Commit
•
5edf317
1
Parent(s):
db205e4
End of training
Browse files- README.md +3 -3
- all_results.json +11 -11
- eval_results.json +6 -6
- runs/May10_13-31-13_85d2b2bb10f2/events.out.tfevents.1715348077.85d2b2bb10f2.34.1 +3 -0
- train_results.json +6 -6
- trainer_state.json +47 -789
README.md
CHANGED
|
@@ -22,7 +22,7 @@ model-index:
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
-
value: 0.
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 0.
|
| 36 |
-
- Accuracy: 0.
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
+
value: 0.8660130718954249
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.2897
|
| 36 |
+
- Accuracy: 0.8660
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
-
"total_flos":
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second": 0.
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 2.79,
|
| 3 |
+
"eval_accuracy": 0.8660130718954249,
|
| 4 |
+
"eval_loss": 0.28969407081604004,
|
| 5 |
+
"eval_runtime": 2.0116,
|
| 6 |
+
"eval_samples_per_second": 152.115,
|
| 7 |
+
"eval_steps_per_second": 2.486,
|
| 8 |
+
"total_flos": 1.9084961608228454e+17,
|
| 9 |
+
"train_loss": 0.4112351576487223,
|
| 10 |
+
"train_runtime": 186.8069,
|
| 11 |
+
"train_samples_per_second": 44.179,
|
| 12 |
+
"train_steps_per_second": 0.161
|
| 13 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 2.79,
|
| 3 |
+
"eval_accuracy": 0.8660130718954249,
|
| 4 |
+
"eval_loss": 0.28969407081604004,
|
| 5 |
+
"eval_runtime": 2.0116,
|
| 6 |
+
"eval_samples_per_second": 152.115,
|
| 7 |
+
"eval_steps_per_second": 2.486
|
| 8 |
}
|
runs/May10_13-31-13_85d2b2bb10f2/events.out.tfevents.1715348077.85d2b2bb10f2.34.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ffdbfeb295a15d885e2b951bb2fadf4e412db2a817e7499a73c33078d097eba9
|
| 3 |
+
size 405
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 2.79,
|
| 3 |
+
"total_flos": 1.9084961608228454e+17,
|
| 4 |
+
"train_loss": 0.4112351576487223,
|
| 5 |
+
"train_runtime": 186.8069,
|
| 6 |
+
"train_samples_per_second": 44.179,
|
| 7 |
+
"train_steps_per_second": 0.161
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,819 +1,77 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 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.
|
| 13 |
-
"grad_norm":
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss": 0.
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch": 0.
|
| 20 |
-
"
|
| 21 |
-
"
|
| 22 |
-
"
|
| 23 |
-
"
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
"epoch": 0.3,
|
| 27 |
-
"grad_norm": 5.400581359863281,
|
| 28 |
-
"learning_rate": 3e-05,
|
| 29 |
-
"loss": 0.1062,
|
| 30 |
-
"step": 30
|
| 31 |
-
},
|
| 32 |
-
{
|
| 33 |
-
"epoch": 0.4,
|
| 34 |
-
"grad_norm": 5.083698749542236,
|
| 35 |
-
"learning_rate": 4e-05,
|
| 36 |
-
"loss": 0.074,
|
| 37 |
-
"step": 40
|
| 38 |
-
},
|
| 39 |
-
{
|
| 40 |
-
"epoch": 0.5,
|
| 41 |
-
"grad_norm": 2.7988944053649902,
|
| 42 |
-
"learning_rate": 5e-05,
|
| 43 |
-
"loss": 0.0639,
|
| 44 |
-
"step": 50
|
| 45 |
-
},
|
| 46 |
-
{
|
| 47 |
-
"epoch": 0.6,
|
| 48 |
-
"grad_norm": 1.6099319458007812,
|
| 49 |
-
"learning_rate": 6e-05,
|
| 50 |
-
"loss": 0.0508,
|
| 51 |
-
"step": 60
|
| 52 |
-
},
|
| 53 |
-
{
|
| 54 |
-
"epoch": 0.7,
|
| 55 |
-
"grad_norm": 2.6441915035247803,
|
| 56 |
-
"learning_rate": 7e-05,
|
| 57 |
-
"loss": 0.0524,
|
| 58 |
-
"step": 70
|
| 59 |
-
},
|
| 60 |
-
{
|
| 61 |
-
"epoch": 0.8,
|
| 62 |
-
"grad_norm": 5.100390434265137,
|
| 63 |
-
"learning_rate": 8e-05,
|
| 64 |
-
"loss": 0.06,
|
| 65 |
-
"step": 80
|
| 66 |
-
},
|
| 67 |
-
{
|
| 68 |
-
"epoch": 0.9,
|
| 69 |
-
"grad_norm": 4.311460971832275,
|
| 70 |
-
"learning_rate": 9e-05,
|
| 71 |
-
"loss": 0.0424,
|
| 72 |
-
"step": 90
|
| 73 |
-
},
|
| 74 |
-
{
|
| 75 |
-
"epoch": 1.0,
|
| 76 |
-
"grad_norm": 2.94564151763916,
|
| 77 |
-
