573529411764706e-05, "loss": 3.293, "step": 414500 }, { "epoch": 7.1, "learning_rate": 1.453077975376197e-05, "loss": 3.2808, "step": 415000 }, { "epoch": 7.1, "learning_rate": 1.4488030095759234e-05, "loss": 3.2617, "step": 415500 }, { "epoch": 7.11, "learning_rate": 1.4445280437756497e-05, "loss": 3.2534, "step": 416000 }, { "epoch": 7.12, "learning_rate": 1.4402530779753762e-05, "loss": 3.2641, "step": 416500 }, { "epoch": 7.13, "learning_rate": 1.4359781121751026e-05, "loss": 3.2449, "step": 417000 }, { "epoch": 7.14, "learning_rate": 1.431703146374829e-05, "loss": 3.2399, "step": 417500 }, { "epoch": 7.15, "learning_rate": 1.4274281805745554e-05, "loss": 3.2933, "step": 418000 }, { "epoch": 7.16, "learning_rate": 1.4231532147742819e-05, "loss": 3.2522, "step": 418500 }, { "epoch": 7.16, "learning_rate": 1.4188782489740082e-05, "loss": 3.2584, "step": 419000 }, { "epoch": 7.17, "learning_rate": 1.4146032831737347e-05, "loss": 3.2633, "step": 419500 }, { "epoch": 7.18, "learning_rate": 1.410328317373461e-05, "loss": 3.2595, "step": 420000 }, { "epoch": 7.19, "learning_rate": 1.4060533515731875e-05, "loss": 3.233, "step": 420500 }, { "epoch": 7.2, "learning_rate": 1.4017869357045143e-05, "loss": 3.2439, "step": 421000 }, { "epoch": 7.21, "learning_rate": 1.3975205198358413e-05, "loss": 3.257, "step": 421500 }, { "epoch": 7.22, "learning_rate": 1.3932455540355676e-05, "loss": 3.2857, "step": 422000 }, { "epoch": 7.22, "learning_rate": 1.3889705882352941e-05, "loss": 3.25, "step": 422500 }, { "epoch": 7.23, "learning_rate": 1.3846956224350204e-05, "loss": 3.2634, "step": 423000 }, { "epoch": 7.24, "learning_rate": 1.380420656634747e-05, "loss": 3.2566, "step": 423500 }, { "epoch": 7.25, "learning_rate": 1.3761456908344733e-05, "loss": 3.2589, "step": 424000 }, { "epoch": 7.26, "learning_rate": 1.3718707250341997e-05, "loss": 3.284, "step": 424500 }, { "epoch": 7.27, "learning_rate": 1.367595759233926e-05, "loss": 3.2565, "step": 425000 }, { "epoch": 7.28, "learning_rate": 1.3633207934336526e-05, "loss": 3.2414, "step": 425500 }, { "epoch": 7.28, "learning_rate": 1.3590543775649795e-05, "loss": 3.2518, "step": 426000 }, { "epoch": 7.29, "learning_rate": 1.3547794117647058e-05, "loss": 3.2658, "step": 426500 }, { "epoch": 7.3, "learning_rate": 1.3505044459644323e-05, "loss": 3.262, "step": 427000 }, { "epoch": 7.31, "learning_rate": 1.3462294801641587e-05, "loss": 3.2322, "step": 427500 }, { "epoch": 7.32, "learning_rate": 1.3419630642954856e-05, "loss": 3.2504, "step": 428000 }, { "epoch": 7.33, "learning_rate": 1.337688098495212e-05, "loss": 3.2753, "step": 428500 }, { "epoch": 7.34, "learning_rate": 1.3334131326949384e-05, "loss": 3.2577, "step": 429000 }, { "epoch": 7.34, "learning_rate": 1.3291381668946648e-05, "loss": 3.2698, "step": 429500 }, { "epoch": 7.35, "learning_rate": 1.3248632010943913e-05, "loss": 3.2636, "step": 430000 }, { "epoch": 7.36, "learning_rate": 1.3205882352941176e-05, "loss": 3.249, "step": 430500 }, { "epoch": 7.37, "learning_rate": 1.3163132694938441e-05, "loss": 3.2515, "step": 431000 }, { "epoch": 7.38, "learning_rate": 1.3120468536251709e-05, "loss": 3.2606, "step": 431500 }, { "epoch": 7.39, "learning_rate": 1.3077718878248974e-05, "loss": 3.258, "step": 432000 }, { "epoch": 7.4, "learning_rate": 1.3034969220246237e-05, "loss": 3.2687, "step": 432500 }, { "epoch": 7.4, "learning_rate": 1.2992219562243502e-05, "loss": 3.2241, "step": 433000 }, { "epoch": 7.41, "learning_rate": 1.2949469904240765e-05, "loss": 3.2589, "step": 433500 }, { "epoch": 7.42, "learning_rate": 1.2906805745554038e-05, "loss": 3.2287, "step": 434000 }, { "epoch": 7.43, "learning_rate": 1.28640560875513e-05, "loss": 3.234, "step": 434500 }, { "epoch": 7.44, "learning_rate": 1.2821306429548563e-05, "loss": 3.2273, "step": 435000 }, { "epoch": 7.45, "learning_rate": 1.2778642270861834e-05, "loss": 3.2778, "step": 435500 }, { "epoch": 7.46, "learning_rate": 