{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.7564184767031974, "global_step": 48000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 1e-05, "loss": 1.3064, "step": 250 }, { "epoch": 0.01, "learning_rate": 2e-05, "loss": 1.2686, "step": 500 }, { "epoch": 0.01, "learning_rate": 3e-05, "loss": 1.2536, "step": 750 }, { "epoch": 0.02, "learning_rate": 4e-05, "loss": 1.2402, "step": 1000 }, { "epoch": 0.02, "learning_rate": 5e-05, "loss": 1.2291, "step": 1250 }, { "epoch": 0.02, "learning_rate": 6e-05, "loss": 1.2202, "step": 1500 }, { "epoch": 0.03, "learning_rate": 7e-05, "loss": 1.2107, "step": 1750 }, { "epoch": 0.03, "learning_rate": 8e-05, "loss": 1.2039, "step": 2000 }, { "epoch": 0.04, "learning_rate": 9e-05, "loss": 1.1978, "step": 2250 }, { "epoch": 0.04, "learning_rate": 0.0001, "loss": 1.1937, "step": 2500 }, { "epoch": 0.04, "learning_rate": 9.9873417721519e-05, "loss": 1.1933, "step": 2750 }, { "epoch": 0.05, "learning_rate": 9.974683544303798e-05, "loss": 1.1742, "step": 3000 }, { "epoch": 0.05, "learning_rate": 9.962025316455697e-05, "loss": 1.1665, "step": 3250 }, { "epoch": 0.06, "learning_rate": 9.949367088607595e-05, "loss": 1.1584, "step": 3500 }, { "epoch": 0.06, "learning_rate": 9.936708860759493e-05, "loss": 1.1502, "step": 3750 }, { "epoch": 0.06, "learning_rate": 9.924050632911392e-05, "loss": 1.147, "step": 4000 }, { "epoch": 0.07, "learning_rate": 9.911392405063291e-05, "loss": 1.1423, "step": 4250 }, { "epoch": 0.07, "learning_rate": 9.89873417721519e-05, "loss": 1.1343, "step": 4500 }, { "epoch": 0.07, "learning_rate": 9.88607594936709e-05, "loss": 1.1306, "step": 4750 }, { "epoch": 0.08, "learning_rate": 9.873417721518988e-05, "loss": 1.1237, "step": 5000 }, { "epoch": 0.08, "learning_rate": 9.860759493670887e-05, "loss": 1.1181, "step": 5250 }, { "epoch": 0.09, "learning_rate": 9.848101265822785e-05, "loss": 1.1135, "step": 5500 }, { "epoch": 0.09, "learning_rate": 9.835443037974684e-05, "loss": 1.1087, "step": 5750 }, { "epoch": 0.09, "learning_rate": 9.822784810126583e-05, "loss": 1.1047, "step": 6000 }, { "epoch": 0.1, "learning_rate": 9.810126582278482e-05, "loss": 1.101, "step": 6250 }, { "epoch": 0.1, "learning_rate": 9.797468354430381e-05, "loss": 1.0963, "step": 6500 }, { "epoch": 0.11, "learning_rate": 9.784810126582278e-05, "loss": 1.0933, "step": 6750 }, { "epoch": 0.11, "learning_rate": 9.772151898734177e-05, "loss": 1.0895, "step": 7000 }, { "epoch": 0.11, "learning_rate": 9.759493670886076e-05, "loss": 1.0879, "step": 7250 }, { "epoch": 0.12, "learning_rate": 9.746835443037975e-05, "loss": 1.0845, "step": 7500 }, { "epoch": 0.12, "learning_rate": 9.734177215189874e-05, "loss": 1.0802, "step": 7750 }, { "epoch": 0.13, "learning_rate": 9.721518987341773e-05, "loss": 1.077, "step": 8000 }, { "epoch": 0.13, "learning_rate": 9.708860759493671e-05, "loss": 1.075, "step": 