Training in progress, epoch 1
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +18 -493
- last-checkpoint/training_args.bin +1 -1
- pytorch_model.bin +1 -1
- runs/Aug12_18-51-37_6f9eef05c7c8/1660330305.0889966/events.out.tfevents.1660330305.6f9eef05c7c8.122.1 +3 -0
- runs/Aug12_18-51-37_6f9eef05c7c8/events.out.tfevents.1660330305.6f9eef05c7c8.122.0 +3 -0
- training_args.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 29835597
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a748b5e46129566d2982ff8686a1bc46c5c98aee94dd7cdf2b7fde4ec538dc91
|
| 3 |
size 29835597
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14929953
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:524025e770935b8efedbfc1b73798f24785b777f4a593727d96f454137ded48f
|
| 3 |
size 14929953
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4ee7803a0bc44eb31c67b3c1d1cc3c9c80c2a787bc6faa33069d96933b867d3
|
| 3 |
size 14503
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:093800f3d93a6e057e10ae7d5be294fe2ebe608b5a7c4e7423cede0f2b161832
|
| 3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,516 +1,41 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "drive/MyDrive/segformer-b0-finetuned-pokemon/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 1.0,
|
| 12 |
-
"learning_rate": 5.
|
| 13 |
-
"loss": 0.
|
| 14 |
"step": 340
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 1.0,
|
| 18 |
-
"eval_loss": 0.
|
| 19 |
-
"eval_mean_accuracy": 0.
|
| 20 |
-
"eval_mean_iou": 0.
|
| 21 |
-
"eval_overall_accuracy": 0.
|
| 22 |
-
"eval_per_category_accuracy": [
|
| 23 |
-
NaN,
|
| 24 |
-
0.9879431125060076
|
| 25 |
-
],
|
| 26 |
-
"eval_per_category_iou": [
|
| 27 |
-
0.0,
|
| 28 |
-
0.9879431125060076
|
| 29 |
-
],
|
| 30 |
-
"eval_runtime": 608.9147,
|
| 31 |
-
"eval_samples_per_second": 0.709,
|
| 32 |
-
"eval_steps_per_second": 0.03,
|
| 33 |
-
"step": 340
|
| 34 |
-
},
|
| 35 |
-
{
|
| 36 |
-
"epoch": 2.0,
|
| 37 |
-
"learning_rate": 5.4000000000000005e-05,
|
| 38 |
-
"loss": 0.0141,
|
| 39 |
-
"step": 680
|
| 40 |
-
},
|
| 41 |
-
{
|
| 42 |
-
"epoch": 2.0,
|
| 43 |
-
"eval_loss": 0.022794678807258606,
|
| 44 |
-
"eval_mean_accuracy": 0.9892920565835466,
|
| 45 |
-
"eval_mean_iou": 0.4946460282917733,
|
| 46 |
-
"eval_overall_accuracy": 0.9892920565835466,
|
| 47 |
-
"eval_per_category_accuracy": [
|
| 48 |
-
NaN,
|
| 49 |
-
0.9892920565835466
|
| 50 |
-
],
|
| 51 |
-
"eval_per_category_iou": [
|
| 52 |
-
0.0,
|
| 53 |
-
0.9892920565835466
|
| 54 |
-
],
|
| 55 |
-
"eval_runtime": 607.356,
|
| 56 |
-
"eval_samples_per_second": 0.711,
|
| 57 |
-
"eval_steps_per_second": 0.03,
|
| 58 |
-
"step": 680
|
| 59 |
-
},
|
| 60 |
-
{
|
| 61 |
-
"epoch": 3.0,
|
| 62 |
-
