Commit
•
f3eb9f6
1
Parent(s):
1fc9b8a
End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.9702970297029703,
|
| 4 |
+
"eval_loss": 0.113469697535038,
|
| 5 |
+
"eval_runtime": 19.6577,
|
| 6 |
+
"eval_samples_per_second": 41.103,
|
| 7 |
+
"eval_steps_per_second": 1.323,
|
| 8 |
+
"total_flos": 9.517308690649375e+17,
|
| 9 |
+
"train_loss": 0.11255148539417668,
|
| 10 |
+
"train_runtime": 3845.8146,
|
| 11 |
+
"train_samples_per_second": 9.453,
|
| 12 |
+
"train_steps_per_second": 0.074
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.9702970297029703,
|
| 4 |
+
"eval_loss": 0.113469697535038,
|
| 5 |
+
"eval_runtime": 19.6577,
|
| 6 |
+
"eval_samples_per_second": 41.103,
|
| 7 |
+
"eval_steps_per_second": 1.323
|
| 8 |
+
}
|
runs/Feb08_07-27-11_b7f9e0f97031/events.out.tfevents.1707384260.b7f9e0f97031.1264.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:086e866da823080532c633c8ce943cdb64ee258eb6a4e16259d6b4d6e58430b2
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"total_flos": 9.517308690649375e+17,
|
| 4 |
+
"train_loss": 0.11255148539417668,
|
| 5 |
+
"train_runtime": 3845.8146,
|
| 6 |
+
"train_samples_per_second": 9.453,
|
| 7 |
+
"train_steps_per_second": 0.074
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,241 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9702970297029703,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-285",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 285,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.18,
|
| 13 |
+
"learning_rate": 1.7241379310344828e-05,
|
| 14 |
+
"loss": 0.4028,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.35,
|
| 19 |
+
"learning_rate": 3.4482758620689657e-05,
|
| 20 |
+
"loss": 0.3212,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.53,
|
| 25 |
+
"learning_rate": 4.9804687500000004e-05,
|
| 26 |
+
"loss": 0.2394,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.7,
|
| 31 |
+
"learning_rate": 4.78515625e-05,
|
| 32 |
+
"loss": 0.1597,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.88,
|
| 37 |
+
"learning_rate": 4.58984375e-05,
|
| 38 |
+
"loss": 0.1503,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.0,
|
| 43 |
+
"eval_accuracy": 0.9381188118811881,
|
| 44 |
+
"eval_loss": 0.22037547826766968,
|
| 45 |
+
"eval_runtime": 522.4952,
|
| 46 |
+
"eval_samples_per_second": 1.546,
|
| 47 |
+
"eval_steps_per_second": 0.05,
|
| 48 |
+
"step": 57
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 1.05,
|
| 52 |
+
"learning_rate": 4.3945312500000005e-05,
|
| 53 |
+
"loss": 0.1178,
|
| 54 |
+
"step": 60
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.23,
|
| 58 |
+
"learning_rate": 4.1992187500000003e-05,
|
| 59 |
+
"loss": 0.1253,
|
| 60 |
+
"step": 70
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 1.4,
|
| 64 |
+
"learning_rate": 4.00390625e-05,
|
| 65 |
+
"loss": 0.107,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.58,
|
| 70 |
+
"learning_rate": 3.80859375e-05,
|
| 71 |
+
"loss": 0.1339,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.75,
|
| 76 |
+
"learning_rate": 3.6132812500000005e-05,
|
| 77 |
+
"loss": 0.1155,
|
| 78 |
+
"step": 100
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 1.93,
|
| 82 |
+
"learning_rate": 3.41796875e-05,
|
| 83 |
+
"loss": 0.1349,
|
| 84 |
+
"step": 110
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.0,
|
| 88 |
+
"eval_accuracy": 0.9566831683168316,
|
| 89 |
+
"eval_loss": 0.13936376571655273,
|
| 90 |
+
"eval_runtime": 15.2812,
|
| 91 |
+
"eval_samples_per_second": 52.875,
|
| 92 |
+
"eval_steps_per_second": 1.701,
|
| 93 |
+
"step": 114
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 2.11,
|
| 97 |
+
"learning_rate": 3.22265625e-05,
|
| 98 |
+
"loss": 0.0974,
|
| 99 |
+
"step": 120
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.28,
|
| 103 |
+
"learning_rate": 3.02734375e-05,
|
| 104 |
+
