End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.5959595959595959,
|
| 4 |
+
"eval_loss": 1.0639073848724365,
|
| 5 |
+
"eval_runtime": 18.6017,
|
| 6 |
+
"eval_samples_per_second": 154.341,
|
| 7 |
+
"eval_steps_per_second": 2.419,
|
| 8 |
+
"total_flos": 1.9269563116415754e+18,
|
| 9 |
+
"train_loss": 1.4176573658933733,
|
| 10 |
+
"train_runtime": 1088.6076,
|
| 11 |
+
"train_samples_per_second": 71.205,
|
| 12 |
+
"train_steps_per_second": 0.278
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.5959595959595959,
|
| 4 |
+
"eval_loss": 1.0639073848724365,
|
| 5 |
+
"eval_runtime": 18.6017,
|
| 6 |
+
"eval_samples_per_second": 154.341,
|
| 7 |
+
"eval_steps_per_second": 2.419
|
| 8 |
+
}
|
runs/Jan07_17-29-20_8d63f48709fd/events.out.tfevents.1673113743.8d63f48709fd.23.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3a4e80a43686facd1902834f11eb0cd2727626f6bd5dfb5dde6da0cdf59c913
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1.9269563116415754e+18,
|
| 4 |
+
"train_loss": 1.4176573658933733,
|
| 5 |
+
"train_runtime": 1088.6076,
|
| 6 |
+
"train_samples_per_second": 71.205,
|
| 7 |
+
"train_steps_per_second": 0.278
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,232 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5959595959595959,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-303",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 303,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.1,
|
| 12 |
+
"learning_rate": 1.6129032258064517e-05,
|
| 13 |
+
"loss": 1.9087,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.2,
|
| 18 |
+
"learning_rate": 3.2258064516129034e-05,
|
| 19 |
+
"loss": 1.8114,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.3,
|
| 24 |
+
"learning_rate": 4.8387096774193554e-05,
|
| 25 |
+
"loss": 1.7686,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.4,
|
| 30 |
+
"learning_rate": 4.834558823529412e-05,
|
| 31 |
+
"loss": 1.6973,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.5,
|
| 36 |
+
"learning_rate": 4.6507352941176475e-05,
|
| 37 |
+
"loss": 1.6149,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.59,
|
| 42 |
+
"learning_rate": 4.4669117647058825e-05,
|
| 43 |
+
"loss": 1.5863,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.69,
|
| 48 |
+
"learning_rate": 4.2830882352941174e-05,
|
| 49 |
+
"loss": 1.5316,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.79,
|
| 54 |
+
"learning_rate": 4.099264705882353e-05,
|
| 55 |
+
"loss": 1.4933,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.89,
|
| 60 |
+
"learning_rate": 3.915441176470588e-05,
|
| 61 |
+
"loss": 1.4753,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.99,
|
| 66 |
+
"learning_rate": 3.731617647058824e-05,
|
| 67 |
+
"loss": 1.4361,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.0,
|
| 72 |
+
"eval_accuracy": 0.5283873214907697,
|
| 73 |
+
"eval_loss": 1.2521955966949463,
|
| 74 |
+
"eval_runtime": 21.0765,
|
| 75 |
+
"eval_samples_per_second": 136.218,
|
| 76 |
+
"eval_steps_per_second": 2.135,
|
| 77 |
+
"step": 101
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 1.09,
|
| 81 |
+
"learning_rate": 3.5477941176470594e-05,
|
| 82 |
+
"loss": 1.4278,
|
| 83 |
+
"step": 110
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.19,
|
| 87 |
+
"learning_rate": 3.363970588235294e-05,
|
| 88 |
+
"loss": 1.413,
|
| 89 |
+
"step": 120
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.29,
|
| 93 |
+
"learning_rate": 3.180147058823529e-05,
|
| 94 |
+
"loss": 1.3808,
|
| 95 |
+
"step": 130
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.39,
|
| 99 |
+
"learning_rate": 2.9963235294117646e-05,
|
| 100 |
+
"loss": 1.3992,
|
| 101 |
+
"step": 140