"learning_rate": 0.0001,
|
| 78 |
-
"loss": 0.0511,
|
| 79 |
-
"step": 100
|
| 80 |
-
},
|
| 81 |
-
{
|
| 82 |
-
"epoch": 1.0,
|
| 83 |
-
"eval_accuracy": 0.8720196353436185,
|
| 84 |
-
"eval_loss": 0.5181019306182861,
|
| 85 |
-
"eval_runtime": 38.2631,
|
| 86 |
-
"eval_samples_per_second": 74.537,
|
| 87 |
-
"eval_steps_per_second": 1.176,
|
| 88 |
-
"step": 100
|
| 89 |
-
},
|
| 90 |
-
{
|
| 91 |
-
"epoch": 1.1,
|
| 92 |
-
"grad_norm": 4.313048839569092,
|
| 93 |
-
"learning_rate": 9.888888888888889e-05,
|
| 94 |
-
"loss": 0.0887,
|
| 95 |
-
"step": 110
|
| 96 |
-
},
|
| 97 |
-
{
|
| 98 |
-
"epoch": 1.2,
|
| 99 |
-
"grad_norm": 5.640860557556152,
|
| 100 |
-
"learning_rate": 9.777777777777778e-05,
|
| 101 |
-
"loss": 0.084,
|
| 102 |
-
"step": 120
|
| 103 |
-
},
|
| 104 |
-
{
|
| 105 |
-
"epoch": 1.3,
|
| 106 |
-
"grad_norm": 2.4771900177001953,
|
| 107 |
-
"learning_rate": 9.666666666666667e-05,
|
| 108 |
-
"loss": 0.0879,
|
| 109 |
-
"step": 130
|
| 110 |
-
},
|
| 111 |
-
{
|
| 112 |
-
"epoch": 1.4,
|
| 113 |
-
"grad_norm": 7.712289810180664,
|
| 114 |
-
"learning_rate": 9.555555555555557e-05,
|
| 115 |
-
"loss": 0.1231,
|
| 116 |
-
"step": 140
|
| 117 |
-
},
|
| 118 |
-
{
|
| 119 |
-
"epoch": 1.5,
|
| 120 |
-
"grad_norm": 7.235645771026611,
|
| 121 |
-
"learning_rate": 9.444444444444444e-05,
|
| 122 |
-
"loss": 0.143,
|
| 123 |
-
"step": 150
|
| 124 |
-
},
|
| 125 |
-
{
|
| 126 |
-
"epoch": 1.6,
|
| 127 |
-
"grad_norm": 11.080587387084961,
|
| 128 |
-
"learning_rate": 9.333333333333334e-05,
|
| 129 |
-
"loss": 0.1804,
|
| 130 |
-
"step": 160
|
| 131 |
-
},
|
| 132 |
-
{
|
| 133 |
-
"epoch": 1.7,
|
| 134 |
-
"grad_norm": 4.359196662902832,
|
| 135 |
-
"learning_rate": 9.222222222222223e-05,
|
| 136 |
-
"loss": 0.1894,
|
| 137 |
-
"step": 170
|
| 138 |
-
},
|
| 139 |
-
{
|
| 140 |
-
"epoch": 1.8,
|
| 141 |
-
"grad_norm": 4.214484214782715,
|
| 142 |
-
"learning_rate": 9.111111111111112e-05,
|
| 143 |
-
"loss": 0.1589,
|
| 144 |
-
"step": 180
|
| 145 |
-
},
|
| 146 |
-
{
|
| 147 |
-
"epoch": 1.9,
|
| 148 |
-
"grad_norm": 6.100831508636475,
|
| 149 |
-
"learning_rate": 9e-05,
|
| 150 |
-
"loss": 0.1317,
|
| 151 |
-
"step": 190
|
| 152 |
-
},
|
| 153 |
-
{
|
| 154 |
-
"epoch": 2.0,
|
| 155 |
-
"grad_norm": 4.592179298400879,
|
| 156 |
-
"learning_rate": 8.888888888888889e-05,
|
| 157 |
-
"loss": 0.1166,
|
| 158 |
-
"step": 200
|
| 159 |
-
},
|
| 160 |
-
{
|
| 161 |
-
"epoch": 2.0,
|
| 162 |
-
"eval_accuracy": 0.8716690042075736,
|
| 163 |
-
"eval_loss": 0.4709436595439911,
|
| 164 |
-
"eval_runtime": 38.3291,
|
| 165 |
-
"eval_samples_per_second": 74.408,
|
| 166 |
-
"eval_steps_per_second": 1.174,
|
| 167 |
-
"step": 200
|
| 168 |
-
},
|
| 169 |
-
{
|
| 170 |
-
"epoch": 2.09,
|
| 171 |
-
"grad_norm": 9.383784294128418,
|
| 172 |
-
"learning_rate": 8.777777777777778e-05,
|
| 173 |
-
"loss": 0.1538,
|
| 174 |
-
"step": 210
|
| 175 |
-
},
|
| 176 |
-
{
|
| 177 |
-
"epoch": 2.19,
|
| 178 |
-
"grad_norm": 5.486557960510254,
|
| 179 |
-
"learning_rate": 8.666666666666667e-05,
|
| 180 |
-
"loss": 0.1292,
|
| 181 |
-
"step": 220
|
| 182 |
-
},
|
| 183 |
-
{
|
| 184 |
-
"epoch": 2.29,
|
| 185 |
-
"grad_norm": 5.093433856964111,
|
| 186 |
-
"learning_rate": 8.555555555555556e-05,
|
| 187 |
-
"loss": 0.1411,
|
| 188 |
-
"step": 230
|
| 189 |
-
},
|
| 190 |
-
{
|
| 191 |
-
"epoch": 2.39,
|
| 192 |
-
"grad_norm": 6.046931266784668,
|
| 193 |
-
"learning_rate": 8.444444444444444e-05,
|
| 194 |
-
"loss": 0.1502,
|
| 195 |
-
"step": 240
|
| 196 |
-
},
|
| 197 |
-
{
|
| 198 |
-
"epoch": 2.49,
|
| 199 |
-
"grad_norm": 6.943304061889648,
|
| 200 |
-
"learning_rate": 8.333333333333334e-05,
|
| 201 |
-
"loss": 0.1298,
|
| 202 |
-
"step": 250
|
| 203 |
},
|
| 204 |
{
|
| 205 |
-
"epoch":
|
| 206 |
-
"grad_norm":
|
| 207 |
-
"learning_rate":
|
| 208 |
-
"loss": 0.
