End of training
Browse files- all_results.json +16 -0
- eval_results.json +11 -0
- train_results.json +8 -0
- trainer_state.json +259 -0
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.9981308411214953,
|
| 4 |
+
"eval_f1": 0.9985111662531018,
|
| 5 |
+
"eval_loss": 0.0054078237153589725,
|
| 6 |
+
"eval_precision": 0.998015873015873,
|
| 7 |
+
"eval_recall": 0.9990069513406157,
|
| 8 |
+
"eval_runtime": 185.8991,
|
| 9 |
+
"eval_samples_per_second": 8.634,
|
| 10 |
+
"eval_steps_per_second": 0.274,
|
| 11 |
+
"total_flos": 3.3948696164738826e+18,
|
| 12 |
+
"train_loss": 0.1033598997775784,
|
| 13 |
+
"train_runtime": 25716.3258,
|
| 14 |
+
"train_samples_per_second": 1.685,
|
| 15 |
+
"train_steps_per_second": 0.013
|
| 16 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.9981308411214953,
|
| 4 |
+
"eval_f1": 0.9985111662531018,
|
| 5 |
+
"eval_loss": 0.0054078237153589725,
|
| 6 |
+
"eval_precision": 0.998015873015873,
|
| 7 |
+
"eval_recall": 0.9990069513406157,
|
| 8 |
+
"eval_runtime": 185.8991,
|
| 9 |
+
"eval_samples_per_second": 8.634,
|
| 10 |
+
"eval_steps_per_second": 0.274
|
| 11 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 3.3948696164738826e+18,
|
| 4 |
+
"train_loss": 0.1033598997775784,
|
| 5 |
+
"train_runtime": 25716.3258,
|
| 6 |
+
"train_samples_per_second": 1.685,
|
| 7 |
+
"train_steps_per_second": 0.013
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,259 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9990069513406157,
|
| 3 |
+
"best_model_checkpoint": "Brain_Tumor_Detector_swin/checkpoint-339",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 339,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.09,
|
| 12 |
+
"learning_rate": 1.4705882352941177e-05,
|
| 13 |
+
"loss": 0.6023,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.18,
|
| 18 |
+
"learning_rate": 2.9411764705882354e-05,
|
| 19 |
+
"loss": 0.368,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.27,
|
| 24 |
+
"learning_rate": 4.411764705882353e-05,
|
| 25 |
+
"loss": 0.2555,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.35,
|
| 30 |
+
"learning_rate": 4.9016393442622957e-05,
|
| 31 |
+
"loss": 0.1834,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.44,
|
| 36 |
+
"learning_rate": 4.737704918032787e-05,
|
| 37 |
+
"loss": 0.1955,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.53,
|
| 42 |
+
"learning_rate": 4.5737704918032786e-05,
|
| 43 |
+
"loss": 0.168,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.62,
|
| 48 |
+
"learning_rate": 4.409836065573771e-05,
|
| 49 |
+
"loss": 0.1057,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.71,
|
| 54 |
+
"learning_rate": 4.245901639344262e-05,
|
| 55 |
+
"loss": 0.1323,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.8,
|
| 60 |
+
"learning_rate": 4.081967213114754e-05,
|
| 61 |
+
"loss": 0.0936,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.88,
|
| 66 |
+
"learning_rate": 3.9180327868852464e-05,
|
| 67 |
+
"loss": 0.0855,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.97,
|
| 72 |
+
"learning_rate": 3.754098360655738e-05,
|
| 73 |
+
"loss": 0.079,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.0,
|
| 78 |
+
"eval_accuracy": 0.9881619937694704,
|
| 79 |
+
"eval_f1": 0.9905894006934126,
|
| 80 |
+
"eval_loss": 0.02834915742278099,
|
| 81 |
+
"eval_precision": 0.9881422924901185,
|
| 82 |
+
"eval_recall": 0.9930486593843099,
|
| 83 |
+
"eval_runtime": 203.14,
|
| 84 |
+
"eval_samples_per_second": 7.901,
|
| 85 |
+
"eval_steps_per_second": 0.251,
|
| 86 |
+
"step": 113
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.06,
|
| 90 |
+
"learning_rate": 3.590163934426229e-05,
|
| 91 |
+
"loss": 0.0843,
|
| 92 |
+
"step": 120
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.15,
|
| 96 |
+
"learning_rate": 3.4262295081967214e-05,
|
| 97 |
+
"loss": 0.0651,
|
| 98 |
+
"step": 130
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.24,
|
| 102 |
+
"learning_rate": 3.2622950819672136e-05,
|
| 103 |
+
"loss": 0.0893,
|
| 104 |
+
"step": 140
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.33,
|
| 108 |
+
"learning_rate": 3.098360655737705e-05,
|
| 109 |
+
"loss": 0.093,
|
| 110 |
+
"step": 150
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.42,
|
