| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.484536082474227, | |
| "global_step": 460, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.0833333333333333e-07, | |
| "loss": 0.7393, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.1666666666666667e-07, | |
| "loss": 0.7516, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 6.25e-07, | |
| "loss": 0.7506, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 8.333333333333333e-07, | |
| "loss": 0.7494, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.0416666666666667e-06, | |
| "loss": 0.7602, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_accuracy": 0.6200000047683716, | |
| "eval_average_score": 0.6218893527984619, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.7480455040931702, | |
| "eval_runtime": 3.4088, | |
| "eval_samples_per_second": 14.668, | |
| "eval_steps_per_second": 3.814, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.25e-06, | |
| "loss": 0.7501, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.4583333333333335e-06, | |
| "loss": 0.743, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.6666666666666667e-06, | |
| "loss": 0.7412, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.8750000000000003e-06, | |
| "loss": 0.7553, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.0833333333333334e-06, | |
| "loss": 0.7355, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_accuracy": 0.5400000214576721, | |
| "eval_average_score": 0.5707897543907166, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.7415069341659546, | |
| "eval_runtime": 3.405, | |
| "eval_samples_per_second": 14.684, | |
| "eval_steps_per_second": 3.818, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.2916666666666666e-06, | |
| "loss": 0.7402, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.7427, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.7083333333333334e-06, | |
| "loss": 0.7286, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.916666666666667e-06, | |
| "loss": 0.727, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.125e-06, | |
| "loss": 0.7305, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_accuracy": 0.6000000238418579, | |
| "eval_average_score": 0.4747978150844574, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.7272794842720032, | |
| "eval_runtime": 3.41, | |
| "eval_samples_per_second": 14.663, | |
| "eval_steps_per_second": 3.812, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.7186, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.5416666666666673e-06, | |
| "loss": 0.7398, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 0.7166, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 3.958333333333333e-06, | |
| "loss": 0.7148, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 4.166666666666667e-06, | |
| "loss": 0.7116, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_accuracy": 0.6000000238418579, | |
| "eval_average_score": 0.3107444643974304, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.7109410166740417, | |
| "eval_runtime": 3.4072, | |
| "eval_samples_per_second": 14.675, | |
| "eval_steps_per_second": 3.815, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 4.3750000000000005e-06, | |
| "loss": 0.7221, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 4.583333333333333e-06, | |
| "loss": 0.7042, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 4.791666666666668e-06, | |
| "loss": 0.7011, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6987, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 5.208333333333334e-06, | |
| "loss": 0.6926, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_accuracy": 0.6800000071525574, | |
| "eval_average_score": 0.07106868177652359, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.6947080492973328, | |
| "eval_runtime": 3.4106, | |
| "eval_samples_per_second": 14.66, | |
| "eval_steps_per_second": 3.812, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 5.416666666666667e-06, | |
| "loss": 0.695, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 5.625e-06, | |
| "loss": 0.6917, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 5.833333333333334e-06, | |
| "loss": 0.7115, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 6.041666666666667e-06, | |
| "loss": 0.6858, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 6.25e-06, | |
| "loss": 0.6867, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "eval_accuracy": 0.6000000238418579, | |
| "eval_average_score": -0.15788692235946655, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.6935771703720093, | |
| "eval_runtime": 3.4133, | |
| "eval_samples_per_second": 14.648, | |
| "eval_steps_per_second": 3.809, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 6.458333333333334e-06, | |
| "loss": 0.6868, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.6837, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 6.875e-06, | |
| "loss": 0.6883, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 7.083333333333335e-06, | |
| "loss": 0.689, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 7.291666666666667e-06, | |
| "loss": 0.6761, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_accuracy": 0.7799999713897705, | |
| "eval_average_score": -0.07916055619716644, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.6847817897796631, | |
| "eval_runtime": 3.4111, | |
| "eval_samples_per_second": 14.658, | |
| "eval_steps_per_second": 3.811, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.6863, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 7.708333333333334e-06, | |
| "loss": 0.6841, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 7.916666666666667e-06, | |
| "loss": 0.6719, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 8.125000000000001e-06, | |
| "loss": 0.6802, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.672, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "eval_accuracy": 0.8199999928474426, | |
| "eval_average_score": -0.042581118643283844, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.6735163331031799, | |
| "eval_runtime": 3.4082, | |
| "eval_samples_per_second": 14.67, | |
| "eval_steps_per_second": 3.814, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 8.541666666666666e-06, | |
| "loss": 0.6675, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 8.750000000000001e-06, | |
| "loss": 0.6649, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 8.958333333333334e-06, | |
| "loss": 0.6804, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 9.166666666666666e-06, | |
| "loss": 0.6692, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 9.375000000000001e-06, | |
| "loss": 0.654, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_accuracy": 0.8600000143051147, | |
| "eval_average_score": -0.11977884918451309, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.652625560760498, | |
| "eval_runtime": 3.4105, | |
| "eval_samples_per_second": 14.661, | |
| "eval_steps_per_second": 3.812, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 9.583333333333335e-06, | |
| "loss": 0.6495, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 9.791666666666666e-06, | |
| "loss": 0.6472, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6499, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6247, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6422, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "eval_accuracy": 0.8799999952316284, | |
| "eval_average_score": -0.13170765340328217, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.608478307723999, | |
| "eval_runtime": 3.4104, | |
| "eval_samples_per_second": 14.661, | |
| "eval_steps_per_second": 3.812, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6252, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6065, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5829, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5936, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5528, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_accuracy": 0.8600000143051147, | |
| "eval_average_score": -0.0412043035030365, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.5438380241394043, | |
| "eval_runtime": 3.4096, | |
| "eval_samples_per_second": 14.665, | |