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.49,
|
| 105 |
+
"learning_rate": 2.8125000000000003e-05,
|
| 106 |
+
"loss": 1.3421,
|
| 107 |
+
"step": 150
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.58,
|
| 111 |
+
"learning_rate": 2.6286764705882356e-05,
|
| 112 |
+
"loss": 1.3373,
|
| 113 |
+
"step": 160
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.68,
|
| 117 |
+
"learning_rate": 2.4448529411764705e-05,
|
| 118 |
+
"loss": 1.3337,
|
| 119 |
+
"step": 170
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.78,
|
| 123 |
+
"learning_rate": 2.261029411764706e-05,
|
| 124 |
+
"loss": 1.3195,
|
| 125 |
+
"step": 180
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.88,
|
| 129 |
+
"learning_rate": 2.0772058823529415e-05,
|
| 130 |
+
"loss": 1.3166,
|
| 131 |
+
"step": 190
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.98,
|
| 135 |
+
"learning_rate": 1.8933823529411765e-05,
|
| 136 |
+
"loss": 1.3156,
|
| 137 |
+
"step": 200
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 2.0,
|
| 141 |
+
"eval_accuracy": 0.5719261581330547,
|
| 142 |
+
"eval_loss": 1.1060255765914917,
|
| 143 |
+
"eval_runtime": 18.9599,
|
| 144 |
+
"eval_samples_per_second": 151.425,
|
| 145 |
+
"eval_steps_per_second": 2.373,
|
| 146 |
+
"step": 202
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.08,
|
| 150 |
+
"learning_rate": 1.7095588235294118e-05,
|
| 151 |
+
"loss": 1.2613,
|
| 152 |
+
"step": 210
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.18,
|
| 156 |
+
"learning_rate": 1.5257352941176473e-05,
|
| 157 |
+
"loss": 1.256,
|
| 158 |
+
"step": 220
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.28,
|
| 162 |
+
"learning_rate": 1.3419117647058824e-05,
|
| 163 |
+
"loss": 1.2718,
|
| 164 |
+
"step": 230
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.38,
|
| 168 |
+
"learning_rate": 1.1580882352941177e-05,
|
| 169 |
+
"loss": 1.2637,
|
| 170 |
+
"step": 240
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.48,
|
| 174 |
+
"learning_rate": 9.74264705882353e-06,
|
| 175 |
+
"loss": 1.2919,
|
| 176 |
+
"step": 250
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.57,
|
| 180 |
+
"learning_rate": 7.904411764705882e-06,
|
| 181 |
+
"loss": 1.2583,
|
| 182 |
+
"step": 260
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.67,
|
| 186 |
+
"learning_rate": 6.066176470588236e-06,
|
| 187 |
+
"loss": 1.2879,
|
| 188 |
+
"step": 270
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.77,
|
| 192 |
+
"learning_rate": 4.227941176470589e-06,
|
| 193 |
+
"loss": 1.2621,
|
| 194 |
+
"step": 280
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.87,
|
| 198 |
+
"learning_rate": 2.389705882352941e-06,
|
| 199 |
+
"loss": 1.2717,
|
| 200 |
+
"step": 290
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.97,
|
| 204 |
+
"learning_rate": 5.514705882352942e-07,
|
| 205 |
+
"loss": 1.2426,
|
| 206 |
+
"step": 300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 3.0,
|
| 210 |
+
"eval_accuracy": 0.5959595959595959,
|
| 211 |
+
"eval_loss": 1.0639073848724365,
|
| 212 |
+
"eval_runtime": 18.6023,
|
| 213 |
+
"eval_samples_per_second": 154.336,
|
| 214 |
+
"eval_steps_per_second": 2.419,
|
| 215 |
+
"step": 303
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 3.0,
|
| 219 |
+
"step": 303,
|
| 220 |
+
"total_flos": 1.9269563116415754e+18,
|
| 221 |
+
"train_loss": 1.4176573658933733,
|
| 222 |
+
"train_runtime": 1088.6076,
|
| 223 |
+
"train_samples_per_second": 71.205,
|
| 224 |
+
"train_steps_per_second": 0.278
|
| 225 |
+
}
|
| 226 |
+
],
|
| 227 |
+
"max_steps": 303,
|
| 228 |
+
"num_train_epochs": 3,
|
| 229 |
+
"total_flos": 1.9269563116415754e+18,
|
| 230 |
+
"trial_name": null,
|
| 231 |
+
"trial_params": null
|
| 232 |
+
}
|