Model save
Browse files- all_results.json +8 -0
- pytorch_model.bin +1 -1
- runs/May28_05-43-32_project/events.out.tfevents.1685252633.project.163671.0 +2 -2
- train_results.json +8 -0
- trainer_state.json +269 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.87,
|
| 3 |
+
"total_flos": 5.909979961466413e+18,
|
| 4 |
+
"train_loss": 0.17303451366330447,
|
| 5 |
+
"train_runtime": 18917.559,
|
| 6 |
+
"train_samples_per_second": 4.037,
|
| 7 |
+
"train_steps_per_second": 0.01
|
| 8 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 347601681
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:822495105e3bd4963341c5188e47eb9cd9796d2430f3ec711a30f6eff4a95a0c
|
| 3 |
size 347601681
|
runs/May28_05-43-32_project/events.out.tfevents.1685252633.project.163671.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69c2a45428f3e49887dbff200ecb62c65e87e147ef7666ee4c84f89670985a00
|
| 3 |
+
size 13252
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.87,
|
| 3 |
+
"total_flos": 5.909979961466413e+18,
|
| 4 |
+
"train_loss": 0.17303451366330447,
|
| 5 |
+
"train_runtime": 18917.559,
|
| 6 |
+
"train_samples_per_second": 4.037,
|
| 7 |
+
"train_steps_per_second": 0.01
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,269 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9375490966221524,
|
| 3 |
+
"best_model_checkpoint": "swin-base-patch4-window7-224-in22k-finetuned-brain-tumor-final_10/checkpoint-134",
|
| 4 |
+
"epoch": 9.87012987012987,
|
| 5 |
+
"global_step": 190,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.52,
|
| 12 |
+
"learning_rate": 5.2631578947368424e-05,
|
| 13 |
+
"loss": 1.3428,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.99,
|
| 18 |
+
"eval_accuracy": 0.746661429693637,
|
| 19 |
+
"eval_f1_score": 0.753523551976274,
|
| 20 |
+
"eval_loss": 0.7058983445167542,
|
| 21 |
+
"eval_precision": 0.795110851786091,
|
| 22 |
+
"eval_runtime": 146.233,
|
| 23 |
+
"eval_samples_per_second": 17.411,
|
| 24 |
+
"eval_sensitivity": 0.7464002960313376,
|
| 25 |
+
"eval_specificity": 0.9331964767537173,
|
| 26 |
+
"eval_steps_per_second": 0.178,
|
| 27 |
+
"step": 19
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 1.04,
|
| 31 |
+
"learning_rate": 9.941520467836257e-05,
|
| 32 |
+
"loss": 0.6123,
|
| 33 |
+
"step": 20
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 1.56,
|
| 37 |
+
"learning_rate": 9.35672514619883e-05,
|
| 38 |
+
"loss": 0.3308,
|
| 39 |
+
"step": 30
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.97,
|
| 43 |
+
"eval_accuracy": 0.9183032207384132,
|
| 44 |
+
"eval_f1_score": 0.9193672975136655,
|
| 45 |
+
"eval_loss": 0.23141688108444214,
|
| 46 |
+
"eval_precision": 0.9238848426841779,
|
| 47 |
+
"eval_runtime": 147.0071,
|
| 48 |
+
"eval_samples_per_second": 17.319,
|
| 49 |
+
"eval_sensitivity": 0.919131340710936,
|
| 50 |
+
"eval_specificity": 0.9792488763058318,
|
| 51 |
+
"eval_steps_per_second": 0.177,
|
| 52 |
+
"step": 38
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 2.08,
|
| 56 |
+
"learning_rate": 8.771929824561403e-05,
|
| 57 |
+
"loss": 0.2143,
|
| 58 |
+
"step": 40
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 2.6,
|
| 62 |
+
"learning_rate": 8.187134502923976e-05,
|
| 63 |
+
"loss": 0.1601,
|
| 64 |
+
"step": 50
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 2.96,
|
| 68 |
+
"eval_accuracy": 0.9304791830322073,
|