|
| 209 |
-
"step":
|
| 210 |
},
|
| 211 |
{
|
| 212 |
-
"epoch":
|
| 213 |
-
"
|
| 214 |
-
"
|
| 215 |
-
"
|
| 216 |
-
"
|
|
|
|
|
|
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"epoch": 2.79,
|
| 220 |
-
"grad_norm":
|
| 221 |
-
"learning_rate": 8e-05,
|
| 222 |
-
"loss": 0.1353,
|
| 223 |
-
"step": 280
|
| 224 |
-
},
|
| 225 |
-
{
|
| 226 |
-
"epoch": 2.89,
|
| 227 |
-
"grad_norm": 6.133541584014893,
|
| 228 |
-
"learning_rate": 7.88888888888889e-05,
|
| 229 |
-
"loss": 0.1252,
|
| 230 |
-
"step": 290
|
| 231 |
-
},
|
| 232 |
-
{
|
| 233 |
-
"epoch": 2.99,
|
| 234 |
-
"grad_norm": 5.344182014465332,
|
| 235 |
-
"learning_rate": 7.777777777777778e-05,
|
| 236 |
-
"loss": 0.1189,
|
| 237 |
-
"step": 300
|
| 238 |
-
},
|
| 239 |
-
{
|
| 240 |
-
"epoch": 2.99,
|
| 241 |
-
"eval_accuracy": 0.8839410939691444,
|
| 242 |
-
"eval_loss": 0.41620370745658875,
|
| 243 |
-
"eval_runtime": 38.187,
|
| 244 |
-
"eval_samples_per_second": 74.685,
|
| 245 |
-
"eval_steps_per_second": 1.178,
|
| 246 |
-
"step": 300
|
| 247 |
-
},
|
| 248 |
-
{
|
| 249 |
-
"epoch": 3.09,
|
| 250 |
-
"grad_norm": 5.3231706619262695,
|
| 251 |
-
"learning_rate": 7.666666666666667e-05,
|
| 252 |
-
"loss": 0.11,
|
| 253 |
-
"step": 310
|
| 254 |
-
},
|
| 255 |
-
{
|
| 256 |
-
"epoch": 3.19,
|
| 257 |
-
"grad_norm": 6.189892292022705,
|
| 258 |
-
"learning_rate": 7.555555555555556e-05,
|
| 259 |
-
"loss": 0.1151,
|
| 260 |
-
"step": 320
|
| 261 |
-
},
|
| 262 |
-
{
|
| 263 |
-
"epoch": 3.29,
|
| 264 |
-
"grad_norm": 4.102895259857178,
|
| 265 |
-
"learning_rate": 7.444444444444444e-05,
|
| 266 |
-
"loss": 0.1023,
|
| 267 |
-
"step": 330
|
| 268 |
-
},
|
| 269 |
-
{
|
| 270 |
-
"epoch": 3.39,
|
| 271 |
-
"grad_norm": 4.935023784637451,
|
| 272 |
-
"learning_rate": 7.333333333333333e-05,
|
| 273 |
-
"loss": 0.1298,
|
| 274 |
-
"step": 340
|
| 275 |
-
},
|
| 276 |
-
{
|
| 277 |
-
"epoch": 3.49,
|
| 278 |
-
"grad_norm": 6.158393859863281,
|
| 279 |
-
"learning_rate": 7.222222222222222e-05,
|
| 280 |
-
"loss": 0.1382,
|
| 281 |
-
"step": 350
|
| 282 |
-
},
|
| 283 |
-
{
|
| 284 |
-
"epoch": 3.59,
|
| 285 |
-
"grad_norm": 4.13533878326416,
|
| 286 |
-
"learning_rate": 7.111111111111112e-05,
|
| 287 |
-
"loss": 0.1526,
|
| 288 |
-
"step": 360
|
| 289 |
-
},
|
| 290 |
-
{
|
| 291 |
-
"epoch": 3.69,
|
| 292 |
-
"grad_norm": 2.808582067489624,
|
| 293 |
-
"learning_rate": 7e-05,
|
| 294 |
-
"loss": 0.1106,
|
| 295 |
-
"step": 370
|
| 296 |
-
},
|
| 297 |
-
{
|
| 298 |
-
"epoch": 3.79,
|
| 299 |
-
"grad_norm": 4.059571266174316,
|
| 300 |
-
"learning_rate": 6.88888888888889e-05,
|
| 301 |
-
"loss": 0.1221,
|
| 302 |
-
"step": 380
|
| 303 |
-
},
|
| 304 |
-
{
|
| 305 |
-
"epoch": 3.89,
|
| 306 |
-
"grad_norm": 4.626064777374268,
|
| 307 |
-
"learning_rate": 6.777777777777778e-05,
|
| 308 |
-
"loss": 0.1303,
|
| 309 |
-
"step": 390
|
| 310 |
-
},
|
| 311 |
-
{
|
| 312 |
-
"epoch": 3.99,
|
| 313 |
-
"grad_norm": 6.2365031242370605,
|
| 314 |
-
"learning_rate": 6.666666666666667e-05,
|
| 315 |
-
"loss": 0.1306,
|
| 316 |
-
"step": 400
|
| 317 |
-
},
|
| 318 |
-
{
|
| 319 |
-
"epoch": 4.0,
|
| 320 |
-
"eval_accuracy": 0.8807854137447405,
|
| 321 |
-
"eval_loss": 0.4251408874988556,
|
| 322 |
-
"eval_runtime": 38.3771,
|
| 323 |
-
"eval_samples_per_second": 74.315,
|
| 324 |
-
"eval_steps_per_second": 1.173,
|
| 325 |
-
"step": 401
|
| 326 |
-
},
|
| 327 |
-
{
|
| 328 |
-