"learning_rate": 5.1e-05,
|
| 63 |
-
"loss": 0.0136,
|
| 64 |
-
"step": 1020
|
| 65 |
-
},
|
| 66 |
-
{
|
| 67 |
-
"epoch": 3.0,
|
| 68 |
-
"eval_loss": 0.02348109893500805,
|
| 69 |
-
"eval_mean_accuracy": 0.9878666758924011,
|
| 70 |
-
"eval_mean_iou": 0.49393333794620053,
|
| 71 |
-
"eval_overall_accuracy": 0.9878666758924011,
|
| 72 |
-
"eval_per_category_accuracy": [
|
| 73 |
-
NaN,
|
| 74 |
-
0.9878666758924011
|
| 75 |
-
],
|
| 76 |
-
"eval_per_category_iou": [
|
| 77 |
-
0.0,
|
| 78 |
-
0.9878666758924011
|
| 79 |
-
],
|
| 80 |
-
"eval_runtime": 614.3099,
|
| 81 |
-
"eval_samples_per_second": 0.703,
|
| 82 |
-
"eval_steps_per_second": 0.029,
|
| 83 |
-
"step": 1020
|
| 84 |
-
},
|
| 85 |
-
{
|
| 86 |
-
"epoch": 4.0,
|
| 87 |
-
"learning_rate": 4.8e-05,
|
| 88 |
-
"loss": 0.0134,
|
| 89 |
-
"step": 1360
|
| 90 |
-
},
|
| 91 |
-
{
|
| 92 |
-
"epoch": 4.0,
|
| 93 |
-
"eval_loss": 0.025509441271424294,
|
| 94 |
-
"eval_mean_accuracy": 0.987905095410482,
|
| 95 |
-
"eval_mean_iou": 0.493952547705241,
|
| 96 |
-
"eval_overall_accuracy": 0.987905095410482,
|
| 97 |
"eval_per_category_accuracy": [
|
| 98 |
NaN,
|
| 99 |
-
0.
|
| 100 |
],
|
| 101 |
"eval_per_category_iou": [
|
| 102 |
0.0,
|
| 103 |
-
0.
|
| 104 |
-
],
|
| 105 |
-
"eval_runtime": 626.9326,
|
| 106 |
-
"eval_samples_per_second": 0.689,
|
| 107 |
-
"eval_steps_per_second": 0.029,
|
| 108 |
-
"step": 1360
|
| 109 |
-
},
|
| 110 |
-
{
|
| 111 |
-
"epoch": 5.0,
|
| 112 |
-
"learning_rate": 4.5e-05,
|
| 113 |
-
"loss": 0.0133,
|
| 114 |
-
"step": 1700
|
| 115 |
-
},
|
| 116 |
-
{
|
| 117 |
-
"epoch": 5.0,
|
| 118 |
-
"eval_loss": 0.025961697101593018,
|
| 119 |
-
"eval_mean_accuracy": 0.9858244761115225,
|
| 120 |
-
"eval_mean_iou": 0.49291223805576123,
|
| 121 |
-
"eval_overall_accuracy": 0.9858244761115225,
|
| 122 |
-
"eval_per_category_accuracy": [
|
| 123 |
-
NaN,
|
| 124 |
-
0.9858244761115225
|
| 125 |
-
],
|
| 126 |
-
"eval_per_category_iou": [
|
| 127 |
-
0.0,
|
| 128 |
-
0.9858244761115225
|
| 129 |
-
],
|
| 130 |
-
"eval_runtime": 629.4017,
|
| 131 |
-
"eval_samples_per_second": 0.686,
|
| 132 |
-
"eval_steps_per_second": 0.029,
|
| 133 |
-
"step": 1700
|
| 134 |
-
},
|
| 135 |
-
{
|
| 136 |
-
"epoch": 6.0,
|
| 137 |
-
"learning_rate": 4.2e-05,
|
| 138 |
-
"loss": 0.0128,
|
| 139 |
-
"step": 2040
|
| 140 |
-
},
|
| 141 |
-
{
|
| 142 |
-
"epoch": 6.0,
|
| 143 |
-
"eval_loss": 0.025503695011138916,
|
| 144 |
-
"eval_mean_accuracy": 0.988041658688245,
|
| 145 |
-
"eval_mean_iou": 0.4940208293441225,
|
| 146 |
-
"eval_overall_accuracy": 0.988041658688245,
|
| 147 |
-
"eval_per_category_accuracy": [
|
| 148 |
-
NaN,
|
| 149 |
-
0.988041658688245
|
| 150 |
],
|
| 151 |
-
"
|
| 152 |
-
|
| 153 |
-
0.988041658688245
