Edison
commited on
Commit
•
65be213
1
Parent(s):
0db06d2
End of training
Browse files- all_results.json +18 -0
- eval_results.json +13 -0
- train_results.json +8 -0
- trainer_state.json +215 -0
all_results.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.7019009565322678,
|
| 4 |
+
"eval_f1": 0.6654891304347826,
|
| 5 |
+
"eval_loss": 0.7599468231201172,
|
| 6 |
+
"eval_precision": 0.7660306537378793,
|
| 7 |
+
"eval_recall": 0.5882776843622388,
|
| 8 |
+
"eval_roc_auc": 0.7028302484311194,
|
| 9 |
+
"eval_runtime": 28.5103,
|
| 10 |
+
"eval_samples": 8259,
|
| 11 |
+
"eval_samples_per_second": 289.685,
|
| 12 |
+
"eval_steps_per_second": 6.454,
|
| 13 |
+
"train_loss": 0.4179859999087242,
|
| 14 |
+
"train_runtime": 3050.636,
|
| 15 |
+
"train_samples": 24774,
|
| 16 |
+
"train_samples_per_second": 81.209,
|
| 17 |
+
"train_steps_per_second": 1.806
|
| 18 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.7019009565322678,
|
| 4 |
+
"eval_f1": 0.6654891304347826,
|
| 5 |
+
"eval_loss": 0.7599468231201172,
|
| 6 |
+
"eval_precision": 0.7660306537378793,
|
| 7 |
+
"eval_recall": 0.5882776843622388,
|
| 8 |
+
"eval_roc_auc": 0.7028302484311194,
|
| 9 |
+
"eval_runtime": 28.5103,
|
| 10 |
+
"eval_samples": 8259,
|
| 11 |
+
"eval_samples_per_second": 289.685,
|
| 12 |
+
"eval_steps_per_second": 6.454
|
| 13 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 0.4179859999087242,
|
| 4 |
+
"train_runtime": 3050.636,
|
| 5 |
+
"train_samples": 24774,
|
| 6 |
+
"train_samples_per_second": 81.209,
|
| 7 |
+
"train_steps_per_second": 1.806
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,215 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 5510,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"learning_rate": 8.101633393829401e-06,
|
| 13 |
+
"loss": 0.6213,
|
| 14 |
+
"step": 551
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_accuracy": 0.6627921055817896,
|
| 19 |
+
"eval_f1": 0.6499937162247078,
|
| 20 |
+
"eval_loss": 0.5820437073707581,
|
| 21 |
+
"eval_precision": 0.6816025303110174,
|
| 22 |
+
"eval_recall": 0.6211866442469373,
|
| 23 |
+
"eval_roc_auc": 0.6631323846234687,
|
| 24 |
+
"eval_runtime": 28.6308,
|
| 25 |
+
"eval_samples_per_second": 288.465,
|
| 26 |
+
"eval_steps_per_second": 6.427,
|
| 27 |
+
"step": 551
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 2.0,
|
| 31 |
+
"learning_rate": 7.203266787658802e-06,
|
| 32 |
+
"loss": 0.5585,
|
| 33 |
+
"step": 1102
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 2.0,
|
| 37 |
+
"eval_accuracy": 0.6689671873108124,
|
| 38 |
+
"eval_f1": 0.5894894894894895,
|
| 39 |
+
"eval_loss": 0.5801684856414795,
|
| 40 |
+
"eval_precision": 0.7861433720464558,
|
| 41 |
+
"eval_recall": 0.47153495075666585,
|
| 42 |
+
"eval_roc_auc": 0.670581928503333,
|
| 43 |
+
"eval_runtime": 28.9285,
|
| 44 |
+
"eval_samples_per_second": 285.497,
|
| 45 |
+
"eval_steps_per_second": 6.361,