| "eval_steps_per_second": 3.813, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5529, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5658, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5421, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5503, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4854, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "eval_accuracy": 0.8999999761581421, | |
| "eval_average_score": -0.40412548184394836, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.46706727147102356, | |
| "eval_runtime": 3.4091, | |
| "eval_samples_per_second": 14.667, | |
| "eval_steps_per_second": 3.813, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5268, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5251, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4857, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5307, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4672, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "eval_accuracy": 0.8999999761581421, | |
| "eval_average_score": -0.14681239426136017, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.391941636800766, | |
| "eval_runtime": 3.4094, | |
| "eval_samples_per_second": 14.665, | |
| "eval_steps_per_second": 3.813, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4077, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3849, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4358, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3896, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4903, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "eval_accuracy": 0.8999999761581421, | |
| "eval_average_score": -0.11637383699417114, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.3501974940299988, | |
| "eval_runtime": 3.4098, | |
| "eval_samples_per_second": 14.664, | |
| "eval_steps_per_second": 3.813, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3395, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3976, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3826, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4534, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3473, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "eval_accuracy": 0.9200000166893005, | |
| "eval_average_score": -0.3039152920246124, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.3362675607204437, | |
| "eval_runtime": 3.4088, | |
| "eval_samples_per_second": 14.668, | |
| "eval_steps_per_second": 3.814, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 1e-05, | |
| "loss": 0.368, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4096, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3829, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 1e-05, | |
| "loss": 0.389, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4191, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "eval_accuracy": 0.8999999761581421, | |
| "eval_average_score": 0.41642922163009644, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.31328877806663513, | |
| "eval_runtime": 3.415, | |
| "eval_samples_per_second": 14.641, | |
| "eval_steps_per_second": 3.807, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2698, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4149, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3844, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3549, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3571, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "eval_accuracy": 0.8999999761581421, | |
| "eval_average_score": -0.14143863320350647, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.3141113221645355, | |
| "eval_runtime": 3.4148, | |
| "eval_samples_per_second": 14.642, | |
| "eval_steps_per_second": 3.807, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2812, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4222, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3538, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2896, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3285, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "eval_accuracy": 0.8999999761581421, | |
| "eval_average_score": -0.04474750533699989, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.30486491322517395, | |
| "eval_runtime": 3.4082, | |
| "eval_samples_per_second": 14.67, | |
| "eval_steps_per_second": 3.814, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3278, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3715, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3234, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2756, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3535, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "eval_accuracy": 0.8999999761581421, | |
| "eval_average_score": -0.3523316979408264, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.3148648738861084, | |
| "eval_runtime": 3.4081, | |
| "eval_samples_per_second": 14.671, | |
| "eval_steps_per_second": 3.814, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3098, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2694, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2731, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 1e-05, | |
| "loss": 0.309, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3961, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "eval_accuracy": 0.8999999761581421, | |
| "eval_average_score": 0.40198975801467896, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.2921418249607086, | |
| "eval_runtime": 3.4104, | |
| "eval_samples_per_second": 14.661, | |
| "eval_steps_per_second": 3.812, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3488, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 1e-05, | |
| "loss": 0.399, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 1e-05, | |
| "loss": 0.348, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2844, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3491, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "eval_accuracy": 0.8999999761581421, | |
| "eval_average_score": 0.008343610912561417, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.2992297410964966, | |
| "eval_runtime": 3.4089, | |
| "eval_samples_per_second": 14.667, | |
| "eval_steps_per_second": 3.814, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2381, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3823, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2863, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2731, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2552, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "eval_accuracy": 0.8999999761581421, | |
| "eval_average_score": 0.21405518054962158, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.28597450256347656, | |
| "eval_runtime": 3.4094, | |
| "eval_samples_per_second": 14.665, | |
| "eval_steps_per_second": 3.813, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3438, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3672, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2783, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2705, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1839, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "eval_accuracy": 0.9200000166893005, | |
| "eval_average_score": -0.29983624815940857, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.2997009754180908, | |
| "eval_runtime": 3.409, | |
| "eval_samples_per_second": 14.667, | |
| "eval_steps_per_second": 3.813, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2776, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "learning_rate": 1e-05, | |
| "loss": 0.284, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3313, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2521, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2896, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "eval_accuracy": 0.8999999761581421, | |
| "eval_average_score": 0.08488038927316666, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.2867457866668701, | |
| "eval_runtime": 3.4098, | |
| "eval_samples_per_second": 14.664, | |
| "eval_steps_per_second": 3.813, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3284, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3234, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2818, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3356, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 5.15, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3125, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 5.15, | |