|
| 154 |
-
],
|
| 155 |
-
"eval_runtime": 636.3637,
|
| 156 |
-
"eval_samples_per_second": 0.679,
|
| 157 |
-
"eval_steps_per_second": 0.028,
|
| 158 |
-
"step": 2040
|
| 159 |
-
},
|
| 160 |
-
{
|
| 161 |
-
"epoch": 7.0,
|
| 162 |
-
"learning_rate": 3.9e-05,
|
| 163 |
-
"loss": 0.013,
|
| 164 |
-
"step": 2380
|
| 165 |
-
},
|
| 166 |
-
{
|
| 167 |
-
"epoch": 7.0,
|
| 168 |
-
"eval_loss": 0.013553046621382236,
|
| 169 |
-
"eval_mean_accuracy": 0.9925333929482818,
|
| 170 |
-
"eval_mean_iou": 0.4962666964741409,
|
| 171 |
-
"eval_overall_accuracy": 0.9925333929482818,
|
| 172 |
-
"eval_per_category_accuracy": [
|
| 173 |
-
NaN,
|
| 174 |
-
0.9925333929482818
|
| 175 |
-
],
|
| 176 |
-
"eval_per_category_iou": [
|
| 177 |
-
0.0,
|
| 178 |
-
0.9925333929482818
|
| 179 |
-
],
|
| 180 |
-
"eval_runtime": 578.111,
|
| 181 |
-
"eval_samples_per_second": 0.747,
|
| 182 |
"eval_steps_per_second": 0.031,
|
| 183 |
-
"step":
|
| 184 |
-
},
|
| 185 |
-
{
|
| 186 |
-
"epoch": 8.0,
|
| 187 |
-
"learning_rate": 3.6e-05,
|
| 188 |
-
"loss": 0.0128,
|
| 189 |
-
"step": 2720
|
| 190 |
-
},
|
| 191 |
-
{
|
| 192 |
-
"epoch": 8.0,
|
| 193 |
-
"eval_loss": 0.013631226494908333,
|
| 194 |
-
"eval_mean_accuracy": 0.9916881291497741,
|
| 195 |
-
"eval_mean_iou": 0.49584406457488706,
|
| 196 |
-
"eval_overall_accuracy": 0.9916881291497741,
|
| 197 |
-
"eval_per_category_accuracy": [
|
| 198 |
-
NaN,
|
| 199 |
-
0.9916881291497741
|
| 200 |
-
],
|
| 201 |
-
"eval_per_category_iou": [
|
| 202 |
-
0.0,
|
| 203 |
-
0.9916881291497741
|
| 204 |
-
],
|
| 205 |
-
"eval_runtime": 585.5235,
|
| 206 |
-
"eval_samples_per_second": 0.738,
|
| 207 |
-
"eval_steps_per_second": 0.031,
|
| 208 |
-
"step": 2720
|
| 209 |
-
},
|
| 210 |
-
{
|
| 211 |
-
"epoch": 9.0,
|
| 212 |
-
"learning_rate": 3.3e-05,
|
| 213 |
-
"loss": 0.0129,
|
| 214 |
-
"step": 3060
|
| 215 |
-
},
|
| 216 |
-
{
|
| 217 |
-
"epoch": 9.0,
|
| 218 |
-
"eval_loss": 0.013744899071753025,
|
| 219 |
-
"eval_mean_accuracy": 0.9920058761957417,
|
| 220 |
-
"eval_mean_iou": 0.4960029380978708,
|
| 221 |
-
"eval_overall_accuracy": 0.9920058761957417,
|
| 222 |
-
"eval_per_category_accuracy": [
|
| 223 |
-
NaN,
|
| 224 |
-
0.9920058761957417
|
| 225 |
-
],
|
| 226 |
-
"eval_per_category_iou": [
|
| 227 |
-
0.0,
|
| 228 |
-
0.9920058761957417
|
| 229 |
-
],
|
| 230 |
-
"eval_runtime": 598.6814,
|
| 231 |
-
"eval_samples_per_second": 0.722,
|
| 232 |
-
"eval_steps_per_second": 0.03,
|
| 233 |
-
"step": 3060
|
| 234 |
-
},
|
| 235 |
-
{
|
| 236 |
-
"epoch": 10.0,
|
| 237 |
-
"learning_rate": 3e-05,
|
| 238 |
-
"loss": 0.013,
|
| 239 |
-
"step": 3400
|
| 240 |
-
},
|
| 241 |
-
{
|
| 242 |
-
"epoch": 10.0,
|
| 243 |
-
"eval_loss": 0.01346308458596468,
