End of training
Browse files- all_results.json +17 -0
- eval_results.json +12 -0
- train_results.json +8 -0
- trainer_state.json +283 -0
all_results.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.9642789042140724,
|
| 4 |
+
"eval_f1": 0.664968152866242,
|
| 5 |
+
"eval_loss": 0.21516220271587372,
|
| 6 |
+
"eval_precision": 0.7111716621253406,
|
| 7 |
+
"eval_recall": 0.6244019138755981,
|
| 8 |
+
"eval_runtime": 1.5873,
|
| 9 |
+
"eval_samples": 1009,
|
| 10 |
+
"eval_samples_per_second": 635.669,
|
| 11 |
+
"eval_steps_per_second": 0.63,
|
| 12 |
+
"train_loss": 0.06299664935580006,
|
| 13 |
+
"train_runtime": 158.2675,
|
| 14 |
+
"train_samples": 3394,
|
| 15 |
+
"train_samples_per_second": 214.447,
|
| 16 |
+
"train_steps_per_second": 3.412
|
| 17 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.9642789042140724,
|
| 4 |
+
"eval_f1": 0.664968152866242,
|
| 5 |
+
"eval_loss": 0.21516220271587372,
|
| 6 |
+
"eval_precision": 0.7111716621253406,
|
| 7 |
+
"eval_recall": 0.6244019138755981,
|
| 8 |
+
"eval_runtime": 1.5873,
|
| 9 |
+
"eval_samples": 1009,
|
| 10 |
+
"eval_samples_per_second": 635.669,
|
| 11 |
+
"eval_steps_per_second": 0.63
|
| 12 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 0.06299664935580006,
|
| 4 |
+
"train_runtime": 158.2675,
|
| 5 |
+
"train_samples": 3394,
|
| 6 |
+
"train_samples_per_second": 214.447,
|
| 7 |
+
"train_steps_per_second": 3.412
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,283 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.664968152866242,
|
| 3 |
+
"best_model_checkpoint": "twitter-roberta-base-dec2021-WNUT/checkpoint-500",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 540,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.46,
|
| 12 |
+
"eval_accuracy": 0.9241085616220682,
|
| 13 |
+
"eval_f1": 0.055077452667814115,
|
| 14 |
+
"eval_loss": 0.28182554244995117,
|
| 15 |
+
"eval_precision": 0.09815950920245399,
|
| 16 |
+
"eval_recall": 0.03827751196172249,
|
| 17 |
+
"eval_runtime": 1.4976,
|
| 18 |
+
"eval_samples_per_second": 673.746,
|
| 19 |
+
"eval_steps_per_second": 0.668,
|
| 20 |
+
"step": 25
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.93,
|
| 24 |
+
"eval_accuracy": 0.9480073730375643,
|
| 25 |
+
"eval_f1": 0.5254470426409903,
|
| 26 |
+
"eval_loss": 0.21579432487487793,
|
| 27 |
+
"eval_precision": 0.6181229773462783,
|
| 28 |
+
"eval_recall": 0.4569377990430622,
|
| 29 |
+
"eval_runtime": 1.5062,
|
| 30 |
+
"eval_samples_per_second": 669.914,
|
| 31 |
+
"eval_steps_per_second": 0.664,
|
| 32 |
+
"step": 50
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.39,
|
| 36 |
+
"eval_accuracy": 0.955507531939236,
|
| 37 |
+
"eval_f1": 0.5940199335548173,
|
| 38 |
+
"eval_loss": 0.19296418130397797,
|
| 39 |
+
"eval_precision": 0.6681614349775785,
|
| 40 |
+
"eval_recall": 0.534688995215311,
|
| 41 |
+
"eval_runtime": 1.4928,
|
| 42 |
+
"eval_samples_per_second": 675.914,
