Training in progress, epoch 0
Browse files- all_results.json +11 -11
- eval_results.json +6 -6
- pytorch_model.bin +1 -1
- runs/Jan08_21-56-41_2cd0117f6e75/events.out.tfevents.1673215831.2cd0117f6e75.24.2 +3 -0
- runs/Jan08_22-21-08_2cd0117f6e75/1673216473.4465296/events.out.tfevents.1673216473.2cd0117f6e75.24.4 +3 -0
- runs/Jan08_22-21-08_2cd0117f6e75/events.out.tfevents.1673216473.2cd0117f6e75.24.3 +3 -0
- train_results.json +6 -6
- trainer_state.json +59 -317
- training_args.bin +1 -1
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime": 25.
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 3.
|
| 8 |
-
"total_flos":
|
| 9 |
-
"train_loss": 1.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second": 0.
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_accuracy": 0.6422849181469871,
|
| 4 |
+
"eval_loss": 0.9593217372894287,
|
| 5 |
+
"eval_runtime": 25.0315,
|
| 6 |
+
"eval_samples_per_second": 114.696,
|
| 7 |
+
"eval_steps_per_second": 3.595,
|
| 8 |
+
"total_flos": 2.0014719749914337e+18,
|
| 9 |
+
"train_loss": 1.316133418885788,
|
| 10 |
+
"train_runtime": 615.4563,
|
| 11 |
+
"train_samples_per_second": 41.982,
|
| 12 |
+
"train_steps_per_second": 0.328
|
| 13 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime": 25.
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 3.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_accuracy": 0.6422849181469871,
|
| 4 |
+
"eval_loss": 0.9593217372894287,
|
| 5 |
+
"eval_runtime": 25.0315,
|
| 6 |
+
"eval_samples_per_second": 114.696,
|
| 7 |
+
"eval_steps_per_second": 3.595
|
| 8 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 346873835
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ee5de78662c922c5854ae86d2d9f98c469aebe27a40b5d3053612233dfd8227
|
| 3 |
size 346873835
|
runs/Jan08_21-56-41_2cd0117f6e75/events.out.tfevents.1673215831.2cd0117f6e75.24.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94f90e33293a2551171d0fa3b5afe86f424bb6c42a2f36559cf4ab7d21b53fed
|
| 3 |
+
size 363
|
runs/Jan08_22-21-08_2cd0117f6e75/1673216473.4465296/events.out.tfevents.1673216473.2cd0117f6e75.24.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:747f7f7f9a1b787d79be992962531b760c6e1f4a0a4b5d747683297de94d2662
|
| 3 |
+
size 5456
|
runs/Jan08_22-21-08_2cd0117f6e75/events.out.tfevents.1673216473.2cd0117f6e75.24.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4c9240884765586efe0db5884060de52f5b6423b94106506bec096bfa266ccb
|
| 3 |
+
size 8219
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 1.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 2.0014719749914337e+18,
|
| 4 |
+
"train_loss": 1.316133418885788,
|
| 5 |
+
"train_runtime": 615.4563,
|
| 6 |
+
"train_samples_per_second": 41.982,
|
| 7 |
+
"train_steps_per_second": 0.328
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,412 +1,154 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "beit-base-patch16-224-pt22k-ft22k-finetuned-FER2013-9e-05/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": 0.05,
|
| 12 |
-
"learning_rate":
|
| 13 |
-
"loss": 1.
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.1,
|
| 18 |
-
"learning_rate":
|
| 19 |
-
"loss": 1.
|
| 20 |
"step": 20
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.15,
|
| 24 |
-
"learning_rate":
|
| 25 |
-
"loss": 1.
|
| 26 |
"step": 30
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.2,
|
| 30 |
-
"learning_rate":
|
| 31 |
-
"loss": 1.
|
| 32 |
"step": 40
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.25,
|
| 36 |
-
"learning_rate": 7.
|
| 37 |
-
"loss": 1.
|
| 38 |
"step": 50
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.3,
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss": 1.
|
| 44 |
"step": 60
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.35,
|
| 48 |
-
"learning_rate":
|
| 49 |
-
"loss": 1.