| 114 |
+
"learning_rate": 2.934426229508197e-05,
|
| 115 |
+
"loss": 0.0666,
|
| 116 |
+
"step": 160
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.5,
|
| 120 |
+
"learning_rate": 2.7704918032786886e-05,
|
| 121 |
+
"loss": 0.0601,
|
| 122 |
+
"step": 170
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.59,
|
| 126 |
+
"learning_rate": 2.6065573770491804e-05,
|
| 127 |
+
"loss": 0.0734,
|
| 128 |
+
"step": 180
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.68,
|
| 132 |
+
"learning_rate": 2.442622950819672e-05,
|
| 133 |
+
"loss": 0.0523,
|
| 134 |
+
"step": 190
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.77,
|
| 138 |
+
"learning_rate": 2.278688524590164e-05,
|
| 139 |
+
"loss": 0.0572,
|
| 140 |
+
"step": 200
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.86,
|
| 144 |
+
"learning_rate": 2.114754098360656e-05,
|
| 145 |
+
"loss": 0.0415,
|
| 146 |
+
"step": 210
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.95,
|
| 150 |
+
"learning_rate": 1.9508196721311475e-05,
|
| 151 |
+
"loss": 0.0575,
|
| 152 |
+
"step": 220
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.0,
|
| 156 |
+
"eval_accuracy": 0.9956386292834891,
|
| 157 |
+
"eval_f1": 0.9965191447041274,
|
| 158 |
+
"eval_loss": 0.01207876205444336,
|
| 159 |
+
"eval_precision": 0.99800796812749,
|
| 160 |
+
"eval_recall": 0.9950347567030785,
|
| 161 |
+
"eval_runtime": 193.9311,
|
| 162 |
+
"eval_samples_per_second": 8.276,
|
| 163 |
+
"eval_steps_per_second": 0.263,
|
| 164 |
+
"step": 226
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.04,
|
| 168 |
+
"learning_rate": 1.7868852459016393e-05,
|
| 169 |
+
"loss": 0.0398,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.12,
|
| 174 |
+
"learning_rate": 1.6229508196721314e-05,
|
| 175 |
+
"loss": 0.0419,
|
| 176 |
+
"step": 240
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.21,
|
| 180 |
+
"learning_rate": 1.4590163934426229e-05,
|
| 181 |
+
"loss": 0.0467,
|
| 182 |
+
"step": 250
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.3,
|
| 186 |
+
"learning_rate": 1.2950819672131149e-05,
|
| 187 |
+
"loss": 0.0502,
|
| 188 |
+
"step": 260
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.39,
|
| 192 |
+
"learning_rate": 1.1311475409836065e-05,
|
| 193 |
+
"loss": 0.0304,
|
| 194 |
+
"step": 270
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.48,
|
| 198 |
+
"learning_rate": 9.672131147540984e-06,
|
| 199 |
+
"loss": 0.0442,
|
| 200 |
+
"step": 280
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.57,
|
| 204 |
+
"learning_rate": 8.032786885245902e-06,
|
| 205 |
+
"loss": 0.0396,
|
| 206 |
+
"step": 290
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.65,
|
| 210 |
+
"learning_rate": 6.393442622950819e-06,
|
| 211 |
+
"loss": 0.0429,
|
| 212 |
+
"step": 300
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.74,
|
| 216 |
+
"learning_rate": 4.754098360655738e-06,
|
| 217 |
+
"loss": 0.0387,
|
| 218 |
+
"step": 310
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.83,
|
| 222 |
+
"learning_rate": 3.114754098360656e-06,
|
| 223 |
+
"loss": 0.0537,
|
| 224 |
+
"step": 320
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.92,
|
| 228 |
+
"learning_rate": 1.4754098360655739e-06,
|
| 229 |
+
"loss": 0.0312,
|
| 230 |
+
"step": 330
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 3.0,
|
| 234 |
+
"eval_accuracy": 0.9981308411214953,
|
| 235 |
+
"eval_f1": 0.9985111662531018,
|
| 236 |
+
"eval_loss": 0.0054078237153589725,
|
| 237 |
+
"eval_precision": 0.998015873015873,
|
| 238 |
+
"eval_recall": 0.9990069513406157,
|
| 239 |
+
"eval_runtime": 193.8262,
|
| 240 |
+
"eval_samples_per_second": 8.281,
|
| 241 |
+
"eval_steps_per_second": 0.263,
|
| 242 |
+
"step": 339
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 3.0,
|
| 246 |
+
"step": 339,
|
| 247 |
+
"total_flos": 3.3948696164738826e+18,
|
| 248 |
+
"train_loss": 0.1033598997775784,
|
| 249 |
+
"train_runtime": 25716.3258,
|
| 250 |
+
"train_samples_per_second": 1.685,
|
| 251 |
+
"train_steps_per_second": 0.013
|
| 252 |
+
}
|
| 253 |
+
],
|
| 254 |
+
"max_steps": 339,
|
| 255 |
+
"num_train_epochs": 3,
|
| 256 |
+
"total_flos": 3.3948696164738826e+18,
|
| 257 |
+
"trial_name": null,
|
| 258 |
+
"trial_params": null
|
| 259 |
+
}
|