"epoch": 4.09,
|
| 329 |
-
"grad_norm": 4.386157035827637,
|
| 330 |
-
"learning_rate": 6.555555555555556e-05,
|
| 331 |
-
"loss": 0.1149,
|
| 332 |
-
"step": 410
|
| 333 |
-
},
|
| 334 |
-
{
|
| 335 |
-
"epoch": 4.19,
|
| 336 |
-
"grad_norm": 5.805418968200684,
|
| 337 |
-
"learning_rate": 6.444444444444446e-05,
|
| 338 |
-
"loss": 0.0997,
|
| 339 |
-
"step": 420
|
| 340 |
-
},
|
| 341 |
-
{
|
| 342 |
-
"epoch": 4.29,
|
| 343 |
-
"grad_norm": 7.228994846343994,
|
| 344 |
-
"learning_rate": 6.333333333333333e-05,
|
| 345 |
-
"loss": 0.1262,
|
| 346 |
-
"step": 430
|
| 347 |
-
},
|
| 348 |
-
{
|
| 349 |
-
"epoch": 4.39,
|
| 350 |
-
"grad_norm": 8.70606517791748,
|
| 351 |
-
"learning_rate": 6.222222222222222e-05,
|
| 352 |
-
"loss": 0.1422,
|
| 353 |
-
"step": 440
|
| 354 |
-
},
|
| 355 |
-
{
|
| 356 |
-
"epoch": 4.49,
|
| 357 |
-
"grad_norm": 5.861635208129883,
|
| 358 |
-
"learning_rate": 6.111111111111112e-05,
|
| 359 |
-
"loss": 0.1128,
|
| 360 |
-
"step": 450
|
| 361 |
-
},
|
| 362 |
-
{
|
| 363 |
-
"epoch": 4.59,
|
| 364 |
-
"grad_norm": 5.075900554656982,
|
| 365 |
-
"learning_rate": 6e-05,
|
| 366 |
-
"loss": 0.1142,
|
| 367 |
-
"step": 460
|
| 368 |
-
},
|
| 369 |
-
{
|
| 370 |
-
"epoch": 4.69,
|
| 371 |
-
"grad_norm": 5.3067498207092285,
|
| 372 |
-
"learning_rate": 5.8888888888888896e-05,
|
| 373 |
-
"loss": 0.1359,
|
| 374 |
-
"step": 470
|
| 375 |
-
},
|
| 376 |
-
{
|
| 377 |
-
"epoch": 4.79,
|
| 378 |
-
"grad_norm": 3.890895366668701,
|
| 379 |
-
"learning_rate": 5.7777777777777776e-05,
|
| 380 |
-
"loss": 0.1173,
|
| 381 |
-
"step": 480
|
| 382 |
-
},
|
| 383 |
-
{
|
| 384 |
-
"epoch": 4.89,
|
| 385 |
-
"grad_norm": 5.006656646728516,
|
| 386 |
-
"learning_rate": 5.666666666666667e-05,
|
| 387 |
-
"loss": 0.1087,
|
| 388 |
-
"step": 490
|
| 389 |
-
},
|
| 390 |
-
{
|
| 391 |
-
"epoch": 4.99,
|
| 392 |
-
"grad_norm": 4.467653274536133,
|
| 393 |
-
"learning_rate": 5.555555555555556e-05,
|
| 394 |
-
"loss": 0.1063,
|
| 395 |
-
"step": 500
|
| 396 |
-
},
|
| 397 |
-
{
|
| 398 |
-
"epoch": 5.0,
|
| 399 |
-
"eval_accuracy": 0.8888499298737728,
|
| 400 |
-
"eval_loss": 0.41856977343559265,
|
| 401 |
-
"eval_runtime": 37.7302,
|
| 402 |
-
"eval_samples_per_second": 75.589,
|
| 403 |
-
"eval_steps_per_second": 1.193,
|
| 404 |
-
"step": 501
|
| 405 |
-
},
|
| 406 |
-
{
|
| 407 |
-
"epoch": 5.09,
|
| 408 |
-
"grad_norm": 6.331502914428711,
|
| 409 |
-
"learning_rate": 5.4444444444444446e-05,
|
| 410 |
-
"loss": 0.1132,
|
| 411 |
-
"step": 510
|
| 412 |
-
},
|
| 413 |
-
{
|
| 414 |
-
"epoch": 5.19,
|
| 415 |
-
"grad_norm": 6.853649139404297,
|
| 416 |
-
"learning_rate": 5.333333333333333e-05,
|
| 417 |
-
"loss": 0.1256,
|
| 418 |
-
"step": 520
|
| 419 |
-
},
|
| 420 |
-
{
|
| 421 |
-
"epoch": 5.29,
|
| 422 |
-
"grad_norm": 6.621553421020508,
|
| 423 |
-
"learning_rate": 5.222222222222223e-05,
|
| 424 |
-
"loss": 0.121,
|
| 425 |
-
"step": 530
|
| 426 |
-
},
|
| 427 |
-
{
|
| 428 |
-
"epoch": 5.39,
|
| 429 |
-
"grad_norm": 5.279974460601807,
|
| 430 |
-
"learning_rate": 5.111111111111111e-05,
|
| 431 |
-
"loss": 0.1119,
|
| 432 |
-
"step": 540
|
| 433 |
-
},
|
| 434 |
-
{
|
| 435 |
-
"epoch": 5.49,
|
| 436 |
-
"grad_norm": 6.570211410522461,
|
| 437 |
-
"learning_rate": 5e-05,
|
| 438 |
-
"loss": 0.1067,
|
| 439 |
-
"step": 550
|
| 440 |
-
},
|
| 441 |
-
{
|
| 442 |
-
"epoch": 5.59,
|
| 443 |
-
"grad_norm": 4.3511199951171875,
|
| 444 |