|
| 244 |
-
"eval_mean_accuracy": 0.9919511557163544,
|
| 245 |
-
"eval_mean_iou": 0.4959755778581772,
|
| 246 |
-
"eval_overall_accuracy": 0.9919511557163544,
|
| 247 |
-
"eval_per_category_accuracy": [
|
| 248 |
-
NaN,
|
| 249 |
-
0.9919511557163544
|
| 250 |
-
],
|
| 251 |
-
"eval_per_category_iou": [
|
| 252 |
-
0.0,
|
| 253 |
-
0.9919511557163544
|
| 254 |
-
],
|
| 255 |
-
"eval_runtime": 625.7746,
|
| 256 |
-
"eval_samples_per_second": 0.69,
|
| 257 |
-
"eval_steps_per_second": 0.029,
|
| 258 |
-
"step": 3400
|
| 259 |
-
},
|
| 260 |
-
{
|
| 261 |
-
"epoch": 11.0,
|
| 262 |
-
"learning_rate": 2.7000000000000002e-05,
|
| 263 |
-
"loss": 0.0132,
|
| 264 |
-
"step": 3740
|
| 265 |
-
},
|
| 266 |
-
{
|
| 267 |
-
"epoch": 11.0,
|
| 268 |
-
"eval_loss": 0.014067417941987514,
|
| 269 |
-
"eval_mean_accuracy": 0.991989705562273,
|
| 270 |
-
"eval_mean_iou": 0.4959948527811365,
|
| 271 |
-
"eval_overall_accuracy": 0.991989705562273,
|
| 272 |
-
"eval_per_category_accuracy": [
|
| 273 |
-
NaN,
|
| 274 |
-
0.991989705562273
|
| 275 |
-
],
|
| 276 |
-
"eval_per_category_iou": [
|
| 277 |
-
0.0,
|
| 278 |
-
0.991989705562273
|
| 279 |
-
],
|
| 280 |
-
"eval_runtime": 585.9151,
|
| 281 |
-
"eval_samples_per_second": 0.737,
|
| 282 |
-
"eval_steps_per_second": 0.031,
|
| 283 |
-
"step": 3740
|
| 284 |
-
},
|
| 285 |
-
{
|
| 286 |
-
"epoch": 12.0,
|
| 287 |
-
"learning_rate": 2.4e-05,
|
| 288 |
-
"loss": 0.0126,
|
| 289 |
-
"step": 4080
|
| 290 |
-
},
|
| 291 |
-
{
|
| 292 |
-
"epoch": 12.0,
|
| 293 |
-
"eval_loss": 0.013786387629806995,
|
| 294 |
-
"eval_mean_accuracy": 0.9923228206117268,
|
| 295 |
-
"eval_mean_iou": 0.4961614103058634,
|
| 296 |
-
"eval_overall_accuracy": 0.9923228206117268,
|
| 297 |
-
"eval_per_category_accuracy": [
|
| 298 |
-
NaN,
|
| 299 |
-
0.9923228206117268
|
| 300 |
-
],
|
| 301 |
-
"eval_per_category_iou": [
|
| 302 |
-
0.0,
|
| 303 |
-
0.9923228206117268
|
| 304 |
-
],
|
| 305 |
-
"eval_runtime": 634.4181,
|
| 306 |
-
"eval_samples_per_second": 0.681,
|
| 307 |
-
"eval_steps_per_second": 0.028,
|
| 308 |
-
"step": 4080
|
| 309 |
-
},
|
| 310 |
-
{
|
| 311 |
-
"epoch": 13.0,
|
| 312 |
-
"learning_rate": 2.1e-05,
|
| 313 |
-
"loss": 0.0125,
|
| 314 |
-
"step": 4420
|
| 315 |
-
},
|
| 316 |
-
{
|
| 317 |
-
"epoch": 13.0,
|
| 318 |
-
"eval_loss": 0.013361201621592045,
|
| 319 |
-
"eval_mean_accuracy": 0.9927345697926901,
|
| 320 |
-
"eval_mean_iou": 0.4963672848963451,
|
| 321 |
-
"eval_overall_accuracy": 0.9927345697926901,
|
| 322 |
-
"eval_per_category_accuracy": [
|
| 323 |
-
NaN,
|
| 324 |
-
0.9927345697926901
|
| 325 |
-
],
|
| 326 |
-
"eval_per_category_iou": [
|
| 327 |
-
0.0,
|
| 328 |
-
0.9927345697926901
|
| 329 |
-
],
|
| 330 |