1.2735892612859099e-05, "loss": 3.2463, "step": 436000 }, { "epoch": 7.46, "learning_rate": 1.2693142954856362e-05, "loss": 3.2382, "step": 436500 }, { "epoch": 7.47, "learning_rate": 1.2650393296853627e-05, "loss": 3.2488, "step": 437000 }, { "epoch": 7.48, "learning_rate": 1.2607729138166897e-05, "loss": 3.254, "step": 437500 }, { "epoch": 7.49, "learning_rate": 1.256497948016416e-05, "loss": 3.1991, "step": 438000 }, { "epoch": 7.5, "learning_rate": 1.2522229822161423e-05, "loss": 3.2751, "step": 438500 }, { "epoch": 7.51, "learning_rate": 1.2479480164158687e-05, "loss": 3.2693, "step": 439000 }, { "epoch": 7.52, "learning_rate": 1.2436730506155952e-05, "loss": 3.2495, "step": 439500 }, { "epoch": 7.52, "learning_rate": 1.2393980848153215e-05, "loss": 3.2524, "step": 440000 }, { "epoch": 7.53, "learning_rate": 1.235123119015048e-05, "loss": 3.2337, "step": 440500 }, { "epoch": 7.54, "learning_rate": 1.2308481532147743e-05, "loss": 3.2655, "step": 441000 }, { "epoch": 7.55, "learning_rate": 1.2265731874145008e-05, "loss": 3.263, "step": 441500 }, { "epoch": 7.56, "learning_rate": 1.2222982216142271e-05, "loss": 3.2338, "step": 442000 }, { "epoch": 7.57, "learning_rate": 1.2180232558139536e-05, "loss": 3.2083, "step": 442500 }, { "epoch": 7.58, "learning_rate": 1.21374829001368e-05, "loss": 3.2351, "step": 443000 }, { "epoch": 7.58, "learning_rate": 1.2094733242134065e-05, "loss": 3.2481, "step": 443500 }, { "epoch": 7.59, "learning_rate": 1.2051983584131328e-05, "loss": 3.2739, "step": 444000 }, { "epoch": 7.6, "learning_rate": 1.2009233926128593e-05, "loss": 3.2697, "step": 444500 }, { "epoch": 7.61, "learning_rate": 1.1966484268125854e-05, "loss": 3.2032, "step": 445000 }, { "epoch": 7.62, "learning_rate": 1.1923820109439126e-05, "loss": 3.2565, "step": 445500 }, { "epoch": 7.63, "learning_rate": 1.1881070451436389e-05, "loss": 3.237, "step": 446000 }, { "epoch": 7.64, "learning_rate": 1.1838406292749658e-05, "loss": 3.2526, "step": 446500 }, { "epoch": 7.64, "learning_rate": 1.1795656634746922e-05, "loss": 3.2335, "step": 447000 }, { "epoch": 7.65, "learning_rate": 1.1752906976744187e-05, "loss": 3.2464, "step": 447500 }, { "epoch": 7.66, "learning_rate": 1.171015731874145e-05, "loss": 3.2647, "step": 448000 }, { "epoch": 7.67, "learning_rate": 1.166749316005472e-05, "loss": 3.2644, "step": 448500 }, { "epoch": 7.68, "learning_rate": 1.162482900136799e-05, "loss": 3.2278, "step": 449000 }, { "epoch": 7.69, "learning_rate": 1.1582164842681258e-05, "loss": 3.2506, "step": 449500 }, { "epoch": 7.69, "learning_rate": 1.1539415184678523e-05, "loss": 3.2518, "step": 450000 }, { "epoch": 7.7, "learning_rate": 1.1496665526675787e-05, "loss": 3.235, "step": 450500 }, { "epoch": 7.71, "learning_rate": 1.1453915868673052e-05, "loss": 3.2097, "step": 451000 }, { "epoch": 7.72, "learning_rate": 1.1411166210670315e-05, "loss": 3.2222, "step": 451500 }, { "epoch": 7.73, "learning_rate": 1.136841655266758e-05, "loss": 3.2005, "step": 452000 }, { "epoch": 7.74, "learning_rate": 1.1325666894664843e-05, "loss": 3.1938, "step": 452500 }, { "epoch": 7.75, "learning_rate": 1.1282917236662108e-05, "loss": 3.2184, "step": 453000 }, { "epoch": 7.75, "learning_rate": 1.1240167578659371e-05, "loss": 3.2335, "step": 453500 }, { "epoch": 7.76, "learning_rate": 1.1197503419972641e-05, "loss": 3.2127, "step": 454000 }, { "epoch": 7.77, "learning_rate": 1.1154753761969904e-05, "loss": 3.2088, "step": 454500 }, { "epoch": 7.78, "learning_rate": 1.1112089603283174e-05, "loss": 3.2448, "step": 455000 }, { "epoch": 7.79, "learning_rate": 1.1069339945280439e-05, "loss": 3.2104, "step": 455500 }, { "epoch": 7.8, "learning_rate": 1.1026590287277702e-05, "loss": 3.2223, "step": 456000 }, { "epoch": 7.81, "learning_rate": 1.0983840629274967e-05, "loss": 3.2369, "step": 456500 }, { "epoch": 7.81, "learning_rate": 1.094109097127223e-05, "loss": 3.2023, "step": 457000 }, { "epoch": 