-
"learning_rate": 4.888888888888889e-05,
|
| 445 |
-
"loss": 0.1202,
|
| 446 |
-
"step": 560
|
| 447 |
-
},
|
| 448 |
-
{
|
| 449 |
-
"epoch": 5.69,
|
| 450 |
-
"grad_norm": 4.396121978759766,
|
| 451 |
-
"learning_rate": 4.7777777777777784e-05,
|
| 452 |
-
"loss": 0.1041,
|
| 453 |
-
"step": 570
|
| 454 |
-
},
|
| 455 |
-
{
|
| 456 |
-
"epoch": 5.79,
|
| 457 |
-
"grad_norm": 5.755546569824219,
|
| 458 |
-
"learning_rate": 4.666666666666667e-05,
|
| 459 |
-
"loss": 0.1144,
|
| 460 |
-
"step": 580
|
| 461 |
-
},
|
| 462 |
-
{
|
| 463 |
-
"epoch": 5.89,
|
| 464 |
-
"grad_norm": 4.096261501312256,
|
| 465 |
-
"learning_rate": 4.555555555555556e-05,
|
| 466 |
-
"loss": 0.109,
|
| 467 |
-
"step": 590
|
| 468 |
-
},
|
| 469 |
-
{
|
| 470 |
-
"epoch": 5.99,
|
| 471 |
-
"grad_norm": 7.311570644378662,
|
| 472 |
-
"learning_rate": 4.4444444444444447e-05,
|
| 473 |
-
"loss": 0.1188,
|
| 474 |
-
"step": 600
|
| 475 |
-
},
|
| 476 |
-
{
|
| 477 |
-
"epoch": 6.0,
|
| 478 |
-
"eval_accuracy": 0.8842917251051894,
|
| 479 |
-
"eval_loss": 0.4293117821216583,
|
| 480 |
-
"eval_runtime": 36.9523,
|
| 481 |
-
"eval_samples_per_second": 77.181,
|
| 482 |
-
"eval_steps_per_second": 1.218,
|
| 483 |
-
"step": 601
|
| 484 |
-
},
|
| 485 |
-
{
|
| 486 |
-
"epoch": 6.08,
|
| 487 |
-
"grad_norm": 3.6034762859344482,
|
| 488 |
-
"learning_rate": 4.3333333333333334e-05,
|
| 489 |
-
"loss": 0.1118,
|
| 490 |
-
"step": 610
|
| 491 |
-
},
|
| 492 |
-
{
|
| 493 |
-
"epoch": 6.18,
|
| 494 |
-
"grad_norm": 5.649061679840088,
|
| 495 |
-
"learning_rate": 4.222222222222222e-05,
|
| 496 |
-
"loss": 0.1005,
|
| 497 |
-
"step": 620
|
| 498 |
-
},
|
| 499 |
-
{
|
| 500 |
-
"epoch": 6.28,
|
| 501 |
-
"grad_norm": 6.543485164642334,
|
| 502 |
-
"learning_rate": 4.111111111111111e-05,
|
| 503 |
-
"loss": 0.1012,
|
| 504 |
-
"step": 630
|
| 505 |
-
},
|
| 506 |
-
{
|
| 507 |
-
"epoch": 6.38,
|
| 508 |
-
"grad_norm": 5.104783058166504,
|
| 509 |
-
"learning_rate": 4e-05,
|
| 510 |
-
"loss": 0.0862,
|
| 511 |
-
"step": 640
|
| 512 |
-
},
|
| 513 |
-
{
|
| 514 |
-
"epoch": 6.48,
|
| 515 |
-
"grad_norm": 7.024726867675781,
|
| 516 |
-
"learning_rate": 3.888888888888889e-05,
|
| 517 |
-
"loss": 0.1063,
|
| 518 |
-
"step": 650
|
| 519 |
-
},
|
| 520 |
-
{
|
| 521 |
-
"epoch": 6.58,
|
| 522 |
-
"grad_norm": 3.0800111293792725,
|
| 523 |
-
"learning_rate": 3.777777777777778e-05,
|
| 524 |
-
"loss": 0.0974,
|
| 525 |
-
"step": 660
|
| 526 |
-
},
|
| 527 |
-
{
|
| 528 |
-
"epoch": 6.68,
|
| 529 |
-
"grad_norm": 8.348942756652832,
|
| 530 |
-
"learning_rate": 3.6666666666666666e-05,
|
| 531 |
-
"loss": 0.1079,
|
| 532 |
-
"step": 670
|
| 533 |
-
},
|
| 534 |
-
{
|
| 535 |
-
"epoch": 6.78,
|
| 536 |
-
"grad_norm": 5.644587516784668,
|
| 537 |
-
"learning_rate": 3.555555555555556e-05,
|
| 538 |
-
"loss": 0.0917,
|
| 539 |
-
"step": 680
|
| 540 |
-
},
|
| 541 |
-
{
|
| 542 |
-
"epoch": 6.88,
|
| 543 |
-
"grad_norm": 6.3199872970581055,
|
| 544 |
-
"learning_rate": 3.444444444444445e-05,
|
| 545 |
-
"loss": 0.1043,
|
| 546 |
-
"step": 690
|
| 547 |
-
},
|
| 548 |
-
{
|
| 549 |
-
"epoch": 6.98,
|
| 550 |
-
"grad_norm": 7.193106174468994,
|
| 551 |
-
"learning_rate": 3.3333333333333335e-05,
|
| 552 |
-
"loss": 0.1293,
|
| 553 |
-
"step": 700
|
| 554 |
-
},
|
| 555 |
-
{
|
| 556 |
-
"epoch": 6.99,
|
| 557 |
-
"eval_accuracy": 0.9032258064516129,
|
| 558 |
-
"eval_loss": 0.3595149517059326,
|
