{ "best_metric": null, "best_model_checkpoint": null, "epoch": 14.972861688190156, "eval_steps": 100, "global_step": 5000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 1.4099295e-05, "loss": 2.9964, "step": 1 }, { "epoch": 0.01, "learning_rate": 1.409859e-05, "loss": 2.9957, "step": 2 }, { "epoch": 0.01, "learning_rate": 1.4097885e-05, "loss": 2.9916, "step": 3 }, { "epoch": 0.01, "learning_rate": 1.4097180000000001e-05, "loss": 2.9905, "step": 4 }, { "epoch": 0.01, "learning_rate": 1.4096475000000001e-05, "loss": 2.9882, "step": 5 }, { "epoch": 0.02, "learning_rate": 1.4095770000000001e-05, "loss": 2.9911, "step": 6 }, { "epoch": 0.02, "learning_rate": 1.4095065000000001e-05, "loss": 2.9913, "step": 7 }, { "epoch": 0.02, "learning_rate": 1.409436e-05, "loss": 2.9884, "step": 8 }, { "epoch": 0.03, "learning_rate": 1.4093655e-05, "loss": 2.9906, "step": 9 }, { "epoch": 0.03, "learning_rate": 1.4092950000000002e-05, "loss": 2.9887, "step": 10 }, { "epoch": 0.03, "learning_rate": 1.4092245e-05, "loss": 2.9838, "step": 11 }, { "epoch": 0.04, "learning_rate": 1.409154e-05, "loss": 2.9889, "step": 12 }, { "epoch": 0.04, "learning_rate": 1.4090835e-05, "loss": 2.9816, "step": 13 }, { "epoch": 0.04, "learning_rate": 1.409013e-05, "loss": 2.9825, "step": 14 }, { "epoch": 0.04, "learning_rate": 1.4089425e-05, "loss": 2.9799, "step": 15 }, { "epoch": 0.05, "learning_rate": 1.4088720000000001e-05, "loss": 2.9763, "step": 16 }, { "epoch": 0.05, "learning_rate": 1.4088015e-05, "loss": 2.9825, "step": 17 }, { "epoch": 0.05, "learning_rate": 1.408731e-05, "loss": 2.9803, "step": 18 }, { "epoch": 0.06, "learning_rate": 1.4086605e-05, "loss": 2.98, "step": 19 }, { "epoch": 0.06, "learning_rate": 1.40859e-05, "loss": 2.9783, "step": 20 }, { "epoch": 0.06, "learning_rate": 1.4085195e-05, "loss": 2.9698, "step": 21 }, { "epoch": 0.07, "learning_rate": 1.4084490000000001e-05, "loss": 2.9732, "step": 22 }, { "epoch": 0.07, "learning_rate": 1.4083785000000001e-05, "loss": 2.9712, "step": 23 }, { "epoch": 0.07, "learning_rate": 1.4083080000000001e-05, "loss": 2.9768, "step": 24 }, { "epoch": 0.07, "learning_rate": 1.4082375e-05, "loss": 2.9704, "step": 25 }, { "epoch": 0.08, "learning_rate": 1.408167e-05, "loss": 2.9719, "step": 26 }, { "epoch": 0.08, "learning_rate": 1.4080965e-05, "loss": 2.9634, "step": 27 }, { "epoch": 0.08, "learning_rate": 1.4080260000000002e-05, "loss": 2.9662, "step": 28 }, { "epoch": 0.09, "learning_rate": 1.4079555000000002e-05, "loss": 2.9724, "step": 29 }, { "epoch": 0.09, "learning_rate": 1.4078850000000002e-05, "loss": 2.9685, "step": 30 }, { "epoch": 0.09, "learning_rate": 1.4078145e-05, "loss": 2.9624, "step": 31 }, { "epoch": 0.1, "learning_rate": 1.407744e-05, "loss": 2.9631, "step": 32 }, { "epoch": 0.1, "learning_rate": 1.4076735e-05, "loss": 2.9631, "step": 33 }, { "epoch": 0.1, "learning_rate": 1.407603e-05, "loss": 2.9575, "step": 34 }, { "epoch": 0.1, "learning_rate": 1.4075325e-05, "loss": 2.9589, "step": 35 }, { "epoch": 0.11, "learning_rate": 1.407462e-05, "loss": 2.9564, "step": 36 }, { "epoch": 0.11, "learning_rate": 1.4073915e-05, "loss": 2.9577, "step": 37 }, { "epoch": 0.11, "learning_rate": 1.407321e-05, "loss": 2.9524, "step": 38 }, { "epoch": 0.12, "learning_rate": 1.4072505e-05, "loss": 2.9536, "step": 39 }, { "epoch": 0.12, "learning_rate": 1.40718e-05, "loss": 2.9589, "step": 40 }, { "epoch": 0.12, "learning_rate": 1.4071095000000001e-05, "loss": 2.9515, "step": 41 }, { "epoch": 0.13, "learning_rate": 1.4070390000000001e-05, "loss": 2.9536, "step": 42 }, { "epoch": 0.13, "learning_rate": 1.4069685e-05, "loss": 2.9487, "step": 43 }, { "epoch": 0.13, "learning_rate": 1.406898e-05, "loss": 2.9465, "step": 44 }, { "epoch": 0.13, "learning_rate": 1.4068275e-05, "loss": 2.9504, "step": 45 }, { "epoch": 0.14, "learning_rate": 1.406757e-05, "loss": 2.9486, "step": 46 }, { "epoch": 0.14, "learning_rate": 1.4066865000000002e-05, "loss": 2.9473, "step": 47 }, { "epoch": 0.14, "learning_rate": 1.4066160000000002e-05, "loss": 2.9399, "step": 48 }, { "epoch": 0.15, "learning_rate": 1.4065455000000001e-05, "loss": 2.9475, "step": 49 }, { "epoch": 0.15, "learning_rate": 1.4064750000000001e-05, "loss": 2.9454, "step": 50 }, { "epoch": 0.15, "learning_rate": 1.4064045e-05, "loss": 2.9381, "step": 51 }, { "epoch": 0.16, "learning_rate": 1.4063339999999999e-05, "loss": 2.94, "step": 52 }, { "epoch": 0.16, "learning_rate": 1.4062635e-05, "loss": 2.9374, "step": 53 }, { "epoch": 0.16, "learning_rate": 1.406193e-05, "loss": 2.9369, "step": 54 }, { "epoch": 0.16, "learning_rate": 1.4061225e-05, "loss": 2.9316, "step": 55 }, { "epoch": 0.17, "learning_rate": 1.406052e-05, "loss": 2.9324, "step": 56 }, { "epoch": 0.17, "learning_rate": 1.4059815e-05, "loss": 2.9289, "step": 57 }, { "epoch": 0.17, "learning_rate": 1.405911e-05, "loss": 2.9286, "step": 58 }, { "epoch": 0.18, "learning_rate": 1.4058405000000001e-05, "loss": 2.9304, "step": 59 }, { "epoch": 0.18, "learning_rate": 1.4057700000000001e-05, "loss": 2.9225, "step": 60 }, { "epoch": 0.18, "learning_rate": 1.4056995e-05, "loss": 2.9263, "step": 61 }, { "epoch": 0.19, "learning_rate": 1.405629e-05, "loss": 2.9235, "step": 62 }, { "epoch": 0.19, "learning_rate": 1.4055585e-05, "loss": 2.9271, "step": 63 }, { "epoch": 0.19, "learning_rate": 1.405488e-05, "loss": 2.9214, "step": 64 }, { "epoch": 0.19, "learning_rate": 1.4054175000000002e-05, "loss": 2.9175, "step": 65 }, { "epoch": 0.2, "learning_rate": 1.4053470000000001e-05, "loss": 2.912, "step": 66 }, { "epoch": 0.2, "learning_rate": 1.4052765000000001e-05, "loss": 2.9184, "step": 67 }, { "epoch": 0.2, "learning_rate": 1.4052060000000001e-05, "loss": 2.918, "step": 68 }, { "epoch": 0.21, "learning_rate": 1.4051355000000001e-05, "loss": 2.9141, "step": 69 }, { "epoch": 0.21, "learning_rate": 1.405065e-05, "loss": 2.9137, "step": 70 }, { "epoch": 0.21, "learning_rate": 1.4049945e-05, "loss": 2.9099, "step": 71 }, { "epoch": 0.22, "learning_rate": 1.404924e-05, "loss": 2.9079, "step": 72 }, { "epoch": 0.22, "learning_rate": 1.4048535e-05, "loss": 2.9094, "step": 73 }, { "epoch": 0.22, "learning_rate": 1.404783e-05, "loss": 2.9001, "step": 74 }, { "epoch": 0.22, "learning_rate": 1.4047125e-05, "loss": 2.8997, "step": 75 }, { "epoch": 0.23, "learning_rate": 1.404642e-05, "loss": 2.8978, "step": 76 }, { "epoch": 0.23, "learning_rate": 1.4045715e-05, "loss": 2.9003, "step": 77 }, { "epoch": 0.23, "learning_rate": 1.4045010000000001e-05, "loss": 2.9061, "step": 78 }, { "epoch": 0.24, "learning_rate": 1.4044305e-05, "loss": 2.8936, "step": 79 }, { "epoch": 0.24, "learning_rate": 1.40436e-05, "loss": 2.902, "step": 80 }, { "epoch": 0.24, "learning_rate": 1.4042895e-05, "loss": 2.8964, "step": 81 }, { "epoch": 0.25, "learning_rate": 1.404219e-05, "loss": 2.8943, "step": 82 }, { "epoch": 0.25, "learning_rate": 1.4041485e-05, "loss": 2.8908, "step": 83 }, { "epoch": 0.25, "learning_rate": 1.4040780000000001e-05, "loss": 2.8891, "step": 84 }, { "epoch": 0.25, "learning_rate": 1.4040075000000001e-05, "loss": 2.8876, "step": 85 }, { "epoch": 0.26, "learning_rate": 1.4039370000000001e-05, "loss": 2.8885, "step": 86 }, { "epoch": 0.26, "learning_rate": 1.4038665000000001e-05, "loss": 2.8841, "step": 87 }, { "epoch": 0.26, "learning_rate": 1.403796e-05, "loss": 2.8817, "step": 88 }, { "epoch": 0.27, "learning_rate": 1.4037255e-05, "loss": 2.8828, "step": 89 }, { "epoch": 0.27, "learning_rate": 1.4036550000000002e-05, "loss": 2.8797, "step": 90 }, { "epoch": 0.27, "learning_rate": 1.4035845e-05, "loss": 2.8805, "step": 91 }, { "epoch": 0.28, "learning_rate": 1.403514e-05, "loss": 2.8751, "step": 92 }, { "epoch": 0.28, "learning_rate": 1.4034435e-05, "loss": 2.8732, "step": 93 }, { "epoch": 0.28, "learning_rate": 1.403373e-05, "loss": 2.8771, "step": 94 }, { "epoch": 0.28, "learning_rate": 1.4033025e-05, "loss": 2.8727, "step": 95 }, { "epoch": 0.29, "learning_rate": 1.4032320000000001e-05, "loss": 2.869, "step": 96 }, { "epoch": 0.29, "learning_rate": 1.4031615e-05, "loss": 2.8728, "step": 97 }, { "epoch": 0.29, "learning_rate": 1.403091e-05, "loss": 2.8638, "step": 98 }, { "epoch": 0.3, "learning_rate": 1.4030205e-05, "loss": 2.8644, "step": 99 }, { "epoch": 0.3, "learning_rate": 1.40295e-05, "loss": 2.8539, "step": 100 }, { "epoch": 0.3, "eval_accuracy": 0.005741401006711409, "eval_loss": 2.497692584991455, "eval_runtime": 33.8362, "eval_samples_per_second": 8.807, "eval_steps_per_second": 0.562, "step": 100 }, { "epoch": 0.3, "learning_rate": 1.4028795e-05, "loss": 2.861, "step": 101 }, { "epoch": 0.31, "learning_rate": 1.4028090000000001e-05, "loss": 2.8592, "step": 102 }, { "epoch": 0.31, "learning_rate": 1.4027385000000001e-05, "loss": 2.8544, "step": 103 }, { "epoch": 0.31, "learning_rate": 1.4026680000000001e-05, "loss": 2.8535, "step": 104 }, { "epoch": 0.31, "learning_rate": 1.4025975e-05, "loss": 2.8537, "step": 105 }, { "epoch": 0.32, "learning_rate": 1.402527e-05, "loss": 2.856, "step": 106 }, { "epoch": 0.32, "learning_rate": 1.4024565e-05, "loss": 2.8547, "step": 107 }, { "epoch": 0.32, "learning_rate": 1.402386e-05, "loss": 2.851, "step": 108 }, { "epoch": 0.33, "learning_rate": 1.4023155000000002e-05, "loss": 2.8472, "step": 109 }, { "epoch": 0.33, "learning_rate": 1.4022450000000002e-05, "loss": 2.8439, "step": 110 }, { "epoch": 0.33, "learning_rate": 1.4021745e-05, "loss": 2.8429, "step": 111 }, { "epoch": 0.34, "learning_rate": 1.402104e-05, "loss": 2.8413, "step": 112 }, { "epoch": 0.34, "learning_rate": 1.4020335e-05, "loss": 2.8379, "step": 113 }, { "epoch": 0.34, "learning_rate": 1.401963e-05, "loss": 2.8411, "step": 114 }, { "epoch": 0.34, "learning_rate": 1.4018925e-05, "loss": 2.8384, "step": 115 }, { "epoch": 0.35, "learning_rate": 1.401822e-05, "loss": 2.8394, "step": 116 }, { "epoch": 0.35, "learning_rate": 1.4017515e-05, "loss": 2.8364, "step": 117 }, { "epoch": 0.35, "learning_rate": 1.401681e-05, "loss": 2.833, "step": 118 }, { "epoch": 0.36, "learning_rate": 1.4016105e-05, "loss": 2.8341, "step": 119 }, { "epoch": 0.36, "learning_rate": 1.40154e-05, "loss": 2.8285, "step": 120 }, { "epoch": 0.36, "learning_rate": 1.4014695000000001e-05, "loss": 2.8294, "step": 121 }, { "epoch": 0.37, "learning_rate": 1.4013990000000001e-05, "loss": 2.8247, "step": 122 }, { "epoch": 0.37, "learning_rate": 1.4013285e-05, "loss": 2.8241, "step": 123 }, { "epoch": 0.37, "learning_rate": 1.401258e-05, "loss": 2.8216, "step": 124 }, { "epoch": 0.37, "learning_rate": 1.4011875e-05, "loss": 2.8221, "step": 125 }, { "epoch": 0.38, "learning_rate": 1.401117e-05, "loss": 2.8218, "step": 126 }, { "epoch": 0.38, "learning_rate": 1.4010465000000002e-05, "loss": 2.8186, "step": 127 }, { "epoch": 0.38, "learning_rate": 1.4009760000000002e-05, "loss": 2.818, "step": 128 }, { "epoch": 0.39, "learning_rate": 1.4009055000000001e-05, "loss": 2.8136, "step": 129 }, { "epoch": 0.39, "learning_rate": 1.4008350000000001e-05, "loss": 2.8108, "step": 130 }, { "epoch": 0.39, "learning_rate": 1.4007645000000001e-05, "loss": 2.8121, "step": 131 }, { "epoch": 0.4, "learning_rate": 1.4006939999999999e-05, "loss": 2.8087, "step": 132 }, { "epoch": 0.4, "learning_rate": 1.4006235e-05, "loss": 2.8062, "step": 133 }, { "epoch": 0.4, "learning_rate": 1.400553e-05, "loss": 2.8097, "step": 134 }, { "epoch": 0.4, "learning_rate": 1.4004825e-05, "loss": 2.8043, "step": 135 }, { "epoch": 0.41, "learning_rate": 1.400412e-05, "loss": 2.8016, "step": 136 }, { "epoch": 0.41, "learning_rate": 1.4003415e-05, "loss": 2.8073, "step": 137 }, { "epoch": 0.41, "learning_rate": 1.400271e-05, "loss": 2.8062, "step": 138 }, { "epoch": 0.42, "learning_rate": 1.4002005000000001e-05, "loss": 2.7996, "step": 139 }, { "epoch": 0.42, "learning_rate": 1.4001300000000001e-05, "loss": 2.7946, "step": 140 }, { "epoch": 0.42, "learning_rate": 1.4000595e-05, "loss": 2.7949, "step": 141 }, { "epoch": 0.43, "learning_rate": 1.399989e-05, "loss": 2.7956, "step": 142 }, { "epoch": 0.43, "learning_rate": 1.3999185e-05, "loss": 2.7988, "step": 143 }, { "epoch": 0.43, "learning_rate": 1.399848e-05, "loss": 2.7909, "step": 144 }, { "epoch": 0.43, "learning_rate": 1.3997775e-05, "loss": 2.7933, "step": 145 }, { "epoch": 0.44, "learning_rate": 1.3997070000000001e-05, "loss": 2.7907, "step": 146 }, { "epoch": 0.44, "learning_rate": 1.3996365000000001e-05, "loss": 2.7888, "step": 147 }, { "epoch": 0.44, "learning_rate": 1.3995660000000001e-05, "loss": 2.7852, "step": 148 }, { "epoch": 0.45, "learning_rate": 1.3994955000000001e-05, "loss": 2.7824, "step": 149 }, { "epoch": 0.45, "learning_rate": 1.399425e-05, "loss": 2.7808, "step": 150 }, { "epoch": 0.45, "learning_rate": 1.3993545e-05, "loss": 2.7792, "step": 151 }, { "epoch": 0.46, "learning_rate": 1.399284e-05, "loss": 2.7799, "step": 152 }, { "epoch": 0.46, "learning_rate": 1.3992135e-05, "loss": 2.7773, "step": 153 }, { "epoch": 0.46, "learning_rate": 1.399143e-05, "loss": 2.7791, "step": 154 }, { "epoch": 0.46, "learning_rate": 1.3990725e-05, "loss": 2.7739, "step": 155 }, { "epoch": 0.47, "learning_rate": 1.399002e-05, "loss": 2.7666, "step": 156 }, { "epoch": 0.47, "learning_rate": 1.3989315e-05, "loss": 2.771, "step": 157 }, { "epoch": 0.47, "learning_rate": 1.3988610000000001e-05, "loss": 2.772, "step": 158 }, { "epoch": 0.48, "learning_rate": 1.3987905e-05, "loss": 2.7718, "step": 159 }, { "epoch": 0.48, "learning_rate": 1.39872e-05, "loss": 2.7697, "step": 160 }, { "epoch": 0.48, "learning_rate": 1.3986495e-05, "loss": 2.7691, "step": 161 }, { "epoch": 0.49, "learning_rate": 1.398579e-05, "loss": 2.7621, "step": 162 }, { "epoch": 0.49, "learning_rate": 1.3985085e-05, "loss": 2.7653, "step": 163 }, { "epoch": 0.49, "learning_rate": 1.3984380000000001e-05, "loss": 2.7639, "step": 164 }, { "epoch": 0.49, "learning_rate": 1.3983675000000001e-05, "loss": 2.7634, "step": 165 }, { "epoch": 0.5, "learning_rate": 1.3982970000000001e-05, "loss": 2.7599, "step": 166 }, { "epoch": 0.5, "learning_rate": 1.3982265000000001e-05, "loss": 2.757, "step": 167 }, { "epoch": 0.5, "learning_rate": 1.398156e-05, "loss": 2.756, "step": 168 }, { "epoch": 0.51, "learning_rate": 1.3980855e-05, "loss": 2.7508, "step": 169 }, { "epoch": 0.51, "learning_rate": 1.3980150000000002e-05, "loss": 2.7562, "step": 170 }, { "epoch": 0.51, "learning_rate": 1.3979445000000002e-05, "loss": 2.7515, "step": 171 }, { "epoch": 0.52, "learning_rate": 1.397874e-05, "loss": 2.7461, "step": 172 }, { "epoch": 0.52, "learning_rate": 1.3978035e-05, "loss": 2.7455, "step": 173 }, { "epoch": 0.52, "learning_rate": 1.397733e-05, "loss": 2.7471, "step": 174 }, { "epoch": 0.52, "learning_rate": 1.3976625e-05, "loss": 2.7457, "step": 175 }, { "epoch": 0.53, "learning_rate": 1.3975920000000001e-05, "loss": 2.7475, "step": 176 }, { "epoch": 0.53, "learning_rate": 1.3975215e-05, "loss": 2.7453, "step": 177 }, { "epoch": 0.53, "learning_rate": 1.397451e-05, "loss": 2.7447, "step": 178 }, { "epoch": 0.54, "learning_rate": 1.3973805e-05, "loss": 2.7409, "step": 179 }, { "epoch": 0.54, "learning_rate": 1.39731e-05, "loss": 2.7407, "step": 180 }, { "epoch": 0.54, "learning_rate": 1.3972395e-05, "loss": 2.7398, "step": 181 }, { "epoch": 0.55, "learning_rate": 1.3971690000000001e-05, "loss": 2.7378, "step": 182 }, { "epoch": 0.55, "learning_rate": 1.3970985000000001e-05, "loss": 2.7294, "step": 183 }, { "epoch": 0.55, "learning_rate": 1.3970280000000001e-05, "loss": 2.735, "step": 184 }, { "epoch": 0.55, "learning_rate": 1.3969575e-05, "loss": 2.7334, "step": 185 }, { "epoch": 0.56, "learning_rate": 1.396887e-05, "loss": 2.7327, "step": 186 }, { "epoch": 0.56, "learning_rate": 1.3968165e-05, "loss": 2.7246, "step": 187 }, { "epoch": 0.56, "learning_rate": 1.396746e-05, "loss": 2.7224, "step": 188 }, { "epoch": 0.57, "learning_rate": 1.3966755000000002e-05, "loss": 2.7281, "step": 189 }, { "epoch": 0.57, "learning_rate": 1.3966050000000002e-05, "loss": 2.7271, "step": 190 }, { "epoch": 0.57, "learning_rate": 1.3965345000000001e-05, "loss": 2.724, "step": 191 }, { "epoch": 0.57, "learning_rate": 1.396464e-05, "loss": 2.7223, "step": 192 }, { "epoch": 0.58, "learning_rate": 1.3963935e-05, "loss": 2.7201, "step": 193 }, { "epoch": 0.58, "learning_rate": 1.3963229999999999e-05, "loss": 2.7232, "step": 194 }, { "epoch": 0.58, "learning_rate": 1.3962525e-05, "loss": 2.7128, "step": 195 }, { "epoch": 0.59, "learning_rate": 1.396182e-05, "loss": 2.7158, "step": 196 }, { "epoch": 0.59, "learning_rate": 1.3961115e-05, "loss": 2.7163, "step": 197 }, { "epoch": 0.59, "learning_rate": 1.396041e-05, "loss": 2.714, "step": 198 }, { "epoch": 0.6, "learning_rate": 1.3959705e-05, "loss": 2.7111, "step": 199 }, { "epoch": 0.6, "learning_rate": 1.3959e-05, "loss": 2.7052, "step": 200 }, { "epoch": 0.6, "eval_accuracy": 0.0041946308724832215, "eval_loss": 2.438399076461792, "eval_runtime": 33.6582, "eval_samples_per_second": 8.854, "eval_steps_per_second": 0.564, "step": 200 }, { "epoch": 0.6, "learning_rate": 1.3958295000000001e-05, "loss": 2.7084, "step": 201 }, { "epoch": 0.6, "learning_rate": 1.3957590000000001e-05, "loss": 2.7077, "step": 202 }, { "epoch": 0.61, "learning_rate": 1.3956885e-05, "loss": 2.7064, "step": 203 }, { "epoch": 0.61, "learning_rate": 1.395618e-05, "loss": 2.71, "step": 204 }, { "epoch": 0.61, "learning_rate": 1.3955475e-05, "loss": 2.708, "step": 205 }, { "epoch": 0.62, "learning_rate": 1.395477e-05, "loss": 2.7074, "step": 206 }, { "epoch": 0.62, "learning_rate": 1.3954065000000002e-05, "loss": 2.7065, "step": 207 }, { "epoch": 0.62, "learning_rate": 1.3953360000000002e-05, "loss": 2.6985, "step": 208 }, { "epoch": 0.63, "learning_rate": 1.3952655000000001e-05, "loss": 2.7002, "step": 209 }, { "epoch": 0.63, "learning_rate": 1.3951950000000001e-05, "loss": 2.6963, "step": 210 }, { "epoch": 0.63, "learning_rate": 1.3951245000000001e-05, "loss": 2.6959, "step": 211 }, { "epoch": 0.63, "learning_rate": 1.3950539999999999e-05, "loss": 2.6946, "step": 212 }, { "epoch": 0.64, "learning_rate": 1.3949835e-05, "loss": 2.6932, "step": 213 }, { "epoch": 0.64, "learning_rate": 1.394913e-05, "loss": 2.692, "step": 214 }, { "epoch": 0.64, "learning_rate": 1.3948425e-05, "loss": 2.6987, "step": 215 }, { "epoch": 0.65, "learning_rate": 1.394772e-05, "loss": 2.6903, "step": 216 }, { "epoch": 0.65, "learning_rate": 1.3947015e-05, "loss": 2.6875, "step": 217 }, { "epoch": 0.65, "learning_rate": 1.394631e-05, "loss": 2.6885, "step": 218 }, { "epoch": 0.66, "learning_rate": 1.3945605000000001e-05, "loss": 2.6877, "step": 219 }, { "epoch": 0.66, "learning_rate": 1.3944900000000001e-05, "loss": 2.6872, "step": 220 }, { "epoch": 0.66, "learning_rate": 1.3944195e-05, "loss": 2.6775, "step": 221 }, { "epoch": 0.66, "learning_rate": 1.394349e-05, "loss": 2.6808, "step": 222 }, { "epoch": 0.67, "learning_rate": 1.3942785e-05, "loss": 2.6791, "step": 223 }, { "epoch": 0.67, "learning_rate": 1.394208e-05, "loss": 2.6763, "step": 224 }, { "epoch": 0.67, "learning_rate": 1.3941375e-05, "loss": 2.6835, "step": 225 }, { "epoch": 0.68, "learning_rate": 1.3940670000000001e-05, "loss": 2.6773, "step": 226 }, { "epoch": 0.68, "learning_rate": 1.3939965000000001e-05, "loss": 2.6764, "step": 227 }, { "epoch": 0.68, "learning_rate": 1.3939260000000001e-05, "loss": 2.678, "step": 228 }, { "epoch": 0.69, "learning_rate": 1.3938555000000001e-05, "loss": 2.6695, "step": 229 }, { "epoch": 0.69, "learning_rate": 1.393785e-05, "loss": 2.6749, "step": 230 }, { "epoch": 0.69, "learning_rate": 1.3937145e-05, "loss": 2.6742, "step": 231 }, { "epoch": 0.69, "learning_rate": 1.393644e-05, "loss": 2.6649, "step": 232 }, { "epoch": 0.7, "learning_rate": 1.3935735e-05, "loss": 2.6663, "step": 233 }, { "epoch": 0.7, "learning_rate": 1.393503e-05, "loss": 2.6681, "step": 234 }, { "epoch": 0.7, "learning_rate": 1.3934325e-05, "loss": 2.6664, "step": 235 }, { "epoch": 0.71, "learning_rate": 1.393362e-05, "loss": 2.6668, "step": 236 }, { "epoch": 0.71, "learning_rate": 1.3932915e-05, "loss": 2.6658, "step": 237 }, { "epoch": 0.71, "learning_rate": 1.3932210000000001e-05, "loss": 2.6668, "step": 238 }, { "epoch": 0.72, "learning_rate": 1.3931505e-05, "loss": 2.6586, "step": 239 }, { "epoch": 0.72, "learning_rate": 1.39308e-05, "loss": 2.6622, "step": 240 }, { "epoch": 0.72, "learning_rate": 1.3930095e-05, "loss": 2.6635, "step": 241 }, { "epoch": 0.72, "learning_rate": 1.392939e-05, "loss": 2.6574, "step": 242 }, { "epoch": 0.73, "learning_rate": 1.3928685e-05, "loss": 2.6593, "step": 243 }, { "epoch": 0.73, "learning_rate": 1.3927980000000001e-05, "loss": 2.6537, "step": 244 }, { "epoch": 0.73, "learning_rate": 1.3927275000000001e-05, "loss": 2.6582, "step": 245 }, { "epoch": 0.74, "learning_rate": 1.3926570000000001e-05, "loss": 2.6518, "step": 246 }, { "epoch": 0.74, "learning_rate": 1.3925865000000001e-05, "loss": 2.6522, "step": 247 }, { "epoch": 0.74, "learning_rate": 1.392516e-05, "loss": 2.6522, "step": 248 }, { "epoch": 0.75, "learning_rate": 1.3924455e-05, "loss": 2.6469, "step": 249 }, { "epoch": 0.75, "learning_rate": 1.392375e-05, "loss": 2.6493, "step": 250 }, { "epoch": 0.75, "learning_rate": 1.3923045000000002e-05, "loss": 2.6504, "step": 251 }, { "epoch": 0.75, "learning_rate": 1.3922340000000002e-05, "loss": 2.6447, "step": 252 }, { "epoch": 0.76, "learning_rate": 1.3921635e-05, "loss": 2.6502, "step": 253 }, { "epoch": 0.76, "learning_rate": 1.392093e-05, "loss": 2.6415, "step": 254 }, { "epoch": 0.76, "learning_rate": 1.3920225e-05, "loss": 2.6425, "step": 255 }, { "epoch": 0.77, "learning_rate": 1.3919520000000001e-05, "loss": 2.6479, "step": 256 }, { "epoch": 0.77, "learning_rate": 1.3918815e-05, "loss": 2.6414, "step": 257 }, { "epoch": 0.77, "learning_rate": 1.391811e-05, "loss": 2.6387, "step": 258 }, { "epoch": 0.78, "learning_rate": 1.3917405e-05, "loss": 2.6374, "step": 259 }, { "epoch": 0.78, "learning_rate": 1.39167e-05, "loss": 2.6378, "step": 260 }, { "epoch": 0.78, "learning_rate": 1.3915995e-05, "loss": 2.6386, "step": 261 }, { "epoch": 0.78, "learning_rate": 1.391529e-05, "loss": 2.6332, "step": 262 }, { "epoch": 0.79, "learning_rate": 1.3914585000000001e-05, "loss": 2.6363, "step": 263 }, { "epoch": 0.79, "learning_rate": 1.3913880000000001e-05, "loss": 2.6347, "step": 264 }, { "epoch": 0.79, "learning_rate": 1.3913175e-05, "loss": 2.6322, "step": 265 }, { "epoch": 0.8, "learning_rate": 1.391247e-05, "loss": 2.6372, "step": 266 }, { "epoch": 0.8, "learning_rate": 1.3911765e-05, "loss": 2.6285, "step": 267 }, { "epoch": 0.8, "learning_rate": 1.391106e-05, "loss": 2.6306, "step": 268 }, { "epoch": 0.81, "learning_rate": 1.3910355000000002e-05, "loss": 2.6252, "step": 269 }, { "epoch": 0.81, "learning_rate": 1.3909650000000002e-05, "loss": 2.6298, "step": 270 }, { "epoch": 0.81, "learning_rate": 1.3908945000000001e-05, "loss": 2.6225, "step": 271 }, { "epoch": 0.81, "learning_rate": 1.3908240000000001e-05, "loss": 2.6257, "step": 272 }, { "epoch": 0.82, "learning_rate": 1.3907535e-05, "loss": 2.6219, "step": 273 }, { "epoch": 0.82, "learning_rate": 1.3906829999999999e-05, "loss": 2.622, "step": 274 }, { "epoch": 0.82, "learning_rate": 1.3906125e-05, "loss": 2.623, "step": 275 }, { "epoch": 0.83, "learning_rate": 1.390542e-05, "loss": 2.6237, "step": 276 }, { "epoch": 0.83, "learning_rate": 1.3904715e-05, "loss": 2.6161, "step": 277 }, { "epoch": 0.83, "learning_rate": 1.390401e-05, "loss": 2.6131, "step": 278 }, { "epoch": 0.84, "learning_rate": 1.3903305e-05, "loss": 2.6198, "step": 279 }, { "epoch": 0.84, "learning_rate": 1.39026e-05, "loss": 2.6129, "step": 280 }, { "epoch": 0.84, "learning_rate": 1.3901895000000001e-05, "loss": 2.6135, "step": 281 }, { "epoch": 0.84, "learning_rate": 1.3901190000000001e-05, "loss": 2.6161, "step": 282 }, { "epoch": 0.85, "learning_rate": 1.3900485e-05, "loss": 2.6112, "step": 283 }, { "epoch": 0.85, "learning_rate": 1.389978e-05, "loss": 2.6164, "step": 284 }, { "epoch": 0.85, "learning_rate": 1.3899075e-05, "loss": 2.6104, "step": 285 }, { "epoch": 0.86, "learning_rate": 1.389837e-05, "loss": 2.609, "step": 286 }, { "epoch": 0.86, "learning_rate": 1.3897665000000002e-05, "loss": 2.6048, "step": 287 }, { "epoch": 0.86, "learning_rate": 1.3896960000000002e-05, "loss": 2.6109, "step": 288 }, { "epoch": 0.87, "learning_rate": 1.3896255000000001e-05, "loss": 2.6075, "step": 289 }, { "epoch": 0.87, "learning_rate": 1.3895550000000001e-05, "loss": 2.6035, "step": 290 }, { "epoch": 0.87, "learning_rate": 1.3894845000000001e-05, "loss": 2.604, "step": 291 }, { "epoch": 0.87, "learning_rate": 1.389414e-05, "loss": 2.6067, "step": 292 }, { "epoch": 0.88, "learning_rate": 1.3893435e-05, "loss": 2.6034, "step": 293 }, { "epoch": 0.88, "learning_rate": 1.389273e-05, "loss": 2.5989, "step": 294 }, { "epoch": 0.88, "learning_rate": 1.3892025e-05, "loss": 2.6005, "step": 295 }, { "epoch": 0.89, "learning_rate": 1.389132e-05, "loss": 2.5971, "step": 296 }, { "epoch": 0.89, "learning_rate": 1.3890615e-05, "loss": 2.5977, "step": 297 }, { "epoch": 0.89, "learning_rate": 1.388991e-05, "loss": 2.5965, "step": 298 }, { "epoch": 0.9, "learning_rate": 1.3889205e-05, "loss": 2.5983, "step": 299 }, { "epoch": 0.9, "learning_rate": 1.3888500000000001e-05, "loss": 2.5933, "step": 300 }, { "epoch": 0.9, "eval_accuracy": 0.0034212458053691276, "eval_loss": 2.371124744415283, "eval_runtime": 30.2278, "eval_samples_per_second": 9.858, "eval_steps_per_second": 0.629, "step": 300 }, { "epoch": 0.9, "learning_rate": 1.3887795e-05, "loss": 2.5961, "step": 301 }, { "epoch": 0.9, "learning_rate": 1.388709e-05, "loss": 2.5872, "step": 302 }, { "epoch": 0.91, "learning_rate": 1.3886385e-05, "loss": 2.592, "step": 303 }, { "epoch": 0.91, "learning_rate": 1.388568e-05, "loss": 2.5919, "step": 304 }, { "epoch": 0.91, "learning_rate": 1.3884975e-05, "loss": 2.591, "step": 305 }, { "epoch": 0.92, "learning_rate": 1.3884270000000001e-05, "loss": 2.5895, "step": 306 }, { "epoch": 0.92, "learning_rate": 1.3883565000000001e-05, "loss": 2.5905, "step": 307 }, { "epoch": 0.92, "learning_rate": 1.3882860000000001e-05, "loss": 2.5864, "step": 308 }, { "epoch": 0.93, "learning_rate": 1.3882155000000001e-05, "loss": 2.5824, "step": 309 }, { "epoch": 0.93, "learning_rate": 1.388145e-05, "loss": 2.58, "step": 310 }, { "epoch": 0.93, "learning_rate": 1.3880745e-05, "loss": 2.5861, "step": 311 }, { "epoch": 0.93, "learning_rate": 1.3880040000000002e-05, "loss": 2.5827, "step": 312 }, { "epoch": 0.94, "learning_rate": 1.3879335e-05, "loss": 2.5778, "step": 313 }, { "epoch": 0.94, "learning_rate": 1.387863e-05, "loss": 2.5792, "step": 314 }, { "epoch": 0.94, "learning_rate": 1.3877925e-05, "loss": 2.5824, "step": 315 }, { "epoch": 0.95, "learning_rate": 1.387722e-05, "loss": 2.5789, "step": 316 }, { "epoch": 0.95, "learning_rate": 1.3876515e-05, "loss": 2.5725, "step": 317 }, { "epoch": 0.95, "learning_rate": 1.3875810000000001e-05, "loss": 2.5796, "step": 318 }, { "epoch": 0.96, "learning_rate": 1.3875105e-05, "loss": 2.5782, "step": 319 }, { "epoch": 0.96, "learning_rate": 1.38744e-05, "loss": 2.5741, "step": 320 }, { "epoch": 0.96, "learning_rate": 1.3873695e-05, "loss": 2.5751, "step": 321 }, { "epoch": 0.96, "learning_rate": 1.387299e-05, "loss": 2.5727, "step": 322 }, { "epoch": 0.97, "learning_rate": 1.3872285e-05, "loss": 2.5733, "step": 323 }, { "epoch": 0.97, "learning_rate": 1.3871580000000001e-05, "loss": 2.5718, "step": 324 }, { "epoch": 0.97, "learning_rate": 1.3870875000000001e-05, "loss": 2.5659, "step": 325 }, { "epoch": 0.98, "learning_rate": 1.3870170000000001e-05, "loss": 2.5716, "step": 326 }, { "epoch": 0.98, "learning_rate": 1.3869465000000001e-05, "loss": 2.5701, "step": 327 }, { "epoch": 0.98, "learning_rate": 1.386876e-05, "loss": 2.5658, "step": 328 }, { "epoch": 0.99, "learning_rate": 1.3868055e-05, "loss": 2.5659, "step": 329 }, { "epoch": 0.99, "learning_rate": 1.386735e-05, "loss": 2.5592, "step": 330 }, { "epoch": 0.99, "learning_rate": 1.3866645000000002e-05, "loss": 2.5662, "step": 331 }, { "epoch": 0.99, "learning_rate": 1.3865940000000002e-05, "loss": 2.5658, "step": 332 }, { "epoch": 1.0, "learning_rate": 1.3865235e-05, "loss": 2.5678, "step": 333 }, { "epoch": 1.0, "learning_rate": 1.386453e-05, "loss": 2.5623, "step": 334 }, { "epoch": 1.0, "learning_rate": 1.3863825e-05, "loss": 2.5651, "step": 335 }, { "epoch": 1.01, "learning_rate": 1.386312e-05, "loss": 2.5635, "step": 336 }, { "epoch": 1.01, "learning_rate": 1.3862415e-05, "loss": 2.5584, "step": 337 }, { "epoch": 1.01, "learning_rate": 1.386171e-05, "loss": 2.5575, "step": 338 }, { "epoch": 1.02, "learning_rate": 1.3861005e-05, "loss": 2.5575, "step": 339 }, { "epoch": 1.02, "learning_rate": 1.38603e-05, "loss": 2.555, "step": 340 }, { "epoch": 1.02, "learning_rate": 1.3859595e-05, "loss": 2.5511, "step": 341 }, { "epoch": 1.02, "learning_rate": 1.385889e-05, "loss": 2.5517, "step": 342 }, { "epoch": 1.03, "learning_rate": 1.3858185000000001e-05, "loss": 2.5524, "step": 343 }, { "epoch": 1.03, "learning_rate": 1.3857480000000001e-05, "loss": 2.5545, "step": 344 }, { "epoch": 1.03, "learning_rate": 1.3856775e-05, "loss": 2.5505, "step": 345 }, { "epoch": 1.04, "learning_rate": 1.385607e-05, "loss": 2.5541, "step": 346 }, { "epoch": 1.04, "learning_rate": 1.3855365e-05, "loss": 2.5489, "step": 347 }, { "epoch": 1.04, "learning_rate": 1.385466e-05, "loss": 2.5481, "step": 348 }, { "epoch": 1.05, "learning_rate": 1.3853955000000002e-05, "loss": 2.5483, "step": 349 }, { "epoch": 1.05, "learning_rate": 1.3853250000000002e-05, "loss": 2.5401, "step": 350 }, { "epoch": 1.05, "learning_rate": 1.3852545000000001e-05, "loss": 2.5394, "step": 351 }, { "epoch": 1.05, "learning_rate": 1.3851840000000001e-05, "loss": 2.5434, "step": 352 }, { "epoch": 1.06, "learning_rate": 1.3851135e-05, "loss": 2.5389, "step": 353 }, { "epoch": 1.06, "learning_rate": 1.3850429999999999e-05, "loss": 2.5456, "step": 354 }, { "epoch": 1.06, "learning_rate": 1.3849725e-05, "loss": 2.5397, "step": 355 }, { "epoch": 1.07, "learning_rate": 1.384902e-05, "loss": 2.5402, "step": 356 }, { "epoch": 1.07, "learning_rate": 1.3848315e-05, "loss": 2.5409, "step": 357 }, { "epoch": 1.07, "learning_rate": 1.384761e-05, "loss": 2.5368, "step": 358 }, { "epoch": 1.08, "learning_rate": 1.3846905e-05, "loss": 2.5378, "step": 359 }, { "epoch": 1.08, "learning_rate": 1.38462e-05, "loss": 2.535, "step": 360 }, { "epoch": 1.08, "learning_rate": 1.3845495000000001e-05, "loss": 2.5334, "step": 361 }, { "epoch": 1.08, "learning_rate": 1.3844790000000001e-05, "loss": 2.5367, "step": 362 }, { "epoch": 1.09, "learning_rate": 1.3844085e-05, "loss": 2.5326, "step": 363 }, { "epoch": 1.09, "learning_rate": 1.384338e-05, "loss": 2.5292, "step": 364 }, { "epoch": 1.09, "learning_rate": 1.3842675e-05, "loss": 2.5399, "step": 365 }, { "epoch": 1.1, "learning_rate": 1.384197e-05, "loss": 2.5313, "step": 366 }, { "epoch": 1.1, "learning_rate": 1.3841265e-05, "loss": 2.5278, "step": 367 }, { "epoch": 1.1, "learning_rate": 1.3840560000000002e-05, "loss": 2.5322, "step": 368 }, { "epoch": 1.1, "learning_rate": 1.3839855000000001e-05, "loss": 2.5248, "step": 369 }, { "epoch": 1.11, "learning_rate": 1.3839150000000001e-05, "loss": 2.5254, "step": 370 }, { "epoch": 1.11, "learning_rate": 1.3838445000000001e-05, "loss": 2.5256, "step": 371 }, { "epoch": 1.11, "learning_rate": 1.383774e-05, "loss": 2.5246, "step": 372 }, { "epoch": 1.12, "learning_rate": 1.3837035e-05, "loss": 2.5232, "step": 373 }, { "epoch": 1.12, "learning_rate": 1.383633e-05, "loss": 2.5253, "step": 374 }, { "epoch": 1.12, "learning_rate": 1.3835625e-05, "loss": 2.5248, "step": 375 }, { "epoch": 1.13, "learning_rate": 1.383492e-05, "loss": 2.5224, "step": 376 }, { "epoch": 1.13, "learning_rate": 1.3834215e-05, "loss": 2.5225, "step": 377 }, { "epoch": 1.13, "learning_rate": 1.383351e-05, "loss": 2.5215, "step": 378 }, { "epoch": 1.13, "learning_rate": 1.3832805e-05, "loss": 2.5163, "step": 379 }, { "epoch": 1.14, "learning_rate": 1.3832100000000001e-05, "loss": 2.523, "step": 380 }, { "epoch": 1.14, "learning_rate": 1.3831395e-05, "loss": 2.5188, "step": 381 }, { "epoch": 1.14, "learning_rate": 1.383069e-05, "loss": 2.5183, "step": 382 }, { "epoch": 1.15, "learning_rate": 1.3829985e-05, "loss": 2.5164, "step": 383 }, { "epoch": 1.15, "learning_rate": 1.382928e-05, "loss": 2.5157, "step": 384 }, { "epoch": 1.15, "learning_rate": 1.3828575e-05, "loss": 2.518, "step": 385 }, { "epoch": 1.16, "learning_rate": 1.3827870000000001e-05, "loss": 2.5138, "step": 386 }, { "epoch": 1.16, "learning_rate": 1.3827165000000001e-05, "loss": 2.5122, "step": 387 }, { "epoch": 1.16, "learning_rate": 1.3826460000000001e-05, "loss": 2.5119, "step": 388 }, { "epoch": 1.16, "learning_rate": 1.3825755000000001e-05, "loss": 2.5115, "step": 389 }, { "epoch": 1.17, "learning_rate": 1.382505e-05, "loss": 2.5114, "step": 390 }, { "epoch": 1.17, "learning_rate": 1.3824345e-05, "loss": 2.5133, "step": 391 }, { "epoch": 1.17, "learning_rate": 1.3823640000000002e-05, "loss": 2.5062, "step": 392 }, { "epoch": 1.18, "learning_rate": 1.3822935000000002e-05, "loss": 2.5159, "step": 393 }, { "epoch": 1.18, "learning_rate": 1.382223e-05, "loss": 2.5064, "step": 394 }, { "epoch": 1.18, "learning_rate": 1.3821525e-05, "loss": 2.5111, "step": 395 }, { "epoch": 1.19, "learning_rate": 1.382082e-05, "loss": 2.5065, "step": 396 }, { "epoch": 1.19, "learning_rate": 1.3820115e-05, "loss": 2.5108, "step": 397 }, { "epoch": 1.19, "learning_rate": 1.3819410000000001e-05, "loss": 2.5064, "step": 398 }, { "epoch": 1.19, "learning_rate": 1.3818705e-05, "loss": 2.505, "step": 399 }, { "epoch": 1.2, "learning_rate": 1.3818e-05, "loss": 2.5043, "step": 400 }, { "epoch": 1.2, "eval_accuracy": 0.0029886744966442953, "eval_loss": 2.3105242252349854, "eval_runtime": 30.6998, "eval_samples_per_second": 9.707, "eval_steps_per_second": 0.619, "step": 400 }, { "epoch": 1.2, "learning_rate": 1.3817295e-05, "loss": 2.5042, "step": 401 }, { "epoch": 1.2, "learning_rate": 1.381659e-05, "loss": 2.4984, "step": 402 }, { "epoch": 1.21, "learning_rate": 1.3815885e-05, "loss": 2.4995, "step": 403 }, { "epoch": 1.21, "learning_rate": 1.381518e-05, "loss": 2.5014, "step": 404 }, { "epoch": 1.21, "learning_rate": 1.3814475000000001e-05, "loss": 2.4969, "step": 405 }, { "epoch": 1.22, "learning_rate": 1.3813770000000001e-05, "loss": 2.4967, "step": 406 }, { "epoch": 1.22, "learning_rate": 1.3813065000000001e-05, "loss": 2.4999, "step": 407 }, { "epoch": 1.22, "learning_rate": 1.381236e-05, "loss": 2.4983, "step": 408 }, { "epoch": 1.22, "learning_rate": 1.3811655e-05, "loss": 2.4972, "step": 409 }, { "epoch": 1.23, "learning_rate": 1.381095e-05, "loss": 2.4921, "step": 410 }, { "epoch": 1.23, "learning_rate": 1.3810245000000002e-05, "loss": 2.4968, "step": 411 }, { "epoch": 1.23, "learning_rate": 1.3809540000000002e-05, "loss": 2.498, "step": 412 }, { "epoch": 1.24, "learning_rate": 1.3808835000000001e-05, "loss": 2.4945, "step": 413 }, { "epoch": 1.24, "learning_rate": 1.380813e-05, "loss": 2.4905, "step": 414 }, { "epoch": 1.24, "learning_rate": 1.3807425e-05, "loss": 2.4935, "step": 415 }, { "epoch": 1.25, "learning_rate": 1.380672e-05, "loss": 2.4909, "step": 416 }, { "epoch": 1.25, "learning_rate": 1.3806015e-05, "loss": 2.4922, "step": 417 }, { "epoch": 1.25, "learning_rate": 1.380531e-05, "loss": 2.4875, "step": 418 }, { "epoch": 1.25, "learning_rate": 1.3804605e-05, "loss": 2.4925, "step": 419 }, { "epoch": 1.26, "learning_rate": 1.38039e-05, "loss": 2.486, "step": 420 }, { "epoch": 1.26, "learning_rate": 1.3803195e-05, "loss": 2.4908, "step": 421 }, { "epoch": 1.26, "learning_rate": 1.380249e-05, "loss": 2.4869, "step": 422 }, { "epoch": 1.27, "learning_rate": 1.3801785000000001e-05, "loss": 2.4875, "step": 423 }, { "epoch": 1.27, "learning_rate": 1.3801080000000001e-05, "loss": 2.4809, "step": 424 }, { "epoch": 1.27, "learning_rate": 1.3800375e-05, "loss": 2.4857, "step": 425 }, { "epoch": 1.28, "learning_rate": 1.379967e-05, "loss": 2.4825, "step": 426 }, { "epoch": 1.28, "learning_rate": 1.3798965e-05, "loss": 2.4839, "step": 427 }, { "epoch": 1.28, "learning_rate": 1.379826e-05, "loss": 2.4823, "step": 428 }, { "epoch": 1.28, "learning_rate": 1.3797555000000002e-05, "loss": 2.4817, "step": 429 }, { "epoch": 1.29, "learning_rate": 1.3796850000000002e-05, "loss": 2.4814, "step": 430 }, { "epoch": 1.29, "learning_rate": 1.3796145000000001e-05, "loss": 2.4775, "step": 431 }, { "epoch": 1.29, "learning_rate": 1.3795440000000001e-05, "loss": 2.4767, "step": 432 }, { "epoch": 1.3, "learning_rate": 1.3794735000000001e-05, "loss": 2.4778, "step": 433 }, { "epoch": 1.3, "learning_rate": 1.3794029999999999e-05, "loss": 2.4752, "step": 434 }, { "epoch": 1.3, "learning_rate": 1.3793325e-05, "loss": 2.4787, "step": 435 }, { "epoch": 1.31, "learning_rate": 1.379262e-05, "loss": 2.4741, "step": 436 }, { "epoch": 1.31, "learning_rate": 1.3791915e-05, "loss": 2.4754, "step": 437 }, { "epoch": 1.31, "learning_rate": 1.379121e-05, "loss": 2.4787, "step": 438 }, { "epoch": 1.31, "learning_rate": 1.3790505e-05, "loss": 2.4718, "step": 439 }, { "epoch": 1.32, "learning_rate": 1.37898e-05, "loss": 2.4735, "step": 440 }, { "epoch": 1.32, "learning_rate": 1.3789095e-05, "loss": 2.4748, "step": 441 }, { "epoch": 1.32, "learning_rate": 1.3788390000000001e-05, "loss": 2.4666, "step": 442 }, { "epoch": 1.33, "learning_rate": 1.3787685e-05, "loss": 2.4652, "step": 443 }, { "epoch": 1.33, "learning_rate": 1.378698e-05, "loss": 2.4669, "step": 444 }, { "epoch": 1.33, "learning_rate": 1.3786275e-05, "loss": 2.4677, "step": 445 }, { "epoch": 1.34, "learning_rate": 1.378557e-05, "loss": 2.4666, "step": 446 }, { "epoch": 1.34, "learning_rate": 1.3784865e-05, "loss": 2.469, "step": 447 }, { "epoch": 1.34, "learning_rate": 1.3784160000000002e-05, "loss": 2.4665, "step": 448 }, { "epoch": 1.34, "learning_rate": 1.3783455000000001e-05, "loss": 2.463, "step": 449 }, { "epoch": 1.35, "learning_rate": 1.3782750000000001e-05, "loss": 2.4649, "step": 450 }, { "epoch": 1.35, "learning_rate": 1.3782045000000001e-05, "loss": 2.4683, "step": 451 }, { "epoch": 1.35, "learning_rate": 1.378134e-05, "loss": 2.4641, "step": 452 }, { "epoch": 1.36, "learning_rate": 1.3780635e-05, "loss": 2.4662, "step": 453 }, { "epoch": 1.36, "learning_rate": 1.377993e-05, "loss": 2.4617, "step": 454 }, { "epoch": 1.36, "learning_rate": 1.3779225e-05, "loss": 2.4604, "step": 455 }, { "epoch": 1.37, "learning_rate": 1.377852e-05, "loss": 2.4601, "step": 456 }, { "epoch": 1.37, "learning_rate": 1.3777815e-05, "loss": 2.4598, "step": 457 }, { "epoch": 1.37, "learning_rate": 1.377711e-05, "loss": 2.4602, "step": 458 }, { "epoch": 1.37, "learning_rate": 1.3776405e-05, "loss": 2.4589, "step": 459 }, { "epoch": 1.38, "learning_rate": 1.3775700000000001e-05, "loss": 2.4582, "step": 460 }, { "epoch": 1.38, "learning_rate": 1.3774995e-05, "loss": 2.4512, "step": 461 }, { "epoch": 1.38, "learning_rate": 1.377429e-05, "loss": 2.4536, "step": 462 }, { "epoch": 1.39, "learning_rate": 1.3773585e-05, "loss": 2.4576, "step": 463 }, { "epoch": 1.39, "learning_rate": 1.377288e-05, "loss": 2.4529, "step": 464 }, { "epoch": 1.39, "learning_rate": 1.3772175e-05, "loss": 2.4542, "step": 465 }, { "epoch": 1.4, "learning_rate": 1.3771470000000001e-05, "loss": 2.4535, "step": 466 }, { "epoch": 1.4, "learning_rate": 1.3770765000000001e-05, "loss": 2.4486, "step": 467 }, { "epoch": 1.4, "learning_rate": 1.3770060000000001e-05, "loss": 2.4491, "step": 468 }, { "epoch": 1.4, "learning_rate": 1.3769355000000001e-05, "loss": 2.4516, "step": 469 }, { "epoch": 1.41, "learning_rate": 1.376865e-05, "loss": 2.4498, "step": 470 }, { "epoch": 1.41, "learning_rate": 1.3767945e-05, "loss": 2.4487, "step": 471 }, { "epoch": 1.41, "learning_rate": 1.376724e-05, "loss": 2.4442, "step": 472 }, { "epoch": 1.42, "learning_rate": 1.3766535000000002e-05, "loss": 2.4496, "step": 473 }, { "epoch": 1.42, "learning_rate": 1.376583e-05, "loss": 2.4501, "step": 474 }, { "epoch": 1.42, "learning_rate": 1.3765125e-05, "loss": 2.4427, "step": 475 }, { "epoch": 1.43, "learning_rate": 1.376442e-05, "loss": 2.4463, "step": 476 }, { "epoch": 1.43, "learning_rate": 1.3763715e-05, "loss": 2.4426, "step": 477 }, { "epoch": 1.43, "learning_rate": 1.3763010000000001e-05, "loss": 2.4411, "step": 478 }, { "epoch": 1.43, "learning_rate": 1.3762305e-05, "loss": 2.4449, "step": 479 }, { "epoch": 1.44, "learning_rate": 1.37616e-05, "loss": 2.4428, "step": 480 }, { "epoch": 1.44, "learning_rate": 1.3760895e-05, "loss": 2.4395, "step": 481 }, { "epoch": 1.44, "learning_rate": 1.376019e-05, "loss": 2.4441, "step": 482 }, { "epoch": 1.45, "learning_rate": 1.3759485e-05, "loss": 2.4382, "step": 483 }, { "epoch": 1.45, "learning_rate": 1.375878e-05, "loss": 2.4403, "step": 484 }, { "epoch": 1.45, "learning_rate": 1.3758075000000001e-05, "loss": 2.4367, "step": 485 }, { "epoch": 1.46, "learning_rate": 1.3757370000000001e-05, "loss": 2.437, "step": 486 }, { "epoch": 1.46, "learning_rate": 1.3756665000000001e-05, "loss": 2.4393, "step": 487 }, { "epoch": 1.46, "learning_rate": 1.375596e-05, "loss": 2.435, "step": 488 }, { "epoch": 1.46, "learning_rate": 1.3755255e-05, "loss": 2.4335, "step": 489 }, { "epoch": 1.47, "learning_rate": 1.375455e-05, "loss": 2.4406, "step": 490 }, { "epoch": 1.47, "learning_rate": 1.3753845000000002e-05, "loss": 2.4342, "step": 491 }, { "epoch": 1.47, "learning_rate": 1.3753140000000002e-05, "loss": 2.4382, "step": 492 }, { "epoch": 1.48, "learning_rate": 1.3752435000000001e-05, "loss": 2.4326, "step": 493 }, { "epoch": 1.48, "learning_rate": 1.375173e-05, "loss": 2.4345, "step": 494 }, { "epoch": 1.48, "learning_rate": 1.3751025e-05, "loss": 2.4329, "step": 495 }, { "epoch": 1.49, "learning_rate": 1.375032e-05, "loss": 2.4311, "step": 496 }, { "epoch": 1.49, "learning_rate": 1.3749615e-05, "loss": 2.4285, "step": 497 }, { "epoch": 1.49, "learning_rate": 1.374891e-05, "loss": 2.4318, "step": 498 }, { "epoch": 1.49, "learning_rate": 1.3748205e-05, "loss": 2.4308, "step": 499 }, { "epoch": 1.5, "learning_rate": 1.37475e-05, "loss": 2.4304, "step": 500 }, { "epoch": 1.5, "eval_accuracy": 0.0024905620805369126, "eval_loss": 2.2562174797058105, "eval_runtime": 29.675, "eval_samples_per_second": 10.042, "eval_steps_per_second": 0.64, "step": 500 }, { "epoch": 1.5, "learning_rate": 1.3746795e-05, "loss": 2.4269, "step": 501 }, { "epoch": 1.5, "learning_rate": 1.374609e-05, "loss": 2.4234, "step": 502 }, { "epoch": 1.51, "learning_rate": 1.3745385000000001e-05, "loss": 2.4268, "step": 503 }, { "epoch": 1.51, "learning_rate": 1.3744680000000001e-05, "loss": 2.427, "step": 504 }, { "epoch": 1.51, "learning_rate": 1.3743975e-05, "loss": 2.4247, "step": 505 }, { "epoch": 1.52, "learning_rate": 1.374327e-05, "loss": 2.4236, "step": 506 }, { "epoch": 1.52, "learning_rate": 1.3742565e-05, "loss": 2.4264, "step": 507 }, { "epoch": 1.52, "learning_rate": 1.374186e-05, "loss": 2.4248, "step": 508 }, { "epoch": 1.52, "learning_rate": 1.3741155e-05, "loss": 2.4239, "step": 509 }, { "epoch": 1.53, "learning_rate": 1.3740450000000002e-05, "loss": 2.4253, "step": 510 }, { "epoch": 1.53, "learning_rate": 1.3739745000000001e-05, "loss": 2.4205, "step": 511 }, { "epoch": 1.53, "learning_rate": 1.3739040000000001e-05, "loss": 2.4188, "step": 512 }, { "epoch": 1.54, "learning_rate": 1.3738335000000001e-05, "loss": 2.4149, "step": 513 }, { "epoch": 1.54, "learning_rate": 1.373763e-05, "loss": 2.4146, "step": 514 }, { "epoch": 1.54, "learning_rate": 1.3736925e-05, "loss": 2.414, "step": 515 }, { "epoch": 1.55, "learning_rate": 1.373622e-05, "loss": 2.4188, "step": 516 }, { "epoch": 1.55, "learning_rate": 1.3735515e-05, "loss": 2.4164, "step": 517 }, { "epoch": 1.55, "learning_rate": 1.373481e-05, "loss": 2.4181, "step": 518 }, { "epoch": 1.55, "learning_rate": 1.3734105e-05, "loss": 2.4169, "step": 519 }, { "epoch": 1.56, "learning_rate": 1.37334e-05, "loss": 2.4139, "step": 520 }, { "epoch": 1.56, "learning_rate": 1.3732695e-05, "loss": 2.4151, "step": 521 }, { "epoch": 1.56, "learning_rate": 1.3731990000000001e-05, "loss": 2.4144, "step": 522 }, { "epoch": 1.57, "learning_rate": 1.3731285e-05, "loss": 2.413, "step": 523 }, { "epoch": 1.57, "learning_rate": 1.373058e-05, "loss": 2.4125, "step": 524 }, { "epoch": 1.57, "learning_rate": 1.3729875e-05, "loss": 2.4145, "step": 525 }, { "epoch": 1.58, "learning_rate": 1.372917e-05, "loss": 2.41, "step": 526 }, { "epoch": 1.58, "learning_rate": 1.3728465e-05, "loss": 2.4106, "step": 527 }, { "epoch": 1.58, "learning_rate": 1.3727760000000002e-05, "loss": 2.4082, "step": 528 }, { "epoch": 1.58, "learning_rate": 1.3727055000000001e-05, "loss": 2.4055, "step": 529 }, { "epoch": 1.59, "learning_rate": 1.3726350000000001e-05, "loss": 2.4068, "step": 530 }, { "epoch": 1.59, "learning_rate": 1.3725645000000001e-05, "loss": 2.4092, "step": 531 }, { "epoch": 1.59, "learning_rate": 1.372494e-05, "loss": 2.4058, "step": 532 }, { "epoch": 1.6, "learning_rate": 1.3724235e-05, "loss": 2.4051, "step": 533 }, { "epoch": 1.6, "learning_rate": 1.3723530000000002e-05, "loss": 2.4061, "step": 534 }, { "epoch": 1.6, "learning_rate": 1.3722825e-05, "loss": 2.4096, "step": 535 }, { "epoch": 1.61, "learning_rate": 1.372212e-05, "loss": 2.4022, "step": 536 }, { "epoch": 1.61, "learning_rate": 1.3721415e-05, "loss": 2.4057, "step": 537 }, { "epoch": 1.61, "learning_rate": 1.372071e-05, "loss": 2.4001, "step": 538 }, { "epoch": 1.61, "learning_rate": 1.3720005e-05, "loss": 2.398, "step": 539 }, { "epoch": 1.62, "learning_rate": 1.3719300000000001e-05, "loss": 2.4043, "step": 540 }, { "epoch": 1.62, "learning_rate": 1.3718595e-05, "loss": 2.4035, "step": 541 }, { "epoch": 1.62, "learning_rate": 1.371789e-05, "loss": 2.3986, "step": 542 }, { "epoch": 1.63, "learning_rate": 1.3717185e-05, "loss": 2.3977, "step": 543 }, { "epoch": 1.63, "learning_rate": 1.371648e-05, "loss": 2.3995, "step": 544 }, { "epoch": 1.63, "learning_rate": 1.3715775e-05, "loss": 2.397, "step": 545 }, { "epoch": 1.64, "learning_rate": 1.3715070000000001e-05, "loss": 2.395, "step": 546 }, { "epoch": 1.64, "learning_rate": 1.3714365000000001e-05, "loss": 2.3952, "step": 547 }, { "epoch": 1.64, "learning_rate": 1.3713660000000001e-05, "loss": 2.3951, "step": 548 }, { "epoch": 1.64, "learning_rate": 1.3712955000000001e-05, "loss": 2.3995, "step": 549 }, { "epoch": 1.65, "learning_rate": 1.371225e-05, "loss": 2.3954, "step": 550 }, { "epoch": 1.65, "learning_rate": 1.3711545e-05, "loss": 2.3945, "step": 551 }, { "epoch": 1.65, "learning_rate": 1.371084e-05, "loss": 2.39, "step": 552 }, { "epoch": 1.66, "learning_rate": 1.3710135000000002e-05, "loss": 2.394, "step": 553 }, { "epoch": 1.66, "learning_rate": 1.3709430000000002e-05, "loss": 2.3926, "step": 554 }, { "epoch": 1.66, "learning_rate": 1.3708725e-05, "loss": 2.3947, "step": 555 }, { "epoch": 1.66, "learning_rate": 1.370802e-05, "loss": 2.3915, "step": 556 }, { "epoch": 1.67, "learning_rate": 1.3707315e-05, "loss": 2.3904, "step": 557 }, { "epoch": 1.67, "learning_rate": 1.370661e-05, "loss": 2.3888, "step": 558 }, { "epoch": 1.67, "learning_rate": 1.3705905e-05, "loss": 2.39, "step": 559 }, { "epoch": 1.68, "learning_rate": 1.37052e-05, "loss": 2.3905, "step": 560 }, { "epoch": 1.68, "learning_rate": 1.3704495e-05, "loss": 2.3853, "step": 561 }, { "epoch": 1.68, "learning_rate": 1.370379e-05, "loss": 2.3879, "step": 562 }, { "epoch": 1.69, "learning_rate": 1.3703085e-05, "loss": 2.3856, "step": 563 }, { "epoch": 1.69, "learning_rate": 1.370238e-05, "loss": 2.3843, "step": 564 }, { "epoch": 1.69, "learning_rate": 1.3701675000000001e-05, "loss": 2.3835, "step": 565 }, { "epoch": 1.69, "learning_rate": 1.3700970000000001e-05, "loss": 2.3844, "step": 566 }, { "epoch": 1.7, "learning_rate": 1.3700265000000001e-05, "loss": 2.3822, "step": 567 }, { "epoch": 1.7, "learning_rate": 1.369956e-05, "loss": 2.3816, "step": 568 }, { "epoch": 1.7, "learning_rate": 1.3698855e-05, "loss": 2.3811, "step": 569 }, { "epoch": 1.71, "learning_rate": 1.369815e-05, "loss": 2.3809, "step": 570 }, { "epoch": 1.71, "learning_rate": 1.3697445000000002e-05, "loss": 2.3803, "step": 571 }, { "epoch": 1.71, "learning_rate": 1.3696740000000002e-05, "loss": 2.3781, "step": 572 }, { "epoch": 1.72, "learning_rate": 1.3696035000000001e-05, "loss": 2.3798, "step": 573 }, { "epoch": 1.72, "learning_rate": 1.3695330000000001e-05, "loss": 2.378, "step": 574 }, { "epoch": 1.72, "learning_rate": 1.3694625e-05, "loss": 2.3789, "step": 575 }, { "epoch": 1.72, "learning_rate": 1.369392e-05, "loss": 2.3782, "step": 576 }, { "epoch": 1.73, "learning_rate": 1.3693215e-05, "loss": 2.3763, "step": 577 }, { "epoch": 1.73, "learning_rate": 1.369251e-05, "loss": 2.3776, "step": 578 }, { "epoch": 1.73, "learning_rate": 1.3691805e-05, "loss": 2.373, "step": 579 }, { "epoch": 1.74, "learning_rate": 1.36911e-05, "loss": 2.3732, "step": 580 }, { "epoch": 1.74, "learning_rate": 1.3690395e-05, "loss": 2.3735, "step": 581 }, { "epoch": 1.74, "learning_rate": 1.368969e-05, "loss": 2.3739, "step": 582 }, { "epoch": 1.75, "learning_rate": 1.3688985000000001e-05, "loss": 2.3756, "step": 583 }, { "epoch": 1.75, "learning_rate": 1.3688280000000001e-05, "loss": 2.3727, "step": 584 }, { "epoch": 1.75, "learning_rate": 1.3687575e-05, "loss": 2.3713, "step": 585 }, { "epoch": 1.75, "learning_rate": 1.368687e-05, "loss": 2.3704, "step": 586 }, { "epoch": 1.76, "learning_rate": 1.3686165e-05, "loss": 2.3722, "step": 587 }, { "epoch": 1.76, "learning_rate": 1.368546e-05, "loss": 2.3651, "step": 588 }, { "epoch": 1.76, "learning_rate": 1.3684755e-05, "loss": 2.3736, "step": 589 }, { "epoch": 1.77, "learning_rate": 1.3684050000000002e-05, "loss": 2.3715, "step": 590 }, { "epoch": 1.77, "learning_rate": 1.3683345000000001e-05, "loss": 2.3674, "step": 591 }, { "epoch": 1.77, "learning_rate": 1.3682640000000001e-05, "loss": 2.3684, "step": 592 }, { "epoch": 1.78, "learning_rate": 1.3681935000000001e-05, "loss": 2.3664, "step": 593 }, { "epoch": 1.78, "learning_rate": 1.368123e-05, "loss": 2.3692, "step": 594 }, { "epoch": 1.78, "learning_rate": 1.3680524999999999e-05, "loss": 2.3655, "step": 595 }, { "epoch": 1.78, "learning_rate": 1.367982e-05, "loss": 2.3641, "step": 596 }, { "epoch": 1.79, "learning_rate": 1.3679115e-05, "loss": 2.3629, "step": 597 }, { "epoch": 1.79, "learning_rate": 1.367841e-05, "loss": 2.3611, "step": 598 }, { "epoch": 1.79, "learning_rate": 1.3677705e-05, "loss": 2.3621, "step": 599 }, { "epoch": 1.8, "learning_rate": 1.3677e-05, "loss": 2.3609, "step": 600 }, { "epoch": 1.8, "eval_accuracy": 0.001743393456375839, "eval_loss": 2.2031397819519043, "eval_runtime": 28.9856, "eval_samples_per_second": 10.281, "eval_steps_per_second": 0.655, "step": 600 }, { "epoch": 1.8, "learning_rate": 1.3676295e-05, "loss": 2.3616, "step": 601 }, { "epoch": 1.8, "learning_rate": 1.3675590000000001e-05, "loss": 2.3643, "step": 602 }, { "epoch": 1.81, "learning_rate": 1.3674885e-05, "loss": 2.3584, "step": 603 }, { "epoch": 1.81, "learning_rate": 1.367418e-05, "loss": 2.3563, "step": 604 }, { "epoch": 1.81, "learning_rate": 1.3673475e-05, "loss": 2.36, "step": 605 }, { "epoch": 1.81, "learning_rate": 1.367277e-05, "loss": 2.3584, "step": 606 }, { "epoch": 1.82, "learning_rate": 1.3672065e-05, "loss": 2.3584, "step": 607 }, { "epoch": 1.82, "learning_rate": 1.3671360000000002e-05, "loss": 2.3554, "step": 608 }, { "epoch": 1.82, "learning_rate": 1.3670655000000001e-05, "loss": 2.3559, "step": 609 }, { "epoch": 1.83, "learning_rate": 1.3669950000000001e-05, "loss": 2.3542, "step": 610 }, { "epoch": 1.83, "learning_rate": 1.3669245000000001e-05, "loss": 2.3518, "step": 611 }, { "epoch": 1.83, "learning_rate": 1.366854e-05, "loss": 2.3574, "step": 612 }, { "epoch": 1.84, "learning_rate": 1.3667835e-05, "loss": 2.3535, "step": 613 }, { "epoch": 1.84, "learning_rate": 1.366713e-05, "loss": 2.3571, "step": 614 }, { "epoch": 1.84, "learning_rate": 1.3666425e-05, "loss": 2.3518, "step": 615 }, { "epoch": 1.84, "learning_rate": 1.366572e-05, "loss": 2.352, "step": 616 }, { "epoch": 1.85, "learning_rate": 1.3665015e-05, "loss": 2.3523, "step": 617 }, { "epoch": 1.85, "learning_rate": 1.366431e-05, "loss": 2.3475, "step": 618 }, { "epoch": 1.85, "learning_rate": 1.3663605e-05, "loss": 2.352, "step": 619 }, { "epoch": 1.86, "learning_rate": 1.3662900000000001e-05, "loss": 2.3494, "step": 620 }, { "epoch": 1.86, "learning_rate": 1.3662195e-05, "loss": 2.3477, "step": 621 }, { "epoch": 1.86, "learning_rate": 1.366149e-05, "loss": 2.3473, "step": 622 }, { "epoch": 1.87, "learning_rate": 1.3660785e-05, "loss": 2.3454, "step": 623 }, { "epoch": 1.87, "learning_rate": 1.366008e-05, "loss": 2.3478, "step": 624 }, { "epoch": 1.87, "learning_rate": 1.3659375e-05, "loss": 2.3471, "step": 625 }, { "epoch": 1.87, "learning_rate": 1.365867e-05, "loss": 2.3452, "step": 626 }, { "epoch": 1.88, "learning_rate": 1.3657965000000001e-05, "loss": 2.3457, "step": 627 }, { "epoch": 1.88, "learning_rate": 1.3657260000000001e-05, "loss": 2.3466, "step": 628 }, { "epoch": 1.88, "learning_rate": 1.3656555000000001e-05, "loss": 2.3474, "step": 629 }, { "epoch": 1.89, "learning_rate": 1.365585e-05, "loss": 2.3438, "step": 630 }, { "epoch": 1.89, "learning_rate": 1.3655145e-05, "loss": 2.3393, "step": 631 }, { "epoch": 1.89, "learning_rate": 1.365444e-05, "loss": 2.3443, "step": 632 }, { "epoch": 1.9, "learning_rate": 