-
"eval_runtime": 578.6226,
|
| 331 |
-
"eval_samples_per_second": 0.747,
|
| 332 |
-
"eval_steps_per_second": 0.031,
|
| 333 |
-
"step": 4420
|
| 334 |
-
},
|
| 335 |
-
{
|
| 336 |
-
"epoch": 14.0,
|
| 337 |
-
"learning_rate": 1.8e-05,
|
| 338 |
-
"loss": 0.0127,
|
| 339 |
-
"step": 4760
|
| 340 |
-
},
|
| 341 |
-
{
|
| 342 |
-
"epoch": 14.0,
|
| 343 |
-
"eval_loss": 0.014840549789369106,
|
| 344 |
-
"eval_mean_accuracy": 0.991889022713012,
|
| 345 |
-
"eval_mean_iou": 0.495944511356506,
|
| 346 |
-
"eval_overall_accuracy": 0.991889022713012,
|
| 347 |
-
"eval_per_category_accuracy": [
|
| 348 |
-
NaN,
|
| 349 |
-
0.991889022713012
|
| 350 |
-
],
|
| 351 |
-
"eval_per_category_iou": [
|
| 352 |
-
0.0,
|
| 353 |
-
0.991889022713012
|
| 354 |
-
],
|
| 355 |
-
"eval_runtime": 569.9371,
|
| 356 |
-
"eval_samples_per_second": 0.758,
|
| 357 |
-
"eval_steps_per_second": 0.032,
|
| 358 |
-
"step": 4760
|
| 359 |
-
},
|
| 360 |
-
{
|
| 361 |
-
"epoch": 15.0,
|
| 362 |
-
"learning_rate": 1.5e-05,
|
| 363 |
-
"loss": 0.0127,
|
| 364 |
-
"step": 5100
|
| 365 |
-
},
|
| 366 |
-
{
|
| 367 |
-
"epoch": 15.0,
|
| 368 |
-
"eval_loss": 0.016987059265375137,
|
| 369 |
-
"eval_mean_accuracy": 0.9918633580107863,
|
| 370 |
-
"eval_mean_iou": 0.49593167900539314,
|
| 371 |
-
"eval_overall_accuracy": 0.9918633580107863,
|
| 372 |
-
"eval_per_category_accuracy": [
|
| 373 |
-
NaN,
|
| 374 |
-
0.9918633580107863
|
| 375 |
-
],
|
| 376 |
-
"eval_per_category_iou": [
|
| 377 |
-
0.0,
|
| 378 |
-
0.9918633580107863
|
| 379 |
-
],
|
| 380 |
-
"eval_runtime": 555.0671,
|
| 381 |
-
"eval_samples_per_second": 0.778,
|
| 382 |
-
"eval_steps_per_second": 0.032,
|
| 383 |
-
"step": 5100
|
| 384 |
-
},
|
| 385 |
-
{
|
| 386 |
-
"epoch": 16.0,
|
| 387 |
-
"learning_rate": 1.2e-05,
|
| 388 |
-
"loss": 0.0125,
|
| 389 |
-
"step": 5440
|
| 390 |
-
},
|
| 391 |
-
{
|
| 392 |
-
"epoch": 16.0,
|
| 393 |
-
"eval_loss": 0.01838378794491291,
|
| 394 |
-
"eval_mean_accuracy": 0.9900458918744116,
|
| 395 |
-
"eval_mean_iou": 0.4950229459372058,
|
| 396 |
-
"eval_overall_accuracy": 0.9900458918744116,
|
| 397 |
-
"eval_per_category_accuracy": [
|
| 398 |
-
NaN,
|
| 399 |
-
0.9900458918744116
|
| 400 |
-
],
|
| 401 |
-
"eval_per_category_iou": [
|
| 402 |
-
0.0,
|
| 403 |
-
0.9900458918744116
|
| 404 |
-
],
|
| 405 |
-
"eval_runtime": 549.578,
|
| 406 |
-
"eval_samples_per_second": 0.786,
|
| 407 |
-
"eval_steps_per_second": 0.033,
|
| 408 |
-
"step": 5440
|
| 409 |
-
},
|
| 410 |
-
{
|
| 411 |
-
"epoch": 17.0,
|
| 412 |
-
"learning_rate": 9e-06,
|
| 413 |
-
"loss": 0.013,
|
| 414 |
-
"step": 5780
|
| 415 |
-
},
|
| 416 |
-
{
|
| 417 |
-
"epoch": 17.0,
|
| 418 |
-
"eval_loss": 0.01879480667412281,
|
| 419 |