|
| 50 |
"step": 70
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.4,
|
| 54 |
-
"learning_rate":
|
| 55 |
-
"loss": 1.
|
| 56 |
"step": 80
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 0.45,
|
| 60 |
-
"learning_rate":
|
| 61 |
-
"loss": 1.
|
| 62 |
"step": 90
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 0.5,
|
| 66 |
-
"learning_rate":
|
| 67 |
-
"loss": 1.
|
| 68 |
"step": 100
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 0.54,
|
| 72 |
-
"learning_rate":
|
| 73 |
-
"loss": 1.
|
| 74 |
"step": 110
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 0.59,
|
| 78 |
-
"learning_rate":
|
| 79 |
-
"loss": 1.
|
| 80 |
"step": 120
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.64,
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss": 1.
|
| 86 |
"step": 130
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.69,
|
| 90 |
-
"learning_rate":
|
| 91 |
-
"loss": 1.
|
| 92 |
"step": 140
|
| 93 |
},
|
| 94 |
{
|
| 95 |
"epoch": 0.74,
|
| 96 |
-
"learning_rate":
|
| 97 |
-
"loss": 1.
|
| 98 |
"step": 150
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 0.79,
|
| 102 |
-
"learning_rate":
|
| 103 |
-
"loss": 1.
|
| 104 |
"step": 160
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 0.84,
|
| 108 |
-
"learning_rate":
|
| 109 |
-
"loss": 1.
|
| 110 |
"step": 170
|
| 111 |
},
|
| 112 |
{
|
| 113 |
"epoch": 0.89,
|
| 114 |
-
"learning_rate":
|
| 115 |
-
"loss": 1.
|
| 116 |
"step": 180
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 0.94,
|
| 120 |
-
"learning_rate":
|
| 121 |
-
"loss": 1.
|
| 122 |
"step": 190
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 0.99,
|
| 126 |
-
"learning_rate":
|
| 127 |
-
"loss": 1.
|
| 128 |
"step": 200
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 1.0,
|
| 132 |
-
"eval_accuracy": 0.
|
| 133 |
-
"eval_loss": 0.
|
| 134 |
-
"eval_runtime": 24.
|
| 135 |
-
"eval_samples_per_second":
|
| 136 |
-
"eval_steps_per_second": 3.
|
| 137 |
"step": 202
|
| 138 |
},
|
| 139 |
{
|
| 140 |
-
"epoch": 1.
|
| 141 |
-
"
|
| 142 |
-
"
|
| 143 |
-
"
|
| 144 |
-
|
| 145 |
-
|
| 146 |
-
"
|
| 147 |
-
"learning_rate": 6.374311926605506e-05,
|
| 148 |
-
"loss": 1.1316,
|
| 149 |
-
"step": 220
|
| 150 |
-
},
|
| 151 |
-
{
|
| 152 |
-
"epoch": 1.14,
|
| 153 |
-
"learning_rate": 6.209174311926606e-05,
|
| 154 |
-
"loss": 1.1899,
|
| 155 |
-
"step": 230
|
| 156 |
-
},
|
| 157 |
-
{
|
| 158 |
-
"epoch": 1.19,
|
| 159 |
-
"learning_rate": 6.044036697247707e-05,
|
| 160 |
-
"loss": 1.1514,
|
| 161 |
-
"step": 240
|
| 162 |
-
},
|
| 163 |
-
{
|
| 164 |
-
"epoch": 1.24,
|
| 165 |
-
"learning_rate": 5.878899082568808e-05,
|
| 166 |
-
"loss": 1.1313,
|
| 167 |
-
"step": 250
|
| 168 |
-
},
|
| 169 |
-
{
|
| 170 |
-
"epoch": 1.29,
|
| 171 |
-