| 559 |
-
"eval_runtime": 37.0853,
|
| 560 |
-
"eval_samples_per_second": 76.904,
|
| 561 |
-
"eval_steps_per_second": 1.213,
|
| 562 |
-
"step": 701
|
| 563 |
-
},
|
| 564 |
-
{
|
| 565 |
-
"epoch": 7.08,
|
| 566 |
-
"grad_norm": 5.787723541259766,
|
| 567 |
-
"learning_rate": 3.222222222222223e-05,
|
| 568 |
-
"loss": 0.1175,
|
| 569 |
-
"step": 710
|
| 570 |
-
},
|
| 571 |
-
{
|
| 572 |
-
"epoch": 7.18,
|
| 573 |
-
"grad_norm": 3.8590798377990723,
|
| 574 |
-
"learning_rate": 3.111111111111111e-05,
|
| 575 |
-
"loss": 0.1003,
|
| 576 |
-
"step": 720
|
| 577 |
-
},
|
| 578 |
-
{
|
| 579 |
-
"epoch": 7.28,
|
| 580 |
-
"grad_norm": 4.482466220855713,
|
| 581 |
-
"learning_rate": 3e-05,
|
| 582 |
-
"loss": 0.0991,
|
| 583 |
-
"step": 730
|
| 584 |
-
},
|
| 585 |
-
{
|
| 586 |
-
"epoch": 7.38,
|
| 587 |
-
"grad_norm": 2.0709593296051025,
|
| 588 |
-
"learning_rate": 2.8888888888888888e-05,
|
| 589 |
-
"loss": 0.0827,
|
| 590 |
-
"step": 740
|
| 591 |
-
},
|
| 592 |
-
{
|
| 593 |
-
"epoch": 7.48,
|
| 594 |
-
"grad_norm": 5.126271724700928,
|
| 595 |
-
"learning_rate": 2.777777777777778e-05,
|
| 596 |
-
"loss": 0.1008,
|
| 597 |
-
"step": 750
|
| 598 |
-
},
|
| 599 |
-
{
|
| 600 |
-
"epoch": 7.58,
|
| 601 |
-
"grad_norm": 4.332973003387451,
|
| 602 |
-
"learning_rate": 2.6666666666666667e-05,
|
| 603 |
-
"loss": 0.0805,
|
| 604 |
-
"step": 760
|
| 605 |
-
},
|
| 606 |
-
{
|
| 607 |
-
"epoch": 7.68,
|
| 608 |
-
"grad_norm": 4.371252059936523,
|
| 609 |
-
"learning_rate": 2.5555555555555554e-05,
|
| 610 |
-
"loss": 0.0951,
|
| 611 |
-
"step": 770
|
| 612 |
-
},
|
| 613 |
-
{
|
| 614 |
-
"epoch": 7.78,
|
| 615 |
-
"grad_norm": 4.181329250335693,
|
| 616 |
-
"learning_rate": 2.4444444444444445e-05,
|
| 617 |
-
"loss": 0.0937,
|
| 618 |
-
"step": 780
|
| 619 |
-
},
|
| 620 |
-
{
|
| 621 |
-
"epoch": 7.88,
|
| 622 |
-
"grad_norm": 4.650885581970215,
|
| 623 |
-
"learning_rate": 2.3333333333333336e-05,
|
| 624 |
-
"loss": 0.0857,
|
| 625 |
-
"step": 790
|
| 626 |
-
},
|
| 627 |
-
{
|
| 628 |
-
"epoch": 7.98,
|
| 629 |
-
"grad_norm": 5.875858306884766,
|
| 630 |
-
"learning_rate": 2.2222222222222223e-05,
|
| 631 |
-
"loss": 0.1094,
|
| 632 |
-
"step": 800
|
| 633 |
-
},
|
| 634 |
-
{
|
| 635 |
-
"epoch": 8.0,
|
| 636 |
-
"eval_accuracy": 0.8993688639551192,
|
| 637 |
-
"eval_loss": 0.36655670404434204,
|
| 638 |
-
"eval_runtime": 37.936,
|
| 639 |
-
"eval_samples_per_second": 75.179,
|
| 640 |
-
"eval_steps_per_second": 1.186,
|
| 641 |
-
"step": 802
|
| 642 |
-
},
|
| 643 |
-
{
|
| 644 |
-
"epoch": 8.08,
|
| 645 |
-
"grad_norm": 6.7501349449157715,
|
| 646 |
-
"learning_rate": 2.111111111111111e-05,
|
| 647 |
-
"loss": 0.1025,
|
| 648 |
-
"step": 810
|
| 649 |
-
},
|
| 650 |
-
{
|
| 651 |
-
"epoch": 8.18,
|
| 652 |
-
"grad_norm": 4.238629341125488,
|
| 653 |
-
"learning_rate": 2e-05,
|
| 654 |
-
"loss": 0.0783,
|
| 655 |
-
"step": 820
|
| 656 |
-
},
|
| 657 |
-
{
|
| 658 |
-
"epoch": 8.28,
|
| 659 |
-
"grad_norm": 4.994195938110352,
|
| 660 |
-
"learning_rate": 1.888888888888889e-05,
|
| 661 |
-
"loss": 0.0989,
|
| 662 |
-
"step": 830
|
| 663 |
-
},
|
| 664 |
-
{
|
| 665 |
-
"epoch": 8.38,
|
| 666 |
-
"grad_norm": 4.091785430908203,
|
| 667 |
-
"learning_rate": 1.777777777777778e-05,
|
| 668 |
-
"loss": 0.093,
|
| 669 |
-
"step": 840
|
| 670 |
-
},
|
| 671 |
-
{
|
| 672 |
-
"epoch": 8.48,
|
| 673 |
-
"grad_norm": 4.5268378257751465,
|
| 674 |