1.3653735000000002e-05, "loss": 2.3386, "step": 633 }, { "epoch": 1.9, "learning_rate": 1.3653030000000002e-05, "loss": 2.3392, "step": 634 }, { "epoch": 1.9, "learning_rate": 1.3652325000000001e-05, "loss": 2.3413, "step": 635 }, { "epoch": 1.9, "learning_rate": 1.365162e-05, "loss": 2.3397, "step": 636 }, { "epoch": 1.91, "learning_rate": 1.3650915e-05, "loss": 2.3381, "step": 637 }, { "epoch": 1.91, "learning_rate": 1.365021e-05, "loss": 2.3402, "step": 638 }, { "epoch": 1.91, "learning_rate": 1.3649505e-05, "loss": 2.3404, "step": 639 }, { "epoch": 1.92, "learning_rate": 1.36488e-05, "loss": 2.3378, "step": 640 }, { "epoch": 1.92, "learning_rate": 1.3648095e-05, "loss": 2.3353, "step": 641 }, { "epoch": 1.92, "learning_rate": 1.364739e-05, "loss": 2.3346, "step": 642 }, { "epoch": 1.93, "learning_rate": 1.3646685e-05, "loss": 2.3397, "step": 643 }, { "epoch": 1.93, "learning_rate": 1.364598e-05, "loss": 2.3349, "step": 644 }, { "epoch": 1.93, "learning_rate": 1.3645275000000001e-05, "loss": 2.3332, "step": 645 }, { "epoch": 1.93, "learning_rate": 1.3644570000000001e-05, "loss": 2.3325, "step": 646 }, { "epoch": 1.94, "learning_rate": 1.3643865000000001e-05, "loss": 2.3295, "step": 647 }, { "epoch": 1.94, "learning_rate": 1.364316e-05, "loss": 2.3308, "step": 648 }, { "epoch": 1.94, "learning_rate": 1.3642455e-05, "loss": 2.3355, "step": 649 }, { "epoch": 1.95, "learning_rate": 1.364175e-05, "loss": 2.3315, "step": 650 }, { "epoch": 1.95, "learning_rate": 1.3641045000000002e-05, "loss": 2.334, "step": 651 }, { "epoch": 1.95, "learning_rate": 1.3640340000000002e-05, "loss": 2.3325, "step": 652 }, { "epoch": 1.96, "learning_rate": 1.3639635000000001e-05, "loss": 2.3307, "step": 653 }, { "epoch": 1.96, "learning_rate": 1.3638930000000001e-05, "loss": 2.3301, "step": 654 }, { "epoch": 1.96, "learning_rate": 1.3638225000000001e-05, "loss": 2.3253, "step": 655 }, { "epoch": 1.96, "learning_rate": 1.363752e-05, "loss": 2.3259, "step": 656 }, { "epoch": 1.97, "learning_rate": 1.3636815e-05, "loss": 2.3294, "step": 657 }, { "epoch": 1.97, "learning_rate": 1.363611e-05, "loss": 2.3279, "step": 658 }, { "epoch": 1.97, "learning_rate": 1.3635405e-05, "loss": 2.3255, "step": 659 }, { "epoch": 1.98, "learning_rate": 1.36347e-05, "loss": 2.3286, "step": 660 }, { "epoch": 1.98, "learning_rate": 1.3633995e-05, "loss": 2.3249, "step": 661 }, { "epoch": 1.98, "learning_rate": 1.363329e-05, "loss": 2.3327, "step": 662 }, { "epoch": 1.99, "learning_rate": 1.3632585e-05, "loss": 2.324, "step": 663 }, { "epoch": 1.99, "learning_rate": 1.3631880000000001e-05, "loss": 2.3259, "step": 664 }, { "epoch": 1.99, "learning_rate": 1.3631175e-05, "loss": 2.3267, "step": 665 }, { "epoch": 1.99, "learning_rate": 1.363047e-05, "loss": 2.3213, "step": 666 }, { "epoch": 2.0, "learning_rate": 1.3629765e-05, "loss": 2.3203, "step": 667 }, { "epoch": 2.0, "learning_rate": 1.362906e-05, "loss": 2.3226, "step": 668 }, { "epoch": 2.0, "learning_rate": 1.3628355e-05, "loss": 2.322, "step": 669 }, { "epoch": 2.01, "learning_rate": 1.3627650000000002e-05, "loss": 2.3189, "step": 670 }, { "epoch": 2.01, "learning_rate": 1.3626945000000001e-05, "loss": 2.3158, "step": 671 }, { "epoch": 2.01, "learning_rate": 1.3626240000000001e-05, "loss": 2.3139, "step": 672 }, { "epoch": 2.02, "learning_rate": 1.3625535000000001e-05, "loss": 2.3161, "step": 673 }, { "epoch": 2.02, "learning_rate": 1.362483e-05, "loss": 2.3208, "step": 674 }, { "epoch": 2.02, "learning_rate": 1.3624125e-05, "loss": 2.3186, "step": 675 }, { "epoch": 2.02, "learning_rate": 1.362342e-05, "loss": 2.3169, "step": 676 }, { "epoch": 2.03, "learning_rate": 1.3622715e-05, "loss": 2.3147, "step": 677 }, { "epoch": 2.03, "learning_rate": 1.362201e-05, "loss": 2.3135, "step": 678 }, { "epoch": 2.03, "learning_rate": 1.3621305e-05, "loss": 2.3128, "step": 679 }, { "epoch": 2.04, "learning_rate": 1.36206e-05, "loss": 2.3165, "step": 680 }, { "epoch": 2.04, "learning_rate": 1.3619895e-05, "loss": 2.3157, "step": 681 }, { "epoch": 2.04, "learning_rate": 1.3619190000000001e-05, "loss": 2.3113, "step": 682 }, { "epoch": 2.05, "learning_rate": 1.3618485e-05, "loss": 2.3172, "step": 683 }, { "epoch": 2.05, "learning_rate": 1.361778e-05, "loss": 2.3145, "step": 684 }, { "epoch": 2.05, "learning_rate": 1.3617075e-05, "loss": 2.3141, "step": 685 }, { "epoch": 2.05, "learning_rate": 1.361637e-05, "loss": 2.3153, "step": 686 }, { "epoch": 2.06, "learning_rate": 1.3615665e-05, "loss": 2.3123, "step": 687 }, { "epoch": 2.06, "learning_rate": 1.3614960000000002e-05, "loss": 2.3071, "step": 688 }, { "epoch": 2.06, "learning_rate": 1.3614255000000001e-05, "loss": 2.3087, "step": 689 }, { "epoch": 2.07, "learning_rate": 1.3613550000000001e-05, "loss": 2.3076, "step": 690 }, { "epoch": 2.07, "learning_rate": 1.3612845000000001e-05, "loss": 2.305, "step": 691 }, { "epoch": 2.07, "learning_rate": 1.361214e-05, "loss": 2.3081, "step": 692 }, { "epoch": 2.08, "learning_rate": 1.3611435e-05, "loss": 2.3042, "step": 693 }, { "epoch": 2.08, "learning_rate": 1.361073e-05, "loss": 2.3103, "step": 694 }, { "epoch": 2.08, "learning_rate": 1.3610025000000002e-05, "loss": 2.3044, "step": 695 }, { "epoch": 2.08, "learning_rate": 1.360932e-05, "loss": 2.3062, "step": 696 }, { "epoch": 2.09, "learning_rate": 1.3608615e-05, "loss": 2.3059, "step": 697 }, { "epoch": 2.09, "learning_rate": 1.360791e-05, "loss": 2.3049, "step": 698 }, { "epoch": 2.09, "learning_rate": 1.3607205e-05, "loss": 2.3006, "step": 699 }, { "epoch": 2.1, "learning_rate": 1.36065e-05, "loss": 2.3016, "step": 700 }, { "epoch": 2.1, "eval_accuracy": 0.0011141988255033556, "eval_loss": 2.153825521469116, "eval_runtime": 31.6811, "eval_samples_per_second": 9.406, "eval_steps_per_second": 0.6, "step": 700 }, { "epoch": 2.1, "learning_rate": 1.3605795e-05, "loss": 2.3034, "step": 701 }, { "epoch": 2.1, "learning_rate": 1.360509e-05, "loss": 2.303, "step": 702 }, { "epoch": 2.11, "learning_rate": 1.3604385e-05, "loss": 2.3006, "step": 703 }, { "epoch": 2.11, "learning_rate": 1.360368e-05, "loss": 2.3043, "step": 704 }, { "epoch": 2.11, "learning_rate": 1.3602975e-05, "loss": 2.3016, "step": 705 }, { "epoch": 2.11, "learning_rate": 1.360227e-05, "loss": 2.3004, "step": 706 }, { "epoch": 2.12, "learning_rate": 1.3601565000000001e-05, "loss": 2.3, "step": 707 }, { "epoch": 2.12, "learning_rate": 1.3600860000000001e-05, "loss": 2.2944, "step": 708 }, { "epoch": 2.12, "learning_rate": 1.3600155000000001e-05, "loss": 2.2992, "step": 709 }, { "epoch": 2.13, "learning_rate": 1.359945e-05, "loss": 2.2984, "step": 710 }, { "epoch": 2.13, "learning_rate": 1.3598745e-05, "loss": 2.2934, "step": 711 }, { "epoch": 2.13, "learning_rate": 1.359804e-05, "loss": 2.2936, "step": 712 }, { "epoch": 2.14, "learning_rate": 1.3597335000000002e-05, "loss": 2.3006, "step": 713 }, { "epoch": 2.14, "learning_rate": 1.3596630000000002e-05, "loss": 2.2955, "step": 714 }, { "epoch": 2.14, "learning_rate": 1.3595925000000001e-05, "loss": 2.295, "step": 715 }, { "epoch": 2.14, "learning_rate": 1.359522e-05, "loss": 2.2949, "step": 716 }, { "epoch": 2.15, "learning_rate": 1.3594515e-05, "loss": 2.2908, "step": 717 }, { "epoch": 2.15, "learning_rate": 1.359381e-05, "loss": 2.2915, "step": 718 }, { "epoch": 2.15, "learning_rate": 1.3593105e-05, "loss": 2.2963, "step": 719 }, { "epoch": 2.16, "learning_rate": 1.35924e-05, "loss": 2.2918, "step": 720 }, { "epoch": 2.16, "learning_rate": 1.3591695e-05, "loss": 2.2962, "step": 721 }, { "epoch": 2.16, "learning_rate": 1.359099e-05, "loss": 2.2924, "step": 722 }, { "epoch": 2.17, "learning_rate": 1.3590285e-05, "loss": 2.2918, "step": 723 }, { "epoch": 2.17, "learning_rate": 1.358958e-05, "loss": 2.2875, "step": 724 }, { "epoch": 2.17, "learning_rate": 1.3588875000000001e-05, "loss": 2.2917, "step": 725 }, { "epoch": 2.17, "learning_rate": 1.3588170000000001e-05, "loss": 2.2896, "step": 726 }, { "epoch": 2.18, "learning_rate": 1.3587465000000001e-05, "loss": 2.2891, "step": 727 }, { "epoch": 2.18, "learning_rate": 1.358676e-05, "loss": 2.2908, "step": 728 }, { "epoch": 2.18, "learning_rate": 1.3586055e-05, "loss": 2.2888, "step": 729 }, { "epoch": 2.19, "learning_rate": 1.358535e-05, "loss": 2.2861, "step": 730 }, { "epoch": 2.19, "learning_rate": 1.3584645e-05, "loss": 2.2824, "step": 731 }, { "epoch": 2.19, "learning_rate": 1.3583940000000002e-05, "loss": 2.2845, "step": 732 }, { "epoch": 2.2, "learning_rate": 1.3583235000000001e-05, "loss": 2.2838, "step": 733 }, { "epoch": 2.2, "learning_rate": 1.3582530000000001e-05, "loss": 2.291, "step": 734 }, { "epoch": 2.2, "learning_rate": 1.3581825000000001e-05, "loss": 2.2837, "step": 735 }, { "epoch": 2.2, "learning_rate": 1.3581119999999999e-05, "loss": 2.2829, "step": 736 }, { "epoch": 2.21, "learning_rate": 1.3580415e-05, "loss": 2.2825, "step": 737 }, { "epoch": 2.21, "learning_rate": 1.357971e-05, "loss": 2.2871, "step": 738 }, { "epoch": 2.21, "learning_rate": 1.3579005e-05, "loss": 2.2818, "step": 739 }, { "epoch": 2.22, "learning_rate": 1.35783e-05, "loss": 2.2798, "step": 740 }, { "epoch": 2.22, "learning_rate": 1.3577595e-05, "loss": 2.2806, "step": 741 }, { "epoch": 2.22, "learning_rate": 1.357689e-05, "loss": 2.2837, "step": 742 }, { "epoch": 2.22, "learning_rate": 1.3576185e-05, "loss": 2.2765, "step": 743 }, { "epoch": 2.23, "learning_rate": 1.3575480000000001e-05, "loss": 2.2815, "step": 744 }, { "epoch": 2.23, "learning_rate": 1.3574775e-05, "loss": 2.2773, "step": 745 }, { "epoch": 2.23, "learning_rate": 1.357407e-05, "loss": 2.2796, "step": 746 }, { "epoch": 2.24, "learning_rate": 1.3573365e-05, "loss": 2.2773, "step": 747 }, { "epoch": 2.24, "learning_rate": 1.357266e-05, "loss": 2.2781, "step": 748 }, { "epoch": 2.24, "learning_rate": 1.3571955e-05, "loss": 2.2787, "step": 749 }, { "epoch": 2.25, "learning_rate": 1.3571250000000002e-05, "loss": 2.2791, "step": 750 }, { "epoch": 2.25, "learning_rate": 1.3570545000000001e-05, "loss": 2.2749, "step": 751 }, { "epoch": 2.25, "learning_rate": 1.3569840000000001e-05, "loss": 2.2752, "step": 752 }, { "epoch": 2.25, "learning_rate": 1.3569135000000001e-05, "loss": 2.2778, "step": 753 }, { "epoch": 2.26, "learning_rate": 1.356843e-05, "loss": 2.2746, "step": 754 }, { "epoch": 2.26, "learning_rate": 1.3567725e-05, "loss": 2.2717, "step": 755 }, { "epoch": 2.26, "learning_rate": 1.3567020000000002e-05, "loss": 2.2761, "step": 756 }, { "epoch": 2.27, "learning_rate": 1.3566315e-05, "loss": 2.2705, "step": 757 }, { "epoch": 2.27, "learning_rate": 1.356561e-05, "loss": 2.2722, "step": 758 }, { "epoch": 2.27, "learning_rate": 1.3564905e-05, "loss": 2.2705, "step": 759 }, { "epoch": 2.28, "learning_rate": 1.35642e-05, "loss": 2.2718, "step": 760 }, { "epoch": 2.28, "learning_rate": 1.3563495e-05, "loss": 2.2731, "step": 761 }, { "epoch": 2.28, "learning_rate": 1.3562790000000001e-05, "loss": 2.2668, "step": 762 }, { "epoch": 2.28, "learning_rate": 1.3562085e-05, "loss": 2.2704, "step": 763 }, { "epoch": 2.29, "learning_rate": 1.356138e-05, "loss": 2.2707, "step": 764 }, { "epoch": 2.29, "learning_rate": 1.3560675e-05, "loss": 2.268, "step": 765 }, { "epoch": 2.29, "learning_rate": 1.355997e-05, "loss": 2.2648, "step": 766 }, { "epoch": 2.3, "learning_rate": 1.3559265e-05, "loss": 2.2669, "step": 767 }, { "epoch": 2.3, "learning_rate": 1.355856e-05, "loss": 2.2648, "step": 768 }, { "epoch": 2.3, "learning_rate": 1.3557855000000001e-05, "loss": 2.2659, "step": 769 }, { "epoch": 2.31, "learning_rate": 1.3557150000000001e-05, "loss": 2.2635, "step": 770 }, { "epoch": 2.31, "learning_rate": 1.3556445000000001e-05, "loss": 2.2663, "step": 771 }, { "epoch": 2.31, "learning_rate": 1.355574e-05, "loss": 2.2644, "step": 772 }, { "epoch": 2.31, "learning_rate": 1.3555035e-05, "loss": 2.2613, "step": 773 }, { "epoch": 2.32, "learning_rate": 1.355433e-05, "loss": 2.2622, "step": 774 }, { "epoch": 2.32, "learning_rate": 1.3553625000000002e-05, "loss": 2.2637, "step": 775 }, { "epoch": 2.32, "learning_rate": 1.3552920000000002e-05, "loss": 2.2636, "step": 776 }, { "epoch": 2.33, "learning_rate": 1.3552215e-05, "loss": 2.2638, "step": 777 }, { "epoch": 2.33, "learning_rate": 1.355151e-05, "loss": 2.2605, "step": 778 }, { "epoch": 2.33, "learning_rate": 1.3550805e-05, "loss": 2.2578, "step": 779 }, { "epoch": 2.34, "learning_rate": 1.35501e-05, "loss": 2.263, "step": 780 }, { "epoch": 2.34, "learning_rate": 1.3549395e-05, "loss": 2.261, "step": 781 }, { "epoch": 2.34, "learning_rate": 1.354869e-05, "loss": 2.2605, "step": 782 }, { "epoch": 2.34, "learning_rate": 1.3547985e-05, "loss": 2.2606, "step": 783 }, { "epoch": 2.35, "learning_rate": 1.354728e-05, "loss": 2.2574, "step": 784 }, { "epoch": 2.35, "learning_rate": 1.3546575e-05, "loss": 2.258, "step": 785 }, { "epoch": 2.35, "learning_rate": 1.354587e-05, "loss": 2.2592, "step": 786 }, { "epoch": 2.36, "learning_rate": 1.3545165000000001e-05, "loss": 2.2572, "step": 787 }, { "epoch": 2.36, "learning_rate": 1.3544460000000001e-05, "loss": 2.2539, "step": 788 }, { "epoch": 2.36, "learning_rate": 1.3543755000000001e-05, "loss": 2.254, "step": 789 }, { "epoch": 2.37, "learning_rate": 1.354305e-05, "loss": 2.2553, "step": 790 }, { "epoch": 2.37, "learning_rate": 1.3542345e-05, "loss": 2.2593, "step": 791 }, { "epoch": 2.37, "learning_rate": 1.354164e-05, "loss": 2.2536, "step": 792 }, { "epoch": 2.37, "learning_rate": 1.3540935000000002e-05, "loss": 2.2534, "step": 793 }, { "epoch": 2.38, "learning_rate": 1.3540230000000002e-05, "loss": 2.2515, "step": 794 }, { "epoch": 2.38, "learning_rate": 1.3539525000000001e-05, "loss": 2.2541, "step": 795 }, { "epoch": 2.38, "learning_rate": 1.3538820000000001e-05, "loss": 2.2512, "step": 796 }, { "epoch": 2.39, "learning_rate": 1.3538115e-05, "loss": 2.2523, "step": 797 }, { "epoch": 2.39, "learning_rate": 1.353741e-05, "loss": 2.2506, "step": 798 }, { "epoch": 2.39, "learning_rate": 1.3536705e-05, "loss": 2.2541, "step": 799 }, { "epoch": 2.4, "learning_rate": 1.3536e-05, "loss": 2.2483, "step": 800 }, { "epoch": 2.4, "eval_accuracy": 0.0010158871644295301, "eval_loss": 2.1085779666900635, "eval_runtime": 30.8027, "eval_samples_per_second": 9.674, "eval_steps_per_second": 0.617, "step": 800 }, { "epoch": 2.4, "learning_rate": 1.3535295e-05, "loss": 2.2459, "step": 801 }, { "epoch": 2.4, "learning_rate": 1.353459e-05, "loss": 2.2505, "step": 802 }, { "epoch": 2.4, "learning_rate": 1.3533885e-05, "loss": 2.2479, "step": 803 }, { "epoch": 2.41, "learning_rate": 1.353318e-05, "loss": 2.2445, "step": 804 }, { "epoch": 2.41, "learning_rate": 1.3532475e-05, "loss": 2.2459, "step": 805 }, { "epoch": 2.41, "learning_rate": 1.3531770000000001e-05, "loss": 2.2436, "step": 806 }, { "epoch": 2.42, "learning_rate": 1.3531065000000001e-05, "loss": 2.2475, "step": 807 }, { "epoch": 2.42, "learning_rate": 1.353036e-05, "loss": 2.2426, "step": 808 }, { "epoch": 2.42, "learning_rate": 1.3529655e-05, "loss": 2.2424, "step": 809 }, { "epoch": 2.43, "learning_rate": 1.352895e-05, "loss": 2.2437, "step": 810 }, { "epoch": 2.43, "learning_rate": 1.3528245e-05, "loss": 2.246, "step": 811 }, { "epoch": 2.43, "learning_rate": 1.3527540000000002e-05, "loss": 2.2496, "step": 812 }, { "epoch": 2.43, "learning_rate": 1.3526835000000001e-05, "loss": 2.2455, "step": 813 }, { "epoch": 2.44, "learning_rate": 1.3526130000000001e-05, "loss": 2.2465, "step": 814 }, { "epoch": 2.44, "learning_rate": 1.3525425000000001e-05, "loss": 2.2419, "step": 815 }, { "epoch": 2.44, "learning_rate": 1.352472e-05, "loss": 2.2445, "step": 816 }, { "epoch": 2.45, "learning_rate": 1.3524014999999999e-05, "loss": 2.2406, "step": 817 }, { "epoch": 2.45, "learning_rate": 1.352331e-05, "loss": 2.2413, "step": 818 }, { "epoch": 2.45, "learning_rate": 1.3522605e-05, "loss": 2.2387, "step": 819 }, { "epoch": 2.46, "learning_rate": 1.35219e-05, "loss": 2.2386, "step": 820 }, { "epoch": 2.46, "learning_rate": 1.3521195e-05, "loss": 2.2379, "step": 821 }, { "epoch": 2.46, "learning_rate": 1.352049e-05, "loss": 2.2376, "step": 822 }, { "epoch": 2.46, "learning_rate": 1.3519785e-05, "loss": 2.2351, "step": 823 }, { "epoch": 2.47, "learning_rate": 1.3519080000000001e-05, "loss": 2.2363, "step": 824 }, { "epoch": 2.47, "learning_rate": 1.3518375e-05, "loss": 2.2323, "step": 825 }, { "epoch": 2.47, "learning_rate": 1.351767e-05, "loss": 2.2326, "step": 826 }, { "epoch": 2.48, "learning_rate": 1.3516965e-05, "loss": 2.2358, "step": 827 }, { "epoch": 2.48, "learning_rate": 1.351626e-05, "loss": 2.2348, "step": 828 }, { "epoch": 2.48, "learning_rate": 1.3515555e-05, "loss": 2.2324, "step": 829 }, { "epoch": 2.49, "learning_rate": 1.3514850000000002e-05, "loss": 2.2365, "step": 830 }, { "epoch": 2.49, "learning_rate": 1.3514145000000001e-05, "loss": 2.2355, "step": 831 }, { "epoch": 2.49, "learning_rate": 1.3513440000000001e-05, "loss": 2.2342, "step": 832 }, { "epoch": 2.49, "learning_rate": 1.3512735000000001e-05, "loss": 2.235, "step": 833 }, { "epoch": 2.5, "learning_rate": 1.351203e-05, "loss": 2.2317, "step": 834 }, { "epoch": 2.5, "learning_rate": 1.3511325e-05, "loss": 2.2316, "step": 835 }, { "epoch": 2.5, "learning_rate": 1.351062e-05, "loss": 2.2336, "step": 836 }, { "epoch": 2.51, "learning_rate": 1.3509915e-05, "loss": 2.2328, "step": 837 }, { "epoch": 2.51, "learning_rate": 1.350921e-05, "loss": 2.2343, "step": 838 }, { "epoch": 2.51, "learning_rate": 1.3508505e-05, "loss": 2.231, "step": 839 }, { "epoch": 2.52, "learning_rate": 1.35078e-05, "loss": 2.2337, "step": 840 }, { "epoch": 2.52, "learning_rate": 1.3507095e-05, "loss": 2.2288, "step": 841 }, { "epoch": 2.52, "learning_rate": 1.3506390000000001e-05, "loss": 2.2278, "step": 842 }, { "epoch": 2.52, "learning_rate": 1.3505685e-05, "loss": 2.2299, "step": 843 }, { "epoch": 2.53, "learning_rate": 1.350498e-05, "loss": 2.2274, "step": 844 }, { "epoch": 2.53, "learning_rate": 1.3504275e-05, "loss": 2.2249, "step": 845 }, { "epoch": 2.53, "learning_rate": 1.350357e-05, "loss": 2.226, "step": 846 }, { "epoch": 2.54, "learning_rate": 1.3502865e-05, "loss": 2.2245, "step": 847 }, { "epoch": 2.54, "learning_rate": 1.350216e-05, "loss": 2.231, "step": 848 }, { "epoch": 2.54, "learning_rate": 1.3501455000000001e-05, "loss": 2.2244, "step": 849 }, { "epoch": 2.55, "learning_rate": 1.3500750000000001e-05, "loss": 2.226, "step": 850 }, { "epoch": 2.55, "learning_rate": 1.3500045000000001e-05, "loss": 2.225, "step": 851 }, { "epoch": 2.55, "learning_rate": 1.349934e-05, "loss": 2.2225, "step": 852 }, { "epoch": 2.55, "learning_rate": 1.3498635e-05, "loss": 2.2213, "step": 853 }, { "epoch": 2.56, "learning_rate": 1.349793e-05, "loss": 2.2207, "step": 854 }, { "epoch": 2.56, "learning_rate": 1.3497225000000002e-05, "loss": 2.2243, "step": 855 }, { "epoch": 2.56, "learning_rate": 1.3496520000000002e-05, "loss": 2.2244, "step": 856 }, { "epoch": 2.57, "learning_rate": 1.3495815e-05, "loss": 2.2195, "step": 857 }, { "epoch": 2.57, "learning_rate": 1.349511e-05, "loss": 2.2242, "step": 858 }, { "epoch": 2.57, "learning_rate": 1.3494405e-05, "loss": 2.2199, "step": 859 }, { "epoch": 2.58, "learning_rate": 1.34937e-05, "loss": 2.2215, "step": 860 }, { "epoch": 2.58, "learning_rate": 1.3492995e-05, "loss": 2.2216, "step": 861 }, { "epoch": 2.58, "learning_rate": 1.349229e-05, "loss": 2.2164, "step": 862 }, { "epoch": 2.58, "learning_rate": 1.3491585e-05, "loss": 2.2203, "step": 863 }, { "epoch": 2.59, "learning_rate": 1.349088e-05, "loss": 2.2167, "step": 864 }, { "epoch": 2.59, "learning_rate": 1.3490175e-05, "loss": 2.2143, "step": 865 }, { "epoch": 2.59, "learning_rate": 1.348947e-05, "loss": 2.2161, "step": 866 }, { "epoch": 2.6, "learning_rate": 1.3488765000000001e-05, "loss": 2.2132, "step": 867 }, { "epoch": 2.6, "learning_rate": 1.3488060000000001e-05, "loss": 2.216, "step": 868 }, { "epoch": 2.6, "learning_rate": 1.3487355000000001e-05, "loss": 2.216, "step": 869 }, { "epoch": 2.61, "learning_rate": 1.348665e-05, "loss": 2.2159, "step": 870 }, { "epoch": 2.61, "learning_rate": 1.3485945e-05, "loss": 2.2128, "step": 871 }, { "epoch": 2.61, "learning_rate": 1.348524e-05, "loss": 2.215, "step": 872 }, { "epoch": 2.61, "learning_rate": 1.3484535e-05, "loss": 2.215, "step": 873 }, { "epoch": 2.62, "learning_rate": 1.3483830000000002e-05, "loss": 2.213, "step": 874 }, { "epoch": 2.62, "learning_rate": 1.3483125000000001e-05, "loss": 2.2151, "step": 875 }, { "epoch": 2.62, "learning_rate": 1.3482420000000001e-05, "loss": 2.2142, "step": 876 }, { "epoch": 2.63, "learning_rate": 1.3481715000000001e-05, "loss": 2.2108, "step": 877 }, { "epoch": 2.63, "learning_rate": 1.348101e-05, "loss": 2.2119, "step": 878 }, { "epoch": 2.63, "learning_rate": 1.3480305e-05, "loss": 2.2142, "step": 879 }, { "epoch": 2.64, "learning_rate": 1.34796e-05, "loss": 2.2083, "step": 880 }, { "epoch": 2.64, "learning_rate": 1.3478895e-05, "loss": 2.2085, "step": 881 }, { "epoch": 2.64, "learning_rate": 1.347819e-05, "loss": 2.2095, "step": 882 }, { "epoch": 2.64, "learning_rate": 1.3477485e-05, "loss": 2.2127, "step": 883 }, { "epoch": 2.65, "learning_rate": 1.347678e-05, "loss": 2.2085, "step": 884 }, { "epoch": 2.65, "learning_rate": 1.3476075e-05, "loss": 2.2086, "step": 885 }, { "epoch": 2.65, "learning_rate": 1.3475370000000001e-05, "loss": 2.2102, "step": 886 }, { "epoch": 2.66, "learning_rate": 1.3474665000000001e-05, "loss": 2.2021, "step": 887 }, { "epoch": 2.66, "learning_rate": 1.347396e-05, "loss": 2.2049, "step": 888 }, { "epoch": 2.66, "learning_rate": 1.3473255e-05, "loss": 2.2052, "step": 889 }, { "epoch": 2.67, "learning_rate": 1.347255e-05, "loss": 2.2112, "step": 890 }, { "epoch": 2.67, "learning_rate": 1.3471845e-05, "loss": 2.2049, "step": 891 }, { "epoch": 2.67, "learning_rate": 1.3471140000000002e-05, "loss": 2.203, "step": 892 }, { "epoch": 2.67, "learning_rate": 1.3470435000000001e-05, "loss": 2.2066, "step": 893 }, { "epoch": 2.68, "learning_rate": 1.3469730000000001e-05, "loss": 2.2032, "step": 894 }, { "epoch": 2.68, "learning_rate": 1.3469025000000001e-05, "loss": 2.2051, "step": 895 }, { "epoch": 2.68, "learning_rate": 1.346832e-05, "loss": 2.2032, "step": 896 }, { "epoch": 2.69, "learning_rate": 1.3467615e-05, "loss": 2.2006, "step": 897 }, { "epoch": 2.69, "learning_rate": 1.346691e-05, "loss": 2.2001, "step": 898 }, { "epoch": 2.69, "learning_rate": 1.3466205e-05, "loss": 2.2, "step": 899 }, { "epoch": 2.7, "learning_rate": 1.34655e-05, "loss": 2.2009, "step": 900 }, { "epoch": 2.7, "eval_accuracy": 0.0007930473993288591, "eval_loss": 2.0654594898223877, "eval_runtime": 31.3594, "eval_samples_per_second": 9.503, "eval_steps_per_second": 0.606, "step": 900 }, { "epoch": 2.7, "learning_rate": 1.3464795e-05, "loss": 2.199, "step": 901 }, { "epoch": 2.7, "learning_rate": 1.346409e-05, "loss": 2.1994, "step": 902 }, { "epoch": 2.7, "learning_rate": 1.3463385e-05, "loss": 2.1972, "step": 903 }, { "epoch": 2.71, "learning_rate": 1.3462680000000001e-05, "loss": 2.1981, "step": 904 }, { "epoch": 2.71, "learning_rate": 1.3461975e-05, "loss": 2.1997, "step": 905 }, { "epoch": 2.71, "learning_rate": 1.346127e-05, "loss": 2.1998, "step": 906 }, { "epoch": 2.72, "learning_rate": 1.3460565e-05, "loss": 2.1983, "step": 907 }, { "epoch": 2.72, "learning_rate": 1.345986e-05, "loss": 2.2003, "step": 908 }, { "epoch": 2.72, "learning_rate": 1.3459155e-05, "loss": 2.1958, "step": 909 }, { "epoch": 2.73, "learning_rate": 1.3458450000000002e-05, "loss": 2.1987, "step": 910 }, { "epoch": 2.73, "learning_rate": 1.3457745000000001e-05, "loss": 2.1943, "step": 911 }, { "epoch": 2.73, "learning_rate": 1.3457040000000001e-05, "loss": 2.1955, "step": 912 }, { "epoch": 2.73, "learning_rate": 1.3456335000000001e-05, "loss": 2.1976, "step": 913 }, { "epoch": 2.74, "learning_rate": 1.345563e-05, "loss": 2.1953, "step": 914 }, { "epoch": 2.74, "learning_rate": 1.3454925e-05, "loss": 2.1963, "step": 915 }, { "epoch": 2.74, "learning_rate": 1.345422e-05, "loss": 2.1944, "step": 916 }, { "epoch": 2.75, "learning_rate": 1.3453515000000002e-05, "loss": 2.1934, "step": 917 }, { "epoch": 2.75, "learning_rate": 1.345281e-05, "loss": 2.1891, "step": 918 }, { "epoch": 2.75, "learning_rate": 1.3452105e-05, "loss": 2.1917, "step": 919 }, { "epoch": 2.76, "learning_rate": 1.34514e-05, "loss": 2.1911, "step": 920 }, { "epoch": 2.76, "learning_rate": 1.3450695e-05, "loss": 2.1907, "step": 921 }, { "epoch": 2.76, "learning_rate": 1.344999e-05, "loss": 2.1899, "step": 922 }, { "epoch": 2.76, "learning_rate": 1.3449285e-05, "loss": 2.1925, "step": 923 }, { "epoch": 2.77, "learning_rate": 1.344858e-05, "loss": 2.1905, "step": 924 }, { "epoch": 2.77, "learning_rate": 1.3447875e-05, "loss": 2.1925, "step": 925 }, { "epoch": 2.77, "learning_rate": 1.344717e-05, "loss": 2.1879, "step": 926 }, { "epoch": 2.78, "learning_rate": 1.3446465e-05, "loss": 2.184, "step": 927 }, { "epoch": 2.78, "learning_rate": 1.344576e-05, "loss": 2.1859, "step": 928 }, { "epoch": 2.78, "learning_rate": 1.3445055000000001e-05, "loss": 2.1845, "step": 929 }, { "epoch": 2.78, "learning_rate": 1.3444350000000001e-05, "loss": 2.1855, "step": 930 }, { "epoch": 2.79, "learning_rate": 1.3443645000000001e-05, "loss": 2.1883, "step": 931 }, { "epoch": 2.79, "learning_rate": 1.344294e-05, "loss": 2.1854, "step": 932 }, { "epoch": 2.79, "learning_rate": 1.3442235e-05, "loss": 2.1842, "step": 933 }, { "epoch": 2.8, "learning_rate": 1.344153e-05, "loss": 2.1818, "step": 934 }, { "epoch": 2.8, "learning_rate": 1.3440825000000002e-05, "loss": 2.1855, "step": 935 }, { "epoch": 2.8, "learning_rate": 1.3440120000000002e-05, "loss": 2.1844, "step": 936 }, { "epoch": 2.81, "learning_rate": 1.3439415000000001e-05, "loss": 2.1831, "step": 937 }, { "epoch": 2.81, "learning_rate": 1.343871e-05, "loss": 2.1814, "step": 938 }, { "epoch": 2.81, "learning_rate": 1.3438005e-05, "loss": 2.1791, "step": 939 }, { "epoch": 2.81, "learning_rate": 1.34373e-05, "loss": 2.1811, "step": 940 }, { "epoch": 2.82, "learning_rate": 1.3436595e-05, "loss": 2.1788, "step": 941 }, { "epoch": 2.82, "learning_rate": 1.343589e-05, "loss": 2.1797, "step": 942 }, { "epoch": 2.82, "learning_rate": 1.3435185e-05, "loss": 2.1823, "step": 943 }, { "epoch": 2.83, "learning_rate": 1.343448e-05, "loss": 2.1786, "step": 944 }, { "epoch": 2.83, "learning_rate": 1.3433775e-05, "loss": 2.1816, "step": 945 }, { "epoch": 2.83, "learning_rate": 1.343307e-05, "loss": 2.1767, "step": 946 }, { "epoch": 2.84, "learning_rate": 1.3432365000000001e-05, "loss": 2.18, "step": 947 }, { "epoch": 2.84, "learning_rate": 1.3431660000000001e-05, "loss": 2.1768, "step": 948 }, { "epoch": 2.84, "learning_rate": 1.3430955000000001e-05, "loss": 2.1794, "step": 949 }, { "epoch": 2.84, "learning_rate": 1.343025e-05, "loss": 2.1794, "step": 950 }, { "epoch": 2.85, "learning_rate": 1.3429545e-05, "loss": 2.1777, "step": 951 }, { "epoch": 2.85, "learning_rate": 1.342884e-05, "loss": 2.1757, "step": 952 }, { "epoch": 2.85, "learning_rate": 1.3428135e-05, "loss": 2.1735, "step": 953 }, { "epoch": 2.86, "learning_rate": 1.3427430000000002e-05, "loss": 2.177, "step": 954 }, { "epoch": 2.86, "learning_rate": 1.3426725000000001e-05, "loss": 2.173, "step": 955 }, { "epoch": 2.86, "learning_rate": 1.3426020000000001e-05, "loss": 2.1757, "step": 956 }, { "epoch": 2.87, "learning_rate": 1.3425315000000001e-05, "loss": 2.1717, "step": 957 }, { "epoch": 2.87, "learning_rate": 1.342461e-05, "loss": 2.1737, "step": 958 }, { "epoch": 2.87, "learning_rate": 1.3423904999999999e-05, "loss": 2.1723, "step": 959 }, { "epoch": 2.87, "learning_rate": 1.34232e-05, "loss": 2.1737, "step": 960 }, { "epoch": 2.88, "learning_rate": 1.3422495e-05, "loss": 2.1701, "step": 961 }, { "epoch": 2.88, "learning_rate": 1.342179e-05, "loss": 2.1718, "step": 962 }, { "epoch": 2.88, "learning_rate": 1.3421085e-05, "loss": 2.1727, "step": 963 }, { "epoch": 2.89, "learning_rate": 1.342038e-05, "loss": 2.1673, "step": 964 }, { "epoch": 2.89, "learning_rate": 1.3419675e-05, "loss": 2.1689, "step": 965 }, { "epoch": 2.89, "learning_rate": 1.3418970000000001e-05, "loss": 2.1687, "step": 966 }, { "epoch": 2.9, "learning_rate": 1.3418265000000001e-05, "loss": 2.1691, "step": 967 }, { "epoch": 2.9, "learning_rate": 1.341756e-05, "loss": 2.1727, "step": 968 }, { "epoch": 2.9, "learning_rate": 1.3416855e-05, "loss": 2.1678, "step": 969 }, { "epoch": 2.9, "learning_rate": 1.341615e-05, "loss": 2.1654, "step": 970 }, { "epoch": 2.91, "learning_rate": 1.3415445e-05, "loss": 2.1702, "step": 971 }, { "epoch": 2.91, "learning_rate": 1.3414740000000002e-05, "loss": 2.1675, "step": 972 }, { "epoch": 2.91, "learning_rate": 1.3414035000000001e-05, "loss": 2.1658, "step": 973 }, { "epoch": 2.92, "learning_rate": 1.3413330000000001e-05, "loss": 2.1681, "step": 974 }, { "epoch": 2.92, "learning_rate": 1.3412625000000001e-05, "loss": 2.1651, "step": 975 }, { "epoch": 2.92, "learning_rate": 1.341192e-05, "loss": 2.1674, "step": 976 }, { "epoch": 2.93, "learning_rate": 1.3411215e-05, "loss": 2.1654, "step": 977 }, { "epoch": 2.93, "learning_rate": 1.341051e-05, "loss": 2.1632, "step": 978 }, { "epoch": 2.93, "learning_rate": 1.3409805e-05, "loss": 2.1632, "step": 979 }, { "epoch": 2.93, "learning_rate": 1.34091e-05, "loss": 2.1666, "step": 980 }, { "epoch": 2.94, "learning_rate": 1.3408395e-05, "loss": 2.1618, "step": 981 }, { "epoch": 2.94, "learning_rate": 1.340769e-05, "loss": 2.1622, "step": 982 }, { "epoch": 2.94, "learning_rate": 1.3406985e-05, "loss": 2.1605, "step": 983 }, { "epoch": 2.95, "learning_rate": 1.3406280000000001e-05, "loss": 2.1599, "step": 984 }, { "epoch": 2.95, "learning_rate": 1.3405575e-05, "loss": 2.1627, "step": 985 }, { "epoch": 2.95, "learning_rate": 1.340487e-05, "loss": 2.1599, "step": 986 }, { "epoch": 2.96, "learning_rate": 1.3404165e-05, "loss": 2.1596, "step": 987 }, { "epoch": 2.96, "learning_rate": 1.340346e-05, "loss": 2.1604, "step": 988 }, { "epoch": 2.96, "learning_rate": 1.3402755e-05, "loss": 2.1608, "step": 989 }, { "epoch": 2.96, "learning_rate": 1.340205e-05, "loss": 2.1583, "step": 990 }, { "epoch": 2.97, "learning_rate": 1.3401345000000001e-05, "loss": 2.1618, "step": 991 }, { "epoch": 2.97, "learning_rate": 1.3400640000000001e-05, "loss": 2.1574, "step": 992 }, { "epoch": 2.97, "learning_rate": 1.3399935000000001e-05, "loss": 2.1654, "step": 993 }, { "epoch": 2.98, "learning_rate": 1.339923e-05, "loss": 2.1567, "step": 994 }, { "epoch": 2.98, "learning_rate": 1.3398525e-05, "loss": 2.1563, "step": 995 }, { "epoch": 2.98, "learning_rate": 1.339782e-05, "loss": 2.1574, "step": 996 }, { "epoch": 2.99, "learning_rate": 1.3397115000000002e-05, "loss": 2.1577, "step": 997 }, { "epoch": 2.99, "learning_rate": 1.339641e-05, "loss": 2.1567, "step": 998 }, { "epoch": 2.99, "learning_rate": 1.3395705e-05, "loss": 2.1572, "step": 999 }, { "epoch": 2.99, "learning_rate": 1.3395e-05, "loss": 2.1542, "step": 1000 }, { "epoch": 2.99, "eval_accuracy": 0.0006947357382550335, "eval_loss": 2.0252981185913086, "eval_runtime": 30.5941, "eval_samples_per_second": 9.74, "eval_steps_per_second": 0.621, "step": 1000 }, { "epoch": 3.0, "learning_rate": 1.3394295e-05, "loss": 2.1554, "step": 1001 }, { "epoch": 3.0, "learning_rate": 1.339359e-05, "loss": 2.1527, "step": 1002 }, { "epoch": 3.0, "learning_rate": 1.3392885e-05, "loss": 2.1579, "step": 1003 }, { "epoch": 3.01, "learning_rate": 1.339218e-05, "loss": 2.1558, "step": 1004 }, { "epoch": 3.01, "learning_rate": 1.3391475e-05, "loss": 2.1526, "step": 1005 }, { "epoch": 3.01, "learning_rate": 1.339077e-05, "loss": 2.1519, "step": 1006 }, { "epoch": 3.02, "learning_rate": 1.3390065e-05, "loss": 2.1521, "step": 1007 }, { "epoch": 3.02, "learning_rate": 1.338936e-05, "loss": 2.1533, "step": 1008 }, { "epoch": 3.02, "learning_rate": 1.3388655000000001e-05, "loss": 2.1564, "step": 1009 }, { "epoch": 3.02, "learning_rate": 1.3387950000000001e-05, "loss": 2.1519, "step": 1010 }, { "epoch": 3.03, "learning_rate": 1.3387245000000001e-05, "loss": 2.1485, "step": 1011 }, { "epoch": 3.03, "learning_rate": 1.338654e-05, "loss": 2.1514, "step": 1012 }, { "epoch": 3.03, "learning_rate": 1.3385835e-05, "loss": 2.1513, "step": 1013 }, { "epoch": 3.04, "learning_rate": 1.338513e-05, "loss": 2.1527, "step": 1014 }, { "epoch": 3.04, "learning_rate": 1.3384425000000002e-05, "loss": 2.1487, "step": 1015 }, { "epoch": 3.04, "learning_rate": 1.3383720000000002e-05, "loss": 2.1501, "step": 1016 }, { "epoch": 3.05, "learning_rate": 1.3383015000000001e-05, "loss": 2.1472, "step": 1017 }, { "epoch": 3.05, "learning_rate": 1.3382310000000001e-05, "loss": 2.1503, "step": 1018 }, { "epoch": 3.05, "learning_rate": 1.3381605e-05, "loss": 2.1477, "step": 1019 }, { "epoch": 3.05, "learning_rate": 1.33809e-05, "loss": 2.1475, "step": 1020 }, { "epoch": 3.06, "learning_rate": 1.3380195e-05, "loss": 2.1451, "step": 1021 }, { "epoch": 3.06, "learning_rate": 1.337949e-05, "loss": 2.1459, "step": 1022 }, { "epoch": 3.06, "learning_rate": 1.3378785e-05, "loss": 2.1461, "step": 1023 }, { "epoch": 3.07, "learning_rate": 1.337808e-05, "loss": 2.1455, "step": 1024 }, { "epoch": 3.07, "learning_rate": 1.3377375e-05, "loss": 2.143, "step": 1025 }, { "epoch": 3.07, "learning_rate": 1.337667e-05, "loss": 2.1452, "step": 1026 }, { "epoch": 3.08, "learning_rate": 1.3375965e-05, "loss": 2.1442, "step": 1027 }, { "epoch": 3.08, "learning_rate": 1.3375260000000001e-05, "loss": 2.1416, "step": 1028 }, { "epoch": 3.08, "learning_rate": 1.3374555000000001e-05, "loss": 2.1421, "step": 1029 }, { "epoch": 3.08, "learning_rate": 1.337385e-05, "loss": 2.1419, "step": 1030 }, { "epoch": 3.09, "learning_rate": 1.3373145e-05, "loss": 2.1426, "step": 1031 }, { "epoch": 3.09, "learning_rate": 1.337244e-05, "loss": 2.1437, "step": 1032 }, { "epoch": 3.09, "learning_rate": 1.3371735e-05, "loss": 2.14, "step": 1033 }, { "epoch": 3.1, "learning_rate": 1.3371030000000002e-05, "loss": 2.1422, "step": 1034 }, { "epoch": 3.1, "learning_rate": 1.3370325000000001e-05, "loss": 2.1399, "step": 1035 }, { "epoch": 3.1, "learning_rate": 1.3369620000000001e-05, "loss": 2.1402, "step": 1036 }, { "epoch": 3.11, "learning_rate": 1.3368915000000001e-05, "loss": 2.1432, "step": 1037 }, { "epoch": 3.11, "learning_rate": 1.3368210000000001e-05, "loss": 2.1396, "step": 1038 }, { "epoch": 3.11, "learning_rate": 1.3367504999999999e-05, "loss": 2.1398, "step": 1039 }, { "epoch": 3.11, "learning_rate": 1.33668e-05, "loss": 2.1392, "step": 1040 }, { "epoch": 3.12, "learning_rate": 1.3366095e-05, "loss": 2.1372, "step": 1041 }, { "epoch": 3.12, "learning_rate": 1.336539e-05, "loss": 2.1392, "step": 1042 }, { "epoch": 3.12, "learning_rate": 1.3364685e-05, "loss": 2.1357, "step": 1043 }, { "epoch": 3.13, "learning_rate": 1.336398e-05, "loss": 2.1354, "step": 1044 }, { "epoch": 3.13, "learning_rate": 1.3363275e-05, "loss": 2.1377, "step": 1045 }, { "epoch": 3.13, "learning_rate": 1.3362570000000001e-05, "loss": 2.1379, "step": 1046 }, { "epoch": 3.14, "learning_rate": 1.3361865000000001e-05, "loss": 2.1371, "step": 1047 }, { "epoch": 3.14, "learning_rate": 1.336116e-05, "loss": 2.1383, "step": 1048 }, { "epoch": 3.14, "learning_rate": 1.3360455e-05, "loss": 2.1385, "step": 1049 }, { "epoch": 3.14, "learning_rate": 1.335975e-05, "loss": 2.136, "step": 1050 }, { "epoch": 3.15, "learning_rate": 1.3359045e-05, "loss": 2.136, "step": 1051 }, { "epoch": 3.15, "learning_rate": 1.3358340000000002e-05, "loss": 2.1356, "step": 1052 }, { "epoch": 3.15, "learning_rate": 1.3357635000000001e-05, "loss": 2.1342, "step": 1053 }, { "epoch": 3.16, "learning_rate": 1.3356930000000001e-05, "loss": 2.1321, "step": 1054 }, { "epoch": 3.16, "learning_rate": 1.3356225000000001e-05, "loss": 2.1309, "step": 1055 }, { "epoch": 3.16, "learning_rate": 1.335552e-05, "loss": 2.1334, "step": 1056 }, { "epoch": 3.17, "learning_rate": 1.3354815e-05, "loss": 2.1344, "step": 1057 }, { "epoch": 3.17, "learning_rate": 1.335411e-05, "loss": 2.1341, "step": 1058 }, { "epoch": 3.17, "learning_rate": 1.3353405e-05, "loss": 2.1346, "step": 1059 }, { "epoch": 3.17, "learning_rate": 1.33527e-05, "loss": 2.1308, "step": 1060 }, { "epoch": 3.18, "learning_rate": 1.3351995e-05, "loss": 2.1302, "step": 1061 }, { "epoch": 3.18, "learning_rate": 1.335129e-05, "loss": 2.1301, "step": 1062 }, { "epoch": 3.18, "learning_rate": 1.3350585e-05, "loss": 2.1307, "step": 1063 }, { "epoch": 3.19, "learning_rate": 1.334988e-05, "loss": 2.129, "step": 1064 }, { "epoch": 3.19, "learning_rate": 1.3349175e-05, "loss": 2.134, "step": 1065 }, { "epoch": 3.19, "learning_rate": 1.334847e-05, "loss": 2.1269, "step": 1066 }, { "epoch": 3.2, "learning_rate": 1.3347765e-05, "loss": 2.1289, "step": 1067 }, { "epoch": 3.2, "learning_rate": 1.334706e-05, "loss": 2.1304, "step": 1068 }, { "epoch": 3.2, "learning_rate": 1.3346355e-05, "loss": 2.1272, "step": 1069 }, { "epoch": 3.2, "learning_rate": 1.334565e-05, "loss": 2.1281, "step": 1070 }, { "epoch": 3.21, "learning_rate": 1.3344945000000001e-05, "loss": 2.1268, "step": 1071 }, { "epoch": 3.21, "learning_rate": 1.3344240000000001e-05, "loss": 2.1279, "step": 1072 }, { "epoch": 3.21, "learning_rate": 1.3343535000000001e-05, "loss": 2.1297, "step": 1073 }, { "epoch": 3.22, "learning_rate": 1.334283e-05, "loss": 2.1251, "step": 1074 }, { "epoch": 3.22, "learning_rate": 1.3342125e-05, "loss": 2.125, "step": 1075 }, { "epoch": 3.22, "learning_rate": 1.334142e-05, "loss": 2.126, "step": 1076 }, { "epoch": 3.23, "learning_rate": 1.3340715000000002e-05, "loss": 2.1249, "step": 1077 }, { "epoch": 3.23, "learning_rate": 1.3340010000000002e-05, "loss": 2.1218, "step": 1078 }, { "epoch": 3.23, "learning_rate": 1.3339305e-05, "loss": 2.124, "step": 1079 }, { "epoch": 3.23, "learning_rate": 1.33386e-05, "loss": 2.1261, "step": 1080 }, { "epoch": 3.24, "learning_rate": 1.3337895e-05, "loss": 2.1254, "step": 1081 }, { "epoch": 3.24, "learning_rate": 1.333719e-05, "loss": 2.1227, "step": 1082 }, { "epoch": 3.24, "learning_rate": 1.3336485e-05, "loss": 2.126, "step": 1083 }, { "epoch": 3.25, "learning_rate": 1.333578e-05, "loss": 2.1224, "step": 1084 }, { "epoch": 3.25, "learning_rate": 1.3335075e-05, "loss": 2.1197, "step": 1085 }, { "epoch": 3.25, "learning_rate": 1.333437e-05, "loss": 2.1219, "step": 1086 }, { "epoch": 3.26, "learning_rate": 1.3333665e-05, "loss": 2.1234, "step": 1087 }, { "epoch": 3.26, "learning_rate": 1.333296e-05, "loss": 2.1208, "step": 1088 }, { "epoch": 3.26, "learning_rate": 1.3332255000000001e-05, "loss": 2.1222, "step": 1089 }, { "epoch": 3.26, "learning_rate": 1.3331550000000001e-05, "loss": 2.1204, "step": 1090 }, { "epoch": 3.27, "learning_rate": 1.3330845000000001e-05, "loss": 2.1196, "step": 1091 }, { "epoch": 3.27, "learning_rate": 1.333014e-05, "loss": 2.1154, "step": 1092 }, { "epoch": 3.27, "learning_rate": 1.3329435e-05, "loss": 2.1247, "step": 1093 }, { "epoch": 3.28, "learning_rate": 1.332873e-05, "loss": 2.1211, "step": 1094 }, { "epoch": 3.28, "learning_rate": 1.3328025e-05, "loss": 2.1197, "step": 1095 }, { "epoch": 3.28, "learning_rate": 1.3327320000000002e-05, "loss": 2.1182, "step": 1096 }, { "epoch": 3.29, "learning_rate": 1.3326615000000001e-05, "loss": 2.12, "step": 1097 }, { "epoch": 3.29, "learning_rate": 1.3325910000000001e-05, "loss": 2.1179, "step": 1098 }, { "epoch": 3.29, "learning_rate": 1.3325205e-05, "loss": 2.1187, "step": 1099 }, { "epoch": 3.29, "learning_rate": 1.33245e-05, "loss": 2.1181, "step": 1100 }, { "epoch": 3.29, "eval_accuracy": 0.0005570994127516778, "eval_loss": 1.9922733306884766, "eval_runtime": 29.2202, "eval_samples_per_second": 10.198, "eval_steps_per_second": 0.65, "step": 1100 }, { "epoch": 3.3, "learning_rate": 1.3323795e-05, "loss": 2.1142, "step": 1101 }, { "epoch": 3.3, "learning_rate": 1.332309e-05, "loss": 2.1128, "step": 1102 }, { "epoch": 3.3, "learning_rate": 1.3322385e-05, "loss": 2.1157, "step": 1103 }, { "epoch": 3.31, "learning_rate": 1.332168e-05, "loss": 2.1159, "step": 1104 }, { "epoch": 3.31, "learning_rate": 1.3320975e-05, "loss": 2.1139, "step": 1105 }, { "epoch": 3.31, "learning_rate": 1.332027e-05, "loss": 2.1147, "step": 1106 }, { "epoch": 3.31, "learning_rate": 1.3319565e-05, "loss": 2.1167, "step": 1107 }, { "epoch": 3.32, "learning_rate": 1.3318860000000001e-05, "loss": 2.1132, "step": 1108 }, { "epoch": 3.32, "learning_rate": 1.3318155000000001e-05, "loss": 2.1111, "step": 1109 }, { "epoch": 3.32, "learning_rate": 1.331745e-05, "loss": 2.1135, "step": 1110 }, { "epoch": 3.33, "learning_rate": 1.3316745e-05, "loss": 2.1147, "step": 1111 }, { "epoch": 3.33, "learning_rate": 1.331604e-05, "loss": 2.1113, "step": 1112 }, { "epoch": 3.33, "learning_rate": 1.3315335e-05, "loss": 2.1105, "step": 1113 }, { "epoch": 3.34, "learning_rate": 1.3314630000000002e-05, "loss": 2.1119, "step": 1114 }, { "epoch": 3.34, "learning_rate": 1.3313925000000001e-05, "loss": 2.1126, "step": 1115 }, { "epoch": 3.34, "learning_rate": 1.3313220000000001e-05, "loss": 2.1094, "step": 1116 }, { "epoch": 3.34, "learning_rate": 1.3312515000000001e-05, "loss": 2.1093, "step": 1117 }, { "epoch": 3.35, "learning_rate": 1.3311810000000001e-05, "loss": 2.1102, "step": 1118 }, { "epoch": 3.35, "learning_rate": 1.3311104999999999e-05, "loss": 2.1102, "step": 1119 }, { "epoch": 3.35, "learning_rate": 1.33104e-05, "loss": 2.1117, "step": 1120 }, { "epoch": 3.36, "learning_rate": 1.3309695e-05, "loss": 2.1104, "step": 1121 }, { "epoch": 3.36, "learning_rate": 1.330899e-05, "loss": 2.1089, "step": 1122 }, { "epoch": 3.36, "learning_rate": 1.3308285e-05, "loss": 2.1081, "step": 1123 }, { "epoch": 3.37, "learning_rate": 1.330758e-05, "loss": 2.1106, "step": 1124 }, { "epoch": 3.37, "learning_rate": 1.3306875e-05, "loss": 2.1063, "step": 1125 }, { "epoch": 3.37, "learning_rate": 1.3306170000000001e-05, "loss": 2.1093, "step": 1126 }, { "epoch": 3.37, "learning_rate": 1.3305465000000001e-05, "loss": 2.108, "step": 1127 }, { "epoch": 3.38, "learning_rate": 1.330476e-05, "loss": 2.1084, "step": 1128 }, { "epoch": 3.38, "learning_rate": 1.3304055e-05, "loss": 2.1056, "step": 1129 }, { "epoch": 3.38, "learning_rate": 1.330335e-05, "loss": 2.1072, "step": 1130 }, { "epoch": 3.39, "learning_rate": 1.3302645e-05, "loss": 2.1078, "step": 1131 }, { "epoch": 3.39, "learning_rate": 1.330194e-05, "loss": 2.1063, "step": 1132 }, { "epoch": 3.39, "learning_rate": 1.3301235000000001e-05, "loss": 2.1054, "step": 1133 }, { "epoch": 3.4, "learning_rate": 1.3300530000000001e-05, "loss": 2.1051, "step": 1134 }, { "epoch": 3.4, "learning_rate": 1.3299825000000001e-05, "loss": 2.107, "step": 1135 }, { "epoch": 3.4, "learning_rate": 1.329912e-05, "loss": 2.1014, "step": 1136 }, { "epoch": 3.4, "learning_rate": 1.3298415e-05, "loss": 2.103, "step": 1137 }, { "epoch": 3.41, "learning_rate": 1.329771e-05, "loss": 2.1053, "step": 1138 }, { "epoch": 3.41, "learning_rate": 1.3297005000000002e-05, "loss": 2.1008, "step": 1139 }, { "epoch": 3.41, "learning_rate": 1.32963e-05, "loss": 2.1021, "step": 1140 }, { "epoch": 3.42, "learning_rate": 1.3295595e-05, "loss": 2.1022, "step": 1141 }, { "epoch": 3.42, "learning_rate": 1.329489e-05, "loss": 2.1019, "step": 1142 }, { "epoch": 3.42, "learning_rate": 1.3294185e-05, "loss": 2.103, "step": 1143 }, { "epoch": 3.43, "learning_rate": 1.329348e-05, "loss": 2.104, "step": 1144 }, { "epoch": 3.43, "learning_rate": 1.3292775e-05, "loss": 2.1004, "step": 1145 }, { "epoch": 3.43, "learning_rate": 1.329207e-05, "loss": 2.1005, "step": 1146 }, { "epoch": 3.43, "learning_rate": 1.3291365e-05, "loss": 2.0983, "step": 1147 }, { "epoch": 3.44, "learning_rate": 1.329066e-05, "loss": 2.0994, "step": 1148 }, { "epoch": 3.44, "learning_rate": 1.3289955e-05, "loss": 2.1015, "step": 1149 }, { "epoch": 3.44, "learning_rate": 1.328925e-05, "loss": 2.1023, "step": 1150 }, { "epoch": 3.45, "learning_rate": 1.3288545000000001e-05, "loss": 2.1027, "step": 1151 }, { "epoch": 3.45, "learning_rate": 1.3287840000000001e-05, "loss": 2.1043, "step": 1152 }, { "epoch": 3.45, "learning_rate": 1.3287135000000001e-05, "loss": 2.0993, "step": 1153 }, { "epoch": 3.46, "learning_rate": 1.328643e-05, "loss": 2.1008, "step": 1154 }, { "epoch": 3.46, "learning_rate": 1.3285725e-05, "loss": 2.0956, "step": 1155 }, { "epoch": 3.46, "learning_rate": 1.328502e-05, "loss": 2.0944, "step": 1156 }, { "epoch": 3.46, "learning_rate": 1.3284315000000002e-05, "loss": 2.0933, "step": 1157 }, { "epoch": 3.47, "learning_rate": 1.3283610000000002e-05, "loss": 2.0965, "step": 1158 }, { "epoch": 3.47, "learning_rate": 1.3282905000000002e-05, "loss": 2.1014, "step": 1159 }, { "epoch": 3.47, "learning_rate": 1.32822e-05, "loss": 2.0943, "step": 1160 }, { "epoch": 3.48, "learning_rate": 1.3281495e-05, "loss": 2.0942, "step": 1161 }, { "epoch": 3.48, "learning_rate": 1.328079e-05, "loss": 2.0954, "step": 1162 }, { "epoch": 3.48, "learning_rate": 1.3280085e-05, "loss": 2.0963, "step": 1163 }, { "epoch": 3.49, "learning_rate": 1.327938e-05, "loss": 2.0961, "step": 1164 }, { "epoch": 3.49, "learning_rate": 1.3278675e-05, "loss": 2.0951, "step": 1165 }, { "epoch": 3.49, "learning_rate": 1.327797e-05, "loss": 2.0935, "step": 1166 }, { "epoch": 3.49, "learning_rate": 1.3277265e-05, "loss": 2.0922, "step": 1167 }, { "epoch": 3.5, "learning_rate": 1.327656e-05, "loss": 2.0945, "step": 1168 }, { "epoch": 3.5, "learning_rate": 1.3275855e-05, "loss": 2.0969, "step": 1169 }, { "epoch": 3.5, "learning_rate": 1.3275150000000001e-05, "loss": 2.0938, "step": 1170 }, { "epoch": 3.51, "learning_rate": 1.3274445000000001e-05, "loss": 2.0963, "step": 1171 }, { "epoch": 3.51, "learning_rate": 1.327374e-05, "loss": 2.0916, "step": 1172 }, { "epoch": 3.51, "learning_rate": 1.3273035e-05, "loss": 2.0926, "step": 1173 }, { "epoch": 3.52, "learning_rate": 1.327233e-05, "loss": 2.0899, "step": 1174 }, { "epoch": 3.52, "learning_rate": 1.3271625e-05, "loss": 2.0897, "step": 1175 }, { "epoch": 3.52, "learning_rate": 1.3270920000000002e-05, "loss": 2.0965, "step": 1176 }, { "epoch": 3.52, "learning_rate": 1.3270215000000001e-05, "loss": 2.0912, "step": 1177 }, { "epoch": 3.53, "learning_rate": 1.3269510000000001e-05, "loss": 2.0916, "step": 1178 }, { "epoch": 3.53, "learning_rate": 1.3268805000000001e-05, "loss": 2.0898, "step": 1179 }, { "epoch": 3.53, "learning_rate": 1.32681e-05, "loss": 2.0906, "step": 1180 }, { "epoch": 3.54, "learning_rate": 1.3267394999999999e-05, "loss": 2.0902, "step": 1181 }, { "epoch": 3.54, "learning_rate": 1.326669e-05, "loss": 2.0889, "step": 1182 }, { "epoch": 3.54, "learning_rate": 1.3265985e-05, "loss": 2.091, "step": 1183 }, { "epoch": 3.55, "learning_rate": 1.326528e-05, "loss": 2.0872, "step": 1184 }, { "epoch": 3.55, "learning_rate": 1.3264575e-05, "loss": 2.0853, "step": 1185 }, { "epoch": 3.55, "learning_rate": 1.326387e-05, "loss": 2.0863, "step": 1186 }, { "epoch": 3.55, "learning_rate": 1.3263165e-05, "loss": 2.0879, "step": 1187 }, { "epoch": 3.56, "learning_rate": 1.3262460000000001e-05, "loss": 2.0865, "step": 1188 }, { "epoch": 3.56, "learning_rate": 1.3261755000000001e-05, "loss": 2.0888, "step": 1189 }, { "epoch": 3.56, "learning_rate": 1.326105e-05, "loss": 2.0866, "step": 1190 }, { "epoch": 3.57, "learning_rate": 1.3260345e-05, "loss": 2.0848, "step": 1191 }, { "epoch": 3.57, "learning_rate": 1.325964e-05, "loss": 2.0859, "step": 1192 }, { "epoch": 3.57, "learning_rate": 1.3258935e-05, "loss": 2.0872, "step": 1193 }, { "epoch": 3.58, "learning_rate": 1.3258230000000002e-05, "loss": 2.0839, "step": 1194 }, { "epoch": 3.58, "learning_rate": 1.3257525000000001e-05, "loss": 2.0864, "step": 1195 }, { "epoch": 3.58, "learning_rate": 1.3256820000000001e-05, "loss": 2.0849, "step": 1196 }, { "epoch": 3.58, "learning_rate": 1.3256115000000001e-05, "loss": 2.0852, "step": 1197 }, { "epoch": 3.59, "learning_rate": 1.3255410000000001e-05, "loss": 2.0893, "step": 1198 }, { "epoch": 3.59, "learning_rate": 1.3254705e-05, "loss": 2.0865, "step": 1199 }, { "epoch": 3.59, "learning_rate": 1.3254e-05, "loss": 2.0823, "step": 1200 }, { "epoch": 3.59, "eval_accuracy": 0.000576761744966443, "eval_loss": 1.9653271436691284, "eval_runtime": 31.0176, "eval_samples_per_second": 9.607, "eval_steps_per_second": 0.613, "step": 1200 }, { "epoch": 3.6, "learning_rate": 1.3253295e-05, "loss": 2.0842, "step": 1201 }, { "epoch": 3.6, "learning_rate": 1.325259e-05, "loss": 2.0832, "step": 1202 }, { "epoch": 3.6, "learning_rate": 1.3251885e-05, "loss": 2.0839, "step": 1203 }, { "epoch": 3.61, "learning_rate": 1.325118e-05, "loss": 2.0826, "step": 1204 }, { "epoch": 3.61, "learning_rate": 1.3250475e-05, "loss": 2.0845, "step": 1205 }, { "epoch": 3.61, "learning_rate": 1.3249770000000001e-05, "loss": 2.0829, "step": 1206 }, { "epoch": 3.61, "learning_rate": 1.3249065000000001e-05, "loss": 2.0813, "step": 1207 }, { "epoch": 3.62, "learning_rate": 1.324836e-05, "loss": 2.0803, "step": 1208 }, { "epoch": 3.62, "learning_rate": 1.3247655e-05, "loss": 2.0814, "step": 1209 }, { "epoch": 3.62, "learning_rate": 1.324695e-05, "loss": 2.0809, "step": 1210 }, { "epoch": 3.63, "learning_rate": 1.3246245e-05, "loss": 2.0833, "step": 1211 }, { "epoch": 3.63, "learning_rate": 1.324554e-05, "loss": 2.0806, "step": 1212 }, { "epoch": 3.63, "learning_rate": 1.3244835000000001e-05, "loss": 2.0807, "step": 1213 }, { "epoch": 3.64, "learning_rate": 1.3244130000000001e-05, "loss": 2.0827, "step": 1214 }, { "epoch": 3.64, "learning_rate": 1.3243425000000001e-05, "loss": 2.0779, "step": 1215 }, { "epoch": 3.64, "learning_rate": 1.324272e-05, "loss": 2.0797, "step": 1216 }, { "epoch": 3.64, "learning_rate": 1.3242015e-05, "loss": 2.0802, "step": 1217 }, { "epoch": 3.65, "learning_rate": 1.324131e-05, "loss": 2.0786, "step": 1218 }, { "epoch": 3.65, "learning_rate": 1.3240605000000002e-05, "loss": 2.0785, "step": 1219 }, { "epoch": 3.65, "learning_rate": 1.32399e-05, "loss": 2.0788, "step": 1220 }, { "epoch": 3.66, "learning_rate": 1.3239195e-05, "loss": 2.0774, "step": 1221 }, { "epoch": 3.66, "learning_rate": 1.323849e-05, "loss": 2.0786, "step": 1222 }, { "epoch": 3.66, "learning_rate": 1.3237785e-05, "loss": 2.0771, "step": 1223 }, { "epoch": 3.67, "learning_rate": 1.323708e-05, "loss": 2.0729, "step": 1224 }, { "epoch": 3.67, "learning_rate": 1.3236375e-05, "loss": 2.0794, "step": 1225 }, { "epoch": 3.67, "learning_rate": 1.323567e-05, "loss": 2.0786, "step": 1226 }, { "epoch": 3.67, "learning_rate": 1.3234965e-05, "loss": 2.0792, "step": 1227 }, { "epoch": 3.68, "learning_rate": 1.323426e-05, "loss": 2.0785, "step": 1228 }, { "epoch": 3.68, "learning_rate": 1.3233555e-05, "loss": 2.0781, "step": 1229 }, { "epoch": 3.68, "learning_rate": 1.323285e-05, "loss": 2.076, "step": 1230 }, { "epoch": 3.69, "learning_rate": 1.3232145000000001e-05, "loss": 2.0743, "step": 1231 }, { "epoch": 3.69, "learning_rate": 1.3231440000000001e-05, "loss": 2.0743, "step": 1232 }, { "epoch": 3.69, "learning_rate": 1.3230735000000001e-05, "loss": 2.0743, "step": 1233 }, { "epoch": 3.7, "learning_rate": 1.323003e-05, "loss": 2.0734, "step": 1234 }, { "epoch": 3.7, "learning_rate": 1.3229325e-05, "loss": 2.0729, "step": 1235 }, { "epoch": 3.7, "learning_rate": 1.322862e-05, "loss": 2.0755, "step": 1236 }, { "epoch": 3.7, "learning_rate": 1.3227915e-05, "loss": 2.0722, "step": 1237 }, { "epoch": 3.71, "learning_rate": 1.3227210000000002e-05, "loss": 2.0764, "step": 1238 }, { "epoch": 3.71, "learning_rate": 1.3226505000000002e-05, "loss": 2.0742, "step": 1239 }, { "epoch": 3.71, "learning_rate": 1.32258e-05, "loss": 2.0738, "step": 1240 }, { "epoch": 3.72, "learning_rate": 1.3225095e-05, "loss": 2.0682, "step": 1241 }, { "epoch": 3.72, "learning_rate": 1.322439e-05, "loss": 2.0721, "step": 1242 }, { "epoch": 3.72, "learning_rate": 1.3223685e-05, "loss": 2.0732, "step": 1243 }, { "epoch": 3.73, "learning_rate": 1.322298e-05, "loss": 2.0728, "step": 1244 }, { "epoch": 3.73, "learning_rate": 1.3222275e-05, "loss": 2.0715, "step": 1245 }, { "epoch": 3.73, "learning_rate": 1.322157e-05, "loss": 2.0662, "step": 1246 }, { "epoch": 3.73, "learning_rate": 1.3220865e-05, "loss": 2.07, "step": 1247 }, { "epoch": 3.74, "learning_rate": 1.322016e-05, "loss": 2.071, "step": 1248 }, { "epoch": 3.74, "learning_rate": 1.3219455e-05, "loss": 2.0711, "step": 1249 }, { "epoch": 3.74, "learning_rate": 1.3218750000000001e-05, "loss": 2.0696, "step": 1250 }, { "epoch": 3.75, "learning_rate": 1.3218045000000001e-05, "loss": 2.0713, "step": 1251 }, { "epoch": 3.75, "learning_rate": 1.321734e-05, "loss": 2.0673, "step": 1252 }, { "epoch": 3.75, "learning_rate": 1.3216635e-05, "loss": 2.0661, "step": 1253 }, { "epoch": 3.76, "learning_rate": 1.321593e-05, "loss": 2.0683, "step": 1254 }, { "epoch": 3.76, "learning_rate": 1.3215225e-05, "loss": 2.0719, "step": 1255 }, { "epoch": 3.76, "learning_rate": 1.3214520000000002e-05, "loss": 2.0677, "step": 1256 }, { "epoch": 3.76, "learning_rate": 1.3213815000000001e-05, "loss": 2.0684, "step": 1257 }, { "epoch": 3.77, "learning_rate": 1.3213110000000001e-05, "loss": 2.0665, "step": 1258 }, { "epoch": 3.77, "learning_rate": 1.3212405000000001e-05, "loss": 2.0635, "step": 1259 }, { "epoch": 3.77, "learning_rate": 1.3211700000000001e-05, "loss": 2.0647, "step": 1260 }, { "epoch": 3.78, "learning_rate": 1.3210994999999999e-05, "loss": 2.0655, "step": 1261 }, { "epoch": 3.78, "learning_rate": 1.321029e-05, "loss": 2.0652, "step": 1262 }, { "epoch": 3.78, "learning_rate": 1.3209585e-05, "loss": 2.0697, "step": 1263 }, { "epoch": 3.79, "learning_rate": 