7.82, "learning_rate": 1.0898341313269495e-05, "loss": 3.2394, "step": 457500 }, { "epoch": 7.83, "learning_rate": 1.0855591655266758e-05, "loss": 3.2306, "step": 458000 }, { "epoch": 7.84, "learning_rate": 1.0812841997264023e-05, "loss": 3.2302, "step": 458500 }, { "epoch": 7.85, "learning_rate": 1.0770092339261287e-05, "loss": 3.2492, "step": 459000 }, { "epoch": 7.86, "learning_rate": 1.0727342681258552e-05, "loss": 3.1999, "step": 459500 }, { "epoch": 7.87, "learning_rate": 1.0684593023255815e-05, "loss": 3.2289, "step": 460000 }, { "epoch": 7.87, "learning_rate": 1.064184336525308e-05, "loss": 3.1947, "step": 460500 }, { "epoch": 7.88, "learning_rate": 1.0599093707250341e-05, "loss": 3.1999, "step": 461000 }, { "epoch": 7.89, "learning_rate": 1.0556344049247606e-05, "loss": 3.2143, "step": 461500 }, { "epoch": 7.9, "learning_rate": 1.0513679890560876e-05, "loss": 3.2127, "step": 462000 }, { "epoch": 7.91, "learning_rate": 1.0470930232558141e-05, "loss": 3.2414, "step": 462500 }, { "epoch": 7.92, "learning_rate": 1.0428180574555404e-05, "loss": 3.2481, "step": 463000 }, { "epoch": 7.93, "learning_rate": 1.0385430916552669e-05, "loss": 3.1932, "step": 463500 }, { "epoch": 7.93, "learning_rate": 1.0342681258549932e-05, "loss": 3.1899, "step": 464000 }, { "epoch": 7.94, "learning_rate": 1.0299931600547196e-05, "loss": 3.2225, "step": 464500 }, { "epoch": 7.95, "learning_rate": 1.0257181942544459e-05, "loss": 3.2112, "step": 465000 }, { "epoch": 7.96, "learning_rate": 1.0214432284541724e-05, "loss": 3.2088, "step": 465500 }, { "epoch": 7.97, "learning_rate": 1.0171768125854993e-05, "loss": 3.2226, "step": 466000 }, { "epoch": 7.98, "learning_rate": 1.0129103967168263e-05, "loss": 3.19, "step": 466500 }, { "epoch": 7.99, "learning_rate": 1.0086354309165528e-05, "loss": 3.2036, "step": 467000 }, { "epoch": 7.99, "learning_rate": 1.0043604651162791e-05, "loss": 3.221, "step": 467500 }, { "epoch": 8.0, "learning_rate": 1.0000854993160056e-05, "loss": 3.2074, "step": 468000 }, { "epoch": 8.01, "learning_rate": 9.95810533515732e-06, "loss": 3.1987, "step": 468500 }, { "epoch": 8.02, "learning_rate": 9.915355677154584e-06, "loss": 3.1829, "step": 469000 }, { "epoch": 8.03, "learning_rate": 9.872606019151848e-06, "loss": 3.1928, "step": 469500 }, { "epoch": 8.04, "learning_rate": 9.829856361149113e-06, "loss": 3.2033, "step": 470000 }, { "epoch": 8.05, "learning_rate": 9.78719220246238e-06, "loss": 3.2044, "step": 470500 }, { "epoch": 8.05, "learning_rate": 9.744442544459645e-06, "loss": 3.1988, "step": 471000 }, { "epoch": 8.06, "learning_rate": 9.701692886456909e-06, "loss": 3.2401, "step": 471500 }, { "epoch": 8.07, "learning_rate": 9.658943228454174e-06, "loss": 3.1829, "step": 472000 }, { "epoch": 8.08, "learning_rate": 9.616193570451437e-06, "loss": 3.1798, "step": 472500 }, { "epoch": 8.09, "learning_rate": 9.573443912448702e-06, "loss": 3.1866, "step": 473000 }, { "epoch": 8.1, "learning_rate": 9.53077975376197e-06, "loss": 3.178, "step": 473500 }, { "epoch": 8.11, "learning_rate": 9.488030095759235e-06, "loss": 3.203, "step": 474000 }, { "epoch": 8.11, "learning_rate": 9.445280437756498e-06, "loss": 3.1573, "step": 474500 }, { "epoch": 8.12, "learning_rate": 9.402530779753763e-06, "loss": 3.229, "step": 475000 }, { "epoch": 8.13, "learning_rate": 9.359866621067032e-06, "loss": 3.2164, "step": 475500 }, { "epoch": 8.14, "learning_rate": 9.317202462380302e-06, "loss": 3.2015, "step": 476000 }, { "epoch": 8.15, "learning_rate": 9.274452804377567e-06, "loss": 3.1918, "step": 476500 }, { "epoch": 8.16, "learning_rate": 9.231703146374828e-06, "loss": 3.1751, "step": 477000 }, { "epoch": 8.17, "learning_rate": 9.188953488372093e-06, "loss": 3.204, "step": 477500 }, { "epoch": 8.17, "learning_rate": 9.146203830369357e-06, "loss": 3.2142, "step": 478000 }, { "epoch": 8.18, "learning_rate": 9.103454172366622e-06, "loss": 3.1818, "step": 478500 }, { "epoch": 8.19, "learning_rate": 