-
"learning_rate": 1.6666666666666667e-05,
|
| 675 |
-
"loss": 0.0993,
|
| 676 |
-
"step": 850
|
| 677 |
-
},
|
| 678 |
-
{
|
| 679 |
-
"epoch": 8.58,
|
| 680 |
-
"grad_norm": 4.056771755218506,
|
| 681 |
-
"learning_rate": 1.5555555555555555e-05,
|
| 682 |
-
"loss": 0.0989,
|
| 683 |
-
"step": 860
|
| 684 |
-
},
|
| 685 |
-
{
|
| 686 |
-
"epoch": 8.68,
|
| 687 |
-
"grad_norm": 3.3963980674743652,
|
| 688 |
-
"learning_rate": 1.4444444444444444e-05,
|
| 689 |
-
"loss": 0.0975,
|
| 690 |
-
"step": 870
|
| 691 |
-
},
|
| 692 |
-
{
|
| 693 |
-
"epoch": 8.78,
|
| 694 |
-
"grad_norm": 4.109832763671875,
|
| 695 |
-
"learning_rate": 1.3333333333333333e-05,
|
| 696 |
-
"loss": 0.1079,
|
| 697 |
-
"step": 880
|
| 698 |
-
},
|
| 699 |
-
{
|
| 700 |
-
"epoch": 8.88,
|
| 701 |
-
"grad_norm": 4.538650035858154,
|
| 702 |
-
"learning_rate": 1.2222222222222222e-05,
|
| 703 |
-
"loss": 0.091,
|
| 704 |
-
"step": 890
|
| 705 |
-
},
|
| 706 |
-
{
|
| 707 |
-
"epoch": 8.98,
|
| 708 |
-
"grad_norm": 3.982865571975708,
|
| 709 |
-
"learning_rate": 1.1111111111111112e-05,
|
| 710 |
-
"loss": 0.1047,
|
| 711 |
-
"step": 900
|
| 712 |
-
},
|
| 713 |
-
{
|
| 714 |
-
"epoch": 9.0,
|
| 715 |
-
"eval_accuracy": 0.9021739130434783,
|
| 716 |
-
"eval_loss": 0.3615379333496094,
|
| 717 |
-
"eval_runtime": 37.2047,
|
| 718 |
-
"eval_samples_per_second": 76.657,
|
| 719 |
-
"eval_steps_per_second": 1.21,
|
| 720 |
-
"step": 902
|
| 721 |
-
},
|
| 722 |
-
{
|
| 723 |
-
"epoch": 9.08,
|
| 724 |
-
"grad_norm": 5.261457920074463,
|
| 725 |
-
"learning_rate": 1e-05,
|
| 726 |
-
"loss": 0.1016,
|
| 727 |
-
"step": 910
|
| 728 |
-
},
|
| 729 |
-
{
|
| 730 |
-
"epoch": 9.18,
|
| 731 |
-
"grad_norm": 4.270400047302246,
|
| 732 |
-
"learning_rate": 8.88888888888889e-06,
|
| 733 |
-
"loss": 0.109,
|
| 734 |
-
"step": 920
|
| 735 |
-
},
|
| 736 |
-
{
|
| 737 |
-
"epoch": 9.28,
|
| 738 |
-
"grad_norm": 4.025336265563965,
|
| 739 |
-
"learning_rate": 7.777777777777777e-06,
|
| 740 |
-
"loss": 0.0955,
|
| 741 |
-
"step": 930
|
| 742 |
-
},
|
| 743 |
-
{
|
| 744 |
-
"epoch": 9.38,
|
| 745 |
-
"grad_norm": 4.099737167358398,
|
| 746 |
-
"learning_rate": 6.666666666666667e-06,
|
| 747 |
-
"loss": 0.1024,
|
| 748 |
-
"step": 940
|
| 749 |
-
},
|
| 750 |
-
{
|
| 751 |
-
"epoch": 9.48,
|
| 752 |
-
"grad_norm": 4.68928861618042,
|
| 753 |
-
"learning_rate": 5.555555555555556e-06,
|
| 754 |
-
"loss": 0.1069,
|
| 755 |
-
"step": 950
|
| 756 |
-
},
|
| 757 |
-
{
|
| 758 |
-
"epoch": 9.58,
|
| 759 |
-
"grad_norm": 4.062239170074463,
|
| 760 |
-
"learning_rate": 4.444444444444445e-06,
|
| 761 |
-
"loss": 0.0971,
|
| 762 |
-
"step": 960
|
| 763 |
-
},
|
| 764 |
-
{
|
| 765 |
-
"epoch": 9.68,
|
| 766 |
-
"grad_norm": 3.338601589202881,
|
| 767 |
-
"learning_rate": 3.3333333333333333e-06,
|
| 768 |
-
"loss": 0.1033,
|
| 769 |
-
"step": 970
|
| 770 |
-
},
|
| 771 |
-
{
|
| 772 |
-
"epoch": 9.78,
|
| 773 |
-
"grad_norm": 7.083847522735596,
|
| 774 |
-
"learning_rate": 2.2222222222222225e-06,
|
| 775 |
-
"loss": 0.1139,
|
| 776 |
-
"step": 980
|
| 777 |
-
},
|
| 778 |
-
{
|
| 779 |
-
"epoch": 9.88,
|
| 780 |
-
"grad_norm": 5.833040714263916,
|
| 781 |
-
"learning_rate": 1.1111111111111112e-06,
|
| 782 |
-
"loss": 0.1198,
|
| 783 |
-
"step": 990
|
| 784 |
-
},
|
| 785 |
-
{
|
| 786 |
-
"epoch": 9.98,
|
| 787 |
-
"grad_norm": 4.501120567321777,
|
| 788 |
"learning_rate": 0.0,
|
| 789 |
-
"loss": 0.