"learning_rate": 5.713761467889909e-05,
|
| 172 |
-
"loss": 1.1409,
|
| 173 |
-
"step": 260
|
| 174 |
-
},
|
| 175 |
-
{
|
| 176 |
-
"epoch": 1.34,
|
| 177 |
-
"learning_rate": 5.54862385321101e-05,
|
| 178 |
-
"loss": 1.1199,
|
| 179 |
-
"step": 270
|
| 180 |
-
},
|
| 181 |
-
{
|
| 182 |
-
"epoch": 1.39,
|
| 183 |
-
"learning_rate": 5.3834862385321106e-05,
|
| 184 |
-
"loss": 1.0977,
|
| 185 |
-
"step": 280
|
| 186 |
-
},
|
| 187 |
-
{
|
| 188 |
-
"epoch": 1.44,
|
| 189 |
-
"learning_rate": 5.2183486238532116e-05,
|
| 190 |
-
"loss": 1.0992,
|
| 191 |
-
"step": 290
|
| 192 |
-
},
|
| 193 |
-
{
|
| 194 |
-
"epoch": 1.49,
|
| 195 |
-
"learning_rate": 5.0532110091743125e-05,
|
| 196 |
-
"loss": 1.188,
|
| 197 |
-
"step": 300
|
| 198 |
-
},
|
| 199 |
-
{
|
| 200 |
-
"epoch": 1.53,
|
| 201 |
-
"learning_rate": 4.8880733944954135e-05,
|
| 202 |
-
"loss": 1.1191,
|
| 203 |
-
"step": 310
|
| 204 |
-
},
|
| 205 |
-
{
|
| 206 |
-
"epoch": 1.58,
|
| 207 |
-
"learning_rate": 4.7229357798165144e-05,
|
| 208 |
-
"loss": 1.0916,
|
| 209 |
-
"step": 320
|
| 210 |
-
},
|
| 211 |
-
{
|
| 212 |
-
"epoch": 1.63,
|
| 213 |
-
"learning_rate": 4.5577981651376154e-05,
|
| 214 |
-
"loss": 1.0855,
|
| 215 |
-
"step": 330
|
| 216 |
-
},
|
| 217 |
-
{
|
| 218 |
-
"epoch": 1.68,
|
| 219 |
-
"learning_rate": 4.3926605504587163e-05,
|
| 220 |
-
"loss": 1.078,
|
| 221 |
-
"step": 340
|
| 222 |
-
},
|
| 223 |
-
{
|
| 224 |
-
"epoch": 1.73,
|
| 225 |
-
"learning_rate": 4.227522935779817e-05,
|
| 226 |
-
"loss": 1.055,
|
| 227 |
-
"step": 350
|
| 228 |
-
},
|
| 229 |
-
{
|
| 230 |
-
"epoch": 1.78,
|
| 231 |
-
"learning_rate": 4.062385321100918e-05,
|
| 232 |
-
"loss": 1.0762,
|
| 233 |
-
"step": 360
|
| 234 |
-
},
|
| 235 |
-
{
|
| 236 |
-
"epoch": 1.83,
|
| 237 |
-
"learning_rate": 3.8972477064220185e-05,
|
| 238 |
-
"loss": 1.078,
|
| 239 |
-
"step": 370
|
| 240 |
-
},
|
| 241 |
-
{
|
| 242 |
-
"epoch": 1.88,
|
| 243 |
-
"learning_rate": 3.7321100917431195e-05,
|
| 244 |
-
"loss": 1.0907,
|
| 245 |
-
"step": 380
|
| 246 |
-
},
|
| 247 |
-
{
|
| 248 |
-
"epoch": 1.93,
|
| 249 |
-
"learning_rate": 3.5669724770642204e-05,
|
| 250 |
-
"loss": 1.0911,
|
| 251 |
-
"step": 390
|
| 252 |
-
},
|
| 253 |
-
{
|
| 254 |
-
"epoch": 1.98,
|
| 255 |
-
"learning_rate": 3.4018348623853214e-05,
|
| 256 |
-
"loss": 1.0531,
|
| 257 |
-
"step": 400
|
| 258 |
-
},
|
| 259 |
-
{
|
| 260 |
-
"epoch": 2.0,
|
| 261 |
-
"eval_accuracy": 0.6732845698362939,
|
| 262 |
-
"eval_loss": 0.891925036907196,
|
| 263 |
-
"eval_runtime": 24.8114,
|
| 264 |
-
"eval_samples_per_second": 115.713,
|
| 265 |
-
"eval_steps_per_second": 3.627,
|
| 266 |
-
"step": 404
|
| 267 |
-
},
|
| 268 |
-
{
|
| 269 |
-
"epoch": 2.03,
|
| 270 |
-
"learning_rate": 3.236697247706422e-05,
|
| 271 |
-
"loss": 1.0555,
|