9.060704514363885e-06, "loss": 3.1766, "step": 479000 }, { "epoch": 8.2, "learning_rate": 9.01795485636115e-06, "loss": 3.2069, "step": 479500 }, { "epoch": 8.21, "learning_rate": 8.975205198358413e-06, "loss": 3.2092, "step": 480000 }, { "epoch": 8.22, "learning_rate": 8.932455540355678e-06, "loss": 3.1638, "step": 480500 }, { "epoch": 8.23, "learning_rate": 8.889705882352941e-06, "loss": 3.1489, "step": 481000 }, { "epoch": 8.23, "learning_rate": 8.846956224350206e-06, "loss": 3.2052, "step": 481500 }, { "epoch": 8.24, "learning_rate": 8.80420656634747e-06, "loss": 3.2058, "step": 482000 }, { "epoch": 8.25, "learning_rate": 8.761542407660739e-06, "loss": 3.1677, "step": 482500 }, { "epoch": 8.26, "learning_rate": 8.718792749658002e-06, "loss": 3.1631, "step": 483000 }, { "epoch": 8.27, "learning_rate": 8.676043091655267e-06, "loss": 3.1883, "step": 483500 }, { "epoch": 8.28, "learning_rate": 8.633378932968537e-06, "loss": 3.2155, "step": 484000 }, { "epoch": 8.28, "learning_rate": 8.5906292749658e-06, "loss": 3.1711, "step": 484500 }, { "epoch": 8.29, "learning_rate": 8.547965116279071e-06, "loss": 3.1825, "step": 485000 }, { "epoch": 8.3, "learning_rate": 8.505215458276335e-06, "loss": 3.2052, "step": 485500 }, { "epoch": 8.31, "learning_rate": 8.4624658002736e-06, "loss": 3.2135, "step": 486000 }, { "epoch": 8.32, "learning_rate": 8.419716142270863e-06, "loss": 3.181, "step": 486500 }, { "epoch": 8.33, "learning_rate": 8.376966484268126e-06, "loss": 3.1724, "step": 487000 }, { "epoch": 8.34, "learning_rate": 8.3343878248974e-06, "loss": 3.1972, "step": 487500 }, { "epoch": 8.34, "learning_rate": 8.291638166894665e-06, "loss": 3.2148, "step": 488000 }, { "epoch": 8.35, "learning_rate": 8.248888508891928e-06, "loss": 3.2156, "step": 488500 }, { "epoch": 8.36, "learning_rate": 8.206138850889193e-06, "loss": 3.1812, "step": 489000 }, { "epoch": 8.37, "learning_rate": 8.163389192886457e-06, "loss": 3.2076, "step": 489500 }, { "epoch": 8.38, "learning_rate": 8.120639534883722e-06, "loss": 3.2092, "step": 490000 }, { "epoch": 8.39, "learning_rate": 8.077889876880985e-06, "loss": 3.173, "step": 490500 }, { "epoch": 8.4, "learning_rate": 8.03514021887825e-06, "loss": 3.1829, "step": 491000 }, { "epoch": 8.4, "learning_rate": 7.992390560875513e-06, "loss": 3.1571, "step": 491500 }, { "epoch": 8.41, "learning_rate": 7.949726402188783e-06, "loss": 3.188, "step": 492000 }, { "epoch": 8.42, "learning_rate": 7.906976744186048e-06, "loss": 3.1643, "step": 492500 }, { "epoch": 8.43, "learning_rate": 7.864227086183311e-06, "loss": 3.1916, "step": 493000 }, { "epoch": 8.44, "learning_rate": 7.821477428180576e-06, "loss": 3.1885, "step": 493500 }, { "epoch": 8.45, "learning_rate": 7.778727770177839e-06, "loss": 3.1953, "step": 494000 }, { "epoch": 8.46, "learning_rate": 7.735978112175102e-06, "loss": 3.2119, "step": 494500 }, { "epoch": 8.46, "learning_rate": 7.693228454172367e-06, "loss": 3.18, "step": 495000 }, { "epoch": 8.47, "learning_rate": 7.65047879616963e-06, "loss": 3.1932, "step": 495500 }, { "epoch": 8.48, "learning_rate": 7.607729138166896e-06, "loss": 3.163, "step": 496000 }, { "epoch": 8.49, "learning_rate": 7.565064979480164e-06, "loss": 3.1755, "step": 496500 }, { "epoch": 8.5, "learning_rate": 7.522315321477428e-06, "loss": 3.1608, "step": 497000 }, { "epoch": 8.51, "learning_rate": 7.479651162790698e-06, "loss": 3.2063, "step": 497500 }, { "epoch": 8.52, "learning_rate": 7.436901504787962e-06, "loss": 3.1997, "step": 498000 }, { "epoch": 8.52, "learning_rate": 7.394151846785226e-06, "loss": 3.2201, "step": 498500 }, { "epoch": 8.53, "learning_rate": 7.35140218878249e-06, "loss": 3.2128, "step": 499000 }, { "epoch": 8.54, "learning_rate": 7.308652530779754e-06, "loss": 3.174, "step": 499500 }, { "epoch": 8.55, "learning_rate": 7.2659028727770185e-06, "loss": 3.1539, "step": 500000 }, { "epoch": 8.56, "learning_rate": 7.223153214774283e-06, "loss": 