File size: 6,761 Bytes
47eeece |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 |
{
"best_metric": 0.827712178226716,
"best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_paragraphs_ml512-v1/checkpoint-500",
"epoch": 0.8528784648187633,
"eval_steps": 100,
"global_step": 1600,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.05,
"eval_accuracy": 0.687484404164213,
"eval_f1": 0.687484404164213,
"eval_loss": 0.11619879305362701,
"eval_precision": 0.687484404164213,
"eval_recall": 0.687484404164213,
"eval_runtime": 114.5058,
"eval_samples_per_second": 14.034,
"eval_steps_per_second": 0.882,
"step": 100
},
{
"epoch": 0.11,
"eval_accuracy": 0.6755467276193519,
"eval_f1": 0.6755467276193519,
"eval_loss": 0.1096724346280098,
"eval_precision": 0.6755467276193519,
"eval_recall": 0.6755467276193519,
"eval_runtime": 97.2211,
"eval_samples_per_second": 16.529,
"eval_steps_per_second": 1.039,
"step": 200
},
{
"epoch": 0.16,
"eval_accuracy": 0.7780849810853704,
"eval_f1": 0.7780849810853703,
"eval_loss": 0.08659958839416504,
"eval_precision": 0.7780849810853704,
"eval_recall": 0.7780849810853704,
"eval_runtime": 98.762,
"eval_samples_per_second": 16.271,
"eval_steps_per_second": 1.023,
"step": 300
},
{
"epoch": 0.21,
"eval_accuracy": 0.7477716669827422,
"eval_f1": 0.7477716669827422,
"eval_loss": 0.10182594507932663,
"eval_precision": 0.7477716669827422,
"eval_recall": 0.7477716669827422,
"eval_runtime": 99.9428,
"eval_samples_per_second": 16.079,
"eval_steps_per_second": 1.011,
"step": 400
},
{
"epoch": 0.27,
"learning_rate": 1.4669509594882732e-05,
"loss": 0.0975,
"step": 500
},
{
"epoch": 0.27,
"eval_accuracy": 0.827712178226716,
"eval_f1": 0.827712178226716,
"eval_loss": 0.06453556567430496,
"eval_precision": 0.827712178226716,
"eval_recall": 0.827712178226716,
"eval_runtime": 100.1167,
"eval_samples_per_second": 16.051,
"eval_steps_per_second": 1.009,
"step": 500
},
{
"epoch": 0.32,
"eval_accuracy": 0.7984968109634982,
"eval_f1": 0.7984968109634982,
"eval_loss": 0.07669692486524582,
"eval_precision": 0.7984968109634982,
"eval_recall": 0.7984968109634982,
"eval_runtime": 101.2405,
"eval_samples_per_second": 15.873,
"eval_steps_per_second": 0.998,
"step": 600
},
{
"epoch": 0.37,
"eval_accuracy": 0.7903320790122471,
"eval_f1": 0.7903320790122471,
"eval_loss": 0.07575991004705429,
"eval_precision": 0.7903320790122471,
"eval_recall": 0.7903320790122471,
"eval_runtime": 99.3914,
"eval_samples_per_second": 16.168,
"eval_steps_per_second": 1.016,
"step": 700
},
{
"epoch": 0.43,
"eval_accuracy": 0.7865491530837334,
"eval_f1": 0.7865491530837335,
"eval_loss": 0.08622009307146072,
"eval_precision": 0.7865491530837334,
"eval_recall": 0.7865491530837334,
"eval_runtime": 102.0728,
"eval_samples_per_second": 15.744,
"eval_steps_per_second": 0.989,
"step": 800
},
{
"epoch": 0.48,
"eval_accuracy": 0.6891712497629433,
"eval_f1": 0.6891712497629433,
"eval_loss": 0.12430301308631897,
"eval_precision": 0.6891712497629433,
"eval_recall": 0.6891712497629433,
"eval_runtime": 101.8092,
"eval_samples_per_second": 15.784,
"eval_steps_per_second": 0.992,
"step": 900
},
{
"epoch": 0.53,
"learning_rate": 9.339019189765458e-06,
"loss": 0.1389,
"step": 1000
},
{
"epoch": 0.53,
"eval_accuracy": 0.8255961352271253,
"eval_f1": 0.8255961352271252,
"eval_loss": 0.07946911454200745,
"eval_precision": 0.8255961352271253,
"eval_recall": 0.8255961352271253,
"eval_runtime": 101.762,
"eval_samples_per_second": 15.792,
"eval_steps_per_second": 0.993,
"step": 1000
},
{
"epoch": 0.59,
"eval_accuracy": 0.470200724644914,
"eval_f1": 0.470200724644914,
"eval_loss": 0.1683182567358017,
"eval_precision": 0.470200724644914,
"eval_recall": 0.470200724644914,
"eval_runtime": 100.8271,
"eval_samples_per_second": 15.938,
"eval_steps_per_second": 1.002,
"step": 1100
},
{
"epoch": 0.64,
"eval_accuracy": 0.6635990697395869,
"eval_f1": 0.6635990697395869,
"eval_loss": 0.12526559829711914,
"eval_precision": 0.6635990697395869,
"eval_recall": 0.6635990697395869,
"eval_runtime": 98.9873,
"eval_samples_per_second": 16.234,
"eval_steps_per_second": 1.02,
"step": 1200
},
{
"epoch": 0.69,
"eval_accuracy": 0.7294758801042052,
"eval_f1": 0.7294758801042052,
"eval_loss": 0.10443996638059616,
"eval_precision": 0.7294758801042052,
"eval_recall": 0.7294758801042052,
"eval_runtime": 98.9922,
"eval_samples_per_second": 16.234,
"eval_steps_per_second": 1.02,
"step": 1300
},
{
"epoch": 0.75,
"eval_accuracy": 0.6476788405681376,
"eval_f1": 0.6476788405681376,
"eval_loss": 0.12347274273633957,
"eval_precision": 0.6476788405681376,
"eval_recall": 0.6476788405681376,
"eval_runtime": 99.0722,
"eval_samples_per_second": 16.22,
"eval_steps_per_second": 1.019,
"step": 1400
},
{
"epoch": 0.8,
"learning_rate": 4.008528784648188e-06,
"loss": 0.1018,
"step": 1500
},
{
"epoch": 0.8,
"eval_accuracy": 0.7275993891423039,
"eval_f1": 0.7275993891423039,
"eval_loss": 0.11132516711950302,
"eval_precision": 0.7275993891423039,
"eval_recall": 0.7275993891423039,
"eval_runtime": 105.053,
"eval_samples_per_second": 15.297,
"eval_steps_per_second": 0.961,
"step": 1500
},
{
"epoch": 0.85,
"eval_accuracy": 0.7316518111132183,
"eval_f1": 0.7316518111132183,
"eval_loss": 0.10142996907234192,
"eval_precision": 0.7316518111132183,
"eval_recall": 0.7316518111132183,
"eval_runtime": 100.1827,
"eval_samples_per_second": 16.041,
"eval_steps_per_second": 1.008,
"step": 1600
}
],
"logging_steps": 500,
"max_steps": 1876,
"num_train_epochs": 1,
"save_steps": 100,
"total_flos": 3560604657254400.0,
"trial_name": null,
"trial_params": null
}
|