| 272 |
-
"step": 410
|
| 273 |
-
},
|
| 274 |
-
{
|
| 275 |
-
"epoch": 2.08,
|
| 276 |
-
"learning_rate": 3.071559633027523e-05,
|
| 277 |
-
"loss": 1.0806,
|
| 278 |
-
"step": 420
|
| 279 |
-
},
|
| 280 |
-
{
|
| 281 |
-
"epoch": 2.13,
|
| 282 |
-
"learning_rate": 2.9064220183486242e-05,
|
| 283 |
-
"loss": 1.0574,
|
| 284 |
-
"step": 430
|
| 285 |
-
},
|
| 286 |
-
{
|
| 287 |
-
"epoch": 2.18,
|
| 288 |
-
"learning_rate": 2.7412844036697252e-05,
|
| 289 |
-
"loss": 0.9992,
|
| 290 |
-
"step": 440
|
| 291 |
-
},
|
| 292 |
-
{
|
| 293 |
-
"epoch": 2.23,
|
| 294 |
-
"learning_rate": 2.576146788990826e-05,
|
| 295 |
-
"loss": 1.0317,
|
| 296 |
-
"step": 450
|
| 297 |
-
},
|
| 298 |
-
{
|
| 299 |
-
"epoch": 2.28,
|
| 300 |
-
"learning_rate": 2.4110091743119267e-05,
|
| 301 |
-
"loss": 1.0397,
|
| 302 |
-
"step": 460
|
| 303 |
-
},
|
| 304 |
-
{
|
| 305 |
-
"epoch": 2.33,
|
| 306 |
-
"learning_rate": 2.2458715596330277e-05,
|
| 307 |
-
"loss": 1.0628,
|
| 308 |
-
"step": 470
|
| 309 |
-
},
|
| 310 |
-
{
|
| 311 |
-
"epoch": 2.38,
|
| 312 |
-
"learning_rate": 2.0807339449541286e-05,
|
| 313 |
-
"loss": 1.0128,
|
| 314 |
-
"step": 480
|
| 315 |
-
},
|
| 316 |
-
{
|
| 317 |
-
"epoch": 2.43,
|
| 318 |
-
"learning_rate": 1.9155963302752296e-05,
|
| 319 |
-
"loss": 1.0218,
|
| 320 |
-
"step": 490
|
| 321 |
-
},
|
| 322 |
-
{
|
| 323 |
-
"epoch": 2.48,
|
| 324 |
-
"learning_rate": 1.7504587155963305e-05,
|
| 325 |
-
"loss": 1.0342,
|
| 326 |
-
"step": 500
|
| 327 |
-
},
|
| 328 |
-
{
|
| 329 |
-
"epoch": 2.52,
|
| 330 |
-
"learning_rate": 1.5853211009174315e-05,
|
| 331 |
-
"loss": 1.0246,
|
| 332 |
-
"step": 510
|
| 333 |
-
},
|
| 334 |
-
{
|
| 335 |
-
"epoch": 2.57,
|
| 336 |
-
"learning_rate": 1.4201834862385323e-05,
|
| 337 |
-
"loss": 0.9893,
|
| 338 |
-
"step": 520
|
| 339 |
-
},
|
| 340 |
-
{
|
| 341 |
-
"epoch": 2.62,
|
| 342 |
-
"learning_rate": 1.2550458715596332e-05,
|
| 343 |
-
"loss": 1.0331,
|
| 344 |
-
"step": 530
|
| 345 |
-
},
|
| 346 |
-
{
|
| 347 |
-
"epoch": 2.67,
|
| 348 |
-
"learning_rate": 1.089908256880734e-05,
|
| 349 |
-
"loss": 1.0342,
|
| 350 |
-
"step": 540
|
| 351 |
-
},
|
| 352 |
-
{
|
| 353 |
-
"epoch": 2.72,
|
| 354 |
-
"learning_rate": 9.24770642201835e-06,
|
| 355 |
-
"loss": 0.9767,
|
| 356 |
-
"step": 550
|
| 357 |
-
},
|
| 358 |
-
{
|
| 359 |
-
"epoch": 2.77,
|
| 360 |
-
"learning_rate": 7.596330275229359e-06,
|
| 361 |
-
"loss": 0.983,
|
| 362 |
-
"step": 560
|
| 363 |
-
},
|
| 364 |
-
{
|
| 365 |
-
"epoch": 2.82,
|
| 366 |
-
"learning_rate": 5.944954128440368e-06,
|
| 367 |
-
"loss": 0.991,
|
| 368 |
-
"step": 570
|
| 369 |
-
},
|
| 370 |
-
{
|
| 371 |
-
"epoch": 2.87,
|
| 372 |
-
"learning_rate": 4.293577981651376e-06,
|
| 373 |
-
"loss": 0.9894,
|
| 374 |
-
"step": 580
|
| 375 |
-
},