1.320888e-05, "loss": 2.0675, "step": 1264 }, { "epoch": 3.79, "learning_rate": 1.3208175e-05, "loss": 2.0656, "step": 1265 }, { "epoch": 3.79, "learning_rate": 1.320747e-05, "loss": 2.064, "step": 1266 }, { "epoch": 3.79, "learning_rate": 1.3206765e-05, "loss": 2.0626, "step": 1267 }, { "epoch": 3.8, "learning_rate": 1.3206060000000001e-05, "loss": 2.065, "step": 1268 }, { "epoch": 3.8, "learning_rate": 1.3205355000000001e-05, "loss": 2.0639, "step": 1269 }, { "epoch": 3.8, "learning_rate": 1.320465e-05, "loss": 2.0614, "step": 1270 }, { "epoch": 3.81, "learning_rate": 1.3203945e-05, "loss": 2.0629, "step": 1271 }, { "epoch": 3.81, "learning_rate": 1.320324e-05, "loss": 2.0658, "step": 1272 }, { "epoch": 3.81, "learning_rate": 1.3202535e-05, "loss": 2.0637, "step": 1273 }, { "epoch": 3.82, "learning_rate": 1.3201830000000002e-05, "loss": 2.0617, "step": 1274 }, { "epoch": 3.82, "learning_rate": 1.3201125000000001e-05, "loss": 2.0644, "step": 1275 }, { "epoch": 3.82, "learning_rate": 1.3200420000000001e-05, "loss": 2.0588, "step": 1276 }, { "epoch": 3.82, "learning_rate": 1.3199715000000001e-05, "loss": 2.0641, "step": 1277 }, { "epoch": 3.83, "learning_rate": 1.3199010000000001e-05, "loss": 2.0639, "step": 1278 }, { "epoch": 3.83, "learning_rate": 1.3198305e-05, "loss": 2.0622, "step": 1279 }, { "epoch": 3.83, "learning_rate": 1.31976e-05, "loss": 2.0604, "step": 1280 }, { "epoch": 3.84, "learning_rate": 1.3196895e-05, "loss": 2.0625, "step": 1281 }, { "epoch": 3.84, "learning_rate": 1.319619e-05, "loss": 2.0607, "step": 1282 }, { "epoch": 3.84, "learning_rate": 1.3195485e-05, "loss": 2.0613, "step": 1283 }, { "epoch": 3.85, "learning_rate": 1.319478e-05, "loss": 2.0611, "step": 1284 }, { "epoch": 3.85, "learning_rate": 1.3194075e-05, "loss": 2.064, "step": 1285 }, { "epoch": 3.85, "learning_rate": 1.319337e-05, "loss": 2.0584, "step": 1286 }, { "epoch": 3.85, "learning_rate": 1.3192665000000001e-05, "loss": 2.0619, "step": 1287 }, { "epoch": 3.86, "learning_rate": 1.319196e-05, "loss": 2.0599, "step": 1288 }, { "epoch": 3.86, "learning_rate": 1.3191255e-05, "loss": 2.0598, "step": 1289 }, { "epoch": 3.86, "learning_rate": 1.319055e-05, "loss": 2.0566, "step": 1290 }, { "epoch": 3.87, "learning_rate": 1.3189845e-05, "loss": 2.0591, "step": 1291 }, { "epoch": 3.87, "learning_rate": 1.318914e-05, "loss": 2.0604, "step": 1292 }, { "epoch": 3.87, "learning_rate": 1.3188435000000001e-05, "loss": 2.0593, "step": 1293 }, { "epoch": 3.87, "learning_rate": 1.3187730000000001e-05, "loss": 2.0607, "step": 1294 }, { "epoch": 3.88, "learning_rate": 1.3187025000000001e-05, "loss": 2.0561, "step": 1295 }, { "epoch": 3.88, "learning_rate": 1.318632e-05, "loss": 2.0556, "step": 1296 }, { "epoch": 3.88, "learning_rate": 1.3185615e-05, "loss": 2.0549, "step": 1297 }, { "epoch": 3.89, "learning_rate": 1.318491e-05, "loss": 2.0544, "step": 1298 }, { "epoch": 3.89, "learning_rate": 1.3184205000000002e-05, "loss": 2.0585, "step": 1299 }, { "epoch": 3.89, "learning_rate": 1.3183500000000002e-05, "loss": 2.0568, "step": 1300 }, { "epoch": 3.89, "eval_accuracy": 0.0006947357382550335, "eval_loss": 1.942599892616272, "eval_runtime": 29.7388, "eval_samples_per_second": 10.021, "eval_steps_per_second": 0.639, "step": 1300 }, { "epoch": 3.9, "learning_rate": 1.3182795e-05, "loss": 2.0559, "step": 1301 }, { "epoch": 3.9, "learning_rate": 1.318209e-05, "loss": 2.0577, "step": 1302 }, { "epoch": 3.9, "learning_rate": 1.3181385e-05, "loss": 2.0558, "step": 1303 }, { "epoch": 3.9, "learning_rate": 1.318068e-05, "loss": 2.0553, "step": 1304 }, { "epoch": 3.91, "learning_rate": 1.3179975e-05, "loss": 2.0544, "step": 1305 }, { "epoch": 3.91, "learning_rate": 1.317927e-05, "loss": 2.0583, "step": 1306 }, { "epoch": 3.91, "learning_rate": 1.3178565e-05, "loss": 2.0559, "step": 1307 }, { "epoch": 3.92, "learning_rate": 1.317786e-05, "loss": 2.0549, "step": 1308 }, { "epoch": 3.92, "learning_rate": 1.3177155e-05, "loss": 2.0555, "step": 1309 }, { "epoch": 3.92, "learning_rate": 1.317645e-05, "loss": 2.0525, "step": 1310 }, { "epoch": 3.93, "learning_rate": 1.3175745000000001e-05, "loss": 2.0535, "step": 1311 }, { "epoch": 3.93, "learning_rate": 1.3175040000000001e-05, "loss": 2.0505, "step": 1312 }, { "epoch": 3.93, "learning_rate": 1.3174335000000001e-05, "loss": 2.0537, "step": 1313 }, { "epoch": 3.93, "learning_rate": 1.317363e-05, "loss": 2.0519, "step": 1314 }, { "epoch": 3.94, "learning_rate": 1.3172925e-05, "loss": 2.0548, "step": 1315 }, { "epoch": 3.94, "learning_rate": 1.317222e-05, "loss": 2.0549, "step": 1316 }, { "epoch": 3.94, "learning_rate": 1.3171515e-05, "loss": 2.0537, "step": 1317 }, { "epoch": 3.95, "learning_rate": 1.3170810000000002e-05, "loss": 2.0522, "step": 1318 }, { "epoch": 3.95, "learning_rate": 1.3170105000000002e-05, "loss": 2.0502, "step": 1319 }, { "epoch": 3.95, "learning_rate": 1.3169400000000001e-05, "loss": 2.0523, "step": 1320 }, { "epoch": 3.96, "learning_rate": 1.3168695e-05, "loss": 2.0485, "step": 1321 }, { "epoch": 3.96, "learning_rate": 1.316799e-05, "loss": 2.051, "step": 1322 }, { "epoch": 3.96, "learning_rate": 1.3167284999999999e-05, "loss": 2.0509, "step": 1323 }, { "epoch": 3.96, "learning_rate": 1.316658e-05, "loss": 2.0493, "step": 1324 }, { "epoch": 3.97, "learning_rate": 1.3165875e-05, "loss": 2.0482, "step": 1325 }, { "epoch": 3.97, "learning_rate": 1.316517e-05, "loss": 2.047, "step": 1326 }, { "epoch": 3.97, "learning_rate": 1.3164465e-05, "loss": 2.0497, "step": 1327 }, { "epoch": 3.98, "learning_rate": 1.316376e-05, "loss": 2.0488, "step": 1328 }, { "epoch": 3.98, "learning_rate": 1.3163055e-05, "loss": 2.0492, "step": 1329 }, { "epoch": 3.98, "learning_rate": 1.3162350000000001e-05, "loss": 2.0499, "step": 1330 }, { "epoch": 3.99, "learning_rate": 1.3161645000000001e-05, "loss": 2.0497, "step": 1331 }, { "epoch": 3.99, "learning_rate": 1.316094e-05, "loss": 2.0472, "step": 1332 }, { "epoch": 3.99, "learning_rate": 1.3160235e-05, "loss": 2.0466, "step": 1333 }, { "epoch": 3.99, "learning_rate": 1.315953e-05, "loss": 2.0497, "step": 1334 }, { "epoch": 4.0, "learning_rate": 1.3158825e-05, "loss": 2.0488, "step": 1335 }, { "epoch": 4.0, "learning_rate": 1.3158120000000002e-05, "loss": 2.0474, "step": 1336 }, { "epoch": 4.0, "learning_rate": 1.3157415000000001e-05, "loss": 2.0481, "step": 1337 }, { "epoch": 4.01, "learning_rate": 1.3156710000000001e-05, "loss": 2.0492, "step": 1338 }, { "epoch": 4.01, "learning_rate": 1.3156005000000001e-05, "loss": 2.0495, "step": 1339 }, { "epoch": 4.01, "learning_rate": 1.3155300000000001e-05, "loss": 2.0471, "step": 1340 }, { "epoch": 4.02, "learning_rate": 1.3154594999999999e-05, "loss": 2.0429, "step": 1341 }, { "epoch": 4.02, "learning_rate": 1.315389e-05, "loss": 2.0461, "step": 1342 }, { "epoch": 4.02, "learning_rate": 1.3153185e-05, "loss": 2.0437, "step": 1343 }, { "epoch": 4.02, "learning_rate": 1.315248e-05, "loss": 2.0421, "step": 1344 }, { "epoch": 4.03, "learning_rate": 1.3151775e-05, "loss": 2.0425, "step": 1345 }, { "epoch": 4.03, "learning_rate": 1.315107e-05, "loss": 2.0478, "step": 1346 }, { "epoch": 4.03, "learning_rate": 1.3150365e-05, "loss": 2.044, "step": 1347 }, { "epoch": 4.04, "learning_rate": 1.3149660000000001e-05, "loss": 2.0462, "step": 1348 }, { "epoch": 4.04, "learning_rate": 1.3148955000000001e-05, "loss": 2.0447, "step": 1349 }, { "epoch": 4.04, "learning_rate": 1.314825e-05, "loss": 2.0428, "step": 1350 }, { "epoch": 4.05, "learning_rate": 1.3147545e-05, "loss": 2.0416, "step": 1351 }, { "epoch": 4.05, "learning_rate": 1.314684e-05, "loss": 2.0444, "step": 1352 }, { "epoch": 4.05, "learning_rate": 1.3146135e-05, "loss": 2.0455, "step": 1353 }, { "epoch": 4.05, "learning_rate": 1.314543e-05, "loss": 2.0428, "step": 1354 }, { "epoch": 4.06, "learning_rate": 1.3144725000000001e-05, "loss": 2.0432, "step": 1355 }, { "epoch": 4.06, "learning_rate": 1.3144020000000001e-05, "loss": 2.0452, "step": 1356 }, { "epoch": 4.06, "learning_rate": 1.3143315000000001e-05, "loss": 2.041, "step": 1357 }, { "epoch": 4.07, "learning_rate": 1.3142610000000001e-05, "loss": 2.0402, "step": 1358 }, { "epoch": 4.07, "learning_rate": 1.3141905e-05, "loss": 2.0457, "step": 1359 }, { "epoch": 4.07, "learning_rate": 1.31412e-05, "loss": 2.0428, "step": 1360 }, { "epoch": 4.08, "learning_rate": 1.3140495e-05, "loss": 2.0423, "step": 1361 }, { "epoch": 4.08, "learning_rate": 1.313979e-05, "loss": 2.043, "step": 1362 }, { "epoch": 4.08, "learning_rate": 1.3139085e-05, "loss": 2.0423, "step": 1363 }, { "epoch": 4.08, "learning_rate": 1.313838e-05, "loss": 2.0381, "step": 1364 }, { "epoch": 4.09, "learning_rate": 1.3137675e-05, "loss": 2.0403, "step": 1365 }, { "epoch": 4.09, "learning_rate": 1.313697e-05, "loss": 2.0401, "step": 1366 }, { "epoch": 4.09, "learning_rate": 1.3136265000000001e-05, "loss": 2.0401, "step": 1367 }, { "epoch": 4.1, "learning_rate": 1.313556e-05, "loss": 2.0385, "step": 1368 }, { "epoch": 4.1, "learning_rate": 1.3134855e-05, "loss": 2.0399, "step": 1369 }, { "epoch": 4.1, "learning_rate": 1.313415e-05, "loss": 2.0379, "step": 1370 }, { "epoch": 4.11, "learning_rate": 1.3133445e-05, "loss": 2.037, "step": 1371 }, { "epoch": 4.11, "learning_rate": 1.313274e-05, "loss": 2.0408, "step": 1372 }, { "epoch": 4.11, "learning_rate": 1.3132035000000001e-05, "loss": 2.0397, "step": 1373 }, { "epoch": 4.11, "learning_rate": 1.3131330000000001e-05, "loss": 2.0394, "step": 1374 }, { "epoch": 4.12, "learning_rate": 1.3130625000000001e-05, "loss": 2.0417, "step": 1375 }, { "epoch": 4.12, "learning_rate": 1.312992e-05, "loss": 2.0363, "step": 1376 }, { "epoch": 4.12, "learning_rate": 1.3129215e-05, "loss": 2.0356, "step": 1377 }, { "epoch": 4.13, "learning_rate": 1.312851e-05, "loss": 2.0354, "step": 1378 }, { "epoch": 4.13, "learning_rate": 1.3127805000000002e-05, "loss": 2.0368, "step": 1379 }, { "epoch": 4.13, "learning_rate": 1.3127100000000002e-05, "loss": 2.037, "step": 1380 }, { "epoch": 4.14, "learning_rate": 1.3126395000000002e-05, "loss": 2.0358, "step": 1381 }, { "epoch": 4.14, "learning_rate": 1.312569e-05, "loss": 2.0358, "step": 1382 }, { "epoch": 4.14, "learning_rate": 1.3124985e-05, "loss": 2.0389, "step": 1383 }, { "epoch": 4.14, "learning_rate": 1.312428e-05, "loss": 2.0385, "step": 1384 }, { "epoch": 4.15, "learning_rate": 1.3123575e-05, "loss": 2.035, "step": 1385 }, { "epoch": 4.15, "learning_rate": 1.312287e-05, "loss": 2.0358, "step": 1386 }, { "epoch": 4.15, "learning_rate": 1.3122165e-05, "loss": 2.0351, "step": 1387 }, { "epoch": 4.16, "learning_rate": 1.312146e-05, "loss": 2.0349, "step": 1388 }, { "epoch": 4.16, "learning_rate": 1.3120755e-05, "loss": 2.0303, "step": 1389 }, { "epoch": 4.16, "learning_rate": 1.312005e-05, "loss": 2.0352, "step": 1390 }, { "epoch": 4.17, "learning_rate": 1.3119345e-05, "loss": 2.032, "step": 1391 }, { "epoch": 4.17, "learning_rate": 1.3118640000000001e-05, "loss": 2.0325, "step": 1392 }, { "epoch": 4.17, "learning_rate": 1.3117935000000001e-05, "loss": 2.0356, "step": 1393 }, { "epoch": 4.17, "learning_rate": 1.311723e-05, "loss": 2.0357, "step": 1394 }, { "epoch": 4.18, "learning_rate": 1.3116525e-05, "loss": 2.0305, "step": 1395 }, { "epoch": 4.18, "learning_rate": 1.311582e-05, "loss": 2.0339, "step": 1396 }, { "epoch": 4.18, "learning_rate": 1.3115115e-05, "loss": 2.0341, "step": 1397 }, { "epoch": 4.19, "learning_rate": 1.3114410000000002e-05, "loss": 2.0325, "step": 1398 }, { "epoch": 4.19, "learning_rate": 1.3113705000000002e-05, "loss": 2.0318, "step": 1399 }, { "epoch": 4.19, "learning_rate": 1.3113000000000001e-05, "loss": 2.037, "step": 1400 }, { "epoch": 4.19, "eval_accuracy": 0.0007471686241610738, "eval_loss": 1.9238648414611816, "eval_runtime": 29.3673, "eval_samples_per_second": 10.147, "eval_steps_per_second": 0.647, "step": 1400 }, { "epoch": 4.2, "learning_rate": 1.3112295000000001e-05, "loss": 2.0293, "step": 1401 }, { "epoch": 4.2, "learning_rate": 1.311159e-05, "loss": 2.0303, "step": 1402 }, { "epoch": 4.2, "learning_rate": 1.3110884999999999e-05, "loss": 2.0333, "step": 1403 }, { "epoch": 4.2, "learning_rate": 1.311018e-05, "loss": 2.0299, "step": 1404 }, { "epoch": 4.21, "learning_rate": 1.3109475e-05, "loss": 2.0315, "step": 1405 }, { "epoch": 4.21, "learning_rate": 1.310877e-05, "loss": 2.0338, "step": 1406 }, { "epoch": 4.21, "learning_rate": 1.3108065e-05, "loss": 2.0305, "step": 1407 }, { "epoch": 4.22, "learning_rate": 1.310736e-05, "loss": 2.0303, "step": 1408 }, { "epoch": 4.22, "learning_rate": 1.3106655e-05, "loss": 2.0279, "step": 1409 }, { "epoch": 4.22, "learning_rate": 1.3105950000000001e-05, "loss": 2.03, "step": 1410 }, { "epoch": 4.23, "learning_rate": 1.3105245000000001e-05, "loss": 2.0307, "step": 1411 }, { "epoch": 4.23, "learning_rate": 1.310454e-05, "loss": 2.0286, "step": 1412 }, { "epoch": 4.23, "learning_rate": 1.3103835e-05, "loss": 2.0302, "step": 1413 }, { "epoch": 4.23, "learning_rate": 1.310313e-05, "loss": 2.0276, "step": 1414 }, { "epoch": 4.24, "learning_rate": 1.3102425e-05, "loss": 2.0276, "step": 1415 }, { "epoch": 4.24, "learning_rate": 1.3101720000000002e-05, "loss": 2.0288, "step": 1416 }, { "epoch": 4.24, "learning_rate": 1.3101015000000001e-05, "loss": 2.0262, "step": 1417 }, { "epoch": 4.25, "learning_rate": 1.3100310000000001e-05, "loss": 2.0292, "step": 1418 }, { "epoch": 4.25, "learning_rate": 1.3099605000000001e-05, "loss": 2.0275, "step": 1419 }, { "epoch": 4.25, "learning_rate": 1.3098900000000001e-05, "loss": 2.0279, "step": 1420 }, { "epoch": 4.26, "learning_rate": 1.3098195e-05, "loss": 2.0266, "step": 1421 }, { "epoch": 4.26, "learning_rate": 1.309749e-05, "loss": 2.028, "step": 1422 }, { "epoch": 4.26, "learning_rate": 1.3096785e-05, "loss": 2.028, "step": 1423 }, { "epoch": 4.26, "learning_rate": 1.309608e-05, "loss": 2.0238, "step": 1424 }, { "epoch": 4.27, "learning_rate": 1.3095375e-05, "loss": 2.0265, "step": 1425 }, { "epoch": 4.27, "learning_rate": 1.309467e-05, "loss": 2.0256, "step": 1426 }, { "epoch": 4.27, "learning_rate": 1.3093965e-05, "loss": 2.0249, "step": 1427 }, { "epoch": 4.28, "learning_rate": 1.309326e-05, "loss": 2.027, "step": 1428 }, { "epoch": 4.28, "learning_rate": 1.3092555000000001e-05, "loss": 2.0276, "step": 1429 }, { "epoch": 4.28, "learning_rate": 1.309185e-05, "loss": 2.0268, "step": 1430 }, { "epoch": 4.29, "learning_rate": 1.3091145e-05, "loss": 2.0279, "step": 1431 }, { "epoch": 4.29, "learning_rate": 1.309044e-05, "loss": 2.0243, "step": 1432 }, { "epoch": 4.29, "learning_rate": 1.3089735e-05, "loss": 2.0256, "step": 1433 }, { "epoch": 4.29, "learning_rate": 1.308903e-05, "loss": 2.0229, "step": 1434 }, { "epoch": 4.3, "learning_rate": 1.3088325000000001e-05, "loss": 2.0239, "step": 1435 }, { "epoch": 4.3, "learning_rate": 1.3087620000000001e-05, "loss": 2.0237, "step": 1436 }, { "epoch": 4.3, "learning_rate": 1.3086915000000001e-05, "loss": 2.0236, "step": 1437 }, { "epoch": 4.31, "learning_rate": 1.3086210000000001e-05, "loss": 2.0267, "step": 1438 }, { "epoch": 4.31, "learning_rate": 1.3085505e-05, "loss": 2.0244, "step": 1439 }, { "epoch": 4.31, "learning_rate": 1.30848e-05, "loss": 2.0231, "step": 1440 }, { "epoch": 4.32, "learning_rate": 1.3084095000000002e-05, "loss": 2.022, "step": 1441 }, { "epoch": 4.32, "learning_rate": 1.308339e-05, "loss": 2.0243, "step": 1442 }, { "epoch": 4.32, "learning_rate": 1.3082685e-05, "loss": 2.0237, "step": 1443 }, { "epoch": 4.32, "learning_rate": 1.308198e-05, "loss": 2.023, "step": 1444 }, { "epoch": 4.33, "learning_rate": 1.3081275e-05, "loss": 2.0216, "step": 1445 }, { "epoch": 4.33, "learning_rate": 1.308057e-05, "loss": 2.0212, "step": 1446 }, { "epoch": 4.33, "learning_rate": 1.3079865000000001e-05, "loss": 2.0216, "step": 1447 }, { "epoch": 4.34, "learning_rate": 1.307916e-05, "loss": 2.0205, "step": 1448 }, { "epoch": 4.34, "learning_rate": 1.3078455e-05, "loss": 2.0207, "step": 1449 }, { "epoch": 4.34, "learning_rate": 1.307775e-05, "loss": 2.0228, "step": 1450 }, { "epoch": 4.35, "learning_rate": 1.3077045e-05, "loss": 2.0231, "step": 1451 }, { "epoch": 4.35, "learning_rate": 1.307634e-05, "loss": 2.0201, "step": 1452 }, { "epoch": 4.35, "learning_rate": 1.3075635000000001e-05, "loss": 2.022, "step": 1453 }, { "epoch": 4.35, "learning_rate": 1.3074930000000001e-05, "loss": 2.0204, "step": 1454 }, { "epoch": 4.36, "learning_rate": 1.3074225000000001e-05, "loss": 2.0237, "step": 1455 }, { "epoch": 4.36, "learning_rate": 1.307352e-05, "loss": 2.0203, "step": 1456 }, { "epoch": 4.36, "learning_rate": 1.3072815e-05, "loss": 2.0193, "step": 1457 }, { "epoch": 4.37, "learning_rate": 1.307211e-05, "loss": 2.0183, "step": 1458 }, { "epoch": 4.37, "learning_rate": 1.3071405e-05, "loss": 2.022, "step": 1459 }, { "epoch": 4.37, "learning_rate": 1.3070700000000002e-05, "loss": 2.0194, "step": 1460 }, { "epoch": 4.38, "learning_rate": 1.3069995000000002e-05, "loss": 2.0188, "step": 1461 }, { "epoch": 4.38, "learning_rate": 1.306929e-05, "loss": 2.0215, "step": 1462 }, { "epoch": 4.38, "learning_rate": 1.3068585e-05, "loss": 2.021, "step": 1463 }, { "epoch": 4.38, "learning_rate": 1.306788e-05, "loss": 2.0194, "step": 1464 }, { "epoch": 4.39, "learning_rate": 1.3067175e-05, "loss": 2.0172, "step": 1465 }, { "epoch": 4.39, "learning_rate": 1.306647e-05, "loss": 2.019, "step": 1466 }, { "epoch": 4.39, "learning_rate": 1.3065765e-05, "loss": 2.018, "step": 1467 }, { "epoch": 4.4, "learning_rate": 1.306506e-05, "loss": 2.018, "step": 1468 }, { "epoch": 4.4, "learning_rate": 1.3064355e-05, "loss": 2.0159, "step": 1469 }, { "epoch": 4.4, "learning_rate": 1.306365e-05, "loss": 2.0183, "step": 1470 }, { "epoch": 4.41, "learning_rate": 1.3062945e-05, "loss": 2.0199, "step": 1471 }, { "epoch": 4.41, "learning_rate": 1.3062240000000001e-05, "loss": 2.0153, "step": 1472 }, { "epoch": 4.41, "learning_rate": 1.3061535000000001e-05, "loss": 2.016, "step": 1473 }, { "epoch": 4.41, "learning_rate": 1.306083e-05, "loss": 2.014, "step": 1474 }, { "epoch": 4.42, "learning_rate": 1.3060125e-05, "loss": 2.0183, "step": 1475 }, { "epoch": 4.42, "learning_rate": 1.305942e-05, "loss": 2.0175, "step": 1476 }, { "epoch": 4.42, "learning_rate": 1.3058715e-05, "loss": 2.0172, "step": 1477 }, { "epoch": 4.43, "learning_rate": 1.3058010000000002e-05, "loss": 2.0162, "step": 1478 }, { "epoch": 4.43, "learning_rate": 1.3057305000000002e-05, "loss": 2.0136, "step": 1479 }, { "epoch": 4.43, "learning_rate": 1.3056600000000001e-05, "loss": 2.0144, "step": 1480 }, { "epoch": 4.43, "learning_rate": 1.3055895000000001e-05, "loss": 2.0148, "step": 1481 }, { "epoch": 4.44, "learning_rate": 1.305519e-05, "loss": 2.0146, "step": 1482 }, { "epoch": 4.44, "learning_rate": 1.3054484999999999e-05, "loss": 2.0108, "step": 1483 }, { "epoch": 4.44, "learning_rate": 1.305378e-05, "loss": 2.015, "step": 1484 }, { "epoch": 4.45, "learning_rate": 1.3053075e-05, "loss": 2.0148, "step": 1485 }, { "epoch": 4.45, "learning_rate": 1.305237e-05, "loss": 2.0144, "step": 1486 }, { "epoch": 4.45, "learning_rate": 1.3051665e-05, "loss": 2.0189, "step": 1487 }, { "epoch": 4.46, "learning_rate": 1.305096e-05, "loss": 2.0152, "step": 1488 }, { "epoch": 4.46, "learning_rate": 1.3050255e-05, "loss": 2.0137, "step": 1489 }, { "epoch": 4.46, "learning_rate": 1.3049550000000001e-05, "loss": 2.0127, "step": 1490 }, { "epoch": 4.46, "learning_rate": 1.3048845000000001e-05, "loss": 2.0163, "step": 1491 }, { "epoch": 4.47, "learning_rate": 1.304814e-05, "loss": 2.0135, "step": 1492 }, { "epoch": 4.47, "learning_rate": 1.3047435e-05, "loss": 2.0138, "step": 1493 }, { "epoch": 4.47, "learning_rate": 1.304673e-05, "loss": 2.0149, "step": 1494 }, { "epoch": 4.48, "learning_rate": 1.3046025e-05, "loss": 2.0118, "step": 1495 }, { "epoch": 4.48, "learning_rate": 1.304532e-05, "loss": 2.0091, "step": 1496 }, { "epoch": 4.48, "learning_rate": 1.3044615000000001e-05, "loss": 2.0105, "step": 1497 }, { "epoch": 4.49, "learning_rate": 1.3043910000000001e-05, "loss": 2.0154, "step": 1498 }, { "epoch": 4.49, "learning_rate": 1.3043205000000001e-05, "loss": 2.0116, "step": 1499 }, { "epoch": 4.49, "learning_rate": 1.3042500000000001e-05, "loss": 2.0123, "step": 1500 }, { "epoch": 4.49, "eval_accuracy": 0.0007537227348993289, "eval_loss": 1.9082914590835571, "eval_runtime": 28.7685, "eval_samples_per_second": 10.359, "eval_steps_per_second": 0.66, "step": 1500 }, { "epoch": 4.49, "learning_rate": 1.3041795e-05, "loss": 2.0104, "step": 1501 }, { "epoch": 4.5, "learning_rate": 1.304109e-05, "loss": 2.0095, "step": 1502 }, { "epoch": 4.5, "learning_rate": 1.3040385e-05, "loss": 2.0137, "step": 1503 }, { "epoch": 4.5, "learning_rate": 1.303968e-05, "loss": 2.0109, "step": 1504 }, { "epoch": 4.51, "learning_rate": 1.3038975e-05, "loss": 2.0106, "step": 1505 }, { "epoch": 4.51, "learning_rate": 1.303827e-05, "loss": 2.0108, "step": 1506 }, { "epoch": 4.51, "learning_rate": 1.3037565e-05, "loss": 2.0109, "step": 1507 }, { "epoch": 4.52, "learning_rate": 1.303686e-05, "loss": 2.0107, "step": 1508 }, { "epoch": 4.52, "learning_rate": 1.3036155000000001e-05, "loss": 2.0093, "step": 1509 }, { "epoch": 4.52, "learning_rate": 1.303545e-05, "loss": 2.0083, "step": 1510 }, { "epoch": 4.52, "learning_rate": 1.3034745e-05, "loss": 2.0118, "step": 1511 }, { "epoch": 4.53, "learning_rate": 1.303404e-05, "loss": 2.0086, "step": 1512 }, { "epoch": 4.53, "learning_rate": 1.3033335e-05, "loss": 2.0088, "step": 1513 }, { "epoch": 4.53, "learning_rate": 1.303263e-05, "loss": 2.0092, "step": 1514 }, { "epoch": 4.54, "learning_rate": 1.3031925000000001e-05, "loss": 2.009, "step": 1515 }, { "epoch": 4.54, "learning_rate": 1.3031220000000001e-05, "loss": 2.0101, "step": 1516 }, { "epoch": 4.54, "learning_rate": 1.3030515000000001e-05, "loss": 2.0079, "step": 1517 }, { "epoch": 4.55, "learning_rate": 1.3029810000000001e-05, "loss": 2.0075, "step": 1518 }, { "epoch": 4.55, "learning_rate": 1.3029105e-05, "loss": 2.0048, "step": 1519 }, { "epoch": 4.55, "learning_rate": 1.30284e-05, "loss": 2.0059, "step": 1520 }, { "epoch": 4.55, "learning_rate": 1.3027695000000002e-05, "loss": 2.0086, "step": 1521 }, { "epoch": 4.56, "learning_rate": 1.3026990000000002e-05, "loss": 2.0077, "step": 1522 }, { "epoch": 4.56, "learning_rate": 1.3026285e-05, "loss": 2.0067, "step": 1523 }, { "epoch": 4.56, "learning_rate": 1.302558e-05, "loss": 2.0095, "step": 1524 }, { "epoch": 4.57, "learning_rate": 1.3024875e-05, "loss": 2.007, "step": 1525 }, { "epoch": 4.57, "learning_rate": 1.302417e-05, "loss": 2.0076, "step": 1526 }, { "epoch": 4.57, "learning_rate": 1.3023465e-05, "loss": 2.0061, "step": 1527 }, { "epoch": 4.58, "learning_rate": 1.302276e-05, "loss": 2.0058, "step": 1528 }, { "epoch": 4.58, "learning_rate": 1.3022055e-05, "loss": 2.0083, "step": 1529 }, { "epoch": 4.58, "learning_rate": 1.302135e-05, "loss": 2.0063, "step": 1530 }, { "epoch": 4.58, "learning_rate": 1.3020645e-05, "loss": 2.0068, "step": 1531 }, { "epoch": 4.59, "learning_rate": 1.301994e-05, "loss": 2.0053, "step": 1532 }, { "epoch": 4.59, "learning_rate": 1.3019235e-05, "loss": 2.0081, "step": 1533 }, { "epoch": 4.59, "learning_rate": 1.3018530000000001e-05, "loss": 2.0066, "step": 1534 }, { "epoch": 4.6, "learning_rate": 1.3017825000000001e-05, "loss": 2.0048, "step": 1535 }, { "epoch": 4.6, "learning_rate": 1.301712e-05, "loss": 2.005, "step": 1536 }, { "epoch": 4.6, "learning_rate": 1.3016415e-05, "loss": 2.006, "step": 1537 }, { "epoch": 4.61, "learning_rate": 1.301571e-05, "loss": 2.0038, "step": 1538 }, { "epoch": 4.61, "learning_rate": 1.3015005e-05, "loss": 2.0041, "step": 1539 }, { "epoch": 4.61, "learning_rate": 1.3014300000000002e-05, "loss": 2.0027, "step": 1540 }, { "epoch": 4.61, "learning_rate": 1.3013595000000002e-05, "loss": 2.0032, "step": 1541 }, { "epoch": 4.62, "learning_rate": 1.3012890000000001e-05, "loss": 2.0013, "step": 1542 }, { "epoch": 4.62, "learning_rate": 1.3012185e-05, "loss": 2.0043, "step": 1543 }, { "epoch": 4.62, "learning_rate": 1.301148e-05, "loss": 2.005, "step": 1544 }, { "epoch": 4.63, "learning_rate": 1.3010774999999999e-05, "loss": 2.0046, "step": 1545 }, { "epoch": 4.63, "learning_rate": 1.301007e-05, "loss": 2.0002, "step": 1546 }, { "epoch": 4.63, "learning_rate": 1.3009365e-05, "loss": 2.0032, "step": 1547 }, { "epoch": 4.64, "learning_rate": 1.300866e-05, "loss": 2.0031, "step": 1548 }, { "epoch": 4.64, "learning_rate": 1.3007955e-05, "loss": 1.9991, "step": 1549 }, { "epoch": 4.64, "learning_rate": 1.300725e-05, "loss": 2.0035, "step": 1550 }, { "epoch": 4.64, "learning_rate": 1.3006545e-05, "loss": 2.0056, "step": 1551 }, { "epoch": 4.65, "learning_rate": 1.3005840000000001e-05, "loss": 2.0037, "step": 1552 }, { "epoch": 4.65, "learning_rate": 1.3005135000000001e-05, "loss": 1.9987, "step": 1553 }, { "epoch": 4.65, "learning_rate": 1.300443e-05, "loss": 1.999, "step": 1554 }, { "epoch": 4.66, "learning_rate": 1.3003725e-05, "loss": 2.003, "step": 1555 }, { "epoch": 4.66, "learning_rate": 1.300302e-05, "loss": 1.9964, "step": 1556 }, { "epoch": 4.66, "learning_rate": 1.3002315e-05, "loss": 2.0006, "step": 1557 }, { "epoch": 4.67, "learning_rate": 1.3001610000000002e-05, "loss": 2.0003, "step": 1558 }, { "epoch": 4.67, "learning_rate": 1.3000905000000002e-05, "loss": 1.9989, "step": 1559 }, { "epoch": 4.67, "learning_rate": 1.3000200000000001e-05, "loss": 1.9993, "step": 1560 }, { "epoch": 4.67, "learning_rate": 1.2999495000000001e-05, "loss": 2.001, "step": 1561 }, { "epoch": 4.68, "learning_rate": 1.2998790000000001e-05, "loss": 2.0022, "step": 1562 }, { "epoch": 4.68, "learning_rate": 1.2998084999999999e-05, "loss": 2.0003, "step": 1563 }, { "epoch": 4.68, "learning_rate": 1.299738e-05, "loss": 2.0025, "step": 1564 }, { "epoch": 4.69, "learning_rate": 1.2996675e-05, "loss": 2.0009, "step": 1565 }, { "epoch": 4.69, "learning_rate": 1.299597e-05, "loss": 1.9984, "step": 1566 }, { "epoch": 4.69, "learning_rate": 1.2995265e-05, "loss": 2.0001, "step": 1567 }, { "epoch": 4.7, "learning_rate": 1.299456e-05, "loss": 1.9977, "step": 1568 }, { "epoch": 4.7, "learning_rate": 1.2993855e-05, "loss": 1.9984, "step": 1569 }, { "epoch": 4.7, "learning_rate": 1.2993150000000001e-05, "loss": 1.9986, "step": 1570 }, { "epoch": 4.7, "learning_rate": 1.2992445000000001e-05, "loss": 1.9987, "step": 1571 }, { "epoch": 4.71, "learning_rate": 1.299174e-05, "loss": 1.9976, "step": 1572 }, { "epoch": 4.71, "learning_rate": 1.2991035e-05, "loss": 1.9958, "step": 1573 }, { "epoch": 4.71, "learning_rate": 1.299033e-05, "loss": 1.9988, "step": 1574 }, { "epoch": 4.72, "learning_rate": 1.2989625e-05, "loss": 1.9989, "step": 1575 }, { "epoch": 4.72, "learning_rate": 1.298892e-05, "loss": 1.9962, "step": 1576 }, { "epoch": 4.72, "learning_rate": 1.2988215000000001e-05, "loss": 1.9943, "step": 1577 }, { "epoch": 4.73, "learning_rate": 1.2987510000000001e-05, "loss": 1.9996, "step": 1578 }, { "epoch": 4.73, "learning_rate": 1.2986805000000001e-05, "loss": 1.9976, "step": 1579 }, { "epoch": 4.73, "learning_rate": 1.2986100000000001e-05, "loss": 1.9949, "step": 1580 }, { "epoch": 4.73, "learning_rate": 1.2985395e-05, "loss": 1.9982, "step": 1581 }, { "epoch": 4.74, "learning_rate": 1.298469e-05, "loss": 1.9989, "step": 1582 }, { "epoch": 4.74, "learning_rate": 1.2983985e-05, "loss": 1.9943, "step": 1583 }, { "epoch": 4.74, "learning_rate": 1.298328e-05, "loss": 1.9945, "step": 1584 }, { "epoch": 4.75, "learning_rate": 1.2982575e-05, "loss": 1.9955, "step": 1585 }, { "epoch": 4.75, "learning_rate": 1.298187e-05, "loss": 1.9983, "step": 1586 }, { "epoch": 4.75, "learning_rate": 1.2981165e-05, "loss": 1.9932, "step": 1587 }, { "epoch": 4.76, "learning_rate": 1.298046e-05, "loss": 1.9942, "step": 1588 }, { "epoch": 4.76, "learning_rate": 1.2979755000000001e-05, "loss": 1.9984, "step": 1589 }, { "epoch": 4.76, "learning_rate": 1.297905e-05, "loss": 1.9944, "step": 1590 }, { "epoch": 4.76, "learning_rate": 1.2978345e-05, "loss": 1.9979, "step": 1591 }, { "epoch": 4.77, "learning_rate": 1.297764e-05, "loss": 1.9967, "step": 1592 }, { "epoch": 4.77, "learning_rate": 1.2976935e-05, "loss": 1.9959, "step": 1593 }, { "epoch": 4.77, "learning_rate": 1.297623e-05, "loss": 1.9964, "step": 1594 }, { "epoch": 4.78, "learning_rate": 1.2975525000000001e-05, "loss": 1.9943, "step": 1595 }, { "epoch": 4.78, "learning_rate": 1.2974820000000001e-05, "loss": 1.9953, "step": 1596 }, { "epoch": 4.78, "learning_rate": 1.2974115000000001e-05, "loss": 1.9955, "step": 1597 }, { "epoch": 4.79, "learning_rate": 1.2973410000000001e-05, "loss": 1.9966, "step": 1598 }, { "epoch": 4.79, "learning_rate": 1.2972705e-05, "loss": 1.9955, "step": 1599 }, { "epoch": 4.79, "learning_rate": 1.2972e-05, "loss": 1.9929, "step": 1600 }, { "epoch": 4.79, "eval_accuracy": 0.000779939177852349, "eval_loss": 1.8949816226959229, "eval_runtime": 28.9264, "eval_samples_per_second": 10.302, "eval_steps_per_second": 0.657, "step": 1600 }, { "epoch": 4.79, "learning_rate": 1.2971295e-05, "loss": 1.9927, "step": 1601 }, { "epoch": 4.8, "learning_rate": 1.2970590000000002e-05, "loss": 1.9927, "step": 1602 }, { "epoch": 4.8, "learning_rate": 1.2969885e-05, "loss": 1.996, "step": 1603 }, { "epoch": 4.8, "learning_rate": 1.296918e-05, "loss": 1.9936, "step": 1604 }, { "epoch": 4.81, "learning_rate": 1.2968475e-05, "loss": 1.9926, "step": 1605 }, { "epoch": 4.81, "learning_rate": 1.296777e-05, "loss": 1.9934, "step": 1606 }, { "epoch": 4.81, "learning_rate": 1.2967065e-05, "loss": 1.9945, "step": 1607 }, { "epoch": 4.82, "learning_rate": 1.296636e-05, "loss": 1.9927, "step": 1608 }, { "epoch": 4.82, "learning_rate": 1.2965655e-05, "loss": 1.9922, "step": 1609 }, { "epoch": 4.82, "learning_rate": 1.296495e-05, "loss": 1.9898, "step": 1610 }, { "epoch": 4.82, "learning_rate": 1.2964245e-05, "loss": 1.9884, "step": 1611 }, { "epoch": 4.83, "learning_rate": 1.296354e-05, "loss": 1.9962, "step": 1612 }, { "epoch": 4.83, "learning_rate": 1.2962835e-05, "loss": 1.9916, "step": 1613 }, { "epoch": 4.83, "learning_rate": 1.2962130000000001e-05, "loss": 1.9887, "step": 1614 }, { "epoch": 4.84, "learning_rate": 1.2961425000000001e-05, "loss": 1.992, "step": 1615 }, { "epoch": 4.84, "learning_rate": 1.296072e-05, "loss": 1.9911, "step": 1616 }, { "epoch": 4.84, "learning_rate": 1.2960015e-05, "loss": 1.9917, "step": 1617 }, { "epoch": 4.85, "learning_rate": 1.295931e-05, "loss": 1.9921, "step": 1618 }, { "epoch": 4.85, "learning_rate": 1.2958605e-05, "loss": 1.9908, "step": 1619 }, { "epoch": 4.85, "learning_rate": 1.2957900000000002e-05, "loss": 1.9906, "step": 1620 }, { "epoch": 4.85, "learning_rate": 1.2957195000000002e-05, "loss": 1.9879, "step": 1621 }, { "epoch": 4.86, "learning_rate": 1.2956490000000001e-05, "loss": 1.9896, "step": 1622 }, { "epoch": 4.86, "learning_rate": 1.2955785e-05, "loss": 1.9909, "step": 1623 }, { "epoch": 4.86, "learning_rate": 1.295508e-05, "loss": 1.9888, "step": 1624 }, { "epoch": 4.87, "learning_rate": 1.2954374999999999e-05, "loss": 1.9885, "step": 1625 }, { "epoch": 4.87, "learning_rate": 1.295367e-05, "loss": 1.991, "step": 1626 }, { "epoch": 4.87, "learning_rate": 1.2952965e-05, "loss": 1.9891, "step": 1627 }, { "epoch": 4.88, "learning_rate": 1.295226e-05, "loss": 1.9883, "step": 1628 }, { "epoch": 4.88, "learning_rate": 1.2951555e-05, "loss": 1.9902, "step": 1629 }, { "epoch": 4.88, "learning_rate": 1.295085e-05, "loss": 1.9905, "step": 1630 }, { "epoch": 4.88, "learning_rate": 1.2950145e-05, "loss": 1.9888, "step": 1631 }, { "epoch": 4.89, "learning_rate": 1.2949440000000001e-05, "loss": 1.9865, "step": 1632 }, { "epoch": 4.89, "learning_rate": 1.2948735000000001e-05, "loss": 1.9878, "step": 1633 }, { "epoch": 4.89, "learning_rate": 1.294803e-05, "loss": 1.9903, "step": 1634 }, { "epoch": 4.9, "learning_rate": 1.2947325e-05, "loss": 1.9896, "step": 1635 }, { "epoch": 4.9, "learning_rate": 1.294662e-05, "loss": 1.9873, "step": 1636 }, { "epoch": 4.9, "learning_rate": 1.2945915e-05, "loss": 1.9846, "step": 1637 }, { "epoch": 4.91, "learning_rate": 1.2945210000000002e-05, "loss": 1.9854, "step": 1638 }, { "epoch": 4.91, "learning_rate": 1.2944505000000002e-05, "loss": 1.9868, "step": 1639 }, { "epoch": 4.91, "learning_rate": 1.2943800000000001e-05, "loss": 1.9897, "step": 1640 }, { "epoch": 4.91, "learning_rate": 1.2943095000000001e-05, "loss": 1.9863, "step": 1641 }, { "epoch": 4.92, "learning_rate": 1.2942390000000001e-05, "loss": 1.9885, "step": 1642 }, { "epoch": 4.92, "learning_rate": 1.2941685e-05, "loss": 1.9845, "step": 1643 }, { "epoch": 4.92, "learning_rate": 1.294098e-05, "loss": 1.9877, "step": 1644 }, { "epoch": 4.93, "learning_rate": 1.2940275e-05, "loss": 1.986, "step": 1645 }, { "epoch": 4.93, "learning_rate": 1.293957e-05, "loss": 1.9872, "step": 1646 }, { "epoch": 4.93, "learning_rate": 1.2938865e-05, "loss": 1.9854, "step": 1647 }, { "epoch": 4.94, "learning_rate": 1.293816e-05, "loss": 1.9866, "step": 1648 }, { "epoch": 4.94, "learning_rate": 1.2937455e-05, "loss": 1.9863, "step": 1649 }, { "epoch": 4.94, "learning_rate": 1.293675e-05, "loss": 1.9849, "step": 1650 }, { "epoch": 4.94, "learning_rate": 1.2936045000000001e-05, "loss": 1.9851, "step": 1651 }, { "epoch": 4.95, "learning_rate": 1.293534e-05, "loss": 1.9859, "step": 1652 }, { "epoch": 4.95, "learning_rate": 1.2934635e-05, "loss": 1.9872, "step": 1653 }, { "epoch": 4.95, "learning_rate": 1.293393e-05, "loss": 1.9859, "step": 1654 }, { "epoch": 4.96, "learning_rate": 1.2933225e-05, "loss": 1.9878, "step": 1655 }, { "epoch": 4.96, "learning_rate": 1.293252e-05, "loss": 1.9838, "step": 1656 }, { "epoch": 4.96, "learning_rate": 1.2931815000000001e-05, "loss": 1.9852, "step": 1657 }, { "epoch": 4.97, "learning_rate": 1.2931110000000001e-05, "loss": 1.9826, "step": 1658 }, { "epoch": 4.97, "learning_rate": 1.2930405000000001e-05, "loss": 1.9834, "step": 1659 }, { "epoch": 4.97, "learning_rate": 1.2929700000000001e-05, "loss": 1.9837, "step": 1660 }, { "epoch": 4.97, "learning_rate": 1.2928995e-05, "loss": 1.9833, "step": 1661 }, { "epoch": 4.98, "learning_rate": 1.292829e-05, "loss": 1.9826, "step": 1662 }, { "epoch": 4.98, "learning_rate": 1.2927585000000002e-05, "loss": 1.9814, "step": 1663 }, { "epoch": 4.98, "learning_rate": 1.292688e-05, "loss": 1.9803, "step": 1664 }, { "epoch": 4.99, "learning_rate": 1.2926175e-05, "loss": 1.982, "step": 1665 }, { "epoch": 4.99, "learning_rate": 1.292547e-05, "loss": 1.9823, "step": 1666 }, { "epoch": 4.99, "learning_rate": 1.2924765e-05, "loss": 1.9815, "step": 1667 }, { "epoch": 4.99, "learning_rate": 1.292406e-05, "loss": 1.9832, "step": 1668 }, { "epoch": 5.0, "learning_rate": 1.2923355000000001e-05, "loss": 1.9859, "step": 1669 }, { "epoch": 5.0, "learning_rate": 1.292265e-05, "loss": 1.9858, "step": 1670 }, { "epoch": 5.0, "learning_rate": 1.2921945e-05, "loss": 1.9822, "step": 1671 }, { "epoch": 5.01, "learning_rate": 1.292124e-05, "loss": 1.9809, "step": 1672 }, { "epoch": 5.01, "learning_rate": 1.2920535e-05, "loss": 1.986, "step": 1673 }, { "epoch": 5.01, "learning_rate": 1.291983e-05, "loss": 1.9818, "step": 1674 }, { "epoch": 5.02, "learning_rate": 1.2919125000000001e-05, "loss": 1.9813, "step": 1675 }, { "epoch": 5.02, "learning_rate": 1.2918420000000001e-05, "loss": 1.9841, "step": 1676 }, { "epoch": 5.02, "learning_rate": 1.2917715000000001e-05, "loss": 1.9815, "step": 1677 }, { "epoch": 5.02, "learning_rate": 1.2917010000000001e-05, "loss": 1.9809, "step": 1678 }, { "epoch": 5.03, "learning_rate": 1.2916305e-05, "loss": 1.9808, "step": 1679 }, { "epoch": 5.03, "learning_rate": 1.29156e-05, "loss": 1.9816, "step": 1680 }, { "epoch": 5.03, "learning_rate": 1.2914895e-05, "loss": 1.9797, "step": 1681 }, { "epoch": 5.04, "learning_rate": 1.2914190000000002e-05, "loss": 1.984, "step": 1682 }, { "epoch": 5.04, "learning_rate": 1.2913485000000002e-05, "loss": 1.9808, "step": 1683 }, { "epoch": 5.04, "learning_rate": 1.291278e-05, "loss": 1.9805, "step": 1684 }, { "epoch": 5.05, "learning_rate": 1.2912075e-05, "loss": 1.9792, "step": 1685 }, { "epoch": 5.05, "learning_rate": 1.291137e-05, "loss": 1.9794, "step": 1686 }, { "epoch": 5.05, "learning_rate": 1.2910664999999999e-05, "loss": 1.9806, "step": 1687 }, { "epoch": 5.05, "learning_rate": 1.290996e-05, "loss": 1.9801, "step": 1688 }, { "epoch": 5.06, "learning_rate": 1.2909255e-05, "loss": 1.9777, "step": 1689 }, { "epoch": 5.06, "learning_rate": 1.290855e-05, "loss": 1.98, "step": 1690 }, { "epoch": 5.06, "learning_rate": 1.2907845e-05, "loss": 1.9799, "step": 1691 }, { "epoch": 5.07, "learning_rate": 1.290714e-05, "loss": 1.9766, "step": 1692 }, { "epoch": 5.07, "learning_rate": 1.2906435e-05, "loss": 1.9809, "step": 1693 }, { "epoch": 5.07, "learning_rate": 1.2905730000000001e-05, "loss": 1.9811, "step": 1694 }, { "epoch": 5.08, "learning_rate": 1.2905025000000001e-05, "loss": 1.9801, "step": 1695 }, { "epoch": 5.08, "learning_rate": 1.290432e-05, "loss": 1.9766, "step": 1696 }, { "epoch": 5.08, "learning_rate": 1.2903615e-05, "loss": 1.9767, "step": 1697 }, { "epoch": 5.08, "learning_rate": 1.290291e-05, "loss": 1.9764, "step": 1698 }, { "epoch": 5.09, "learning_rate": 1.2902205e-05, "loss": 1.9775, "step": 1699 }, { "epoch": 5.09, "learning_rate": 1.2901500000000002e-05, "loss": 1.9811, "step": 1700 }, { "epoch": 5.09, "eval_accuracy": 0.0007930473993288591, "eval_loss": 1.883575677871704, "eval_runtime": 38.2512, "eval_samples_per_second": 7.791, "eval_steps_per_second": 0.497, "step": 1700 }, { "epoch": 5.09, "learning_rate": 1.2900795000000002e-05, "loss": 1.9771, "step": 1701 }, { "epoch": 5.1, "learning_rate": 1.2900090000000001e-05, "loss": 1.9774, "step": 1702 }, { "epoch": 5.1, "learning_rate": 1.2899385000000001e-05, "loss": 1.9789, "step": 1703 }, { "epoch": 5.1, "learning_rate": 1.289868e-05, "loss": 1.9769, "step": 1704 }, { "epoch": 5.11, "learning_rate": 1.2897974999999999e-05, "loss": 1.9749, "step": 1705 }, { "epoch": 5.11, "learning_rate": 1.289727e-05, "loss": 1.9771, "step": 1706 }, { "epoch": 5.11, "learning_rate": 1.2896565e-05, "loss": 1.9759, "step": 1707 }, { "epoch": 5.11, "learning_rate": 1.289586e-05, "loss": 1.978, "step": 1708 }, { "epoch": 5.12, "learning_rate": 1.2895155e-05, "loss": 1.9785, "step": 1709 }, { "epoch": 5.12, "learning_rate": 1.289445e-05, "loss": 1.9779, "step": 1710 }, { "epoch": 5.12, "learning_rate": 1.2893745e-05, "loss": 1.9766, "step": 1711 }, { "epoch": 5.13, "learning_rate": 1.2893040000000001e-05, "loss": 1.9751, "step": 1712 }, { "epoch": 5.13, "learning_rate": 1.2892335000000001e-05, "loss": 1.9734, "step": 1713 }, { "epoch": 5.13, "learning_rate": 1.289163e-05, "loss": 1.9747, "step": 1714 }, { "epoch": 5.14, "learning_rate": 1.2890925e-05, "loss": 1.9766, "step": 1715 }, { "epoch": 5.14, "learning_rate": 1.289022e-05, "loss": 1.9767, "step": 1716 }, { "epoch": 5.14, "learning_rate": 1.2889515e-05, "loss": 1.9775, "step": 1717 }, { "epoch": 5.14, "learning_rate": 1.288881e-05, "loss": 1.9739, "step": 1718 }, { "epoch": 5.15, "learning_rate": 1.2888105000000002e-05, "loss": 1.9761, "step": 1719 }, { "epoch": 5.15, "learning_rate": 1.2887400000000001e-05, "loss": 1.9761, "step": 1720 }, { "epoch": 5.15, "learning_rate": 1.2886695000000001e-05, "loss": 1.9763, "step": 1721 }, { "epoch": 5.16, "learning_rate": 1.2885990000000001e-05, "loss": 1.9746, "step": 1722 }, { "epoch": 5.16, "learning_rate": 1.2885285e-05, "loss": 1.9769, "step": 1723 }, { "epoch": 5.16, "learning_rate": 1.2884579999999999e-05, "loss": 1.9755, "step": 1724 }, { "epoch": 5.17, "learning_rate": 1.2883875e-05, "loss": 1.9744, "step": 1725 }, { "epoch": 5.17, "learning_rate": 1.288317e-05, "loss": 1.9725, "step": 1726 }, { "epoch": 5.17, "learning_rate": 1.2882465e-05, "loss": 1.976, "step": 1727 }, { "epoch": 5.17, "learning_rate": 1.288176e-05, "loss": 1.9747, "step": 1728 }, { "epoch": 5.18, "learning_rate": 1.2881055e-05, "loss": 1.9711, "step": 1729 }, { "epoch": 5.18, "learning_rate": 1.288035e-05, "loss": 1.9739, "step": 1730 }, { "epoch": 5.18, "learning_rate": 1.2879645000000001e-05, "loss": 1.9733, "step": 1731 }, { "epoch": 5.19, "learning_rate": 1.287894e-05, "loss": 1.9728, "step": 1732 }, { "epoch": 5.19, "learning_rate": 1.2878235e-05, "loss": 1.9742, "step": 1733 }, { "epoch": 5.19, "learning_rate": 1.287753e-05, "loss": 1.9744, "step": 1734 }, { "epoch": 5.2, "learning_rate": 1.2876825e-05, "loss": 1.9727, "step": 1735 }, { "epoch": 5.2, "learning_rate": 1.287612e-05, "loss": 1.9701, "step": 1736 }, { "epoch": 5.2, "learning_rate": 1.2875415000000001e-05, "loss": 1.9753, "step": 1737 }, { "epoch": 5.2, "learning_rate": 1.2874710000000001e-05, "loss": 1.9705, "step": 1738 }, { "epoch": 5.21, "learning_rate": 1.2874005000000001e-05, "loss": 1.9734, "step": 1739 }, { "epoch": 5.21, "learning_rate": 1.2873300000000001e-05, "loss": 1.972, "step": 1740 }, { "epoch": 5.21, "learning_rate": 1.2872595e-05, "loss": 1.974, "step": 1741 }, { "epoch": 5.22, "learning_rate": 1.287189e-05, "loss": 1.9743, "step": 1742 }, { "epoch": 5.22, "learning_rate": 1.2871185000000002e-05, "loss": 1.974, "step": 1743 }, { "epoch": 5.22, "learning_rate": 1.287048e-05, "loss": 1.9694, "step": 1744 }, { "epoch": 5.23, "learning_rate": 1.2869775e-05, "loss": 1.972, "step": 1745 }, { "epoch": 5.23, "learning_rate": 1.286907e-05, "loss": 1.9708, "step": 1746 }, { "epoch": 5.23, "learning_rate": 1.2868365e-05, "loss": 1.9738, "step": 1747 }, { "epoch": 5.23, "learning_rate": 1.286766e-05, "loss": 1.9715, "step": 1748 }, { "epoch": 5.24, "learning_rate": 1.2866955000000001e-05, "loss": 1.975, "step": 1749 }, { "epoch": 5.24, "learning_rate": 1.286625e-05, "loss": 1.9735, "step": 1750 }, { "epoch": 5.24, "learning_rate": 1.2865545e-05, "loss": 1.9706, "step": 1751 }, { "epoch": 5.25, "learning_rate": 1.286484e-05, "loss": 1.973, "step": 1752 }, { "epoch": 5.25, "learning_rate": 1.2864135e-05, "loss": 1.9702, "step": 1753 }, { "epoch": 5.25, "learning_rate": 1.286343e-05, "loss": 1.9692, "step": 1754 }, { "epoch": 5.26, "learning_rate": 1.2862725e-05, "loss": 1.9703, "step": 1755 }, { "epoch": 5.26, "learning_rate": 1.2862020000000001e-05, "loss": 1.968, "step": 1756 }, { "epoch": 5.26, "learning_rate": 1.2861315000000001e-05, "loss": 1.9736, "step": 1757 }, { "epoch": 5.26, "learning_rate": 1.2860610000000001e-05, "loss": 1.9679, "step": 1758 }, { "epoch": 5.27, "learning_rate": 1.2859905e-05, "loss": 1.9717, "step": 1759 }, { "epoch": 5.27, "learning_rate": 1.28592e-05, "loss": 1.9696, "step": 1760 }, { "epoch": 5.27, "learning_rate": 1.2858495e-05, "loss": 1.9701, "step": 1761 }, { "epoch": 5.28, "learning_rate": 1.2857790000000002e-05, "loss": 1.9714, "step": 1762 }, { "epoch": 5.28, "learning_rate": 1.2857085000000002e-05, "loss": 1.9703, "step": 1763 }, { "epoch": 5.28, "learning_rate": 1.2856380000000001e-05, "loss": 1.9696, "step": 1764 }, { "epoch": 5.29, "learning_rate": 1.2855675e-05, "loss": 1.9701, "step": 1765 }, { "epoch": 5.29, "learning_rate": 1.285497e-05, "loss": 1.9678, "step": 1766 }, { "epoch": 5.29, "learning_rate": 1.2854264999999999e-05, "loss": 1.9677, "step": 1767 }, { "epoch": 5.29, "learning_rate": 1.285356e-05, "loss": 1.9695, "step": 1768 }, { "epoch": 5.3, "learning_rate": 1.2852855e-05, "loss": 1.9688, "step": 1769 }, { "epoch": 5.3, "learning_rate": 1.285215e-05, "loss": 1.9694, "step": 1770 }, { "epoch": 5.3, "learning_rate": 1.2851445e-05, "loss": 1.9679, "step": 1771 }, { "epoch": 5.31, "learning_rate": 1.285074e-05, "loss": 1.9699, "step": 1772 }, { "epoch": 5.31, "learning_rate": 1.2850035e-05, "loss": 1.9698, "step": 1773 }, { "epoch": 5.31, "learning_rate": 1.2849330000000001e-05, "loss": 1.9702, "step": 1774 }, { "epoch": 5.32, "learning_rate": 1.2848625000000001e-05, "loss": 1.9658, "step": 1775 }, { "epoch": 5.32, "learning_rate": 1.284792e-05, "loss": 1.9674, "step": 1776 }, { "epoch": 5.32, "learning_rate": 1.2847215e-05, "loss": 1.9716, "step": 1777 }, { "epoch": 5.32, "learning_rate": 1.284651e-05, "loss": 1.9652, "step": 1778 }, { "epoch": 5.33, "learning_rate": 1.2845805e-05, "loss": 1.9701, "step": 1779 }, { "epoch": 5.33, "learning_rate": 1.2845100000000002e-05, "loss": 1.9654, "step": 1780 }, { "epoch": 5.33, "learning_rate": 1.2844395000000002e-05, "loss": 1.965, "step": 1781 }, { "epoch": 5.34, "learning_rate": 1.2843690000000001e-05, "loss": 1.9662, "step": 1782 }, { "epoch": 5.34, "learning_rate": 1.2842985000000001e-05, "loss": 1.9666, "step": 1783 }, { "epoch": 5.34, "learning_rate": 1.2842280000000001e-05, "loss": 1.9657, "step": 1784 }, { "epoch": 5.35, "learning_rate": 1.2841574999999999e-05, "loss": 1.9692, "step": 1785 }, { "epoch": 5.35, "learning_rate": 1.284087e-05, "loss": 1.9661, "step": 1786 }, { "epoch": 5.35, "learning_rate": 1.2840165e-05, "loss": 1.9671, "step": 1787 }, { "epoch": 5.35, "learning_rate": 1.283946e-05, "loss": 1.9681, "step": 1788 }, { "epoch": 5.36, "learning_rate": 1.2838755e-05, "loss": 1.9653, "step": 1789 }, { "epoch": 5.36, "learning_rate": 1.283805e-05, "loss": 1.9678, "step": 1790 }, { "epoch": 5.36, "learning_rate": 1.2837345e-05, "loss": 1.9666, "step": 1791 }, { "epoch": 5.37, "learning_rate": 1.283664e-05, "loss": 1.9647, "step": 1792 }, { "epoch": 5.37, "learning_rate": 1.2835935000000001e-05, "loss": 1.9645, "step": 1793 }, { "epoch": 5.37, "learning_rate": 1.283523e-05, "loss": 1.965, "step": 1794 }, { "epoch": 5.38, "learning_rate": 1.2834525e-05, "loss": 1.9646, "step": 1795 }, { "epoch": 5.38, "learning_rate": 1.283382e-05, "loss": 1.9681, "step": 1796 }, { "epoch": 5.38, "learning_rate": 1.2833115e-05, "loss": 1.9684, "step": 1797 }, { "epoch": 5.38, "learning_rate": 1.283241e-05, "loss": 1.9648, "step": 1798 }, { "epoch": 5.39, "learning_rate": 1.2831705000000002e-05, "loss": 1.9663, "step": 1799 }, { "epoch": 5.39, "learning_rate": 1.2831000000000001e-05, "loss": 1.9639, "step": 1800 }, { "epoch": 5.39, "eval_accuracy": 0.0007537227348993289, "eval_loss": 1.8735462427139282, "eval_runtime": 34.1757, "eval_samples_per_second": 8.72, "eval_steps_per_second": 0.556, "step": 1800 }, { "epoch": 5.39, "learning_rate": 1.2830295000000001e-05, "loss": 1.9634, "step": 1801 }, { "epoch": 5.4, "learning_rate": 1.2829590000000001e-05, "loss": 1.9626, "step": 1802 }, { "epoch": 5.4, "learning_rate": 1.2828885e-05, "loss": 1.964, "step": 1803 }, { "epoch": 5.4, "learning_rate": 1.282818e-05, "loss": 1.9631, "step": 1804 }, { "epoch": 5.41, "learning_rate": 1.2827475e-05, "loss": 1.965, "step": 1805 }, { "epoch": 5.41, "learning_rate": 1.282677e-05, "loss": 1.964, "step": 1806 }, { "epoch": 5.41, "learning_rate": 1.2826065e-05, "loss": 1.9649, "step": 1807 }, { "epoch": 5.41, "learning_rate": 1.282536e-05, "loss": 1.9636, "step": 1808 }, { "epoch": 5.42, "learning_rate": 1.2824655e-05, "loss": 1.964, "step": 1809 }, { "epoch": 5.42, "learning_rate": 1.282395e-05, "loss": 1.9624, "step": 1810 }, { "epoch": 5.42, "learning_rate": 1.2823245000000001e-05, "loss": 1.9645, "step": 1811 }, { "epoch": 5.43, "learning_rate": 1.282254e-05, "loss": 1.965, "step": 1812 }, { "epoch": 5.43, "learning_rate": 1.2821835e-05, "loss": 1.9622, "step": 1813 }, { "epoch": 5.43, "learning_rate": 1.282113e-05, "loss": 1.963, "step": 1814 }, { "epoch": 5.44, "learning_rate": 1.2820425e-05, "loss": 1.9622, "step": 1815 }, { "epoch": 5.44, "learning_rate": 1.281972e-05, "loss": 1.9641, "step": 1816 }, { "epoch": 5.44, "learning_rate": 1.2819015000000001e-05, "loss": 1.9615, "step": 1817 }, { "epoch": 5.44, "learning_rate": 1.2818310000000001e-05, "loss": 1.9632, "step": 1818 }, { "epoch": 5.45, "learning_rate": 1.2817605000000001e-05, "loss": 1.962, "step": 1819 }, { "epoch": 5.45, "learning_rate": 1.2816900000000001e-05, "loss": 1.962, "step": 1820 }, { "epoch": 5.45, "learning_rate": 1.2816195e-05, "loss": 1.9612, "step": 1821 }, { "epoch": 5.46, "learning_rate": 1.281549e-05, "loss": 1.9616, "step": 1822 }, { "epoch": 5.46, "learning_rate": 1.2814785e-05, "loss": 1.9606, "step": 1823 }, { "epoch": 5.46, "learning_rate": 1.2814080000000002e-05, "loss": 1.9617, "step": 1824 }, { "epoch": 5.47, "learning_rate": 1.2813375e-05, "loss": 1.9583, "step": 1825 }, { "epoch": 5.47, "learning_rate": 1.281267e-05, "loss": 1.9596, "step": 1826 }, { "epoch": 5.47, "learning_rate": 1.2811965e-05, "loss": 1.9612, "step": 1827 }, { "epoch": 5.47, "learning_rate": 1.281126e-05, "loss": 1.9617, "step": 1828 }, { "epoch": 5.48, "learning_rate": 1.2810555000000001e-05, "loss": 1.9634, "step": 1829 }, { "epoch": 5.48, "learning_rate": 1.280985e-05, "loss": 1.9612, "step": 1830 }, { "epoch": 5.48, "learning_rate": 1.2809145e-05, "loss": 1.96, "step": 1831 }, { "epoch": 5.49, "learning_rate": 1.280844e-05, "loss": 1.9606, "step": 1832 }, { "epoch": 5.49, "learning_rate": 1.2807735e-05, "loss": 1.9595, "step": 1833 }, { "epoch": 5.49, "learning_rate": 1.280703e-05, "loss": 1.959, "step": 1834 }, { "epoch": 5.5, "learning_rate": 1.2806325e-05, "loss": 1.9605, "step": 1835 }, { "epoch": 5.5, "learning_rate": 1.2805620000000001e-05, "loss": 1.9581, "step": 1836 }, { "epoch": 5.5, "learning_rate": 1.2804915000000001e-05, "loss": 1.9604, "step": 1837 }, { "epoch": 5.5, "learning_rate": 1.2804210000000001e-05, "loss": 1.9566, "step": 1838 }, { "epoch": 5.51, "learning_rate": 1.2803505e-05, "loss": 1.9599, "step": 1839 }, { "epoch": 5.51, "learning_rate": 1.28028e-05, "loss": 1.96, "step": 1840 }, { "epoch": 5.51, "learning_rate": 1.2802095e-05, "loss": 1.961, "step": 1841 }, { "epoch": 5.52, "learning_rate": 1.2801390000000002e-05, "loss": 1.9595, "step": 1842 }, { "epoch": 5.52, "learning_rate": 1.2800685000000002e-05, "loss": 1.9593, "step": 1843 }, { "epoch": 5.52, "learning_rate": 1.2799980000000001e-05, "loss": 1.9573, "step": 1844 }, { "epoch": 5.52, "learning_rate": 1.2799275e-05, "loss": 1.9584, "step": 1845 }, { "epoch": 5.53, "learning_rate": 1.279857e-05, "loss": 1.96, "step": 1846 }, { "epoch": 5.53, "learning_rate": 1.2797864999999999e-05, "loss": 1.9599, "step": 1847 }, { "epoch": 5.53, "learning_rate": 1.279716e-05, "loss": 1.9595, "step": 1848 }, { "epoch": 5.54, "learning_rate": 1.2796455e-05, "loss": 1.9579, "step": 1849 }, { "epoch": 5.54, "learning_rate": 1.279575e-05, "loss": 1.9554, "step": 1850 }, { "epoch": 5.54, "learning_rate": 1.2795045e-05, "loss": 1.96, "step": 1851 }, { "epoch": 5.55, "learning_rate": 1.279434e-05, "loss": 1.9584, "step": 1852 }, { "epoch": 5.55, "learning_rate": 1.2793635e-05, "loss": 1.9579, "step": 1853 }, { "epoch": 5.55, "learning_rate": 1.2792930000000001e-05, "loss": 1.9585, "step": 1854 }, { "epoch": 5.55, "learning_rate": 1.2792225000000001e-05, "loss": 1.9596, "step": 1855 }, { "epoch": 5.56, "learning_rate": 1.279152e-05, "loss": 1.9557, "step": 1856 }, { "epoch": 5.56, "learning_rate": 1.2790815e-05, "loss": 1.9581, "step": 1857 }, { "epoch": 5.56, "learning_rate": 1.279011e-05, "loss": 1.9572, "step": 1858 }, { "epoch": 5.57, "learning_rate": 1.2789405e-05, "loss": 1.9542, "step": 1859 }, { "epoch": 5.57, "learning_rate": 1.27887e-05, "loss": 1.9575, "step": 1860 }, { "epoch": 5.57, "learning_rate": 1.2787995000000002e-05, "loss": 1.9539, "step": 1861 }, { "epoch": 5.58, "learning_rate": 1.2787290000000001e-05, "loss": 1.9567, "step": 1862 }, { "epoch": 5.58, "learning_rate": 1.2786585000000001e-05, "loss": 1.9573, "step": 1863 }, { "epoch": 5.58, "learning_rate": 1.2785880000000001e-05, "loss": 1.9578, "step": 1864 }, { "epoch": 5.58, "learning_rate": 1.2785174999999999e-05, "loss": 1.9556, "step": 1865 }, { "epoch": 5.59, "learning_rate": 1.278447e-05, "loss": 1.958, "step": 1866 }, { "epoch": 5.59, "learning_rate": 1.2783765e-05, "loss": 1.9587, "step": 1867 }, { "epoch": 5.59, "learning_rate": 1.278306e-05, "loss": 1.9584, "step": 1868 }, { "epoch": 5.6, "learning_rate": 1.2782355e-05, "loss": 1.9545, "step": 1869 }, { "epoch": 5.6, "learning_rate": 1.278165e-05, "loss": 1.9579, "step": 1870 }, { "epoch": 5.6, "learning_rate": 1.2780945e-05, "loss": 1.9528, "step": 1871 }, { "epoch": 5.61, "learning_rate": 1.278024e-05, "loss": 1.9569, "step": 1872 }, { "epoch": 5.61, "learning_rate": 1.2779535000000001e-05, "loss": 1.9545, "step": 1873 }, { "epoch": 5.61, "learning_rate": 1.277883e-05, "loss": 1.9575, "step": 1874 }, { "epoch": 5.61, "learning_rate": 1.2778125e-05, "loss": 1.954, "step": 1875 }, { "epoch": 5.62, "learning_rate": 1.277742e-05, "loss": 1.9555, "step": 1876 }, { "epoch": 5.62, "learning_rate": 1.2776715e-05, "loss": 1.953, "step": 1877 }, { "epoch": 5.62, "learning_rate": 1.277601e-05, "loss": 1.9549, "step": 1878 }, { "epoch": 5.63, "learning_rate": 1.2775305000000002e-05, "loss": 1.9574, "step": 1879 }, { "epoch": 5.63, "learning_rate": 1.2774600000000001e-05, "loss": 1.9541, "step": 1880 }, { "epoch": 5.63, "learning_rate": 1.2773895000000001e-05, "loss": 1.9555, "step": 1881 }, { "epoch": 5.64, "learning_rate": 1.2773190000000001e-05, "loss": 1.9523, "step": 1882 }, { "epoch": 5.64, "learning_rate": 1.2772485e-05, "loss": 1.9545, "step": 1883 }, { "epoch": 5.64, "learning_rate": 1.277178e-05, "loss": 1.9553, "step": 1884 }, { "epoch": 5.64, "learning_rate": 1.2771075000000002e-05, "loss": 1.952, "step": 1885 }, { "epoch": 5.65, "learning_rate": 1.277037e-05, "loss": 1.9532, "step": 1886 }, { "epoch": 5.65, "learning_rate": 1.2769665e-05, "loss": 1.9546, "step": 1887 }, { "epoch": 5.65, "learning_rate": 1.276896e-05, "loss": 1.9554, "step": 1888 }, { "epoch": 5.66, "learning_rate": 1.2768255e-05, "loss": 1.9555, "step": 