File size: 5,419 Bytes
8b9fa0f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 9.996742671009772,
"global_step": 1530,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"learning_rate": 3e-05,
"loss": 1.5521,
"step": 153
},
{
"epoch": 1.0,
"eval_accuracy": 0.020859987762140514,
"eval_f1": 0.3928758387664779,
"eval_loss": 0.7758789658546448,
"eval_mAP": 0.339376592817118,
"eval_roc_auc": 0.6789196770069326,
"eval_runtime": 199.2822,
"eval_samples_per_second": 90.209,
"eval_steps_per_second": 2.82,
"step": 153
},
{
"epoch": 2.0,
"learning_rate": 2.6666666666666667e-05,
"loss": 0.7088,
"step": 306
},
{
"epoch": 2.0,
"eval_accuracy": 0.03487789953829894,
"eval_f1": 0.44802049737602123,
"eval_loss": 0.518318772315979,
"eval_mAP": 0.40469907094541646,
"eval_roc_auc": 0.7161709917220414,
"eval_runtime": 199.2709,
"eval_samples_per_second": 90.214,
"eval_steps_per_second": 2.82,
"step": 306
},
{
"epoch": 3.0,
"learning_rate": 2.3333333333333336e-05,
"loss": 0.484,
"step": 459
},
{
"epoch": 3.0,
"eval_accuracy": 0.04472381376202926,
"eval_f1": 0.4673244026068067,
"eval_loss": 0.4342249929904938,
"eval_mAP": 0.43476738028039985,
"eval_roc_auc": 0.7240716119428349,
"eval_runtime": 199.3141,
"eval_samples_per_second": 90.194,
"eval_steps_per_second": 2.82,
"step": 459
},
{
"epoch": 4.0,
"learning_rate": 1.9999999999999998e-05,
"loss": 0.369,
"step": 612
},
{
"epoch": 4.0,
"eval_accuracy": 0.05039773043333148,
"eval_f1": 0.4777058032688526,
"eval_loss": 0.38471919298171997,
"eval_mAP": 0.4462659411425718,
"eval_roc_auc": 0.7332463051626695,
"eval_runtime": 199.7831,
"eval_samples_per_second": 89.983,
"eval_steps_per_second": 2.813,
"step": 612
},
{
"epoch": 5.0,
"learning_rate": 1.6666666666666667e-05,
"loss": 0.2943,
"step": 765
},
{
"epoch": 5.0,
"eval_accuracy": 0.057184179785281196,
"eval_f1": 0.48378530618813875,
"eval_loss": 0.35873091220855713,
"eval_mAP": 0.4555505029466916,
"eval_roc_auc": 0.728419646417412,
"eval_runtime": 199.5573,
"eval_samples_per_second": 90.084,
"eval_steps_per_second": 2.816,
"step": 765
},
{
"epoch": 6.0,
"learning_rate": 1.3333333333333333e-05,
"loss": 0.2446,
"step": 918
},
{
"epoch": 6.0,
"eval_accuracy": 0.06079991099738555,
"eval_f1": 0.48746197105190375,
"eval_loss": 0.34149762988090515,
"eval_mAP": 0.4627587003938359,
"eval_roc_auc": 0.7296145264183724,
"eval_runtime": 199.5498,
"eval_samples_per_second": 90.088,
"eval_steps_per_second": 2.816,
"step": 918
},
{
"epoch": 7.0,
"learning_rate": 9.999999999999999e-06,
"loss": 0.2099,
"step": 1071
},
{
"epoch": 7.0,
"eval_accuracy": 0.06480502864771652,
"eval_f1": 0.48957753814467153,
"eval_loss": 0.3272540867328644,
"eval_mAP": 0.46815321516964326,
"eval_roc_auc": 0.7245854561214261,
"eval_runtime": 199.6486,
"eval_samples_per_second": 90.043,
"eval_steps_per_second": 2.815,
"step": 1071
},
{
"epoch": 8.0,
"learning_rate": 6.666666666666667e-06,
"loss": 0.186,
"step": 1224
},
{
"epoch": 8.0,
"eval_accuracy": 0.06892139956611225,
"eval_f1": 0.4888448554234551,
"eval_loss": 0.31404560804367065,
"eval_mAP": 0.47110233159119475,
"eval_roc_auc": 0.7170914721421969,
"eval_runtime": 199.7258,
"eval_samples_per_second": 90.008,
"eval_steps_per_second": 2.814,
"step": 1224
},
{
"epoch": 9.0,
"learning_rate": 3.3333333333333333e-06,
"loss": 0.1693,
"step": 1377
},
{
"epoch": 9.0,
"eval_accuracy": 0.07031206541692162,
"eval_f1": 0.48868811698382614,
"eval_loss": 0.3100704848766327,
"eval_mAP": 0.4740859292456036,
"eval_roc_auc": 0.7156721287285349,
"eval_runtime": 199.6676,
"eval_samples_per_second": 90.035,
"eval_steps_per_second": 2.815,
"step": 1377
},
{
"epoch": 10.0,
"learning_rate": 0.0,
"loss": 0.1582,
"step": 1530
},
{
"epoch": 10.0,
"eval_accuracy": 0.07136897146353674,
"eval_f1": 0.48760985270454266,
"eval_loss": 0.30630359053611755,
"eval_mAP": 0.47426149334040063,
"eval_roc_auc": 0.7140083968239697,
"eval_runtime": 199.7463,
"eval_samples_per_second": 89.999,
"eval_steps_per_second": 2.814,
"step": 1530
},
{
"epoch": 10.0,
"step": 1530,
"total_flos": 6.805036258155823e+18,
"train_loss": 0.4376198089200687,
"train_runtime": 5452.4515,
"train_samples_per_second": 36.024,
"train_steps_per_second": 0.281
}
],
"max_steps": 1530,
"num_train_epochs": 10,
"total_flos": 6.805036258155823e+18,
"trial_name": null,
"trial_params": null
}
|