8250 }, { "epoch": 0.13, "learning_rate": 9.696202531645569e-05, "loss": 1.0714, "step": 8500 }, { "epoch": 0.14, "learning_rate": 9.683544303797469e-05, "loss": 1.0696, "step": 8750 }, { "epoch": 0.14, "learning_rate": 9.670886075949368e-05, "loss": 1.0674, "step": 9000 }, { "epoch": 0.15, "learning_rate": 9.658227848101267e-05, "loss": 1.0647, "step": 9250 }, { "epoch": 0.15, "learning_rate": 9.645569620253166e-05, "loss": 1.0652, "step": 9500 }, { "epoch": 0.15, "learning_rate": 9.632911392405065e-05, "loss": 1.0622, "step": 9750 }, { "epoch": 0.16, "learning_rate": 9.620253164556962e-05, "loss": 1.0599, "step": 10000 }, { "epoch": 0.16, "learning_rate": 9.607594936708861e-05, "loss": 1.0568, "step": 10250 }, { "epoch": 0.17, "learning_rate": 9.59493670886076e-05, "loss": 1.0537, "step": 10500 }, { "epoch": 0.17, "learning_rate": 9.582278481012659e-05, "loss": 1.0504, "step": 10750 }, { "epoch": 0.17, "learning_rate": 9.569620253164557e-05, "loss": 1.0494, "step": 11000 }, { "epoch": 0.18, "learning_rate": 9.556962025316456e-05, "loss": 1.0485, "step": 11250 }, { "epoch": 0.18, "learning_rate": 9.544303797468355e-05, "loss": 1.0445, "step": 11500 }, { "epoch": 0.19, "learning_rate": 9.531645569620253e-05, "loss": 1.0423, "step": 11750 }, { "epoch": 0.19, "learning_rate": 9.518987341772152e-05, "loss": 1.0412, "step": 12000 }, { "epoch": 0.19, "learning_rate": 9.50632911392405e-05, "loss": 1.0392, "step": 12250 }, { "epoch": 0.2, "learning_rate": 9.493670886075949e-05, "loss": 1.0368, "step": 12500 }, { "epoch": 0.2, "learning_rate": 9.481012658227848e-05, "loss": 1.035, "step": 12750 }, { "epoch": 0.2, "learning_rate": 9.468354430379748e-05, "loss": 1.035, "step": 13000 }, { "epoch": 0.21, "learning_rate": 9.455696202531646e-05, "loss": 1.0337, "step": 13250 }, { "epoch": 0.21, "learning_rate": 9.443037974683545e-05, "loss": 1.0318, "step": 13500 }, { "epoch": 0.22, "learning_rate": 9.430379746835444e-05, "loss": 1.0314, "step": 13750 }, { "epoch": 0.22, "learning_rate": 9.417721518987342e-05, "loss": 1.0288, "step": 14000 }, { "epoch": 0.22, "learning_rate": 9.405063291139241e-05, "loss": 1.03, "step": 14250 }, { "epoch": 0.23, "learning_rate": 9.39240506329114e-05, "loss": 1.0261, "step": 14500 }, { "epoch": 0.23, "learning_rate": 9.379746835443039e-05, "loss": 1.026, "step": 14750 }, { "epoch": 0.24, "learning_rate": 9.367088607594936e-05, "loss": 1.0238, "step": 15000 }, { "epoch": 0.24, "learning_rate": 9.354430379746835e-05, "loss": 1.0248, "step": 15250 }, { "epoch": 0.24, "learning_rate": 9.341772151898734e-05, "loss": 1.0213, "step": 15500 }, { "epoch": 0.25, "learning_rate": 9.329113924050633e-05, "loss": 1.0212, "step": 15750 }, { "epoch": 0.25, "learning_rate": 9.316455696202532e-05, "loss": 1.0213, "step": 16000 }, { "epoch": 0.26, "learning_rate": 9.303797468354431e-05, "loss": 1.0177, "step": 16250 }, { "epoch": 0.26, "learning_rate": 9.29113924050633e-05, "loss": 1.0192, "step": 16500 }, { "epoch": 0.26, "learning_rate": 9.278481012658227e-05, "loss": 1.0155, "step": 16750 }, { "epoch": 0.27, "learning_rate": 9.265822784810127e-05, "loss": 1.0148, "step": 17000 }, { "epoch": 0.27, "learning_rate": 9.253164556962026e-05, "loss": 1.0139, "step": 17250 }, { "epoch": 0.28, "learning_rate": 9.240506329113925e-05, "loss": 1.0126, "step": 17500 }, { "epoch": 0.28, "learning_rate": 9.227848101265824e-05, "loss": 1.012, "step": 17750 }, { "epoch": 0.28, "learning_rate": 9.215189873417723e-05, "loss": 1.0108, "step": 18000 }, { "epoch": 0.29, "learning_rate": 9.20253164556962e-05, "loss": 1.0114, "step": 18250 }, { "epoch": 0.29, "learning_rate": 9.189873417721519e-05, "loss": 1.0103, "step": 18500 }, { "epoch": 0.3, "learning_rate": 9.177215189873418e-05, "loss": 1.0086, "step": 18750 }, { "epoch": 0.3, "learning_rate": 9.164556962025317e-05, "loss": 1.0082, "step": 19000 }, { "epoch": 0.3, "learning_rate": 9.151898734177216e-05, "loss": 1.0058, "step": 19250 }, { "epoch": 0.31, "learning_rate": 9.139240506329115e-05, "loss": 1.0049, "step": 19500 }, { "epoch": 0.31, "learning_rate": 9.126582278481013e-05, "loss": 1.0055, "step": 19750 }, { "epoch": 0.32, "learning_rate": 9.113924050632912e-05, "loss": 1.0006, "step": 20000 }, { "epoch": 0.32, "learning_rate": 9.10126582278481e-05, "loss": 1.0028, "step": 20250 }, { "epoch": 0.32, "learning_rate": 9.088607594936709e-05, "loss": 1.0, "step": 20500 }, { "epoch": 0.33, "learning_rate": 9.075949367088607e-05, "loss": 1.0012, "step": 20750 }, { "epoch": 0.33, "learning_rate": 9.063291139240506e-05, "loss": 0.9976, "step": 21000 }, { "epoch": 0.33, "learning_rate": 9.050632911392407e-05, "loss": 0.9963, "step": 21250 }, { "epoch": 0.34, "learning_rate": 9.037974683544304e-05, "loss": 0.9969, "step": 21500 }, { "epoch": 0.34, "learning_rate": 9.025316455696203e-05, "loss": 0.9963, "step": 21750 }, { "epoch": 0.35, "learning_rate": 9.012658227848102e-05, "loss": 0.9959, "step": 22000 }, { "epoch": 0.35, "learning_rate": 9e-05, "loss": 0.9939, "step": 22250 }, { "epoch": 0.35, "learning_rate": 8.9873417721519e-05, "loss": 0.9925, "step": 22500 }, { "epoch": 0.36, "learning_rate": 8.974683544303798e-05, "loss": 0.9935, "step": 22750 }, { "epoch": 0.36, "learning_rate": 8.962025316455697e-05, "loss": 0.991, "step": 23000 }, { "epoch": 0.37, "learning_rate": 8.949367088607596e-05, "loss": 0.9894, "step": 23250 }, { "epoch": 0.37, "learning_rate": 8.936708860759493e-05, "loss": 0.9892, "step": 23500 }, { "epoch": 0.37, "learning_rate": 8.924050632911392e-05, "loss": 0.9892, "step": 23750 }, { "epoch": 0.38, "learning_rate": 8.911392405063291e-05, "loss": 0.9895, "step": 24000 }, { "epoch": 0.38, "learning_rate": 8.89873417721519e-05, "loss": 0.9871, "step": 24250 }, { "epoch": 