|
| 43 |
+
"eval_steps_per_second": 0.67,
|
| 44 |
+
"step": 75
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.85,
|
| 48 |
+
"eval_accuracy": 0.9593847327273883,
|
| 49 |
+
"eval_f1": 0.6078557630392788,
|
| 50 |
+
"eval_loss": 0.17283694446086884,
|
| 51 |
+
"eval_precision": 0.6582984658298466,
|
| 52 |
+
"eval_recall": 0.5645933014354066,
|
| 53 |
+
"eval_runtime": 1.4931,
|
| 54 |
+
"eval_samples_per_second": 675.766,
|
| 55 |
+
"eval_steps_per_second": 0.67,
|
| 56 |
+
"step": 100
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 2.31,
|
| 60 |
+
"eval_accuracy": 0.9619271594737177,
|
| 61 |
+
"eval_f1": 0.6314398943196828,
|
| 62 |
+
"eval_loss": 0.17873725295066833,
|
| 63 |
+
"eval_precision": 0.7050147492625368,
|
| 64 |
+
"eval_recall": 0.5717703349282297,
|
| 65 |
+
"eval_runtime": 1.5276,
|
| 66 |
+
"eval_samples_per_second": 660.504,
|
| 67 |
+
"eval_steps_per_second": 0.655,
|
| 68 |
+
"step": 125
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 2.78,
|
| 72 |
+
"eval_accuracy": 0.958749126040806,
|
| 73 |
+
"eval_f1": 0.5993174061433448,
|
| 74 |
+
"eval_loss": 0.20510223507881165,
|
| 75 |
+
"eval_precision": 0.6979332273449921,
|
| 76 |
+
"eval_recall": 0.5251196172248804,
|
| 77 |
+
"eval_runtime": 1.5126,
|
| 78 |
+
"eval_samples_per_second": 667.078,
|
| 79 |
+
"eval_steps_per_second": 0.661,
|
| 80 |
+
"step": 150
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 3.24,
|
| 84 |
+
"eval_accuracy": 0.9620542808110342,
|
| 85 |
+
"eval_f1": 0.6500981033355134,
|
| 86 |
+
"eval_loss": 0.17545387148857117,
|
| 87 |
+
"eval_precision": 0.7171717171717171,
|
| 88 |
+
"eval_recall": 0.5944976076555024,
|
| 89 |
+
"eval_runtime": 1.5007,
|
| 90 |
+
"eval_samples_per_second": 672.361,
|
| 91 |
+
"eval_steps_per_second": 0.666,
|
| 92 |
+
"step": 175
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 3.7,
|
| 96 |
+
"eval_accuracy": 0.9644695862200471,
|
| 97 |
+
"eval_f1": 0.6608150470219436,
|
| 98 |
+
"eval_loss": 0.17198117077350616,
|
| 99 |
+
"eval_precision": 0.69433465085639,
|
| 100 |
+
"eval_recall": 0.6303827751196173,
|
| 101 |
+
"eval_runtime": 1.5311,
|
| 102 |
+
"eval_samples_per_second": 659.017,
|
| 103 |
+
"eval_steps_per_second": 0.653,
|
| 104 |
+
"step": 200
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 4.17,
|
| 108 |
+
"eval_accuracy": 0.9645967075573635,
|
| 109 |
+
"eval_f1": 0.6730401529636711,
|
| 110 |
+
"eval_loss": 0.18734638392925262,
|
| 111 |
+
"eval_precision": 0.7203274215552524,
|
| 112 |
+
"eval_recall": 0.631578947368421,
|
| 113 |
+
"eval_runtime": 1.812,
|
| 114 |
+
"eval_samples_per_second": 556.831,
|
| 115 |
+
"eval_steps_per_second": 0.552,
|
| 116 |
+
"step": 225
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 4.63,
|
| 120 |
+
"eval_accuracy": 0.9638339795334647,
|
| 121 |
+
"eval_f1": 0.6544535691724572,
|
| 122 |
+
"eval_loss": 0.17807357013225555,
|
