File size: 5,576 Bytes
78429a6 |
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 |
{
"best_metric": 0.07265603542327881,
"best_model_checkpoint": "/data/jcanete/all_results/pos/albeto_large/epochs_4_bs_16_lr_5e-6/checkpoint-3300",
"epoch": 4.0,
"global_step": 3580,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.34,
"eval_accuracy": 0.9613357957337219,
"eval_f1": 0.956240711001167,
"eval_loss": 0.15343289077281952,
"eval_precision": 0.9548025975060754,
"eval_recall": 0.957683163173563,
"eval_runtime": 3.7594,
"eval_samples_per_second": 439.96,
"eval_steps_per_second": 27.664,
"step": 300
},
{
"epoch": 0.56,
"learning_rate": 4.305865921787709e-06,
"loss": 0.5366,
"step": 500
},
{
"epoch": 0.67,
"eval_accuracy": 0.9719421900679419,
"eval_f1": 0.9686646055649745,
"eval_loss": 0.1060481071472168,
"eval_precision": 0.9670443457655469,
"eval_recall": 0.9702903038900321,
"eval_runtime": 3.5348,
"eval_samples_per_second": 467.913,
"eval_steps_per_second": 29.421,
"step": 600
},
{
"epoch": 1.01,
"eval_accuracy": 0.9751444401145355,
"eval_f1": 0.972691003391183,
"eval_loss": 0.09304744005203247,
"eval_precision": 0.9711605489055747,
"eval_recall": 0.9742262891850313,
"eval_runtime": 3.5404,
"eval_samples_per_second": 467.179,
"eval_steps_per_second": 29.375,
"step": 900
},
{
"epoch": 1.12,
"learning_rate": 3.607541899441341e-06,
"loss": 0.0981,
"step": 1000
},
{
"epoch": 1.34,
"eval_accuracy": 0.9768726385523797,
"eval_f1": 0.9757217127518386,
"eval_loss": 0.0842280164361,
"eval_precision": 0.9746421594035326,
"eval_recall": 0.9768036602665281,
"eval_runtime": 3.5912,
"eval_samples_per_second": 460.574,
"eval_steps_per_second": 28.96,
"step": 1200
},
{
"epoch": 1.68,
"learning_rate": 2.9092178770949727e-06,
"loss": 0.0752,
"step": 1500
},
{
"epoch": 1.68,
"eval_accuracy": 0.9773131597228105,
"eval_f1": 0.9761464958613322,
"eval_loss": 0.0810752809047699,
"eval_precision": 0.9756496746636861,
"eval_recall": 0.9766438233002338,
"eval_runtime": 3.5387,
"eval_samples_per_second": 467.408,
"eval_steps_per_second": 29.39,
"step": 1500
},
{
"epoch": 2.01,
"eval_accuracy": 0.9785669507463445,
"eval_f1": 0.9775089095864156,
"eval_loss": 0.07652546465396881,
"eval_precision": 0.9768165675751167,
"eval_recall": 0.978202233721604,
"eval_runtime": 3.5669,
"eval_samples_per_second": 463.705,
"eval_steps_per_second": 29.157,
"step": 1800
},
{
"epoch": 2.23,
"learning_rate": 2.2108938547486037e-06,
"loss": 0.0665,
"step": 2000
},
{
"epoch": 2.35,
"eval_accuracy": 0.9788888700631978,
"eval_f1": 0.9777791081709423,
"eval_loss": 0.07642523944377899,
"eval_precision": 0.9766194937213474,
"eval_recall": 0.9789414796907154,
"eval_runtime": 3.5528,
"eval_samples_per_second": 465.546,
"eval_steps_per_second": 29.273,
"step": 2100
},
{
"epoch": 2.68,
"eval_accuracy": 0.9798715711356975,
"eval_f1": 0.9788792845307728,
"eval_loss": 0.07392332702875137,
"eval_precision": 0.97805924005186,
"eval_recall": 0.9797007052806138,
"eval_runtime": 6.3431,
"eval_samples_per_second": 260.756,
"eval_steps_per_second": 16.396,
"step": 2400
},
{
"epoch": 2.79,
"learning_rate": 1.5125698324022347e-06,
"loss": 0.0572,
"step": 2500
},
{
"epoch": 3.02,
"eval_accuracy": 0.980379864793887,
"eval_f1": 0.9797258851832258,
"eval_loss": 0.07377304136753082,
"eval_precision": 0.9789929377967522,
"eval_recall": 0.9804599308705121,
"eval_runtime": 3.5438,
"eval_samples_per_second": 466.727,
"eval_steps_per_second": 29.347,
"step": 2700
},
{
"epoch": 3.35,
"learning_rate": 8.142458100558661e-07,
"loss": 0.0517,
"step": 3000
},
{
"epoch": 3.35,
"eval_accuracy": 0.979939343623456,
"eval_f1": 0.9793008417457987,
"eval_loss": 0.07385215163230896,
"eval_precision": 0.9788414707173939,
"eval_recall": 0.9797606441429741,
"eval_runtime": 3.532,
"eval_samples_per_second": 468.288,
"eval_steps_per_second": 29.445,
"step": 3000
},
{
"epoch": 3.69,
"eval_accuracy": 0.9801257179647922,
"eval_f1": 0.9793164031304904,
"eval_loss": 0.07265603542327881,
"eval_precision": 0.9785935162094763,
"eval_recall": 0.9800403588339893,
"eval_runtime": 3.5347,
"eval_samples_per_second": 467.935,
"eval_steps_per_second": 29.423,
"step": 3300
},
{
"epoch": 3.91,
"learning_rate": 1.1592178770949721e-07,
"loss": 0.0501,
"step": 3500
},
{
"epoch": 4.0,
"step": 3580,
"total_flos": 338555299892352.0,
"train_loss": 0.1316441932870023,
"train_runtime": 1079.4521,
"train_samples_per_second": 53.008,
"train_steps_per_second": 3.316
}
],
"max_steps": 3580,
"num_train_epochs": 4,
"total_flos": 338555299892352.0,
"trial_name": null,
"trial_params": null
}
|