1889 }, { "epoch": 5.66, "learning_rate": 1.276755e-05, "loss": 1.9536, "step": 1890 }, { "epoch": 5.66, "learning_rate": 1.2766845000000001e-05, "loss": 1.9528, "step": 1891 }, { "epoch": 5.67, "learning_rate": 1.276614e-05, "loss": 1.9547, "step": 1892 }, { "epoch": 5.67, "learning_rate": 1.2765435e-05, "loss": 1.954, "step": 1893 }, { "epoch": 5.67, "learning_rate": 1.276473e-05, "loss": 1.9543, "step": 1894 }, { "epoch": 5.67, "learning_rate": 1.2764025e-05, "loss": 1.9541, "step": 1895 }, { "epoch": 5.68, "learning_rate": 1.276332e-05, "loss": 1.9529, "step": 1896 }, { "epoch": 5.68, "learning_rate": 1.2762615e-05, "loss": 1.9541, "step": 1897 }, { "epoch": 5.68, "learning_rate": 1.2761910000000001e-05, "loss": 1.9518, "step": 1898 }, { "epoch": 5.69, "learning_rate": 1.2761205000000001e-05, "loss": 1.955, "step": 1899 }, { "epoch": 5.69, "learning_rate": 1.2760500000000001e-05, "loss": 1.9562, "step": 1900 }, { "epoch": 5.69, "eval_accuracy": 0.000786493288590604, "eval_loss": 1.8642175197601318, "eval_runtime": 33.4685, "eval_samples_per_second": 8.904, "eval_steps_per_second": 0.568, "step": 1900 }, { "epoch": 5.69, "learning_rate": 1.2759795e-05, "loss": 1.9508, "step": 1901 }, { "epoch": 5.7, "learning_rate": 1.275909e-05, "loss": 1.9529, "step": 1902 }, { "epoch": 5.7, "learning_rate": 1.2758385e-05, "loss": 1.9544, "step": 1903 }, { "epoch": 5.7, "learning_rate": 1.2757680000000002e-05, "loss": 1.9532, "step": 1904 }, { "epoch": 5.7, "learning_rate": 1.2756975000000002e-05, "loss": 1.9505, "step": 1905 }, { "epoch": 5.71, "learning_rate": 1.275627e-05, "loss": 1.9533, "step": 1906 }, { "epoch": 5.71, "learning_rate": 1.2755565e-05, "loss": 1.9503, "step": 1907 }, { "epoch": 5.71, "learning_rate": 1.275486e-05, "loss": 1.9485, "step": 1908 }, { "epoch": 5.72, "learning_rate": 1.2754155e-05, "loss": 1.9502, "step": 1909 }, { "epoch": 5.72, "learning_rate": 1.275345e-05, "loss": 1.9535, "step": 1910 }, { "epoch": 5.72, "learning_rate": 1.2752745e-05, "loss": 1.95, "step": 1911 }, { "epoch": 5.73, "learning_rate": 1.275204e-05, "loss": 1.9527, "step": 1912 }, { "epoch": 5.73, "learning_rate": 1.2751335e-05, "loss": 1.9497, "step": 1913 }, { "epoch": 5.73, "learning_rate": 1.275063e-05, "loss": 1.9534, "step": 1914 }, { "epoch": 5.73, "learning_rate": 1.2749925e-05, "loss": 1.9506, "step": 1915 }, { "epoch": 5.74, "learning_rate": 1.2749220000000001e-05, "loss": 1.951, "step": 1916 }, { "epoch": 5.74, "learning_rate": 1.2748515000000001e-05, "loss": 1.9494, "step": 1917 }, { "epoch": 5.74, "learning_rate": 1.2747810000000001e-05, "loss": 1.9497, "step": 1918 }, { "epoch": 5.75, "learning_rate": 1.2747105e-05, "loss": 1.9506, "step": 1919 }, { "epoch": 5.75, "learning_rate": 1.27464e-05, "loss": 1.9497, "step": 1920 }, { "epoch": 5.75, "learning_rate": 1.2745695e-05, "loss": 1.9485, "step": 1921 }, { "epoch": 5.76, "learning_rate": 1.2744990000000002e-05, "loss": 1.9499, "step": 1922 }, { "epoch": 5.76, "learning_rate": 1.2744285000000002e-05, "loss": 1.9492, "step": 1923 }, { "epoch": 5.76, "learning_rate": 1.2743580000000001e-05, "loss": 1.9517, "step": 1924 }, { "epoch": 5.76, "learning_rate": 1.2742875000000001e-05, "loss": 1.9476, "step": 1925 }, { "epoch": 5.77, "learning_rate": 1.274217e-05, "loss": 1.9505, "step": 1926 }, { "epoch": 5.77, "learning_rate": 1.2741464999999999e-05, "loss": 1.9486, "step": 1927 }, { "epoch": 5.77, "learning_rate": 1.274076e-05, "loss": 1.9491, "step": 1928 }, { "epoch": 5.78, "learning_rate": 1.2740055e-05, "loss": 1.9475, "step": 1929 }, { "epoch": 5.78, "learning_rate": 1.273935e-05, "loss": 1.9491, "step": 1930 }, { "epoch": 5.78, "learning_rate": 1.2738645e-05, "loss": 1.9499, "step": 1931 }, { "epoch": 5.79, "learning_rate": 1.273794e-05, "loss": 1.9496, "step": 1932 }, { "epoch": 5.79, "learning_rate": 1.2737235e-05, "loss": 1.9477, "step": 1933 }, { "epoch": 5.79, "learning_rate": 1.2736530000000001e-05, "loss": 1.9472, "step": 1934 }, { "epoch": 5.79, "learning_rate": 1.2735825000000001e-05, "loss": 1.9474, "step": 1935 }, { "epoch": 5.8, "learning_rate": 1.273512e-05, "loss": 1.9489, "step": 1936 }, { "epoch": 5.8, "learning_rate": 1.2734415e-05, "loss": 1.9488, "step": 1937 }, { "epoch": 5.8, "learning_rate": 1.273371e-05, "loss": 1.9524, "step": 1938 }, { "epoch": 5.81, "learning_rate": 1.2733005e-05, "loss": 1.9486, "step": 1939 }, { "epoch": 5.81, "learning_rate": 1.27323e-05, "loss": 1.9468, "step": 1940 }, { "epoch": 5.81, "learning_rate": 1.2731595000000002e-05, "loss": 1.9463, "step": 1941 }, { "epoch": 5.82, "learning_rate": 1.2730890000000001e-05, "loss": 1.9495, "step": 1942 }, { "epoch": 5.82, "learning_rate": 1.2730185000000001e-05, "loss": 1.9474, "step": 1943 }, { "epoch": 5.82, "learning_rate": 1.2729480000000001e-05, "loss": 1.9457, "step": 1944 }, { "epoch": 5.82, "learning_rate": 1.2728775e-05, "loss": 1.9504, "step": 1945 }, { "epoch": 5.83, "learning_rate": 1.2728069999999999e-05, "loss": 1.9488, "step": 1946 }, { "epoch": 5.83, "learning_rate": 1.2727365e-05, "loss": 1.9477, "step": 1947 }, { "epoch": 5.83, "learning_rate": 1.272666e-05, "loss": 1.9466, "step": 1948 }, { "epoch": 5.84, "learning_rate": 1.2725955e-05, "loss": 1.948, "step": 1949 }, { "epoch": 5.84, "learning_rate": 1.272525e-05, "loss": 1.9475, "step": 1950 }, { "epoch": 5.84, "learning_rate": 1.2724545e-05, "loss": 1.9452, "step": 1951 }, { "epoch": 5.85, "learning_rate": 1.272384e-05, "loss": 1.9446, "step": 1952 }, { "epoch": 5.85, "learning_rate": 1.2723135000000001e-05, "loss": 1.9469, "step": 1953 }, { "epoch": 5.85, "learning_rate": 1.272243e-05, "loss": 1.9451, "step": 1954 }, { "epoch": 5.85, "learning_rate": 1.2721725e-05, "loss": 1.9462, "step": 1955 }, { "epoch": 5.86, "learning_rate": 1.272102e-05, "loss": 1.9473, "step": 1956 }, { "epoch": 5.86, "learning_rate": 1.2720315e-05, "loss": 1.9423, "step": 1957 }, { "epoch": 5.86, "learning_rate": 1.271961e-05, "loss": 1.9463, "step": 1958 }, { "epoch": 5.87, "learning_rate": 1.2718905000000002e-05, "loss": 1.9471, "step": 1959 }, { "epoch": 5.87, "learning_rate": 1.2718200000000001e-05, "loss": 1.9456, "step": 1960 }, { "epoch": 5.87, "learning_rate": 1.2717495000000001e-05, "loss": 1.9452, "step": 1961 }, { "epoch": 5.88, "learning_rate": 1.2716790000000001e-05, "loss": 1.9459, "step": 1962 }, { "epoch": 5.88, "learning_rate": 1.2716085e-05, "loss": 1.9436, "step": 1963 }, { "epoch": 5.88, "learning_rate": 1.271538e-05, "loss": 1.9408, "step": 1964 }, { "epoch": 5.88, "learning_rate": 1.2714675e-05, "loss": 1.9443, "step": 1965 }, { "epoch": 5.89, "learning_rate": 1.271397e-05, "loss": 1.9441, "step": 1966 }, { "epoch": 5.89, "learning_rate": 1.2713265e-05, "loss": 1.9436, "step": 1967 }, { "epoch": 5.89, "learning_rate": 1.271256e-05, "loss": 1.9458, "step": 1968 }, { "epoch": 5.9, "learning_rate": 1.2711855e-05, "loss": 1.9461, "step": 1969 }, { "epoch": 5.9, "learning_rate": 1.271115e-05, "loss": 1.9462, "step": 1970 }, { "epoch": 5.9, "learning_rate": 1.2710445000000001e-05, "loss": 1.9448, "step": 1971 }, { "epoch": 5.91, "learning_rate": 1.270974e-05, "loss": 1.9436, "step": 1972 }, { "epoch": 5.91, "learning_rate": 1.2709035e-05, "loss": 1.9443, "step": 1973 }, { "epoch": 5.91, "learning_rate": 1.270833e-05, "loss": 1.9441, "step": 1974 }, { "epoch": 5.91, "learning_rate": 1.2707625e-05, "loss": 1.9437, "step": 1975 }, { "epoch": 5.92, "learning_rate": 1.270692e-05, "loss": 1.9441, "step": 1976 }, { "epoch": 5.92, "learning_rate": 1.2706215e-05, "loss": 1.9442, "step": 1977 }, { "epoch": 5.92, "learning_rate": 1.2705510000000001e-05, "loss": 1.9419, "step": 1978 }, { "epoch": 5.93, "learning_rate": 1.2704805000000001e-05, "loss": 1.944, "step": 1979 }, { "epoch": 5.93, "learning_rate": 1.2704100000000001e-05, "loss": 1.9443, "step": 1980 }, { "epoch": 5.93, "learning_rate": 1.2703395e-05, "loss": 1.9442, "step": 1981 }, { "epoch": 5.94, "learning_rate": 1.270269e-05, "loss": 1.944, "step": 1982 }, { "epoch": 5.94, "learning_rate": 1.2701985e-05, "loss": 1.9441, "step": 1983 }, { "epoch": 5.94, "learning_rate": 1.2701280000000002e-05, "loss": 1.9431, "step": 1984 }, { "epoch": 5.94, "learning_rate": 1.2700575000000002e-05, "loss": 1.9431, "step": 1985 }, { "epoch": 5.95, "learning_rate": 1.269987e-05, "loss": 1.9439, "step": 1986 }, { "epoch": 5.95, "learning_rate": 1.2699165e-05, "loss": 1.943, "step": 1987 }, { "epoch": 5.95, "learning_rate": 1.269846e-05, "loss": 1.9422, "step": 1988 }, { "epoch": 5.96, "learning_rate": 1.2697755e-05, "loss": 1.9414, "step": 1989 }, { "epoch": 5.96, "learning_rate": 1.269705e-05, "loss": 1.9454, "step": 1990 }, { "epoch": 5.96, "learning_rate": 1.2696345e-05, "loss": 1.9418, "step": 1991 }, { "epoch": 5.97, "learning_rate": 1.269564e-05, "loss": 1.9419, "step": 1992 }, { "epoch": 5.97, "learning_rate": 1.2694935e-05, "loss": 1.9433, "step": 1993 }, { "epoch": 5.97, "learning_rate": 1.269423e-05, "loss": 1.9414, "step": 1994 }, { "epoch": 5.97, "learning_rate": 1.2693525e-05, "loss": 1.9424, "step": 1995 }, { "epoch": 5.98, "learning_rate": 1.2692820000000001e-05, "loss": 1.9415, "step": 1996 }, { "epoch": 5.98, "learning_rate": 1.2692115000000001e-05, "loss": 1.9418, "step": 1997 }, { "epoch": 5.98, "learning_rate": 1.2691410000000001e-05, "loss": 1.9402, "step": 1998 }, { "epoch": 5.99, "learning_rate": 1.2690705e-05, "loss": 1.9438, "step": 1999 }, { "epoch": 5.99, "learning_rate": 1.269e-05, "loss": 1.94, "step": 2000 }, { "epoch": 5.99, "eval_accuracy": 0.000779939177852349, "eval_loss": 1.8559544086456299, "eval_runtime": 34.2874, "eval_samples_per_second": 8.691, "eval_steps_per_second": 0.554, "step": 2000 }, { "epoch": 5.99, "learning_rate": 1.2689295e-05, "loss": 1.9417, "step": 2001 }, { "epoch": 6.0, "learning_rate": 1.2688590000000002e-05, "loss": 1.9408, "step": 2002 }, { "epoch": 6.0, "learning_rate": 1.2687885000000002e-05, "loss": 1.9399, "step": 2003 }, { "epoch": 6.0, "learning_rate": 1.2687180000000001e-05, "loss": 1.9384, "step": 2004 }, { "epoch": 6.0, "learning_rate": 1.2686475000000001e-05, "loss": 1.9405, "step": 2005 }, { "epoch": 6.01, "learning_rate": 1.2685770000000001e-05, "loss": 1.9405, "step": 2006 }, { "epoch": 6.01, "learning_rate": 1.2685064999999999e-05, "loss": 1.9382, "step": 2007 }, { "epoch": 6.01, "learning_rate": 1.268436e-05, "loss": 1.9379, "step": 2008 }, { "epoch": 6.02, "learning_rate": 1.2683655e-05, "loss": 1.9377, "step": 2009 }, { "epoch": 6.02, "learning_rate": 1.268295e-05, "loss": 1.9392, "step": 2010 }, { "epoch": 6.02, "learning_rate": 1.2682245e-05, "loss": 1.9396, "step": 2011 }, { "epoch": 6.03, "learning_rate": 1.268154e-05, "loss": 1.9393, "step": 2012 }, { "epoch": 6.03, "learning_rate": 1.2680835e-05, "loss": 1.9412, "step": 2013 }, { "epoch": 6.03, "learning_rate": 1.268013e-05, "loss": 1.9395, "step": 2014 }, { "epoch": 6.03, "learning_rate": 1.2679425000000001e-05, "loss": 1.9437, "step": 2015 }, { "epoch": 6.04, "learning_rate": 1.267872e-05, "loss": 1.9388, "step": 2016 }, { "epoch": 6.04, "learning_rate": 1.2678015e-05, "loss": 1.9407, "step": 2017 }, { "epoch": 6.04, "learning_rate": 1.267731e-05, "loss": 1.9385, "step": 2018 }, { "epoch": 6.05, "learning_rate": 1.2676605e-05, "loss": 1.9399, "step": 2019 }, { "epoch": 6.05, "learning_rate": 1.26759e-05, "loss": 1.9395, "step": 2020 }, { "epoch": 6.05, "learning_rate": 1.2675195000000002e-05, "loss": 1.9385, "step": 2021 }, { "epoch": 6.06, "learning_rate": 1.2674490000000001e-05, "loss": 1.9388, "step": 2022 }, { "epoch": 6.06, "learning_rate": 1.2673785000000001e-05, "loss": 1.9367, "step": 2023 }, { "epoch": 6.06, "learning_rate": 1.2673080000000001e-05, "loss": 1.9372, "step": 2024 }, { "epoch": 6.06, "learning_rate": 1.2672375e-05, "loss": 1.9371, "step": 2025 }, { "epoch": 6.07, "learning_rate": 1.267167e-05, "loss": 1.9365, "step": 2026 }, { "epoch": 6.07, "learning_rate": 1.2670965e-05, "loss": 1.9412, "step": 2027 }, { "epoch": 6.07, "learning_rate": 1.267026e-05, "loss": 1.9368, "step": 2028 }, { "epoch": 6.08, "learning_rate": 1.2669555e-05, "loss": 1.9385, "step": 2029 }, { "epoch": 6.08, "learning_rate": 1.266885e-05, "loss": 1.9386, "step": 2030 }, { "epoch": 6.08, "learning_rate": 1.2668145e-05, "loss": 1.939, "step": 2031 }, { "epoch": 6.08, "learning_rate": 1.266744e-05, "loss": 1.9381, "step": 2032 }, { "epoch": 6.09, "learning_rate": 1.2666735000000001e-05, "loss": 1.9368, "step": 2033 }, { "epoch": 6.09, "learning_rate": 1.266603e-05, "loss": 1.9366, "step": 2034 }, { "epoch": 6.09, "learning_rate": 1.2665325e-05, "loss": 1.9394, "step": 2035 }, { "epoch": 6.1, "learning_rate": 1.266462e-05, "loss": 1.9373, "step": 2036 }, { "epoch": 6.1, "learning_rate": 1.2663915e-05, "loss": 1.9371, "step": 2037 }, { "epoch": 6.1, "learning_rate": 1.266321e-05, "loss": 1.9352, "step": 2038 }, { "epoch": 6.11, "learning_rate": 1.2662505000000002e-05, "loss": 1.9381, "step": 2039 }, { "epoch": 6.11, "learning_rate": 1.2661800000000001e-05, "loss": 1.9347, "step": 2040 }, { "epoch": 6.11, "learning_rate": 1.2661095000000001e-05, "loss": 1.9392, "step": 2041 }, { "epoch": 6.11, "learning_rate": 1.2660390000000001e-05, "loss": 1.9362, "step": 2042 }, { "epoch": 6.12, "learning_rate": 1.2659685e-05, "loss": 1.9354, "step": 2043 }, { "epoch": 6.12, "learning_rate": 1.265898e-05, "loss": 1.9367, "step": 2044 }, { "epoch": 6.12, "learning_rate": 1.2658275e-05, "loss": 1.9364, "step": 2045 }, { "epoch": 6.13, "learning_rate": 1.2657570000000002e-05, "loss": 1.9345, "step": 2046 }, { "epoch": 6.13, "learning_rate": 1.2656865e-05, "loss": 1.9353, "step": 2047 }, { "epoch": 6.13, "learning_rate": 1.265616e-05, "loss": 1.9388, "step": 2048 }, { "epoch": 6.14, "learning_rate": 1.2655455e-05, "loss": 1.936, "step": 2049 }, { "epoch": 6.14, "learning_rate": 1.265475e-05, "loss": 1.9374, "step": 2050 }, { "epoch": 6.14, "learning_rate": 1.2654045e-05, "loss": 1.9346, "step": 2051 }, { "epoch": 6.14, "learning_rate": 1.265334e-05, "loss": 1.9364, "step": 2052 }, { "epoch": 6.15, "learning_rate": 1.2652635e-05, "loss": 1.937, "step": 2053 }, { "epoch": 6.15, "learning_rate": 1.265193e-05, "loss": 1.9353, "step": 2054 }, { "epoch": 6.15, "learning_rate": 1.2651225e-05, "loss": 1.9354, "step": 2055 }, { "epoch": 6.16, "learning_rate": 1.265052e-05, "loss": 1.9386, "step": 2056 }, { "epoch": 6.16, "learning_rate": 1.2649815e-05, "loss": 1.9348, "step": 2057 }, { "epoch": 6.16, "learning_rate": 1.2649110000000001e-05, "loss": 1.9326, "step": 2058 }, { "epoch": 6.17, "learning_rate": 1.2648405000000001e-05, "loss": 1.9363, "step": 2059 }, { "epoch": 6.17, "learning_rate": 1.2647700000000001e-05, "loss": 1.9357, "step": 2060 }, { "epoch": 6.17, "learning_rate": 1.2646995e-05, "loss": 1.9372, "step": 2061 }, { "epoch": 6.17, "learning_rate": 1.264629e-05, "loss": 1.9338, "step": 2062 }, { "epoch": 6.18, "learning_rate": 1.2645585e-05, "loss": 1.9353, "step": 2063 }, { "epoch": 6.18, "learning_rate": 1.2644880000000002e-05, "loss": 1.9381, "step": 2064 }, { "epoch": 6.18, "learning_rate": 1.2644175000000002e-05, "loss": 1.9324, "step": 2065 }, { "epoch": 6.19, "learning_rate": 1.2643470000000001e-05, "loss": 1.9346, "step": 2066 }, { "epoch": 6.19, "learning_rate": 1.2642765e-05, "loss": 1.9304, "step": 2067 }, { "epoch": 6.19, "learning_rate": 1.264206e-05, "loss": 1.9309, "step": 2068 }, { "epoch": 6.2, "learning_rate": 1.2641355e-05, "loss": 1.9325, "step": 2069 }, { "epoch": 6.2, "learning_rate": 1.264065e-05, "loss": 1.9348, "step": 2070 }, { "epoch": 6.2, "learning_rate": 1.2639945e-05, "loss": 1.9344, "step": 2071 }, { "epoch": 6.2, "learning_rate": 1.263924e-05, "loss": 1.9356, "step": 2072 }, { "epoch": 6.21, "learning_rate": 1.2638535e-05, "loss": 1.9333, "step": 2073 }, { "epoch": 6.21, "learning_rate": 1.263783e-05, "loss": 1.9338, "step": 2074 }, { "epoch": 6.21, "learning_rate": 1.2637125e-05, "loss": 1.9352, "step": 2075 }, { "epoch": 6.22, "learning_rate": 1.2636420000000001e-05, "loss": 1.9342, "step": 2076 }, { "epoch": 6.22, "learning_rate": 1.2635715000000001e-05, "loss": 1.9337, "step": 2077 }, { "epoch": 6.22, "learning_rate": 1.2635010000000001e-05, "loss": 1.9346, "step": 2078 }, { "epoch": 6.23, "learning_rate": 1.2634305e-05, "loss": 1.9336, "step": 2079 }, { "epoch": 6.23, "learning_rate": 1.26336e-05, "loss": 1.9322, "step": 2080 }, { "epoch": 6.23, "learning_rate": 1.2632895e-05, "loss": 1.9351, "step": 2081 }, { "epoch": 6.23, "learning_rate": 1.263219e-05, "loss": 1.9309, "step": 2082 }, { "epoch": 6.24, "learning_rate": 1.2631485000000002e-05, "loss": 1.9307, "step": 2083 }, { "epoch": 6.24, "learning_rate": 1.2630780000000001e-05, "loss": 1.9315, "step": 2084 }, { "epoch": 6.24, "learning_rate": 1.2630075000000001e-05, "loss": 1.9336, "step": 2085 }, { "epoch": 6.25, "learning_rate": 1.2629370000000001e-05, "loss": 1.9341, "step": 2086 }, { "epoch": 6.25, "learning_rate": 1.2628664999999999e-05, "loss": 1.9332, "step": 2087 }, { "epoch": 6.25, "learning_rate": 1.2627959999999999e-05, "loss": 1.9327, "step": 2088 }, { "epoch": 6.26, "learning_rate": 1.2627255e-05, "loss": 1.9333, "step": 2089 }, { "epoch": 6.26, "learning_rate": 1.262655e-05, "loss": 1.9303, "step": 2090 }, { "epoch": 6.26, "learning_rate": 1.2625845e-05, "loss": 1.9336, "step": 2091 }, { "epoch": 6.26, "learning_rate": 1.262514e-05, "loss": 1.9318, "step": 2092 }, { "epoch": 6.27, "learning_rate": 1.2624435e-05, "loss": 1.9313, "step": 2093 }, { "epoch": 6.27, "learning_rate": 1.262373e-05, "loss": 1.9327, "step": 2094 }, { "epoch": 6.27, "learning_rate": 1.2623025000000001e-05, "loss": 1.9332, "step": 2095 }, { "epoch": 6.28, "learning_rate": 1.262232e-05, "loss": 1.9323, "step": 2096 }, { "epoch": 6.28, "learning_rate": 1.2621615e-05, "loss": 1.9313, "step": 2097 }, { "epoch": 6.28, "learning_rate": 1.262091e-05, "loss": 1.9304, "step": 2098 }, { "epoch": 6.29, "learning_rate": 1.2620205e-05, "loss": 1.9307, "step": 2099 }, { "epoch": 6.29, "learning_rate": 1.26195e-05, "loss": 1.9332, "step": 2100 }, { "epoch": 6.29, "eval_accuracy": 0.0007012898489932886, "eval_loss": 1.8483192920684814, "eval_runtime": 34.0883, "eval_samples_per_second": 8.742, "eval_steps_per_second": 0.557, "step": 2100 }, { "epoch": 6.29, "learning_rate": 1.2618795000000002e-05, "loss": 1.9334, "step": 2101 }, { "epoch": 6.29, "learning_rate": 1.2618090000000001e-05, "loss": 1.9307, "step": 2102 }, { "epoch": 6.3, "learning_rate": 1.2617385000000001e-05, "loss": 1.9307, "step": 2103 }, { "epoch": 6.3, "learning_rate": 1.2616680000000001e-05, "loss": 1.9327, "step": 2104 }, { "epoch": 6.3, "learning_rate": 1.2615975e-05, "loss": 1.9326, "step": 2105 }, { "epoch": 6.31, "learning_rate": 1.261527e-05, "loss": 1.9312, "step": 2106 }, { "epoch": 6.31, "learning_rate": 1.2614565e-05, "loss": 1.9337, "step": 2107 }, { "epoch": 6.31, "learning_rate": 1.261386e-05, "loss": 1.9298, "step": 2108 }, { "epoch": 6.32, "learning_rate": 1.2613155e-05, "loss": 1.9314, "step": 2109 }, { "epoch": 6.32, "learning_rate": 1.261245e-05, "loss": 1.9324, "step": 2110 }, { "epoch": 6.32, "learning_rate": 1.2611745e-05, "loss": 1.9315, "step": 2111 }, { "epoch": 6.32, "learning_rate": 1.261104e-05, "loss": 1.9317, "step": 2112 }, { "epoch": 6.33, "learning_rate": 1.2610335000000001e-05, "loss": 1.9288, "step": 2113 }, { "epoch": 6.33, "learning_rate": 1.260963e-05, "loss": 1.9281, "step": 2114 }, { "epoch": 6.33, "learning_rate": 1.2608925e-05, "loss": 1.9304, "step": 2115 }, { "epoch": 6.34, "learning_rate": 1.260822e-05, "loss": 1.9274, "step": 2116 }, { "epoch": 6.34, "learning_rate": 1.2607515e-05, "loss": 1.9318, "step": 2117 }, { "epoch": 6.34, "learning_rate": 1.260681e-05, "loss": 1.931, "step": 2118 }, { "epoch": 6.35, "learning_rate": 1.2606105e-05, "loss": 1.9312, "step": 2119 }, { "epoch": 6.35, "learning_rate": 1.2605400000000001e-05, "loss": 1.9289, "step": 2120 }, { "epoch": 6.35, "learning_rate": 1.2604695000000001e-05, "loss": 1.9265, "step": 2121 }, { "epoch": 6.35, "learning_rate": 1.2603990000000001e-05, "loss": 1.9277, "step": 2122 }, { "epoch": 6.36, "learning_rate": 1.2603285e-05, "loss": 1.9264, "step": 2123 }, { "epoch": 6.36, "learning_rate": 1.260258e-05, "loss": 1.9287, "step": 2124 }, { "epoch": 6.36, "learning_rate": 1.2601875e-05, "loss": 1.9305, "step": 2125 }, { "epoch": 6.37, "learning_rate": 1.2601170000000002e-05, "loss": 1.9275, "step": 2126 }, { "epoch": 6.37, "learning_rate": 1.2600465000000002e-05, "loss": 1.9268, "step": 2127 }, { "epoch": 6.37, "learning_rate": 1.259976e-05, "loss": 1.9288, "step": 2128 }, { "epoch": 6.38, "learning_rate": 1.2599055e-05, "loss": 1.9272, "step": 2129 }, { "epoch": 6.38, "learning_rate": 1.259835e-05, "loss": 1.9287, "step": 2130 }, { "epoch": 6.38, "learning_rate": 1.2597645e-05, "loss": 1.9273, "step": 2131 }, { "epoch": 6.38, "learning_rate": 1.259694e-05, "loss": 1.9282, "step": 2132 }, { "epoch": 6.39, "learning_rate": 1.2596235e-05, "loss": 1.9273, "step": 2133 }, { "epoch": 6.39, "learning_rate": 1.259553e-05, "loss": 1.9292, "step": 2134 }, { "epoch": 6.39, "learning_rate": 1.2594825e-05, "loss": 1.9267, "step": 2135 }, { "epoch": 6.4, "learning_rate": 1.259412e-05, "loss": 1.9254, "step": 2136 }, { "epoch": 6.4, "learning_rate": 1.2593415e-05, "loss": 1.9266, "step": 2137 }, { "epoch": 6.4, "learning_rate": 1.2592710000000001e-05, "loss": 1.9261, "step": 2138 }, { "epoch": 6.41, "learning_rate": 1.2592005000000001e-05, "loss": 1.9271, "step": 2139 }, { "epoch": 6.41, "learning_rate": 1.2591300000000001e-05, "loss": 1.9286, "step": 2140 }, { "epoch": 6.41, "learning_rate": 1.2590595e-05, "loss": 1.9279, "step": 2141 }, { "epoch": 6.41, "learning_rate": 1.258989e-05, "loss": 1.9267, "step": 2142 }, { "epoch": 6.42, "learning_rate": 1.2589185e-05, "loss": 1.9263, "step": 2143 }, { "epoch": 6.42, "learning_rate": 1.2588480000000002e-05, "loss": 1.9302, "step": 2144 }, { "epoch": 6.42, "learning_rate": 1.2587775000000002e-05, "loss": 1.9294, "step": 2145 }, { "epoch": 6.43, "learning_rate": 1.2587070000000001e-05, "loss": 1.925, "step": 2146 }, { "epoch": 6.43, "learning_rate": 1.2586365000000001e-05, "loss": 1.9265, "step": 2147 }, { "epoch": 6.43, "learning_rate": 1.258566e-05, "loss": 1.9286, "step": 2148 }, { "epoch": 6.44, "learning_rate": 1.2584955e-05, "loss": 1.9273, "step": 2149 }, { "epoch": 6.44, "learning_rate": 1.258425e-05, "loss": 1.9248, "step": 2150 }, { "epoch": 6.44, "learning_rate": 1.2583545e-05, "loss": 1.927, "step": 2151 }, { "epoch": 6.44, "learning_rate": 1.258284e-05, "loss": 1.9239, "step": 2152 }, { "epoch": 6.45, "learning_rate": 1.2582135e-05, "loss": 1.9266, "step": 2153 }, { "epoch": 6.45, "learning_rate": 1.258143e-05, "loss": 1.9273, "step": 2154 }, { "epoch": 6.45, "learning_rate": 1.2580725e-05, "loss": 1.9263, "step": 2155 }, { "epoch": 6.46, "learning_rate": 1.258002e-05, "loss": 1.928, "step": 2156 }, { "epoch": 6.46, "learning_rate": 1.2579315000000001e-05, "loss": 1.9258, "step": 2157 }, { "epoch": 6.46, "learning_rate": 1.2578610000000001e-05, "loss": 1.9244, "step": 2158 }, { "epoch": 6.47, "learning_rate": 1.2577905e-05, "loss": 1.9285, "step": 2159 }, { "epoch": 6.47, "learning_rate": 1.25772e-05, "loss": 1.9236, "step": 2160 }, { "epoch": 6.47, "learning_rate": 1.2576495e-05, "loss": 1.9228, "step": 2161 }, { "epoch": 6.47, "learning_rate": 1.257579e-05, "loss": 1.9239, "step": 2162 }, { "epoch": 6.48, "learning_rate": 1.2575085000000002e-05, "loss": 1.9233, "step": 2163 }, { "epoch": 6.48, "learning_rate": 1.2574380000000001e-05, "loss": 1.9269, "step": 2164 }, { "epoch": 6.48, "learning_rate": 1.2573675000000001e-05, "loss": 1.926, "step": 2165 }, { "epoch": 6.49, "learning_rate": 1.2572970000000001e-05, "loss": 1.9247, "step": 2166 }, { "epoch": 6.49, "learning_rate": 1.2572265e-05, "loss": 1.9259, "step": 2167 }, { "epoch": 6.49, "learning_rate": 1.2571559999999999e-05, "loss": 1.9239, "step": 2168 }, { "epoch": 6.5, "learning_rate": 1.2570855e-05, "loss": 1.9252, "step": 2169 }, { "epoch": 6.5, "learning_rate": 1.257015e-05, "loss": 1.9252, "step": 2170 }, { "epoch": 6.5, "learning_rate": 1.2569445e-05, "loss": 1.9235, "step": 2171 }, { "epoch": 6.5, "learning_rate": 1.256874e-05, "loss": 1.9248, "step": 2172 }, { "epoch": 6.51, "learning_rate": 1.2568035e-05, "loss": 1.9236, "step": 2173 }, { "epoch": 6.51, "learning_rate": 1.256733e-05, "loss": 1.9234, "step": 2174 }, { "epoch": 6.51, "learning_rate": 1.2566625000000001e-05, "loss": 1.9251, "step": 2175 }, { "epoch": 6.52, "learning_rate": 1.256592e-05, "loss": 1.9214, "step": 2176 }, { "epoch": 6.52, "learning_rate": 1.2565215e-05, "loss": 1.925, "step": 2177 }, { "epoch": 6.52, "learning_rate": 1.256451e-05, "loss": 1.9223, "step": 2178 }, { "epoch": 6.53, "learning_rate": 1.2563805e-05, "loss": 1.9239, "step": 2179 }, { "epoch": 6.53, "learning_rate": 1.25631e-05, "loss": 1.9249, "step": 2180 }, { "epoch": 6.53, "learning_rate": 1.2562395000000002e-05, "loss": 1.923, "step": 2181 }, { "epoch": 6.53, "learning_rate": 1.2561690000000001e-05, "loss": 1.923, "step": 2182 }, { "epoch": 6.54, "learning_rate": 1.2560985000000001e-05, "loss": 1.9244, "step": 2183 }, { "epoch": 6.54, "learning_rate": 1.2560280000000001e-05, "loss": 1.9232, "step": 2184 }, { "epoch": 6.54, "learning_rate": 1.2559575e-05, "loss": 1.924, "step": 2185 }, { "epoch": 6.55, "learning_rate": 1.255887e-05, "loss": 1.9246, "step": 2186 }, { "epoch": 6.55, "learning_rate": 1.2558165e-05, "loss": 1.922, "step": 2187 }, { "epoch": 6.55, "learning_rate": 1.255746e-05, "loss": 1.9213, "step": 2188 }, { "epoch": 6.56, "learning_rate": 1.2556755e-05, "loss": 1.9239, "step": 2189 }, { "epoch": 6.56, "learning_rate": 1.255605e-05, "loss": 1.9253, "step": 2190 }, { "epoch": 6.56, "learning_rate": 1.2555345e-05, "loss": 1.9242, "step": 2191 }, { "epoch": 6.56, "learning_rate": 1.255464e-05, "loss": 1.9213, "step": 2192 }, { "epoch": 6.57, "learning_rate": 1.2553935000000001e-05, "loss": 1.9239, "step": 2193 }, { "epoch": 6.57, "learning_rate": 1.255323e-05, "loss": 1.9209, "step": 2194 }, { "epoch": 6.57, "learning_rate": 1.2552525e-05, "loss": 1.9221, "step": 2195 }, { "epoch": 6.58, "learning_rate": 1.255182e-05, "loss": 1.9229, "step": 2196 }, { "epoch": 6.58, "learning_rate": 1.2551115e-05, "loss": 1.9221, "step": 2197 }, { "epoch": 6.58, "learning_rate": 1.255041e-05, "loss": 1.9227, "step": 2198 }, { "epoch": 6.59, "learning_rate": 1.2549705e-05, "loss": 1.9209, "step": 2199 }, { "epoch": 6.59, "learning_rate": 1.2549000000000001e-05, "loss": 1.921, "step": 2200 }, { "epoch": 6.59, "eval_accuracy": 0.0006816275167785235, "eval_loss": 1.8413642644882202, "eval_runtime": 37.6665, "eval_samples_per_second": 7.912, "eval_steps_per_second": 0.504, "step": 2200 }, { "epoch": 6.59, "learning_rate": 1.2548295000000001e-05, "loss": 1.9241, "step": 2201 }, { "epoch": 6.59, "learning_rate": 1.2547590000000001e-05, "loss": 1.9238, "step": 2202 }, { "epoch": 6.6, "learning_rate": 1.2546885e-05, "loss": 1.9216, "step": 2203 }, { "epoch": 6.6, "learning_rate": 1.254618e-05, "loss": 1.9205, "step": 2204 }, { "epoch": 6.6, "learning_rate": 1.2545475e-05, "loss": 1.9208, "step": 2205 }, { "epoch": 6.61, "learning_rate": 1.2544770000000002e-05, "loss": 1.9195, "step": 2206 }, { "epoch": 6.61, "learning_rate": 1.2544065000000002e-05, "loss": 1.9213, "step": 2207 }, { "epoch": 6.61, "learning_rate": 1.254336e-05, "loss": 1.9201, "step": 2208 }, { "epoch": 6.62, "learning_rate": 1.2542655e-05, "loss": 1.9204, "step": 2209 }, { "epoch": 6.62, "learning_rate": 1.254195e-05, "loss": 1.9209, "step": 2210 }, { "epoch": 6.62, "learning_rate": 1.2541245e-05, "loss": 1.9221, "step": 2211 }, { "epoch": 6.62, "learning_rate": 1.254054e-05, "loss": 1.921, "step": 2212 }, { "epoch": 6.63, "learning_rate": 1.2539835e-05, "loss": 1.9231, "step": 2213 }, { "epoch": 6.63, "learning_rate": 1.253913e-05, "loss": 1.9221, "step": 2214 }, { "epoch": 6.63, "learning_rate": 1.2538425e-05, "loss": 1.9209, "step": 2215 }, { "epoch": 6.64, "learning_rate": 1.253772e-05, "loss": 1.9193, "step": 2216 }, { "epoch": 6.64, "learning_rate": 1.2537015e-05, "loss": 1.9211, "step": 2217 }, { "epoch": 6.64, "learning_rate": 1.2536310000000001e-05, "loss": 1.9208, "step": 2218 }, { "epoch": 6.64, "learning_rate": 1.2535605000000001e-05, "loss": 1.9216, "step": 2219 }, { "epoch": 6.65, "learning_rate": 1.2534900000000001e-05, "loss": 1.9207, "step": 2220 }, { "epoch": 6.65, "learning_rate": 1.2534195e-05, "loss": 1.9208, "step": 2221 }, { "epoch": 6.65, "learning_rate": 1.253349e-05, "loss": 1.9201, "step": 2222 }, { "epoch": 6.66, "learning_rate": 1.2532785e-05, "loss": 1.9228, "step": 2223 }, { "epoch": 6.66, "learning_rate": 1.253208e-05, "loss": 1.9224, "step": 2224 }, { "epoch": 6.66, "learning_rate": 1.2531375000000002e-05, "loss": 1.9186, "step": 2225 }, { "epoch": 6.67, "learning_rate": 1.2530670000000001e-05, "loss": 1.9213, "step": 2226 }, { "epoch": 6.67, "learning_rate": 1.2529965000000001e-05, "loss": 1.9207, "step": 2227 }, { "epoch": 6.67, "learning_rate": 1.252926e-05, "loss": 1.9193, "step": 2228 }, { "epoch": 6.67, "learning_rate": 1.2528555e-05, "loss": 1.9233, "step": 2229 }, { "epoch": 6.68, "learning_rate": 1.252785e-05, "loss": 1.9188, "step": 2230 }, { "epoch": 6.68, "learning_rate": 1.2527145e-05, "loss": 1.9207, "step": 2231 }, { "epoch": 6.68, "learning_rate": 1.252644e-05, "loss": 1.9202, "step": 2232 }, { "epoch": 6.69, "learning_rate": 1.2525735e-05, "loss": 1.92, "step": 2233 }, { "epoch": 6.69, "learning_rate": 1.252503e-05, "loss": 1.9167, "step": 2234 }, { "epoch": 6.69, "learning_rate": 1.2524325e-05, "loss": 1.9195, "step": 2235 }, { "epoch": 6.7, "learning_rate": 1.252362e-05, "loss": 1.9178, "step": 2236 }, { "epoch": 6.7, "learning_rate": 1.2522915000000001e-05, "loss": 1.9188, "step": 2237 }, { "epoch": 6.7, "learning_rate": 1.2522210000000001e-05, "loss": 1.9184, "step": 2238 }, { "epoch": 6.7, "learning_rate": 1.2521505e-05, "loss": 1.9182, "step": 2239 }, { "epoch": 6.71, "learning_rate": 1.25208e-05, "loss": 1.9176, "step": 2240 }, { "epoch": 6.71, "learning_rate": 1.2520095e-05, "loss": 1.9178, "step": 2241 }, { "epoch": 6.71, "learning_rate": 1.251939e-05, "loss": 1.916, "step": 2242 }, { "epoch": 6.72, "learning_rate": 1.2518685000000002e-05, "loss": 1.9163, "step": 2243 }, { "epoch": 6.72, "learning_rate": 1.2517980000000001e-05, "loss": 1.9165, "step": 2244 }, { "epoch": 6.72, "learning_rate": 1.2517275000000001e-05, "loss": 1.9202, "step": 2245 }, { "epoch": 6.73, "learning_rate": 1.2516570000000001e-05, "loss": 1.9182, "step": 2246 }, { "epoch": 6.73, "learning_rate": 1.2515865e-05, "loss": 1.92, "step": 2247 }, { "epoch": 6.73, "learning_rate": 1.2515159999999999e-05, "loss": 1.9189, "step": 2248 }, { "epoch": 6.73, "learning_rate": 1.2514455e-05, "loss": 1.916, "step": 2249 }, { "epoch": 6.74, "learning_rate": 1.251375e-05, "loss": 1.9186, "step": 2250 }, { "epoch": 6.74, "learning_rate": 1.2513045e-05, "loss": 1.9179, "step": 2251 }, { "epoch": 6.74, "learning_rate": 1.251234e-05, "loss": 1.9184, "step": 2252 }, { "epoch": 6.75, "learning_rate": 1.2511635e-05, "loss": 1.9187, "step": 2253 }, { "epoch": 6.75, "learning_rate": 1.251093e-05, "loss": 1.9174, "step": 2254 }, { "epoch": 6.75, "learning_rate": 1.2510225000000001e-05, "loss": 1.9152, "step": 2255 }, { "epoch": 6.76, "learning_rate": 1.250952e-05, "loss": 1.9144, "step": 2256 }, { "epoch": 6.76, "learning_rate": 1.2508815e-05, "loss": 1.916, "step": 2257 }, { "epoch": 6.76, "learning_rate": 1.250811e-05, "loss": 1.9173, "step": 2258 }, { "epoch": 6.76, "learning_rate": 1.2507405e-05, "loss": 1.9154, "step": 2259 }, { "epoch": 6.77, "learning_rate": 1.25067e-05, "loss": 1.9149, "step": 2260 }, { "epoch": 6.77, "learning_rate": 1.2505995e-05, "loss": 1.9187, "step": 2261 }, { "epoch": 6.77, "learning_rate": 1.2505290000000001e-05, "loss": 1.9155, "step": 2262 }, { "epoch": 6.78, "learning_rate": 1.2504585000000001e-05, "loss": 1.9156, "step": 2263 }, { "epoch": 6.78, "learning_rate": 1.2503880000000001e-05, "loss": 1.9161, "step": 2264 }, { "epoch": 6.78, "learning_rate": 1.2503175e-05, "loss": 1.9153, "step": 2265 }, { "epoch": 6.79, "learning_rate": 1.250247e-05, "loss": 1.9149, "step": 2266 }, { "epoch": 6.79, "learning_rate": 1.2501765e-05, "loss": 1.9182, "step": 2267 }, { "epoch": 6.79, "learning_rate": 1.2501060000000002e-05, "loss": 1.9171, "step": 2268 }, { "epoch": 6.79, "learning_rate": 1.2500355e-05, "loss": 1.917, "step": 2269 }, { "epoch": 6.8, "learning_rate": 1.249965e-05, "loss": 1.9177, "step": 2270 }, { "epoch": 6.8, "learning_rate": 1.2498945e-05, "loss": 1.9148, "step": 2271 }, { "epoch": 6.8, "learning_rate": 1.249824e-05, "loss": 1.9177, "step": 2272 }, { "epoch": 6.81, "learning_rate": 1.2497535e-05, "loss": 1.9148, "step": 2273 }, { "epoch": 6.81, "learning_rate": 1.249683e-05, "loss": 1.914, "step": 2274 }, { "epoch": 6.81, "learning_rate": 1.2496125e-05, "loss": 1.9154, "step": 2275 }, { "epoch": 6.82, "learning_rate": 1.249542e-05, "loss": 1.9156, "step": 2276 }, { "epoch": 6.82, "learning_rate": 1.2494715e-05, "loss": 1.9146, "step": 2277 }, { "epoch": 6.82, "learning_rate": 1.249401e-05, "loss": 1.9161, "step": 2278 }, { "epoch": 6.82, "learning_rate": 1.2493305e-05, "loss": 1.9151, "step": 2279 }, { "epoch": 6.83, "learning_rate": 1.2492600000000001e-05, "loss": 1.9126, "step": 2280 }, { "epoch": 6.83, "learning_rate": 1.2491895000000001e-05, "loss": 1.913, "step": 2281 }, { "epoch": 6.83, "learning_rate": 1.2491190000000001e-05, "loss": 1.9135, "step": 2282 }, { "epoch": 6.84, "learning_rate": 1.2490485e-05, "loss": 1.9134, "step": 2283 }, { "epoch": 6.84, "learning_rate": 1.248978e-05, "loss": 1.914, "step": 2284 }, { "epoch": 6.84, "learning_rate": 1.2489075e-05, "loss": 1.9177, "step": 2285 }, { "epoch": 6.85, "learning_rate": 1.2488370000000002e-05, "loss": 1.9135, "step": 2286 }, { "epoch": 6.85, "learning_rate": 1.2487665000000002e-05, "loss": 1.9139, "step": 2287 }, { "epoch": 6.85, "learning_rate": 1.2486960000000001e-05, "loss": 1.9132, "step": 2288 }, { "epoch": 6.85, "learning_rate": 1.2486255e-05, "loss": 1.9152, "step": 2289 }, { "epoch": 6.86, "learning_rate": 1.248555e-05, "loss": 1.913, "step": 2290 }, { "epoch": 6.86, "learning_rate": 1.2484845e-05, "loss": 1.9112, "step": 2291 }, { "epoch": 6.86, "learning_rate": 1.248414e-05, "loss": 1.9155, "step": 2292 }, { "epoch": 6.87, "learning_rate": 1.2483435e-05, "loss": 1.9128, "step": 2293 }, { "epoch": 6.87, "learning_rate": 1.248273e-05, "loss": 1.9124, "step": 2294 }, { "epoch": 6.87, "learning_rate": 1.2482025e-05, "loss": 1.913, "step": 2295 }, { "epoch": 6.88, "learning_rate": 1.248132e-05, "loss": 1.9158, "step": 2296 }, { "epoch": 6.88, "learning_rate": 1.2480615e-05, "loss": 1.913, "step": 2297 }, { "epoch": 6.88, "learning_rate": 1.2479910000000001e-05, "loss": 1.9111, "step": 2298 }, { "epoch": 6.88, "learning_rate": 1.2479205000000001e-05, "loss": 1.911, "step": 2299 }, { "epoch": 6.89, "learning_rate": 1.2478500000000001e-05, "loss": 1.9134, "step": 2300 }, { "epoch": 6.89, "eval_accuracy": 0.0006488569630872484, "eval_loss": 1.835094928741455, "eval_runtime": 35.2138, "eval_samples_per_second": 8.463, "eval_steps_per_second": 0.54, "step": 2300 }, { "epoch": 6.89, "learning_rate": 1.2477795e-05, "loss": 1.9131, "step": 2301 }, { "epoch": 6.89, "learning_rate": 1.247709e-05, "loss": 1.9119, "step": 2302 }, { "epoch": 6.9, "learning_rate": 1.2476385e-05, "loss": 1.9124, "step": 2303 }, { "epoch": 6.9, "learning_rate": 1.247568e-05, "loss": 1.9124, "step": 2304 }, { "epoch": 6.9, "learning_rate": 1.2474975000000002e-05, "loss": 1.9132, "step": 2305 }, { "epoch": 6.91, "learning_rate": 1.2474270000000001e-05, "loss": 1.9145, "step": 2306 }, { "epoch": 6.91, "learning_rate": 1.2473565000000001e-05, "loss": 1.9134, "step": 2307 }, { "epoch": 6.91, "learning_rate": 1.2472860000000001e-05, "loss": 1.9124, "step": 2308 }, { "epoch": 6.91, "learning_rate": 1.2472155e-05, "loss": 1.9118, "step": 2309 }, { "epoch": 6.92, "learning_rate": 1.2471449999999999e-05, "loss": 1.9113, "step": 2310 }, { "epoch": 6.92, "learning_rate": 1.2470745e-05, "loss": 1.9149, "step": 2311 }, { "epoch": 6.92, "learning_rate": 1.247004e-05, "loss": 1.9125, "step": 2312 }, { "epoch": 6.93, "learning_rate": 1.2469335e-05, "loss": 1.9117, "step": 2313 }, { "epoch": 6.93, "learning_rate": 1.246863e-05, "loss": 1.911, "step": 2314 }, { "epoch": 6.93, "learning_rate": 1.2467925e-05, "loss": 1.9143, "step": 2315 }, { "epoch": 6.94, "learning_rate": 1.246722e-05, "loss": 1.9119, "step": 2316 }, { "epoch": 6.94, "learning_rate": 1.2466515000000001e-05, "loss": 1.9152, "step": 2317 }, { "epoch": 6.94, "learning_rate": 1.246581e-05, "loss": 1.9098, "step": 2318 }, { "epoch": 6.94, "learning_rate": 1.2465105e-05, "loss": 1.9113, "step": 2319 }, { "epoch": 6.95, "learning_rate": 1.24644e-05, "loss": 1.9105, "step": 2320 }, { "epoch": 6.95, "learning_rate": 1.2463695e-05, "loss": 1.9131, "step": 2321 }, { "epoch": 6.95, "learning_rate": 1.246299e-05, "loss": 1.9118, "step": 2322 }, { "epoch": 6.96, "learning_rate": 1.2462285000000002e-05, "loss": 1.9127, "step": 2323 }, { "epoch": 6.96, "learning_rate": 1.2461580000000001e-05, "loss": 1.9118, "step": 2324 }, { "epoch": 6.96, "learning_rate": 1.2460875000000001e-05, "loss": 1.9096, "step": 2325 }, { "epoch": 6.97, "learning_rate": 1.2460170000000001e-05, "loss": 1.914, "step": 2326 }, { "epoch": 6.97, "learning_rate": 1.2459465e-05, "loss": 1.9119, "step": 2327 }, { "epoch": 6.97, "learning_rate": 1.245876e-05, "loss": 1.9091, "step": 2328 }, { "epoch": 6.97, "learning_rate": 1.2458055e-05, "loss": 1.9093, "step": 2329 }, { "epoch": 6.98, "learning_rate": 1.245735e-05, "loss": 1.9111, "step": 2330 }, { "epoch": 6.98, "learning_rate": 1.2456645e-05, "loss": 1.9091, "step": 2331 }, { "epoch": 6.98, "learning_rate": 1.245594e-05, "loss": 1.9097, "step": 2332 }, { "epoch": 6.99, "learning_rate": 1.2455235e-05, "loss": 1.9133, "step": 2333 }, { "epoch": 6.99, "learning_rate": 1.245453e-05, "loss": 1.9125, "step": 2334 }, { "epoch": 6.99, "learning_rate": 1.2453825000000001e-05, "loss": 1.9107, "step": 2335 }, { "epoch": 7.0, "learning_rate": 1.245312e-05, "loss": 1.9114, "step": 2336 }, { "epoch": 7.0, "learning_rate": 1.2452415e-05, "loss": 1.9096, "step": 2337 }, { "epoch": 7.0, "learning_rate": 1.245171e-05, "loss": 1.9093, "step": 2338 }, { "epoch": 7.0, "learning_rate": 1.2451005e-05, "loss": 1.9115, "step": 2339 }, { "epoch": 7.01, "learning_rate": 1.24503e-05, "loss": 1.9109, "step": 2340 }, { "epoch": 7.01, "learning_rate": 1.2449595e-05, "loss": 1.9105, "step": 2341 }, { "epoch": 7.01, "learning_rate": 1.2448890000000001e-05, "loss": 1.9087, "step": 2342 }, { "epoch": 7.02, "learning_rate": 1.2448185000000001e-05, "loss": 1.909, "step": 2343 }, { "epoch": 7.02, "learning_rate": 1.2447480000000001e-05, "loss": 1.9059, "step": 2344 }, { "epoch": 7.02, "learning_rate": 1.2446775e-05, "loss": 1.9106, "step": 2345 }, { "epoch": 7.03, "learning_rate": 1.244607e-05, "loss": 1.9103, "step": 2346 }, { "epoch": 7.03, "learning_rate": 1.2445365e-05, "loss": 1.91, "step": 2347 }, { "epoch": 7.03, "learning_rate": 1.2444660000000002e-05, "loss": 1.9076, "step": 2348 }, { "epoch": 7.03, "learning_rate": 1.2443955e-05, "loss": 1.9108, "step": 2349 }, { "epoch": 7.04, "learning_rate": 1.244325e-05, "loss": 1.9105, "step": 2350 }, { "epoch": 7.04, "learning_rate": 1.2442545e-05, "loss": 1.9096, "step": 2351 }, { "epoch": 7.04, "learning_rate": 1.244184e-05, "loss": 1.9077, "step": 2352 }, { "epoch": 7.05, "learning_rate": 1.2441135e-05, "loss": 1.9076, "step": 2353 }, { "epoch": 7.05, "learning_rate": 1.244043e-05, "loss": 1.91, "step": 2354 }, { "epoch": 7.05, "learning_rate": 1.2439725e-05, "loss": 1.9097, "step": 2355 }, { "epoch": 7.06, "learning_rate": 1.243902e-05, "loss": 1.9123, "step": 2356 }, { "epoch": 7.06, "learning_rate": 1.2438315e-05, "loss": 1.9088, "step": 2357 }, { "epoch": 7.06, "learning_rate": 1.243761e-05, "loss": 1.9099, "step": 2358 }, { "epoch": 7.06, "learning_rate": 1.2436905e-05, "loss": 1.9076, "step": 2359 }, { "epoch": 7.07, "learning_rate": 1.2436200000000001e-05, "loss": 1.9062, "step": 2360 }, { "epoch": 7.07, "learning_rate": 1.2435495000000001e-05, "loss": 1.9081, "step": 2361 }, { "epoch": 7.07, "learning_rate": 1.2434790000000001e-05, "loss": 1.9092, "step": 2362 }, { "epoch": 7.08, "learning_rate": 1.2434085e-05, "loss": 1.9107, "step": 2363 }, { "epoch": 7.08, "learning_rate": 1.243338e-05, "loss": 1.9068, "step": 2364 }, { "epoch": 7.08, "learning_rate": 1.2432675e-05, "loss": 1.9102, "step": 2365 }, { "epoch": 7.09, "learning_rate": 1.2431970000000002e-05, "loss": 1.9058, "step": 2366 }, { "epoch": 7.09, "learning_rate": 1.2431265000000002e-05, "loss": 1.9094, "step": 2367 }, { "epoch": 7.09, "learning_rate": 1.2430560000000001e-05, "loss": 1.9092, "step": 2368 }, { "epoch": 7.09, "learning_rate": 1.2429855e-05, "loss": 1.9077, "step": 2369 }, { "epoch": 7.1, "learning_rate": 1.242915e-05, "loss": 1.9071, "step": 2370 }, { "epoch": 7.1, "learning_rate": 1.2428445e-05, "loss": 1.9076, "step": 2371 }, { "epoch": 7.1, "learning_rate": 1.242774e-05, "loss": 1.9064, "step": 2372 }, { "epoch": 7.11, "learning_rate": 1.2427035e-05, "loss": 1.9069, "step": 2373 }, { "epoch": 7.11, "learning_rate": 1.242633e-05, "loss": 1.9057, "step": 2374 }, { "epoch": 7.11, "learning_rate": 1.2425625e-05, "loss": 1.9079, "step": 2375 }, { "epoch": 7.12, "learning_rate": 1.242492e-05, "loss": 1.9052, "step": 2376 }, { "epoch": 7.12, "learning_rate": 1.2424215e-05, "loss": 1.912, "step": 2377 }, { "epoch": 7.12, "learning_rate": 1.242351e-05, "loss": 1.9085, "step": 2378 }, { "epoch": 7.12, "learning_rate": 1.2422805000000001e-05, "loss": 1.907, "step": 2379 }, { "epoch": 7.13, "learning_rate": 1.2422100000000001e-05, "loss": 1.9087, "step": 2380 }, { "epoch": 7.13, "learning_rate": 1.2421395e-05, "loss": 1.9058, "step": 2381 }, { "epoch": 7.13, "learning_rate": 1.242069e-05, "loss": 1.9075, "step": 2382 }, { "epoch": 7.14, "learning_rate": 1.2419985e-05, "loss": 1.906, "step": 2383 }, { "epoch": 7.14, "learning_rate": 1.241928e-05, "loss": 1.9078, "step": 2384 }, { "epoch": 7.14, "learning_rate": 1.2418575000000002e-05, "loss": 1.9087, "step": 2385 }, { "epoch": 7.15, "learning_rate": 1.2417870000000001e-05, "loss": 1.9066, "step": 2386 }, { "epoch": 7.15, "learning_rate": 1.2417165000000001e-05, "loss": 1.905, "step": 2387 }, { "epoch": 7.15, "learning_rate": 1.2416460000000001e-05, "loss": 1.9055, "step": 2388 }, { "epoch": 7.15, "learning_rate": 1.2415755000000001e-05, "loss": 1.9085, "step": 2389 }, { "epoch": 7.16, "learning_rate": 1.2415049999999999e-05, "loss": 1.9046, "step": 2390 }, { "epoch": 7.16, "learning_rate": 1.2414345e-05, "loss": 1.9086, "step": 2391 }, { "epoch": 7.16, "learning_rate": 1.241364e-05, "loss": 1.9078, "step": 2392 }, { "epoch": 7.17, "learning_rate": 1.2412935e-05, "loss": 1.9073, "step": 2393 }, { "epoch": 7.17, "learning_rate": 1.241223e-05, "loss": 1.9063, "step": 2394 }, { "epoch": 7.17, "learning_rate": 1.2411525e-05, "loss": 1.9074, "step": 2395 }, { "epoch": 7.17, "learning_rate": 1.241082e-05, "loss": 1.9035, "step": 2396 }, { "epoch": 7.18, "learning_rate": 1.2410115000000001e-05, "loss": 1.9062, "step": 2397 }, { "epoch": 7.18, "learning_rate": 1.240941e-05, "loss": 1.9075, "step": 2398 }, { "epoch": 7.18, "learning_rate": 1.2408705e-05, "loss": 1.9043, "step": 2399 }, { "epoch": 7.19, "learning_rate": 1.2408e-05, "loss": 1.9052, "step": 2400 }, { "epoch": 7.19, "eval_accuracy": 0.0005964240771812081, "eval_loss": 1.829280138015747, "eval_runtime": 33.1458, "eval_samples_per_second": 8.991, "eval_steps_per_second": 0.573, "step": 2400 }, { "epoch": 7.19, "learning_rate": 1.2407295e-05, "loss": 1.9051, "step": 2401 }, { "epoch": 7.19, "learning_rate": 1.240659e-05, "loss": 1.9051, "step": 2402 }, { "epoch": 7.2, "learning_rate": 1.2405885000000002e-05, "loss": 1.9049, "step": 2403 }, { "epoch": 7.2, "learning_rate": 1.2405180000000001e-05, "loss": 1.9039, "step": 2404 }, { "epoch": 7.2, "learning_rate": 1.2404475000000001e-05, "loss": 1.9044, "step": 2405 }, { "epoch": 7.2, "learning_rate": 1.2403770000000001e-05, "loss": 1.9068, "step": 2406 }, { "epoch": 7.21, "learning_rate": 1.2403065e-05, "loss": 1.9044, "step": 2407 }, { "epoch": 7.21, "learning_rate": 1.240236e-05, "loss": 1.9056, "step": 2408 }, { "epoch": 7.21, "learning_rate": 1.2401655e-05, "loss": 1.9038, "step": 2409 }, { "epoch": 7.22, "learning_rate": 1.240095e-05, "loss": 1.9043, "step": 2410 }, { "epoch": 7.22, "learning_rate": 1.2400245e-05, "loss": 1.9036, "step": 2411 }, { "epoch": 7.22, "learning_rate": 1.239954e-05, "loss": 1.9026, "step": 2412 }, { "epoch": 7.23, "learning_rate": 1.2398835e-05, "loss": 1.902, "step": 2413 }, { "epoch": 7.23, "learning_rate": 1.239813e-05, "loss": 1.9079, "step": 2414 }, { "epoch": 7.23, "learning_rate": 1.2397425e-05, "loss": 1.9035, "step": 2415 }, { "epoch": 7.23, "learning_rate": 1.239672e-05, "loss": 1.9053, "step": 2416 }, { "epoch": 7.24, "learning_rate": 1.2396015e-05, "loss": 1.9022, "step": 2417 }, { "epoch": 7.24, "learning_rate": 1.239531e-05, "loss": 1.9048, "step": 2418 }, { "epoch": 7.24, "learning_rate": 1.2394605e-05, "loss": 1.9043, "step": 2419 }, { "epoch": 7.25, "learning_rate": 1.23939e-05, "loss": 1.9062, "step": 2420 }, { "epoch": 7.25, "learning_rate": 1.2393195e-05, "loss": 1.9036, "step": 2421 }, { "epoch": 7.25, "learning_rate": 1.2392490000000001e-05, "loss": 1.9044, "step": 2422 }, { "epoch": 7.26, "learning_rate": 1.2391785000000001e-05, "loss": 1.9089, "step": 2423 }, { "epoch": 7.26, "learning_rate": 1.2391080000000001e-05, "loss": 1.9045, "step": 2424 }, { "epoch": 7.26, "learning_rate": 1.2390375e-05, "loss": 1.903, "step": 2425 }, { "epoch": 7.26, "learning_rate": 1.238967e-05, "loss": 1.9053, "step": 2426 }, { "epoch": 7.27, "learning_rate": 1.2388965e-05, "loss": 1.9043, "step": 2427 }, { "epoch": 7.27, "learning_rate": 1.2388260000000002e-05, "loss": 1.9015, "step": 2428 }, { "epoch": 7.27, "learning_rate": 1.2387555000000002e-05, "loss": 1.9038, "step": 2429 }, { "epoch": 7.28, "learning_rate": 1.238685e-05, "loss": 1.9037, "step": 2430 }, { "epoch": 7.28, "learning_rate": 1.2386145e-05, "loss": 1.9025, "step": 2431 }, { "epoch": 7.28, "learning_rate": 1.238544e-05, "loss": 1.9035, "step": 2432 }, { "epoch": 7.29, "learning_rate": 1.2384735e-05, "loss": 1.901, "step": 2433 }, { "epoch": 7.29, "learning_rate": 1.238403e-05, "loss": 1.9032, "step": 2434 }, { "epoch": 7.29, "learning_rate": 1.2383325e-05, "loss": 1.9037, "step": 2435 }, { "epoch": 7.29, "learning_rate": 1.238262e-05, "loss": 1.9011, "step": 2436 }, { "epoch": 7.3, "learning_rate": 1.2381915e-05, "loss": 1.9011, "step": 2437 }, { "epoch": 7.3, "learning_rate": 1.238121e-05, "loss": 1.9025, "step": 2438 }, { "epoch": 7.3, "learning_rate": 1.2380505e-05, "loss": 1.899, "step": 2439 }, { "epoch": 7.31, "learning_rate": 1.2379800000000001e-05, "loss": 1.9034, "step": 2440 }, { "epoch": 7.31, "learning_rate": 1.2379095000000001e-05, "loss": 1.9035, "step": 2441 }, { "epoch": 7.31, "learning_rate": 1.2378390000000001e-05, "loss": 1.9042, "step": 2442 }, { "epoch": 7.32, "learning_rate": 1.2377685e-05, "loss": 1.9009, "step": 2443 }, { "epoch": 7.32, "learning_rate": 1.237698e-05, "loss": 1.9021, "step": 2444 }, { "epoch": 7.32, "learning_rate": 1.2376275e-05, "loss": 1.901, "step": 2445 }, { "epoch": 7.32, "learning_rate": 1.237557e-05, "loss": 1.9, "step": 2446 }, { "epoch": 7.33, "learning_rate": 1.2374865000000002e-05, "loss": 1.903, "step": 2447 }, { "epoch": 7.33, "learning_rate": 1.2374160000000001e-05, "loss": 1.9013, "step": 2448 }, { "epoch": 7.33, "learning_rate": 1.2373455000000001e-05, "loss": 1.9036, "step": 2449 }, { "epoch": 7.34, "learning_rate": 1.237275e-05, "loss": 1.9038, "step": 2450 }, { "epoch": 7.34, "learning_rate": 1.2372045e-05, "loss": 1.8995, "step": 2451 }, { "epoch": 7.34, "learning_rate": 1.2371339999999999e-05, "loss": 1.9023, "step": 2452 }, { "epoch": 7.35, "learning_rate": 1.2370635e-05, "loss": 1.9021, "step": 2453 }, { "epoch": 7.35, "learning_rate": 1.236993e-05, "loss": 1.9, "step": 2454 }, { "epoch": 7.35, "learning_rate": 1.2369225e-05, "loss": 1.9007, "step": 2455 }, { "epoch": 7.35, "learning_rate": 1.236852e-05, "loss": 1.902, "step": 2456 }, { "epoch": 7.36, "learning_rate": 1.2367815e-05, "loss": 1.9031, "step": 2457 }, { "epoch": 7.36, "learning_rate": 1.236711e-05, "loss": 1.9037, "step": 2458 }, { "epoch": 7.36, "learning_rate": 1.2366405000000001e-05, "loss": 1.9028, "step": 2459 }, { "epoch": 7.37, "learning_rate": 1.2365700000000001e-05, "loss": 1.9032, "step": 2460 }, { "epoch": 7.37, "learning_rate": 1.2364995e-05, "loss": 1.9002, "step": 2461 }, { "epoch": 7.37, "learning_rate": 1.236429e-05, "loss": 1.8998, "step": 2462 }, { "epoch": 7.38, "learning_rate": 1.2363585e-05, "loss": 1.8987, "step": 2463 }, { "epoch": 7.38, "learning_rate": 1.236288e-05, "loss": 1.9021, "step": 2464 }, { "epoch": 7.38, "learning_rate": 1.2362175000000002e-05, "loss": 1.899, "step": 2465 }, { "epoch": 7.38, "learning_rate": 1.2361470000000001e-05, "loss": 1.9042, "step": 2466 }, { "epoch": 7.39, "learning_rate": 1.2360765000000001e-05, "loss": 1.9009, "step": 2467 }, { "epoch": 7.39, "learning_rate": 1.2360060000000001e-05, "loss": 1.9002, "step": 2468 }, { "epoch": 7.39, "learning_rate": 1.2359355000000001e-05, "loss": 1.9029, "step": 2469 }, { "epoch": 7.4, "learning_rate": 1.2358649999999999e-05, "loss": 1.8981, "step": 2470 }, { "epoch": 7.4, "learning_rate": 1.2357945e-05, "loss": 1.902, "step": 2471 }, { "epoch": 7.4, "learning_rate": 1.235724e-05, "loss": 1.8995, "step": 2472 }, { "epoch": 7.41, "learning_rate": 1.2356535e-05, "loss": 1.901, "step": 2473 }, { "epoch": 7.41, "learning_rate": 1.235583e-05, "loss": 1.8992, "step": 2474 }, { "epoch": 7.41, "learning_rate": 1.2355125e-05, "loss": 1.9008, "step": 2475 }, { "epoch": 7.41, "learning_rate": 1.235442e-05, "loss": 1.9009, "step": 2476 }, { "epoch": 7.42, "learning_rate": 1.2353715000000001e-05, "loss": 1.8997, "step": 2477 }, { "epoch": 7.42, "learning_rate": 1.235301e-05, "loss": 1.9008, "step": 2478 }, { "epoch": 7.42, "learning_rate": 1.2352305e-05, "loss": 1.9004, "step": 2479 }, { "epoch": 7.43, "learning_rate": 1.23516e-05, "loss": 1.8986, "step": 2480 }, { "epoch": 7.43, "learning_rate": 1.2350895e-05, "loss": 1.8986, "step": 2481 }, { "epoch": 7.43, "learning_rate": 1.235019e-05, "loss": 1.901, "step": 2482 }, { "epoch": 7.44, "learning_rate": 1.2349485e-05, "loss": 1.8983, "step": 2483 }, { "epoch": 7.44, "learning_rate": 1.2348780000000001e-05, "loss": 1.8973, "step": 2484 }, { "epoch": 7.44, "learning_rate": 1.2348075000000001e-05, "loss": 1.8989, "step": 2485 }, { "epoch": 7.44, "learning_rate": 1.2347370000000001e-05, "loss": 1.8988, "step": 2486 }, { "epoch": 7.45, "learning_rate": 1.2346665e-05, "loss": 1.9023, "step": 2487 }, { "epoch": 7.45, "learning_rate": 1.234596e-05, "loss": 1.899, "step": 2488 }, { "epoch": 7.45, "learning_rate": 1.2345255e-05, "loss": 1.902, "step": 2489 }, { "epoch": 7.46, "learning_rate": 1.234455e-05, "loss": 1.8997, "step": 2490 }, { "epoch": 7.46, "learning_rate": 1.2343845e-05, "loss": 1.8985, "step": 2491 }, { "epoch": 7.46, "learning_rate": 1.234314e-05, "loss": 1.8987, "step": 2492 }, { "epoch": 7.47, "learning_rate": 1.2342435e-05, "loss": 1.8973, "step": 2493 }, { "epoch": 7.47, "learning_rate": 1.234173e-05, "loss": 1.8981, "step": 2494 }, { "epoch": 7.47, "learning_rate": 1.2341025e-05, "loss": 1.8959, "step": 2495 }, { "epoch": 7.47, "learning_rate": 1.234032e-05, "loss": 1.9022, "step": 2496 }, { "epoch": 7.48, "learning_rate": 1.2339615e-05, "loss": 1.8996, "step": 2497 }, { "epoch": 7.48, "learning_rate": 1.233891e-05, "loss": 1.8983, "step": 2498 }, { "epoch": 7.48, "learning_rate": 1.2338205e-05, "loss": 1.9007, "step": 2499 }, { "epoch": 7.49, "learning_rate": 1.23375e-05, "loss": 1.8968, "step": 2500 }, { "epoch": 7.49, "eval_accuracy": 0.0005636535234899329, "eval_loss": 1.823848843574524, "eval_runtime": 34.0676, "eval_samples_per_second": 8.747, "eval_steps_per_second": 0.558, "step": 2500 }, { "epoch": 7.49, "learning_rate": 1.2336795e-05, "loss": 1.8998, "step": 2501 }, { "epoch": 7.49, "learning_rate": 1.2336090000000001e-05, "loss": 1.8973, "step": 2502 }, { "epoch": 7.5, "learning_rate": 1.2335385000000001e-05, "loss": 1.898, "step": 2503 }, { "epoch": 7.5, "learning_rate": 1.2334680000000001e-05, "loss": 1.898, "step": 2504 }, { "epoch": 7.5, "learning_rate": 1.2333975e-05, "loss": 1.8961, "step": 2505 }, { "epoch": 7.5, "learning_rate": 1.233327e-05, "loss": 1.8965, "step": 2506 }, { "epoch": 7.51, "learning_rate": 1.2332565e-05, "loss": 1.8996, "step": 2507 }, { "epoch": 7.51, "learning_rate": 1.2331860000000002e-05, "loss": 1.8965, "step": 2508 }, { "epoch": 7.51, "learning_rate": 1.2331155000000002e-05, "loss": 1.897, "step": 2509 }, { "epoch": 7.52, "learning_rate": 1.2330450000000002e-05, "loss": 1.8974, "step": 2510 }, { "epoch": 7.52, "learning_rate": 1.2329745e-05, "loss": 1.8959, "step": 2511 }, { "epoch": 7.52, "learning_rate": 1.232904e-05, "loss": 1.8981, "step": 2512 }, { "epoch": 7.53, "learning_rate": 1.2328335e-05, "loss": 1.896, "step": 2513 }, { "epoch": 7.53, "learning_rate": 