| 123 |
+
"eval_precision": 0.6934404283801874,
|
| 124 |
+
"eval_recall": 0.6196172248803827,
|
| 125 |
+
"eval_runtime": 1.5526,
|
| 126 |
+
"eval_samples_per_second": 649.864,
|
| 127 |
+
"eval_steps_per_second": 0.644,
|
| 128 |
+
"step": 250
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 5.09,
|
| 132 |
+
"eval_accuracy": 0.9631348121782242,
|
| 133 |
+
"eval_f1": 0.6577437858508605,
|
| 134 |
+
"eval_loss": 0.19528818130493164,
|
| 135 |
+
"eval_precision": 0.703956343792633,
|
| 136 |
+
"eval_recall": 0.6172248803827751,
|
| 137 |
+
"eval_runtime": 1.5217,
|
| 138 |
+
"eval_samples_per_second": 663.053,
|
| 139 |
+
"eval_steps_per_second": 0.657,
|
| 140 |
+
"step": 275
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 5.56,
|
| 144 |
+
"eval_accuracy": 0.964215343545414,
|
| 145 |
+
"eval_f1": 0.6738991703892788,
|
| 146 |
+
"eval_loss": 0.1952667236328125,
|
| 147 |
+
"eval_precision": 0.7222982216142271,
|
| 148 |
+
"eval_recall": 0.631578947368421,
|
| 149 |
+
"eval_runtime": 1.5375,
|
| 150 |
+
"eval_samples_per_second": 656.259,
|
| 151 |
+
"eval_steps_per_second": 0.65,
|
| 152 |
+
"step": 300
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 6.02,
|
| 156 |
+
"eval_accuracy": 0.9647873895633382,
|
| 157 |
+
"eval_f1": 0.6728855721393034,
|
| 158 |
+
"eval_loss": 0.18392899632453918,
|
| 159 |
+
"eval_precision": 0.7007772020725389,
|
| 160 |
+
"eval_recall": 0.6471291866028708,
|
| 161 |
+
"eval_runtime": 1.541,
|
| 162 |
+
"eval_samples_per_second": 654.776,
|
| 163 |
+
"eval_steps_per_second": 0.649,
|
| 164 |
+
"step": 325
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 6.48,
|
| 168 |
+
"eval_accuracy": 0.9650416322379711,
|
| 169 |
+
"eval_f1": 0.6771752837326608,
|
| 170 |
+
"eval_loss": 0.19951151311397552,
|
| 171 |
+
"eval_precision": 0.716,
|
| 172 |
+
"eval_recall": 0.6423444976076556,
|
| 173 |
+
"eval_runtime": 1.5364,
|
| 174 |
+
"eval_samples_per_second": 656.733,
|
| 175 |
+
"eval_steps_per_second": 0.651,
|
| 176 |
+
"step": 350
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 6.94,
|
| 180 |
+
"eval_accuracy": 0.9639611008707811,
|
| 181 |
+
"eval_f1": 0.6675274370561652,
|
| 182 |
+
"eval_loss": 0.20560267567634583,
|
| 183 |
+
"eval_precision": 0.7251051893408135,
|
| 184 |
+
"eval_recall": 0.618421052631579,
|
| 185 |
+
"eval_runtime": 1.5238,
|
| 186 |
+
"eval_samples_per_second": 662.157,
|
| 187 |
+
"eval_steps_per_second": 0.656,
|
| 188 |
+
"step": 375
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 7.41,
|
| 192 |
+
"eval_accuracy": 0.9639611008707811,
|
| 193 |
+
"eval_f1": 0.6615776081424937,
|
| 194 |
+
"eval_loss": 0.20440098643302917,
|
| 195 |
+
"eval_precision": 0.7065217391304348,
|
| 196 |
+
"eval_recall": 0.6220095693779905,
|
| 197 |
+
"eval_runtime": 1.529,
|
| 198 |
+
"eval_samples_per_second": 659.91,
|
| 199 |
+
"eval_steps_per_second": 0.654,
|
| 200 |
+
"step": 400