| 69 |
+
"eval_f1_score": 0.9313957168409166,
|
| 70 |
+
"eval_loss": 0.2024356573820114,
|
| 71 |
+
"eval_precision": 0.934946390389874,
|
| 72 |
+
"eval_runtime": 143.4571,
|
| 73 |
+
"eval_samples_per_second": 17.747,
|
| 74 |
+
"eval_sensitivity": 0.9306462457126936,
|
| 75 |
+
"eval_specificity": 0.982384433175612,
|
| 76 |
+
"eval_steps_per_second": 0.181,
|
| 77 |
+
"step": 57
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 3.12,
|
| 81 |
+
"learning_rate": 7.602339181286549e-05,
|
| 82 |
+
"loss": 0.1393,
|
| 83 |
+
"step": 60
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 3.64,
|
| 87 |
+
"learning_rate": 7.017543859649122e-05,
|
| 88 |
+
"loss": 0.0976,
|
| 89 |
+
"step": 70
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 4.0,
|
| 93 |
+
"eval_accuracy": 0.8904163393558523,
|
| 94 |
+
"eval_f1_score": 0.8942865194972388,
|
| 95 |
+
"eval_loss": 0.33763808012008667,
|
| 96 |
+
"eval_precision": 0.912649070740494,
|
| 97 |
+
"eval_runtime": 144.2099,
|
| 98 |
+
"eval_samples_per_second": 17.655,
|
| 99 |
+
"eval_sensitivity": 0.8930050036912869,
|
| 100 |
+
"eval_specificity": 0.9724007687462364,
|
| 101 |
+
"eval_steps_per_second": 0.18,
|
| 102 |
+
"step": 77
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 4.16,
|
| 106 |
+
"learning_rate": 6.432748538011695e-05,
|
| 107 |
+
"loss": 0.0794,
|
| 108 |
+
"step": 80
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 4.68,
|
| 112 |
+
"learning_rate": 5.847953216374269e-05,
|
| 113 |
+
"loss": 0.0585,
|
| 114 |
+
"step": 90
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 4.99,
|
| 118 |
+
"eval_accuracy": 0.8829536527886881,
|
| 119 |
+
"eval_f1_score": 0.8853131975385626,
|
| 120 |
+
"eval_loss": 0.3893134295940399,
|
| 121 |
+
"eval_precision": 0.9115099416703121,
|
| 122 |
+
"eval_runtime": 143.4213,
|
| 123 |
+
"eval_samples_per_second": 17.752,
|
| 124 |
+
"eval_sensitivity": 0.8854325807966088,
|
| 125 |
+
"eval_specificity": 0.970608364089214,
|
| 126 |
+
"eval_steps_per_second": 0.181,
|
| 127 |
+
"step": 96
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 5.19,
|
| 131 |
+
"learning_rate": 5.2631578947368424e-05,
|
| 132 |
+
"loss": 0.0503,
|
| 133 |
+
"step": 100
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 5.71,
|
| 137 |
+
"learning_rate": 4.678362573099415e-05,
|
| 138 |
+
"loss": 0.0432,
|
| 139 |
+
"step": 110
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 5.97,
|
| 143 |
+
"eval_accuracy": 0.9214454045561665,
|
| 144 |
+
"eval_f1_score": 0.9239050681424754,
|
| 145 |
+
"eval_loss": 0.2559237778186798,
|
| 146 |
+
"eval_precision": 0.9329922456780788,
|
| 147 |
+
"eval_runtime": 146.8194,
|
| 148 |
+
"eval_samples_per_second": 17.341,
|
| 149 |
+
"eval_sensitivity": 0.9236729550899102,
|
| 150 |
+
"eval_specificity": 0.9802185130829542,
|
| 151 |
+
"eval_steps_per_second": 0.177,
|
| 152 |
+
"step": 115
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 6.23,
|
| 156 |
+
"learning_rate": 4.093567251461988e-05,
|
| 157 |
+
"loss": 0.0306,
|
| 158 |
+
"step": 120
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 6.75,
|
| 162 |
+
"learning_rate": 3.508771929824561e-05,
|
| 163 |
+
"loss": 0.0313,
|
| 164 |
+
"step": 130
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 6.96,
|
| 168 |
+
"eval_accuracy": 0.9375490966221524,
|
| 169 |
+
"eval_f1_score": 0.9383165022369235,
|
| 170 |
+