|
| 46 |
+
"step": 1102
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 3.0,
|
| 50 |
+
"learning_rate": 6.304900181488204e-06,
|
| 51 |
+
"loss": 0.5109,
|
| 52 |
+
"step": 1653
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 3.0,
|
| 56 |
+
"eval_accuracy": 0.6885821528030028,
|
| 57 |
+
"eval_f1": 0.6392706872370266,
|
| 58 |
+
"eval_loss": 0.5686787962913513,
|
| 59 |
+
"eval_precision": 0.7681159420289855,
|
| 60 |
+
"eval_recall": 0.5474417487388902,
|
| 61 |
+
"eval_roc_auc": 0.689736499369445,
|
| 62 |
+
"eval_runtime": 28.9515,
|
| 63 |
+
"eval_samples_per_second": 285.27,
|
| 64 |
+
"eval_steps_per_second": 6.355,
|
| 65 |
+
"step": 1653
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 4.0,
|
| 69 |
+
"learning_rate": 5.404900181488204e-06,
|
| 70 |
+
"loss": 0.4645,
|
| 71 |
+
"step": 2204
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 4.0,
|
| 75 |
+
"eval_accuracy": 0.6972999152439763,
|
| 76 |
+
"eval_f1": 0.6525847693162868,
|
| 77 |
+
"eval_loss": 0.5875381827354431,
|
| 78 |
+
"eval_precision": 0.7741510056050115,
|
| 79 |
+
"eval_recall": 0.5640163343742494,
|
| 80 |
+
"eval_roc_auc": 0.6983900031246246,
|
| 81 |
+
"eval_runtime": 29.0279,
|
| 82 |
+
"eval_samples_per_second": 284.519,
|
| 83 |
+
"eval_steps_per_second": 6.339,
|
| 84 |
+
"step": 2204
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 5.0,
|
| 88 |
+
"learning_rate": 4.504900181488204e-06,
|
| 89 |
+
"loss": 0.4161,
|
| 90 |
+
"step": 2755
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 5.0,
|
| 94 |
+
"eval_accuracy": 0.709650078702022,
|
| 95 |
+
"eval_f1": 0.6926429120738272,
|
| 96 |
+
"eval_loss": 0.5819324254989624,
|
| 97 |
+
"eval_precision": 0.7425116790327013,
|
| 98 |
+
"eval_recall": 0.6490511650252222,
|
| 99 |
+
"eval_roc_auc": 0.7101456997001111,
|
| 100 |
+
"eval_runtime": 29.0292,
|
| 101 |
+
"eval_samples_per_second": 284.506,
|
| 102 |
+
"eval_steps_per_second": 6.338,
|
| 103 |
+
"step": 2755
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 6.0,
|
| 107 |
+
"learning_rate": 3.6049001814882032e-06,
|
| 108 |
+
"loss": 0.3756,
|
| 109 |
+
"step": 3306
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 6.0,
|
| 113 |
+
"eval_accuracy": 0.705775517617145,
|
| 114 |
+
"eval_f1": 0.6843335931410757,
|
| 115 |
+
"eval_loss": 0.6318923234939575,
|
| 116 |
+
"eval_precision": 0.7451202263083451,
|
| 117 |
+
"eval_recall": 0.6327167907758828,
|
| 118 |
+
"eval_roc_auc": 0.7063730438254414,
|
| 119 |
+
"eval_runtime": 29.1411,
|
| 120 |
+
"eval_samples_per_second": 283.414,
|
| 121 |
+
"eval_steps_per_second": 6.314,
|
| 122 |
+
"step": 3306
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 7.0,
|
| 126 |
+
"learning_rate": 2.706533575317604e-06,
|
| 127 |
+
"loss": 0.3451,
|
| 128 |
+
"step": 3857
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 7.0,
|
| 132 |
+
"eval_accuracy": 0.7025063567017799,