|
| 790 |
-
"step":
|
| 791 |
},
|
| 792 |
{
|
| 793 |
-
"epoch":
|
| 794 |
-
"eval_accuracy": 0.
|
| 795 |
-
"eval_loss": 0.
|
| 796 |
-
"eval_runtime":
|
| 797 |
-
"eval_samples_per_second":
|
| 798 |
-
"eval_steps_per_second":
|
| 799 |
-
"step":
|
| 800 |
},
|
| 801 |
{
|
| 802 |
-
"epoch":
|
| 803 |
-
"step":
|
| 804 |
-
"total_flos":
|
| 805 |
-
"train_loss": 0.
|
| 806 |
-
"train_runtime":
|
| 807 |
-
"train_samples_per_second":
|
| 808 |
-
"train_steps_per_second": 0.
|
| 809 |
}
|
| 810 |
],
|
| 811 |
"logging_steps": 10,
|
| 812 |
-
"max_steps":
|
| 813 |
"num_input_tokens_seen": 0,
|
| 814 |
-
"num_train_epochs":
|
| 815 |
"save_steps": 500,
|
| 816 |
-
"total_flos":
|
| 817 |
"train_batch_size": 64,
|
| 818 |
"trial_name": null,
|
| 819 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.8660130718954249,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-21",
|
| 4 |
+
"epoch": 2.7906976744186047,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 30,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.93,
|
| 13 |
+
"grad_norm": 4.1663103103637695,
|
| 14 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 15 |
+
"loss": 0.7396,
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.93,
|
| 20 |
+
"eval_accuracy": 0.8496732026143791,
|
| 21 |
+
"eval_loss": 0.3929253816604614,
|
| 22 |
+
"eval_runtime": 3.0907,
|
| 23 |
+
"eval_samples_per_second": 99.005,
|
| 24 |
+
"eval_steps_per_second": 1.618,
|
| 25 |
+
"step": 10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
},
|
| 27 |
{
|
| 28 |
+
"epoch": 1.86,
|
| 29 |
+
"grad_norm": 3.590320348739624,
|
| 30 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 31 |
+
"loss": 0.2666,
|
| 32 |
+
"step": 20
|
| 33 |
},
|
| 34 |
{
|
| 35 |
+
"epoch": 1.95,
|
| 36 |
+
"eval_accuracy": 0.8660130718954249,
|
| 37 |
+
"eval_loss": 0.28969407081604004,
|
| 38 |
+
"eval_runtime": 1.9505,
|
| 39 |
+
"eval_samples_per_second": 156.885,
|
| 40 |
+
"eval_steps_per_second": 2.563,
|
| 41 |
+
"step": 21
|
| 42 |
},
|
| 43 |
{
|
| 44 |
"epoch": 2.79,
|
| 45 |
+
"grad_norm": 4.9571614265441895,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
"learning_rate": 0.0,
|
| 47 |
+
"loss": 0.2275,
|
| 48 |
+
"step": 30
|
| 49 |
},
|
| 50 |
{
|
| 51 |
+
"epoch": 2.79,
|
| 52 |
+
"eval_accuracy": 0.8398692810457516,
|
| 53 |
+
"eval_loss": 0.3352753520011902,
|
| 54 |
+
"eval_runtime": 1.9602,
|
| 55 |
+
"eval_samples_per_second": 156.109,
|
| 56 |
+
"eval_steps_per_second": 2.551,
|
| 57 |
+
"step": 30
|
| 58 |
},
|
| 59 |
{
|
| 60 |
+
"epoch": 2.79,
|
| 61 |
+
"step": 30,
|
| 62 |
+
"total_flos": 1.9084961608228454e+17,
|
| 63 |
+
"train_loss": 0.4112351576487223,
|
| 64 |
+
"train_runtime": 186.8069,
|
| 65 |
+
"train_samples_per_second": 44.179,
|
| 66 |
+
"train_steps_per_second": 0.161
|
| 67 |
}
|
| 68 |
],
|
| 69 |
"logging_steps": 10,
|
| 70 |
+
"max_steps": 30,
|
| 71 |
"num_input_tokens_seen": 0,
|
| 72 |
+
"num_train_epochs": 3,
|
| 73 |
"save_steps": 500,
|
| 74 |
+
"total_flos": 1.9084961608228454e+17,
|
| 75 |
"train_batch_size": 64,
|
| 76 |
"trial_name": null,
|
| 77 |
"trial_params": null
|