-
"eval_mean_accuracy": 0.9907627782677692,
|
| 420 |
-
"eval_mean_iou": 0.4953813891338846,
|
| 421 |
-
"eval_overall_accuracy": 0.9907627782677692,
|
| 422 |
-
"eval_per_category_accuracy": [
|
| 423 |
-
NaN,
|
| 424 |
-
0.9907627782677692
|
| 425 |
-
],
|
| 426 |
-
"eval_per_category_iou": [
|
| 427 |
-
0.0,
|
| 428 |
-
0.9907627782677692
|
| 429 |
-
],
|
| 430 |
-
"eval_runtime": 554.1068,
|
| 431 |
-
"eval_samples_per_second": 0.78,
|
| 432 |
-
"eval_steps_per_second": 0.032,
|
| 433 |
-
"step": 5780
|
| 434 |
-
},
|
| 435 |
-
{
|
| 436 |
-
"epoch": 18.0,
|
| 437 |
-
"learning_rate": 6e-06,
|
| 438 |
-
"loss": 0.0124,
|
| 439 |
-
"step": 6120
|
| 440 |
-
},
|
| 441 |
-
{
|
| 442 |
-
"epoch": 18.0,
|
| 443 |
-
"eval_loss": 0.02039848081767559,
|
| 444 |
-
"eval_mean_accuracy": 0.989966290117001,
|
| 445 |
-
"eval_mean_iou": 0.4949831450585005,
|
| 446 |
-
"eval_overall_accuracy": 0.989966290117001,
|
| 447 |
-
"eval_per_category_accuracy": [
|
| 448 |
-
NaN,
|
| 449 |
-
0.989966290117001
|
| 450 |
-
],
|
| 451 |
-
"eval_per_category_iou": [
|
| 452 |
-
0.0,
|
| 453 |
-
0.989966290117001
|
| 454 |
-
],
|
| 455 |
-
"eval_runtime": 552.422,
|
| 456 |
-
"eval_samples_per_second": 0.782,
|
| 457 |
-
"eval_steps_per_second": 0.033,
|
| 458 |
-
"step": 6120
|
| 459 |
-
},
|
| 460 |
-
{
|
| 461 |
-
"epoch": 19.0,
|
| 462 |
-
"learning_rate": 3e-06,
|
| 463 |
-
"loss": 0.0123,
|
| 464 |
-
"step": 6460
|
| 465 |
-
},
|
| 466 |
-
{
|
| 467 |
-
"epoch": 19.0,
|
| 468 |
-
"eval_loss": 0.020339062437415123,
|
| 469 |
-
"eval_mean_accuracy": 0.9900301894742254,
|
| 470 |
-
"eval_mean_iou": 0.4950150947371127,
|
| 471 |
-
"eval_overall_accuracy": 0.9900301894742254,
|
| 472 |
-
"eval_per_category_accuracy": [
|
| 473 |
-
NaN,
|
| 474 |
-
0.9900301894742254
|
| 475 |
-
],
|
| 476 |
-
"eval_per_category_iou": [
|
| 477 |
-
0.0,
|
| 478 |
-
0.9900301894742254
|
| 479 |
-
],
|
| 480 |
-
"eval_runtime": 555.5098,
|
| 481 |
-
"eval_samples_per_second": 0.778,
|
| 482 |
-
"eval_steps_per_second": 0.032,
|
| 483 |
-
"step": 6460
|
| 484 |
-
},
|
| 485 |
-
{
|
| 486 |
-
"epoch": 20.0,
|
| 487 |
-
"learning_rate": 0.0,
|
| 488 |
-
"loss": 0.0123,
|
| 489 |
-
"step": 6800
|
| 490 |
-
},
|
| 491 |
-
{
|
| 492 |
-
"epoch": 20.0,
|
| 493 |
-
"eval_loss": 0.01985727809369564,
|
| 494 |
-
"eval_mean_accuracy": 0.9902555709280016,
|
| 495 |
-
"eval_mean_iou": 0.4951277854640008,
|
| 496 |
-
"eval_overall_accuracy": 0.9902555709280016,
|
| 497 |
-
"eval_per_category_accuracy": [
|
| 498 |
-
NaN,
|
| 499 |
-
0.9902555709280016
|
| 500 |
-
],
|
| 501 |
-
"eval_per_category_iou": [
|
| 502 |
-
0.0,
|
| 503 |
-
0.9902555709280016
|
| 504 |
-
],
|
| 505 |
-
"eval_runtime": 554.4648,
|
| 506 |
-