0.39, "learning_rate": 8.886075949367089e-05, "loss": 0.9857, "step": 24500 }, { "epoch": 0.39, "learning_rate": 8.873417721518988e-05, "loss": 0.9862, "step": 24750 }, { "epoch": 0.39, "learning_rate": 8.860759493670887e-05, "loss": 0.9853, "step": 25000 }, { "epoch": 0.4, "learning_rate": 8.848101265822785e-05, "loss": 0.9836, "step": 25250 }, { "epoch": 0.4, "learning_rate": 8.835443037974684e-05, "loss": 0.981, "step": 25500 }, { "epoch": 0.41, "learning_rate": 8.822784810126583e-05, "loss": 0.9832, "step": 25750 }, { "epoch": 0.41, "learning_rate": 8.810126582278482e-05, "loss": 0.9806, "step": 26000 }, { "epoch": 0.41, "learning_rate": 8.797468354430381e-05, "loss": 0.9815, "step": 26250 }, { "epoch": 0.42, "learning_rate": 8.78481012658228e-05, "loss": 0.9785, "step": 26500 }, { "epoch": 0.42, "learning_rate": 8.772151898734177e-05, "loss": 0.9782, "step": 26750 }, { "epoch": 0.43, "learning_rate": 8.759493670886076e-05, "loss": 0.9779, "step": 27000 }, { "epoch": 0.43, "learning_rate": 8.746835443037975e-05, "loss": 0.9787, "step": 27250 }, { "epoch": 0.43, "learning_rate": 8.734177215189874e-05, "loss": 0.9772, "step": 27500 }, { "epoch": 0.44, "learning_rate": 8.721518987341773e-05, "loss": 0.9774, "step": 27750 }, { "epoch": 0.44, "learning_rate": 8.708860759493672e-05, "loss": 0.9751, "step": 28000 }, { "epoch": 0.45, "learning_rate": 8.69620253164557e-05, "loss": 0.9752, "step": 28250 }, { "epoch": 0.45, "learning_rate": 8.683544303797468e-05, "loss": 0.9753, "step": 28500 }, { "epoch": 0.45, "learning_rate": 8.670886075949367e-05, "loss": 0.9724, "step": 28750 }, { "epoch": 0.46, "learning_rate": 8.658227848101266e-05, "loss": 0.9739, "step": 29000 }, { "epoch": 0.46, "learning_rate": 8.645569620253166e-05, "loss": 0.9712, "step": 29250 }, { "epoch": 0.46, "learning_rate": 8.632911392405065e-05, "loss": 0.9707, "step": 29500 }, { "epoch": 0.47, "learning_rate": 8.620253164556964e-05, "loss": 0.9747, "step": 29750 }, { "epoch": 0.47, "learning_rate": 8.607594936708861e-05, "loss": 0.97, "step": 30000 }, { "epoch": 0.48, "learning_rate": 8.59493670886076e-05, "loss": 0.9707, "step": 30250 }, { "epoch": 0.48, "learning_rate": 8.582278481012659e-05, "loss": 0.9708, "step": 30500 }, { "epoch": 0.48, "learning_rate": 8.569620253164558e-05, "loss": 0.9676, "step": 30750 }, { "epoch": 0.49, "learning_rate": 8.556962025316456e-05, "loss": 0.9672, "step": 31000 }, { "epoch": 0.49, "learning_rate": 8.544303797468355e-05, "loss": 0.9691, "step": 31250 }, { "epoch": 0.5, "learning_rate": 8.531645569620254e-05, "loss": 0.965, "step": 31500 }, { "epoch": 0.5, "learning_rate": 8.518987341772152e-05, "loss": 0.9645, "step": 31750 }, { "epoch": 0.5, "learning_rate": 8.50632911392405e-05, "loss": 0.9643, "step": 32000 }, { "epoch": 0.51, "learning_rate": 8.49367088607595e-05, "loss": 0.9631, "step": 32250 }, { "epoch": 