File size: 5,736 Bytes
453db45 |
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 |
{
"best_metric": 2.2508649826049805,
"best_model_checkpoint": "hBERTv1_new_pretrain_w_init_48_ver2_stsb/checkpoint-540",
"epoch": 11.0,
"eval_steps": 500,
"global_step": 990,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"learning_rate": 3.733333333333334e-05,
"loss": 2.3716,
"step": 90
},
{
"epoch": 1.0,
"eval_combined_score": 0.09954876427078817,
"eval_loss": 2.4198310375213623,
"eval_pearson": 0.1235081678469039,
"eval_runtime": 7.919,
"eval_samples_per_second": 189.417,
"eval_spearmanr": 0.07558936069467244,
"eval_steps_per_second": 3.031,
"step": 90
},
{
"epoch": 2.0,
"learning_rate": 3.466666666666667e-05,
"loss": 2.1648,
"step": 180
},
{
"epoch": 2.0,
"eval_combined_score": 0.059901129208988935,
"eval_loss": 2.421804904937744,
"eval_pearson": 0.05915702497074951,
"eval_runtime": 7.9228,
"eval_samples_per_second": 189.328,
"eval_spearmanr": 0.060645233447228365,
"eval_steps_per_second": 3.029,
"step": 180
},
{
"epoch": 3.0,
"learning_rate": 3.2000000000000005e-05,
"loss": 2.1915,
"step": 270
},
{
"epoch": 3.0,
"eval_combined_score": 0.10509199818892286,
"eval_loss": 2.5305275917053223,
"eval_pearson": 0.11429814840247612,
"eval_runtime": 7.9275,
"eval_samples_per_second": 189.214,
"eval_spearmanr": 0.09588584797536959,
"eval_steps_per_second": 3.027,
"step": 270
},
{
"epoch": 4.0,
"learning_rate": 2.9333333333333333e-05,
"loss": 2.1855,
"step": 360
},
{
"epoch": 4.0,
"eval_combined_score": 0.10434278350873159,
"eval_loss": 2.4912118911743164,
"eval_pearson": 0.11175276310573931,
"eval_runtime": 7.9356,
"eval_samples_per_second": 189.022,
"eval_spearmanr": 0.09693280391172387,
"eval_steps_per_second": 3.024,
"step": 360
},
{
"epoch": 5.0,
"learning_rate": 2.6666666666666667e-05,
"loss": 2.1858,
"step": 450
},
{
"epoch": 5.0,
"eval_combined_score": 0.10867629190279143,
"eval_loss": 2.353940963745117,
"eval_pearson": 0.11303164261998537,
"eval_runtime": 7.8971,
"eval_samples_per_second": 189.944,
"eval_spearmanr": 0.10432094118559751,
"eval_steps_per_second": 3.039,
"step": 450
},
{
"epoch": 6.0,
"learning_rate": 2.4e-05,
"loss": 2.1818,
"step": 540
},
{
"epoch": 6.0,
"eval_combined_score": 0.12661347630524494,
"eval_loss": 2.2508649826049805,
"eval_pearson": 0.12848032160953568,
"eval_runtime": 7.8875,
"eval_samples_per_second": 190.175,
"eval_spearmanr": 0.12474663100095418,
"eval_steps_per_second": 3.043,
"step": 540
},
{
"epoch": 7.0,
"learning_rate": 2.1333333333333335e-05,
"loss": 2.2562,
"step": 630
},
{
"epoch": 7.0,
"eval_combined_score": 0.10085775212511634,
"eval_loss": 2.330181360244751,
"eval_pearson": 0.10432624437463486,
"eval_runtime": 7.8945,
"eval_samples_per_second": 190.005,
"eval_spearmanr": 0.09738925987559782,
"eval_steps_per_second": 3.04,
"step": 630
},
{
"epoch": 8.0,
"learning_rate": 1.866666666666667e-05,
"loss": 2.2299,
"step": 720
},
{
"epoch": 8.0,
"eval_combined_score": 0.17028955228719306,
"eval_loss": 2.3748996257781982,
"eval_pearson": 0.1984074571487062,
"eval_runtime": 7.8956,
"eval_samples_per_second": 189.98,
"eval_spearmanr": 0.14217164742567992,
"eval_steps_per_second": 3.04,
"step": 720
},
{
"epoch": 9.0,
"learning_rate": 1.6000000000000003e-05,
"loss": 2.0676,
"step": 810
},
{
"epoch": 9.0,
"eval_combined_score": 0.13143073261190957,
"eval_loss": 2.3883156776428223,
"eval_pearson": 0.12998858260155782,
"eval_runtime": 7.9009,
"eval_samples_per_second": 189.851,
"eval_spearmanr": 0.13287288262226135,
"eval_steps_per_second": 3.038,
"step": 810
},
{
"epoch": 10.0,
"learning_rate": 1.3333333333333333e-05,
"loss": 1.926,
"step": 900
},
{
"epoch": 10.0,
"eval_combined_score": 0.12458804638022844,
"eval_loss": 2.588383674621582,
"eval_pearson": 0.12590757541676778,
"eval_runtime": 7.9206,
"eval_samples_per_second": 189.38,
"eval_spearmanr": 0.1232685173436891,
"eval_steps_per_second": 3.03,
"step": 900
},
{
"epoch": 11.0,
"learning_rate": 1.0666666666666667e-05,
"loss": 1.7701,
"step": 990
},
{
"epoch": 11.0,
"eval_combined_score": 0.1984576696603884,
"eval_loss": 2.3776161670684814,
"eval_pearson": 0.19105961985541245,
"eval_runtime": 7.9395,
"eval_samples_per_second": 188.928,
"eval_spearmanr": 0.20585571946536435,
"eval_steps_per_second": 3.023,
"step": 990
},
{
"epoch": 11.0,
"step": 990,
"total_flos": 9365417243967488.0,
"train_loss": 2.139166490959399,
"train_runtime": 1123.3813,
"train_samples_per_second": 76.764,
"train_steps_per_second": 1.202
}
],
"logging_steps": 1,
"max_steps": 1350,
"num_train_epochs": 15,
"save_steps": 500,
"total_flos": 9365417243967488.0,
"trial_name": null,
"trial_params": null
}
|