1.232763e-05, "loss": 1.8969, "step": 2514 }, { "epoch": 7.53, "learning_rate": 1.2326925e-05, "loss": 1.8936, "step": 2515 }, { "epoch": 7.53, "learning_rate": 1.232622e-05, "loss": 1.8996, "step": 2516 }, { "epoch": 7.54, "learning_rate": 1.2325515e-05, "loss": 1.8971, "step": 2517 }, { "epoch": 7.54, "learning_rate": 1.232481e-05, "loss": 1.8945, "step": 2518 }, { "epoch": 7.54, "learning_rate": 1.2324105e-05, "loss": 1.8998, "step": 2519 }, { "epoch": 7.55, "learning_rate": 1.23234e-05, "loss": 1.899, "step": 2520 }, { "epoch": 7.55, "learning_rate": 1.2322695000000001e-05, "loss": 1.8974, "step": 2521 }, { "epoch": 7.55, "learning_rate": 1.2321990000000001e-05, "loss": 1.8966, "step": 2522 }, { "epoch": 7.56, "learning_rate": 1.2321285e-05, "loss": 1.8956, "step": 2523 }, { "epoch": 7.56, "learning_rate": 1.232058e-05, "loss": 1.8959, "step": 2524 }, { "epoch": 7.56, "learning_rate": 1.2319875e-05, "loss": 1.897, "step": 2525 }, { "epoch": 7.56, "learning_rate": 1.231917e-05, "loss": 1.8931, "step": 2526 }, { "epoch": 7.57, "learning_rate": 1.2318465000000002e-05, "loss": 1.8978, "step": 2527 }, { "epoch": 7.57, "learning_rate": 1.2317760000000001e-05, "loss": 1.8957, "step": 2528 }, { "epoch": 7.57, "learning_rate": 1.2317055000000001e-05, "loss": 1.8958, "step": 2529 }, { "epoch": 7.58, "learning_rate": 1.2316350000000001e-05, "loss": 1.8962, "step": 2530 }, { "epoch": 7.58, "learning_rate": 1.2315645e-05, "loss": 1.897, "step": 2531 }, { "epoch": 7.58, "learning_rate": 1.2314939999999999e-05, "loss": 1.8962, "step": 2532 }, { "epoch": 7.59, "learning_rate": 1.2314235e-05, "loss": 1.8956, "step": 2533 }, { "epoch": 7.59, "learning_rate": 1.231353e-05, "loss": 1.8973, "step": 2534 }, { "epoch": 7.59, "learning_rate": 1.2312825e-05, "loss": 1.8979, "step": 2535 }, { "epoch": 7.59, "learning_rate": 1.231212e-05, "loss": 1.8978, "step": 2536 }, { "epoch": 7.6, "learning_rate": 1.2311415e-05, "loss": 1.8958, "step": 2537 }, { "epoch": 7.6, "learning_rate": 1.231071e-05, "loss": 1.8957, "step": 2538 }, { "epoch": 7.6, "learning_rate": 1.2310005000000001e-05, "loss": 1.8958, "step": 2539 }, { "epoch": 7.61, "learning_rate": 1.2309300000000001e-05, "loss": 1.8948, "step": 2540 }, { "epoch": 7.61, "learning_rate": 1.2308595e-05, "loss": 1.8964, "step": 2541 }, { "epoch": 7.61, "learning_rate": 1.230789e-05, "loss": 1.8952, "step": 2542 }, { "epoch": 7.62, "learning_rate": 1.2307185e-05, "loss": 1.8967, "step": 2543 }, { "epoch": 7.62, "learning_rate": 1.230648e-05, "loss": 1.8954, "step": 2544 }, { "epoch": 7.62, "learning_rate": 1.2305775000000002e-05, "loss": 1.8978, "step": 2545 }, { "epoch": 7.62, "learning_rate": 1.2305070000000001e-05, "loss": 1.8935, "step": 2546 }, { "epoch": 7.63, "learning_rate": 1.2304365000000001e-05, "loss": 1.8942, "step": 2547 }, { "epoch": 7.63, "learning_rate": 1.2303660000000001e-05, "loss": 1.8962, "step": 2548 }, { "epoch": 7.63, "learning_rate": 1.2302955000000001e-05, "loss": 1.893, "step": 2549 }, { "epoch": 7.64, "learning_rate": 1.230225e-05, "loss": 1.8929, "step": 2550 }, { "epoch": 7.64, "learning_rate": 1.2301545e-05, "loss": 1.8949, "step": 2551 }, { "epoch": 7.64, "learning_rate": 1.230084e-05, "loss": 1.8931, "step": 2552 }, { "epoch": 7.65, "learning_rate": 1.2300135e-05, "loss": 1.8955, "step": 2553 }, { "epoch": 7.65, "learning_rate": 1.229943e-05, "loss": 1.8925, "step": 2554 }, { "epoch": 7.65, "learning_rate": 1.2298725e-05, "loss": 1.8939, "step": 2555 }, { "epoch": 7.65, "learning_rate": 1.229802e-05, "loss": 1.8941, "step": 2556 }, { "epoch": 7.66, "learning_rate": 1.2297315000000001e-05, "loss": 1.894, "step": 2557 }, { "epoch": 7.66, "learning_rate": 1.229661e-05, "loss": 1.8935, "step": 2558 }, { "epoch": 7.66, "learning_rate": 1.2295905e-05, "loss": 1.8927, "step": 2559 }, { "epoch": 7.67, "learning_rate": 1.22952e-05, "loss": 1.8943, "step": 2560 }, { "epoch": 7.67, "learning_rate": 1.2294495e-05, "loss": 1.8933, "step": 2561 }, { "epoch": 7.67, "learning_rate": 1.229379e-05, "loss": 1.8973, "step": 2562 }, { "epoch": 7.68, "learning_rate": 1.2293085e-05, "loss": 1.8928, "step": 2563 }, { "epoch": 7.68, "learning_rate": 1.2292380000000001e-05, "loss": 1.8933, "step": 2564 }, { "epoch": 7.68, "learning_rate": 1.2291675000000001e-05, "loss": 1.893, "step": 2565 }, { "epoch": 7.68, "learning_rate": 1.2290970000000001e-05, "loss": 1.8946, "step": 2566 }, { "epoch": 7.69, "learning_rate": 1.2290265e-05, "loss": 1.8928, "step": 2567 }, { "epoch": 7.69, "learning_rate": 1.228956e-05, "loss": 1.8911, "step": 2568 }, { "epoch": 7.69, "learning_rate": 1.2288855e-05, "loss": 1.8917, "step": 2569 }, { "epoch": 7.7, "learning_rate": 1.2288150000000002e-05, "loss": 1.8939, "step": 2570 }, { "epoch": 7.7, "learning_rate": 1.2287445e-05, "loss": 1.8946, "step": 2571 }, { "epoch": 7.7, "learning_rate": 1.228674e-05, "loss": 1.8954, "step": 2572 }, { "epoch": 7.71, "learning_rate": 1.2286035e-05, "loss": 1.8922, "step": 2573 }, { "epoch": 7.71, "learning_rate": 1.228533e-05, "loss": 1.8923, "step": 2574 }, { "epoch": 7.71, "learning_rate": 1.2284625e-05, "loss": 1.8926, "step": 2575 }, { "epoch": 7.71, "learning_rate": 1.228392e-05, "loss": 1.8954, "step": 2576 }, { "epoch": 7.72, "learning_rate": 1.2283215e-05, "loss": 1.8911, "step": 2577 }, { "epoch": 7.72, "learning_rate": 1.228251e-05, "loss": 1.893, "step": 2578 }, { "epoch": 7.72, "learning_rate": 1.2281805e-05, "loss": 1.8936, "step": 2579 }, { "epoch": 7.73, "learning_rate": 1.22811e-05, "loss": 1.8913, "step": 2580 }, { "epoch": 7.73, "learning_rate": 1.2280395e-05, "loss": 1.8908, "step": 2581 }, { "epoch": 7.73, "learning_rate": 1.2279690000000001e-05, "loss": 1.8954, "step": 2582 }, { "epoch": 7.73, "learning_rate": 1.2278985000000001e-05, "loss": 1.8888, "step": 2583 }, { "epoch": 7.74, "learning_rate": 1.2278280000000001e-05, "loss": 1.8923, "step": 2584 }, { "epoch": 7.74, "learning_rate": 1.2277575e-05, "loss": 1.8922, "step": 2585 }, { "epoch": 7.74, "learning_rate": 1.227687e-05, "loss": 1.8907, "step": 2586 }, { "epoch": 7.75, "learning_rate": 1.2276165e-05, "loss": 1.8901, "step": 2587 }, { "epoch": 7.75, "learning_rate": 1.227546e-05, "loss": 1.8929, "step": 2588 }, { "epoch": 7.75, "learning_rate": 1.2274755000000002e-05, "loss": 1.8952, "step": 2589 }, { "epoch": 7.76, "learning_rate": 1.2274050000000002e-05, "loss": 1.8921, "step": 2590 }, { "epoch": 7.76, "learning_rate": 1.2273345e-05, "loss": 1.8909, "step": 2591 }, { "epoch": 7.76, "learning_rate": 1.227264e-05, "loss": 1.8908, "step": 2592 }, { "epoch": 7.76, "learning_rate": 1.2271935e-05, "loss": 1.8932, "step": 2593 }, { "epoch": 7.77, "learning_rate": 1.227123e-05, "loss": 1.8943, "step": 2594 }, { "epoch": 7.77, "learning_rate": 1.2270525e-05, "loss": 1.8935, "step": 2595 }, { "epoch": 7.77, "learning_rate": 1.226982e-05, "loss": 1.892, "step": 2596 }, { "epoch": 7.78, "learning_rate": 1.2269115e-05, "loss": 1.8934, "step": 2597 }, { "epoch": 7.78, "learning_rate": 1.226841e-05, "loss": 1.8893, "step": 2598 }, { "epoch": 7.78, "learning_rate": 1.2267705e-05, "loss": 1.8911, "step": 2599 }, { "epoch": 7.79, "learning_rate": 1.2267e-05, "loss": 1.8914, "step": 2600 }, { "epoch": 7.79, "eval_accuracy": 0.0005570994127516778, "eval_loss": 1.8189831972122192, "eval_runtime": 36.9455, "eval_samples_per_second": 8.066, "eval_steps_per_second": 0.514, "step": 2600 }, { "epoch": 7.79, "learning_rate": 1.2266295000000001e-05, "loss": 1.8905, "step": 2601 }, { "epoch": 7.79, "learning_rate": 1.2265590000000001e-05, "loss": 1.8884, "step": 2602 }, { "epoch": 7.79, "learning_rate": 1.2264885e-05, "loss": 1.8899, "step": 2603 }, { "epoch": 7.8, "learning_rate": 1.226418e-05, "loss": 1.8926, "step": 2604 }, { "epoch": 7.8, "learning_rate": 1.2263475e-05, "loss": 1.8907, "step": 2605 }, { "epoch": 7.8, "learning_rate": 1.226277e-05, "loss": 1.8917, "step": 2606 }, { "epoch": 7.81, "learning_rate": 1.2262065000000002e-05, "loss": 1.8925, "step": 2607 }, { "epoch": 7.81, "learning_rate": 1.2261360000000001e-05, "loss": 1.8916, "step": 2608 }, { "epoch": 7.81, "learning_rate": 1.2260655000000001e-05, "loss": 1.8883, "step": 2609 }, { "epoch": 7.82, "learning_rate": 1.2259950000000001e-05, "loss": 1.8879, "step": 2610 }, { "epoch": 7.82, "learning_rate": 1.2259245e-05, "loss": 1.8923, "step": 2611 }, { "epoch": 7.82, "learning_rate": 1.2258539999999999e-05, "loss": 1.889, "step": 2612 }, { "epoch": 7.82, "learning_rate": 1.2257835e-05, "loss": 1.8893, "step": 2613 }, { "epoch": 7.83, "learning_rate": 1.225713e-05, "loss": 1.8913, "step": 2614 }, { "epoch": 7.83, "learning_rate": 1.2256425e-05, "loss": 1.8913, "step": 2615 }, { "epoch": 7.83, "learning_rate": 1.225572e-05, "loss": 1.8866, "step": 2616 }, { "epoch": 7.84, "learning_rate": 1.2255015e-05, "loss": 1.8915, "step": 2617 }, { "epoch": 7.84, "learning_rate": 1.225431e-05, "loss": 1.8883, "step": 2618 }, { "epoch": 7.84, "learning_rate": 1.2253605000000001e-05, "loss": 1.8906, "step": 2619 }, { "epoch": 7.85, "learning_rate": 1.2252900000000001e-05, "loss": 1.8901, "step": 2620 }, { "epoch": 7.85, "learning_rate": 1.2252195e-05, "loss": 1.89, "step": 2621 }, { "epoch": 7.85, "learning_rate": 1.225149e-05, "loss": 1.8902, "step": 2622 }, { "epoch": 7.85, "learning_rate": 1.2250785e-05, "loss": 1.8906, "step": 2623 }, { "epoch": 7.86, "learning_rate": 1.225008e-05, "loss": 1.8896, "step": 2624 }, { "epoch": 7.86, "learning_rate": 1.2249375e-05, "loss": 1.8915, "step": 2625 }, { "epoch": 7.86, "learning_rate": 1.2248670000000001e-05, "loss": 1.8909, "step": 2626 }, { "epoch": 7.87, "learning_rate": 1.2247965000000001e-05, "loss": 1.8893, "step": 2627 }, { "epoch": 7.87, "learning_rate": 1.2247260000000001e-05, "loss": 1.8901, "step": 2628 }, { "epoch": 7.87, "learning_rate": 1.2246555000000001e-05, "loss": 1.8899, "step": 2629 }, { "epoch": 7.88, "learning_rate": 1.224585e-05, "loss": 1.8903, "step": 2630 }, { "epoch": 7.88, "learning_rate": 1.2245145e-05, "loss": 1.8898, "step": 2631 }, { "epoch": 7.88, "learning_rate": 1.224444e-05, "loss": 1.8894, "step": 2632 }, { "epoch": 7.88, "learning_rate": 1.2243735e-05, "loss": 1.8884, "step": 2633 }, { "epoch": 7.89, "learning_rate": 1.224303e-05, "loss": 1.8875, "step": 2634 }, { "epoch": 7.89, "learning_rate": 1.2242325e-05, "loss": 1.8891, "step": 2635 }, { "epoch": 7.89, "learning_rate": 1.224162e-05, "loss": 1.8921, "step": 2636 }, { "epoch": 7.9, "learning_rate": 1.2240915e-05, "loss": 1.8889, "step": 2637 }, { "epoch": 7.9, "learning_rate": 1.224021e-05, "loss": 1.8917, "step": 2638 }, { "epoch": 7.9, "learning_rate": 1.2239505e-05, "loss": 1.8878, "step": 2639 }, { "epoch": 7.91, "learning_rate": 1.22388e-05, "loss": 1.8914, "step": 2640 }, { "epoch": 7.91, "learning_rate": 1.2238095e-05, "loss": 1.8885, "step": 2641 }, { "epoch": 7.91, "learning_rate": 1.223739e-05, "loss": 1.8885, "step": 2642 }, { "epoch": 7.91, "learning_rate": 1.2236685e-05, "loss": 1.8867, "step": 2643 }, { "epoch": 7.92, "learning_rate": 1.2235980000000001e-05, "loss": 1.8887, "step": 2644 }, { "epoch": 7.92, "learning_rate": 1.2235275000000001e-05, "loss": 1.8854, "step": 2645 }, { "epoch": 7.92, "learning_rate": 1.2234570000000001e-05, "loss": 1.8877, "step": 2646 }, { "epoch": 7.93, "learning_rate": 1.2233865e-05, "loss": 1.8891, "step": 2647 }, { "epoch": 7.93, "learning_rate": 1.223316e-05, "loss": 1.8902, "step": 2648 }, { "epoch": 7.93, "learning_rate": 1.2232455e-05, "loss": 1.8884, "step": 2649 }, { "epoch": 7.94, "learning_rate": 1.2231750000000002e-05, "loss": 1.8904, "step": 2650 }, { "epoch": 7.94, "learning_rate": 1.2231045000000002e-05, "loss": 1.888, "step": 2651 }, { "epoch": 7.94, "learning_rate": 1.223034e-05, "loss": 1.8877, "step": 2652 }, { "epoch": 7.94, "learning_rate": 1.2229635e-05, "loss": 1.8885, "step": 2653 }, { "epoch": 7.95, "learning_rate": 1.222893e-05, "loss": 1.8867, "step": 2654 }, { "epoch": 7.95, "learning_rate": 1.2228225e-05, "loss": 1.888, "step": 2655 }, { "epoch": 7.95, "learning_rate": 1.222752e-05, "loss": 1.8863, "step": 2656 }, { "epoch": 7.96, "learning_rate": 1.2226815e-05, "loss": 1.8849, "step": 2657 }, { "epoch": 7.96, "learning_rate": 1.222611e-05, "loss": 1.8866, "step": 2658 }, { "epoch": 7.96, "learning_rate": 1.2225405e-05, "loss": 1.8865, "step": 2659 }, { "epoch": 7.97, "learning_rate": 1.22247e-05, "loss": 1.8879, "step": 2660 }, { "epoch": 7.97, "learning_rate": 1.2223995e-05, "loss": 1.8874, "step": 2661 }, { "epoch": 7.97, "learning_rate": 1.2223290000000001e-05, "loss": 1.8874, "step": 2662 }, { "epoch": 7.97, "learning_rate": 1.2222585000000001e-05, "loss": 1.8869, "step": 2663 }, { "epoch": 7.98, "learning_rate": 1.2221880000000001e-05, "loss": 1.8877, "step": 2664 }, { "epoch": 7.98, "learning_rate": 1.2221175e-05, "loss": 1.8842, "step": 2665 }, { "epoch": 7.98, "learning_rate": 1.222047e-05, "loss": 1.887, "step": 2666 }, { "epoch": 7.99, "learning_rate": 1.2219765e-05, "loss": 1.8864, "step": 2667 }, { "epoch": 7.99, "learning_rate": 1.221906e-05, "loss": 1.8884, "step": 2668 }, { "epoch": 7.99, "learning_rate": 1.2218355000000002e-05, "loss": 1.8876, "step": 2669 }, { "epoch": 8.0, "learning_rate": 1.2217650000000002e-05, "loss": 1.8875, "step": 2670 }, { "epoch": 8.0, "learning_rate": 1.2216945000000001e-05, "loss": 1.8906, "step": 2671 }, { "epoch": 8.0, "learning_rate": 1.221624e-05, "loss": 1.8864, "step": 2672 }, { "epoch": 8.0, "learning_rate": 1.2215535e-05, "loss": 1.8854, "step": 2673 }, { "epoch": 8.01, "learning_rate": 1.2214829999999999e-05, "loss": 1.8888, "step": 2674 }, { "epoch": 8.01, "learning_rate": 1.2214125e-05, "loss": 1.8826, "step": 2675 }, { "epoch": 8.01, "learning_rate": 1.221342e-05, "loss": 1.8855, "step": 2676 }, { "epoch": 8.02, "learning_rate": 1.2212715e-05, "loss": 1.8878, "step": 2677 }, { "epoch": 8.02, "learning_rate": 1.221201e-05, "loss": 1.8852, "step": 2678 }, { "epoch": 8.02, "learning_rate": 1.2211305e-05, "loss": 1.885, "step": 2679 }, { "epoch": 8.03, "learning_rate": 1.22106e-05, "loss": 1.8902, "step": 2680 }, { "epoch": 8.03, "learning_rate": 1.2209895000000001e-05, "loss": 1.8852, "step": 2681 }, { "epoch": 8.03, "learning_rate": 1.2209190000000001e-05, "loss": 1.8877, "step": 2682 }, { "epoch": 8.03, "learning_rate": 1.2208485e-05, "loss": 1.8869, "step": 2683 }, { "epoch": 8.04, "learning_rate": 1.220778e-05, "loss": 1.8869, "step": 2684 }, { "epoch": 8.04, "learning_rate": 1.2207075e-05, "loss": 1.8846, "step": 2685 }, { "epoch": 8.04, "learning_rate": 1.220637e-05, "loss": 1.8843, "step": 2686 }, { "epoch": 8.05, "learning_rate": 1.2205665000000002e-05, "loss": 1.8872, "step": 2687 }, { "epoch": 8.05, "learning_rate": 1.2204960000000001e-05, "loss": 1.8879, "step": 2688 }, { "epoch": 8.05, "learning_rate": 1.2204255000000001e-05, "loss": 1.8871, "step": 2689 }, { "epoch": 8.06, "learning_rate": 1.2203550000000001e-05, "loss": 1.8864, "step": 2690 }, { "epoch": 8.06, "learning_rate": 1.2202845000000001e-05, "loss": 1.8845, "step": 2691 }, { "epoch": 8.06, "learning_rate": 1.2202139999999999e-05, "loss": 1.888, "step": 2692 }, { "epoch": 8.06, "learning_rate": 1.2201435e-05, "loss": 1.8862, "step": 2693 }, { "epoch": 8.07, "learning_rate": 1.220073e-05, "loss": 1.8848, "step": 2694 }, { "epoch": 8.07, "learning_rate": 1.2200025e-05, "loss": 1.8843, "step": 2695 }, { "epoch": 8.07, "learning_rate": 1.219932e-05, "loss": 1.8869, "step": 2696 }, { "epoch": 8.08, "learning_rate": 1.2198615e-05, "loss": 1.8874, "step": 2697 }, { "epoch": 8.08, "learning_rate": 1.219791e-05, "loss": 1.8872, "step": 2698 }, { "epoch": 8.08, "learning_rate": 1.2197205000000001e-05, "loss": 1.8859, "step": 2699 }, { "epoch": 8.09, "learning_rate": 1.2196500000000001e-05, "loss": 1.8818, "step": 2700 }, { "epoch": 8.09, "eval_accuracy": 0.0005570994127516778, "eval_loss": 1.8141815662384033, "eval_runtime": 29.5967, "eval_samples_per_second": 10.069, "eval_steps_per_second": 0.642, "step": 2700 }, { "epoch": 8.09, "learning_rate": 1.2195795e-05, "loss": 1.8836, "step": 2701 }, { "epoch": 8.09, "learning_rate": 1.219509e-05, "loss": 1.8846, "step": 2702 }, { "epoch": 8.09, "learning_rate": 1.2194385e-05, "loss": 1.8844, "step": 2703 }, { "epoch": 8.1, "learning_rate": 1.219368e-05, "loss": 1.8862, "step": 2704 }, { "epoch": 8.1, "learning_rate": 1.2192975e-05, "loss": 1.8842, "step": 2705 }, { "epoch": 8.1, "learning_rate": 1.2192270000000001e-05, "loss": 1.8832, "step": 2706 }, { "epoch": 8.11, "learning_rate": 1.2191565000000001e-05, "loss": 1.8863, "step": 2707 }, { "epoch": 8.11, "learning_rate": 1.2190860000000001e-05, "loss": 1.8834, "step": 2708 }, { "epoch": 8.11, "learning_rate": 1.2190155000000001e-05, "loss": 1.8835, "step": 2709 }, { "epoch": 8.12, "learning_rate": 1.218945e-05, "loss": 1.8843, "step": 2710 }, { "epoch": 8.12, "learning_rate": 1.2188745e-05, "loss": 1.8827, "step": 2711 }, { "epoch": 8.12, "learning_rate": 1.218804e-05, "loss": 1.8852, "step": 2712 }, { "epoch": 8.12, "learning_rate": 1.2187335e-05, "loss": 1.8855, "step": 2713 }, { "epoch": 8.13, "learning_rate": 1.218663e-05, "loss": 1.8828, "step": 2714 }, { "epoch": 8.13, "learning_rate": 1.2185925e-05, "loss": 1.8825, "step": 2715 }, { "epoch": 8.13, "learning_rate": 1.218522e-05, "loss": 1.8859, "step": 2716 }, { "epoch": 8.14, "learning_rate": 1.2184515e-05, "loss": 1.8839, "step": 2717 }, { "epoch": 8.14, "learning_rate": 1.218381e-05, "loss": 1.8852, "step": 2718 }, { "epoch": 8.14, "learning_rate": 1.2183105e-05, "loss": 1.8846, "step": 2719 }, { "epoch": 8.15, "learning_rate": 1.21824e-05, "loss": 1.8844, "step": 2720 }, { "epoch": 8.15, "learning_rate": 1.2181695e-05, "loss": 1.8845, "step": 2721 }, { "epoch": 8.15, "learning_rate": 1.218099e-05, "loss": 1.8827, "step": 2722 }, { "epoch": 8.15, "learning_rate": 1.2180285e-05, "loss": 1.8866, "step": 2723 }, { "epoch": 8.16, "learning_rate": 1.2179580000000001e-05, "loss": 1.8831, "step": 2724 }, { "epoch": 8.16, "learning_rate": 1.2178875000000001e-05, "loss": 1.8806, "step": 2725 }, { "epoch": 8.16, "learning_rate": 1.2178170000000001e-05, "loss": 1.884, "step": 2726 }, { "epoch": 8.17, "learning_rate": 1.2177465e-05, "loss": 1.8846, "step": 2727 }, { "epoch": 8.17, "learning_rate": 1.217676e-05, "loss": 1.8825, "step": 2728 }, { "epoch": 8.17, "learning_rate": 1.2176055e-05, "loss": 1.8814, "step": 2729 }, { "epoch": 8.18, "learning_rate": 1.2175350000000002e-05, "loss": 1.8817, "step": 2730 }, { "epoch": 8.18, "learning_rate": 1.2174645000000002e-05, "loss": 1.8844, "step": 2731 }, { "epoch": 8.18, "learning_rate": 1.217394e-05, "loss": 1.8827, "step": 2732 }, { "epoch": 8.18, "learning_rate": 1.2173235e-05, "loss": 1.8838, "step": 2733 }, { "epoch": 8.19, "learning_rate": 1.217253e-05, "loss": 1.8825, "step": 2734 }, { "epoch": 8.19, "learning_rate": 1.2171825e-05, "loss": 1.8855, "step": 2735 }, { "epoch": 8.19, "learning_rate": 1.217112e-05, "loss": 1.8826, "step": 2736 }, { "epoch": 8.2, "learning_rate": 1.2170415e-05, "loss": 1.8814, "step": 2737 }, { "epoch": 8.2, "learning_rate": 1.216971e-05, "loss": 1.8815, "step": 2738 }, { "epoch": 8.2, "learning_rate": 1.2169005e-05, "loss": 1.8825, "step": 2739 }, { "epoch": 8.21, "learning_rate": 1.21683e-05, "loss": 1.8833, "step": 2740 }, { "epoch": 8.21, "learning_rate": 1.2167595e-05, "loss": 1.8832, "step": 2741 }, { "epoch": 8.21, "learning_rate": 1.216689e-05, "loss": 1.8801, "step": 2742 }, { "epoch": 8.21, "learning_rate": 1.2166185000000001e-05, "loss": 1.8815, "step": 2743 }, { "epoch": 8.22, "learning_rate": 1.2165480000000001e-05, "loss": 1.8821, "step": 2744 }, { "epoch": 8.22, "learning_rate": 1.2164775e-05, "loss": 1.8821, "step": 2745 }, { "epoch": 8.22, "learning_rate": 1.216407e-05, "loss": 1.8825, "step": 2746 }, { "epoch": 8.23, "learning_rate": 1.2163365e-05, "loss": 1.883, "step": 2747 }, { "epoch": 8.23, "learning_rate": 1.216266e-05, "loss": 1.8845, "step": 2748 }, { "epoch": 8.23, "learning_rate": 1.2161955000000002e-05, "loss": 1.8814, "step": 2749 }, { "epoch": 8.24, "learning_rate": 1.2161250000000002e-05, "loss": 1.8835, "step": 2750 }, { "epoch": 8.24, "learning_rate": 1.2160545000000001e-05, "loss": 1.8804, "step": 2751 }, { "epoch": 8.24, "learning_rate": 1.2159840000000001e-05, "loss": 1.879, "step": 2752 }, { "epoch": 8.24, "learning_rate": 1.2159135e-05, "loss": 1.8795, "step": 2753 }, { "epoch": 8.25, "learning_rate": 1.2158429999999999e-05, "loss": 1.882, "step": 2754 }, { "epoch": 8.25, "learning_rate": 1.2157725e-05, "loss": 1.8838, "step": 2755 }, { "epoch": 8.25, "learning_rate": 1.215702e-05, "loss": 1.8807, "step": 2756 }, { "epoch": 8.26, "learning_rate": 1.2156315e-05, "loss": 1.8794, "step": 2757 }, { "epoch": 8.26, "learning_rate": 1.215561e-05, "loss": 1.8808, "step": 2758 }, { "epoch": 8.26, "learning_rate": 1.2154905e-05, "loss": 1.8838, "step": 2759 }, { "epoch": 8.27, "learning_rate": 1.21542e-05, "loss": 1.8817, "step": 2760 }, { "epoch": 8.27, "learning_rate": 1.2153495000000001e-05, "loss": 1.8783, "step": 2761 }, { "epoch": 8.27, "learning_rate": 1.2152790000000001e-05, "loss": 1.8811, "step": 2762 }, { "epoch": 8.27, "learning_rate": 1.2152085e-05, "loss": 1.8831, "step": 2763 }, { "epoch": 8.28, "learning_rate": 1.215138e-05, "loss": 1.8819, "step": 2764 }, { "epoch": 8.28, "learning_rate": 1.2150675e-05, "loss": 1.8813, "step": 2765 }, { "epoch": 8.28, "learning_rate": 1.214997e-05, "loss": 1.8814, "step": 2766 }, { "epoch": 8.29, "learning_rate": 1.2149265000000002e-05, "loss": 1.88, "step": 2767 }, { "epoch": 8.29, "learning_rate": 1.2148560000000001e-05, "loss": 1.8812, "step": 2768 }, { "epoch": 8.29, "learning_rate": 1.2147855000000001e-05, "loss": 1.8796, "step": 2769 }, { "epoch": 8.29, "learning_rate": 1.2147150000000001e-05, "loss": 1.8806, "step": 2770 }, { "epoch": 8.3, "learning_rate": 1.2146445000000001e-05, "loss": 1.8778, "step": 2771 }, { "epoch": 8.3, "learning_rate": 1.214574e-05, "loss": 1.8813, "step": 2772 }, { "epoch": 8.3, "learning_rate": 1.2145035e-05, "loss": 1.8812, "step": 2773 }, { "epoch": 8.31, "learning_rate": 1.214433e-05, "loss": 1.8818, "step": 2774 }, { "epoch": 8.31, "learning_rate": 1.2143625e-05, "loss": 1.8824, "step": 2775 }, { "epoch": 8.31, "learning_rate": 1.214292e-05, "loss": 1.8826, "step": 2776 }, { "epoch": 8.32, "learning_rate": 1.2142215e-05, "loss": 1.8839, "step": 2777 }, { "epoch": 8.32, "learning_rate": 1.214151e-05, "loss": 1.8817, "step": 2778 }, { "epoch": 8.32, "learning_rate": 1.2140805e-05, "loss": 1.8791, "step": 2779 }, { "epoch": 8.32, "learning_rate": 1.2140100000000001e-05, "loss": 1.8796, "step": 2780 }, { "epoch": 8.33, "learning_rate": 1.2139395e-05, "loss": 1.8807, "step": 2781 }, { "epoch": 8.33, "learning_rate": 1.213869e-05, "loss": 1.8816, "step": 2782 }, { "epoch": 8.33, "learning_rate": 1.2137985e-05, "loss": 1.8778, "step": 2783 }, { "epoch": 8.34, "learning_rate": 1.213728e-05, "loss": 1.8801, "step": 2784 }, { "epoch": 8.34, "learning_rate": 1.2136575e-05, "loss": 1.8803, "step": 2785 }, { "epoch": 8.34, "learning_rate": 1.2135870000000001e-05, "loss": 1.8803, "step": 2786 }, { "epoch": 8.35, "learning_rate": 1.2135165000000001e-05, "loss": 1.8761, "step": 2787 }, { "epoch": 8.35, "learning_rate": 1.2134460000000001e-05, "loss": 1.882, "step": 2788 }, { "epoch": 8.35, "learning_rate": 1.2133755000000001e-05, "loss": 1.8788, "step": 2789 }, { "epoch": 8.35, "learning_rate": 1.213305e-05, "loss": 1.8814, "step": 2790 }, { "epoch": 8.36, "learning_rate": 1.2132345e-05, "loss": 1.8803, "step": 2791 }, { "epoch": 8.36, "learning_rate": 1.2131640000000002e-05, "loss": 1.8793, "step": 2792 }, { "epoch": 8.36, "learning_rate": 1.2130935e-05, "loss": 1.876, "step": 2793 }, { "epoch": 8.37, "learning_rate": 1.213023e-05, "loss": 1.879, "step": 2794 }, { "epoch": 8.37, "learning_rate": 1.2129525e-05, "loss": 1.8774, "step": 2795 }, { "epoch": 8.37, "learning_rate": 1.212882e-05, "loss": 1.8795, "step": 2796 }, { "epoch": 8.38, "learning_rate": 1.2128115e-05, "loss": 1.8785, "step": 2797 }, { "epoch": 8.38, "learning_rate": 1.212741e-05, "loss": 1.8793, "step": 2798 }, { "epoch": 8.38, "learning_rate": 1.2126705e-05, "loss": 1.8797, "step": 2799 }, { "epoch": 8.38, "learning_rate": 1.2126e-05, "loss": 1.8793, "step": 2800 }, { "epoch": 8.38, "eval_accuracy": 0.000570207634228188, "eval_loss": 1.809898853302002, "eval_runtime": 29.2533, "eval_samples_per_second": 10.187, "eval_steps_per_second": 0.649, "step": 2800 }, { "epoch": 8.39, "learning_rate": 1.2125295e-05, "loss": 1.8779, "step": 2801 }, { "epoch": 8.39, "learning_rate": 1.212459e-05, "loss": 1.8781, "step": 2802 }, { "epoch": 8.39, "learning_rate": 1.2123885e-05, "loss": 1.8757, "step": 2803 }, { "epoch": 8.4, "learning_rate": 1.2123180000000001e-05, "loss": 1.8801, "step": 2804 }, { "epoch": 8.4, "learning_rate": 1.2122475000000001e-05, "loss": 1.8764, "step": 2805 }, { "epoch": 8.4, "learning_rate": 1.2121770000000001e-05, "loss": 1.8786, "step": 2806 }, { "epoch": 8.41, "learning_rate": 1.2121065e-05, "loss": 1.8804, "step": 2807 }, { "epoch": 8.41, "learning_rate": 1.212036e-05, "loss": 1.8794, "step": 2808 }, { "epoch": 8.41, "learning_rate": 1.2119655e-05, "loss": 1.8807, "step": 2809 }, { "epoch": 8.41, "learning_rate": 1.211895e-05, "loss": 1.8796, "step": 2810 }, { "epoch": 8.42, "learning_rate": 1.2118245000000002e-05, "loss": 1.8824, "step": 2811 }, { "epoch": 8.42, "learning_rate": 1.2117540000000002e-05, "loss": 1.8776, "step": 2812 }, { "epoch": 8.42, "learning_rate": 1.2116835e-05, "loss": 1.8792, "step": 2813 }, { "epoch": 8.43, "learning_rate": 1.211613e-05, "loss": 1.8743, "step": 2814 }, { "epoch": 8.43, "learning_rate": 1.2115425e-05, "loss": 1.8777, "step": 2815 }, { "epoch": 8.43, "learning_rate": 1.2114719999999999e-05, "loss": 1.8789, "step": 2816 }, { "epoch": 8.44, "learning_rate": 1.2114015e-05, "loss": 1.8809, "step": 2817 }, { "epoch": 8.44, "learning_rate": 1.211331e-05, "loss": 1.8756, "step": 2818 }, { "epoch": 8.44, "learning_rate": 1.2112605e-05, "loss": 1.8769, "step": 2819 }, { "epoch": 8.44, "learning_rate": 1.21119e-05, "loss": 1.878, "step": 2820 }, { "epoch": 8.45, "learning_rate": 1.2111195e-05, "loss": 1.8779, "step": 2821 }, { "epoch": 8.45, "learning_rate": 1.211049e-05, "loss": 1.8773, "step": 2822 }, { "epoch": 8.45, "learning_rate": 1.2109785000000001e-05, "loss": 1.8807, "step": 2823 }, { "epoch": 8.46, "learning_rate": 1.2109080000000001e-05, "loss": 1.8765, "step": 2824 }, { "epoch": 8.46, "learning_rate": 1.2108375e-05, "loss": 1.8793, "step": 2825 }, { "epoch": 8.46, "learning_rate": 1.210767e-05, "loss": 1.8774, "step": 2826 }, { "epoch": 8.47, "learning_rate": 1.2106965e-05, "loss": 1.8772, "step": 2827 }, { "epoch": 8.47, "learning_rate": 1.210626e-05, "loss": 1.8791, "step": 2828 }, { "epoch": 8.47, "learning_rate": 1.2105555000000002e-05, "loss": 1.8765, "step": 2829 }, { "epoch": 8.47, "learning_rate": 1.2104850000000002e-05, "loss": 1.8749, "step": 2830 }, { "epoch": 8.48, "learning_rate": 1.2104145000000001e-05, "loss": 1.8758, "step": 2831 }, { "epoch": 8.48, "learning_rate": 1.2103440000000001e-05, "loss": 1.8771, "step": 2832 }, { "epoch": 8.48, "learning_rate": 1.2102735e-05, "loss": 1.8788, "step": 2833 }, { "epoch": 8.49, "learning_rate": 1.2102029999999999e-05, "loss": 1.8767, "step": 2834 }, { "epoch": 8.49, "learning_rate": 1.2101325e-05, "loss": 1.876, "step": 2835 }, { "epoch": 8.49, "learning_rate": 1.210062e-05, "loss": 1.8757, "step": 2836 }, { "epoch": 8.5, "learning_rate": 1.2099915e-05, "loss": 1.877, "step": 2837 }, { "epoch": 8.5, "learning_rate": 1.209921e-05, "loss": 1.8776, "step": 2838 }, { "epoch": 8.5, "learning_rate": 1.2098505e-05, "loss": 1.877, "step": 2839 }, { "epoch": 8.5, "learning_rate": 1.20978e-05, "loss": 1.8766, "step": 2840 }, { "epoch": 8.51, "learning_rate": 1.2097095000000001e-05, "loss": 1.8765, "step": 2841 }, { "epoch": 8.51, "learning_rate": 1.2096390000000001e-05, "loss": 1.8763, "step": 2842 }, { "epoch": 8.51, "learning_rate": 1.2095685e-05, "loss": 1.8761, "step": 2843 }, { "epoch": 8.52, "learning_rate": 1.209498e-05, "loss": 1.8768, "step": 2844 }, { "epoch": 8.52, "learning_rate": 1.2094275e-05, "loss": 1.8765, "step": 2845 }, { "epoch": 8.52, "learning_rate": 1.209357e-05, "loss": 1.8747, "step": 2846 }, { "epoch": 8.53, "learning_rate": 1.2092865e-05, "loss": 1.8773, "step": 2847 }, { "epoch": 8.53, "learning_rate": 1.2092160000000001e-05, "loss": 1.8758, "step": 2848 }, { "epoch": 8.53, "learning_rate": 1.2091455000000001e-05, "loss": 1.8773, "step": 2849 }, { "epoch": 8.53, "learning_rate": 1.2090750000000001e-05, "loss": 1.8759, "step": 2850 }, { "epoch": 8.54, "learning_rate": 1.2090045000000001e-05, "loss": 1.8757, "step": 2851 }, { "epoch": 8.54, "learning_rate": 1.208934e-05, "loss": 1.8777, "step": 2852 }, { "epoch": 8.54, "learning_rate": 1.2088635e-05, "loss": 1.8737, "step": 2853 }, { "epoch": 8.55, "learning_rate": 1.208793e-05, "loss": 1.8762, "step": 2854 }, { "epoch": 8.55, "learning_rate": 1.2087225e-05, "loss": 1.8764, "step": 2855 }, { "epoch": 8.55, "learning_rate": 1.208652e-05, "loss": 1.8744, "step": 2856 }, { "epoch": 8.56, "learning_rate": 1.2085815e-05, "loss": 1.8774, "step": 2857 }, { "epoch": 8.56, "learning_rate": 1.208511e-05, "loss": 1.8748, "step": 2858 }, { "epoch": 8.56, "learning_rate": 1.2084405e-05, "loss": 1.8748, "step": 2859 }, { "epoch": 8.56, "learning_rate": 1.2083700000000001e-05, "loss": 1.8746, "step": 2860 }, { "epoch": 8.57, "learning_rate": 1.2082995e-05, "loss": 1.8763, "step": 2861 }, { "epoch": 8.57, "learning_rate": 1.208229e-05, "loss": 1.8721, "step": 2862 }, { "epoch": 8.57, "learning_rate": 1.2081585e-05, "loss": 1.8771, "step": 2863 }, { "epoch": 8.58, "learning_rate": 1.208088e-05, "loss": 1.8742, "step": 2864 }, { "epoch": 8.58, "learning_rate": 1.2080175e-05, "loss": 1.8742, "step": 2865 }, { "epoch": 8.58, "learning_rate": 1.2079470000000001e-05, "loss": 1.8744, "step": 2866 }, { "epoch": 8.59, "learning_rate": 1.2078765000000001e-05, "loss": 1.876, "step": 2867 }, { "epoch": 8.59, "learning_rate": 1.2078060000000001e-05, "loss": 1.8757, "step": 2868 }, { "epoch": 8.59, "learning_rate": 1.2077355000000001e-05, "loss": 1.8757, "step": 2869 }, { "epoch": 8.59, "learning_rate": 1.207665e-05, "loss": 1.8756, "step": 2870 }, { "epoch": 8.6, "learning_rate": 1.2075945e-05, "loss": 1.8743, "step": 2871 }, { "epoch": 8.6, "learning_rate": 1.2075240000000002e-05, "loss": 1.8763, "step": 2872 }, { "epoch": 8.6, "learning_rate": 1.2074535e-05, "loss": 1.876, "step": 2873 }, { "epoch": 8.61, "learning_rate": 1.207383e-05, "loss": 1.8746, "step": 2874 }, { "epoch": 8.61, "learning_rate": 1.2073125e-05, "loss": 1.8727, "step": 2875 }, { "epoch": 8.61, "learning_rate": 1.207242e-05, "loss": 1.8766, "step": 2876 }, { "epoch": 8.62, "learning_rate": 1.2071715e-05, "loss": 1.8733, "step": 2877 }, { "epoch": 8.62, "learning_rate": 1.207101e-05, "loss": 1.875, "step": 2878 }, { "epoch": 8.62, "learning_rate": 1.2070305e-05, "loss": 1.8761, "step": 2879 }, { "epoch": 8.62, "learning_rate": 1.20696e-05, "loss": 1.8756, "step": 2880 }, { "epoch": 8.63, "learning_rate": 1.2068895e-05, "loss": 1.8765, "step": 2881 }, { "epoch": 8.63, "learning_rate": 1.206819e-05, "loss": 1.8745, "step": 2882 }, { "epoch": 8.63, "learning_rate": 1.2067485e-05, "loss": 1.8737, "step": 2883 }, { "epoch": 8.64, "learning_rate": 1.206678e-05, "loss": 1.8748, "step": 2884 }, { "epoch": 8.64, "learning_rate": 1.2066075000000001e-05, "loss": 1.8773, "step": 2885 }, { "epoch": 8.64, "learning_rate": 1.2065370000000001e-05, "loss": 1.8753, "step": 2886 }, { "epoch": 8.65, "learning_rate": 1.2064665e-05, "loss": 1.8744, "step": 2887 }, { "epoch": 8.65, "learning_rate": 1.206396e-05, "loss": 1.8761, "step": 2888 }, { "epoch": 8.65, "learning_rate": 1.2063255e-05, "loss": 1.8718, "step": 2889 }, { "epoch": 8.65, "learning_rate": 1.206255e-05, "loss": 1.873, "step": 2890 }, { "epoch": 8.66, "learning_rate": 1.2061845000000002e-05, "loss": 1.8746, "step": 2891 }, { "epoch": 8.66, "learning_rate": 1.2061140000000002e-05, "loss": 1.8727, "step": 2892 }, { "epoch": 8.66, "learning_rate": 1.2060435000000001e-05, "loss": 1.8751, "step": 2893 }, { "epoch": 8.67, "learning_rate": 1.205973e-05, "loss": 1.8751, "step": 2894 }, { "epoch": 8.67, "learning_rate": 1.2059025e-05, "loss": 1.8761, "step": 2895 }, { "epoch": 8.67, "learning_rate": 1.2058319999999999e-05, "loss": 1.8741, "step": 2896 }, { "epoch": 8.68, "learning_rate": 1.2057615e-05, "loss": 1.8752, "step": 2897 }, { "epoch": 8.68, "learning_rate": 1.205691e-05, "loss": 1.8749, "step": 2898 }, { "epoch": 8.68, "learning_rate": 1.2056205e-05, "loss": 1.876, "step": 2899 }, { "epoch": 8.68, "learning_rate": 1.20555e-05, "loss": 1.8736, "step": 2900 }, { "epoch": 8.68, "eval_accuracy": 0.000570207634228188, "eval_loss": 1.8057316541671753, "eval_runtime": 29.4252, "eval_samples_per_second": 10.127, "eval_steps_per_second": 0.646, "step": 2900 }, { "epoch": 8.69, "learning_rate": 1.2054795e-05, "loss": 1.8748, "step": 2901 }, { "epoch": 8.69, "learning_rate": 1.205409e-05, "loss": 1.8739, "step": 2902 }, { "epoch": 8.69, "learning_rate": 1.2053385000000001e-05, "loss": 1.8706, "step": 2903 }, { "epoch": 8.7, "learning_rate": 1.2052680000000001e-05, "loss": 1.8745, "step": 2904 }, { "epoch": 8.7, "learning_rate": 1.2051975e-05, "loss": 1.8745, "step": 2905 }, { "epoch": 8.7, "learning_rate": 1.205127e-05, "loss": 1.8713, "step": 2906 }, { "epoch": 8.71, "learning_rate": 1.2050565e-05, "loss": 1.8745, "step": 2907 }, { "epoch": 8.71, "learning_rate": 1.204986e-05, "loss": 1.8745, "step": 2908 }, { "epoch": 8.71, "learning_rate": 1.2049155000000002e-05, "loss": 1.8753, "step": 2909 }, { "epoch": 8.71, "learning_rate": 1.2048450000000002e-05, "loss": 1.8735, "step": 2910 }, { "epoch": 8.72, "learning_rate": 1.2047745000000001e-05, "loss": 1.8735, "step": 2911 }, { "epoch": 8.72, "learning_rate": 1.2047040000000001e-05, "loss": 1.8759, "step": 2912 }, { "epoch": 8.72, "learning_rate": 1.2046335000000001e-05, "loss": 1.8719, "step": 2913 }, { "epoch": 8.73, "learning_rate": 1.2045629999999999e-05, "loss": 1.8742, "step": 2914 }, { "epoch": 8.73, "learning_rate": 1.2044925e-05, "loss": 1.8732, "step": 2915 }, { "epoch": 8.73, "learning_rate": 1.204422e-05, "loss": 1.8711, "step": 2916 }, { "epoch": 8.74, "learning_rate": 1.2043515e-05, "loss": 1.8725, "step": 2917 }, { "epoch": 8.74, "learning_rate": 1.204281e-05, "loss": 1.8726, "step": 2918 }, { "epoch": 8.74, "learning_rate": 1.2042105e-05, "loss": 1.8739, "step": 2919 }, { "epoch": 8.74, "learning_rate": 1.20414e-05, "loss": 1.8727, "step": 2920 }, { "epoch": 8.75, "learning_rate": 1.2040695000000001e-05, "loss": 1.8737, "step": 2921 }, { "epoch": 8.75, "learning_rate": 1.2039990000000001e-05, "loss": 1.8706, "step": 2922 }, { "epoch": 8.75, "learning_rate": 1.2039285e-05, "loss": 1.8735, "step": 2923 }, { "epoch": 8.76, "learning_rate": 1.203858e-05, "loss": 1.8713, "step": 2924 }, { "epoch": 8.76, "learning_rate": 1.2037875e-05, "loss": 1.8729, "step": 2925 }, { "epoch": 8.76, "learning_rate": 1.203717e-05, "loss": 1.8751, "step": 2926 }, { "epoch": 8.77, "learning_rate": 1.2036465e-05, "loss": 1.8699, "step": 2927 }, { "epoch": 8.77, "learning_rate": 1.2035760000000001e-05, "loss": 1.8706, "step": 2928 }, { "epoch": 8.77, "learning_rate": 1.2035055000000001e-05, "loss": 1.8707, "step": 2929 }, { "epoch": 8.77, "learning_rate": 1.2034350000000001e-05, "loss": 1.8706, "step": 2930 }, { "epoch": 8.78, "learning_rate": 1.2033645000000001e-05, "loss": 1.8716, "step": 2931 }, { "epoch": 8.78, "learning_rate": 1.203294e-05, "loss": 1.8727, "step": 2932 }, { "epoch": 8.78, "learning_rate": 1.2032235e-05, "loss": 1.8709, "step": 2933 }, { "epoch": 8.79, "learning_rate": 1.203153e-05, "loss": 1.8698, "step": 2934 }, { "epoch": 8.79, "learning_rate": 1.2030825e-05, "loss": 1.8725, "step": 2935 }, { "epoch": 8.79, "learning_rate": 1.203012e-05, "loss": 1.8747, "step": 2936 }, { "epoch": 8.8, "learning_rate": 1.2029415e-05, "loss": 1.8708, "step": 2937 }, { "epoch": 8.8, "learning_rate": 1.202871e-05, "loss": 1.8713, "step": 2938 }, { "epoch": 8.8, "learning_rate": 1.2028005e-05, "loss": 1.8727, "step": 2939 }, { "epoch": 8.8, "learning_rate": 1.2027300000000001e-05, "loss": 1.8723, "step": 2940 }, { "epoch": 8.81, "learning_rate": 1.2026595e-05, "loss": 1.8695, "step": 2941 }, { "epoch": 8.81, "learning_rate": 1.202589e-05, "loss": 1.8703, "step": 2942 }, { "epoch": 8.81, "learning_rate": 1.2025185e-05, "loss": 1.8713, "step": 2943 }, { "epoch": 8.82, "learning_rate": 1.202448e-05, "loss": 1.8732, "step": 2944 }, { "epoch": 8.82, "learning_rate": 1.2023775e-05, "loss": 1.8705, "step": 2945 }, { "epoch": 8.82, "learning_rate": 1.2023070000000001e-05, "loss": 1.8692, "step": 2946 }, { "epoch": 8.83, "learning_rate": 1.2022365000000001e-05, "loss": 1.8705, "step": 2947 }, { "epoch": 8.83, "learning_rate": 1.2021660000000001e-05, "loss": 1.8701, "step": 2948 }, { "epoch": 8.83, "learning_rate": 1.2020955000000001e-05, "loss": 1.87, "step": 2949 }, { "epoch": 8.83, "learning_rate": 1.202025e-05, "loss": 1.8677, "step": 2950 }, { "epoch": 8.84, "learning_rate": 1.2019545e-05, "loss": 1.8722, "step": 2951 }, { "epoch": 8.84, "learning_rate": 1.201884e-05, "loss": 1.871, "step": 2952 }, { "epoch": 8.84, "learning_rate": 1.2018135000000002e-05, "loss": 1.8716, "step": 2953 }, { "epoch": 8.85, "learning_rate": 1.201743e-05, "loss": 1.8697, "step": 2954 }, { "epoch": 8.85, "learning_rate": 1.2016725e-05, "loss": 1.8718, "step": 2955 }, { "epoch": 8.85, "learning_rate": 1.201602e-05, "loss": 1.8689, "step": 2956 }, { "epoch": 8.85, "learning_rate": 1.2015315e-05, "loss": 1.8698, "step": 2957 }, { "epoch": 8.86, "learning_rate": 1.201461e-05, "loss": 1.868, "step": 2958 }, { "epoch": 8.86, "learning_rate": 1.2013905e-05, "loss": 1.868, "step": 2959 }, { "epoch": 8.86, "learning_rate": 1.20132e-05, "loss": 1.8702, "step": 2960 }, { "epoch": 8.87, "learning_rate": 1.2012495e-05, "loss": 1.8685, "step": 2961 }, { "epoch": 8.87, "learning_rate": 1.201179e-05, "loss": 1.8703, "step": 2962 }, { "epoch": 8.87, "learning_rate": 1.2011085e-05, "loss": 1.8713, "step": 2963 }, { "epoch": 8.88, "learning_rate": 1.201038e-05, "loss": 1.8697, "step": 2964 }, { "epoch": 8.88, "learning_rate": 1.2009675000000001e-05, "loss": 1.8707, "step": 2965 }, { "epoch": 8.88, "learning_rate": 1.2008970000000001e-05, "loss": 1.8682, "step": 2966 }, { "epoch": 8.88, "learning_rate": 1.2008265e-05, "loss": 1.8721, "step": 2967 }, { "epoch": 8.89, "learning_rate": 1.200756e-05, "loss": 1.8674, "step": 2968 }, { "epoch": 8.89, "learning_rate": 1.2006855e-05, "loss": 1.8703, "step": 2969 }, { "epoch": 8.89, "learning_rate": 1.200615e-05, "loss": 1.8717, "step": 2970 }, { "epoch": 8.9, "learning_rate": 1.2005445000000002e-05, "loss": 1.8691, "step": 2971 }, { "epoch": 8.9, "learning_rate": 1.2004740000000002e-05, "loss": 1.8681, "step": 2972 }, { "epoch": 8.9, "learning_rate": 1.2004035000000001e-05, "loss": 1.8691, "step": 2973 }, { "epoch": 8.91, "learning_rate": 1.200333e-05, "loss": 1.8678, "step": 2974 }, { "epoch": 8.91, "learning_rate": 1.2002625e-05, "loss": 1.8711, "step": 2975 }, { "epoch": 8.91, "learning_rate": 1.2001919999999999e-05, "loss": 1.8699, "step": 2976 }, { "epoch": 8.91, "learning_rate": 1.2001215e-05, "loss": 1.8694, "step": 2977 }, { "epoch": 8.92, "learning_rate": 1.200051e-05, "loss": 1.8655, "step": 2978 }, { "epoch": 8.92, "learning_rate": 1.1999805e-05, "loss": 1.8682, "step": 2979 }, { "epoch": 8.92, "learning_rate": 1.19991e-05, "loss": 1.8711, "step": 2980 }, { "epoch": 8.93, "learning_rate": 1.1998395e-05, "loss": 1.8673, "step": 2981 }, { "epoch": 8.93, "learning_rate": 1.199769e-05, "loss": 1.8695, "step": 2982 }, { "epoch": 8.93, "learning_rate": 1.1996985000000001e-05, "loss": 1.87, "step": 2983 }, { "epoch": 8.94, "learning_rate": 1.1996280000000001e-05, "loss": 1.8693, "step": 2984 }, { "epoch": 8.94, "learning_rate": 1.1995575e-05, "loss": 1.87, "step": 2985 }, { "epoch": 8.94, "learning_rate": 1.199487e-05, "loss": 1.8709, "step": 2986 }, { "epoch": 8.94, "learning_rate": 1.1994165e-05, "loss": 1.8697, "step": 2987 }, { "epoch": 8.95, "learning_rate": 1.199346e-05, "loss": 1.8708, "step": 2988 }, { "epoch": 8.95, "learning_rate": 1.1992755e-05, "loss": 1.8701, "step": 2989 }, { "epoch": 8.95, "learning_rate": 1.1992050000000002e-05, "loss": 1.8684, "step": 2990 }, { "epoch": 8.96, "learning_rate": 1.1991345000000001e-05, "loss": 1.8666, "step": 2991 }, { "epoch": 8.96, "learning_rate": 1.1990640000000001e-05, "loss": 1.8674, "step": 2992 }, { "epoch": 8.96, "learning_rate": 1.1989935000000001e-05, "loss": 1.8668, "step": 2993 }, { "epoch": 8.97, "learning_rate": 1.1989229999999999e-05, "loss": 1.8679, "step": 2994 }, { "epoch": 8.97, "learning_rate": 1.1988525e-05, "loss": 1.869, "step": 2995 }, { "epoch": 8.97, "learning_rate": 1.198782e-05, "loss": 1.8686, "step": 2996 }, { "epoch": 8.97, "learning_rate": 1.1987115e-05, "loss": 1.8698, "step": 2997 }, { "epoch": 8.98, "learning_rate": 1.198641e-05, "loss": 1.8691, "step": 2998 }, { "epoch": 8.98, "learning_rate": 1.1985705e-05, "loss": 1.8667, "step": 2999 }, { "epoch": 8.98, "learning_rate": 1.1985e-05, "loss": 1.8692, "step": 3000 }, { "epoch": 8.98, "eval_accuracy": 0.000583315855704698, "eval_loss": 1.8017160892486572, "eval_runtime": 38.3697, "eval_samples_per_second": 7.767, "eval_steps_per_second": 0.495, "step": 3000 }, { "epoch": 8.99, "learning_rate": 1.1984295e-05, "loss": 1.8655, "step": 3001 }, { "epoch": 8.99, "learning_rate": 1.1983590000000001e-05, "loss": 1.8691, "step": 3002 }, { "epoch": 8.99, "learning_rate": 1.1982885e-05, "loss": 1.8653, "step": 3003 }, { "epoch": 9.0, "learning_rate": 1.198218e-05, "loss": 1.8682, "step": 3004 }, { "epoch": 9.0, "learning_rate": 1.1981475e-05, "loss": 1.865, "step": 3005 }, { "epoch": 9.0, "learning_rate": 1.198077e-05, "loss": 1.8684, "step": 3006 }, { "epoch": 9.0, "learning_rate": 1.1980065e-05, "loss": 1.8694, "step": 3007 }, { "epoch": 9.01, "learning_rate": 1.1979360000000001e-05, "loss": 1.8688, "step": 3008 }, { "epoch": 9.01, "learning_rate": 1.1978655000000001e-05, "loss": 1.866, "step": 3009 }, { "epoch": 9.01, "learning_rate": 1.1977950000000001e-05, "loss": 1.8683, "step": 3010 }, { "epoch": 9.02, "learning_rate": 1.1977245000000001e-05, "loss": 1.8631, "step": 3011 }, { "epoch": 9.02, "learning_rate": 1.197654e-05, "loss": 1.8658, "step": 3012 }, { "epoch": 9.02, "learning_rate": 1.1975835e-05, "loss": 1.8677, "step": 3013 }, { "epoch": 9.03, "learning_rate": 1.1975130000000002e-05, "loss": 1.8666, "step": 3014 }, { "epoch": 9.03, "learning_rate": 1.1974425e-05, "loss": 1.8684, "step": 3015 }, { "epoch": 9.03, "learning_rate": 1.197372e-05, "loss": 1.8647, "step": 3016 }, { "epoch": 9.03, "learning_rate": 1.1973015e-05, "loss": 1.8681, "step": 3017 }, { "epoch": 9.04, "learning_rate": 1.197231e-05, "loss": 1.8671, "step": 3018 }, { "epoch": 9.04, "learning_rate": 1.1971605e-05, "loss": 1.8681, "step": 3019 }, { "epoch": 9.04, "learning_rate": 1.1970900000000001e-05, "loss": 1.8687, "step": 3020 }, { "epoch": 9.05, "learning_rate": 1.1970195e-05, "loss": 1.8682, "step": 3021 }, { "epoch": 9.05, "learning_rate": 1.196949e-05, "loss": 1.8646, "step": 3022 }, { "epoch": 9.05, "learning_rate": 1.1968785e-05, "loss": 1.8671, "step": 3023 }, { "epoch": 9.06, "learning_rate": 1.196808e-05, "loss": 1.8677, "step": 3024 }, { "epoch": 9.06, "learning_rate": 1.1967375e-05, "loss": 1.8699, "step": 3025 }, { "epoch": 9.06, "learning_rate": 1.1966670000000001e-05, "loss": 1.8657, "step": 3026 }, { "epoch": 9.06, "learning_rate": 1.1965965000000001e-05, "loss": 1.8649, "step": 3027 }, { "epoch": 9.07, "learning_rate": 1.1965260000000001e-05, "loss": 1.8648, "step": 3028 }, { "epoch": 9.07, "learning_rate": 1.1964555000000001e-05, "loss": 1.8642, "step": 3029 }, { "epoch": 9.07, "learning_rate": 1.196385e-05, "loss": 1.8668, "step": 3030 }, { "epoch": 9.08, "learning_rate": 1.1963145e-05, "loss": 1.8665, "step": 3031 }, { "epoch": 9.08, "learning_rate": 1.196244e-05, "loss": 1.8676, "step": 3032 }, { "epoch": 9.08, "learning_rate": 1.1961735000000002e-05, "loss": 1.8687, "step": 3033 }, { "epoch": 9.09, "learning_rate": 1.1961030000000002e-05, "loss": 1.8676, "step": 3034 }, { "epoch": 9.09, "learning_rate": 1.1960325e-05, "loss": 1.868, "step": 3035 }, { "epoch": 9.09, "learning_rate": 1.195962e-05, "loss": 1.8663, "step": 3036 }, { "epoch": 9.09, "learning_rate": 1.1958915e-05, "loss": 1.8637, "step": 3037 }, { "epoch": 9.1, "learning_rate": 1.1958209999999999e-05, "loss": 1.8658, "step": 3038 }, { "epoch": 9.1, "learning_rate": 1.1957505e-05, "loss": 1.8635, "step": 3039 }, { "epoch": 9.1, "learning_rate": 1.19568e-05, "loss": 1.8671, "step": 3040 }, { "epoch": 9.11, "learning_rate": 1.1956095e-05, "loss": 1.8679, "step": 3041 }, { "epoch": 9.11, "learning_rate": 1.195539e-05, "loss": 1.8646, "step": 3042 }, { "epoch": 9.11, "learning_rate": 1.1954685e-05, "loss": 1.8649, "step": 3043 }, { "epoch": 9.12, "learning_rate": 1.195398e-05, "loss": 1.8667, "step": 3044 }, { "epoch": 9.12, "learning_rate": 1.1953275000000001e-05, "loss": 1.8662, "step": 3045 }, { "epoch": 9.12, "learning_rate": 1.1952570000000001e-05, "loss": 1.8639, "step": 3046 }, { "epoch": 9.12, "learning_rate": 1.1951865e-05, "loss": 1.8673, "step": 3047 }, { "epoch": 9.13, "learning_rate": 1.195116e-05, "loss": 1.8658, "step": 3048 }, { "epoch": 9.13, "learning_rate": 1.1950455e-05, "loss": 1.8652, "step": 3049 }, { "epoch": 9.13, "learning_rate": 1.194975e-05, "loss": 1.8651, "step": 3050 }, { "epoch": 9.14, "learning_rate": 1.1949045000000002e-05, "loss": 1.8634, "step": 3051 }, { "epoch": 9.14, "learning_rate": 1.1948340000000002e-05, "loss": 1.8628, "step": 3052 }, { "epoch": 9.14, "learning_rate": 1.1947635000000001e-05, "loss": 1.8683, "step": 3053 }, { "epoch": 9.15, "learning_rate": 1.1946930000000001e-05, "loss": 1.8658, "step": 3054 }, { "epoch": 9.15, "learning_rate": 1.1946225e-05, "loss": 1.8636, "step": 3055 }, { "epoch": 9.15, "learning_rate": 1.1945519999999999e-05, "loss": 1.8661, "step": 3056 }, { "epoch": 9.15, "learning_rate": 1.1944815e-05, "loss": 1.8619, "step": 3057 }, { "epoch": 9.16, "learning_rate": 1.194411e-05, "loss": 1.8647, "step": 3058 }, { "epoch": 9.16, "learning_rate": 1.1943405e-05, "loss": 1.8662, "step": 3059 }, { "epoch": 9.16, "learning_rate": 1.19427e-05, "loss": 1.8649, "step": 3060 }, { "epoch": 9.17, "learning_rate": 1.1941995e-05, "loss": 1.8657, "step": 3061 }, { "epoch": 9.17, "learning_rate": 1.194129e-05, "loss": 1.8652, "step": 3062 }, { "epoch": 9.17, "learning_rate": 1.1940585000000001e-05, "loss": 1.8662, "step": 3063 }, { "epoch": 9.18, "learning_rate": 1.1939880000000001e-05, "loss": 1.8669, "step": 3064 }, { "epoch": 9.18, "learning_rate": 1.1939175e-05, "loss": 1.8638, "step": 3065 }, { "epoch": 9.18, "learning_rate": 1.193847e-05, "loss": 1.8649, "step": 3066 }, { "epoch": 9.18, "learning_rate": 1.1937765e-05, "loss": 1.8637, "step": 3067 }, { "epoch": 9.19, "learning_rate": 1.193706e-05, "loss": 1.8646, "step": 3068 }, { "epoch": 9.19, "learning_rate": 1.1936355e-05, "loss": 1.861, "step": 3069 }, { "epoch": 9.19, "learning_rate": 1.1935650000000002e-05, "loss": 1.8654, "step": 3070 }, { "epoch": 9.2, "learning_rate": 1.1934945000000001e-05, "loss": 1.8676, "step": 3071 }, { "epoch": 9.2, "learning_rate": 1.1934240000000001e-05, "loss": 1.8668, "step": 3072 }, { "epoch": 9.2, "learning_rate": 1.1933535000000001e-05, "loss": 1.8672, "step": 3073 }, { "epoch": 9.21, "learning_rate": 1.193283e-05, "loss": 1.8619, "step": 3074 }, { "epoch": 9.21, "learning_rate": 1.1932124999999999e-05, "loss": 1.8666, "step": 3075 }, { "epoch": 9.21, "learning_rate": 1.193142e-05, "loss": 1.866, "step": 3076 }, { "epoch": 9.21, "learning_rate": 1.1930715e-05, "loss": 1.8634, "step": 3077 }, { "epoch": 9.22, "learning_rate": 1.193001e-05, "loss": 1.8629, "step": 3078 }, { "epoch": 9.22, "learning_rate": 1.1929305e-05, "loss": 1.8622, "step": 3079 }, { "epoch": 9.22, "learning_rate": 1.19286e-05, "loss": 1.8638, "step": 3080 }, { "epoch": 9.23, "learning_rate": 1.1927895e-05, "loss": 1.8641, "step": 3081 }, { "epoch": 9.23, "learning_rate": 1.1927190000000001e-05, "loss": 1.8638, "step": 3082 }, { "epoch": 9.23, "learning_rate": 1.1926485e-05, "loss": 1.8651, "step": 3083 }, { "epoch": 9.24, "learning_rate": 1.192578e-05, "loss": 1.8626, "step": 3084 }, { "epoch": 9.24, "learning_rate": 1.1925075e-05, "loss": 1.8656, "step": 3085 }, { "epoch": 9.24, "learning_rate": 1.192437e-05, "loss": 1.8648, "step": 3086 }, { "epoch": 9.24, "learning_rate": 1.1923665e-05, "loss": 1.8647, "step": 3087 }, { "epoch": 9.25, "learning_rate": 1.1922960000000001e-05, "loss": 1.8632, "step": 3088 }, { "epoch": 9.25, "learning_rate": 1.1922255000000001e-05, "loss": 1.8648, "step": 3089 }, { "epoch": 9.25, "learning_rate": 1.1921550000000001e-05, "loss": 1.8646, "step": 3090 }, { "epoch": 9.26, "learning_rate": 1.1920845000000001e-05, "loss": 1.8648, "step": 3091 }, { "epoch": 9.26, "learning_rate": 1.192014e-05, "loss": 1.8609, "step": 3092 }, { "epoch": 9.26, "learning_rate": 1.1919435e-05, "loss": 1.865, "step": 3093 }, { "epoch": 9.27, "learning_rate": 1.1918730000000002e-05, "loss": 1.8621, "step": 3094 }, { "epoch": 9.27, "learning_rate": 1.1918025e-05, "loss": 1.8626, "step": 3095 }, { "epoch": 9.27, "learning_rate": 1.191732e-05, "loss": 1.863, "step": 3096 }, { "epoch": 9.27, "learning_rate": 1.1916615e-05, "loss": 1.8656, "step": 3097 }, { "epoch": 9.28, "learning_rate": 1.191591e-05, "loss": 1.8656, "step": 3098 }, { "epoch": 9.28, "learning_rate": 1.1915205e-05, "loss": 1.865, "step": 3099 }, { "epoch": 9.28, "learning_rate": 1.1914500000000001e-05, "loss": 1.862, "step": 3100 }, { "epoch": 9.28, "eval_accuracy": 0.000570207634228188, "eval_loss": 1.798119306564331, "eval_runtime": 34.9677, "eval_samples_per_second": 8.522, "eval_steps_per_second": 0.543, "step": 3100 }, { "epoch": 9.29, "learning_rate": 1.1913795e-05, "loss": 1.8636, "step": 3101 }, { "epoch": 9.29, "learning_rate": 1.191309e-05, "loss": 1.863, "step": 3102 }, { "epoch": 9.29, "learning_rate": 1.1912385e-05, "loss": 1.862, "step": 3103 }, { "epoch": 9.3, "learning_rate": 1.191168e-05, "loss": 1.8632, "step": 3104 }, { "epoch": 9.3, "learning_rate": 1.1910975e-05, "loss": 1.8632, "step": 3105 }, { "epoch": 9.3, "learning_rate": 1.191027e-05, "loss": 1.8645, "step": 3106 }, { "epoch": 9.3, "learning_rate": 1.1909565000000001e-05, "loss": 1.8607, "step": 3107 }, { "epoch": 9.31, "learning_rate": 1.1908860000000001e-05, "loss": 1.8638, "step": 3108 }, { "epoch": 9.31, "learning_rate": 1.1908155000000001e-05, "loss": 1.8616, "step": 3109 }, { "epoch": 9.31, "learning_rate": 1.190745e-05, "loss": 1.8632, "step": 3110 }, { "epoch": 9.32, "learning_rate": 1.1906745e-05, "loss": 1.8623, "step": 3111 }, { "epoch": 9.32, "learning_rate": 1.190604e-05, "loss": 1.8613, "step": 3112 }, { "epoch": 9.32, "learning_rate": 1.1905335000000002e-05, "loss": 1.861, "step": 3113 }, { "epoch": 9.33, "learning_rate": 1.1904630000000002e-05, "loss": 1.8624, "step": 3114 }, { "epoch": 9.33, "learning_rate": 1.1903925e-05, "loss": 1.862, "step": 3115 }, { "epoch": 9.33, "learning_rate": 1.190322e-05, "loss": 1.862, "step": 3116 }, { "epoch": 9.33, "learning_rate": 1.1902515e-05, "loss": 1.8629, "step": 3117 }, { "epoch": 9.34, "learning_rate": 1.1901809999999999e-05, "loss": 1.8626, "step": 3118 }, { "epoch": 9.34, "learning_rate": 1.1901105e-05, "loss": 1.8635, "step": 3119 }, { "epoch": 9.34, "learning_rate": 1.19004e-05, "loss": 1.8617, "step": 3120 }, { "epoch": 9.35, "learning_rate": 1.1899695e-05, "loss": 1.8612, "step": 3121 }, { "epoch": 9.35, "learning_rate": 1.189899e-05, "loss": 1.8596, "step": 3122 }, { "epoch": 9.35, "learning_rate": 1.1898285e-05, "loss": 1.8611, "step": 3123 }, { "epoch": 9.36, "learning_rate": 1.189758e-05, "loss": 1.8637, "step": 3124 }, { "epoch": 9.36, "learning_rate": 1.1896875000000001e-05, "loss": 1.8614, "step": 3125 }, { "epoch": 9.36, "learning_rate": 1.1896170000000001e-05, "loss": 1.8618, "step": 3126 }, { "epoch": 9.36, "learning_rate": 1.1895465e-05, "loss": 1.8632, "step": 3127 }, { "epoch": 9.37, "learning_rate": 1.189476e-05, "loss": 1.8636, "step": 3128 }, { "epoch": 9.37, "learning_rate": 1.1894055e-05, "loss": 1.8632, "step": 3129 }, { "epoch": 9.37, "learning_rate": 1.189335e-05, "loss": 1.8607, "step": 3130 }, { "epoch": 9.38, "learning_rate": 1.1892645000000002e-05, "loss": 1.8612, "step": 3131 }, { "epoch": 9.38, "learning_rate": 1.1891940000000002e-05, "loss": 1.859, "step": 3132 }, { "epoch": 9.38, "learning_rate": 1.1891235000000001e-05, "loss": 1.8602, "step": 3133 }, { "epoch": 9.38, "learning_rate": 1.1890530000000001e-05, "loss": 1.8638, "step": 3134 }, { "epoch": 9.39, "learning_rate": 1.1889825000000001e-05, "loss": 1.8645, "step": 3135 }, { "epoch": 9.39, "learning_rate": 1.1889119999999999e-05, "loss": 1.8569, "step": 3136 }, { "epoch": 9.39, "learning_rate": 1.1888415e-05, "loss": 1.8634, "step": 3137 }, { "epoch": 9.4, "learning_rate": 1.188771e-05, "loss": 1.8614, "step": 3138 }, { "epoch": 9.4, "learning_rate": 1.1887005e-05, "loss": 1.8577, "step": 3139 }, { "epoch": 9.4, "learning_rate": 1.18863e-05, "loss": 