|
| 133 |
+
"eval_f1": 0.6842308186608405,
|
| 134 |
+
"eval_loss": 0.6542169451713562,
|
| 135 |
+
"eval_precision": 0.7357656163626313,
|
| 136 |
+
"eval_recall": 0.6394427095844343,
|
| 137 |
+
"eval_roc_auc": 0.7030221360422172,
|
| 138 |
+
"eval_runtime": 29.0336,
|
| 139 |
+
"eval_samples_per_second": 284.464,
|
| 140 |
+
"eval_steps_per_second": 6.337,
|
| 141 |
+
"step": 3857
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 8.0,
|
| 145 |
+
"learning_rate": 1.8065335753176044e-06,
|
| 146 |
+
"loss": 0.3144,
|
| 147 |
+
"step": 4408
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 8.0,
|
| 151 |
+
"eval_accuracy": 0.701658796464463,
|
| 152 |
+
"eval_f1": 0.6680140123955807,
|
| 153 |
+
"eval_loss": 0.7204051613807678,
|
| 154 |
+
"eval_precision": 0.7606627799938631,
|
| 155 |
+
"eval_recall": 0.5954840259428297,
|
| 156 |
+
"eval_roc_auc": 0.7025271692214148,
|
| 157 |
+
"eval_runtime": 29.0414,
|
| 158 |
+
"eval_samples_per_second": 284.387,
|
| 159 |
+
"eval_steps_per_second": 6.336,
|
| 160 |
+
"step": 4408
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 9.0,
|
| 164 |
+
"learning_rate": 9.065335753176044e-07,
|
| 165 |
+
"loss": 0.2978,
|
| 166 |
+
"step": 4959
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 9.0,
|
| 170 |
+
"eval_accuracy": 0.7032328369051943,
|
| 171 |
+
"eval_f1": 0.6755790866975514,
|
| 172 |
+
"eval_loss": 0.7168041467666626,
|
| 173 |
+
"eval_precision": 0.7523584905660378,
|
| 174 |
+
"eval_recall": 0.6130194571222676,
|
| 175 |
+
"eval_roc_auc": 0.7039706660611338,
|
| 176 |
+
"eval_runtime": 29.0774,
|
| 177 |
+
"eval_samples_per_second": 284.035,
|
| 178 |
+
"eval_steps_per_second": 6.328,
|
| 179 |
+
"step": 4959
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 10.0,
|
| 183 |
+
"learning_rate": 6.533575317604356e-09,
|
| 184 |
+
"loss": 0.2757,
|
| 185 |
+
"step": 5510
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 10.0,
|
| 189 |
+
"eval_accuracy": 0.7019009565322678,
|
| 190 |
+
"eval_f1": 0.6654891304347826,
|
| 191 |
+
"eval_loss": 0.7599468231201172,
|
| 192 |
+
"eval_precision": 0.7660306537378793,
|
| 193 |
+
"eval_recall": 0.5882776843622388,
|
| 194 |
+
"eval_roc_auc": 0.7028302484311194,
|
| 195 |
+
"eval_runtime": 29.101,
|
| 196 |
+
"eval_samples_per_second": 283.804,
|
| 197 |
+
"eval_steps_per_second": 6.323,
|
| 198 |
+
"step": 5510
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 10.0,
|
| 202 |
+
"step": 5510,
|
| 203 |
+
"total_flos": 6.51831328548864e+16,
|
| 204 |
+
"train_loss": 0.4179859999087242,
|
| 205 |
+
"train_runtime": 3050.636,
|
| 206 |
+
"train_samples_per_second": 81.209,
|
| 207 |
+
"train_steps_per_second": 1.806
|
| 208 |
+
}
|
| 209 |
+
],
|
| 210 |
+
"max_steps": 5510,
|
| 211 |
+
"num_train_epochs": 10,
|
| 212 |
+
"total_flos": 6.51831328548864e+16,
|
| 213 |
+
"trial_name": null,
|
| 214 |
+
"trial_params": null
|
| 215 |
+
}
|