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 7.87,
|
| 204 |
+
"eval_accuracy": 0.9650416322379711,
|
| 205 |
+
"eval_f1": 0.6776440785307156,
|
| 206 |
+
"eval_loss": 0.20423652231693268,
|
| 207 |
+
"eval_precision": 0.7200538358008075,
|
| 208 |
+
"eval_recall": 0.6399521531100478,
|
| 209 |
+
"eval_runtime": 1.5395,
|
| 210 |
+
"eval_samples_per_second": 655.429,
|
| 211 |
+
"eval_steps_per_second": 0.65,
|
| 212 |
+
"step": 425
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 8.33,
|
| 216 |
+
"eval_accuracy": 0.9637704188648064,
|
| 217 |
+
"eval_f1": 0.6722472633612363,
|
| 218 |
+
"eval_loss": 0.22472669184207916,
|
| 219 |
+
"eval_precision": 0.7280334728033473,
|
| 220 |
+
"eval_recall": 0.6244019138755981,
|
| 221 |
+
"eval_runtime": 1.5443,
|
| 222 |
+
"eval_samples_per_second": 653.377,
|
| 223 |
+
"eval_steps_per_second": 0.648,
|
| 224 |
+
"step": 450
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 8.8,
|
| 228 |
+
"eval_accuracy": 0.9648509502319964,
|
| 229 |
+
"eval_f1": 0.6741713570981863,
|
| 230 |
+
"eval_loss": 0.20600706338882446,
|
| 231 |
+
"eval_precision": 0.7064220183486238,
|
| 232 |
+
"eval_recall": 0.6447368421052632,
|
| 233 |
+
"eval_runtime": 1.5361,
|
| 234 |
+
"eval_samples_per_second": 656.868,
|
| 235 |
+
"eval_steps_per_second": 0.651,
|
| 236 |
+
"step": 475
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 9.26,
|
| 240 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 241 |
+
"loss": 0.0675,
|
| 242 |
+
"step": 500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 9.26,
|
| 246 |
+
"eval_accuracy": 0.9642789042140724,
|
| 247 |
+
"eval_f1": 0.664968152866242,
|
| 248 |
+
"eval_loss": 0.21516220271587372,
|
| 249 |
+
"eval_precision": 0.7111716621253406,
|
| 250 |
+
"eval_recall": 0.6244019138755981,
|
| 251 |
+
"eval_runtime": 1.7855,
|
| 252 |
+
"eval_samples_per_second": 565.098,
|
| 253 |
+
"eval_steps_per_second": 0.56,
|
| 254 |
+
"step": 500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 9.72,
|
| 258 |
+
"eval_accuracy": 0.9649780715693129,
|
| 259 |
+
"eval_f1": 0.6770573566084789,
|
| 260 |
+
"eval_loss": 0.20861834287643433,
|
| 261 |
+
"eval_precision": 0.70703125,
|
| 262 |
+
"eval_recall": 0.6495215311004785,
|
| 263 |
+
"eval_runtime": 1.5457,
|
| 264 |
+
"eval_samples_per_second": 652.767,
|
| 265 |
+
"eval_steps_per_second": 0.647,
|
| 266 |
+
"step": 525
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 10.0,
|
| 270 |
+
"step": 540,
|
| 271 |
+
"total_flos": 1009327449452316.0,
|
| 272 |
+
"train_loss": 0.06299664935580006,
|
| 273 |
+
"train_runtime": 158.2675,
|
| 274 |
+
"train_samples_per_second": 214.447,
|
| 275 |
+
"train_steps_per_second": 3.412
|
| 276 |
+
}
|
| 277 |
+
],
|
| 278 |
+
"max_steps": 540,
|
| 279 |
+
"num_train_epochs": 10,
|
| 280 |
+
"total_flos": 1009327449452316.0,
|
| 281 |
+
"trial_name": null,
|
| 282 |
+
"trial_params": null
|
| 283 |
+
}
|