1.8604, "step": 3140 }, { "epoch": 9.41, "learning_rate": 1.1885595e-05, "loss": 1.8609, "step": 3141 }, { "epoch": 9.41, "learning_rate": 1.188489e-05, "loss": 1.86, "step": 3142 }, { "epoch": 9.41, "learning_rate": 1.1884185e-05, "loss": 1.861, "step": 3143 }, { "epoch": 9.41, "learning_rate": 1.1883480000000001e-05, "loss": 1.863, "step": 3144 }, { "epoch": 9.42, "learning_rate": 1.1882775e-05, "loss": 1.8618, "step": 3145 }, { "epoch": 9.42, "learning_rate": 1.188207e-05, "loss": 1.8599, "step": 3146 }, { "epoch": 9.42, "learning_rate": 1.1881365e-05, "loss": 1.8626, "step": 3147 }, { "epoch": 9.43, "learning_rate": 1.188066e-05, "loss": 1.8597, "step": 3148 }, { "epoch": 9.43, "learning_rate": 1.1879955e-05, "loss": 1.8618, "step": 3149 }, { "epoch": 9.43, "learning_rate": 1.1879250000000002e-05, "loss": 1.8614, "step": 3150 }, { "epoch": 9.44, "learning_rate": 1.1878545000000001e-05, "loss": 1.8613, "step": 3151 }, { "epoch": 9.44, "learning_rate": 1.1877840000000001e-05, "loss": 1.86, "step": 3152 }, { "epoch": 9.44, "learning_rate": 1.1877135000000001e-05, "loss": 1.8584, "step": 3153 }, { "epoch": 9.44, "learning_rate": 1.187643e-05, "loss": 1.86, "step": 3154 }, { "epoch": 9.45, "learning_rate": 1.1875725e-05, "loss": 1.8586, "step": 3155 }, { "epoch": 9.45, "learning_rate": 1.187502e-05, "loss": 1.8595, "step": 3156 }, { "epoch": 9.45, "learning_rate": 1.1874315e-05, "loss": 1.8585, "step": 3157 }, { "epoch": 9.46, "learning_rate": 1.187361e-05, "loss": 1.8594, "step": 3158 }, { "epoch": 9.46, "learning_rate": 1.1872905e-05, "loss": 1.86, "step": 3159 }, { "epoch": 9.46, "learning_rate": 1.18722e-05, "loss": 1.8592, "step": 3160 }, { "epoch": 9.47, "learning_rate": 1.1871495e-05, "loss": 1.8617, "step": 3161 }, { "epoch": 9.47, "learning_rate": 1.1870790000000001e-05, "loss": 1.8598, "step": 3162 }, { "epoch": 9.47, "learning_rate": 1.1870085e-05, "loss": 1.861, "step": 3163 }, { "epoch": 9.47, "learning_rate": 1.186938e-05, "loss": 1.8625, "step": 3164 }, { "epoch": 9.48, "learning_rate": 1.1868675e-05, "loss": 1.862, "step": 3165 }, { "epoch": 9.48, "learning_rate": 1.186797e-05, "loss": 1.8579, "step": 3166 }, { "epoch": 9.48, "learning_rate": 1.1867265e-05, "loss": 1.8599, "step": 3167 }, { "epoch": 9.49, "learning_rate": 1.1866560000000001e-05, "loss": 1.8582, "step": 3168 }, { "epoch": 9.49, "learning_rate": 1.1865855000000001e-05, "loss": 1.8606, "step": 3169 }, { "epoch": 9.49, "learning_rate": 1.1865150000000001e-05, "loss": 1.8577, "step": 3170 }, { "epoch": 9.5, "learning_rate": 1.1864445000000001e-05, "loss": 1.8583, "step": 3171 }, { "epoch": 9.5, "learning_rate": 1.186374e-05, "loss": 1.8611, "step": 3172 }, { "epoch": 9.5, "learning_rate": 1.1863035e-05, "loss": 1.8603, "step": 3173 }, { "epoch": 9.5, "learning_rate": 1.186233e-05, "loss": 1.8606, "step": 3174 }, { "epoch": 9.51, "learning_rate": 1.1861625000000002e-05, "loss": 1.8573, "step": 3175 }, { "epoch": 9.51, "learning_rate": 1.186092e-05, "loss": 1.8597, "step": 3176 }, { "epoch": 9.51, "learning_rate": 1.1860215e-05, "loss": 1.8602, "step": 3177 }, { "epoch": 9.52, "learning_rate": 1.185951e-05, "loss": 1.8583, "step": 3178 }, { "epoch": 9.52, "learning_rate": 1.1858805e-05, "loss": 1.8572, "step": 3179 }, { "epoch": 9.52, "learning_rate": 1.18581e-05, "loss": 1.8582, "step": 3180 }, { "epoch": 9.53, "learning_rate": 1.1857395e-05, "loss": 1.8574, "step": 3181 }, { "epoch": 9.53, "learning_rate": 1.185669e-05, "loss": 1.8597, "step": 3182 }, { "epoch": 9.53, "learning_rate": 1.1855985e-05, "loss": 1.8586, "step": 3183 }, { "epoch": 9.53, "learning_rate": 1.185528e-05, "loss": 1.8576, "step": 3184 }, { "epoch": 9.54, "learning_rate": 1.1854575e-05, "loss": 1.8591, "step": 3185 }, { "epoch": 9.54, "learning_rate": 1.185387e-05, "loss": 1.858, "step": 3186 }, { "epoch": 9.54, "learning_rate": 1.1853165000000001e-05, "loss": 1.8608, "step": 3187 }, { "epoch": 9.55, "learning_rate": 1.1852460000000001e-05, "loss": 1.8583, "step": 3188 }, { "epoch": 9.55, "learning_rate": 1.1851755e-05, "loss": 1.8575, "step": 3189 }, { "epoch": 9.55, "learning_rate": 1.185105e-05, "loss": 1.8591, "step": 3190 }, { "epoch": 9.56, "learning_rate": 1.1850345e-05, "loss": 1.8567, "step": 3191 }, { "epoch": 9.56, "learning_rate": 1.184964e-05, "loss": 1.8623, "step": 3192 }, { "epoch": 9.56, "learning_rate": 1.1848935000000002e-05, "loss": 1.8583, "step": 3193 }, { "epoch": 9.56, "learning_rate": 1.1848230000000002e-05, "loss": 1.8619, "step": 3194 }, { "epoch": 9.57, "learning_rate": 1.1847525000000001e-05, "loss": 1.8589, "step": 3195 }, { "epoch": 9.57, "learning_rate": 1.184682e-05, "loss": 1.858, "step": 3196 }, { "epoch": 9.57, "learning_rate": 1.1846115e-05, "loss": 1.8577, "step": 3197 }, { "epoch": 9.58, "learning_rate": 1.1845409999999999e-05, "loss": 1.8573, "step": 3198 }, { "epoch": 9.58, "learning_rate": 1.1844705e-05, "loss": 1.858, "step": 3199 }, { "epoch": 9.58, "learning_rate": 1.1844e-05, "loss": 1.8557, "step": 3200 }, { "epoch": 9.58, "eval_accuracy": 0.000583315855704698, "eval_loss": 1.794796109199524, "eval_runtime": 31.8388, "eval_samples_per_second": 9.36, "eval_steps_per_second": 0.597, "step": 3200 }, { "epoch": 9.59, "learning_rate": 1.1843295e-05, "loss": 1.8604, "step": 3201 }, { "epoch": 9.59, "learning_rate": 1.184259e-05, "loss": 1.8571, "step": 3202 }, { "epoch": 9.59, "learning_rate": 1.1841885e-05, "loss": 1.8562, "step": 3203 }, { "epoch": 9.59, "learning_rate": 1.184118e-05, "loss": 1.8557, "step": 3204 }, { "epoch": 9.6, "learning_rate": 1.1840475000000001e-05, "loss": 1.859, "step": 3205 }, { "epoch": 9.6, "learning_rate": 1.1839770000000001e-05, "loss": 1.8586, "step": 3206 }, { "epoch": 9.6, "learning_rate": 1.1839065e-05, "loss": 1.8608, "step": 3207 }, { "epoch": 9.61, "learning_rate": 1.183836e-05, "loss": 1.8557, "step": 3208 }, { "epoch": 9.61, "learning_rate": 1.1837655e-05, "loss": 1.8569, "step": 3209 }, { "epoch": 9.61, "learning_rate": 1.183695e-05, "loss": 1.8608, "step": 3210 }, { "epoch": 9.62, "learning_rate": 1.1836245e-05, "loss": 1.8545, "step": 3211 }, { "epoch": 9.62, "learning_rate": 1.1835540000000002e-05, "loss": 1.8577, "step": 3212 }, { "epoch": 9.62, "learning_rate": 1.1834835000000001e-05, "loss": 1.8598, "step": 3213 }, { "epoch": 9.62, "learning_rate": 1.1834130000000001e-05, "loss": 1.8583, "step": 3214 }, { "epoch": 9.63, "learning_rate": 1.1833425000000001e-05, "loss": 1.8591, "step": 3215 }, { "epoch": 9.63, "learning_rate": 1.1832719999999999e-05, "loss": 1.8577, "step": 3216 }, { "epoch": 9.63, "learning_rate": 1.1832015e-05, "loss": 1.8555, "step": 3217 }, { "epoch": 9.64, "learning_rate": 1.183131e-05, "loss": 1.8593, "step": 3218 }, { "epoch": 9.64, "learning_rate": 1.1830605e-05, "loss": 1.8571, "step": 3219 }, { "epoch": 9.64, "learning_rate": 1.18299e-05, "loss": 1.8572, "step": 3220 }, { "epoch": 9.65, "learning_rate": 1.1829195e-05, "loss": 1.8577, "step": 3221 }, { "epoch": 9.65, "learning_rate": 1.182849e-05, "loss": 1.8572, "step": 3222 }, { "epoch": 9.65, "learning_rate": 1.1827785e-05, "loss": 1.8627, "step": 3223 }, { "epoch": 9.65, "learning_rate": 1.1827080000000001e-05, "loss": 1.8578, "step": 3224 }, { "epoch": 9.66, "learning_rate": 1.1826375e-05, "loss": 1.8582, "step": 3225 }, { "epoch": 9.66, "learning_rate": 1.182567e-05, "loss": 1.8582, "step": 3226 }, { "epoch": 9.66, "learning_rate": 1.1824965e-05, "loss": 1.8596, "step": 3227 }, { "epoch": 9.67, "learning_rate": 1.182426e-05, "loss": 1.8579, "step": 3228 }, { "epoch": 9.67, "learning_rate": 1.1823555e-05, "loss": 1.8571, "step": 3229 }, { "epoch": 9.67, "learning_rate": 1.1822850000000002e-05, "loss": 1.8593, "step": 3230 }, { "epoch": 9.68, "learning_rate": 1.1822145000000001e-05, "loss": 1.8561, "step": 3231 }, { "epoch": 9.68, "learning_rate": 1.1821440000000001e-05, "loss": 1.8555, "step": 3232 }, { "epoch": 9.68, "learning_rate": 1.1820735000000001e-05, "loss": 1.857, "step": 3233 }, { "epoch": 9.68, "learning_rate": 1.182003e-05, "loss": 1.8592, "step": 3234 }, { "epoch": 9.69, "learning_rate": 1.1819325e-05, "loss": 1.8584, "step": 3235 }, { "epoch": 9.69, "learning_rate": 1.181862e-05, "loss": 1.8607, "step": 3236 }, { "epoch": 9.69, "learning_rate": 1.1817915e-05, "loss": 1.8622, "step": 3237 }, { "epoch": 9.7, "learning_rate": 1.181721e-05, "loss": 1.8565, "step": 3238 }, { "epoch": 9.7, "learning_rate": 1.1816505e-05, "loss": 1.8558, "step": 3239 }, { "epoch": 9.7, "learning_rate": 1.18158e-05, "loss": 1.8567, "step": 3240 }, { "epoch": 9.71, "learning_rate": 1.1815095e-05, "loss": 1.8554, "step": 3241 }, { "epoch": 9.71, "learning_rate": 1.1814390000000001e-05, "loss": 1.8566, "step": 3242 }, { "epoch": 9.71, "learning_rate": 1.1813685e-05, "loss": 1.8595, "step": 3243 }, { "epoch": 9.71, "learning_rate": 1.181298e-05, "loss": 1.8562, "step": 3244 }, { "epoch": 9.72, "learning_rate": 1.1812275e-05, "loss": 1.856, "step": 3245 }, { "epoch": 9.72, "learning_rate": 1.181157e-05, "loss": 1.8564, "step": 3246 }, { "epoch": 9.72, "learning_rate": 1.1810865e-05, "loss": 1.8587, "step": 3247 }, { "epoch": 9.73, "learning_rate": 1.181016e-05, "loss": 1.8563, "step": 3248 }, { "epoch": 9.73, "learning_rate": 1.1809455000000001e-05, "loss": 1.8566, "step": 3249 }, { "epoch": 9.73, "learning_rate": 1.1808750000000001e-05, "loss": 1.8555, "step": 3250 }, { "epoch": 9.74, "learning_rate": 1.1808045000000001e-05, "loss": 1.8535, "step": 3251 }, { "epoch": 9.74, "learning_rate": 1.180734e-05, "loss": 1.8535, "step": 3252 }, { "epoch": 9.74, "learning_rate": 1.1806635e-05, "loss": 1.8547, "step": 3253 }, { "epoch": 9.74, "learning_rate": 1.180593e-05, "loss": 1.8547, "step": 3254 }, { "epoch": 9.75, "learning_rate": 1.1805225000000002e-05, "loss": 1.8549, "step": 3255 }, { "epoch": 9.75, "learning_rate": 1.1804520000000002e-05, "loss": 1.8571, "step": 3256 }, { "epoch": 9.75, "learning_rate": 1.1803815e-05, "loss": 1.857, "step": 3257 }, { "epoch": 9.76, "learning_rate": 1.180311e-05, "loss": 1.8568, "step": 3258 }, { "epoch": 9.76, "learning_rate": 1.1802405e-05, "loss": 1.8546, "step": 3259 }, { "epoch": 9.76, "learning_rate": 1.18017e-05, "loss": 1.855, "step": 3260 }, { "epoch": 9.77, "learning_rate": 1.1800995e-05, "loss": 1.8577, "step": 3261 }, { "epoch": 9.77, "learning_rate": 1.180029e-05, "loss": 1.8556, "step": 3262 }, { "epoch": 9.77, "learning_rate": 1.1799585e-05, "loss": 1.8563, "step": 3263 }, { "epoch": 9.77, "learning_rate": 1.179888e-05, "loss": 1.8531, "step": 3264 }, { "epoch": 9.78, "learning_rate": 1.1798175e-05, "loss": 1.8568, "step": 3265 }, { "epoch": 9.78, "learning_rate": 1.179747e-05, "loss": 1.855, "step": 3266 }, { "epoch": 9.78, "learning_rate": 1.1796765000000001e-05, "loss": 1.8544, "step": 3267 }, { "epoch": 9.79, "learning_rate": 1.1796060000000001e-05, "loss": 1.8544, "step": 3268 }, { "epoch": 9.79, "learning_rate": 1.1795355e-05, "loss": 1.8559, "step": 3269 }, { "epoch": 9.79, "learning_rate": 1.179465e-05, "loss": 1.8542, "step": 3270 }, { "epoch": 9.8, "learning_rate": 1.1793945e-05, "loss": 1.8569, "step": 3271 }, { "epoch": 9.8, "learning_rate": 1.179324e-05, "loss": 1.8568, "step": 3272 }, { "epoch": 9.8, "learning_rate": 1.1792535000000002e-05, "loss": 1.8568, "step": 3273 }, { "epoch": 9.8, "learning_rate": 1.1791830000000002e-05, "loss": 1.8549, "step": 3274 }, { "epoch": 9.81, "learning_rate": 1.1791125000000001e-05, "loss": 1.8565, "step": 3275 }, { "epoch": 9.81, "learning_rate": 1.1790420000000001e-05, "loss": 1.8555, "step": 3276 }, { "epoch": 9.81, "learning_rate": 1.1789715e-05, "loss": 1.8571, "step": 3277 }, { "epoch": 9.82, "learning_rate": 1.1789009999999999e-05, "loss": 1.8552, "step": 3278 }, { "epoch": 9.82, "learning_rate": 1.1788305e-05, "loss": 1.8548, "step": 3279 }, { "epoch": 9.82, "learning_rate": 1.17876e-05, "loss": 1.8546, "step": 3280 }, { "epoch": 9.83, "learning_rate": 1.1786895e-05, "loss": 1.8527, "step": 3281 }, { "epoch": 9.83, "learning_rate": 1.178619e-05, "loss": 1.8557, "step": 3282 }, { "epoch": 9.83, "learning_rate": 1.1785485e-05, "loss": 1.8537, "step": 3283 }, { "epoch": 9.83, "learning_rate": 1.178478e-05, "loss": 1.8526, "step": 3284 }, { "epoch": 9.84, "learning_rate": 1.1784075000000001e-05, "loss": 1.8551, "step": 3285 }, { "epoch": 9.84, "learning_rate": 1.1783370000000001e-05, "loss": 1.8538, "step": 3286 }, { "epoch": 9.84, "learning_rate": 1.1782665e-05, "loss": 1.8554, "step": 3287 }, { "epoch": 9.85, "learning_rate": 1.178196e-05, "loss": 1.8555, "step": 3288 }, { "epoch": 9.85, "learning_rate": 1.1781255e-05, "loss": 1.8541, "step": 3289 }, { "epoch": 9.85, "learning_rate": 1.178055e-05, "loss": 1.8573, "step": 3290 }, { "epoch": 9.86, "learning_rate": 1.1779845e-05, "loss": 1.8553, "step": 3291 }, { "epoch": 9.86, "learning_rate": 1.1779140000000002e-05, "loss": 1.8575, "step": 3292 }, { "epoch": 9.86, "learning_rate": 1.1778435000000001e-05, "loss": 1.8549, "step": 3293 }, { "epoch": 9.86, "learning_rate": 1.1777730000000001e-05, "loss": 1.8559, "step": 3294 }, { "epoch": 9.87, "learning_rate": 1.1777025000000001e-05, "loss": 1.856, "step": 3295 }, { "epoch": 9.87, "learning_rate": 1.177632e-05, "loss": 1.8552, "step": 3296 }, { "epoch": 9.87, "learning_rate": 1.1775614999999999e-05, "loss": 1.8528, "step": 3297 }, { "epoch": 9.88, "learning_rate": 1.177491e-05, "loss": 1.8513, "step": 3298 }, { "epoch": 9.88, "learning_rate": 1.1774205e-05, "loss": 1.8552, "step": 3299 }, { "epoch": 9.88, "learning_rate": 1.17735e-05, "loss": 1.8531, "step": 3300 }, { "epoch": 9.88, "eval_accuracy": 0.000576761744966443, "eval_loss": 1.7916767597198486, "eval_runtime": 30.7411, "eval_samples_per_second": 9.694, "eval_steps_per_second": 0.618, "step": 3300 }, { "epoch": 9.89, "learning_rate": 1.1772795e-05, "loss": 1.856, "step": 3301 }, { "epoch": 9.89, "learning_rate": 1.177209e-05, "loss": 1.8548, "step": 3302 }, { "epoch": 9.89, "learning_rate": 1.1771385e-05, "loss": 1.8533, "step": 3303 }, { "epoch": 9.89, "learning_rate": 1.1770680000000001e-05, "loss": 1.8536, "step": 3304 }, { "epoch": 9.9, "learning_rate": 1.1769975e-05, "loss": 1.8527, "step": 3305 }, { "epoch": 9.9, "learning_rate": 1.176927e-05, "loss": 1.8549, "step": 3306 }, { "epoch": 9.9, "learning_rate": 1.1768565e-05, "loss": 1.8559, "step": 3307 }, { "epoch": 9.91, "learning_rate": 1.176786e-05, "loss": 1.8557, "step": 3308 }, { "epoch": 9.91, "learning_rate": 1.1767155e-05, "loss": 1.8568, "step": 3309 }, { "epoch": 9.91, "learning_rate": 1.1766450000000001e-05, "loss": 1.853, "step": 3310 }, { "epoch": 9.92, "learning_rate": 1.1765745000000001e-05, "loss": 1.8533, "step": 3311 }, { "epoch": 9.92, "learning_rate": 1.1765040000000001e-05, "loss": 1.8561, "step": 3312 }, { "epoch": 9.92, "learning_rate": 1.1764335000000001e-05, "loss": 1.8537, "step": 3313 }, { "epoch": 9.92, "learning_rate": 1.176363e-05, "loss": 1.8528, "step": 3314 }, { "epoch": 9.93, "learning_rate": 1.1762925e-05, "loss": 1.8541, "step": 3315 }, { "epoch": 9.93, "learning_rate": 1.176222e-05, "loss": 1.8531, "step": 3316 }, { "epoch": 9.93, "learning_rate": 1.1761515e-05, "loss": 1.8546, "step": 3317 }, { "epoch": 9.94, "learning_rate": 1.176081e-05, "loss": 1.8546, "step": 3318 }, { "epoch": 9.94, "learning_rate": 1.1760105e-05, "loss": 1.8542, "step": 3319 }, { "epoch": 9.94, "learning_rate": 1.17594e-05, "loss": 1.852, "step": 3320 }, { "epoch": 9.94, "learning_rate": 1.1758695e-05, "loss": 1.8539, "step": 3321 }, { "epoch": 9.95, "learning_rate": 1.1757990000000001e-05, "loss": 1.8549, "step": 3322 }, { "epoch": 9.95, "learning_rate": 1.1757285e-05, "loss": 1.8536, "step": 3323 }, { "epoch": 9.95, "learning_rate": 1.175658e-05, "loss": 1.8525, "step": 3324 }, { "epoch": 9.96, "learning_rate": 1.1755875e-05, "loss": 1.8531, "step": 3325 }, { "epoch": 9.96, "learning_rate": 1.175517e-05, "loss": 1.8523, "step": 3326 }, { "epoch": 9.96, "learning_rate": 1.1754465e-05, "loss": 1.8525, "step": 3327 }, { "epoch": 9.97, "learning_rate": 1.175376e-05, "loss": 1.8528, "step": 3328 }, { "epoch": 9.97, "learning_rate": 1.1753055000000001e-05, "loss": 1.8532, "step": 3329 }, { "epoch": 9.97, "learning_rate": 1.1752350000000001e-05, "loss": 1.8532, "step": 3330 }, { "epoch": 9.97, "learning_rate": 1.1751645000000001e-05, "loss": 1.8507, "step": 3331 }, { "epoch": 9.98, "learning_rate": 1.175094e-05, "loss": 1.8509, "step": 3332 }, { "epoch": 9.98, "learning_rate": 1.1750235e-05, "loss": 1.8531, "step": 3333 }, { "epoch": 9.98, "learning_rate": 1.174953e-05, "loss": 1.8534, "step": 3334 }, { "epoch": 9.99, "learning_rate": 1.1748825000000002e-05, "loss": 1.8498, "step": 3335 }, { "epoch": 9.99, "learning_rate": 1.1748120000000002e-05, "loss": 1.8513, "step": 3336 }, { "epoch": 9.99, "learning_rate": 1.1747415e-05, "loss": 1.8533, "step": 3337 }, { "epoch": 10.0, "learning_rate": 1.174671e-05, "loss": 1.853, "step": 3338 }, { "epoch": 10.0, "learning_rate": 1.1746005e-05, "loss": 1.8554, "step": 3339 }, { "epoch": 10.0, "learning_rate": 1.17453e-05, "loss": 1.8506, "step": 3340 }, { "epoch": 10.0, "learning_rate": 1.1744595e-05, "loss": 1.8533, "step": 3341 }, { "epoch": 10.01, "learning_rate": 1.174389e-05, "loss": 1.85, "step": 3342 }, { "epoch": 10.01, "learning_rate": 1.1743185e-05, "loss": 1.8515, "step": 3343 }, { "epoch": 10.01, "learning_rate": 1.174248e-05, "loss": 1.8554, "step": 3344 }, { "epoch": 10.02, "learning_rate": 1.1741775e-05, "loss": 1.8497, "step": 3345 }, { "epoch": 10.02, "learning_rate": 1.174107e-05, "loss": 1.8554, "step": 3346 }, { "epoch": 10.02, "learning_rate": 1.1740365000000001e-05, "loss": 1.854, "step": 3347 }, { "epoch": 10.03, "learning_rate": 1.1739660000000001e-05, "loss": 1.849, "step": 3348 }, { "epoch": 10.03, "learning_rate": 1.1738955e-05, "loss": 1.8506, "step": 3349 }, { "epoch": 10.03, "learning_rate": 1.173825e-05, "loss": 1.8545, "step": 3350 }, { "epoch": 10.03, "learning_rate": 1.1737545e-05, "loss": 1.8487, "step": 3351 }, { "epoch": 10.04, "learning_rate": 1.173684e-05, "loss": 1.855, "step": 3352 }, { "epoch": 10.04, "learning_rate": 1.1736135e-05, "loss": 1.8522, "step": 3353 }, { "epoch": 10.04, "learning_rate": 1.1735430000000002e-05, "loss": 1.8507, "step": 3354 }, { "epoch": 10.05, "learning_rate": 1.1734725000000001e-05, "loss": 1.8513, "step": 3355 }, { "epoch": 10.05, "learning_rate": 1.1734020000000001e-05, "loss": 1.8539, "step": 3356 }, { "epoch": 10.05, "learning_rate": 1.1733315e-05, "loss": 1.8538, "step": 3357 }, { "epoch": 10.06, "learning_rate": 1.1732609999999999e-05, "loss": 1.8498, "step": 3358 }, { "epoch": 10.06, "learning_rate": 1.1731905e-05, "loss": 1.8517, "step": 3359 }, { "epoch": 10.06, "learning_rate": 1.17312e-05, "loss": 1.852, "step": 3360 }, { "epoch": 10.06, "learning_rate": 1.1730495e-05, "loss": 1.8541, "step": 3361 }, { "epoch": 10.07, "learning_rate": 1.172979e-05, "loss": 1.8519, "step": 3362 }, { "epoch": 10.07, "learning_rate": 1.1729085e-05, "loss": 1.854, "step": 3363 }, { "epoch": 10.07, "learning_rate": 1.172838e-05, "loss": 1.8528, "step": 3364 }, { "epoch": 10.08, "learning_rate": 1.1727675e-05, "loss": 1.8501, "step": 3365 }, { "epoch": 10.08, "learning_rate": 1.1726970000000001e-05, "loss": 1.8537, "step": 3366 }, { "epoch": 10.08, "learning_rate": 1.1726265e-05, "loss": 1.8511, "step": 3367 }, { "epoch": 10.09, "learning_rate": 1.172556e-05, "loss": 1.8497, "step": 3368 }, { "epoch": 10.09, "learning_rate": 1.1724855e-05, "loss": 1.8482, "step": 3369 }, { "epoch": 10.09, "learning_rate": 1.172415e-05, "loss": 1.8537, "step": 3370 }, { "epoch": 10.09, "learning_rate": 1.1723445e-05, "loss": 1.8508, "step": 3371 }, { "epoch": 10.1, "learning_rate": 1.1722740000000002e-05, "loss": 1.8523, "step": 3372 }, { "epoch": 10.1, "learning_rate": 1.1722035000000001e-05, "loss": 1.8509, "step": 3373 }, { "epoch": 10.1, "learning_rate": 1.1721330000000001e-05, "loss": 1.8528, "step": 3374 }, { "epoch": 10.11, "learning_rate": 1.1720625000000001e-05, "loss": 1.8505, "step": 3375 }, { "epoch": 10.11, "learning_rate": 1.171992e-05, "loss": 1.8522, "step": 3376 }, { "epoch": 10.11, "learning_rate": 1.1719215e-05, "loss": 1.8504, "step": 3377 }, { "epoch": 10.12, "learning_rate": 1.171851e-05, "loss": 1.8466, "step": 3378 }, { "epoch": 10.12, "learning_rate": 1.1717805e-05, "loss": 1.8517, "step": 3379 }, { "epoch": 10.12, "learning_rate": 1.17171e-05, "loss": 1.8501, "step": 3380 }, { "epoch": 10.12, "learning_rate": 1.1716395e-05, "loss": 1.8506, "step": 3381 }, { "epoch": 10.13, "learning_rate": 1.171569e-05, "loss": 1.8531, "step": 3382 }, { "epoch": 10.13, "learning_rate": 1.1714985e-05, "loss": 1.8483, "step": 3383 }, { "epoch": 10.13, "learning_rate": 1.1714280000000001e-05, "loss": 1.8518, "step": 3384 }, { "epoch": 10.14, "learning_rate": 1.1713575e-05, "loss": 1.8518, "step": 3385 }, { "epoch": 10.14, "learning_rate": 1.171287e-05, "loss": 1.8489, "step": 3386 }, { "epoch": 10.14, "learning_rate": 1.1712165e-05, "loss": 1.851, "step": 3387 }, { "epoch": 10.15, "learning_rate": 1.171146e-05, "loss": 1.8496, "step": 3388 }, { "epoch": 10.15, "learning_rate": 1.1710755e-05, "loss": 1.8498, "step": 3389 }, { "epoch": 10.15, "learning_rate": 1.1710050000000001e-05, "loss": 1.8528, "step": 3390 }, { "epoch": 10.15, "learning_rate": 1.1709345000000001e-05, "loss": 1.8471, "step": 3391 }, { "epoch": 10.16, "learning_rate": 1.1708640000000001e-05, "loss": 1.8491, "step": 3392 }, { "epoch": 10.16, "learning_rate": 1.1707935000000001e-05, "loss": 1.8539, "step": 3393 }, { "epoch": 10.16, "learning_rate": 1.170723e-05, "loss": 1.8473, "step": 3394 }, { "epoch": 10.17, "learning_rate": 1.1706525e-05, "loss": 1.8497, "step": 3395 }, { "epoch": 10.17, "learning_rate": 1.170582e-05, "loss": 1.8492, "step": 3396 }, { "epoch": 10.17, "learning_rate": 1.1705115000000002e-05, "loss": 1.8506, "step": 3397 }, { "epoch": 10.18, "learning_rate": 1.170441e-05, "loss": 1.8515, "step": 3398 }, { "epoch": 10.18, "learning_rate": 1.1703705e-05, "loss": 1.8482, "step": 3399 }, { "epoch": 10.18, "learning_rate": 1.1703e-05, "loss": 1.8513, "step": 3400 }, { "epoch": 10.18, "eval_accuracy": 0.0005636535234899329, "eval_loss": 1.7886021137237549, "eval_runtime": 30.8247, "eval_samples_per_second": 9.668, "eval_steps_per_second": 0.616, "step": 3400 }, { "epoch": 10.18, "learning_rate": 1.1702295e-05, "loss": 1.8495, "step": 3401 }, { "epoch": 10.19, "learning_rate": 1.170159e-05, "loss": 1.8522, "step": 3402 }, { "epoch": 10.19, "learning_rate": 1.1700885e-05, "loss": 1.8503, "step": 3403 }, { "epoch": 10.19, "learning_rate": 1.170018e-05, "loss": 1.8476, "step": 3404 }, { "epoch": 10.2, "learning_rate": 1.1699475e-05, "loss": 1.8507, "step": 3405 }, { "epoch": 10.2, "learning_rate": 1.169877e-05, "loss": 1.8504, "step": 3406 }, { "epoch": 10.2, "learning_rate": 1.1698065e-05, "loss": 1.8495, "step": 3407 }, { "epoch": 10.21, "learning_rate": 1.169736e-05, "loss": 1.8505, "step": 3408 }, { "epoch": 10.21, "learning_rate": 1.1696655000000001e-05, "loss": 1.8494, "step": 3409 }, { "epoch": 10.21, "learning_rate": 1.1695950000000001e-05, "loss": 1.8501, "step": 3410 }, { "epoch": 10.21, "learning_rate": 1.1695245000000001e-05, "loss": 1.8495, "step": 3411 }, { "epoch": 10.22, "learning_rate": 1.169454e-05, "loss": 1.851, "step": 3412 }, { "epoch": 10.22, "learning_rate": 1.1693835e-05, "loss": 1.8479, "step": 3413 }, { "epoch": 10.22, "learning_rate": 1.169313e-05, "loss": 1.8488, "step": 3414 }, { "epoch": 10.23, "learning_rate": 1.1692425000000002e-05, "loss": 1.849, "step": 3415 }, { "epoch": 10.23, "learning_rate": 1.1691720000000002e-05, "loss": 1.8499, "step": 3416 }, { "epoch": 10.23, "learning_rate": 1.1691015000000001e-05, "loss": 1.8504, "step": 3417 }, { "epoch": 10.24, "learning_rate": 1.169031e-05, "loss": 1.8517, "step": 3418 }, { "epoch": 10.24, "learning_rate": 1.1689605e-05, "loss": 1.8471, "step": 3419 }, { "epoch": 10.24, "learning_rate": 1.16889e-05, "loss": 1.8485, "step": 3420 }, { "epoch": 10.24, "learning_rate": 1.1688195e-05, "loss": 1.8484, "step": 3421 }, { "epoch": 10.25, "learning_rate": 1.168749e-05, "loss": 1.8471, "step": 3422 }, { "epoch": 10.25, "learning_rate": 1.1686785e-05, "loss": 1.8498, "step": 3423 }, { "epoch": 10.25, "learning_rate": 1.168608e-05, "loss": 1.8464, "step": 3424 }, { "epoch": 10.26, "learning_rate": 1.1685375e-05, "loss": 1.8444, "step": 3425 }, { "epoch": 10.26, "learning_rate": 1.168467e-05, "loss": 1.8524, "step": 3426 }, { "epoch": 10.26, "learning_rate": 1.1683965000000001e-05, "loss": 1.8488, "step": 3427 }, { "epoch": 10.27, "learning_rate": 1.1683260000000001e-05, "loss": 1.8489, "step": 3428 }, { "epoch": 10.27, "learning_rate": 1.1682555e-05, "loss": 1.8477, "step": 3429 }, { "epoch": 10.27, "learning_rate": 1.168185e-05, "loss": 1.8474, "step": 3430 }, { "epoch": 10.27, "learning_rate": 1.1681145e-05, "loss": 1.8496, "step": 3431 }, { "epoch": 10.28, "learning_rate": 1.168044e-05, "loss": 1.8482, "step": 3432 }, { "epoch": 10.28, "learning_rate": 1.1679735e-05, "loss": 1.8497, "step": 3433 }, { "epoch": 10.28, "learning_rate": 1.1679030000000002e-05, "loss": 1.8488, "step": 3434 }, { "epoch": 10.29, "learning_rate": 1.1678325000000001e-05, "loss": 1.849, "step": 3435 }, { "epoch": 10.29, "learning_rate": 1.1677620000000001e-05, "loss": 1.847, "step": 3436 }, { "epoch": 10.29, "learning_rate": 1.1676915000000001e-05, "loss": 1.8456, "step": 3437 }, { "epoch": 10.3, "learning_rate": 1.1676209999999999e-05, "loss": 1.8437, "step": 3438 }, { "epoch": 10.3, "learning_rate": 1.1675504999999999e-05, "loss": 1.8492, "step": 3439 }, { "epoch": 10.3, "learning_rate": 1.16748e-05, "loss": 1.8491, "step": 3440 }, { "epoch": 10.3, "learning_rate": 1.1674095e-05, "loss": 1.8443, "step": 3441 }, { "epoch": 10.31, "learning_rate": 1.167339e-05, "loss": 1.8487, "step": 3442 }, { "epoch": 10.31, "learning_rate": 1.1672685e-05, "loss": 1.8488, "step": 3443 }, { "epoch": 10.31, "learning_rate": 1.167198e-05, "loss": 1.8495, "step": 3444 }, { "epoch": 10.32, "learning_rate": 1.1671275e-05, "loss": 1.8483, "step": 3445 }, { "epoch": 10.32, "learning_rate": 1.1670570000000001e-05, "loss": 1.8495, "step": 3446 }, { "epoch": 10.32, "learning_rate": 1.1669865e-05, "loss": 1.8476, "step": 3447 }, { "epoch": 10.33, "learning_rate": 1.166916e-05, "loss": 1.8476, "step": 3448 }, { "epoch": 10.33, "learning_rate": 1.1668455e-05, "loss": 1.8504, "step": 3449 }, { "epoch": 10.33, "learning_rate": 1.166775e-05, "loss": 1.8464, "step": 3450 }, { "epoch": 10.33, "learning_rate": 1.1667045e-05, "loss": 1.8462, "step": 3451 }, { "epoch": 10.34, "learning_rate": 1.1666340000000002e-05, "loss": 1.8462, "step": 3452 }, { "epoch": 10.34, "learning_rate": 1.1665635000000001e-05, "loss": 1.8504, "step": 3453 }, { "epoch": 10.34, "learning_rate": 1.1664930000000001e-05, "loss": 1.8481, "step": 3454 }, { "epoch": 10.35, "learning_rate": 1.1664225000000001e-05, "loss": 1.8445, "step": 3455 }, { "epoch": 10.35, "learning_rate": 1.166352e-05, "loss": 1.8457, "step": 3456 }, { "epoch": 10.35, "learning_rate": 1.1662815e-05, "loss": 1.847, "step": 3457 }, { "epoch": 10.36, "learning_rate": 1.166211e-05, "loss": 1.848, "step": 3458 }, { "epoch": 10.36, "learning_rate": 1.1661405e-05, "loss": 1.8499, "step": 3459 }, { "epoch": 10.36, "learning_rate": 1.16607e-05, "loss": 1.8494, "step": 3460 }, { "epoch": 10.36, "learning_rate": 1.1659995e-05, "loss": 1.8478, "step": 3461 }, { "epoch": 10.37, "learning_rate": 1.165929e-05, "loss": 1.8481, "step": 3462 }, { "epoch": 10.37, "learning_rate": 1.1658585e-05, "loss": 1.8461, "step": 3463 }, { "epoch": 10.37, "learning_rate": 1.1657880000000001e-05, "loss": 1.8472, "step": 3464 }, { "epoch": 10.38, "learning_rate": 1.1657175e-05, "loss": 1.8478, "step": 3465 }, { "epoch": 10.38, "learning_rate": 1.165647e-05, "loss": 1.8451, "step": 3466 }, { "epoch": 10.38, "learning_rate": 1.1655765e-05, "loss": 1.8452, "step": 3467 }, { "epoch": 10.39, "learning_rate": 1.165506e-05, "loss": 1.8473, "step": 3468 }, { "epoch": 10.39, "learning_rate": 1.1654355e-05, "loss": 1.8476, "step": 3469 }, { "epoch": 10.39, "learning_rate": 1.165365e-05, "loss": 1.8445, "step": 3470 }, { "epoch": 10.39, "learning_rate": 1.1652945000000001e-05, "loss": 1.847, "step": 3471 }, { "epoch": 10.4, "learning_rate": 1.1652240000000001e-05, "loss": 1.8446, "step": 3472 }, { "epoch": 10.4, "learning_rate": 1.1651535000000001e-05, "loss": 1.8494, "step": 3473 }, { "epoch": 10.4, "learning_rate": 1.165083e-05, "loss": 1.8483, "step": 3474 }, { "epoch": 10.41, "learning_rate": 1.1650125e-05, "loss": 1.8472, "step": 3475 }, { "epoch": 10.41, "learning_rate": 1.164942e-05, "loss": 1.8464, "step": 3476 }, { "epoch": 10.41, "learning_rate": 1.1648715000000002e-05, "loss": 1.8432, "step": 3477 }, { "epoch": 10.42, "learning_rate": 1.164801e-05, "loss": 1.8451, "step": 3478 }, { "epoch": 10.42, "learning_rate": 1.1647305e-05, "loss": 1.8463, "step": 3479 }, { "epoch": 10.42, "learning_rate": 1.16466e-05, "loss": 1.8498, "step": 3480 }, { "epoch": 10.42, "learning_rate": 1.1645895e-05, "loss": 1.8457, "step": 3481 }, { "epoch": 10.43, "learning_rate": 1.164519e-05, "loss": 1.8488, "step": 3482 }, { "epoch": 10.43, "learning_rate": 1.1644485e-05, "loss": 1.8467, "step": 3483 }, { "epoch": 10.43, "learning_rate": 1.164378e-05, "loss": 1.8435, "step": 3484 }, { "epoch": 10.44, "learning_rate": 1.1643075e-05, "loss": 1.8451, "step": 3485 }, { "epoch": 10.44, "learning_rate": 1.164237e-05, "loss": 1.8471, "step": 3486 }, { "epoch": 10.44, "learning_rate": 1.1641665e-05, "loss": 1.8476, "step": 3487 }, { "epoch": 10.45, "learning_rate": 1.164096e-05, "loss": 1.845, "step": 3488 }, { "epoch": 10.45, "learning_rate": 1.1640255000000001e-05, "loss": 1.8461, "step": 3489 }, { "epoch": 10.45, "learning_rate": 1.1639550000000001e-05, "loss": 1.8467, "step": 3490 }, { "epoch": 10.45, "learning_rate": 1.1638845000000001e-05, "loss": 1.8462, "step": 3491 }, { "epoch": 10.46, "learning_rate": 1.163814e-05, "loss": 1.847, "step": 3492 }, { "epoch": 10.46, "learning_rate": 1.1637435e-05, "loss": 1.8478, "step": 3493 }, { "epoch": 10.46, "learning_rate": 1.163673e-05, "loss": 1.8444, "step": 3494 }, { "epoch": 10.47, "learning_rate": 1.1636025000000002e-05, "loss": 1.8478, "step": 3495 }, { "epoch": 10.47, "learning_rate": 1.1635320000000002e-05, "loss": 1.8434, "step": 3496 }, { "epoch": 10.47, "learning_rate": 1.1634615000000001e-05, "loss": 1.8473, "step": 3497 }, { "epoch": 10.48, "learning_rate": 1.163391e-05, "loss": 1.845, "step": 3498 }, { "epoch": 10.48, "learning_rate": 1.1633205e-05, "loss": 1.8473, "step": 3499 }, { "epoch": 10.48, "learning_rate": 1.16325e-05, "loss": 1.845, "step": 3500 }, { "epoch": 10.48, "eval_accuracy": 0.0005570994127516778, "eval_loss": 1.7856297492980957, "eval_runtime": 37.3808, "eval_samples_per_second": 7.972, "eval_steps_per_second": 0.508, "step": 3500 }, { "epoch": 10.48, "learning_rate": 1.1631795e-05, "loss": 1.8458, "step": 3501 }, { "epoch": 10.49, "learning_rate": 1.163109e-05, "loss": 1.8436, "step": 3502 }, { "epoch": 10.49, "learning_rate": 1.1630385e-05, "loss": 1.8441, "step": 3503 }, { "epoch": 10.49, "learning_rate": 1.162968e-05, "loss": 1.8475, "step": 3504 }, { "epoch": 10.5, "learning_rate": 1.1628975e-05, "loss": 1.8447, "step": 3505 }, { "epoch": 10.5, "learning_rate": 1.162827e-05, "loss": 1.8453, "step": 3506 }, { "epoch": 10.5, "learning_rate": 1.1627565e-05, "loss": 1.8476, "step": 3507 }, { "epoch": 10.5, "learning_rate": 1.1626860000000001e-05, "loss": 1.8453, "step": 3508 }, { "epoch": 10.51, "learning_rate": 1.1626155e-05, "loss": 1.8449, "step": 3509 }, { "epoch": 10.51, "learning_rate": 1.162545e-05, "loss": 1.8466, "step": 3510 }, { "epoch": 10.51, "learning_rate": 1.1624745e-05, "loss": 1.8476, "step": 3511 }, { "epoch": 10.52, "learning_rate": 1.162404e-05, "loss": 1.8483, "step": 3512 }, { "epoch": 10.52, "learning_rate": 1.1623335e-05, "loss": 1.8442, "step": 3513 }, { "epoch": 10.52, "learning_rate": 1.1622630000000002e-05, "loss": 1.8467, "step": 3514 }, { "epoch": 10.53, "learning_rate": 1.1621925000000001e-05, "loss": 1.8455, "step": 3515 }, { "epoch": 10.53, "learning_rate": 1.1621220000000001e-05, "loss": 1.8423, "step": 3516 }, { "epoch": 10.53, "learning_rate": 1.1620515000000001e-05, "loss": 1.8455, "step": 3517 }, { "epoch": 10.53, "learning_rate": 1.161981e-05, "loss": 1.8464, "step": 3518 }, { "epoch": 10.54, "learning_rate": 1.1619104999999999e-05, "loss": 1.8454, "step": 3519 }, { "epoch": 10.54, "learning_rate": 1.16184e-05, "loss": 1.8443, "step": 3520 }, { "epoch": 10.54, "learning_rate": 1.1617695e-05, "loss": 1.8441, "step": 3521 }, { "epoch": 10.55, "learning_rate": 1.161699e-05, "loss": 1.8429, "step": 3522 }, { "epoch": 10.55, "learning_rate": 1.1616285e-05, "loss": 1.8479, "step": 3523 }, { "epoch": 10.55, "learning_rate": 1.161558e-05, "loss": 1.8485, "step": 3524 }, { "epoch": 10.56, "learning_rate": 1.1614875e-05, "loss": 1.8469, "step": 3525 }, { "epoch": 10.56, "learning_rate": 1.1614170000000001e-05, "loss": 1.8503, "step": 3526 }, { "epoch": 10.56, "learning_rate": 1.1613465e-05, "loss": 1.8452, "step": 3527 }, { "epoch": 10.56, "learning_rate": 1.161276e-05, "loss": 1.8429, "step": 3528 }, { "epoch": 10.57, "learning_rate": 1.1612055e-05, "loss": 1.8474, "step": 3529 }, { "epoch": 10.57, "learning_rate": 1.161135e-05, "loss": 1.8446, "step": 3530 }, { "epoch": 10.57, "learning_rate": 1.1610645e-05, "loss": 1.8447, "step": 3531 }, { "epoch": 10.58, "learning_rate": 1.1609940000000002e-05, "loss": 1.8455, "step": 3532 }, { "epoch": 10.58, "learning_rate": 1.1609235000000001e-05, "loss": 1.8416, "step": 3533 }, { "epoch": 10.58, "learning_rate": 1.1608530000000001e-05, "loss": 1.8455, "step": 3534 }, { "epoch": 10.59, "learning_rate": 1.1607825000000001e-05, "loss": 1.8436, "step": 3535 }, { "epoch": 10.59, "learning_rate": 1.160712e-05, "loss": 1.8446, "step": 3536 }, { "epoch": 10.59, "learning_rate": 1.1606415e-05, "loss": 1.8467, "step": 3537 }, { "epoch": 10.59, "learning_rate": 1.160571e-05, "loss": 1.8474, "step": 3538 }, { "epoch": 10.6, "learning_rate": 1.1605005e-05, "loss": 1.8437, "step": 3539 }, { "epoch": 10.6, "learning_rate": 1.16043e-05, "loss": 1.8422, "step": 3540 }, { "epoch": 10.6, "learning_rate": 1.1603595e-05, "loss": 1.8447, "step": 3541 }, { "epoch": 10.61, "learning_rate": 1.160289e-05, "loss": 1.8457, "step": 3542 }, { "epoch": 10.61, "learning_rate": 1.1602185e-05, "loss": 1.8442, "step": 3543 }, { "epoch": 10.61, "learning_rate": 1.160148e-05, "loss": 1.8441, "step": 3544 }, { "epoch": 10.62, "learning_rate": 1.1600775e-05, "loss": 1.8433, "step": 3545 }, { "epoch": 10.62, "learning_rate": 1.160007e-05, "loss": 1.8444, "step": 3546 }, { "epoch": 10.62, "learning_rate": 1.1599365e-05, "loss": 1.8464, "step": 3547 }, { "epoch": 10.62, "learning_rate": 1.159866e-05, "loss": 1.8441, "step": 3548 }, { "epoch": 10.63, "learning_rate": 1.1597955e-05, "loss": 1.8451, "step": 3549 }, { "epoch": 10.63, "learning_rate": 1.159725e-05, "loss": 1.8409, "step": 3550 }, { "epoch": 10.63, "learning_rate": 1.1596545000000001e-05, "loss": 1.8449, "step": 3551 }, { "epoch": 10.64, "learning_rate": 1.1595840000000001e-05, "loss": 1.8464, "step": 3552 }, { "epoch": 10.64, "learning_rate": 1.1595135000000001e-05, "loss": 1.8452, "step": 3553 }, { "epoch": 10.64, "learning_rate": 1.159443e-05, "loss": 1.8485, "step": 3554 }, { "epoch": 10.65, "learning_rate": 1.1593725e-05, "loss": 1.8433, "step": 3555 }, { "epoch": 10.65, "learning_rate": 1.159302e-05, "loss": 1.8426, "step": 3556 }, { "epoch": 10.65, "learning_rate": 1.1592315000000002e-05, "loss": 1.8437, "step": 3557 }, { "epoch": 10.65, "learning_rate": 1.1591610000000002e-05, "loss": 1.8454, "step": 3558 }, { "epoch": 10.66, "learning_rate": 1.1590905e-05, "loss": 1.8467, "step": 3559 }, { "epoch": 10.66, "learning_rate": 1.15902e-05, "loss": 1.8439, "step": 3560 }, { "epoch": 10.66, "learning_rate": 1.1589495e-05, "loss": 1.8456, "step": 3561 }, { "epoch": 10.67, "learning_rate": 1.158879e-05, "loss": 1.8457, "step": 3562 }, { "epoch": 10.67, "learning_rate": 1.1588085e-05, "loss": 1.8444, "step": 3563 }, { "epoch": 10.67, "learning_rate": 1.158738e-05, "loss": 1.8413, "step": 3564 }, { "epoch": 10.68, "learning_rate": 1.1586675e-05, "loss": 1.8425, "step": 3565 }, { "epoch": 10.68, "learning_rate": 1.158597e-05, "loss": 1.8451, "step": 3566 }, { "epoch": 10.68, "learning_rate": 1.1585265e-05, "loss": 1.8408, "step": 3567 }, { "epoch": 10.68, "learning_rate": 1.158456e-05, "loss": 1.8393, "step": 3568 }, { "epoch": 10.69, "learning_rate": 1.1583855000000001e-05, "loss": 1.8382, "step": 3569 }, { "epoch": 10.69, "learning_rate": 1.1583150000000001e-05, "loss": 1.843, "step": 3570 }, { "epoch": 10.69, "learning_rate": 1.1582445000000001e-05, "loss": 1.8412, "step": 3571 }, { "epoch": 10.7, "learning_rate": 1.158174e-05, "loss": 1.8464, "step": 3572 }, { "epoch": 10.7, "learning_rate": 1.1581035e-05, "loss": 1.8433, "step": 3573 }, { "epoch": 10.7, "learning_rate": 1.158033e-05, "loss": 1.8423, "step": 3574 }, { "epoch": 10.71, "learning_rate": 1.1579625e-05, "loss": 1.8427, "step": 3575 }, { "epoch": 10.71, "learning_rate": 1.1578920000000002e-05, "loss": 1.841, "step": 3576 }, { "epoch": 10.71, "learning_rate": 1.1578215000000001e-05, "loss": 1.843, "step": 3577 }, { "epoch": 10.71, "learning_rate": 1.1577510000000001e-05, "loss": 1.8445, "step": 3578 }, { "epoch": 10.72, "learning_rate": 1.1576805e-05, "loss": 1.8446, "step": 3579 }, { "epoch": 10.72, "learning_rate": 1.15761e-05, "loss": 1.8441, "step": 3580 }, { "epoch": 10.72, "learning_rate": 1.1575395e-05, "loss": 1.8419, "step": 3581 }, { "epoch": 10.73, "learning_rate": 1.157469e-05, "loss": 1.8442, "step": 3582 }, { "epoch": 10.73, "learning_rate": 1.1573985e-05, "loss": 1.8459, "step": 3583 }, { "epoch": 10.73, "learning_rate": 1.157328e-05, "loss": 1.844, "step": 3584 }, { "epoch": 10.74, "learning_rate": 1.1572575e-05, "loss": 1.8453, "step": 3585 }, { "epoch": 10.74, "learning_rate": 1.157187e-05, "loss": 1.8421, "step": 3586 }, { "epoch": 10.74, "learning_rate": 1.1571165e-05, "loss": 1.8398, "step": 3587 }, { "epoch": 10.74, "learning_rate": 1.1570460000000001e-05, "loss": 1.8425, "step": 3588 }, { "epoch": 10.75, "learning_rate": 1.1569755e-05, "loss": 1.8404, "step": 3589 }, { "epoch": 10.75, "learning_rate": 1.156905e-05, "loss": 1.8417, "step": 3590 }, { "epoch": 10.75, "learning_rate": 1.1568345e-05, "loss": 1.8422, "step": 3591 }, { "epoch": 10.76, "learning_rate": 1.156764e-05, "loss": 1.8426, "step": 3592 }, { "epoch": 10.76, "learning_rate": 1.1566935e-05, "loss": 1.8416, "step": 3593 }, { "epoch": 10.76, "learning_rate": 1.1566230000000002e-05, "loss": 1.8426, "step": 3594 }, { "epoch": 10.77, "learning_rate": 1.1565525000000001e-05, "loss": 1.8422, "step": 3595 }, { "epoch": 10.77, "learning_rate": 1.1564820000000001e-05, "loss": 1.8418, "step": 3596 }, { "epoch": 10.77, "learning_rate": 1.1564115000000001e-05, "loss": 1.8425, "step": 3597 }, { "epoch": 10.77, "learning_rate": 1.156341e-05, "loss": 1.8425, "step": 3598 }, { "epoch": 10.78, "learning_rate": 1.1562704999999999e-05, "loss": 1.8423, "step": 3599 }, { "epoch": 10.78, "learning_rate": 1.1562e-05, "loss": 1.8408, "step": 3600 }, { "epoch": 10.78, "eval_accuracy": 0.0005505453020134228, "eval_loss": 1.783057689666748, "eval_runtime": 29.8845, "eval_samples_per_second": 9.972, "eval_steps_per_second": 0.636, "step": 3600 }, { "epoch": 10.78, "learning_rate": 1.1561295e-05, "loss": 1.8431, "step": 3601 }, { "epoch": 10.79, "learning_rate": 1.156059e-05, "loss": 1.8418, "step": 3602 }, { "epoch": 10.79, "learning_rate": 1.1559885e-05, "loss": 1.8421, "step": 3603 }, { "epoch": 10.79, "learning_rate": 1.155918e-05, "loss": 1.8402, "step": 3604 }, { "epoch": 10.8, "learning_rate": 1.1558475e-05, "loss": 1.8419, "step": 3605 }, { "epoch": 10.8, "learning_rate": 1.1557770000000001e-05, "loss": 1.8404, "step": 3606 }, { "epoch": 10.8, "learning_rate": 1.1557065e-05, "loss": 1.8418, "step": 3607 }, { "epoch": 10.8, "learning_rate": 1.155636e-05, "loss": 1.8388, "step": 3608 }, { "epoch": 10.81, "learning_rate": 1.1555655e-05, "loss": 1.8378, "step": 3609 }, { "epoch": 10.81, "learning_rate": 1.155495e-05, "loss": 1.8412, "step": 3610 }, { "epoch": 10.81, "learning_rate": 1.1554245e-05, "loss": 1.8388, "step": 3611 }, { "epoch": 10.82, "learning_rate": 1.155354e-05, "loss": 1.8429, "step": 3612 }, { "epoch": 10.82, "learning_rate": 1.1552835000000001e-05, "loss": 1.8423, "step": 3613 }, { "epoch": 10.82, "learning_rate": 1.1552130000000001e-05, "loss": 1.8395, "step": 3614 }, { "epoch": 10.83, "learning_rate": 1.1551425000000001e-05, "loss": 1.842, "step": 3615 }, { "epoch": 10.83, "learning_rate": 1.155072e-05, "loss": 1.8393, "step": 3616 }, { "epoch": 10.83, "learning_rate": 1.1550015e-05, "loss": 1.8411, "step": 3617 }, { "epoch": 10.83, "learning_rate": 1.154931e-05, "loss": 1.8415, "step": 3618 }, { "epoch": 10.84, "learning_rate": 1.1548605e-05, "loss": 1.8379, "step": 3619 }, { "epoch": 10.84, "learning_rate": 1.15479e-05, "loss": 1.8415, "step": 3620 }, { "epoch": 10.84, "learning_rate": 1.1547195e-05, "loss": 1.8436, "step": 3621 }, { "epoch": 10.85, "learning_rate": 1.154649e-05, "loss": 1.8428, "step": 3622 }, { "epoch": 10.85, "learning_rate": 1.1545785e-05, "loss": 1.8406, "step": 3623 }, { "epoch": 10.85, "learning_rate": 1.154508e-05, "loss": 1.8426, "step": 3624 }, { "epoch": 10.86, "learning_rate": 1.1544375e-05, "loss": 1.8417, "step": 3625 }, { "epoch": 10.86, "learning_rate": 1.154367e-05, "loss": 1.8417, "step": 3626 }, { "epoch": 10.86, "learning_rate": 1.1542965e-05, "loss": 1.8398, "step": 3627 }, { "epoch": 10.86, "learning_rate": 1.154226e-05, "loss": 1.8409, "step": 3628 }, { "epoch": 10.87, "learning_rate": 1.1541555e-05, "loss": 1.8393, "step": 3629 }, { "epoch": 10.87, "learning_rate": 1.154085e-05, "loss": 1.8399, "step": 3630 }, { "epoch": 10.87, "learning_rate": 1.1540145000000001e-05, "loss": 1.8418, "step": 3631 }, { "epoch": 10.88, "learning_rate": 1.1539440000000001e-05, "loss": 1.8393, "step": 3632 }, { "epoch": 10.88, "learning_rate": 1.1538735000000001e-05, "loss": 1.8433, "step": 3633 }, { "epoch": 10.88, "learning_rate": 1.153803e-05, "loss": 1.8397, "step": 3634 }, { "epoch": 10.89, "learning_rate": 1.1537325e-05, "loss": 1.8424, "step": 3635 }, { "epoch": 10.89, "learning_rate": 1.153662e-05, "loss": 1.8397, "step": 3636 }, { "epoch": 10.89, "learning_rate": 1.1535915000000002e-05, "loss": 1.8394, "step": 3637 }, { "epoch": 10.89, "learning_rate": 1.1535210000000002e-05, "loss": 1.8423, "step": 3638 }, { "epoch": 10.9, "learning_rate": 1.1534505000000001e-05, "loss": 1.84, "step": 3639 }, { "epoch": 10.9, "learning_rate": 1.15338e-05, "loss": 1.8435, "step": 3640 }, { "epoch": 10.9, "learning_rate": 1.1533095e-05, "loss": 1.842, "step": 3641 }, { "epoch": 10.91, "learning_rate": 1.153239e-05, "loss": 1.8399, "step": 3642 }, { "epoch": 10.91, "learning_rate": 1.1531685e-05, "loss": 1.8422, "step": 3643 }, { "epoch": 10.91, "learning_rate": 1.153098e-05, "loss": 1.839, "step": 3644 }, { "epoch": 10.92, "learning_rate": 1.1530275e-05, "loss": 1.8383, "step": 3645 }, { "epoch": 10.92, "learning_rate": 1.152957e-05, "loss": 1.8424, "step": 3646 }, { "epoch": 10.92, "learning_rate": 1.1528865e-05, "loss": 1.8395, "step": 3647 }, { "epoch": 10.92, "learning_rate": 1.152816e-05, "loss": 1.8406, "step": 3648 }, { "epoch": 10.93, "learning_rate": 1.1527455000000001e-05, "loss": 1.8432, "step": 3649 }, { "epoch": 10.93, "learning_rate": 1.1526750000000001e-05, "loss": 1.8427, "step": 3650 }, { "epoch": 10.93, "learning_rate": 1.1526045000000001e-05, "loss": 1.8409, "step": 3651 }, { "epoch": 10.94, "learning_rate": 1.152534e-05, "loss": 1.8399, "step": 3652 }, { "epoch": 10.94, "learning_rate": 1.1524635e-05, "loss": 1.8398, "step": 3653 }, { "epoch": 10.94, "learning_rate": 1.152393e-05, "loss": 1.8417, "step": 3654 }, { "epoch": 10.95, "learning_rate": 1.1523225e-05, "loss": 1.841, "step": 3655 }, { "epoch": 10.95, "learning_rate": 1.1522520000000002e-05, "loss": 1.8406, "step": 3656 }, { "epoch": 10.95, "learning_rate": 1.1521815000000001e-05, "loss": 1.8409, "step": 3657 }, { "epoch": 10.95, "learning_rate": 1.1521110000000001e-05, "loss": 1.8369, "step": 3658 }, { "epoch": 10.96, "learning_rate": 1.1520405000000001e-05, "loss": 1.8401, "step": 3659 }, { "epoch": 10.96, "learning_rate": 1.15197e-05, "loss": 1.8392, "step": 3660 }, { "epoch": 10.96, "learning_rate": 1.1518994999999999e-05, "loss": 1.8404, "step": 3661 }, { "epoch": 10.97, "learning_rate": 1.151829e-05, "loss": 1.8402, "step": 3662 }, { "epoch": 10.97, "learning_rate": 1.1517585e-05, "loss": 1.8398, "step": 3663 }, { "epoch": 10.97, "learning_rate": 1.151688e-05, "loss": 1.8421, "step": 3664 }, { "epoch": 10.98, "learning_rate": 1.1516175e-05, "loss": 1.8411, "step": 3665 }, { "epoch": 10.98, "learning_rate": 1.151547e-05, "loss": 1.8406, "step": 3666 }, { "epoch": 10.98, "learning_rate": 1.1514765e-05, "loss": 1.8419, "step": 3667 }, { "epoch": 10.98, "learning_rate": 1.1514060000000001e-05, "loss": 1.8412, "step": 3668 }, { "epoch": 10.99, "learning_rate": 1.1513355e-05, "loss": 1.8408, "step": 3669 }, { "epoch": 10.99, "learning_rate": 1.151265e-05, "loss": 1.8394, "step": 3670 }, { "epoch": 10.99, "learning_rate": 1.1511945e-05, "loss": 1.8374, "step": 3671 }, { "epoch": 11.0, "learning_rate": 1.151124e-05, "loss": 1.8398, "step": 3672 }, { "epoch": 11.0, "learning_rate": 1.1510535e-05, "loss": 1.8385, "step": 3673 }, { "epoch": 11.0, "learning_rate": 1.1509830000000002e-05, "loss": 1.8372, "step": 3674 }, { "epoch": 11.01, "learning_rate": 1.1509125000000001e-05, "loss": 1.8426, "step": 3675 }, { "epoch": 11.01, "learning_rate": 1.1508420000000001e-05, "loss": 1.8434, "step": 3676 }, { "epoch": 11.01, "learning_rate": 1.1507715000000001e-05, "loss": 1.8384, "step": 3677 }, { "epoch": 11.01, "learning_rate": 1.150701e-05, "loss": 1.8393, "step": 3678 }, { "epoch": 11.02, "learning_rate": 1.1506305e-05, "loss": 1.843, "step": 3679 }, { "epoch": 11.02, "learning_rate": 1.15056e-05, "loss": 1.8387, "step": 3680 }, { "epoch": 11.02, "learning_rate": 1.1504895e-05, "loss": 1.8421, "step": 3681 }, { "epoch": 11.03, "learning_rate": 1.150419e-05, "loss": 1.8392, "step": 3682 }, { "epoch": 11.03, "learning_rate": 1.1503485e-05, "loss": 1.8409, "step": 3683 }, { "epoch": 11.03, "learning_rate": 1.150278e-05, "loss": 1.8403, "step": 3684 }, { "epoch": 11.03, "learning_rate": 1.1502075e-05, "loss": 1.8356, "step": 3685 }, { "epoch": 11.04, "learning_rate": 1.1501370000000001e-05, "loss": 1.8371, "step": 3686 }, { "epoch": 11.04, "learning_rate": 1.1500665e-05, "loss": 1.8418, "step": 3687 }, { "epoch": 11.04, "learning_rate": 1.149996e-05, "loss": 1.8422, "step": 3688 }, { "epoch": 11.05, "learning_rate": 1.1499255e-05, "loss": 1.84, "step": 3689 }, { "epoch": 11.05, "learning_rate": 1.149855e-05, "loss": 1.8395, "step": 3690 }, { "epoch": 11.05, "learning_rate": 1.1497845e-05, "loss": 1.839, "step": 3691 }, { "epoch": 11.06, "learning_rate": 1.149714e-05, "loss": 1.8396, "step": 3692 }, { "epoch": 11.06, "learning_rate": 1.1496435000000001e-05, "loss": 1.8378, "step": 3693 }, { "epoch": 11.06, "learning_rate": 1.1495730000000001e-05, "loss": 1.838, "step": 3694 }, { "epoch": 11.06, "learning_rate": 1.1495025000000001e-05, "loss": 1.8379, "step": 3695 }, { "epoch": 11.07, "learning_rate": 1.149432e-05, "loss": 1.8391, "step": 3696 }, { "epoch": 11.07, "learning_rate": 1.1493615e-05, "loss": 1.8376, "step": 3697 }, { "epoch": 11.07, "learning_rate": 1.149291e-05, "loss": 1.8387, "step": 3698 }, { "epoch": 11.08, "learning_rate": 1.1492205000000002e-05, "loss": 1.8384, "step": 3699 }, { "epoch": 11.08, "learning_rate": 1.14915e-05, "loss": 1.8401, "step": 3700 }, { "epoch": 11.08, "eval_accuracy": 0.0005505453020134228, "eval_loss": 1.7802146673202515, "eval_runtime": 33.088, "eval_samples_per_second": 9.006, "eval_steps_per_second": 0.574, "step": 3700 }, { "epoch": 11.08, "learning_rate": 1.1490795e-05, "loss": 1.839, "step": 3701 }, { "epoch": 11.09, "learning_rate": 1.149009e-05, "loss": 1.8383, "step": 3702 }, { "epoch": 11.09, "learning_rate": 1.1489385e-05, "loss": 1.8373, "step": 3703 }, { "epoch": 11.09, "learning_rate": 1.148868e-05, "loss": 1.8364, "step": 3704 }, { "epoch": 11.09, "learning_rate": 1.1487975e-05, "loss": 1.8362, "step": 3705 }, { "epoch": 11.1, "learning_rate": 1.148727e-05, "loss": 1.8381, "step": 3706 }, { "epoch": 11.1, "learning_rate": 1.1486565e-05, "loss": 1.8394, "step": 3707 }, { "epoch": 11.1, "learning_rate": 1.148586e-05, "loss": 1.837, "step": 3708 }, { "epoch": 11.11, "learning_rate": 1.1485155e-05, "loss": 1.8381, "step": 3709 }, { "epoch": 11.11, "learning_rate": 1.148445e-05, "loss": 1.8367, "step": 3710 }, { "epoch": 11.11, "learning_rate": 1.1483745000000001e-05, "loss": 1.8363, "step": 3711 }, { "epoch": 11.12, "learning_rate": 1.1483040000000001e-05, "loss": 1.8379, "step": 3712 }, { "epoch": 11.12, "learning_rate": 1.1482335000000001e-05, "loss": 1.8357, "step": 3713 }, { "epoch": 11.12, "learning_rate": 1.148163e-05, "loss": 1.8358, "step": 3714 }, { "epoch": 11.12, "learning_rate": 1.1480925e-05, "loss": 1.8391, "step": 3715 }, { "epoch": 11.13, "learning_rate": 1.148022e-05, "loss": 1.8386, "step": 3716 }, { "epoch": 11.13, "learning_rate": 1.1479515e-05, "loss": 1.8403, "step": 3717 }, { "epoch": 11.13, "learning_rate": 1.1478810000000002e-05, "loss": 1.8395, "step": 3718 }, { "epoch": 11.14, "learning_rate": 1.1478105000000001e-05, "loss": 1.8363, "step": 3719 }, { "epoch": 11.14, "learning_rate": 1.14774e-05, "loss": 1.8393, "step": 3720 }, { "epoch": 11.14, "learning_rate": 1.1476695e-05, "loss": 1.8396, "step": 3721 }, { "epoch": 11.15, "learning_rate": 1.147599e-05, "loss": 1.8404, "step": 3722 }, { "epoch": 11.15, "learning_rate": 1.1475285e-05, "loss": 1.8401, "step": 3723 }, { "epoch": 11.15, "learning_rate": 1.147458e-05, "loss": 1.8399, "step": 3724 }, { "epoch": 11.15, "learning_rate": 1.1473875e-05, "loss": 1.8371, "step": 3725 }, { "epoch": 11.16, "learning_rate": 1.147317e-05, "loss": 1.8396, "step": 3726 }, { "epoch": 11.16, "learning_rate": 1.1472465e-05, "loss": 1.8412, "step": 3727 }, { "epoch": 11.16, "learning_rate": 1.147176e-05, "loss": 1.8363, "step": 3728 }, { "epoch": 11.17, "learning_rate": 1.1471055e-05, "loss": 1.8371, "step": 3729 }, { "epoch": 11.17, "learning_rate": 1.1470350000000001e-05, "loss": 1.8381, "step": 3730 }, { "epoch": 11.17, "learning_rate": 1.1469645000000001e-05, "loss": 1.8389, "step": 3731 }, { "epoch": 11.18, "learning_rate": 1.146894e-05, "loss": 1.8372, "step": 3732 }, { "epoch": 11.18, "learning_rate": 1.1468235e-05, "loss": 1.841, "step": 3733 }, { "epoch": 11.18, "learning_rate": 1.146753e-05, "loss": 1.8385, "step": 3734 }, { "epoch": 11.18, "learning_rate": 1.1466825e-05, "loss": 1.8389, "step": 3735 }, { "epoch": 11.19, "learning_rate": 1.1466120000000002e-05, "loss": 1.835, "step": 3736 }, { "epoch": 11.19, "learning_rate": 1.1465415000000001e-05, "loss": 1.8357, "step": 3737 }, { "epoch": 11.19, "learning_rate": 1.1464710000000001e-05, "loss": 1.8351, "step": 3738 }, { "epoch": 11.2, "learning_rate": 1.1464005000000001e-05, "loss": 1.8357, "step": 3739 }, { "epoch": 11.2, "learning_rate": 1.14633e-05, "loss": 1.8376, "step": 3740 }, { "epoch": 11.2, "learning_rate": 1.1462594999999999e-05, "loss": 1.8364, "step": 3741 }, { "epoch": 11.21, "learning_rate": 1.146189e-05, "loss": 1.8351, "step": 3742 }, { "epoch": 11.21, "learning_rate": 1.1461185e-05, "loss": 1.8373, "step": 3743 }, { "epoch": 11.21, "learning_rate": 1.146048e-05, "loss": 1.838, "step": 3744 }, { "epoch": 11.21, "learning_rate": 1.1459775e-05, "loss": 1.8361, "step": 3745 }, { "epoch": 11.22, "learning_rate": 1.145907e-05, "loss": 1.8351, "step": 3746 }, { "epoch": 11.22, "learning_rate": 1.1458365e-05, "loss": 1.8359, "step": 3747 }, { "epoch": 11.22, "learning_rate": 1.1457660000000001e-05, "loss": 1.8382, "step": 3748 }, { "epoch": 11.23, "learning_rate": 1.1456955e-05, "loss": 1.8371, "step": 3749 }, { "epoch": 11.23, "learning_rate": 1.145625e-05, "loss": 1.8384, "step": 3750 }, { "epoch": 11.23, "learning_rate": 1.1455545e-05, "loss": 1.8367, "step": 3751 }, { "epoch": 11.24, "learning_rate": 1.145484e-05, "loss": 1.8386, "step": 3752 }, { "epoch": 11.24, "learning_rate": 1.1454135e-05, "loss": 1.8354, "step": 3753 }, { "epoch": 11.24, "learning_rate": 1.1453430000000002e-05, "loss": 1.8365, "step": 3754 }, { "epoch": 11.24, "learning_rate": 1.1452725000000001e-05, "loss": 1.8364, "step": 3755 }, { "epoch": 11.25, "learning_rate": 1.1452020000000001e-05, "loss": 1.8355, "step": 3756 }, { "epoch": 11.25, "learning_rate": 1.1451315000000001e-05, "loss": 1.8377, "step": 3757 }, { "epoch": 11.25, "learning_rate": 1.145061e-05, "loss": 1.8354, "step": 3758 }, { "epoch": 11.26, "learning_rate": 1.1449905e-05, "loss": 1.8385, "step": 3759 }, { "epoch": 11.26, "learning_rate": 1.14492e-05, "loss": 1.837, "step": 3760 }, { "epoch": 11.26, "learning_rate": 1.1448495e-05, "loss": 1.8377, "step": 3761 }, { "epoch": 11.27, "learning_rate": 1.144779e-05, "loss": 1.8371, "step": 3762 }, { "epoch": 11.27, "learning_rate": 1.1447085e-05, "loss": 1.8346, "step": 3763 }, { "epoch": 