3.1559, "step": 500500 }, { "epoch": 8.57, "learning_rate": 7.180403556771547e-06, "loss": 3.18, "step": 501000 }, { "epoch": 8.58, "learning_rate": 7.137739398084815e-06, "loss": 3.1679, "step": 501500 }, { "epoch": 8.58, "learning_rate": 7.0949897400820795e-06, "loss": 3.1785, "step": 502000 }, { "epoch": 8.59, "learning_rate": 7.05232558139535e-06, "loss": 3.1777, "step": 502500 }, { "epoch": 8.6, "learning_rate": 7.009575923392612e-06, "loss": 3.18, "step": 503000 }, { "epoch": 8.61, "learning_rate": 6.966826265389876e-06, "loss": 3.1958, "step": 503500 }, { "epoch": 8.62, "learning_rate": 6.9240766073871405e-06, "loss": 3.2005, "step": 504000 }, { "epoch": 8.63, "learning_rate": 6.881412448700411e-06, "loss": 3.1982, "step": 504500 }, { "epoch": 8.64, "learning_rate": 6.838662790697675e-06, "loss": 3.1924, "step": 505000 }, { "epoch": 8.64, "learning_rate": 6.795913132694939e-06, "loss": 3.1817, "step": 505500 }, { "epoch": 8.65, "learning_rate": 6.753163474692203e-06, "loss": 3.2, "step": 506000 }, { "epoch": 8.66, "learning_rate": 6.7104138166894665e-06, "loss": 3.1722, "step": 506500 }, { "epoch": 8.67, "learning_rate": 6.667664158686731e-06, "loss": 3.1811, "step": 507000 }, { "epoch": 8.68, "learning_rate": 6.624914500683995e-06, "loss": 3.1592, "step": 507500 }, { "epoch": 8.69, "learning_rate": 6.582164842681259e-06, "loss": 3.2065, "step": 508000 }, { "epoch": 8.7, "learning_rate": 6.539415184678523e-06, "loss": 3.1703, "step": 508500 }, { "epoch": 8.7, "learning_rate": 6.496665526675787e-06, "loss": 3.1724, "step": 509000 }, { "epoch": 8.71, "learning_rate": 6.453915868673051e-06, "loss": 3.1255, "step": 509500 }, { "epoch": 8.72, "learning_rate": 6.4111662106703145e-06, "loss": 3.1615, "step": 510000 }, { "epoch": 8.73, "learning_rate": 6.368502051983584e-06, "loss": 3.1938, "step": 510500 }, { "epoch": 8.74, "learning_rate": 6.325752393980848e-06, "loss": 3.142, "step": 511000 }, { "epoch": 8.75, "learning_rate": 6.283002735978112e-06, "loss": 3.1953, "step": 511500 }, { "epoch": 8.76, "learning_rate": 6.240253077975376e-06, "loss": 3.1544, "step": 512000 }, { "epoch": 8.76, "learning_rate": 6.1975034199726405e-06, "loss": 3.1806, "step": 512500 }, { "epoch": 8.77, "learning_rate": 6.154753761969905e-06, "loss": 3.1752, "step": 513000 }, { "epoch": 8.78, "learning_rate": 6.1121751025991795e-06, "loss": 3.1478, "step": 513500 }, { "epoch": 8.79, "learning_rate": 6.069425444596444e-06, "loss": 3.1946, "step": 514000 }, { "epoch": 8.8, "learning_rate": 6.026675786593707e-06, "loss": 3.1854, "step": 514500 }, { "epoch": 8.81, "learning_rate": 5.983926128590971e-06, "loss": 3.1483, "step": 515000 }, { "epoch": 8.81, "learning_rate": 5.941176470588235e-06, "loss": 3.1759, "step": 515500 }, { "epoch": 8.82, "learning_rate": 5.8985123119015054e-06, "loss": 3.1728, "step": 516000 }, { "epoch": 8.83, "learning_rate": 5.8557626538987696e-06, "loss": 3.1681, "step": 516500 }, { "epoch": 8.84, "learning_rate": 5.813012995896034e-06, "loss": 3.1593, "step": 517000 }, { "epoch": 8.85, "learning_rate": 5.770263337893298e-06, "loss": 3.1827, "step": 517500 }, { "epoch": 8.86, "learning_rate": 5.727513679890561e-06, "loss": 3.2048, "step": 518000 }, { "epoch": 8.87, "learning_rate": 5.684764021887825e-06, "loss": 3.1656, "step": 518500 }, { "epoch": 8.87, "learning_rate": 5.642014363885089e-06, "loss": 3.1457, "step": 519000 }, { "epoch": 8.88, "learning_rate": 5.5992647058823535e-06, "loss": 3.1451, "step": 519500 }, { "epoch": 8.89, "learning_rate": 5.556515047879618e-06, "loss": 3.1706, "step": 520000 }, { "epoch": 8.9, "learning_rate": 5.513765389876882e-06, "loss": 3.1531, "step": 520500 }, { "epoch": 8.91, "learning_rate": 5.471101231190151e-06, "loss": 3.1532, "step": 521000 }, { "epoch": 8.92, "learning_rate": 5.4283515731874145e-06, "loss": 3.1407, "step": 521500 }, { "epoch": 8.93, "learning_rate": 5.385601915184679e-06, "loss": 3.1875, "step": 