"eval_loss": 0.21751664578914642,
|
| 171 |
+
"eval_precision": 0.9451238954076366,
|
| 172 |
+
"eval_runtime": 145.2374,
|
| 173 |
+
"eval_samples_per_second": 17.53,
|
| 174 |
+
"eval_sensitivity": 0.9381317542954977,
|
| 175 |
+
"eval_specificity": 0.9843172049410979,
|
| 176 |
+
"eval_steps_per_second": 0.179,
|
| 177 |
+
"step": 134
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 7.27,
|
| 181 |
+
"learning_rate": 2.9239766081871346e-05,
|
| 182 |
+
"loss": 0.0297,
|
| 183 |
+
"step": 140
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 7.79,
|
| 187 |
+
"learning_rate": 2.3391812865497074e-05,
|
| 188 |
+
"loss": 0.0176,
|
| 189 |
+
"step": 150
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 8.0,
|
| 193 |
+
"eval_accuracy": 0.9312647289866457,
|
| 194 |
+
"eval_f1_score": 0.9325621318348738,
|
| 195 |
+
"eval_loss": 0.2309039980173111,
|
| 196 |
+
"eval_precision": 0.9386195901124972,
|
| 197 |
+
"eval_runtime": 143.3628,
|
| 198 |
+
"eval_samples_per_second": 17.759,
|
| 199 |
+
"eval_sensitivity": 0.9320322207801762,
|
| 200 |
+
"eval_specificity": 0.9826772307398953,
|
| 201 |
+
"eval_steps_per_second": 0.181,
|
| 202 |
+
"step": 154
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 8.31,
|
| 206 |
+
"learning_rate": 1.7543859649122806e-05,
|
| 207 |
+
"loss": 0.0143,
|
| 208 |
+
"step": 160
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 8.83,
|
| 212 |
+
"learning_rate": 1.1695906432748537e-05,
|
| 213 |
+
"loss": 0.0152,
|
| 214 |
+
"step": 170
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 8.99,
|
| 218 |
+
"eval_accuracy": 0.9328358208955224,
|
| 219 |
+
"eval_f1_score": 0.9339352133488944,
|
| 220 |
+
"eval_loss": 0.23582719266414642,
|
| 221 |
+
"eval_precision": 0.9416083548413121,
|
| 222 |
+
"eval_runtime": 143.3217,
|
| 223 |
+
"eval_samples_per_second": 17.764,
|
| 224 |
+
"eval_sensitivity": 0.933574485515878,
|
| 225 |
+
"eval_specificity": 0.9831257832351848,
|
| 226 |
+
"eval_steps_per_second": 0.181,
|
| 227 |
+
"step": 173
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 9.35,
|
| 231 |
+
"learning_rate": 5.8479532163742686e-06,
|
| 232 |
+
"loss": 0.0115,
|
| 233 |
+
"step": 180
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 9.87,
|
| 237 |
+
"learning_rate": 0.0,
|
| 238 |
+
"loss": 0.0089,
|
| 239 |
+
"step": 190
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 9.87,
|
| 243 |
+
"eval_accuracy": 0.9359780047132757,
|
| 244 |
+
"eval_f1_score": 0.9373742931343466,
|
| 245 |
+
"eval_loss": 0.21163314580917358,
|
| 246 |
+
"eval_precision": 0.9436683740999858,
|
| 247 |
+
"eval_runtime": 143.1747,
|
| 248 |
+
"eval_samples_per_second": 17.782,
|
| 249 |
+
"eval_sensitivity": 0.937217001650051,
|
| 250 |
+
"eval_specificity": 0.9838991466840242,
|
| 251 |
+
"eval_steps_per_second": 0.182,
|
| 252 |
+
"step": 190
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 9.87,
|
| 256 |
+
"step": 190,
|
| 257 |
+
"total_flos": 5.909979961466413e+18,
|
| 258 |
+
"train_loss": 0.17303451366330447,
|
| 259 |
+
"train_runtime": 18917.559,
|
| 260 |
+
"train_samples_per_second": 4.037,
|
| 261 |
+
"train_steps_per_second": 0.01
|
| 262 |
+
}
|
| 263 |
+
],
|
| 264 |
+
"max_steps": 190,
|
| 265 |
+
"num_train_epochs": 10,
|
| 266 |
+
"total_flos": 5.909979961466413e+18,
|
| 267 |
+
"trial_name": null,
|
| 268 |
+
"trial_params": null
|
| 269 |
+
}
|