"loss": 0.0716,
|
| 105 |
+
"step": 130
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 2.46,
|
| 109 |
+
"learning_rate": 2.83203125e-05,
|
| 110 |
+
"loss": 0.1008,
|
| 111 |
+
"step": 140
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 2.63,
|
| 115 |
+
"learning_rate": 2.63671875e-05,
|
| 116 |
+
"loss": 0.0843,
|
| 117 |
+
"step": 150
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 2.81,
|
| 121 |
+
"learning_rate": 2.44140625e-05,
|
| 122 |
+
"loss": 0.0835,
|
| 123 |
+
"step": 160
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 2.98,
|
| 127 |
+
"learning_rate": 2.24609375e-05,
|
| 128 |
+
"loss": 0.0552,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.0,
|
| 133 |
+
"eval_accuracy": 0.9678217821782178,
|
| 134 |
+
"eval_loss": 0.14300712943077087,
|
| 135 |
+
"eval_runtime": 15.5346,
|
| 136 |
+
"eval_samples_per_second": 52.013,
|
| 137 |
+
"eval_steps_per_second": 1.674,
|
| 138 |
+
"step": 171
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 3.16,
|
| 142 |
+
"learning_rate": 2.05078125e-05,
|
| 143 |
+
"loss": 0.0625,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.33,
|
| 148 |
+
"learning_rate": 1.85546875e-05,
|
| 149 |
+
"loss": 0.0632,
|
| 150 |
+
"step": 190
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 3.51,
|
| 154 |
+
"learning_rate": 1.66015625e-05,
|
| 155 |
+
"loss": 0.0723,
|
| 156 |
+
"step": 200
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 3.68,
|
| 160 |
+
"learning_rate": 1.4648437500000001e-05,
|
| 161 |
+
"loss": 0.0616,
|
| 162 |
+
"step": 210
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 3.86,
|
| 166 |
+
"learning_rate": 1.2695312500000001e-05,
|
| 167 |
+
"loss": 0.0722,
|
| 168 |
+
"step": 220
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 4.0,
|
| 172 |
+
"eval_accuracy": 0.9628712871287128,
|
| 173 |
+
"eval_loss": 0.15681138634681702,
|
| 174 |
+
"eval_runtime": 15.4019,
|
| 175 |
+
"eval_samples_per_second": 52.461,
|
| 176 |
+
"eval_steps_per_second": 1.688,
|
| 177 |
+
"step": 228
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 4.04,
|
| 181 |
+
"learning_rate": 1.0742187500000001e-05,
|
| 182 |
+
"loss": 0.0662,
|
| 183 |
+
"step": 230
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 4.21,
|
| 187 |
+
"learning_rate": 8.789062500000001e-06,
|
| 188 |
+
"loss": 0.0586,
|
| 189 |
+
"step": 240
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.39,
|
| 193 |
+
"learning_rate": 6.8359375e-06,
|
| 194 |
+
"loss": 0.0761,
|
| 195 |
+
"step": 250
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 4.56,
|
| 199 |
+
"learning_rate": 4.8828125e-06,
|
| 200 |
+
"loss": 0.0635,
|
| 201 |
+
"step": 260
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 4.74,
|
| 205 |
+
"learning_rate": 2.9296875e-06,
|
| 206 |
+
"loss": 0.036,
|
| 207 |
+
"step": 270
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 4.91,
|
| 211 |
+
"learning_rate": 9.765625e-07,
|
| 212 |
+
"loss": 0.0523,
|
| 213 |
+
"step": 280
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 5.0,
|
| 217 |
+
"eval_accuracy": 0.9702970297029703,
|
| 218 |
+
"eval_loss": 0.113469697535038,
|
| 219 |
+
"eval_runtime": 15.3074,
|
| 220 |
+
"eval_samples_per_second": 52.785,
|
| 221 |
+
"eval_steps_per_second": 1.699,
|
| 222 |
+
"step": 285
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 5.0,
|
| 226 |
+
"step": 285,
|
| 227 |
+
"total_flos": 9.517308690649375e+17,
|
| 228 |
+
"train_loss": 0.11255148539417668,
|
| 229 |
+
"train_runtime": 3845.8146,
|
| 230 |
+
"train_samples_per_second": 9.453,
|
| 231 |
+
"train_steps_per_second": 0.074
|
| 232 |
+
}
|
| 233 |
+
],
|
| 234 |
+
"logging_steps": 10,
|
| 235 |
+
"max_steps": 285,
|
| 236 |
+
"num_train_epochs": 5,
|
| 237 |
+
"save_steps": 500,
|
| 238 |
+
"total_flos": 9.517308690649375e+17,
|
| 239 |
+
"trial_name": null,
|
| 240 |
+
"trial_params": null
|
| 241 |
+
}
|