|
| 376 |
-
{
|
| 377 |
-
"epoch": 2.92,
|
| 378 |
-
"learning_rate": 2.642201834862386e-06,
|
| 379 |
-
"loss": 0.9968,
|
| 380 |
-
"step": 590
|
| 381 |
-
},
|
| 382 |
-
{
|
| 383 |
-
"epoch": 2.97,
|
| 384 |
-
"learning_rate": 9.908256880733947e-07,
|
| 385 |
-
"loss": 1.001,
|
| 386 |
-
"step": 600
|
| 387 |
-
},
|
| 388 |
-
{
|
| 389 |
-
"epoch": 3.0,
|
| 390 |
-
"eval_accuracy": 0.6868686868686869,
|
| 391 |
-
"eval_loss": 0.841149091720581,
|
| 392 |
-
"eval_runtime": 24.894,
|
| 393 |
-
"eval_samples_per_second": 115.329,
|
| 394 |
-
"eval_steps_per_second": 3.615,
|
| 395 |
-
"step": 606
|
| 396 |
-
},
|
| 397 |
-
{
|
| 398 |
-
"epoch": 3.0,
|
| 399 |
-
"step": 606,
|
| 400 |
-
"total_flos": 6.004415924974301e+18,
|
| 401 |
-
"train_loss": 1.1650643325088048,
|
| 402 |
-
"train_runtime": 1992.3663,
|
| 403 |
-
"train_samples_per_second": 38.905,
|
| 404 |
-
"train_steps_per_second": 0.304
|
| 405 |
}
|
| 406 |
],
|
| 407 |
-
"max_steps":
|
| 408 |
-
"num_train_epochs":
|
| 409 |
-
"total_flos":
|
| 410 |
"trial_name": null,
|
| 411 |
"trial_params": null
|
| 412 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.6422849181469871,
|
| 3 |
+
"best_model_checkpoint": "beit-base-patch16-224-pt22k-ft22k-finetuned-FER2013-9e-05/checkpoint-202",
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"global_step": 202,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.05,
|
| 12 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 13 |
+
"loss": 1.9259,
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.1,
|
| 18 |
+
"learning_rate": 8.571428571428571e-05,
|
| 19 |
+
"loss": 1.6569,
|
| 20 |
"step": 20
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.15,
|
| 24 |
+
"learning_rate": 8.552486187845305e-05,
|
| 25 |
+
"loss": 1.4853,
|
| 26 |
"step": 30
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.2,
|
| 30 |
+
"learning_rate": 8.055248618784531e-05,
|
| 31 |
+
"loss": 1.512,
|
| 32 |
"step": 40
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.25,
|
| 36 |
+
"learning_rate": 7.558011049723757e-05,
|
| 37 |
+
"loss": 1.395,
|
| 38 |
"step": 50
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.3,
|
| 42 |
+
"learning_rate": 7.060773480662983e-05,
|
| 43 |
+
"loss": 1.3225,
|
| 44 |
"step": 60
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.35,
|
| 48 |
+
"learning_rate": 6.563535911602211e-05,
|
| 49 |
+
"loss": 1.3529,
|
| 50 |
"step": 70
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.4,
|
| 54 |
+
"learning_rate": 6.0662983425414375e-05,
|
| 55 |
+
"loss": 1.3234,
|
| 56 |
"step": 80
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 0.45,
|
| 60 |
+
"learning_rate": 5.569060773480663e-05,
|
| 61 |
+
"loss": 1.2544,
|
| 62 |
"step": 90
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 0.5,