522000 }, { "epoch": 8.93, "learning_rate": 5.342852257181943e-06, "loss": 3.1943, "step": 522500 }, { "epoch": 8.94, "learning_rate": 5.300102599179207e-06, "loss": 3.1857, "step": 523000 }, { "epoch": 8.95, "learning_rate": 5.257352941176471e-06, "loss": 3.1714, "step": 523500 }, { "epoch": 8.96, "learning_rate": 5.214603283173735e-06, "loss": 3.1704, "step": 524000 }, { "epoch": 8.97, "learning_rate": 5.171853625170999e-06, "loss": 3.134, "step": 524500 }, { "epoch": 8.98, "learning_rate": 5.129103967168263e-06, "loss": 3.1762, "step": 525000 }, { "epoch": 8.99, "learning_rate": 5.086439808481532e-06, "loss": 3.1784, "step": 525500 }, { "epoch": 8.99, "learning_rate": 5.043690150478796e-06, "loss": 3.1301, "step": 526000 }, { "epoch": 9.0, "learning_rate": 5.00094049247606e-06, "loss": 3.1415, "step": 526500 }, { "epoch": 9.01, "learning_rate": 4.95827633378933e-06, "loss": 3.1466, "step": 527000 }, { "epoch": 9.02, "learning_rate": 4.915526675786594e-06, "loss": 3.1724, "step": 527500 }, { "epoch": 9.03, "learning_rate": 4.872777017783858e-06, "loss": 3.1706, "step": 528000 }, { "epoch": 9.04, "learning_rate": 4.8301128590971275e-06, "loss": 3.1396, "step": 528500 }, { "epoch": 9.05, "learning_rate": 4.787363201094392e-06, "loss": 3.1442, "step": 529000 }, { "epoch": 9.05, "learning_rate": 4.744613543091656e-06, "loss": 3.16, "step": 529500 }, { "epoch": 9.06, "learning_rate": 4.70186388508892e-06, "loss": 3.1694, "step": 530000 }, { "epoch": 9.07, "learning_rate": 4.659114227086184e-06, "loss": 3.1395, "step": 530500 }, { "epoch": 9.08, "learning_rate": 4.616364569083448e-06, "loss": 3.1536, "step": 531000 }, { "epoch": 9.09, "learning_rate": 4.573614911080711e-06, "loss": 3.1339, "step": 531500 }, { "epoch": 9.1, "learning_rate": 4.5308652530779755e-06, "loss": 3.1808, "step": 532000 }, { "epoch": 9.11, "learning_rate": 4.48811559507524e-06, "loss": 3.1568, "step": 532500 }, { "epoch": 9.11, "learning_rate": 4.445365937072504e-06, "loss": 3.1689, "step": 533000 }, { "epoch": 9.12, "learning_rate": 4.402616279069768e-06, "loss": 3.1291, "step": 533500 }, { "epoch": 9.13, "learning_rate": 4.359866621067032e-06, "loss": 3.134, "step": 534000 }, { "epoch": 9.14, "learning_rate": 4.317116963064296e-06, "loss": 3.1325, "step": 534500 }, { "epoch": 9.15, "learning_rate": 4.27453830369357e-06, "loss": 3.1295, "step": 535000 }, { "epoch": 9.16, "learning_rate": 4.2318741450068404e-06, "loss": 3.1305, "step": 535500 }, { "epoch": 9.17, "learning_rate": 4.1891244870041046e-06, "loss": 3.1508, "step": 536000 }, { "epoch": 9.17, "learning_rate": 4.146374829001369e-06, "loss": 3.1902, "step": 536500 }, { "epoch": 9.18, "learning_rate": 4.103625170998633e-06, "loss": 3.1244, "step": 537000 }, { "epoch": 9.19, "learning_rate": 4.060875512995897e-06, "loss": 3.157, "step": 537500 }, { "epoch": 9.2, "learning_rate": 4.01812585499316e-06, "loss": 3.1585, "step": 538000 }, { "epoch": 9.21, "learning_rate": 3.975376196990424e-06, "loss": 3.1007, "step": 538500 }, { "epoch": 9.22, "learning_rate": 3.9326265389876885e-06, "loss": 3.1622, "step": 539000 }, { "epoch": 9.23, "learning_rate": 3.8898768809849526e-06, "loss": 3.1682, "step": 539500 }, { "epoch": 9.23, "learning_rate": 3.847127222982217e-06, "loss": 3.1487, "step": 540000 }, { "epoch": 9.24, "learning_rate": 3.804548563611491e-06, "loss": 3.1649, "step": 540500 }, { "epoch": 9.25, "learning_rate": 3.7617989056087552e-06, "loss": 3.1929, "step": 541000 }, { "epoch": 9.26, "learning_rate": 3.7190492476060194e-06, "loss": 3.1339, "step": 541500 }, { "epoch": 9.27, "learning_rate": 3.676299589603283e-06, "loss": 3.143, "step": 542000 }, { "epoch": 9.28, "learning_rate": 3.633549931600547e-06, "loss": 3.1158, "step": 542500 }, { "epoch": 9.29, "learning_rate": 3.5908002735978113e-06, "loss": 3.1746, "step": 543000 }, { "epoch": 9.29, "learning_rate": 3.5480506155950754e-06, "loss": 3.1143, "step": 543500 }, { "epoch": 9.3, "learning_rate": 3.5053009575923396e-06, "loss": 3.156, "step": 544000 }, { "epoch": 9.31, "learning_rate": 3.4625512995896033e-06, "loss": 3.1217, "step": 544500 }, { "epoch": 9.32, "learning_rate": 3.4198871409028728e-06, "loss": 3.1251, "step": 545000 }, { "epoch": 9.33, "learning_rate": 3.377137482900137e-06, "loss": 3.1339, "step": 545500 }, { "epoch": 9.34, "learning_rate": 3.334387824897401e-06, "loss": 3.176, "step": 546000 }, { "epoch": 9.35, "learning_rate": 3.291638166894665e-06, "loss": 3.1378, "step": 546500 }, { "epoch": 9.35, "learning_rate": 3.2489740082079346e-06, "loss": 3.1107, "step": 547000 }, { "epoch": 9.36, "learning_rate": 3.2062243502051983e-06, "loss": 3.1422, "step": 547500 }, { "epoch": 9.37, "learning_rate": 3.1634746922024624e-06, "loss": 3.1579, "step": 548000 }, { "epoch": 9.38, "learning_rate": 3.120810533515732e-06, "loss": 3.1277, "step": 548500 }, { "epoch": 9.39, "learning_rate": 3.078060875512996e-06, "loss": 3.1489, "step": 549000 }, { "epoch": 9.4, "learning_rate": 3.03531121751026e-06, "loss": 3.1494, "step": 549500 }, { "epoch": 9.4, "learning_rate": 2.992561559507524e-06, "loss": 3.1361, "step": 550000 }, { "epoch": 9.41, "learning_rate": 2.949811901504788e-06, "loss": 3.1434, "step": 550500 }, { "epoch": 9.42, "learning_rate": 2.907062243502052e-06, "loss": 3.1542, "step": 551000 }, { "epoch": 9.43, "learning_rate": 2.8643125854993162e-06, "loss": 3.1341, "step": 551500 }, { "epoch": 9.44, "learning_rate": 2.82156292749658e-06, "loss": 3.1375, "step": 552000 }, { "epoch": 9.45, "learning_rate": 2.778813269493844e-06, "loss": 3.1461, "step": 552500 }, { "epoch": 9.46, "learning_rate": 2.736063611491108e-06, "loss": 3.1571, "step": 553000 }, { "epoch": 9.46, "learning_rate": 2.6933139534883723e-06, "loss": 3.1532, "step": 553500 }, { "epoch": 9.47, "learning_rate": 2.650649794801642e-06, "loss": 3.1184, "step": 554000 }, { "epoch": 9.48, "learning_rate": 2.607985636114911e-06, "loss": 3.1441, "step": 554500 }, { "epoch": 9.49, "learning_rate": 2.565235978112175e-06, "loss": 3.137, "step": 555000 }, { "epoch": 9.5, "learning_rate": 2.522486320109439e-06, "loss": 3.1563, "step": 555500 }, { "epoch": 9.51, "learning_rate": 2.4797366621067032e-06, "loss": 3.1726, "step": 556000 }, { "epoch": 9.52, "learning_rate": 2.436987004103967e-06, "loss": 3.14, "step": 556500 }, { "epoch": 9.52, "learning_rate": 2.394237346101231e-06, "loss": 3.1285, "step": 557000 }, { "epoch": 9.53, "learning_rate": 2.3516586867305063e-06, "loss": 3.1474, "step": 557500 }, { "epoch": 9.54, "learning_rate": 2.30890902872777e-06, "loss": 3.1652, "step": 558000 }, { "epoch": 9.55, "learning_rate": 2.266159370725034e-06, "loss": 3.1567, "step": 558500 }, { "epoch": 9.56, "learning_rate": 2.2234097127222983e-06, "loss": 3.1305, "step": 559000 }, { "epoch": 9.57, "learning_rate": 2.1806600547195624e-06, "loss": 3.1402, "step": 559500 }, { "epoch": 9.58, "learning_rate": 2.137910396716826e-06, "loss": 3.159, "step": 560000 }, { "epoch": 9.58, "learning_rate": 2.0951607387140902e-06, "loss": 3.1684, "step": 560500 }, { "epoch": 9.59, "learning_rate": 2.0524110807113544e-06, "loss": 3.1483, "step": 561000 }, { "epoch": 9.6, "learning_rate": 2.0096614227086185e-06, "loss": 3.1277, "step": 561500 }, { "epoch": 9.61, "learning_rate": 1.9669117647058826e-06, "loss": 3.1447, "step": 562000 }, { "epoch": 9.62, "learning_rate": 1.9241621067031463e-06, "loss": 3.1503, "step": 562500 }, { "epoch": 9.63, "learning_rate": 1.8814124487004106e-06, "loss": 3.1172, "step": 563000 }, { "epoch": 9.64, "learning_rate": 1.8386627906976743e-06, "loss": 3.1413, "step": 563500 }, { "epoch": 9.64, "learning_rate": 1.795998632010944e-06, "loss": 3.1049, "step": 564000 }, { "epoch": 9.65, "learning_rate": 1.7533344733242133e-06, "loss": 3.1588, "step": 564500 }, { "epoch": 9.66, "learning_rate": 1.7105848153214774e-06, "loss": 3.1232, "step": 565000 }, { "epoch": 