0.51, "learning_rate": 8.481012658227848e-05, "loss": 0.9644, "step": 32500 }, { "epoch": 0.52, "learning_rate": 8.468354430379747e-05, "loss": 0.964, "step": 32750 }, { "epoch": 0.52, "learning_rate": 8.455696202531646e-05, "loss": 0.9627, "step": 33000 }, { "epoch": 0.52, "learning_rate": 8.443037974683545e-05, "loss": 0.9638, "step": 33250 }, { "epoch": 0.53, "learning_rate": 8.430379746835444e-05, "loss": 0.9606, "step": 33500 }, { "epoch": 0.53, "learning_rate": 8.417721518987342e-05, "loss": 0.9605, "step": 33750 }, { "epoch": 0.54, "learning_rate": 8.405063291139241e-05, "loss": 0.9604, "step": 34000 }, { "epoch": 0.54, "learning_rate": 8.39240506329114e-05, "loss": 0.9583, "step": 34250 }, { "epoch": 0.54, "learning_rate": 8.379746835443039e-05, "loss": 0.9589, "step": 34500 }, { "epoch": 0.55, "learning_rate": 8.367088607594938e-05, "loss": 0.9575, "step": 34750 }, { "epoch": 0.55, "learning_rate": 8.354430379746835e-05, "loss": 0.956, "step": 35000 }, { "epoch": 0.56, "learning_rate": 8.341772151898734e-05, "loss": 0.9562, "step": 35250 }, { "epoch": 0.56, "learning_rate": 8.329113924050633e-05, "loss": 0.9551, "step": 35500 }, { "epoch": 0.56, "learning_rate": 8.316455696202532e-05, "loss": 0.9538, "step": 35750 }, { "epoch": 0.57, "learning_rate": 8.303797468354431e-05, "loss": 0.9555, "step": 36000 }, { "epoch": 0.57, "learning_rate": 8.29113924050633e-05, "loss": 0.9547, "step": 36250 }, { "epoch": 0.58, "learning_rate": 8.278481012658229e-05, "loss": 0.9566, "step": 36500 }, { "epoch": 0.58, "learning_rate": 8.265822784810126e-05, "loss": 0.954, "step": 36750 }, { "epoch": 0.58, "learning_rate": 8.253164556962025e-05, "loss": 0.9533, "step": 37000 }, { "epoch": 0.59, "learning_rate": 8.240506329113924e-05, "loss": 0.9544, "step": 37250 }, { "epoch": 0.59, "learning_rate": 8.227848101265824e-05, "loss": 0.9516, "step": 37500 }, { "epoch": 0.59, "learning_rate": 8.215189873417723e-05, "loss": 0.9531, "step": 37750 }, { "epoch": 0.6, "learning_rate": 8.202531645569622e-05, "loss": 0.9538, "step": 38000 }, { "epoch": 0.6, "learning_rate": 8.189873417721519e-05, "loss": 0.953, "step": 38250 }, { "epoch": 0.61, "learning_rate": 8.177215189873418e-05, "loss": 0.9507, "step": 38500 }, { "epoch": 0.61, "learning_rate": 8.164556962025317e-05, "loss": 0.9504, "step": 38750 }, { "epoch": 0.61, "learning_rate": 8.151898734177216e-05, "loss": 0.9519, "step": 39000 }, { "epoch": 0.62, "learning_rate": 8.139240506329115e-05, "loss": 0.9494, "step": 39250 }, { "epoch": 0.62, "learning_rate": 8.126582278481013e-05, "loss": 0.9504, "step": 39500 }, { "epoch": 0.63, "learning_rate": 8.113924050632912e-05, "loss": 0.9479, "step": 39750 }, { "epoch": 0.63, "learning_rate": 8.10126582278481e-05, "loss": 0.9497, "step": 40000 }, { "epoch": 0.63, "learning_rate": 8.088607594936709e-05, "loss": 0.9483, "step": 40250 }, { "epoch": 0.64, "learning_rate": 8.075949367088608e-05, "loss": 0.9464, "step": 40500 }, { "epoch": 0.64, "learning_rate": 8.063291139240506e-05, "loss": 0.9478, "step": 40750 }, { "epoch": 0.65, "learning_rate": 8.050632911392405e-05, "loss": 0.9476, "step": 41000 }, { "epoch": 0.65, "learning_rate": 8.037974683544304e-05, "loss": 0.9444, "step": 41250 }, { "epoch": 0.65, "learning_rate": 8.025316455696203e-05, "loss": 0.9461, "step": 41500 }, { "epoch": 0.66, "learning_rate": 8.012658227848102e-05, "loss": 0.946, "step": 41750 }, { "epoch": 0.66, "learning_rate": 8e-05, "loss": 0.9454, "step": 42000 }, { "epoch": 0.67, "learning_rate": 7.9873417721519e-05, "loss": 0.9441, "step": 42250 }, { "epoch": 0.67, "learning_rate": 7.974683544303798e-05, "loss": 0.9431, "step": 42500 }, { "epoch": 0.67, "learning_rate": 7.962025316455697e-05, "loss": 0.9419, "step": 42750 }, { "epoch": 0.68, "learning_rate": 7.949367088607596e-05, "loss": 0.944, "step": 43000 }, { "epoch": 0.68, "learning_rate": 7.936708860759494e-05, "loss": 0.9433, "step": 43250 }, { "epoch": 0.69, "learning_rate": 7.924050632911392e-05, "loss": 0.9428, "step": 43500 }, { "epoch": 0.69, "learning_rate": 7.911392405063291e-05, "loss": 0.9406, "step": 43750 }, { "epoch": 0.69, "learning_rate": 7.89873417721519e-05, "loss": 0.9397, "step": 44000 }, { "epoch": 0.7, "learning_rate": 7.886075949367089e-05, "loss": 0.9392, "step": 44250 }, { "epoch": 0.7, "learning_rate": 7.873417721518988e-05, "loss": 0.9404, "step": 44500 }, { "epoch": 0.71, "learning_rate": 7.860759493670887e-05, "loss": 0.9388, "step": 44750 }, { "epoch": 0.71, "learning_rate": 7.848101265822784e-05, "loss": 0.9365, "step": 45000 }, { "epoch": 0.71, "learning_rate": 7.835443037974683e-05, "loss": 0.9387, "step": 45250 }, { "epoch": 0.72, "learning_rate": 7.822784810126582e-05, "loss": 0.9366, "step": 45500 }, { "epoch": 0.72, "learning_rate": 7.810126582278482e-05, "loss": 0.9361, "step": 45750 }, { "epoch": 0.72, "learning_rate": 7.797468354430381e-05, "loss": 0.935, "step": 46000 }, { "epoch": 0.73, "learning_rate": 7.78481012658228e-05, "loss": 0.9355, "step": 46250 }, { "epoch": 0.73, "learning_rate": 7.772151898734177e-05, "loss": 0.9352, "step": 46500 }, { "epoch": 0.74, "learning_rate": 7.759493670886076e-05, "loss": 0.9347, "step": 46750 }, { "epoch": 0.74, "learning_rate": 7.746835443037975e-05, "loss": 0.9343, "step": 47000 }, { "epoch": 0.74, "learning_rate": 7.734177215189874e-05, "loss": 0.934, "step": 47250 }, { "epoch": 0.75, "learning_rate": 7.721518987341773e-05, "loss": 0.9336, "step": 47500 }, { "epoch": 0.75, "learning_rate": 7.708860759493672e-05, "loss": 0.9345, "step": 47750 }, { "epoch": 0.76, "learning_rate": 7.69620253164557e-05, "loss": 0.932, "step": 48000 } ], "max_steps": 200000, "num_train_epochs": 4, "total_flos": 5.730504888287232e+18, "trial_name": null, "trial_params": null }