File size: 5,983 Bytes
238d171 |
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": 0.5008143186569214,
"best_model_checkpoint": "mobilebert_add_GLUE_Experiment_qqp/checkpoint-19901",
"epoch": 12.0,
"global_step": 34116,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"learning_rate": 4.9e-05,
"loss": 0.6505,
"step": 2843
},
{
"epoch": 1.0,
"eval_accuracy": 0.6320554044026713,
"eval_combined_score": 0.3166319723772454,
"eval_f1": 0.0012085403518195246,
"eval_loss": 0.6498478651046753,
"eval_runtime": 84.4187,
"eval_samples_per_second": 478.923,
"eval_steps_per_second": 3.743,
"step": 2843
},
{
"epoch": 2.0,
"learning_rate": 4.8e-05,
"loss": 0.6474,
"step": 5686
},
{
"epoch": 2.0,
"eval_accuracy": 0.6320554044026713,
"eval_combined_score": 0.3166319723772454,
"eval_f1": 0.0012085403518195246,
"eval_loss": 0.6484191417694092,
"eval_runtime": 84.4998,
"eval_samples_per_second": 478.463,
"eval_steps_per_second": 3.74,
"step": 5686
},
{
"epoch": 3.0,
"learning_rate": 4.7e-05,
"loss": 0.646,
"step": 8529
},
{
"epoch": 3.0,
"eval_accuracy": 0.6322038090526837,
"eval_combined_score": 0.3173094719488563,
"eval_f1": 0.0024151348450288474,
"eval_loss": 0.6478633880615234,
"eval_runtime": 84.5145,
"eval_samples_per_second": 478.38,
"eval_steps_per_second": 3.739,
"step": 8529
},
{
"epoch": 4.0,
"learning_rate": 4.600000000000001e-05,
"loss": 0.5481,
"step": 11372
},
{
"epoch": 4.0,
"eval_accuracy": 0.7486272569873856,
"eval_combined_score": 0.6866867038546203,
"eval_f1": 0.624746150721855,
"eval_loss": 0.5139716267585754,
"eval_runtime": 85.5613,
"eval_samples_per_second": 472.527,
"eval_steps_per_second": 3.693,
"step": 11372
},
{
"epoch": 5.0,
"learning_rate": 4.5e-05,
"loss": 0.4934,
"step": 14215
},
{
"epoch": 5.0,
"eval_accuracy": 0.7529062577294089,
"eval_combined_score": 0.7038665764495293,
"eval_f1": 0.6548268951696496,
"eval_loss": 0.508634090423584,
"eval_runtime": 85.77,
"eval_samples_per_second": 471.377,
"eval_steps_per_second": 3.684,
"step": 14215
},
{
"epoch": 6.0,
"learning_rate": 4.4000000000000006e-05,
"loss": 0.4794,
"step": 17058
},
{
"epoch": 6.0,
"eval_accuracy": 0.7575315359881276,
"eval_combined_score": 0.7051322705269201,
"eval_f1": 0.6527330050657125,
"eval_loss": 0.5043991208076477,
"eval_runtime": 85.6759,
"eval_samples_per_second": 471.895,
"eval_steps_per_second": 3.688,
"step": 17058
},
{
"epoch": 7.0,
"learning_rate": 4.3e-05,
"loss": 0.4708,
"step": 19901
},
{
"epoch": 7.0,
"eval_accuracy": 0.7599802127133317,
"eval_combined_score": 0.7000865097678635,
"eval_f1": 0.6401928068223952,
"eval_loss": 0.5008143186569214,
"eval_runtime": 85.4807,
"eval_samples_per_second": 472.972,
"eval_steps_per_second": 3.697,
"step": 19901
},
{
"epoch": 8.0,
"learning_rate": 4.2e-05,
"loss": 0.4652,
"step": 22744
},
{
"epoch": 8.0,
"eval_accuracy": 0.7618600049468217,
"eval_combined_score": 0.7001156995887954,
"eval_f1": 0.6383713942307692,
"eval_loss": 0.5009844303131104,
"eval_runtime": 85.8727,
"eval_samples_per_second": 470.813,
"eval_steps_per_second": 3.68,
"step": 22744
},
{
"epoch": 9.0,
"learning_rate": 4.1e-05,
"loss": 0.4604,
"step": 25587
},
{
"epoch": 9.0,
"eval_accuracy": 0.7614147909967846,
"eval_combined_score": 0.7051723831239565,
"eval_f1": 0.6489299752511283,
"eval_loss": 0.5014066100120544,
"eval_runtime": 86.3999,
"eval_samples_per_second": 467.94,
"eval_steps_per_second": 3.657,
"step": 25587
},
{
"epoch": 10.0,
"learning_rate": 4e-05,
"loss": 0.4562,
"step": 28430
},
{
"epoch": 10.0,
"eval_accuracy": 0.7599802127133317,
"eval_combined_score": 0.7108365712848488,
"eval_f1": 0.661692929856366,
"eval_loss": 0.5057373642921448,
"eval_runtime": 86.4384,
"eval_samples_per_second": 467.732,
"eval_steps_per_second": 3.656,
"step": 28430
},
{
"epoch": 11.0,
"learning_rate": 3.9000000000000006e-05,
"loss": 0.452,
"step": 31273
},
{
"epoch": 11.0,
"eval_accuracy": 0.7619836754884987,
"eval_combined_score": 0.6991856786662217,
"eval_f1": 0.6363876818439448,
"eval_loss": 0.5101634860038757,
"eval_runtime": 86.4692,
"eval_samples_per_second": 467.565,
"eval_steps_per_second": 3.654,
"step": 31273
},
{
"epoch": 12.0,
"learning_rate": 3.8e-05,
"loss": 0.4476,
"step": 34116
},
{
"epoch": 12.0,
"eval_accuracy": 0.7621815483551818,
"eval_combined_score": 0.712056633324597,
"eval_f1": 0.6619317182940121,
"eval_loss": 0.5301799774169922,
"eval_runtime": 86.4861,
"eval_samples_per_second": 467.474,
"eval_steps_per_second": 3.654,
"step": 34116
},
{
"epoch": 12.0,
"step": 34116,
"total_flos": 1.2915236812514918e+17,
"train_loss": 0.5180756985645023,
"train_runtime": 29413.6297,
"train_samples_per_second": 618.499,
"train_steps_per_second": 4.833
}
],
"max_steps": 142150,
"num_train_epochs": 50,
"total_flos": 1.2915236812514918e+17,
"trial_name": null,
"trial_params": null
}
|