9.67, "learning_rate": 1.6678351573187416e-06, "loss": 3.1404, "step": 565500 }, { "epoch": 9.68, "learning_rate": 1.6250854993160057e-06, "loss": 3.1532, "step": 566000 }, { "epoch": 9.69, "learning_rate": 1.5823358413132694e-06, "loss": 3.111, "step": 566500 }, { "epoch": 9.7, "learning_rate": 1.5395861833105335e-06, "loss": 3.1191, "step": 567000 }, { "epoch": 9.7, "learning_rate": 1.4968365253077976e-06, "loss": 3.1338, "step": 567500 }, { "epoch": 9.71, "learning_rate": 1.4540868673050615e-06, "loss": 3.116, "step": 568000 }, { "epoch": 9.72, "learning_rate": 1.4113372093023257e-06, "loss": 3.138, "step": 568500 }, { "epoch": 9.73, "learning_rate": 1.3685875512995896e-06, "loss": 3.1462, "step": 569000 }, { "epoch": 9.74, "learning_rate": 1.3258378932968537e-06, "loss": 3.1099, "step": 569500 }, { "epoch": 9.75, "learning_rate": 1.2830882352941176e-06, "loss": 3.1449, "step": 570000 }, { "epoch": 9.76, "learning_rate": 1.2403385772913817e-06, "loss": 3.1476, "step": 570500 }, { "epoch": 9.76, "learning_rate": 1.1977599179206568e-06, "loss": 3.091, "step": 571000 }, { "epoch": 9.77, "learning_rate": 1.1550102599179207e-06, "loss": 3.1714, "step": 571500 }, { "epoch": 9.78, "learning_rate": 1.1122606019151848e-06, "loss": 3.1462, "step": 572000 }, { "epoch": 9.79, "learning_rate": 1.0695109439124488e-06, "loss": 3.0987, "step": 572500 }, { "epoch": 9.8, "learning_rate": 1.0267612859097129e-06, "loss": 3.1309, "step": 573000 }, { "epoch": 9.81, "learning_rate": 9.840116279069768e-07, "loss": 3.1129, "step": 573500 }, { "epoch": 9.82, "learning_rate": 9.412619699042408e-07, "loss": 3.124, "step": 574000 }, { "epoch": 9.82, "learning_rate": 8.985978112175103e-07, "loss": 3.1447, "step": 574500 }, { "epoch": 9.83, "learning_rate": 8.559336525307799e-07, "loss": 3.1516, "step": 575000 }, { "epoch": 9.84, "learning_rate": 8.131839945280438e-07, "loss": 3.1407, "step": 575500 }, { "epoch": 9.85, "learning_rate": 7.705198358413133e-07, "loss": 3.1609, "step": 576000 }, { "epoch": 9.86, "learning_rate": 7.277701778385773e-07, "loss": 3.1213, "step": 576500 }, { "epoch": 9.87, "learning_rate": 6.850205198358413e-07, "loss": 3.1234, "step": 577000 }, { "epoch": 9.88, "learning_rate": 6.422708618331053e-07, "loss": 3.1042, "step": 577500 }, { "epoch": 9.88, "learning_rate": 5.995212038303694e-07, "loss": 3.1261, "step": 578000 }, { "epoch": 9.89, "learning_rate": 5.567715458276334e-07, "loss": 3.1196, "step": 578500 }, { "epoch": 9.9, "learning_rate": 5.140218878248974e-07, "loss": 3.1622, "step": 579000 }, { "epoch": 9.91, "learning_rate": 4.712722298221614e-07, "loss": 3.1254, "step": 579500 }, { "epoch": 9.92, "learning_rate": 4.2852257181942543e-07, "loss": 3.1291, "step": 580000 }, { "epoch": 9.93, "learning_rate": 3.857729138166895e-07, "loss": 3.0939, "step": 580500 }, { "epoch": 9.94, "learning_rate": 3.430232558139535e-07, "loss": 3.1597, "step": 581000 }, { "epoch": 9.94, "learning_rate": 3.002735978112175e-07, "loss": 3.1454, "step": 581500 }, { "epoch": 9.95, "learning_rate": 2.575239398084815e-07, "loss": 3.1569, "step": 582000 }, { "epoch": 9.96, "learning_rate": 2.1485978112175104e-07, "loss": 3.1016, "step": 582500 }, { "epoch": 9.97, "learning_rate": 1.7219562243502053e-07, "loss": 3.1268, "step": 583000 }, { "epoch": 9.98, "learning_rate": 1.2944596443228454e-07, "loss": 3.1422, "step": 583500 }, { "epoch": 9.99, "learning_rate": 8.669630642954856e-08, "loss": 3.1132, "step": 584000 }, { "epoch": 9.99, "learning_rate": 4.394664842681259e-08, "loss": 3.1218, "step": 584500 }, { "epoch": 10.0, "step": 584800, "total_flos": 5.454351260793078e+18, "train_loss": 3.7000725246486845, "train_runtime": 189673.1431, "train_samples_per_second": 30.832, "train_steps_per_second": 3.083 } ], "logging_steps": 500, "max_steps": 584800, "num_train_epochs": 10, "save_steps": 100000, "total_flos": 5.454351260793078e+18, "trial_name": null, "trial_params": null }