11.27, "learning_rate": 1.144638e-05, "loss": 1.837, "step": 3764 }, { "epoch": 11.27, "learning_rate": 1.1445675e-05, "loss": 1.8344, "step": 3765 }, { "epoch": 11.28, "learning_rate": 1.144497e-05, "loss": 1.8373, "step": 3766 }, { "epoch": 11.28, "learning_rate": 1.1444265e-05, "loss": 1.8368, "step": 3767 }, { "epoch": 11.28, "learning_rate": 1.144356e-05, "loss": 1.8331, "step": 3768 }, { "epoch": 11.29, "learning_rate": 1.1442855e-05, "loss": 1.8366, "step": 3769 }, { "epoch": 11.29, "learning_rate": 1.144215e-05, "loss": 1.8369, "step": 3770 }, { "epoch": 11.29, "learning_rate": 1.1441445e-05, "loss": 1.8377, "step": 3771 }, { "epoch": 11.3, "learning_rate": 1.144074e-05, "loss": 1.8357, "step": 3772 }, { "epoch": 11.3, "learning_rate": 1.1440035000000001e-05, "loss": 1.8359, "step": 3773 }, { "epoch": 11.3, "learning_rate": 1.1439330000000001e-05, "loss": 1.8349, "step": 3774 }, { "epoch": 11.3, "learning_rate": 1.1438625000000001e-05, "loss": 1.8373, "step": 3775 }, { "epoch": 11.31, "learning_rate": 1.143792e-05, "loss": 1.8357, "step": 3776 }, { "epoch": 11.31, "learning_rate": 1.1437215e-05, "loss": 1.8358, "step": 3777 }, { "epoch": 11.31, "learning_rate": 1.143651e-05, "loss": 1.8337, "step": 3778 }, { "epoch": 11.32, "learning_rate": 1.1435805000000002e-05, "loss": 1.8364, "step": 3779 }, { "epoch": 11.32, "learning_rate": 1.1435100000000002e-05, "loss": 1.8374, "step": 3780 }, { "epoch": 11.32, "learning_rate": 1.1434395e-05, "loss": 1.8376, "step": 3781 }, { "epoch": 11.33, "learning_rate": 1.143369e-05, "loss": 1.834, "step": 3782 }, { "epoch": 11.33, "learning_rate": 1.1432985e-05, "loss": 1.8365, "step": 3783 }, { "epoch": 11.33, "learning_rate": 1.143228e-05, "loss": 1.8359, "step": 3784 }, { "epoch": 11.33, "learning_rate": 1.1431575e-05, "loss": 1.8361, "step": 3785 }, { "epoch": 11.34, "learning_rate": 1.143087e-05, "loss": 1.8346, "step": 3786 }, { "epoch": 11.34, "learning_rate": 1.1430165e-05, "loss": 1.8349, "step": 3787 }, { "epoch": 11.34, "learning_rate": 1.142946e-05, "loss": 1.8348, "step": 3788 }, { "epoch": 11.35, "learning_rate": 1.1428755e-05, "loss": 1.8366, "step": 3789 }, { "epoch": 11.35, "learning_rate": 1.142805e-05, "loss": 1.8387, "step": 3790 }, { "epoch": 11.35, "learning_rate": 1.1427345000000001e-05, "loss": 1.8361, "step": 3791 }, { "epoch": 11.36, "learning_rate": 1.1426640000000001e-05, "loss": 1.8353, "step": 3792 }, { "epoch": 11.36, "learning_rate": 1.1425935000000001e-05, "loss": 1.8386, "step": 3793 }, { "epoch": 11.36, "learning_rate": 1.142523e-05, "loss": 1.8338, "step": 3794 }, { "epoch": 11.36, "learning_rate": 1.1424525e-05, "loss": 1.8374, "step": 3795 }, { "epoch": 11.37, "learning_rate": 1.142382e-05, "loss": 1.8364, "step": 3796 }, { "epoch": 11.37, "learning_rate": 1.1423115e-05, "loss": 1.8346, "step": 3797 }, { "epoch": 11.37, "learning_rate": 1.1422410000000002e-05, "loss": 1.8361, "step": 3798 }, { "epoch": 11.38, "learning_rate": 1.1421705000000001e-05, "loss": 1.8357, "step": 3799 }, { "epoch": 11.38, "learning_rate": 1.1421000000000001e-05, "loss": 1.8338, "step": 3800 }, { "epoch": 11.38, "eval_accuracy": 0.0005570994127516778, "eval_loss": 1.7777618169784546, "eval_runtime": 38.8072, "eval_samples_per_second": 7.679, "eval_steps_per_second": 0.49, "step": 3800 }, { "epoch": 11.38, "learning_rate": 1.1420295e-05, "loss": 1.8357, "step": 3801 }, { "epoch": 11.39, "learning_rate": 1.141959e-05, "loss": 1.8333, "step": 3802 }, { "epoch": 11.39, "learning_rate": 1.1418884999999999e-05, "loss": 1.8354, "step": 3803 }, { "epoch": 11.39, "learning_rate": 1.141818e-05, "loss": 1.8344, "step": 3804 }, { "epoch": 11.39, "learning_rate": 1.1417475e-05, "loss": 1.8331, "step": 3805 }, { "epoch": 11.4, "learning_rate": 1.141677e-05, "loss": 1.8348, "step": 3806 }, { "epoch": 11.4, "learning_rate": 1.1416065e-05, "loss": 1.8379, "step": 3807 }, { "epoch": 11.4, "learning_rate": 1.141536e-05, "loss": 1.8329, "step": 3808 }, { "epoch": 11.41, "learning_rate": 1.1414655e-05, "loss": 1.8354, "step": 3809 }, { "epoch": 11.41, "learning_rate": 1.1413950000000001e-05, "loss": 1.8365, "step": 3810 }, { "epoch": 11.41, "learning_rate": 1.1413245000000001e-05, "loss": 1.8346, "step": 3811 }, { "epoch": 11.42, "learning_rate": 1.141254e-05, "loss": 1.8351, "step": 3812 }, { "epoch": 11.42, "learning_rate": 1.1411835e-05, "loss": 1.8326, "step": 3813 }, { "epoch": 11.42, "learning_rate": 1.141113e-05, "loss": 1.8359, "step": 3814 }, { "epoch": 11.42, "learning_rate": 1.1410425e-05, "loss": 1.8333, "step": 3815 }, { "epoch": 11.43, "learning_rate": 1.1409720000000002e-05, "loss": 1.8345, "step": 3816 }, { "epoch": 11.43, "learning_rate": 1.1409015000000001e-05, "loss": 1.8342, "step": 3817 }, { "epoch": 11.43, "learning_rate": 1.1408310000000001e-05, "loss": 1.8334, "step": 3818 }, { "epoch": 11.44, "learning_rate": 1.1407605000000001e-05, "loss": 1.8333, "step": 3819 }, { "epoch": 11.44, "learning_rate": 1.1406900000000001e-05, "loss": 1.8332, "step": 3820 }, { "epoch": 11.44, "learning_rate": 1.1406194999999999e-05, "loss": 1.8313, "step": 3821 }, { "epoch": 11.45, "learning_rate": 1.140549e-05, "loss": 1.8359, "step": 3822 }, { "epoch": 11.45, "learning_rate": 1.1404785e-05, "loss": 1.8368, "step": 3823 }, { "epoch": 11.45, "learning_rate": 1.140408e-05, "loss": 1.8335, "step": 3824 }, { "epoch": 11.45, "learning_rate": 1.1403375e-05, "loss": 1.8332, "step": 3825 }, { "epoch": 11.46, "learning_rate": 1.140267e-05, "loss": 1.8321, "step": 3826 }, { "epoch": 11.46, "learning_rate": 1.1401965e-05, "loss": 1.8324, "step": 3827 }, { "epoch": 11.46, "learning_rate": 1.1401260000000001e-05, "loss": 1.8327, "step": 3828 }, { "epoch": 11.47, "learning_rate": 1.1400555e-05, "loss": 1.8324, "step": 3829 }, { "epoch": 11.47, "learning_rate": 1.139985e-05, "loss": 1.8322, "step": 3830 }, { "epoch": 11.47, "learning_rate": 1.1399145e-05, "loss": 1.8327, "step": 3831 }, { "epoch": 11.48, "learning_rate": 1.139844e-05, "loss": 1.8371, "step": 3832 }, { "epoch": 11.48, "learning_rate": 1.1397735e-05, "loss": 1.8332, "step": 3833 }, { "epoch": 11.48, "learning_rate": 1.139703e-05, "loss": 1.8365, "step": 3834 }, { "epoch": 11.48, "learning_rate": 1.1396325000000001e-05, "loss": 1.8344, "step": 3835 }, { "epoch": 11.49, "learning_rate": 1.1395620000000001e-05, "loss": 1.835, "step": 3836 }, { "epoch": 11.49, "learning_rate": 1.1394915000000001e-05, "loss": 1.8357, "step": 3837 }, { "epoch": 11.49, "learning_rate": 1.139421e-05, "loss": 1.8365, "step": 3838 }, { "epoch": 11.5, "learning_rate": 1.1393505e-05, "loss": 1.8344, "step": 3839 }, { "epoch": 11.5, "learning_rate": 1.13928e-05, "loss": 1.8353, "step": 3840 }, { "epoch": 11.5, "learning_rate": 1.1392095e-05, "loss": 1.8355, "step": 3841 }, { "epoch": 11.51, "learning_rate": 1.139139e-05, "loss": 1.831, "step": 3842 }, { "epoch": 11.51, "learning_rate": 1.1390685e-05, "loss": 1.8348, "step": 3843 }, { "epoch": 11.51, "learning_rate": 1.138998e-05, "loss": 1.8349, "step": 3844 }, { "epoch": 11.51, "learning_rate": 1.1389275e-05, "loss": 1.8323, "step": 3845 }, { "epoch": 11.52, "learning_rate": 1.138857e-05, "loss": 1.8336, "step": 3846 }, { "epoch": 11.52, "learning_rate": 1.1387865e-05, "loss": 1.8357, "step": 3847 }, { "epoch": 11.52, "learning_rate": 1.138716e-05, "loss": 1.8339, "step": 3848 }, { "epoch": 11.53, "learning_rate": 1.1386455e-05, "loss": 1.8344, "step": 3849 }, { "epoch": 11.53, "learning_rate": 1.138575e-05, "loss": 1.8334, "step": 3850 }, { "epoch": 11.53, "learning_rate": 1.1385045e-05, "loss": 1.8315, "step": 3851 }, { "epoch": 11.54, "learning_rate": 1.138434e-05, "loss": 1.8374, "step": 3852 }, { "epoch": 11.54, "learning_rate": 1.1383635000000001e-05, "loss": 1.8338, "step": 3853 }, { "epoch": 11.54, "learning_rate": 1.1382930000000001e-05, "loss": 1.8331, "step": 3854 }, { "epoch": 11.54, "learning_rate": 1.1382225000000001e-05, "loss": 1.8356, "step": 3855 }, { "epoch": 11.55, "learning_rate": 1.138152e-05, "loss": 1.8321, "step": 3856 }, { "epoch": 11.55, "learning_rate": 1.1380815e-05, "loss": 1.8304, "step": 3857 }, { "epoch": 11.55, "learning_rate": 1.138011e-05, "loss": 1.8315, "step": 3858 }, { "epoch": 11.56, "learning_rate": 1.1379405000000002e-05, "loss": 1.8328, "step": 3859 }, { "epoch": 11.56, "learning_rate": 1.1378700000000002e-05, "loss": 1.8322, "step": 3860 }, { "epoch": 11.56, "learning_rate": 1.1377995e-05, "loss": 1.8341, "step": 3861 }, { "epoch": 11.57, "learning_rate": 1.137729e-05, "loss": 1.8319, "step": 3862 }, { "epoch": 11.57, "learning_rate": 1.1376585e-05, "loss": 1.8321, "step": 3863 }, { "epoch": 11.57, "learning_rate": 1.137588e-05, "loss": 1.8348, "step": 3864 }, { "epoch": 11.57, "learning_rate": 1.1375175e-05, "loss": 1.8312, "step": 3865 }, { "epoch": 11.58, "learning_rate": 1.137447e-05, "loss": 1.8336, "step": 3866 }, { "epoch": 11.58, "learning_rate": 1.1373765e-05, "loss": 1.8342, "step": 3867 }, { "epoch": 11.58, "learning_rate": 1.137306e-05, "loss": 1.8354, "step": 3868 }, { "epoch": 11.59, "learning_rate": 1.1372355e-05, "loss": 1.8322, "step": 3869 }, { "epoch": 11.59, "learning_rate": 1.137165e-05, "loss": 1.8327, "step": 3870 }, { "epoch": 11.59, "learning_rate": 1.1370945e-05, "loss": 1.8352, "step": 3871 }, { "epoch": 11.59, "learning_rate": 1.1370240000000001e-05, "loss": 1.8314, "step": 3872 }, { "epoch": 11.6, "learning_rate": 1.1369535000000001e-05, "loss": 1.8338, "step": 3873 }, { "epoch": 11.6, "learning_rate": 1.136883e-05, "loss": 1.8323, "step": 3874 }, { "epoch": 11.6, "learning_rate": 1.1368125e-05, "loss": 1.8328, "step": 3875 }, { "epoch": 11.61, "learning_rate": 1.136742e-05, "loss": 1.8297, "step": 3876 }, { "epoch": 11.61, "learning_rate": 1.1366715e-05, "loss": 1.8321, "step": 3877 }, { "epoch": 11.61, "learning_rate": 1.1366010000000002e-05, "loss": 1.8344, "step": 3878 }, { "epoch": 11.62, "learning_rate": 1.1365305000000001e-05, "loss": 1.8329, "step": 3879 }, { "epoch": 11.62, "learning_rate": 1.1364600000000001e-05, "loss": 1.8347, "step": 3880 }, { "epoch": 11.62, "learning_rate": 1.1363895000000001e-05, "loss": 1.834, "step": 3881 }, { "epoch": 11.62, "learning_rate": 1.136319e-05, "loss": 1.833, "step": 3882 }, { "epoch": 11.63, "learning_rate": 1.1362484999999999e-05, "loss": 1.832, "step": 3883 }, { "epoch": 11.63, "learning_rate": 1.136178e-05, "loss": 1.8317, "step": 3884 }, { "epoch": 11.63, "learning_rate": 1.1361075e-05, "loss": 1.8337, "step": 3885 }, { "epoch": 11.64, "learning_rate": 1.136037e-05, "loss": 1.8313, "step": 3886 }, { "epoch": 11.64, "learning_rate": 1.1359665e-05, "loss": 1.8317, "step": 3887 }, { "epoch": 11.64, "learning_rate": 1.135896e-05, "loss": 1.8302, "step": 3888 }, { "epoch": 11.65, "learning_rate": 1.1358255e-05, "loss": 1.828, "step": 3889 }, { "epoch": 11.65, "learning_rate": 1.1357550000000001e-05, "loss": 1.8307, "step": 3890 }, { "epoch": 11.65, "learning_rate": 1.1356845000000001e-05, "loss": 1.8298, "step": 3891 }, { "epoch": 11.65, "learning_rate": 1.135614e-05, "loss": 1.831, "step": 3892 }, { "epoch": 11.66, "learning_rate": 1.1355435e-05, "loss": 1.8328, "step": 3893 }, { "epoch": 11.66, "learning_rate": 1.135473e-05, "loss": 1.8324, "step": 3894 }, { "epoch": 11.66, "learning_rate": 1.1354025e-05, "loss": 1.8331, "step": 3895 }, { "epoch": 11.67, "learning_rate": 1.1353320000000002e-05, "loss": 1.832, "step": 3896 }, { "epoch": 11.67, "learning_rate": 1.1352615000000001e-05, "loss": 1.8319, "step": 3897 }, { "epoch": 11.67, "learning_rate": 1.1351910000000001e-05, "loss": 1.8319, "step": 3898 }, { "epoch": 11.68, "learning_rate": 1.1351205000000001e-05, "loss": 1.8342, "step": 3899 }, { "epoch": 11.68, "learning_rate": 1.1350500000000001e-05, "loss": 1.8305, "step": 3900 }, { "epoch": 11.68, "eval_accuracy": 0.0005570994127516778, "eval_loss": 1.775498390197754, "eval_runtime": 31.239, "eval_samples_per_second": 9.539, "eval_steps_per_second": 0.608, "step": 3900 }, { "epoch": 11.68, "learning_rate": 1.1349795e-05, "loss": 1.8332, "step": 3901 }, { "epoch": 11.68, "learning_rate": 1.134909e-05, "loss": 1.831, "step": 3902 }, { "epoch": 11.69, "learning_rate": 1.1348385e-05, "loss": 1.8315, "step": 3903 }, { "epoch": 11.69, "learning_rate": 1.134768e-05, "loss": 1.8312, "step": 3904 }, { "epoch": 11.69, "learning_rate": 1.1346975e-05, "loss": 1.8316, "step": 3905 }, { "epoch": 11.7, "learning_rate": 1.134627e-05, "loss": 1.8329, "step": 3906 }, { "epoch": 11.7, "learning_rate": 1.1345565e-05, "loss": 1.8295, "step": 3907 }, { "epoch": 11.7, "learning_rate": 1.134486e-05, "loss": 1.831, "step": 3908 }, { "epoch": 11.71, "learning_rate": 1.1344155e-05, "loss": 1.831, "step": 3909 }, { "epoch": 11.71, "learning_rate": 1.134345e-05, "loss": 1.8346, "step": 3910 }, { "epoch": 11.71, "learning_rate": 1.1342745e-05, "loss": 1.8301, "step": 3911 }, { "epoch": 11.71, "learning_rate": 1.134204e-05, "loss": 1.8294, "step": 3912 }, { "epoch": 11.72, "learning_rate": 1.1341335e-05, "loss": 1.8318, "step": 3913 }, { "epoch": 11.72, "learning_rate": 1.134063e-05, "loss": 1.8346, "step": 3914 }, { "epoch": 11.72, "learning_rate": 1.1339925000000001e-05, "loss": 1.8277, "step": 3915 }, { "epoch": 11.73, "learning_rate": 1.1339220000000001e-05, "loss": 1.8297, "step": 3916 }, { "epoch": 11.73, "learning_rate": 1.1338515000000001e-05, "loss": 1.8315, "step": 3917 }, { "epoch": 11.73, "learning_rate": 1.133781e-05, "loss": 1.8326, "step": 3918 }, { "epoch": 11.74, "learning_rate": 1.1337105e-05, "loss": 1.8266, "step": 3919 }, { "epoch": 11.74, "learning_rate": 1.13364e-05, "loss": 1.8352, "step": 3920 }, { "epoch": 11.74, "learning_rate": 1.1335695000000002e-05, "loss": 1.831, "step": 3921 }, { "epoch": 11.74, "learning_rate": 1.133499e-05, "loss": 1.8313, "step": 3922 }, { "epoch": 11.75, "learning_rate": 1.1334285e-05, "loss": 1.8302, "step": 3923 }, { "epoch": 11.75, "learning_rate": 1.133358e-05, "loss": 1.8326, "step": 3924 }, { "epoch": 11.75, "learning_rate": 1.1332875e-05, "loss": 1.8313, "step": 3925 }, { "epoch": 11.76, "learning_rate": 1.133217e-05, "loss": 1.8322, "step": 3926 }, { "epoch": 11.76, "learning_rate": 1.1331465e-05, "loss": 1.8304, "step": 3927 }, { "epoch": 11.76, "learning_rate": 1.133076e-05, "loss": 1.8315, "step": 3928 }, { "epoch": 11.77, "learning_rate": 1.1330055e-05, "loss": 1.8293, "step": 3929 }, { "epoch": 11.77, "learning_rate": 1.132935e-05, "loss": 1.8294, "step": 3930 }, { "epoch": 11.77, "learning_rate": 1.1328645e-05, "loss": 1.828, "step": 3931 }, { "epoch": 11.77, "learning_rate": 1.132794e-05, "loss": 1.8313, "step": 3932 }, { "epoch": 11.78, "learning_rate": 1.1327235000000001e-05, "loss": 1.8331, "step": 3933 }, { "epoch": 11.78, "learning_rate": 1.1326530000000001e-05, "loss": 1.8332, "step": 3934 }, { "epoch": 11.78, "learning_rate": 1.1325825000000001e-05, "loss": 1.8322, "step": 3935 }, { "epoch": 11.79, "learning_rate": 1.132512e-05, "loss": 1.83, "step": 3936 }, { "epoch": 11.79, "learning_rate": 1.1324415e-05, "loss": 1.8298, "step": 3937 }, { "epoch": 11.79, "learning_rate": 1.132371e-05, "loss": 1.8297, "step": 3938 }, { "epoch": 11.8, "learning_rate": 1.1323005e-05, "loss": 1.8313, "step": 3939 }, { "epoch": 11.8, "learning_rate": 1.1322300000000002e-05, "loss": 1.8287, "step": 3940 }, { "epoch": 11.8, "learning_rate": 1.1321595000000002e-05, "loss": 1.8312, "step": 3941 }, { "epoch": 11.8, "learning_rate": 1.132089e-05, "loss": 1.8319, "step": 3942 }, { "epoch": 11.81, "learning_rate": 1.1320185e-05, "loss": 1.8298, "step": 3943 }, { "epoch": 11.81, "learning_rate": 1.131948e-05, "loss": 1.8288, "step": 3944 }, { "epoch": 11.81, "learning_rate": 1.1318775e-05, "loss": 1.8318, "step": 3945 }, { "epoch": 11.82, "learning_rate": 1.131807e-05, "loss": 1.8311, "step": 3946 }, { "epoch": 11.82, "learning_rate": 1.1317365e-05, "loss": 1.8297, "step": 3947 }, { "epoch": 11.82, "learning_rate": 1.131666e-05, "loss": 1.8307, "step": 3948 }, { "epoch": 11.83, "learning_rate": 1.1315955e-05, "loss": 1.8325, "step": 3949 }, { "epoch": 11.83, "learning_rate": 1.131525e-05, "loss": 1.831, "step": 3950 }, { "epoch": 11.83, "learning_rate": 1.1314545e-05, "loss": 1.8315, "step": 3951 }, { "epoch": 11.83, "learning_rate": 1.1313840000000001e-05, "loss": 1.8303, "step": 3952 }, { "epoch": 11.84, "learning_rate": 1.1313135000000001e-05, "loss": 1.8307, "step": 3953 }, { "epoch": 11.84, "learning_rate": 1.131243e-05, "loss": 1.8314, "step": 3954 }, { "epoch": 11.84, "learning_rate": 1.1311725e-05, "loss": 1.8324, "step": 3955 }, { "epoch": 11.85, "learning_rate": 1.131102e-05, "loss": 1.8313, "step": 3956 }, { "epoch": 11.85, "learning_rate": 1.1310315e-05, "loss": 1.8289, "step": 3957 }, { "epoch": 11.85, "learning_rate": 1.1309610000000002e-05, "loss": 1.8302, "step": 3958 }, { "epoch": 11.86, "learning_rate": 1.1308905000000001e-05, "loss": 1.8321, "step": 3959 }, { "epoch": 11.86, "learning_rate": 1.1308200000000001e-05, "loss": 1.8297, "step": 3960 }, { "epoch": 11.86, "learning_rate": 1.1307495000000001e-05, "loss": 1.8309, "step": 3961 }, { "epoch": 11.86, "learning_rate": 1.130679e-05, "loss": 1.8324, "step": 3962 }, { "epoch": 11.87, "learning_rate": 1.1306084999999999e-05, "loss": 1.8297, "step": 3963 }, { "epoch": 11.87, "learning_rate": 1.130538e-05, "loss": 1.8284, "step": 3964 }, { "epoch": 11.87, "learning_rate": 1.1304675e-05, "loss": 1.8284, "step": 3965 }, { "epoch": 11.88, "learning_rate": 1.130397e-05, "loss": 1.8292, "step": 3966 }, { "epoch": 11.88, "learning_rate": 1.1303265e-05, "loss": 1.8281, "step": 3967 }, { "epoch": 11.88, "learning_rate": 1.130256e-05, "loss": 1.8317, "step": 3968 }, { "epoch": 11.89, "learning_rate": 1.1301855e-05, "loss": 1.8274, "step": 3969 }, { "epoch": 11.89, "learning_rate": 1.1301150000000001e-05, "loss": 1.8289, "step": 3970 }, { "epoch": 11.89, "learning_rate": 1.1300445000000001e-05, "loss": 1.8312, "step": 3971 }, { "epoch": 11.89, "learning_rate": 1.129974e-05, "loss": 1.8274, "step": 3972 }, { "epoch": 11.9, "learning_rate": 1.1299035e-05, "loss": 1.8288, "step": 3973 }, { "epoch": 11.9, "learning_rate": 1.129833e-05, "loss": 1.8303, "step": 3974 }, { "epoch": 11.9, "learning_rate": 1.1297625e-05, "loss": 1.8284, "step": 3975 }, { "epoch": 11.91, "learning_rate": 1.129692e-05, "loss": 1.8278, "step": 3976 }, { "epoch": 11.91, "learning_rate": 1.1296215000000001e-05, "loss": 1.832, "step": 3977 }, { "epoch": 11.91, "learning_rate": 1.1295510000000001e-05, "loss": 1.8258, "step": 3978 }, { "epoch": 11.92, "learning_rate": 1.1294805000000001e-05, "loss": 1.828, "step": 3979 }, { "epoch": 11.92, "learning_rate": 1.12941e-05, "loss": 1.8293, "step": 3980 }, { "epoch": 11.92, "learning_rate": 1.1293395e-05, "loss": 1.8282, "step": 3981 }, { "epoch": 11.92, "learning_rate": 1.129269e-05, "loss": 1.8305, "step": 3982 }, { "epoch": 11.93, "learning_rate": 1.1291985e-05, "loss": 1.8301, "step": 3983 }, { "epoch": 11.93, "learning_rate": 1.129128e-05, "loss": 1.829, "step": 3984 }, { "epoch": 11.93, "learning_rate": 1.1290575e-05, "loss": 1.8283, "step": 3985 }, { "epoch": 11.94, "learning_rate": 1.128987e-05, "loss": 1.8277, "step": 3986 }, { "epoch": 11.94, "learning_rate": 1.1289165e-05, "loss": 1.8287, "step": 3987 }, { "epoch": 11.94, "learning_rate": 1.128846e-05, "loss": 1.8272, "step": 3988 }, { "epoch": 11.95, "learning_rate": 1.1287755e-05, "loss": 1.8289, "step": 3989 }, { "epoch": 11.95, "learning_rate": 1.128705e-05, "loss": 1.8307, "step": 3990 }, { "epoch": 11.95, "learning_rate": 1.1286345e-05, "loss": 1.8252, "step": 3991 }, { "epoch": 11.95, "learning_rate": 1.128564e-05, "loss": 1.8293, "step": 3992 }, { "epoch": 11.96, "learning_rate": 1.1284935e-05, "loss": 1.8294, "step": 3993 }, { "epoch": 11.96, "learning_rate": 1.128423e-05, "loss": 1.8292, "step": 3994 }, { "epoch": 11.96, "learning_rate": 1.1283525000000001e-05, "loss": 1.8321, "step": 3995 }, { "epoch": 11.97, "learning_rate": 1.1282820000000001e-05, "loss": 1.8309, "step": 3996 }, { "epoch": 11.97, "learning_rate": 1.1282115000000001e-05, "loss": 1.8276, "step": 3997 }, { "epoch": 11.97, "learning_rate": 1.128141e-05, "loss": 1.8284, "step": 3998 }, { "epoch": 11.98, "learning_rate": 1.1280705e-05, "loss": 1.8282, "step": 3999 }, { "epoch": 11.98, "learning_rate": 1.128e-05, "loss": 1.8263, "step": 4000 }, { "epoch": 11.98, "eval_accuracy": 0.0005570994127516778, "eval_loss": 1.7732090950012207, "eval_runtime": 29.966, "eval_samples_per_second": 9.945, "eval_steps_per_second": 0.634, "step": 4000 }, { "epoch": 11.98, "learning_rate": 1.1279295000000002e-05, "loss": 1.832, "step": 4001 }, { "epoch": 11.98, "learning_rate": 1.1278590000000002e-05, "loss": 1.8287, "step": 4002 }, { "epoch": 11.99, "learning_rate": 1.1277885e-05, "loss": 1.8272, "step": 4003 }, { "epoch": 11.99, "learning_rate": 1.127718e-05, "loss": 1.8277, "step": 4004 }, { "epoch": 11.99, "learning_rate": 1.1276475e-05, "loss": 1.8301, "step": 4005 }, { "epoch": 12.0, "learning_rate": 1.127577e-05, "loss": 1.8317, "step": 4006 }, { "epoch": 12.0, "learning_rate": 1.1275065e-05, "loss": 1.8283, "step": 4007 }, { "epoch": 12.0, "learning_rate": 1.127436e-05, "loss": 1.8308, "step": 4008 }, { "epoch": 12.01, "learning_rate": 1.1273655e-05, "loss": 1.8294, "step": 4009 }, { "epoch": 12.01, "learning_rate": 1.127295e-05, "loss": 1.8272, "step": 4010 }, { "epoch": 12.01, "learning_rate": 1.1272245e-05, "loss": 1.8297, "step": 4011 }, { "epoch": 12.01, "learning_rate": 1.127154e-05, "loss": 1.8272, "step": 4012 }, { "epoch": 12.02, "learning_rate": 1.1270835000000001e-05, "loss": 1.8264, "step": 4013 }, { "epoch": 12.02, "learning_rate": 1.1270130000000001e-05, "loss": 1.8258, "step": 4014 }, { "epoch": 12.02, "learning_rate": 1.1269425000000001e-05, "loss": 1.8279, "step": 4015 }, { "epoch": 12.03, "learning_rate": 1.126872e-05, "loss": 1.8297, "step": 4016 }, { "epoch": 12.03, "learning_rate": 1.1268015e-05, "loss": 1.8276, "step": 4017 }, { "epoch": 12.03, "learning_rate": 1.126731e-05, "loss": 1.8286, "step": 4018 }, { "epoch": 12.04, "learning_rate": 1.1266605e-05, "loss": 1.8284, "step": 4019 }, { "epoch": 12.04, "learning_rate": 1.1265900000000002e-05, "loss": 1.8285, "step": 4020 }, { "epoch": 12.04, "learning_rate": 1.1265195000000002e-05, "loss": 1.8303, "step": 4021 }, { "epoch": 12.04, "learning_rate": 1.1264490000000001e-05, "loss": 1.829, "step": 4022 }, { "epoch": 12.05, "learning_rate": 1.1263785e-05, "loss": 1.829, "step": 4023 }, { "epoch": 12.05, "learning_rate": 1.126308e-05, "loss": 1.8288, "step": 4024 }, { "epoch": 12.05, "learning_rate": 1.1262374999999999e-05, "loss": 1.8321, "step": 4025 }, { "epoch": 12.06, "learning_rate": 1.126167e-05, "loss": 1.8269, "step": 4026 }, { "epoch": 12.06, "learning_rate": 1.1260965e-05, "loss": 1.83, "step": 4027 }, { "epoch": 12.06, "learning_rate": 1.126026e-05, "loss": 1.8277, "step": 4028 }, { "epoch": 12.07, "learning_rate": 1.1259555e-05, "loss": 1.8279, "step": 4029 }, { "epoch": 12.07, "learning_rate": 1.125885e-05, "loss": 1.8311, "step": 4030 }, { "epoch": 12.07, "learning_rate": 1.1258145e-05, "loss": 1.8296, "step": 4031 }, { "epoch": 12.07, "learning_rate": 1.1257440000000001e-05, "loss": 1.8268, "step": 4032 }, { "epoch": 12.08, "learning_rate": 1.1256735000000001e-05, "loss": 1.8249, "step": 4033 }, { "epoch": 12.08, "learning_rate": 1.125603e-05, "loss": 1.8308, "step": 4034 }, { "epoch": 12.08, "learning_rate": 1.1255325e-05, "loss": 1.8276, "step": 4035 }, { "epoch": 12.09, "learning_rate": 1.125462e-05, "loss": 1.8286, "step": 4036 }, { "epoch": 12.09, "learning_rate": 1.1253915e-05, "loss": 1.8274, "step": 4037 }, { "epoch": 12.09, "learning_rate": 1.1253210000000002e-05, "loss": 1.8266, "step": 4038 }, { "epoch": 12.1, "learning_rate": 1.1252505000000001e-05, "loss": 1.8274, "step": 4039 }, { "epoch": 12.1, "learning_rate": 1.1251800000000001e-05, "loss": 1.8295, "step": 4040 }, { "epoch": 12.1, "learning_rate": 1.1251095000000001e-05, "loss": 1.8296, "step": 4041 }, { "epoch": 12.1, "learning_rate": 1.1250390000000001e-05, "loss": 1.8298, "step": 4042 }, { "epoch": 12.11, "learning_rate": 1.1249684999999999e-05, "loss": 1.8291, "step": 4043 }, { "epoch": 12.11, "learning_rate": 1.124898e-05, "loss": 1.8274, "step": 4044 }, { "epoch": 12.11, "learning_rate": 1.1248275e-05, "loss": 1.826, "step": 4045 }, { "epoch": 12.12, "learning_rate": 1.124757e-05, "loss": 1.8294, "step": 4046 }, { "epoch": 12.12, "learning_rate": 1.1246865e-05, "loss": 1.8273, "step": 4047 }, { "epoch": 12.12, "learning_rate": 1.124616e-05, "loss": 1.8296, "step": 4048 }, { "epoch": 12.13, "learning_rate": 1.1245455e-05, "loss": 1.8249, "step": 4049 }, { "epoch": 12.13, "learning_rate": 1.1244750000000001e-05, "loss": 1.8261, "step": 4050 }, { "epoch": 12.13, "learning_rate": 1.1244045000000001e-05, "loss": 1.8261, "step": 4051 }, { "epoch": 12.13, "learning_rate": 1.124334e-05, "loss": 1.8248, "step": 4052 }, { "epoch": 12.14, "learning_rate": 1.1242635e-05, "loss": 1.8277, "step": 4053 }, { "epoch": 12.14, "learning_rate": 1.124193e-05, "loss": 1.8309, "step": 4054 }, { "epoch": 12.14, "learning_rate": 1.1241225e-05, "loss": 1.8255, "step": 4055 }, { "epoch": 12.15, "learning_rate": 1.124052e-05, "loss": 1.826, "step": 4056 }, { "epoch": 12.15, "learning_rate": 1.1239815000000001e-05, "loss": 1.8294, "step": 4057 }, { "epoch": 12.15, "learning_rate": 1.1239110000000001e-05, "loss": 1.8271, "step": 4058 }, { "epoch": 12.15, "learning_rate": 1.1238405000000001e-05, "loss": 1.8288, "step": 4059 }, { "epoch": 12.16, "learning_rate": 1.12377e-05, "loss": 1.8276, "step": 4060 }, { "epoch": 12.16, "learning_rate": 1.1236995e-05, "loss": 1.8259, "step": 4061 }, { "epoch": 12.16, "learning_rate": 1.123629e-05, "loss": 1.829, "step": 4062 }, { "epoch": 12.17, "learning_rate": 1.1235585e-05, "loss": 1.8239, "step": 4063 }, { "epoch": 12.17, "learning_rate": 1.123488e-05, "loss": 1.8259, "step": 4064 }, { "epoch": 12.17, "learning_rate": 1.1234175e-05, "loss": 1.828, "step": 4065 }, { "epoch": 12.18, "learning_rate": 1.123347e-05, "loss": 1.8293, "step": 4066 }, { "epoch": 12.18, "learning_rate": 1.1232765e-05, "loss": 1.8271, "step": 4067 }, { "epoch": 12.18, "learning_rate": 1.123206e-05, "loss": 1.8255, "step": 4068 }, { "epoch": 12.18, "learning_rate": 1.1231355e-05, "loss": 1.8262, "step": 4069 }, { "epoch": 12.19, "learning_rate": 1.123065e-05, "loss": 1.825, "step": 4070 }, { "epoch": 12.19, "learning_rate": 1.1229945e-05, "loss": 1.8268, "step": 4071 }, { "epoch": 12.19, "learning_rate": 1.122924e-05, "loss": 1.8249, "step": 4072 }, { "epoch": 12.2, "learning_rate": 1.1228535e-05, "loss": 1.8277, "step": 4073 }, { "epoch": 12.2, "learning_rate": 1.122783e-05, "loss": 1.8272, "step": 4074 }, { "epoch": 12.2, "learning_rate": 1.1227125000000001e-05, "loss": 1.8273, "step": 4075 }, { "epoch": 12.21, "learning_rate": 1.1226420000000001e-05, "loss": 1.8235, "step": 4076 }, { "epoch": 12.21, "learning_rate": 1.1225715000000001e-05, "loss": 1.8265, "step": 4077 }, { "epoch": 12.21, "learning_rate": 1.122501e-05, "loss": 1.8251, "step": 4078 }, { "epoch": 12.21, "learning_rate": 1.1224305e-05, "loss": 1.8256, "step": 4079 }, { "epoch": 12.22, "learning_rate": 1.12236e-05, "loss": 1.8279, "step": 4080 }, { "epoch": 12.22, "learning_rate": 1.1222895e-05, "loss": 1.8242, "step": 4081 }, { "epoch": 12.22, "learning_rate": 1.1222190000000002e-05, "loss": 1.8241, "step": 4082 }, { "epoch": 12.23, "learning_rate": 1.1221485e-05, "loss": 1.8271, "step": 4083 }, { "epoch": 12.23, "learning_rate": 1.122078e-05, "loss": 1.8241, "step": 4084 }, { "epoch": 12.23, "learning_rate": 1.1220075e-05, "loss": 1.8274, "step": 4085 }, { "epoch": 12.24, "learning_rate": 1.121937e-05, "loss": 1.8275, "step": 4086 }, { "epoch": 12.24, "learning_rate": 1.1218665e-05, "loss": 1.8254, "step": 4087 }, { "epoch": 12.24, "learning_rate": 1.121796e-05, "loss": 1.8242, "step": 4088 }, { "epoch": 12.24, "learning_rate": 1.1217255e-05, "loss": 1.8269, "step": 4089 }, { "epoch": 12.25, "learning_rate": 1.121655e-05, "loss": 1.8256, "step": 4090 }, { "epoch": 12.25, "learning_rate": 1.1215845e-05, "loss": 1.8257, "step": 4091 }, { "epoch": 12.25, "learning_rate": 1.121514e-05, "loss": 1.8278, "step": 4092 }, { "epoch": 12.26, "learning_rate": 1.1214435e-05, "loss": 1.8249, "step": 4093 }, { "epoch": 12.26, "learning_rate": 1.1213730000000001e-05, "loss": 1.8248, "step": 4094 }, { "epoch": 12.26, "learning_rate": 1.1213025000000001e-05, "loss": 1.8231, "step": 4095 }, { "epoch": 12.27, "learning_rate": 1.121232e-05, "loss": 1.8258, "step": 4096 }, { "epoch": 12.27, "learning_rate": 1.1211615e-05, "loss": 1.8236, "step": 4097 }, { "epoch": 12.27, "learning_rate": 1.121091e-05, "loss": 1.8242, "step": 4098 }, { "epoch": 12.27, "learning_rate": 1.1210205e-05, "loss": 1.8242, "step": 4099 }, { "epoch": 12.28, "learning_rate": 1.1209500000000002e-05, "loss": 1.8267, "step": 4100 }, { "epoch": 12.28, "eval_accuracy": 0.0005636535234899329, "eval_loss": 1.770839810371399, "eval_runtime": 29.4428, "eval_samples_per_second": 10.121, "eval_steps_per_second": 0.645, "step": 4100 }, { "epoch": 12.28, "learning_rate": 1.1208795000000001e-05, "loss": 1.825, "step": 4101 }, { "epoch": 12.28, "learning_rate": 1.1208090000000001e-05, "loss": 1.827, "step": 4102 }, { "epoch": 12.29, "learning_rate": 1.1207385e-05, "loss": 1.824, "step": 4103 }, { "epoch": 12.29, "learning_rate": 1.120668e-05, "loss": 1.828, "step": 4104 }, { "epoch": 12.29, "learning_rate": 1.1205974999999999e-05, "loss": 1.8265, "step": 4105 }, { "epoch": 12.3, "learning_rate": 1.120527e-05, "loss": 1.8247, "step": 4106 }, { "epoch": 12.3, "learning_rate": 1.1204565e-05, "loss": 1.827, "step": 4107 }, { "epoch": 12.3, "learning_rate": 1.120386e-05, "loss": 1.8233, "step": 4108 }, { "epoch": 12.3, "learning_rate": 1.1203155e-05, "loss": 1.8248, "step": 4109 }, { "epoch": 12.31, "learning_rate": 1.120245e-05, "loss": 1.8256, "step": 4110 }, { "epoch": 12.31, "learning_rate": 1.1201745e-05, "loss": 1.8248, "step": 4111 }, { "epoch": 12.31, "learning_rate": 1.1201040000000001e-05, "loss": 1.8257, "step": 4112 }, { "epoch": 12.32, "learning_rate": 1.1200335000000001e-05, "loss": 1.8249, "step": 4113 }, { "epoch": 12.32, "learning_rate": 1.119963e-05, "loss": 1.8262, "step": 4114 }, { "epoch": 12.32, "learning_rate": 1.1198925e-05, "loss": 1.826, "step": 4115 }, { "epoch": 12.33, "learning_rate": 1.119822e-05, "loss": 1.8253, "step": 4116 }, { "epoch": 12.33, "learning_rate": 1.1197515e-05, "loss": 1.8256, "step": 4117 }, { "epoch": 12.33, "learning_rate": 1.1196810000000002e-05, "loss": 1.8279, "step": 4118 }, { "epoch": 12.33, "learning_rate": 1.1196105000000001e-05, "loss": 1.8277, "step": 4119 }, { "epoch": 12.34, "learning_rate": 1.1195400000000001e-05, "loss": 1.8268, "step": 4120 }, { "epoch": 12.34, "learning_rate": 1.1194695000000001e-05, "loss": 1.827, "step": 4121 }, { "epoch": 12.34, "learning_rate": 1.1193990000000001e-05, "loss": 1.8272, "step": 4122 }, { "epoch": 12.35, "learning_rate": 1.1193284999999999e-05, "loss": 1.8246, "step": 4123 }, { "epoch": 12.35, "learning_rate": 1.119258e-05, "loss": 1.8233, "step": 4124 }, { "epoch": 12.35, "learning_rate": 1.1191875e-05, "loss": 1.8258, "step": 4125 }, { "epoch": 12.36, "learning_rate": 1.119117e-05, "loss": 1.8241, "step": 4126 }, { "epoch": 12.36, "learning_rate": 1.1190465e-05, "loss": 1.8251, "step": 4127 }, { "epoch": 12.36, "learning_rate": 1.118976e-05, "loss": 1.8212, "step": 4128 }, { "epoch": 12.36, "learning_rate": 1.1189055e-05, "loss": 1.8254, "step": 4129 }, { "epoch": 12.37, "learning_rate": 1.118835e-05, "loss": 1.8273, "step": 4130 }, { "epoch": 12.37, "learning_rate": 1.1187645000000001e-05, "loss": 1.824, "step": 4131 }, { "epoch": 12.37, "learning_rate": 1.118694e-05, "loss": 1.8234, "step": 4132 }, { "epoch": 12.38, "learning_rate": 1.1186235e-05, "loss": 1.825, "step": 4133 }, { "epoch": 12.38, "learning_rate": 1.118553e-05, "loss": 1.8248, "step": 4134 }, { "epoch": 12.38, "learning_rate": 1.1184825e-05, "loss": 1.8245, "step": 4135 }, { "epoch": 12.39, "learning_rate": 1.118412e-05, "loss": 1.824, "step": 4136 }, { "epoch": 12.39, "learning_rate": 1.1183415000000001e-05, "loss": 1.8257, "step": 4137 }, { "epoch": 12.39, "learning_rate": 1.1182710000000001e-05, "loss": 1.8227, "step": 4138 }, { "epoch": 12.39, "learning_rate": 1.1182005000000001e-05, "loss": 1.8262, "step": 4139 }, { "epoch": 12.4, "learning_rate": 1.11813e-05, "loss": 1.8246, "step": 4140 }, { "epoch": 12.4, "learning_rate": 1.1180595e-05, "loss": 1.8251, "step": 4141 }, { "epoch": 12.4, "learning_rate": 1.117989e-05, "loss": 1.8243, "step": 4142 }, { "epoch": 12.41, "learning_rate": 1.1179185000000002e-05, "loss": 1.8299, "step": 4143 }, { "epoch": 12.41, "learning_rate": 1.117848e-05, "loss": 1.8248, "step": 4144 }, { "epoch": 12.41, "learning_rate": 1.1177775e-05, "loss": 1.8254, "step": 4145 }, { "epoch": 12.42, "learning_rate": 1.117707e-05, "loss": 1.8209, "step": 4146 }, { "epoch": 12.42, "learning_rate": 1.1176365e-05, "loss": 1.8225, "step": 4147 }, { "epoch": 12.42, "learning_rate": 1.117566e-05, "loss": 1.8243, "step": 4148 }, { "epoch": 12.42, "learning_rate": 1.1174955e-05, "loss": 1.8241, "step": 4149 }, { "epoch": 12.43, "learning_rate": 1.117425e-05, "loss": 1.8226, "step": 4150 }, { "epoch": 12.43, "learning_rate": 1.1173545e-05, "loss": 1.8242, "step": 4151 }, { "epoch": 12.43, "learning_rate": 1.117284e-05, "loss": 1.8236, "step": 4152 }, { "epoch": 12.44, "learning_rate": 1.1172135e-05, "loss": 1.8283, "step": 4153 }, { "epoch": 12.44, "learning_rate": 1.117143e-05, "loss": 1.8248, "step": 4154 }, { "epoch": 12.44, "learning_rate": 1.1170725000000001e-05, "loss": 1.8221, "step": 4155 }, { "epoch": 12.45, "learning_rate": 1.1170020000000001e-05, "loss": 1.8225, "step": 4156 }, { "epoch": 12.45, "learning_rate": 1.1169315000000001e-05, "loss": 1.8256, "step": 4157 }, { "epoch": 12.45, "learning_rate": 1.116861e-05, "loss": 1.8253, "step": 4158 }, { "epoch": 12.45, "learning_rate": 1.1167905e-05, "loss": 1.8241, "step": 4159 }, { "epoch": 12.46, "learning_rate": 1.11672e-05, "loss": 1.8237, "step": 4160 }, { "epoch": 12.46, "learning_rate": 1.1166495e-05, "loss": 1.8224, "step": 4161 }, { "epoch": 12.46, "learning_rate": 1.1165790000000002e-05, "loss": 1.8232, "step": 4162 }, { "epoch": 12.47, "learning_rate": 1.1165085000000002e-05, "loss": 1.8241, "step": 4163 }, { "epoch": 12.47, "learning_rate": 1.116438e-05, "loss": 1.8233, "step": 4164 }, { "epoch": 12.47, "learning_rate": 1.1163675e-05, "loss": 1.8227, "step": 4165 }, { "epoch": 12.48, "learning_rate": 1.116297e-05, "loss": 1.8251, "step": 4166 }, { "epoch": 12.48, "learning_rate": 1.1162264999999999e-05, "loss": 1.8232, "step": 4167 }, { "epoch": 12.48, "learning_rate": 1.116156e-05, "loss": 1.8241, "step": 4168 }, { "epoch": 12.48, "learning_rate": 1.1160855e-05, "loss": 1.8217, "step": 4169 }, { "epoch": 12.49, "learning_rate": 1.116015e-05, "loss": 1.8224, "step": 4170 }, { "epoch": 12.49, "learning_rate": 1.1159445e-05, "loss": 1.8236, "step": 4171 }, { "epoch": 12.49, "learning_rate": 1.115874e-05, "loss": 1.8236, "step": 4172 }, { "epoch": 12.5, "learning_rate": 1.1158035e-05, "loss": 1.8232, "step": 4173 }, { "epoch": 12.5, "learning_rate": 1.1157330000000001e-05, "loss": 1.8202, "step": 4174 }, { "epoch": 12.5, "learning_rate": 1.1156625000000001e-05, "loss": 1.8249, "step": 4175 }, { "epoch": 12.51, "learning_rate": 1.115592e-05, "loss": 1.8268, "step": 4176 }, { "epoch": 12.51, "learning_rate": 1.1155215e-05, "loss": 1.8246, "step": 4177 }, { "epoch": 12.51, "learning_rate": 1.115451e-05, "loss": 1.8251, "step": 4178 }, { "epoch": 12.51, "learning_rate": 1.1153805e-05, "loss": 1.8233, "step": 4179 }, { "epoch": 12.52, "learning_rate": 1.1153100000000002e-05, "loss": 1.8211, "step": 4180 }, { "epoch": 12.52, "learning_rate": 1.1152395000000001e-05, "loss": 1.8233, "step": 4181 }, { "epoch": 12.52, "learning_rate": 1.1151690000000001e-05, "loss": 1.8213, "step": 4182 }, { "epoch": 12.53, "learning_rate": 1.1150985000000001e-05, "loss": 1.8266, "step": 4183 }, { "epoch": 12.53, "learning_rate": 1.115028e-05, "loss": 1.8247, "step": 4184 }, { "epoch": 12.53, "learning_rate": 1.1149574999999999e-05, "loss": 1.8227, "step": 4185 }, { "epoch": 12.54, "learning_rate": 1.114887e-05, "loss": 1.8216, "step": 4186 }, { "epoch": 12.54, "learning_rate": 1.1148165e-05, "loss": 1.8241, "step": 4187 }, { "epoch": 12.54, "learning_rate": 1.114746e-05, "loss": 1.8242, "step": 4188 }, { "epoch": 12.54, "learning_rate": 1.1146755e-05, "loss": 1.8224, "step": 4189 }, { "epoch": 12.55, "learning_rate": 1.114605e-05, "loss": 1.8228, "step": 4190 }, { "epoch": 12.55, "learning_rate": 1.1145345e-05, "loss": 1.8219, "step": 4191 }, { "epoch": 12.55, "learning_rate": 1.1144640000000001e-05, "loss": 1.8221, "step": 4192 }, { "epoch": 12.56, "learning_rate": 1.1143935000000001e-05, "loss": 1.8236, "step": 4193 }, { "epoch": 12.56, "learning_rate": 1.114323e-05, "loss": 1.8223, "step": 4194 }, { "epoch": 12.56, "learning_rate": 1.1142525e-05, "loss": 1.8256, "step": 4195 }, { "epoch": 12.57, "learning_rate": 1.114182e-05, "loss": 1.8235, "step": 4196 }, { "epoch": 12.57, "learning_rate": 1.1141115e-05, "loss": 1.824, "step": 4197 }, { "epoch": 12.57, "learning_rate": 1.114041e-05, "loss": 1.822, "step": 4198 }, { "epoch": 12.57, "learning_rate": 1.1139705000000001e-05, "loss": 1.8211, "step": 4199 }, { "epoch": 12.58, "learning_rate": 1.1139000000000001e-05, "loss": 1.8226, "step": 4200 }, { "epoch": 12.58, "eval_accuracy": 0.000570207634228188, "eval_loss": 1.768692135810852, "eval_runtime": 30.5127, "eval_samples_per_second": 9.766, "eval_steps_per_second": 0.623, "step": 4200 }, { "epoch": 12.58, "learning_rate": 1.1138295000000001e-05, "loss": 1.8219, "step": 4201 }, { "epoch": 12.58, "learning_rate": 1.1137590000000001e-05, "loss": 1.8228, "step": 4202 }, { "epoch": 12.59, "learning_rate": 1.1136885e-05, "loss": 1.8241, "step": 4203 }, { "epoch": 12.59, "learning_rate": 1.113618e-05, "loss": 1.8226, "step": 4204 }, { "epoch": 12.59, "learning_rate": 1.1135475e-05, "loss": 1.8233, "step": 4205 }, { "epoch": 12.6, "learning_rate": 1.113477e-05, "loss": 1.823, "step": 4206 }, { "epoch": 12.6, "learning_rate": 1.1134065e-05, "loss": 1.8219, "step": 4207 }, { "epoch": 12.6, "learning_rate": 1.113336e-05, "loss": 1.8275, "step": 4208 }, { "epoch": 12.6, "learning_rate": 1.1132655e-05, "loss": 1.825, "step": 4209 }, { "epoch": 12.61, "learning_rate": 1.113195e-05, "loss": 1.822, "step": 4210 }, { "epoch": 12.61, "learning_rate": 1.1131245000000001e-05, "loss": 1.823, "step": 4211 }, { "epoch": 12.61, "learning_rate": 1.113054e-05, "loss": 1.8238, "step": 4212 }, { "epoch": 12.62, "learning_rate": 1.1129835e-05, "loss": 1.8232, "step": 4213 }, { "epoch": 12.62, "learning_rate": 1.112913e-05, "loss": 1.8217, "step": 4214 }, { "epoch": 12.62, "learning_rate": 1.1128425e-05, "loss": 1.8271, "step": 4215 }, { "epoch": 12.63, "learning_rate": 1.112772e-05, "loss": 1.8247, "step": 4216 }, { "epoch": 12.63, "learning_rate": 1.1127015000000001e-05, "loss": 1.8227, "step": 4217 }, { "epoch": 12.63, "learning_rate": 1.1126310000000001e-05, "loss": 1.822, "step": 4218 }, { "epoch": 12.63, "learning_rate": 1.1125605000000001e-05, "loss": 1.8209, "step": 4219 }, { "epoch": 12.64, "learning_rate": 1.11249e-05, "loss": 1.823, "step": 4220 }, { "epoch": 12.64, "learning_rate": 1.1124195e-05, "loss": 1.8227, "step": 4221 }, { "epoch": 12.64, "learning_rate": 1.112349e-05, "loss": 1.8217, "step": 4222 }, { "epoch": 12.65, "learning_rate": 1.1122785000000002e-05, "loss": 1.822, "step": 4223 }, { "epoch": 12.65, "learning_rate": 1.112208e-05, "loss": 1.8189, "step": 4224 }, { "epoch": 12.65, "learning_rate": 1.1121375e-05, "loss": 1.82, "step": 4225 }, { "epoch": 12.66, "learning_rate": 1.112067e-05, "loss": 1.8224, "step": 4226 }, { "epoch": 12.66, "learning_rate": 1.1119965e-05, "loss": 1.8223, "step": 4227 }, { "epoch": 12.66, "learning_rate": 1.111926e-05, "loss": 1.8206, "step": 4228 }, { "epoch": 12.66, "learning_rate": 1.1118555e-05, "loss": 1.82, "step": 4229 }, { "epoch": 12.67, "learning_rate": 1.111785e-05, "loss": 1.8218, "step": 4230 }, { "epoch": 12.67, "learning_rate": 1.1117145e-05, "loss": 1.823, "step": 4231 }, { "epoch": 12.67, "learning_rate": 1.111644e-05, "loss": 1.8187, "step": 4232 }, { "epoch": 12.68, "learning_rate": 1.1115735e-05, "loss": 1.8229, "step": 4233 }, { "epoch": 12.68, "learning_rate": 1.111503e-05, "loss": 1.8226, "step": 4234 }, { "epoch": 12.68, "learning_rate": 1.1114325e-05, "loss": 1.8209, "step": 4235 }, { "epoch": 12.69, "learning_rate": 1.1113620000000001e-05, "loss": 1.8229, "step": 4236 }, { "epoch": 12.69, "learning_rate": 1.1112915000000001e-05, "loss": 1.8197, "step": 4237 }, { "epoch": 12.69, "learning_rate": 1.111221e-05, "loss": 1.8243, "step": 4238 }, { "epoch": 12.69, "learning_rate": 1.1111505e-05, "loss": 1.8219, "step": 4239 }, { "epoch": 12.7, "learning_rate": 1.11108e-05, "loss": 1.8183, "step": 4240 }, { "epoch": 12.7, "learning_rate": 1.1110095e-05, "loss": 1.8213, "step": 4241 }, { "epoch": 12.7, "learning_rate": 1.1109390000000002e-05, "loss": 1.822, "step": 4242 }, { "epoch": 12.71, "learning_rate": 1.1108685000000002e-05, "loss": 1.8215, "step": 4243 }, { "epoch": 12.71, "learning_rate": 1.110798e-05, "loss": 1.8194, "step": 4244 }, { "epoch": 12.71, "learning_rate": 1.1107275e-05, "loss": 1.8212, "step": 4245 }, { "epoch": 12.71, "learning_rate": 1.110657e-05, "loss": 1.8222, "step": 4246 }, { "epoch": 12.72, "learning_rate": 1.1105864999999999e-05, "loss": 1.8194, "step": 4247 }, { "epoch": 12.72, "learning_rate": 1.110516e-05, "loss": 1.8229, "step": 4248 }, { "epoch": 12.72, "learning_rate": 1.1104455e-05, "loss": 1.8214, "step": 4249 }, { "epoch": 12.73, "learning_rate": 1.110375e-05, "loss": 1.8213, "step": 4250 }, { "epoch": 12.73, "learning_rate": 1.1103045e-05, "loss": 1.8218, "step": 4251 }, { "epoch": 12.73, "learning_rate": 1.110234e-05, "loss": 1.821, "step": 4252 }, { "epoch": 12.74, "learning_rate": 1.1101635e-05, "loss": 1.8236, "step": 4253 }, { "epoch": 12.74, "learning_rate": 1.1100930000000001e-05, "loss": 1.8231, "step": 4254 }, { "epoch": 12.74, "learning_rate": 1.1100225000000001e-05, "loss": 1.8206, "step": 4255 }, { "epoch": 12.74, "learning_rate": 1.109952e-05, "loss": 1.8212, "step": 4256 }, { "epoch": 12.75, "learning_rate": 1.1098815e-05, "loss": 1.8206, "step": 4257 }, { "epoch": 12.75, "learning_rate": 1.109811e-05, "loss": 1.8207, "step": 4258 }, { "epoch": 12.75, "learning_rate": 1.1097405e-05, "loss": 1.8199, "step": 4259 }, { "epoch": 12.76, "learning_rate": 1.1096700000000002e-05, "loss": 1.8211, "step": 4260 }, { "epoch": 12.76, "learning_rate": 1.1095995000000001e-05, "loss": 1.8197, "step": 4261 }, { "epoch": 12.76, "learning_rate": 1.1095290000000001e-05, "loss": 1.8199, "step": 4262 }, { "epoch": 12.77, "learning_rate": 1.1094585000000001e-05, "loss": 1.8196, "step": 4263 }, { "epoch": 12.77, "learning_rate": 1.1093880000000001e-05, "loss": 1.8217, "step": 4264 }, { "epoch": 12.77, "learning_rate": 1.1093174999999999e-05, "loss": 1.8215, "step": 4265 }, { "epoch": 12.77, "learning_rate": 1.109247e-05, "loss": 1.8204, "step": 4266 }, { "epoch": 12.78, "learning_rate": 1.1091765e-05, "loss": 1.8219, "step": 4267 }, { "epoch": 12.78, "learning_rate": 1.109106e-05, "loss": 1.8219, "step": 4268 }, { "epoch": 12.78, "learning_rate": 1.1090355e-05, "loss": 1.8218, "step": 4269 }, { "epoch": 12.79, "learning_rate": 1.108965e-05, "loss": 1.8201, "step": 4270 }, { "epoch": 12.79, "learning_rate": 1.1088945e-05, "loss": 1.825, "step": 4271 }, { "epoch": 12.79, "learning_rate": 1.108824e-05, "loss": 1.8218, "step": 4272 }, { "epoch": 12.8, "learning_rate": 1.1087535000000001e-05, "loss": 1.8205, "step": 4273 }, { "epoch": 12.8, "learning_rate": 1.108683e-05, "loss": 1.8209, "step": 4274 }, { "epoch": 12.8, "learning_rate": 1.1086125e-05, "loss": 1.8237, "step": 4275 }, { "epoch": 12.8, "learning_rate": 1.108542e-05, "loss": 1.8193, "step": 4276 }, { "epoch": 12.81, "learning_rate": 1.1084715e-05, "loss": 1.8216, "step": 4277 }, { "epoch": 12.81, "learning_rate": 1.108401e-05, "loss": 1.8197, "step": 4278 }, { "epoch": 12.81, "learning_rate": 1.1083305000000001e-05, "loss": 1.8186, "step": 4279 }, { "epoch": 12.82, "learning_rate": 1.1082600000000001e-05, "loss": 1.8189, "step": 4280 }, { "epoch": 12.82, "learning_rate": 1.1081895000000001e-05, "loss": 1.8227, "step": 4281 }, { "epoch": 12.82, "learning_rate": 1.1081190000000001e-05, "loss": 1.8208, "step": 4282 }, { "epoch": 12.83, "learning_rate": 1.1080485e-05, "loss": 1.8222, "step": 4283 }, { "epoch": 12.83, "learning_rate": 1.107978e-05, "loss": 1.8211, "step": 4284 }, { "epoch": 12.83, "learning_rate": 1.1079075e-05, "loss": 1.8189, "step": 4285 }, { "epoch": 12.83, "learning_rate": 1.107837e-05, "loss": 1.8227, "step": 4286 }, { "epoch": 12.84, "learning_rate": 1.1077665e-05, "loss": 1.8196, "step": 4287 }, { "epoch": 12.84, "learning_rate": 1.107696e-05, "loss": 1.8226, "step": 4288 }, { "epoch": 12.84, "learning_rate": 1.1076255e-05, "loss": 1.8206, "step": 4289 }, { "epoch": 12.85, "learning_rate": 1.107555e-05, "loss": 1.8183, "step": 4290 }, { "epoch": 12.85, "learning_rate": 1.1074845000000001e-05, "loss": 1.822, "step": 4291 }, { "epoch": 12.85, "learning_rate": 1.107414e-05, "loss": 1.8217, "step": 4292 }, { "epoch": 12.86, "learning_rate": 1.1073435e-05, "loss": 1.8195, "step": 4293 }, { "epoch": 12.86, "learning_rate": 1.107273e-05, "loss": 1.82, "step": 4294 }, { "epoch": 12.86, "learning_rate": 1.1072025e-05, "loss": 1.821, "step": 4295 }, { "epoch": 12.86, "learning_rate": 1.107132e-05, "loss": 1.8239, "step": 4296 }, { "epoch": 12.87, "learning_rate": 1.1070615000000001e-05, "loss": 1.82, "step": 4297 }, { "epoch": 12.87, "learning_rate": 1.1069910000000001e-05, "loss": 1.8205, "step": 4298 }, { "epoch": 12.87, "learning_rate": 1.1069205000000001e-05, "loss": 1.8191, "step": 4299 }, { "epoch": 12.88, "learning_rate": 1.10685e-05, "loss": 1.82, "step": 4300 }, { "epoch": 12.88, "eval_accuracy": 0.000570207634228188, "eval_loss": 1.7667068243026733, "eval_runtime": 29.3961, "eval_samples_per_second": 10.137, "eval_steps_per_second": 0.646, "step": 4300 }, { "epoch": 12.88, "learning_rate": 1.1067795e-05, "loss": 1.8223, "step": 4301 }, { "epoch": 12.88, "learning_rate": 1.106709e-05, "loss": 1.8179, "step": 4302 }, { "epoch": 12.89, "learning_rate": 1.1066385e-05, "loss": 1.8193, "step": 4303 }, { "epoch": 12.89, "learning_rate": 1.1065680000000002e-05, "loss": 1.819, "step": 4304 }, { "epoch": 12.89, "learning_rate": 1.1064975e-05, "loss": 1.8179, "step": 4305 }, { "epoch": 12.89, "learning_rate": 1.106427e-05, "loss": 1.8196, "step": 4306 }, { "epoch": 12.9, "learning_rate": 1.1063565e-05, "loss": 1.8187, "step": 4307 }, { "epoch": 12.9, "learning_rate": 1.106286e-05, "loss": 1.8177, "step": 4308 }, { "epoch": 12.9, "learning_rate": 1.1062155e-05, "loss": 1.8203, "step": 4309 }, { "epoch": 12.91, "learning_rate": 1.106145e-05, "loss": 1.8187, "step": 4310 }, { "epoch": 12.91, "learning_rate": 1.1060745e-05, "loss": 1.8173, "step": 4311 }, { "epoch": 12.91, "learning_rate": 1.106004e-05, "loss": 1.8212, "step": 4312 }, { "epoch": 12.92, "learning_rate": 1.1059335e-05, "loss": 1.8205, "step": 4313 }, { "epoch": 12.92, "learning_rate": 1.105863e-05, "loss": 1.8177, "step": 4314 }, { "epoch": 12.92, "learning_rate": 1.1057925e-05, "loss": 1.8212, "step": 4315 }, { "epoch": 12.92, "learning_rate": 1.1057220000000001e-05, "loss": 1.815, "step": 4316 }, { "epoch": 12.93, "learning_rate": 1.1056515000000001e-05, "loss": 1.821, "step": 4317 }, { "epoch": 12.93, "learning_rate": 1.105581e-05, "loss": 1.8211, "step": 4318 }, { "epoch": 12.93, "learning_rate": 1.1055105e-05, "loss": 1.8168, "step": 4319 }, { "epoch": 12.94, "learning_rate": 1.10544e-05, "loss": 1.8191, "step": 4320 }, { "epoch": 12.94, "learning_rate": 1.1053695e-05, "loss": 1.819, "step": 4321 }, { "epoch": 12.94, "learning_rate": 1.1052990000000002e-05, "loss": 1.8193, "step": 4322 }, { "epoch": 12.95, "learning_rate": 1.1052285000000002e-05, "loss": 1.8196, "step": 4323 }, { "epoch": 12.95, "learning_rate": 1.1051580000000001e-05, "loss": 1.8194, "step": 4324 }, { "epoch": 12.95, "learning_rate": 1.1050875e-05, "loss": 1.8203, "step": 4325 }, { "epoch": 12.95, "learning_rate": 1.105017e-05, "loss": 1.8219, "step": 4326 }, { "epoch": 12.96, "learning_rate": 1.1049464999999999e-05, "loss": 1.818, "step": 4327 }, { "epoch": 12.96, "learning_rate": 1.104876e-05, "loss": 1.8225, "step": 4328 }, { "epoch": 12.96, "learning_rate": 1.1048055e-05, "loss": 1.818, "step": 4329 }, { "epoch": 12.97, "learning_rate": 1.104735e-05, "loss": 1.8187, "step": 4330 }, { "epoch": 12.97, "learning_rate": 1.1046645e-05, "loss": 1.8197, "step": 4331 }, { "epoch": 12.97, "learning_rate": 1.104594e-05, "loss": 1.82, "step": 4332 }, { "epoch": 12.98, "learning_rate": 1.1045235e-05, "loss": 1.8211, "step": 4333 }, { "epoch": 12.98, "learning_rate": 1.1044530000000001e-05, "loss": 1.819, "step": 4334 }, { "epoch": 12.98, "learning_rate": 1.1043825000000001e-05, "loss": 1.8185, "step": 4335 }, { "epoch": 12.98, "learning_rate": 1.104312e-05, "loss": 1.8188, "step": 4336 }, { "epoch": 12.99, "learning_rate": 1.1042415e-05, "loss": 1.8185, "step": 4337 }, { "epoch": 12.99, "learning_rate": 1.104171e-05, "loss": 1.8203, "step": 4338 }, { "epoch": 12.99, "learning_rate": 1.1041005e-05, "loss": 1.8197, "step": 4339 }, { "epoch": 13.0, "learning_rate": 1.10403e-05, "loss": 1.8174, "step": 4340 }, { "epoch": 13.0, "learning_rate": 1.1039595000000001e-05, "loss": 1.8214, "step": 4341 }, { "epoch": 13.0, "learning_rate": 1.1038890000000001e-05, "loss": 1.8196, "step": 4342 }, { "epoch": 13.01, "learning_rate": 1.1038185000000001e-05, "loss": 1.8203, "step": 4343 }, { "epoch": 13.01, "learning_rate": 1.1037480000000001e-05, "loss": 1.8161, "step": 4344 }, { "epoch": 13.01, "learning_rate": 1.1036774999999999e-05, "loss": 1.8149, "step": 4345 }, { "epoch": 13.01, "learning_rate": 1.103607e-05, "loss": 1.8196, "step": 4346 }, { "epoch": 13.02, "learning_rate": 1.1035365e-05, "loss": 1.82, "step": 4347 }, { "epoch": 13.02, "learning_rate": 1.103466e-05, "loss": 1.8204, "step": 4348 }, { "epoch": 13.02, "learning_rate": 1.1033955e-05, "loss": 1.8161, "step": 4349 }, { "epoch": 13.03, "learning_rate": 1.103325e-05, "loss": 1.8193, "step": 4350 }, { "epoch": 13.03, "learning_rate": 1.1032545e-05, "loss": 1.818, "step": 4351 }, { "epoch": 13.03, "learning_rate": 1.103184e-05, "loss": 1.8207, "step": 4352 }, { "epoch": 13.04, "learning_rate": 1.1031135000000001e-05, "loss": 1.816, "step": 4353 }, { "epoch": 13.04, "learning_rate": 1.103043e-05, "loss": 1.8176, "step": 4354 }, { "epoch": 13.04, "learning_rate": 1.1029725e-05, "loss": 1.8215, "step": 4355 }, { "epoch": 13.04, "learning_rate": 1.102902e-05, "loss": 1.8168, "step": 4356 }, { "epoch": 13.05, "learning_rate": 1.1028315e-05, "loss": 1.8205, "step": 4357 }, { "epoch": 13.05, "learning_rate": 1.102761e-05, "loss": 1.8173, "step": 4358 }, { "epoch": 13.05, "learning_rate": 1.1026905000000001e-05, "loss": 1.8197, "step": 4359 }, { "epoch": 13.06, "learning_rate": 1.1026200000000001e-05, "loss": 1.8186, "step": 4360 }, { "epoch": 13.06, "learning_rate": 1.1025495000000001e-05, "loss": 1.8191, "step": 4361 }, { "epoch": 13.06, "learning_rate": 1.1024790000000001e-05, "loss": 1.8197, "step": 4362 }, { "epoch": 13.07, "learning_rate": 1.1024085e-05, "loss": 1.8218, "step": 4363 }, { "epoch": 13.07, "learning_rate": 1.102338e-05, "loss": 1.8189, "step": 4364 }, { "epoch": 13.07, "learning_rate": 1.1022675e-05, "loss": 1.8188, "step": 4365 }, { "epoch": 13.07, "learning_rate": 1.102197e-05, "loss": 1.8183, "step": 4366 }, { "epoch": 13.08, "learning_rate": 1.1021265e-05, "loss": 1.8184, "step": 4367 }, { "epoch": 13.08, "learning_rate": 1.102056e-05, "loss": 1.8179, "step": 4368 }, { "epoch": 13.08, "learning_rate": 1.1019855e-05, "loss": 1.8168, "step": 4369 }, { "epoch": 13.09, "learning_rate": 1.101915e-05, "loss": 1.8189, "step": 4370 }, { "epoch": 13.09, "learning_rate": 1.1018445000000001e-05, "loss": 1.8199, "step": 4371 }, { "epoch": 13.09, "learning_rate": 1.101774e-05, "loss": 1.8152, "step": 4372 }, { "epoch": 13.1, "learning_rate": 1.1017035e-05, "loss": 1.8176, "step": 4373 }, { "epoch": 13.1, "learning_rate": 1.101633e-05, "loss": 1.8212, "step": 4374 }, { "epoch": 13.1, "learning_rate": 1.1015625e-05, "loss": 1.8152, "step": 4375 }, { "epoch": 13.1, "learning_rate": 1.101492e-05, "loss": 1.8154, "step": 4376 }, { "epoch": 13.11, "learning_rate": 1.1014215000000001e-05, "loss": 1.8164, "step": 4377 }, { "epoch": 13.11, "learning_rate": 1.1013510000000001e-05, "loss": 1.819, "step": 4378 }, { "epoch": 13.11, "learning_rate": 1.1012805000000001e-05, "loss": 1.8185, "step": 4379 }, { "epoch": 13.12, "learning_rate": 1.10121e-05, "loss": 1.8171, "step": 4380 }, { "epoch": 13.12, "learning_rate": 1.1011395e-05, "loss": 1.8178, "step": 4381 }, { "epoch": 13.12, "learning_rate": 1.101069e-05, "loss": 1.8184, "step": 4382 }, { "epoch": 13.13, "learning_rate": 1.1009985e-05, "loss": 1.8196, "step": 4383 }, { "epoch": 13.13, "learning_rate": 1.1009280000000002e-05, "loss": 1.8155, "step": 4384 }, { "epoch": 