|
| 66 |
+
"learning_rate": 5.07182320441989e-05,
|
| 67 |
+
"loss": 1.2481,
|
| 68 |
"step": 100
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 0.54,
|
| 72 |
+
"learning_rate": 4.5745856353591164e-05,
|
| 73 |
+
"loss": 1.2172,
|
| 74 |
"step": 110
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 0.59,
|
| 78 |
+
"learning_rate": 4.077348066298343e-05,
|
| 79 |
+
"loss": 1.249,
|
| 80 |
"step": 120
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.64,
|
| 84 |
+
"learning_rate": 3.580110497237569e-05,
|
| 85 |
+
"loss": 1.2136,
|
| 86 |
"step": 130
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.69,
|
| 90 |
+
"learning_rate": 3.082872928176796e-05,
|
| 91 |
+
"loss": 1.1581,
|
| 92 |
"step": 140
|
| 93 |
},
|
| 94 |
{
|
| 95 |
"epoch": 0.74,
|
| 96 |
+
"learning_rate": 2.585635359116022e-05,
|
| 97 |
+
"loss": 1.1803,
|
| 98 |
"step": 150
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 0.79,
|
| 102 |
+
"learning_rate": 2.0883977900552486e-05,
|
| 103 |
+
"loss": 1.2273,
|
| 104 |
"step": 160
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 0.84,
|
| 108 |
+
"learning_rate": 1.591160220994475e-05,
|
| 109 |
+
"loss": 1.1976,
|
| 110 |
"step": 170
|
| 111 |
},
|
| 112 |
{
|
| 113 |
"epoch": 0.89,
|
| 114 |
+
"learning_rate": 1.0939226519337016e-05,
|
| 115 |
+
"loss": 1.1569,
|
| 116 |
"step": 180
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 0.94,
|
| 120 |
+
"learning_rate": 5.966850828729282e-06,
|
| 121 |
+
"loss": 1.178,
|
| 122 |
"step": 190
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 0.99,
|
| 126 |
+
"learning_rate": 9.944751381215469e-07,
|
| 127 |
+
"loss": 1.1404,
|
| 128 |
"step": 200
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 1.0,
|
| 132 |
+
"eval_accuracy": 0.6422849181469871,
|
| 133 |
+
"eval_loss": 0.9593217372894287,
|
| 134 |
+
"eval_runtime": 24.866,
|
| 135 |
+
"eval_samples_per_second": 115.459,
|
| 136 |
+
"eval_steps_per_second": 3.619,
|
| 137 |
"step": 202
|
| 138 |
},
|
| 139 |
{
|
| 140 |
+
"epoch": 1.0,
|
| 141 |
+
"step": 202,
|
| 142 |
+
"total_flos": 2.0014719749914337e+18,
|
| 143 |
+
"train_loss": 1.316133418885788,
|
| 144 |
+
"train_runtime": 615.4563,
|
| 145 |
+
"train_samples_per_second": 41.982,
|
| 146 |
+
"train_steps_per_second": 0.328
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 147 |
}
|
| 148 |
],
|
| 149 |
+
"max_steps": 202,
|
| 150 |
+
"num_train_epochs": 1,
|
| 151 |
+
"total_flos": 2.0014719749914337e+18,
|
| 152 |
"trial_name": null,
|
| 153 |
"trial_params": null
|
| 154 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3375
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88fa3bdfe77d35d59be85f3d7634efd03b671815f6a760b0cf0b07a5a98a2528
|
| 3 |
size 3375
|