"eval_samples_per_second": 0.779,
|
| 507 |
-
"eval_steps_per_second": 0.032,
|
| 508 |
-
"step": 6800
|
| 509 |
}
|
| 510 |
],
|
| 511 |
-
"max_steps":
|
| 512 |
-
"num_train_epochs":
|
| 513 |
-
"total_flos":
|
| 514 |
"trial_name": null,
|
| 515 |
"trial_params": null
|
| 516 |
}
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.01995069906115532,
|
| 3 |
+
"best_model_checkpoint": "drive/MyDrive/segformer-b0-finetuned-pokemon/checkpoint-340",
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"global_step": 340,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 1.0,
|
| 12 |
+
"learning_rate": 5.4000000000000005e-05,
|
| 13 |
+
"loss": 0.0121,
|
| 14 |
"step": 340
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 1.0,
|
| 18 |
+
"eval_loss": 0.01995069906115532,
|
| 19 |
+
"eval_mean_accuracy": 0.988013825891106,
|
| 20 |
+
"eval_mean_iou": 0.494006912945553,
|
| 21 |
+
"eval_overall_accuracy": 0.988013825891106,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
"eval_per_category_accuracy": [
|
| 23 |
NaN,
|
| 24 |
+
0.988013825891106
|
| 25 |
],
|
| 26 |
"eval_per_category_iou": [
|
| 27 |
0.0,
|
| 28 |
+
0.988013825891106
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
],
|
| 30 |
+
"eval_runtime": 579.3098,
|
| 31 |
+
"eval_samples_per_second": 0.746,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
"eval_steps_per_second": 0.031,
|
| 33 |
+
"step": 340
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
}
|
| 35 |
],
|
| 36 |
+
"max_steps": 3400,
|
| 37 |
+
"num_train_epochs": 10,
|
| 38 |
+
"total_flos": 1.4294047727812608e+17,
|
| 39 |
"trial_name": null,
|
| 40 |
"trial_params": null
|
| 41 |
}
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3439
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a245dbab64477e1f410bcb52e8e117376f76c8645fa2bdb870b160e7d85ae4ec
|
| 3 |
size 3439
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14929953
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:524025e770935b8efedbfc1b73798f24785b777f4a593727d96f454137ded48f
|
| 3 |
size 14929953
|
runs/Aug12_18-51-37_6f9eef05c7c8/1660330305.0889966/events.out.tfevents.1660330305.6f9eef05c7c8.122.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d78bda54a748bcb9caa07b36cfe2517675240a46600f95ee4afd361129f74f2
|
| 3 |
+
size 5519
|
runs/Aug12_18-51-37_6f9eef05c7c8/events.out.tfevents.1660330305.6f9eef05c7c8.122.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c24c2bde5408a30dad84fa9bc2f60a03233dbb0bb4908c1160973b525aa599a
|
| 3 |
+
size 4852
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3439
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a245dbab64477e1f410bcb52e8e117376f76c8645fa2bdb870b160e7d85ae4ec
|
| 3 |
size 3439
|