| "eval_accuracy": 0.9200000166893005, | |
| "eval_average_score": -0.0647800862789154, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.28697526454925537, | |
| "eval_runtime": 3.4101, | |
| "eval_samples_per_second": 14.663, | |
| "eval_steps_per_second": 3.812, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2619, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2484, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3222, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1985, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 5.36, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3923, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 5.36, | |
| "eval_accuracy": 0.9200000166893005, | |
| "eval_average_score": 0.1731201559305191, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.2790464162826538, | |
| "eval_runtime": 3.4092, | |
| "eval_samples_per_second": 14.666, | |
| "eval_steps_per_second": 3.813, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3787, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2585, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2569, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2574, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3044, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "eval_accuracy": 0.9200000166893005, | |
| "eval_average_score": 0.16195712983608246, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.28128278255462646, | |
| "eval_runtime": 3.4082, | |
| "eval_samples_per_second": 14.67, | |
| "eval_steps_per_second": 3.814, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2866, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2532, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2748, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3158, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3294, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "eval_accuracy": 0.8999999761581421, | |
| "eval_average_score": 0.017967911437153816, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.280609667301178, | |
| "eval_runtime": 3.4082, | |
| "eval_samples_per_second": 14.67, | |
| "eval_steps_per_second": 3.814, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 5.81, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2155, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2301, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3384, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 5.94, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2534, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 5.98, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2902, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 5.98, | |
| "eval_accuracy": 0.9200000166893005, | |
| "eval_average_score": 0.3276750147342682, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.2765599191188812, | |
| "eval_runtime": 3.4103, | |
| "eval_samples_per_second": 14.661, | |
| "eval_steps_per_second": 3.812, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3011, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3248, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "learning_rate": 1e-05, | |
| "loss": 0.37, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "learning_rate": 1e-05, | |
| "loss": 0.278, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 1e-05, | |
| "loss": 0.275, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "eval_accuracy": 0.9200000166893005, | |
| "eval_average_score": -0.1893548220396042, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.2832108438014984, | |
| "eval_runtime": 3.4099, | |
| "eval_samples_per_second": 14.663, | |
| "eval_steps_per_second": 3.812, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 6.23, | |
| "learning_rate": 1e-05, | |
| "loss": 0.262, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 6.27, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2765, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 6.31, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2069, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 6.35, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2567, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2939, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "eval_accuracy": 0.9200000166893005, | |
| "eval_average_score": -0.16238823533058167, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.2794664204120636, | |
| "eval_runtime": 3.407, | |
| "eval_samples_per_second": 14.676, | |
| "eval_steps_per_second": 3.816, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 6.43, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3302, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2244, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2158, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2536, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1905, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "eval_accuracy": 0.9200000166893005, | |
| "eval_average_score": 0.26926523447036743, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.26797807216644287, | |
| "eval_runtime": 3.4064, | |
| "eval_samples_per_second": 14.678, | |
| "eval_steps_per_second": 3.816, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2607, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 6.68, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2542, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 1e-05, | |
| "loss": 0.265, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2763, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3119, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "eval_accuracy": 0.9200000166893005, | |
| "eval_average_score": -0.12742717564105988, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.2834363877773285, | |
| "eval_runtime": 3.4081, | |
| "eval_samples_per_second": 14.671, | |
| "eval_steps_per_second": 3.814, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 6.85, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1726, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 6.89, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2636, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 6.93, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3579, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2635, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2602, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "eval_accuracy": 0.9399999976158142, | |
| "eval_average_score": -0.0478409007191658, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.27865225076675415, | |
| "eval_runtime": 3.4081, | |
| "eval_samples_per_second": 14.671, | |
| "eval_steps_per_second": 3.814, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2111, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2853, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 7.13, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2853, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 7.18, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3026, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 7.22, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2446, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 7.22, | |
| "eval_accuracy": 0.9399999976158142, | |
| "eval_average_score": -0.1700994372367859, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.2747596800327301, | |
| "eval_runtime": 3.4061, | |
| "eval_samples_per_second": 14.679, | |
| "eval_steps_per_second": 3.817, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 7.26, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2469, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2372, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 7.34, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2655, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 7.38, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2661, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 7.42, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2731, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 7.42, | |
| "eval_accuracy": 0.9200000166893005, | |