13.13, "learning_rate": 1.1008575000000002e-05, "loss": 1.8182, "step": 4385 }, { "epoch": 13.13, "learning_rate": 1.100787e-05, "loss": 1.8223, "step": 4386 }, { "epoch": 13.14, "learning_rate": 1.1007165e-05, "loss": 1.8181, "step": 4387 }, { "epoch": 13.14, "learning_rate": 1.100646e-05, "loss": 1.8204, "step": 4388 }, { "epoch": 13.14, "learning_rate": 1.1005754999999999e-05, "loss": 1.8164, "step": 4389 }, { "epoch": 13.15, "learning_rate": 1.100505e-05, "loss": 1.8193, "step": 4390 }, { "epoch": 13.15, "learning_rate": 1.1004345e-05, "loss": 1.8167, "step": 4391 }, { "epoch": 13.15, "learning_rate": 1.100364e-05, "loss": 1.82, "step": 4392 }, { "epoch": 13.16, "learning_rate": 1.1002935e-05, "loss": 1.8179, "step": 4393 }, { "epoch": 13.16, "learning_rate": 1.100223e-05, "loss": 1.8167, "step": 4394 }, { "epoch": 13.16, "learning_rate": 1.1001525e-05, "loss": 1.8163, "step": 4395 }, { "epoch": 13.16, "learning_rate": 1.1000820000000001e-05, "loss": 1.8182, "step": 4396 }, { "epoch": 13.17, "learning_rate": 1.1000115000000001e-05, "loss": 1.8182, "step": 4397 }, { "epoch": 13.17, "learning_rate": 1.099941e-05, "loss": 1.8168, "step": 4398 }, { "epoch": 13.17, "learning_rate": 1.0998705e-05, "loss": 1.8163, "step": 4399 }, { "epoch": 13.18, "learning_rate": 1.0998e-05, "loss": 1.8162, "step": 4400 }, { "epoch": 13.18, "eval_accuracy": 0.000570207634228188, "eval_loss": 1.764907956123352, "eval_runtime": 29.7676, "eval_samples_per_second": 10.011, "eval_steps_per_second": 0.638, "step": 4400 }, { "epoch": 13.18, "learning_rate": 1.0997295e-05, "loss": 1.8145, "step": 4401 }, { "epoch": 13.18, "learning_rate": 1.0996590000000002e-05, "loss": 1.8172, "step": 4402 }, { "epoch": 13.19, "learning_rate": 1.0995885000000002e-05, "loss": 1.8168, "step": 4403 }, { "epoch": 13.19, "learning_rate": 1.0995180000000001e-05, "loss": 1.8138, "step": 4404 }, { "epoch": 13.19, "learning_rate": 1.0994475000000001e-05, "loss": 1.8171, "step": 4405 }, { "epoch": 13.19, "learning_rate": 1.099377e-05, "loss": 1.8178, "step": 4406 }, { "epoch": 13.2, "learning_rate": 1.0993064999999999e-05, "loss": 1.8185, "step": 4407 }, { "epoch": 13.2, "learning_rate": 1.099236e-05, "loss": 1.818, "step": 4408 }, { "epoch": 13.2, "learning_rate": 1.0991655e-05, "loss": 1.8174, "step": 4409 }, { "epoch": 13.21, "learning_rate": 1.099095e-05, "loss": 1.8172, "step": 4410 }, { "epoch": 13.21, "learning_rate": 1.0990245e-05, "loss": 1.817, "step": 4411 }, { "epoch": 13.21, "learning_rate": 1.098954e-05, "loss": 1.8197, "step": 4412 }, { "epoch": 13.22, "learning_rate": 1.0988835e-05, "loss": 1.8156, "step": 4413 }, { "epoch": 13.22, "learning_rate": 1.0988130000000001e-05, "loss": 1.8174, "step": 4414 }, { "epoch": 13.22, "learning_rate": 1.0987425000000001e-05, "loss": 1.816, "step": 4415 }, { "epoch": 13.22, "learning_rate": 1.098672e-05, "loss": 1.8158, "step": 4416 }, { "epoch": 13.23, "learning_rate": 1.0986015e-05, "loss": 1.8149, "step": 4417 }, { "epoch": 13.23, "learning_rate": 1.098531e-05, "loss": 1.8181, "step": 4418 }, { "epoch": 13.23, "learning_rate": 1.0984605e-05, "loss": 1.8153, "step": 4419 }, { "epoch": 13.24, "learning_rate": 1.09839e-05, "loss": 1.8176, "step": 4420 }, { "epoch": 13.24, "learning_rate": 1.0983195000000001e-05, "loss": 1.8159, "step": 4421 }, { "epoch": 13.24, "learning_rate": 1.0982490000000001e-05, "loss": 1.8198, "step": 4422 }, { "epoch": 13.24, "learning_rate": 1.0981785000000001e-05, "loss": 1.8159, "step": 4423 }, { "epoch": 13.25, "learning_rate": 1.0981080000000001e-05, "loss": 1.8169, "step": 4424 }, { "epoch": 13.25, "learning_rate": 1.0980375e-05, "loss": 1.8174, "step": 4425 }, { "epoch": 13.25, "learning_rate": 1.0979669999999999e-05, "loss": 1.8157, "step": 4426 }, { "epoch": 13.26, "learning_rate": 1.0978965e-05, "loss": 1.8169, "step": 4427 }, { "epoch": 13.26, "learning_rate": 1.097826e-05, "loss": 1.8165, "step": 4428 }, { "epoch": 13.26, "learning_rate": 1.0977555e-05, "loss": 1.8165, "step": 4429 }, { "epoch": 13.27, "learning_rate": 1.097685e-05, "loss": 1.8161, "step": 4430 }, { "epoch": 13.27, "learning_rate": 1.0976145e-05, "loss": 1.814, "step": 4431 }, { "epoch": 13.27, "learning_rate": 1.097544e-05, "loss": 1.8144, "step": 4432 }, { "epoch": 13.27, "learning_rate": 1.0974735000000001e-05, "loss": 1.8143, "step": 4433 }, { "epoch": 13.28, "learning_rate": 1.097403e-05, "loss": 1.8155, "step": 4434 }, { "epoch": 13.28, "learning_rate": 1.0973325e-05, "loss": 1.8146, "step": 4435 }, { "epoch": 13.28, "learning_rate": 1.097262e-05, "loss": 1.8188, "step": 4436 }, { "epoch": 13.29, "learning_rate": 1.0971915e-05, "loss": 1.8154, "step": 4437 }, { "epoch": 13.29, "learning_rate": 1.097121e-05, "loss": 1.8145, "step": 4438 }, { "epoch": 13.29, "learning_rate": 1.0970505000000001e-05, "loss": 1.8169, "step": 4439 }, { "epoch": 13.3, "learning_rate": 1.0969800000000001e-05, "loss": 1.8191, "step": 4440 }, { "epoch": 13.3, "learning_rate": 1.0969095000000001e-05, "loss": 1.8191, "step": 4441 }, { "epoch": 13.3, "learning_rate": 1.0968390000000001e-05, "loss": 1.8168, "step": 4442 }, { "epoch": 13.3, "learning_rate": 1.0967685e-05, "loss": 1.8171, "step": 4443 }, { "epoch": 13.31, "learning_rate": 1.096698e-05, "loss": 1.8194, "step": 4444 }, { "epoch": 13.31, "learning_rate": 1.0966275e-05, "loss": 1.8168, "step": 4445 }, { "epoch": 13.31, "learning_rate": 1.096557e-05, "loss": 1.8158, "step": 4446 }, { "epoch": 13.32, "learning_rate": 1.0964865e-05, "loss": 1.8166, "step": 4447 }, { "epoch": 13.32, "learning_rate": 1.096416e-05, "loss": 1.8167, "step": 4448 }, { "epoch": 13.32, "learning_rate": 1.0963455e-05, "loss": 1.8187, "step": 4449 }, { "epoch": 13.33, "learning_rate": 1.096275e-05, "loss": 1.8155, "step": 4450 }, { "epoch": 13.33, "learning_rate": 1.0962045000000001e-05, "loss": 1.8177, "step": 4451 }, { "epoch": 13.33, "learning_rate": 1.096134e-05, "loss": 1.8156, "step": 4452 }, { "epoch": 13.33, "learning_rate": 1.0960635e-05, "loss": 1.8168, "step": 4453 }, { "epoch": 13.34, "learning_rate": 1.095993e-05, "loss": 1.8152, "step": 4454 }, { "epoch": 13.34, "learning_rate": 1.0959225e-05, "loss": 1.8163, "step": 4455 }, { "epoch": 13.34, "learning_rate": 1.095852e-05, "loss": 1.8181, "step": 4456 }, { "epoch": 13.35, "learning_rate": 1.0957815e-05, "loss": 1.8158, "step": 4457 }, { "epoch": 13.35, "learning_rate": 1.0957110000000001e-05, "loss": 1.8201, "step": 4458 }, { "epoch": 13.35, "learning_rate": 1.0956405000000001e-05, "loss": 1.8191, "step": 4459 }, { "epoch": 13.36, "learning_rate": 1.09557e-05, "loss": 1.8159, "step": 4460 }, { "epoch": 13.36, "learning_rate": 1.0954995e-05, "loss": 1.8139, "step": 4461 }, { "epoch": 13.36, "learning_rate": 1.095429e-05, "loss": 1.8157, "step": 4462 }, { "epoch": 13.36, "learning_rate": 1.0953585e-05, "loss": 1.8167, "step": 4463 }, { "epoch": 13.37, "learning_rate": 1.0952880000000002e-05, "loss": 1.8162, "step": 4464 }, { "epoch": 13.37, "learning_rate": 1.0952175000000002e-05, "loss": 1.8116, "step": 4465 }, { "epoch": 13.37, "learning_rate": 1.095147e-05, "loss": 1.8153, "step": 4466 }, { "epoch": 13.38, "learning_rate": 1.0950765e-05, "loss": 1.8153, "step": 4467 }, { "epoch": 13.38, "learning_rate": 1.095006e-05, "loss": 1.8142, "step": 4468 }, { "epoch": 13.38, "learning_rate": 1.0949354999999999e-05, "loss": 1.8148, "step": 4469 }, { "epoch": 13.39, "learning_rate": 1.094865e-05, "loss": 1.8166, "step": 4470 }, { "epoch": 13.39, "learning_rate": 1.0947945e-05, "loss": 1.8164, "step": 4471 }, { "epoch": 13.39, "learning_rate": 1.094724e-05, "loss": 1.8149, "step": 4472 }, { "epoch": 13.39, "learning_rate": 1.0946535e-05, "loss": 1.8176, "step": 4473 }, { "epoch": 13.4, "learning_rate": 1.094583e-05, "loss": 1.8179, "step": 4474 }, { "epoch": 13.4, "learning_rate": 1.0945125e-05, "loss": 1.8158, "step": 4475 }, { "epoch": 13.4, "learning_rate": 1.0944420000000001e-05, "loss": 1.8137, "step": 4476 }, { "epoch": 13.41, "learning_rate": 1.0943715000000001e-05, "loss": 1.8175, "step": 4477 }, { "epoch": 13.41, "learning_rate": 1.094301e-05, "loss": 1.8153, "step": 4478 }, { "epoch": 13.41, "learning_rate": 1.0942305e-05, "loss": 1.8168, "step": 4479 }, { "epoch": 13.42, "learning_rate": 1.09416e-05, "loss": 1.8141, "step": 4480 }, { "epoch": 13.42, "learning_rate": 1.0940895e-05, "loss": 1.8134, "step": 4481 }, { "epoch": 13.42, "learning_rate": 1.0940190000000002e-05, "loss": 1.8172, "step": 4482 }, { "epoch": 13.42, "learning_rate": 1.0939485000000002e-05, "loss": 1.814, "step": 4483 }, { "epoch": 13.43, "learning_rate": 1.0938780000000001e-05, "loss": 1.8163, "step": 4484 }, { "epoch": 13.43, "learning_rate": 1.0938075000000001e-05, "loss": 1.8169, "step": 4485 }, { "epoch": 13.43, "learning_rate": 1.093737e-05, "loss": 1.814, "step": 4486 }, { "epoch": 13.44, "learning_rate": 1.0936664999999999e-05, "loss": 1.8173, "step": 4487 }, { "epoch": 13.44, "learning_rate": 1.093596e-05, "loss": 1.8165, "step": 4488 }, { "epoch": 13.44, "learning_rate": 1.0935255e-05, "loss": 1.8152, "step": 4489 }, { "epoch": 13.45, "learning_rate": 1.093455e-05, "loss": 1.8171, "step": 4490 }, { "epoch": 13.45, "learning_rate": 1.0933845e-05, "loss": 1.816, "step": 4491 }, { "epoch": 13.45, "learning_rate": 1.093314e-05, "loss": 1.8134, "step": 4492 }, { "epoch": 13.45, "learning_rate": 1.0932435e-05, "loss": 1.8157, "step": 4493 }, { "epoch": 13.46, "learning_rate": 1.093173e-05, "loss": 1.8126, "step": 4494 }, { "epoch": 13.46, "learning_rate": 1.0931025000000001e-05, "loss": 1.8157, "step": 4495 }, { "epoch": 13.46, "learning_rate": 1.093032e-05, "loss": 1.8161, "step": 4496 }, { "epoch": 13.47, "learning_rate": 1.0929615e-05, "loss": 1.8148, "step": 4497 }, { "epoch": 13.47, "learning_rate": 1.092891e-05, "loss": 1.815, "step": 4498 }, { "epoch": 13.47, "learning_rate": 1.0928205e-05, "loss": 1.8128, "step": 4499 }, { "epoch": 13.48, "learning_rate": 1.09275e-05, "loss": 1.8124, "step": 4500 }, { "epoch": 13.48, "eval_accuracy": 0.0005964240771812081, "eval_loss": 1.7627805471420288, "eval_runtime": 29.2118, "eval_samples_per_second": 10.201, "eval_steps_per_second": 0.65, "step": 4500 }, { "epoch": 13.48, "learning_rate": 1.0926795000000001e-05, "loss": 1.8151, "step": 4501 }, { "epoch": 13.48, "learning_rate": 1.0926090000000001e-05, "loss": 1.8149, "step": 4502 }, { "epoch": 13.48, "learning_rate": 1.0925385000000001e-05, "loss": 1.8164, "step": 4503 }, { "epoch": 13.49, "learning_rate": 1.0924680000000001e-05, "loss": 1.8128, "step": 4504 }, { "epoch": 13.49, "learning_rate": 1.0923975e-05, "loss": 1.8169, "step": 4505 }, { "epoch": 13.49, "learning_rate": 1.092327e-05, "loss": 1.8147, "step": 4506 }, { "epoch": 13.5, "learning_rate": 1.0922565e-05, "loss": 1.8092, "step": 4507 }, { "epoch": 13.5, "learning_rate": 1.092186e-05, "loss": 1.8165, "step": 4508 }, { "epoch": 13.5, "learning_rate": 1.0921155e-05, "loss": 1.813, "step": 4509 }, { "epoch": 13.51, "learning_rate": 1.092045e-05, "loss": 1.8151, "step": 4510 }, { "epoch": 13.51, "learning_rate": 1.0919745e-05, "loss": 1.8138, "step": 4511 }, { "epoch": 13.51, "learning_rate": 1.091904e-05, "loss": 1.8133, "step": 4512 }, { "epoch": 13.51, "learning_rate": 1.0918335000000001e-05, "loss": 1.8149, "step": 4513 }, { "epoch": 13.52, "learning_rate": 1.091763e-05, "loss": 1.8116, "step": 4514 }, { "epoch": 13.52, "learning_rate": 1.0916925e-05, "loss": 1.8128, "step": 4515 }, { "epoch": 13.52, "learning_rate": 1.091622e-05, "loss": 1.8165, "step": 4516 }, { "epoch": 13.53, "learning_rate": 1.0915515e-05, "loss": 1.8141, "step": 4517 }, { "epoch": 13.53, "learning_rate": 1.091481e-05, "loss": 1.8136, "step": 4518 }, { "epoch": 13.53, "learning_rate": 1.0914105000000001e-05, "loss": 1.8141, "step": 4519 }, { "epoch": 13.54, "learning_rate": 1.0913400000000001e-05, "loss": 1.814, "step": 4520 }, { "epoch": 13.54, "learning_rate": 1.0912695000000001e-05, "loss": 1.8155, "step": 4521 }, { "epoch": 13.54, "learning_rate": 1.0911990000000001e-05, "loss": 1.8115, "step": 4522 }, { "epoch": 13.54, "learning_rate": 1.0911285e-05, "loss": 1.8128, "step": 4523 }, { "epoch": 13.55, "learning_rate": 1.091058e-05, "loss": 1.8143, "step": 4524 }, { "epoch": 13.55, "learning_rate": 1.0909875e-05, "loss": 1.8122, "step": 4525 }, { "epoch": 13.55, "learning_rate": 1.0909170000000002e-05, "loss": 1.8153, "step": 4526 }, { "epoch": 13.56, "learning_rate": 1.0908465e-05, "loss": 1.8132, "step": 4527 }, { "epoch": 13.56, "learning_rate": 1.090776e-05, "loss": 1.8119, "step": 4528 }, { "epoch": 13.56, "learning_rate": 1.0907055e-05, "loss": 1.8156, "step": 4529 }, { "epoch": 13.57, "learning_rate": 1.090635e-05, "loss": 1.8141, "step": 4530 }, { "epoch": 13.57, "learning_rate": 1.0905645e-05, "loss": 1.8124, "step": 4531 }, { "epoch": 13.57, "learning_rate": 1.090494e-05, "loss": 1.8149, "step": 4532 }, { "epoch": 13.57, "learning_rate": 1.0904235e-05, "loss": 1.8143, "step": 4533 }, { "epoch": 13.58, "learning_rate": 1.090353e-05, "loss": 1.8174, "step": 4534 }, { "epoch": 13.58, "learning_rate": 1.0902825e-05, "loss": 1.8128, "step": 4535 }, { "epoch": 13.58, "learning_rate": 1.090212e-05, "loss": 1.8115, "step": 4536 }, { "epoch": 13.59, "learning_rate": 1.0901415e-05, "loss": 1.817, "step": 4537 }, { "epoch": 13.59, "learning_rate": 1.0900710000000001e-05, "loss": 1.8159, "step": 4538 }, { "epoch": 13.59, "learning_rate": 1.0900005000000001e-05, "loss": 1.8137, "step": 4539 }, { "epoch": 13.6, "learning_rate": 1.08993e-05, "loss": 1.8122, "step": 4540 }, { "epoch": 13.6, "learning_rate": 1.0898595e-05, "loss": 1.8139, "step": 4541 }, { "epoch": 13.6, "learning_rate": 1.089789e-05, "loss": 1.8123, "step": 4542 }, { "epoch": 13.6, "learning_rate": 1.0897185e-05, "loss": 1.8148, "step": 4543 }, { "epoch": 13.61, "learning_rate": 1.0896480000000002e-05, "loss": 1.8146, "step": 4544 }, { "epoch": 13.61, "learning_rate": 1.0895775000000002e-05, "loss": 1.8171, "step": 4545 }, { "epoch": 13.61, "learning_rate": 1.0895070000000001e-05, "loss": 1.8136, "step": 4546 }, { "epoch": 13.62, "learning_rate": 1.0894365e-05, "loss": 1.817, "step": 4547 }, { "epoch": 13.62, "learning_rate": 1.089366e-05, "loss": 1.8121, "step": 4548 }, { "epoch": 13.62, "learning_rate": 1.0892954999999999e-05, "loss": 1.8141, "step": 4549 }, { "epoch": 13.63, "learning_rate": 1.089225e-05, "loss": 1.8143, "step": 4550 }, { "epoch": 13.63, "learning_rate": 1.0891545e-05, "loss": 1.8154, "step": 4551 }, { "epoch": 13.63, "learning_rate": 1.089084e-05, "loss": 1.8144, "step": 4552 }, { "epoch": 13.63, "learning_rate": 1.0890135e-05, "loss": 1.8161, "step": 4553 }, { "epoch": 13.64, "learning_rate": 1.088943e-05, "loss": 1.8133, "step": 4554 }, { "epoch": 13.64, "learning_rate": 1.0888725e-05, "loss": 1.8148, "step": 4555 }, { "epoch": 13.64, "learning_rate": 1.0888020000000001e-05, "loss": 1.8091, "step": 4556 }, { "epoch": 13.65, "learning_rate": 1.0887315000000001e-05, "loss": 1.8133, "step": 4557 }, { "epoch": 13.65, "learning_rate": 1.088661e-05, "loss": 1.814, "step": 4558 }, { "epoch": 13.65, "learning_rate": 1.0885905e-05, "loss": 1.8131, "step": 4559 }, { "epoch": 13.66, "learning_rate": 1.08852e-05, "loss": 1.8116, "step": 4560 }, { "epoch": 13.66, "learning_rate": 1.0884495e-05, "loss": 1.8127, "step": 4561 }, { "epoch": 13.66, "learning_rate": 1.088379e-05, "loss": 1.8107, "step": 4562 }, { "epoch": 13.66, "learning_rate": 1.0883085000000002e-05, "loss": 1.8112, "step": 4563 }, { "epoch": 13.67, "learning_rate": 1.0882380000000001e-05, "loss": 1.8147, "step": 4564 }, { "epoch": 13.67, "learning_rate": 1.0881675000000001e-05, "loss": 1.8155, "step": 4565 }, { "epoch": 13.67, "learning_rate": 1.0880970000000001e-05, "loss": 1.815, "step": 4566 }, { "epoch": 13.68, "learning_rate": 1.0880264999999999e-05, "loss": 1.8112, "step": 4567 }, { "epoch": 13.68, "learning_rate": 1.087956e-05, "loss": 1.8138, "step": 4568 }, { "epoch": 13.68, "learning_rate": 1.0878855e-05, "loss": 1.8122, "step": 4569 }, { "epoch": 13.69, "learning_rate": 1.087815e-05, "loss": 1.8144, "step": 4570 }, { "epoch": 13.69, "learning_rate": 1.0877445e-05, "loss": 1.8116, "step": 4571 }, { "epoch": 13.69, "learning_rate": 1.087674e-05, "loss": 1.8114, "step": 4572 }, { "epoch": 13.69, "learning_rate": 1.0876035e-05, "loss": 1.8134, "step": 4573 }, { "epoch": 13.7, "learning_rate": 1.087533e-05, "loss": 1.8147, "step": 4574 }, { "epoch": 13.7, "learning_rate": 1.0874625000000001e-05, "loss": 1.8131, "step": 4575 }, { "epoch": 13.7, "learning_rate": 1.087392e-05, "loss": 1.8132, "step": 4576 }, { "epoch": 13.71, "learning_rate": 1.0873215e-05, "loss": 1.8151, "step": 4577 }, { "epoch": 13.71, "learning_rate": 1.087251e-05, "loss": 1.8145, "step": 4578 }, { "epoch": 13.71, "learning_rate": 1.0871805e-05, "loss": 1.8135, "step": 4579 }, { "epoch": 13.72, "learning_rate": 1.08711e-05, "loss": 1.8107, "step": 4580 }, { "epoch": 13.72, "learning_rate": 1.0870395000000001e-05, "loss": 1.8141, "step": 4581 }, { "epoch": 13.72, "learning_rate": 1.0869690000000001e-05, "loss": 1.8148, "step": 4582 }, { "epoch": 13.72, "learning_rate": 1.0868985000000001e-05, "loss": 1.8144, "step": 4583 }, { "epoch": 13.73, "learning_rate": 1.0868280000000001e-05, "loss": 1.812, "step": 4584 }, { "epoch": 13.73, "learning_rate": 1.0867575e-05, "loss": 1.814, "step": 4585 }, { "epoch": 13.73, "learning_rate": 1.086687e-05, "loss": 1.8131, "step": 4586 }, { "epoch": 13.74, "learning_rate": 1.0866165e-05, "loss": 1.8123, "step": 4587 }, { "epoch": 13.74, "learning_rate": 1.086546e-05, "loss": 1.8136, "step": 4588 }, { "epoch": 13.74, "learning_rate": 1.0864755e-05, "loss": 1.8147, "step": 4589 }, { "epoch": 13.75, "learning_rate": 1.086405e-05, "loss": 1.8141, "step": 4590 }, { "epoch": 13.75, "learning_rate": 1.0863345e-05, "loss": 1.8156, "step": 4591 }, { "epoch": 13.75, "learning_rate": 1.086264e-05, "loss": 1.8122, "step": 4592 }, { "epoch": 13.75, "learning_rate": 1.0861935000000001e-05, "loss": 1.8117, "step": 4593 }, { "epoch": 13.76, "learning_rate": 1.086123e-05, "loss": 1.8117, "step": 4594 }, { "epoch": 13.76, "learning_rate": 1.0860525e-05, "loss": 1.812, "step": 4595 }, { "epoch": 13.76, "learning_rate": 1.085982e-05, "loss": 1.8153, "step": 4596 }, { "epoch": 13.77, "learning_rate": 1.0859115e-05, "loss": 1.8128, "step": 4597 }, { "epoch": 13.77, "learning_rate": 1.085841e-05, "loss": 1.8116, "step": 4598 }, { "epoch": 13.77, "learning_rate": 1.0857705e-05, "loss": 1.8152, "step": 4599 }, { "epoch": 13.78, "learning_rate": 1.0857000000000001e-05, "loss": 1.8106, "step": 4600 }, { "epoch": 13.78, "eval_accuracy": 0.0005964240771812081, "eval_loss": 1.7608240842819214, "eval_runtime": 30.7863, "eval_samples_per_second": 9.68, "eval_steps_per_second": 0.617, "step": 4600 }, { "epoch": 13.78, "learning_rate": 1.0856295000000001e-05, "loss": 1.8111, "step": 4601 }, { "epoch": 13.78, "learning_rate": 1.0855590000000001e-05, "loss": 1.8112, "step": 4602 }, { "epoch": 13.78, "learning_rate": 1.0854885e-05, "loss": 1.8114, "step": 4603 }, { "epoch": 13.79, "learning_rate": 1.085418e-05, "loss": 1.816, "step": 4604 }, { "epoch": 13.79, "learning_rate": 1.0853475e-05, "loss": 1.812, "step": 4605 }, { "epoch": 13.79, "learning_rate": 1.0852770000000002e-05, "loss": 1.8146, "step": 4606 }, { "epoch": 13.8, "learning_rate": 1.0852065e-05, "loss": 1.813, "step": 4607 }, { "epoch": 13.8, "learning_rate": 1.085136e-05, "loss": 1.8121, "step": 4608 }, { "epoch": 13.8, "learning_rate": 1.0850655e-05, "loss": 1.8142, "step": 4609 }, { "epoch": 13.8, "learning_rate": 1.084995e-05, "loss": 1.8115, "step": 4610 }, { "epoch": 13.81, "learning_rate": 1.0849245e-05, "loss": 1.8117, "step": 4611 }, { "epoch": 13.81, "learning_rate": 1.084854e-05, "loss": 1.814, "step": 4612 }, { "epoch": 13.81, "learning_rate": 1.0847835e-05, "loss": 1.8143, "step": 4613 }, { "epoch": 13.82, "learning_rate": 1.084713e-05, "loss": 1.8113, "step": 4614 }, { "epoch": 13.82, "learning_rate": 1.0846425e-05, "loss": 1.8131, "step": 4615 }, { "epoch": 13.82, "learning_rate": 1.084572e-05, "loss": 1.8131, "step": 4616 }, { "epoch": 13.83, "learning_rate": 1.0845015e-05, "loss": 1.8087, "step": 4617 }, { "epoch": 13.83, "learning_rate": 1.0844310000000001e-05, "loss": 1.8077, "step": 4618 }, { "epoch": 13.83, "learning_rate": 1.0843605000000001e-05, "loss": 1.8127, "step": 4619 }, { "epoch": 13.83, "learning_rate": 1.08429e-05, "loss": 1.8111, "step": 4620 }, { "epoch": 13.84, "learning_rate": 1.0842195e-05, "loss": 1.8093, "step": 4621 }, { "epoch": 13.84, "learning_rate": 1.084149e-05, "loss": 1.8126, "step": 4622 }, { "epoch": 13.84, "learning_rate": 1.0840785e-05, "loss": 1.8122, "step": 4623 }, { "epoch": 13.85, "learning_rate": 1.0840080000000002e-05, "loss": 1.8117, "step": 4624 }, { "epoch": 13.85, "learning_rate": 1.0839375000000002e-05, "loss": 1.8131, "step": 4625 }, { "epoch": 13.85, "learning_rate": 1.0838670000000001e-05, "loss": 1.8104, "step": 4626 }, { "epoch": 13.86, "learning_rate": 1.0837965000000001e-05, "loss": 1.8126, "step": 4627 }, { "epoch": 13.86, "learning_rate": 1.083726e-05, "loss": 1.8134, "step": 4628 }, { "epoch": 13.86, "learning_rate": 1.0836554999999999e-05, "loss": 1.809, "step": 4629 }, { "epoch": 13.86, "learning_rate": 1.083585e-05, "loss": 1.8119, "step": 4630 }, { "epoch": 13.87, "learning_rate": 1.0835145e-05, "loss": 1.8098, "step": 4631 }, { "epoch": 13.87, "learning_rate": 1.083444e-05, "loss": 1.8132, "step": 4632 }, { "epoch": 13.87, "learning_rate": 1.0833735e-05, "loss": 1.8114, "step": 4633 }, { "epoch": 13.88, "learning_rate": 1.083303e-05, "loss": 1.8137, "step": 4634 }, { "epoch": 13.88, "learning_rate": 1.0832325e-05, "loss": 1.8109, "step": 4635 }, { "epoch": 13.88, "learning_rate": 1.083162e-05, "loss": 1.8122, "step": 4636 }, { "epoch": 13.89, "learning_rate": 1.0830915000000001e-05, "loss": 1.8109, "step": 4637 }, { "epoch": 13.89, "learning_rate": 1.083021e-05, "loss": 1.8114, "step": 4638 }, { "epoch": 13.89, "learning_rate": 1.0829505e-05, "loss": 1.814, "step": 4639 }, { "epoch": 13.89, "learning_rate": 1.08288e-05, "loss": 1.8118, "step": 4640 }, { "epoch": 13.9, "learning_rate": 1.0828095e-05, "loss": 1.8108, "step": 4641 }, { "epoch": 13.9, "learning_rate": 1.082739e-05, "loss": 1.8126, "step": 4642 }, { "epoch": 13.9, "learning_rate": 1.0826685000000002e-05, "loss": 1.8141, "step": 4643 }, { "epoch": 13.91, "learning_rate": 1.0825980000000001e-05, "loss": 1.8098, "step": 4644 }, { "epoch": 13.91, "learning_rate": 1.0825275000000001e-05, "loss": 1.8083, "step": 4645 }, { "epoch": 13.91, "learning_rate": 1.0824570000000001e-05, "loss": 1.814, "step": 4646 }, { "epoch": 13.92, "learning_rate": 1.0823865e-05, "loss": 1.81, "step": 4647 }, { "epoch": 13.92, "learning_rate": 1.0823159999999999e-05, "loss": 1.8125, "step": 4648 }, { "epoch": 13.92, "learning_rate": 1.0822455e-05, "loss": 1.8134, "step": 4649 }, { "epoch": 13.92, "learning_rate": 1.082175e-05, "loss": 1.8114, "step": 4650 }, { "epoch": 13.93, "learning_rate": 1.0821045e-05, "loss": 1.8105, "step": 4651 }, { "epoch": 13.93, "learning_rate": 1.082034e-05, "loss": 1.8107, "step": 4652 }, { "epoch": 13.93, "learning_rate": 1.0819635e-05, "loss": 1.8086, "step": 4653 }, { "epoch": 13.94, "learning_rate": 1.081893e-05, "loss": 1.8102, "step": 4654 }, { "epoch": 13.94, "learning_rate": 1.0818225000000001e-05, "loss": 1.8136, "step": 4655 }, { "epoch": 13.94, "learning_rate": 1.081752e-05, "loss": 1.811, "step": 4656 }, { "epoch": 13.95, "learning_rate": 1.0816815e-05, "loss": 1.811, "step": 4657 }, { "epoch": 13.95, "learning_rate": 1.081611e-05, "loss": 1.8124, "step": 4658 }, { "epoch": 13.95, "learning_rate": 1.0815405e-05, "loss": 1.8086, "step": 4659 }, { "epoch": 13.95, "learning_rate": 1.08147e-05, "loss": 1.8123, "step": 4660 }, { "epoch": 13.96, "learning_rate": 1.0813995000000001e-05, "loss": 1.8107, "step": 4661 }, { "epoch": 13.96, "learning_rate": 1.0813290000000001e-05, "loss": 1.8092, "step": 4662 }, { "epoch": 13.96, "learning_rate": 1.0812585000000001e-05, "loss": 1.8112, "step": 4663 }, { "epoch": 13.97, "learning_rate": 1.0811880000000001e-05, "loss": 1.8085, "step": 4664 }, { "epoch": 13.97, "learning_rate": 1.0811175e-05, "loss": 1.8122, "step": 4665 }, { "epoch": 13.97, "learning_rate": 1.081047e-05, "loss": 1.8084, "step": 4666 }, { "epoch": 13.98, "learning_rate": 1.0809765e-05, "loss": 1.8106, "step": 4667 }, { "epoch": 13.98, "learning_rate": 1.080906e-05, "loss": 1.8101, "step": 4668 }, { "epoch": 13.98, "learning_rate": 1.0808355e-05, "loss": 1.8111, "step": 4669 }, { "epoch": 13.98, "learning_rate": 1.080765e-05, "loss": 1.8096, "step": 4670 }, { "epoch": 13.99, "learning_rate": 1.0806945e-05, "loss": 1.8096, "step": 4671 }, { "epoch": 13.99, "learning_rate": 1.080624e-05, "loss": 1.8113, "step": 4672 }, { "epoch": 13.99, "learning_rate": 1.0805535000000001e-05, "loss": 1.8092, "step": 4673 }, { "epoch": 14.0, "learning_rate": 1.080483e-05, "loss": 1.8113, "step": 4674 }, { "epoch": 14.0, "learning_rate": 1.0804125e-05, "loss": 1.8103, "step": 4675 }, { "epoch": 14.0, "learning_rate": 1.080342e-05, "loss": 1.8089, "step": 4676 }, { "epoch": 14.01, "learning_rate": 1.0802715e-05, "loss": 1.8091, "step": 4677 }, { "epoch": 14.01, "learning_rate": 1.080201e-05, "loss": 1.8072, "step": 4678 }, { "epoch": 14.01, "learning_rate": 1.0801305e-05, "loss": 1.8128, "step": 4679 }, { "epoch": 14.01, "learning_rate": 1.0800600000000001e-05, "loss": 1.8102, "step": 4680 }, { "epoch": 14.02, "learning_rate": 1.0799895000000001e-05, "loss": 1.8109, "step": 4681 }, { "epoch": 14.02, "learning_rate": 1.0799190000000001e-05, "loss": 1.81, "step": 4682 }, { "epoch": 14.02, "learning_rate": 1.0798485e-05, "loss": 1.8099, "step": 4683 }, { "epoch": 14.03, "learning_rate": 1.079778e-05, "loss": 1.8093, "step": 4684 }, { "epoch": 14.03, "learning_rate": 1.0797075e-05, "loss": 1.8109, "step": 4685 }, { "epoch": 14.03, "learning_rate": 1.0796370000000002e-05, "loss": 1.8089, "step": 4686 }, { "epoch": 14.04, "learning_rate": 1.0795665000000002e-05, "loss": 1.8105, "step": 4687 }, { "epoch": 14.04, "learning_rate": 1.079496e-05, "loss": 1.809, "step": 4688 }, { "epoch": 14.04, "learning_rate": 1.0794255e-05, "loss": 1.8102, "step": 4689 }, { "epoch": 14.04, "learning_rate": 1.079355e-05, "loss": 1.8107, "step": 4690 }, { "epoch": 14.05, "learning_rate": 1.0792845e-05, "loss": 1.8098, "step": 4691 }, { "epoch": 14.05, "learning_rate": 1.079214e-05, "loss": 1.811, "step": 4692 }, { "epoch": 14.05, "learning_rate": 1.0791435e-05, "loss": 1.8084, "step": 4693 }, { "epoch": 14.06, "learning_rate": 1.079073e-05, "loss": 1.8115, "step": 4694 }, { "epoch": 14.06, "learning_rate": 1.0790025e-05, "loss": 1.8123, "step": 4695 }, { "epoch": 14.06, "learning_rate": 1.078932e-05, "loss": 1.8108, "step": 4696 }, { "epoch": 14.07, "learning_rate": 1.0788615e-05, "loss": 1.8119, "step": 4697 }, { "epoch": 14.07, "learning_rate": 1.0787910000000001e-05, "loss": 1.8106, "step": 4698 }, { "epoch": 14.07, "learning_rate": 1.0787205000000001e-05, "loss": 1.8073, "step": 4699 }, { "epoch": 14.07, "learning_rate": 1.07865e-05, "loss": 1.8101, "step": 4700 }, { "epoch": 14.07, "eval_accuracy": 0.0005964240771812081, "eval_loss": 1.7589054107666016, "eval_runtime": 30.9353, "eval_samples_per_second": 9.633, "eval_steps_per_second": 0.614, "step": 4700 }, { "epoch": 14.08, "learning_rate": 1.0785795e-05, "loss": 1.8122, "step": 4701 }, { "epoch": 14.08, "learning_rate": 1.078509e-05, "loss": 1.8089, "step": 4702 }, { "epoch": 14.08, "learning_rate": 1.0784385e-05, "loss": 1.8129, "step": 4703 }, { "epoch": 14.09, "learning_rate": 1.078368e-05, "loss": 1.8112, "step": 4704 }, { "epoch": 14.09, "learning_rate": 1.0782975000000002e-05, "loss": 1.8109, "step": 4705 }, { "epoch": 14.09, "learning_rate": 1.0782270000000001e-05, "loss": 1.8118, "step": 4706 }, { "epoch": 14.1, "learning_rate": 1.0781565000000001e-05, "loss": 1.8096, "step": 4707 }, { "epoch": 14.1, "learning_rate": 1.078086e-05, "loss": 1.8082, "step": 4708 }, { "epoch": 14.1, "learning_rate": 1.0780154999999999e-05, "loss": 1.8118, "step": 4709 }, { "epoch": 14.1, "learning_rate": 1.077945e-05, "loss": 1.8085, "step": 4710 }, { "epoch": 14.11, "learning_rate": 1.0778745e-05, "loss": 1.8092, "step": 4711 }, { "epoch": 14.11, "learning_rate": 1.077804e-05, "loss": 1.8111, "step": 4712 }, { "epoch": 14.11, "learning_rate": 1.0777335e-05, "loss": 1.8113, "step": 4713 }, { "epoch": 14.12, "learning_rate": 1.077663e-05, "loss": 1.8084, "step": 4714 }, { "epoch": 14.12, "learning_rate": 1.0775925e-05, "loss": 1.812, "step": 4715 }, { "epoch": 14.12, "learning_rate": 1.077522e-05, "loss": 1.8099, "step": 4716 }, { "epoch": 14.13, "learning_rate": 1.0774515000000001e-05, "loss": 1.808, "step": 4717 }, { "epoch": 14.13, "learning_rate": 1.077381e-05, "loss": 1.8087, "step": 4718 }, { "epoch": 14.13, "learning_rate": 1.0773105e-05, "loss": 1.809, "step": 4719 }, { "epoch": 14.13, "learning_rate": 1.07724e-05, "loss": 1.809, "step": 4720 }, { "epoch": 14.14, "learning_rate": 1.0771695e-05, "loss": 1.8097, "step": 4721 }, { "epoch": 14.14, "learning_rate": 1.077099e-05, "loss": 1.8085, "step": 4722 }, { "epoch": 14.14, "learning_rate": 1.0770285000000002e-05, "loss": 1.808, "step": 4723 }, { "epoch": 14.15, "learning_rate": 1.0769580000000001e-05, "loss": 1.8095, "step": 4724 }, { "epoch": 14.15, "learning_rate": 1.0768875000000001e-05, "loss": 1.8112, "step": 4725 }, { "epoch": 14.15, "learning_rate": 1.0768170000000001e-05, "loss": 1.8084, "step": 4726 }, { "epoch": 14.16, "learning_rate": 1.0767465e-05, "loss": 1.8064, "step": 4727 }, { "epoch": 14.16, "learning_rate": 1.0766759999999999e-05, "loss": 1.8077, "step": 4728 }, { "epoch": 14.16, "learning_rate": 1.0766055e-05, "loss": 1.8118, "step": 4729 }, { "epoch": 14.16, "learning_rate": 1.076535e-05, "loss": 1.8088, "step": 4730 }, { "epoch": 14.17, "learning_rate": 1.0764645e-05, "loss": 1.809, "step": 4731 }, { "epoch": 14.17, "learning_rate": 1.076394e-05, "loss": 1.8057, "step": 4732 }, { "epoch": 14.17, "learning_rate": 1.0763235e-05, "loss": 1.8104, "step": 4733 }, { "epoch": 14.18, "learning_rate": 1.076253e-05, "loss": 1.8131, "step": 4734 }, { "epoch": 14.18, "learning_rate": 1.0761825000000001e-05, "loss": 1.8076, "step": 4735 }, { "epoch": 14.18, "learning_rate": 1.076112e-05, "loss": 1.806, "step": 4736 }, { "epoch": 14.19, "learning_rate": 1.0760415e-05, "loss": 1.8104, "step": 4737 }, { "epoch": 14.19, "learning_rate": 1.075971e-05, "loss": 1.8108, "step": 4738 }, { "epoch": 14.19, "learning_rate": 1.0759005e-05, "loss": 1.8087, "step": 4739 }, { "epoch": 14.19, "learning_rate": 1.07583e-05, "loss": 1.8105, "step": 4740 }, { "epoch": 14.2, "learning_rate": 1.0757595000000001e-05, "loss": 1.8083, "step": 4741 }, { "epoch": 14.2, "learning_rate": 1.0756890000000001e-05, "loss": 1.8094, "step": 4742 }, { "epoch": 14.2, "learning_rate": 1.0756185000000001e-05, "loss": 1.8094, "step": 4743 }, { "epoch": 14.21, "learning_rate": 1.0755480000000001e-05, "loss": 1.8074, "step": 4744 }, { "epoch": 14.21, "learning_rate": 1.0754775e-05, "loss": 1.8098, "step": 4745 }, { "epoch": 14.21, "learning_rate": 1.075407e-05, "loss": 1.8092, "step": 4746 }, { "epoch": 14.22, "learning_rate": 1.0753365e-05, "loss": 1.8081, "step": 4747 }, { "epoch": 14.22, "learning_rate": 1.075266e-05, "loss": 1.8076, "step": 4748 }, { "epoch": 14.22, "learning_rate": 1.0751955e-05, "loss": 1.8077, "step": 4749 }, { "epoch": 14.22, "learning_rate": 1.075125e-05, "loss": 1.8108, "step": 4750 }, { "epoch": 14.23, "learning_rate": 1.0750545e-05, "loss": 1.8078, "step": 4751 }, { "epoch": 14.23, "learning_rate": 1.074984e-05, "loss": 1.807, "step": 4752 }, { "epoch": 14.23, "learning_rate": 1.0749135e-05, "loss": 1.8103, "step": 4753 }, { "epoch": 14.24, "learning_rate": 1.074843e-05, "loss": 1.8099, "step": 4754 }, { "epoch": 14.24, "learning_rate": 1.0747725e-05, "loss": 1.8099, "step": 4755 }, { "epoch": 14.24, "learning_rate": 1.074702e-05, "loss": 1.8094, "step": 4756 }, { "epoch": 14.25, "learning_rate": 1.0746315e-05, "loss": 1.8095, "step": 4757 }, { "epoch": 14.25, "learning_rate": 1.074561e-05, "loss": 1.8058, "step": 4758 }, { "epoch": 14.25, "learning_rate": 1.0744905e-05, "loss": 1.8075, "step": 4759 }, { "epoch": 14.25, "learning_rate": 1.0744200000000001e-05, "loss": 1.8074, "step": 4760 }, { "epoch": 14.26, "learning_rate": 1.0743495000000001e-05, "loss": 1.8091, "step": 4761 }, { "epoch": 14.26, "learning_rate": 1.0742790000000001e-05, "loss": 1.8087, "step": 4762 }, { "epoch": 14.26, "learning_rate": 1.0742085e-05, "loss": 1.8075, "step": 4763 }, { "epoch": 14.27, "learning_rate": 1.074138e-05, "loss": 1.8069, "step": 4764 }, { "epoch": 14.27, "learning_rate": 1.0740675e-05, "loss": 1.808, "step": 4765 }, { "epoch": 14.27, "learning_rate": 1.0739970000000002e-05, "loss": 1.8099, "step": 4766 }, { "epoch": 14.28, "learning_rate": 1.0739265000000002e-05, "loss": 1.8109, "step": 4767 }, { "epoch": 14.28, "learning_rate": 1.0738560000000001e-05, "loss": 1.8083, "step": 4768 }, { "epoch": 14.28, "learning_rate": 1.0737855e-05, "loss": 1.8053, "step": 4769 }, { "epoch": 14.28, "learning_rate": 1.073715e-05, "loss": 1.8094, "step": 4770 }, { "epoch": 14.29, "learning_rate": 1.0736444999999999e-05, "loss": 1.8089, "step": 4771 }, { "epoch": 14.29, "learning_rate": 1.073574e-05, "loss": 1.8065, "step": 4772 }, { "epoch": 14.29, "learning_rate": 1.0735035e-05, "loss": 1.8077, "step": 4773 }, { "epoch": 14.3, "learning_rate": 1.073433e-05, "loss": 1.8086, "step": 4774 }, { "epoch": 14.3, "learning_rate": 1.0733625e-05, "loss": 1.8109, "step": 4775 }, { "epoch": 14.3, "learning_rate": 1.073292e-05, "loss": 1.8082, "step": 4776 }, { "epoch": 14.31, "learning_rate": 1.0732215e-05, "loss": 1.8083, "step": 4777 }, { "epoch": 14.31, "learning_rate": 1.0731510000000001e-05, "loss": 1.8066, "step": 4778 }, { "epoch": 14.31, "learning_rate": 1.0730805000000001e-05, "loss": 1.809, "step": 4779 }, { "epoch": 14.31, "learning_rate": 1.07301e-05, "loss": 1.8096, "step": 4780 }, { "epoch": 14.32, "learning_rate": 1.0729395e-05, "loss": 1.8074, "step": 4781 }, { "epoch": 14.32, "learning_rate": 1.072869e-05, "loss": 1.8074, "step": 4782 }, { "epoch": 14.32, "learning_rate": 1.0727985e-05, "loss": 1.8082, "step": 4783 }, { "epoch": 14.33, "learning_rate": 1.072728e-05, "loss": 1.8079, "step": 4784 }, { "epoch": 14.33, "learning_rate": 1.0726575000000002e-05, "loss": 1.8077, "step": 4785 }, { "epoch": 14.33, "learning_rate": 1.0725870000000001e-05, "loss": 1.808, "step": 4786 }, { "epoch": 14.34, "learning_rate": 1.0725165000000001e-05, "loss": 1.8095, "step": 4787 }, { "epoch": 14.34, "learning_rate": 1.0724460000000001e-05, "loss": 1.8101, "step": 4788 }, { "epoch": 14.34, "learning_rate": 1.0723754999999999e-05, "loss": 1.8115, "step": 4789 }, { "epoch": 14.34, "learning_rate": 1.0723049999999999e-05, "loss": 1.8063, "step": 4790 }, { "epoch": 14.35, "learning_rate": 1.0722345e-05, "loss": 1.8037, "step": 4791 }, { "epoch": 14.35, "learning_rate": 1.072164e-05, "loss": 1.8086, "step": 4792 }, { "epoch": 14.35, "learning_rate": 1.0720935e-05, "loss": 1.8069, "step": 4793 }, { "epoch": 14.36, "learning_rate": 1.072023e-05, "loss": 1.8081, "step": 4794 }, { "epoch": 14.36, "learning_rate": 1.0719525e-05, "loss": 1.8099, "step": 4795 }, { "epoch": 14.36, "learning_rate": 1.071882e-05, "loss": 1.8067, "step": 4796 }, { "epoch": 14.36, "learning_rate": 1.0718115000000001e-05, "loss": 1.8069, "step": 4797 }, { "epoch": 14.37, "learning_rate": 1.071741e-05, "loss": 1.8085, "step": 4798 }, { "epoch": 14.37, "learning_rate": 1.0716705e-05, "loss": 1.807, "step": 4799 }, { "epoch": 14.37, "learning_rate": 1.0716e-05, "loss": 1.8086, "step": 4800 }, { "epoch": 14.37, "eval_accuracy": 0.000583315855704698, "eval_loss": 1.7572226524353027, "eval_runtime": 29.8155, "eval_samples_per_second": 9.995, "eval_steps_per_second": 0.637, "step": 4800 }, { "epoch": 14.38, "learning_rate": 1.0715295e-05, "loss": 1.8081, "step": 4801 }, { "epoch": 14.38, "learning_rate": 1.071459e-05, "loss": 1.8088, "step": 4802 }, { "epoch": 14.38, "learning_rate": 1.0713885000000002e-05, "loss": 1.8079, "step": 4803 }, { "epoch": 14.39, "learning_rate": 1.0713180000000001e-05, "loss": 1.8085, "step": 4804 }, { "epoch": 14.39, "learning_rate": 1.0712475000000001e-05, "loss": 1.8087, "step": 4805 }, { "epoch": 14.39, "learning_rate": 1.0711770000000001e-05, "loss": 1.804, "step": 4806 }, { "epoch": 14.39, "learning_rate": 1.0711065e-05, "loss": 1.8077, "step": 4807 }, { "epoch": 14.4, "learning_rate": 1.071036e-05, "loss": 1.8094, "step": 4808 }, { "epoch": 14.4, "learning_rate": 1.0709655e-05, "loss": 1.8095, "step": 4809 }, { "epoch": 14.4, "learning_rate": 1.070895e-05, "loss": 1.8078, "step": 4810 }, { "epoch": 14.41, "learning_rate": 1.0708245e-05, "loss": 1.8111, "step": 4811 }, { "epoch": 14.41, "learning_rate": 1.070754e-05, "loss": 1.8074, "step": 4812 }, { "epoch": 14.41, "learning_rate": 1.0706835e-05, "loss": 1.8053, "step": 4813 }, { "epoch": 14.42, "learning_rate": 1.070613e-05, "loss": 1.8076, "step": 4814 }, { "epoch": 14.42, "learning_rate": 1.0705425000000001e-05, "loss": 1.8092, "step": 4815 }, { "epoch": 14.42, "learning_rate": 1.070472e-05, "loss": 1.8094, "step": 4816 }, { "epoch": 14.42, "learning_rate": 1.0704015e-05, "loss": 1.8076, "step": 4817 }, { "epoch": 14.43, "learning_rate": 1.070331e-05, "loss": 1.8114, "step": 4818 }, { "epoch": 14.43, "learning_rate": 1.0702605e-05, "loss": 1.8061, "step": 4819 }, { "epoch": 14.43, "learning_rate": 1.07019e-05, "loss": 1.8054, "step": 4820 }, { "epoch": 14.44, "learning_rate": 1.0701195e-05, "loss": 1.8094, "step": 4821 }, { "epoch": 14.44, "learning_rate": 1.0700490000000001e-05, "loss": 1.8073, "step": 4822 }, { "epoch": 14.44, "learning_rate": 1.0699785000000001e-05, "loss": 1.8104, "step": 4823 }, { "epoch": 14.45, "learning_rate": 1.0699080000000001e-05, "loss": 1.8068, "step": 4824 }, { "epoch": 14.45, "learning_rate": 1.0698375e-05, "loss": 1.806, "step": 4825 }, { "epoch": 14.45, "learning_rate": 1.069767e-05, "loss": 1.8095, "step": 4826 }, { "epoch": 14.45, "learning_rate": 1.0696965e-05, "loss": 1.8106, "step": 4827 }, { "epoch": 14.46, "learning_rate": 1.0696260000000002e-05, "loss": 1.8045, "step": 4828 }, { "epoch": 14.46, "learning_rate": 1.0695555e-05, "loss": 1.806, "step": 4829 }, { "epoch": 14.46, "learning_rate": 1.069485e-05, "loss": 1.8064, "step": 4830 }, { "epoch": 14.47, "learning_rate": 1.0694145e-05, "loss": 1.8092, "step": 4831 }, { "epoch": 14.47, "learning_rate": 1.069344e-05, "loss": 1.8071, "step": 4832 }, { "epoch": 14.47, "learning_rate": 1.0692735e-05, "loss": 1.8099, "step": 4833 }, { "epoch": 14.48, "learning_rate": 1.069203e-05, "loss": 1.8084, "step": 4834 }, { "epoch": 14.48, "learning_rate": 1.0691325e-05, "loss": 1.8072, "step": 4835 }, { "epoch": 14.48, "learning_rate": 1.069062e-05, "loss": 1.8092, "step": 4836 }, { "epoch": 14.48, "learning_rate": 1.0689915e-05, "loss": 1.8033, "step": 4837 }, { "epoch": 14.49, "learning_rate": 1.068921e-05, "loss": 1.8076, "step": 4838 }, { "epoch": 14.49, "learning_rate": 1.0688505e-05, "loss": 1.809, "step": 4839 }, { "epoch": 14.49, "learning_rate": 1.0687800000000001e-05, "loss": 1.8044, "step": 4840 }, { "epoch": 14.5, "learning_rate": 1.0687095000000001e-05, "loss": 1.807, "step": 4841 }, { "epoch": 14.5, "learning_rate": 1.0686390000000001e-05, "loss": 1.8095, "step": 4842 }, { "epoch": 14.5, "learning_rate": 1.0685685e-05, "loss": 1.8068, "step": 4843 }, { "epoch": 14.51, "learning_rate": 1.068498e-05, "loss": 1.8096, "step": 4844 }, { "epoch": 14.51, "learning_rate": 1.0684275e-05, "loss": 1.8052, "step": 4845 }, { "epoch": 14.51, "learning_rate": 1.0683570000000002e-05, "loss": 1.8082, "step": 4846 }, { "epoch": 14.51, "learning_rate": 1.0682865000000002e-05, "loss": 1.8057, "step": 4847 }, { "epoch": 14.52, "learning_rate": 1.0682160000000001e-05, "loss": 1.8073, "step": 4848 }, { "epoch": 14.52, "learning_rate": 1.0681455e-05, "loss": 1.8053, "step": 4849 }, { "epoch": 14.52, "learning_rate": 1.068075e-05, "loss": 1.8054, "step": 4850 }, { "epoch": 14.53, "learning_rate": 1.0680044999999999e-05, "loss": 1.8052, "step": 4851 }, { "epoch": 14.53, "learning_rate": 1.067934e-05, "loss": 1.8076, "step": 4852 }, { "epoch": 14.53, "learning_rate": 1.0678635e-05, "loss": 1.8069, "step": 4853 }, { "epoch": 14.54, "learning_rate": 1.067793e-05, "loss": 1.8065, "step": 4854 }, { "epoch": 14.54, "learning_rate": 1.0677225e-05, "loss": 1.8067, "step": 4855 }, { "epoch": 14.54, "learning_rate": 1.067652e-05, "loss": 1.8089, "step": 4856 }, { "epoch": 14.54, "learning_rate": 1.0675815e-05, "loss": 1.8053, "step": 4857 }, { "epoch": 14.55, "learning_rate": 1.067511e-05, "loss": 1.8081, "step": 4858 }, { "epoch": 14.55, "learning_rate": 1.0674405000000001e-05, "loss": 1.8052, "step": 4859 }, { "epoch": 14.55, "learning_rate": 1.06737e-05, "loss": 1.8039, "step": 4860 }, { "epoch": 14.56, "learning_rate": 1.0672995e-05, "loss": 1.8084, "step": 4861 }, { "epoch": 14.56, "learning_rate": 1.067229e-05, "loss": 1.8028, "step": 4862 }, { "epoch": 14.56, "learning_rate": 1.0671585e-05, "loss": 1.8091, "step": 4863 }, { "epoch": 14.57, "learning_rate": 1.067088e-05, "loss": 1.8059, "step": 4864 }, { "epoch": 14.57, "learning_rate": 1.0670175000000002e-05, "loss": 1.8022, "step": 4865 }, { "epoch": 14.57, "learning_rate": 1.0669470000000001e-05, "loss": 1.8054, "step": 4866 }, { "epoch": 14.57, "learning_rate": 1.0668765000000001e-05, "loss": 1.805, "step": 4867 }, { "epoch": 14.58, "learning_rate": 1.0668060000000001e-05, "loss": 1.8061, "step": 4868 }, { "epoch": 14.58, "learning_rate": 1.0667354999999999e-05, "loss": 1.8079, "step": 4869 }, { "epoch": 14.58, "learning_rate": 1.0666649999999999e-05, "loss": 1.808, "step": 4870 }, { "epoch": 14.59, "learning_rate": 1.0665945e-05, "loss": 1.807, "step": 4871 }, { "epoch": 14.59, "learning_rate": 1.066524e-05, "loss": 1.8055, "step": 4872 }, { "epoch": 14.59, "learning_rate": 1.0664535e-05, "loss": 1.8061, "step": 4873 }, { "epoch": 14.6, "learning_rate": 1.066383e-05, "loss": 1.8061, "step": 4874 }, { "epoch": 14.6, "learning_rate": 1.0663125e-05, "loss": 1.8052, "step": 4875 }, { "epoch": 14.6, "learning_rate": 1.066242e-05, "loss": 1.8041, "step": 4876 }, { "epoch": 14.6, "learning_rate": 1.0661715000000001e-05, "loss": 1.8057, "step": 4877 }, { "epoch": 14.61, "learning_rate": 1.066101e-05, "loss": 1.8048, "step": 4878 }, { "epoch": 14.61, "learning_rate": 1.0660305e-05, "loss": 1.8047, "step": 4879 }, { "epoch": 14.61, "learning_rate": 1.06596e-05, "loss": 1.8097, "step": 4880 }, { "epoch": 14.62, "learning_rate": 1.0658895e-05, "loss": 1.8056, "step": 4881 }, { "epoch": 14.62, "learning_rate": 1.065819e-05, "loss": 1.8065, "step": 4882 }, { "epoch": 14.62, "learning_rate": 1.0657485000000002e-05, "loss": 1.8052, "step": 4883 }, { "epoch": 14.63, "learning_rate": 1.0656780000000001e-05, "loss": 1.805, "step": 4884 }, { "epoch": 14.63, "learning_rate": 1.0656075000000001e-05, "loss": 1.8057, "step": 4885 }, { "epoch": 14.63, "learning_rate": 1.0655370000000001e-05, "loss": 1.8062, "step": 4886 }, { "epoch": 14.63, "learning_rate": 1.0654665e-05, "loss": 1.8098, "step": 4887 }, { "epoch": 14.64, "learning_rate": 1.065396e-05, "loss": 1.8067, "step": 4888 }, { "epoch": 14.64, "learning_rate": 1.0653255e-05, "loss": 1.8037, "step": 4889 }, { "epoch": 14.64, "learning_rate": 1.065255e-05, "loss": 1.8059, "step": 4890 }, { "epoch": 14.65, "learning_rate": 1.0651845e-05, "loss": 1.8034, "step": 4891 }, { "epoch": 14.65, "learning_rate": 1.065114e-05, "loss": 1.8064, "step": 4892 }, { "epoch": 14.65, "learning_rate": 1.0650435e-05, "loss": 1.8034, "step": 4893 }, { "epoch": 14.66, "learning_rate": 1.064973e-05, "loss": 1.8051, "step": 4894 }, { "epoch": 14.66, "learning_rate": 1.0649025e-05, "loss": 1.8047, "step": 4895 }, { "epoch": 14.66, "learning_rate": 1.064832e-05, "loss": 1.8048, "step": 4896 }, { "epoch": 14.66, "learning_rate": 1.0647615e-05, "loss": 1.8064, "step": 4897 }, { "epoch": 14.67, "learning_rate": 1.064691e-05, "loss": 1.8062, "step": 4898 }, { "epoch": 14.67, "learning_rate": 1.0646205e-05, "loss": 1.807, "step": 4899 }, { "epoch": 14.67, "learning_rate": 1.06455e-05, "loss": 1.8015, "step": 4900 }, { "epoch": 14.67, "eval_accuracy": 0.000570207634228188, "eval_loss": 1.7556281089782715, "eval_runtime": 29.6434, "eval_samples_per_second": 10.053, "eval_steps_per_second": 0.641, "step": 4900 }, { "epoch": 14.68, "learning_rate": 1.0644795e-05, "loss": 1.8041, "step": 4901 }, { "epoch": 14.68, "learning_rate": 1.0644090000000001e-05, "loss": 1.8071, "step": 4902 }, { "epoch": 14.68, "learning_rate": 1.0643385000000001e-05, "loss": 1.806, "step": 4903 }, { "epoch": 14.69, "learning_rate": 1.0642680000000001e-05, "loss": 1.8057, "step": 4904 }, { "epoch": 14.69, "learning_rate": 1.0641975e-05, "loss": 1.8035, "step": 4905 }, { "epoch": 14.69, "learning_rate": 1.064127e-05, "loss": 1.8077, "step": 4906 }, { "epoch": 14.69, "learning_rate": 1.0640565e-05, "loss": 1.8049, "step": 4907 }, { "epoch": 14.7, "learning_rate": 1.0639860000000002e-05, "loss": 1.8061, "step": 4908 }, { "epoch": 14.7, "learning_rate": 1.0639155000000002e-05, "loss": 1.8036, "step": 4909 }, { "epoch": 14.7, "learning_rate": 1.063845e-05, "loss": 1.8068, "step": 4910 }, { "epoch": 14.71, "learning_rate": 1.0637745e-05, "loss": 1.8044, "step": 4911 }, { "epoch": 14.71, "learning_rate": 1.063704e-05, "loss": 1.8056, "step": 4912 }, { "epoch": 14.71, "learning_rate": 1.0636335e-05, "loss": 1.8069, "step": 4913 }, { "epoch": 14.72, "learning_rate": 1.063563e-05, "loss": 1.8051, "step": 4914 }, { "epoch": 14.72, "learning_rate": 1.0634925e-05, "loss": 1.8043, "step": 4915 }, { "epoch": 14.72, "learning_rate": 1.063422e-05, "loss": 1.8048, "step": 4916 }, { "epoch": 14.72, "learning_rate": 1.0633515e-05, "loss": 1.8086, "step": 4917 }, { "epoch": 14.73, "learning_rate": 1.063281e-05, "loss": 1.807, "step": 4918 }, { "epoch": 14.73, "learning_rate": 1.0632105e-05, "loss": 1.8028, "step": 4919 }, { "epoch": 14.73, "learning_rate": 1.0631400000000001e-05, "loss": 1.806, "step": 4920 }, { "epoch": 14.74, "learning_rate": 1.0630695000000001e-05, "loss": 1.802, "step": 4921 }, { "epoch": 14.74, "learning_rate": 1.0629990000000001e-05, "loss": 1.8041, "step": 4922 }, { "epoch": 14.74, "learning_rate": 1.0629285e-05, "loss": 1.8071, "step": 4923 }, { "epoch": 14.75, "learning_rate": 1.062858e-05, "loss": 1.8024, "step": 4924 }, { "epoch": 14.75, "learning_rate": 1.0627875e-05, "loss": 1.8071, "step": 4925 }, { "epoch": 14.75, "learning_rate": 1.062717e-05, "loss": 1.8044, "step": 4926 }, { "epoch": 14.75, "learning_rate": 1.0626465000000002e-05, "loss": 1.807, "step": 4927 }, { "epoch": 14.76, "learning_rate": 1.0625760000000001e-05, "loss": 1.8041, "step": 4928 }, { "epoch": 14.76, "learning_rate": 1.0625055000000001e-05, "loss": 1.803, "step": 4929 }, { "epoch": 14.76, "learning_rate": 1.062435e-05, "loss": 1.8047, "step": 4930 }, { "epoch": 14.77, "learning_rate": 1.0623644999999999e-05, "loss": 1.8041, "step": 4931 }, { "epoch": 14.77, "learning_rate": 1.062294e-05, "loss": 1.8052, "step": 4932 }, { "epoch": 14.77, "learning_rate": 1.0622235e-05, "loss": 1.8033, "step": 4933 }, { "epoch": 14.78, "learning_rate": 1.062153e-05, "loss": 1.8067, "step": 4934 }, { "epoch": 14.78, "learning_rate": 1.0620825e-05, "loss": 1.8054, "step": 4935 }, { "epoch": 14.78, "learning_rate": 1.062012e-05, "loss": 1.8078, "step": 4936 }, { "epoch": 14.78, "learning_rate": 1.0619415e-05, "loss": 1.8038, "step": 4937 }, { "epoch": 14.79, "learning_rate": 1.061871e-05, "loss": 1.8018, "step": 4938 }, { "epoch": 14.79, "learning_rate": 1.0618005000000001e-05, "loss": 1.8015, "step": 4939 }, { "epoch": 14.79, "learning_rate": 1.06173e-05, "loss": 1.8059, "step": 4940 }, { "epoch": 14.8, "learning_rate": 1.0616595e-05, "loss": 1.8016, "step": 4941 }, { "epoch": 14.8, "learning_rate": 1.061589e-05, "loss": 1.8036, "step": 4942 }, { "epoch": 14.8, "learning_rate": 1.0615185e-05, "loss": 1.8058, "step": 4943 }, { "epoch": 14.81, "learning_rate": 1.061448e-05, "loss": 1.8027, "step": 4944 }, { "epoch": 14.81, "learning_rate": 1.0613775000000002e-05, "loss": 1.8041, "step": 4945 }, { "epoch": 14.81, "learning_rate": 1.0613070000000001e-05, "loss": 1.8044, "step": 4946 }, { "epoch": 14.81, "learning_rate": 1.0612365000000001e-05, "loss": 1.8037, "step": 4947 }, { "epoch": 14.82, "learning_rate": 1.0611660000000001e-05, "loss": 1.8034, "step": 4948 }, { "epoch": 14.82, "learning_rate": 1.0610955e-05, "loss": 1.807, "step": 4949 }, { "epoch": 14.82, "learning_rate": 1.0610249999999999e-05, "loss": 1.804, "step": 4950 }, { "epoch": 14.83, "learning_rate": 1.0609545e-05, "loss": 1.8035, "step": 4951 }, { "epoch": 14.83, "learning_rate": 1.060884e-05, "loss": 1.8036, "step": 4952 }, { "epoch": 14.83, "learning_rate": 1.0608135e-05, "loss": 1.8033, "step": 4953 }, { "epoch": 14.84, "learning_rate": 1.060743e-05, "loss": 1.803, "step": 4954 }, { "epoch": 14.84, "learning_rate": 1.0606725e-05, "loss": 1.8058, "step": 4955 }, { "epoch": 14.84, "learning_rate": 1.060602e-05, "loss": 1.8016, "step": 4956 }, { "epoch": 14.84, "learning_rate": 1.0605315000000001e-05, "loss": 1.8047, "step": 4957 }, { "epoch": 14.85, "learning_rate": 1.060461e-05, "loss": 1.8066, "step": 4958 }, { "epoch": 14.85, "learning_rate": 1.0603905e-05, "loss": 1.804, "step": 4959 }, { "epoch": 14.85, "learning_rate": 1.06032e-05, "loss": 1.8049, "step": 4960 }, { "epoch": 14.86, "learning_rate": 1.0602495e-05, "loss": 1.8051, "step": 4961 }, { "epoch": 14.86, "learning_rate": 1.060179e-05, "loss": 1.8012, "step": 4962 }, { "epoch": 14.86, "learning_rate": 1.0601085e-05, "loss": 1.8025, "step": 4963 }, { "epoch": 14.87, "learning_rate": 1.0600380000000001e-05, "loss": 1.8029, "step": 4964 }, { "epoch": 14.87, "learning_rate": 1.0599675000000001e-05, "loss": 1.8046, "step": 4965 }, { "epoch": 14.87, "learning_rate": 1.0598970000000001e-05, "loss": 1.8035, "step": 4966 }, { "epoch": 14.87, "learning_rate": 1.0598265e-05, "loss": 1.8031, "step": 4967 }, { "epoch": 14.88, "learning_rate": 1.059756e-05, "loss": 1.8064, "step": 4968 }, { "epoch": 14.88, "learning_rate": 1.0596855e-05, "loss": 1.8036, "step": 4969 }, { "epoch": 14.88, "learning_rate": 1.059615e-05, "loss": 1.8043, "step": 4970 }, { "epoch": 14.89, "learning_rate": 1.0595445e-05, "loss": 1.8009, "step": 4971 }, { "epoch": 14.89, "learning_rate": 1.059474e-05, "loss": 1.8039, "step": 4972 }, { "epoch": 14.89, "learning_rate": 1.0594035e-05, "loss": 1.8026, "step": 4973 }, { "epoch": 14.9, "learning_rate": 1.059333e-05, "loss": 1.8037, "step": 4974 }, { "epoch": 14.9, "learning_rate": 1.0592625e-05, "loss": 1.8027, "step": 4975 }, { "epoch": 14.9, "learning_rate": 1.059192e-05, "loss": 1.8037, "step": 4976 }, { "epoch": 14.9, "learning_rate": 1.0591215e-05, "loss": 1.8046, "step": 4977 }, { "epoch": 14.91, "learning_rate": 1.059051e-05, "loss": 1.8029, "step": 4978 }, { "epoch": 14.91, "learning_rate": 1.0589805e-05, "loss": 1.803, "step": 4979 }, { "epoch": 14.91, "learning_rate": 1.05891e-05, "loss": 1.8038, "step": 4980 }, { "epoch": 14.92, "learning_rate": 1.0588395e-05, "loss": 1.8025, "step": 4981 }, { "epoch": 14.92, "learning_rate": 1.0587690000000001e-05, "loss": 1.8039, "step": 4982 }, { "epoch": 14.92, "learning_rate": 1.0586985000000001e-05, "loss": 1.8003, "step": 4983 }, { "epoch": 14.92, "learning_rate": 1.0586280000000001e-05, "loss": 1.8066, "step": 4984 }, { "epoch": 14.93, "learning_rate": 1.0585575e-05, "loss": 1.8046, "step": 4985 }, { "epoch": 14.93, "learning_rate": 1.058487e-05, "loss": 1.8056, "step": 4986 }, { "epoch": 14.93, "learning_rate": 1.0584165e-05, "loss": 1.8034, "step": 4987 }, { "epoch": 14.94, "learning_rate": 1.0583460000000002e-05, "loss": 1.8057, "step": 4988 }, { "epoch": 14.94, "learning_rate": 1.0582755000000002e-05, "loss": 1.8034, "step": 4989 }, { "epoch": 14.94, "learning_rate": 1.058205e-05, "loss": 1.8044, "step": 4990 }, { "epoch": 14.95, "learning_rate": 1.0581345e-05, "loss": 1.8047, "step": 4991 }, { "epoch": 14.95, "learning_rate": 1.058064e-05, "loss": 1.8026, "step": 4992 }, { "epoch": 14.95, "learning_rate": 1.0579935e-05, "loss": 1.8025, "step": 4993 }, { "epoch": 14.95, "learning_rate": 1.057923e-05, "loss": 1.8026, "step": 4994 }, { "epoch": 14.96, "learning_rate": 1.0578525e-05, "loss": 1.803, "step": 4995 }, { "epoch": 14.96, "learning_rate": 1.057782e-05, "loss": 1.8042, "step": 4996 }, { "epoch": 14.96, "learning_rate": 1.0577115e-05, "loss": 1.803, "step": 4997 }, { "epoch": 14.97, "learning_rate": 1.057641e-05, "loss": 1.8031, "step": 4998 }, { "epoch": 14.97, "learning_rate": 1.0575705e-05, "loss": 1.8045, "step": 4999 }, { "epoch": 14.97, "learning_rate": 1.0575e-05, "loss": 1.805, "step": 5000 }, { "epoch": 14.97, "eval_accuracy": 0.000570207634228188, "eval_loss": 1.7537741661071777, "eval_runtime": 30.4528, "eval_samples_per_second": 9.786, "eval_steps_per_second": 0.624, "step": 5000 } ], "logging_steps": 1.0, "max_steps": 20000, "num_input_tokens_seen": 0, "num_train_epochs": 61, "save_steps": 500, "total_flos": 2.749471486849843e+18, "train_batch_size": 128, "trial_name": null, "trial_params": null }