| "eval_average_score": 0.01858169585466385, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.2665027379989624, | |
| "eval_runtime": 3.4061, | |
| "eval_samples_per_second": 14.68, | |
| "eval_steps_per_second": 3.817, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 7.46, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1845, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 7.51, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2881, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 7.55, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2038, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 7.59, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2111, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2992, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "eval_accuracy": 0.9399999976158142, | |
| "eval_average_score": 0.4874734878540039, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.2591661810874939, | |
| "eval_runtime": 3.4058, | |
| "eval_samples_per_second": 14.681, | |
| "eval_steps_per_second": 3.817, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 7.67, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1714, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2276, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3777, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2173, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "eval_accuracy": 0.9200000166893005, | |
| "eval_average_score": -0.07412362843751907, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.274651437997818, | |
| "eval_runtime": 3.4072, | |
| "eval_samples_per_second": 14.675, | |
| "eval_steps_per_second": 3.815, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 7.88, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2491, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 7.92, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2425, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2925, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2723, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3516, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "eval_accuracy": 0.9399999976158142, | |
| "eval_average_score": 0.005836525000631809, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.26507002115249634, | |
| "eval_runtime": 3.4088, | |
| "eval_samples_per_second": 14.668, | |
| "eval_steps_per_second": 3.814, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 8.08, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2519, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2991, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 8.16, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2234, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 8.21, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2711, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 8.25, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3236, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 8.25, | |
| "eval_accuracy": 0.9200000166893005, | |
| "eval_average_score": 0.04313167557120323, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.25931546092033386, | |
| "eval_runtime": 3.4059, | |
| "eval_samples_per_second": 14.681, | |
| "eval_steps_per_second": 3.817, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 8.29, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1869, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 8.33, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2314, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 8.37, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2405, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 8.41, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1779, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2458, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "eval_accuracy": 0.8999999761581421, | |
| "eval_average_score": -0.21540480852127075, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.2680150270462036, | |
| "eval_runtime": 3.4085, | |
| "eval_samples_per_second": 14.669, | |
| "eval_steps_per_second": 3.814, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1723, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 8.54, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3219, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "learning_rate": 1e-05, | |
| "loss": 0.243, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 8.62, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2095, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1976, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "eval_accuracy": 0.8999999761581421, | |
| "eval_average_score": 0.17054100334644318, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.2620932459831238, | |
| "eval_runtime": 3.4133, | |
| "eval_samples_per_second": 14.648, | |
| "eval_steps_per_second": 3.809, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 8.7, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1717, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 8.74, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2759, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 8.78, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3572, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1688, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 8.87, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2358, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 8.87, | |
| "eval_accuracy": 0.8999999761581421, | |
| "eval_average_score": 0.2345839887857437, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.2618144154548645, | |
| "eval_runtime": 3.406, | |
| "eval_samples_per_second": 14.68, | |
| "eval_steps_per_second": 3.817, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 8.91, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1975, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 8.95, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3316, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1964, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2148, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 9.07, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1855, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 9.07, | |
| "eval_accuracy": 0.8999999761581421, | |
| "eval_average_score": 0.04021953418850899, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.2684229612350464, | |
| "eval_runtime": 3.4104, | |
| "eval_samples_per_second": 14.661, | |
| "eval_steps_per_second": 3.812, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 9.11, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2186, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 9.15, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1604, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1649, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 9.24, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2496, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3004, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "eval_accuracy": 0.8999999761581421, | |
| "eval_average_score": 0.08485334366559982, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.26888754963874817, | |
| "eval_runtime": 3.4093, | |
| "eval_samples_per_second": 14.666, | |
| "eval_steps_per_second": 3.813, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2056, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2284, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2529, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 9.44, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2847, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 9.48, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2804, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 9.48, | |
| "eval_accuracy": 0.9200000166893005, | |
| "eval_average_score": -0.19331374764442444, | |
| "eval_label_positive_rate": 0.47999998927116394, | |
| "eval_loss": 0.2731383442878723, | |
| "eval_runtime": 3.4089, | |
| "eval_samples_per_second": 14.668, | |
| "eval_steps_per_second": 3.814, | |
| "step": 460 | |
| } | |
| ], | |
| "max_steps": 480, | |
| "num_train_epochs": 10, | |
| "total_flos": 8.790703793881743e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |