Training in progress, epoch 0
Browse files- all_results.json +5 -5
- pytorch_model.bin +2 -2
- test_results.json +5 -5
- trainer_state.json +105 -645
- training_args.bin +1 -1
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.25,
|
| 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": 3.25,
|
| 3 |
+
"eval_accuracy": 0.8387096774193549,
|
| 4 |
+
"eval_loss": 0.4286610186100006,
|
| 5 |
+
"eval_runtime": 12.6984,
|
| 6 |
+
"eval_samples_per_second": 12.206,
|
| 7 |
+
"eval_steps_per_second": 3.071
|
| 8 |
}
|
pytorch_model.bin
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:d0297de5a668e3575a74144d278c911fb0b63d22e20f7c4ecf55dbeb6da3791a
|
| 3 |
+
size 345004566
|
test_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.25,
|
| 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": 3.25,
|
| 3 |
+
"eval_accuracy": 0.8387096774193549,
|
| 4 |
+
"eval_loss": 0.4286610186100006,
|
| 5 |
+
"eval_runtime": 12.6984,
|
| 6 |
+
"eval_samples_per_second": 12.206,
|
| 7 |
+
"eval_steps_per_second": 3.071
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,797 +1,257 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-
|
| 4 |
"epoch": 3.25,
|
| 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": 0.01,
|
| 12 |
-
"learning_rate": 4.166666666666667e-06,
|
| 13 |
-
"loss": 2.4409,
|
| 14 |
-
"step": 10
|
| 15 |
-
},
|
| 16 |
-
{
|
| 17 |
-
"epoch": 0.02,
|
| 18 |
-
"learning_rate": 8.333333333333334e-06,
|
| 19 |
-
"loss": 2.2714,
|
| 20 |
-
"step": 20
|
| 21 |
-
},
|
| 22 |
-
{
|
| 23 |
-
"epoch": 0.03,
|
| 24 |
-
"learning_rate": 1.25e-05,
|
| 25 |
-
"loss": 2.4193,
|
| 26 |
-
"step": 30
|
| 27 |
-
},
|
| 28 |
{
|
| 29 |
"epoch": 0.03,
|
| 30 |
"learning_rate": 1.6666666666666667e-05,
|
| 31 |
-
"loss": 2.
|
| 32 |
-
"step":
|
| 33 |
-
},
|
| 34 |
-
{
|
| 35 |
-
"epoch": 0.04,
|
| 36 |
-
"learning_rate": 2.0833333333333336e-05,
|
| 37 |
-
"loss": 2.413,
|
| 38 |
-
"step": 50
|
| 39 |
-
},
|
| 40 |
-
{
|
| 41 |
-
"epoch": 0.05,
|
| 42 |
-
"learning_rate": 2.5e-05,
|
| 43 |
-
"loss": 2.2647,
|
| 44 |
-
"step": 60
|
| 45 |
-
},
|
| 46 |
-
{
|
| 47 |
-
"epoch": 0.06,
|
| 48 |
-
"learning_rate": 2.916666666666667e-05,
|
| 49 |
-
"loss": 2.3393,
|
| 50 |
-
"step": 70
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.07,
|
| 54 |
"learning_rate": 3.3333333333333335e-05,
|
| 55 |
-
"loss": 2.
|
| 56 |
-
"step":
|
| 57 |
-
},
|
| 58 |
-
{
|
| 59 |
-
"epoch": 0.07,
|
| 60 |
-
"learning_rate": 3.7500000000000003e-05,
|
| 61 |
-
"loss": 1.9369,
|
| 62 |
-
"step": 90
|
| 63 |
-
},
|
| 64 |
-
{
|
| 65 |
-
"epoch": 0.08,
|
| 66 |
-
"learning_rate": 4.166666666666667e-05,
|
| 67 |
-
"loss": 2.0877,
|
| 68 |
-
"step": 100
|
| 69 |
-
},
|
| 70 |
-
{
|
| 71 |
-
"epoch": 0.09,
|
| 72 |
-
"learning_rate": 4.5833333333333334e-05,
|
| 73 |
-
"loss": 2.3769,
|
| 74 |
-
"step": 110
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 0.1,
|
| 78 |
"learning_rate": 5e-05,
|
| 79 |
-
"loss": 2.
|
| 80 |
-
"step":
|
| 81 |
-
},
|
| 82 |
-
{
|
| 83 |
-
"epoch": 0.11,
|
| 84 |
-
"learning_rate": 4.9537037037037035e-05,
|
| 85 |
-
"loss": 2.3568,
|
| 86 |
-
"step": 130
|
| 87 |
-
},
|
| 88 |
-
{
|
| 89 |
-
"epoch": 0.12,
|
| 90 |
-
"learning_rate": 4.9074074074074075e-05,
|
| 91 |
-
"loss": 2.1998,
|
| 92 |
-
"step": 140
|
| 93 |
-
},
|
| 94 |
-
{
|
| 95 |
-
"epoch": 0.12,
|
| 96 |
-
"learning_rate": 4.8611111111111115e-05,
|
| 97 |
-
"loss": 1.6882,
|
| 98 |
-
"step": 150
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 0.13,
|
| 102 |
"learning_rate": 4.814814814814815e-05,
|
| 103 |
-
"loss":
|
| 104 |
-
"step":
|
| 105 |
-
},
|
| 106 |
-
{
|
| 107 |
-
"epoch": 0.14,
|
| 108 |
-
"learning_rate": 4.768518518518519e-05,
|
| 109 |
-
"loss": 1.8284,
|
| 110 |
-
"step": 170
|
| 111 |
-
},
|
| 112 |
-
{
|
| 113 |
-
"epoch": 0.15,
|
| 114 |
-
"learning_rate": 4.722222222222222e-05,
|
| 115 |
-
"loss": 1.9579,
|
| 116 |
-
"step": 180
|
| 117 |
-
},
|
| 118 |
-
{
|
| 119 |
-
"epoch": 0.16,
|
| 120 |
-
"learning_rate": 4.675925925925926e-05,
|
| 121 |
-
"loss": 2.2044,
|
| 122 |
-
"step": 190
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 0.17,
|
| 126 |
"learning_rate": 4.62962962962963e-05,
|
| 127 |
-
"loss":
|
| 128 |
-
"step":
|
| 129 |
-
},
|
| 130 |
-
{
|
| 131 |
-
"epoch": 0.17,
|
| 132 |
-
"learning_rate": 4.5833333333333334e-05,
|
| 133 |
-
"loss": 2.4752,
|
| 134 |
-
"step": 210
|
| 135 |
-
},
|
| 136 |
-
{
|
| 137 |
-
"epoch": 0.18,
|
| 138 |
-
"learning_rate": 4.5370370370370374e-05,
|
| 139 |
-
"loss": 1.7249,
|
| 140 |
-
"step": 220
|
| 141 |
-
},
|
| 142 |
-
{
|
| 143 |
-
"epoch": 0.19,
|
| 144 |
-
"learning_rate": 4.490740740740741e-05,
|
| 145 |
-
"loss": 1.7212,
|
| 146 |
-
"step": 230
|
| 147 |
},
|
| 148 |
{
|
| 149 |
"epoch": 0.2,
|
| 150 |
"learning_rate": 4.4444444444444447e-05,
|
| 151 |
-
"loss":
|
| 152 |
-
"step":
|
| 153 |
-
},
|
| 154 |
-
{
|
| 155 |
-
"epoch": 0.21,
|
| 156 |
-
"learning_rate": 4.3981481481481486e-05,
|
| 157 |
-
"loss": 1.7036,
|
| 158 |
-
"step": 250
|
| 159 |
-
},
|
| 160 |
-
{
|
| 161 |
-
"epoch": 0.22,
|
| 162 |
-
"learning_rate": 4.351851851851852e-05,
|
| 163 |
-
"loss": 1.9239,
|
| 164 |
-
"step": 260
|
| 165 |
-
},
|
| 166 |
-
{
|
| 167 |
-
"epoch": 0.23,
|
| 168 |
-
"learning_rate": 4.305555555555556e-05,
|
| 169 |
-
"loss": 1.5625,
|
| 170 |
-
"step": 270
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 0.23,
|
| 174 |
"learning_rate": 4.259259259259259e-05,
|
| 175 |
-
"loss": 1.
|
| 176 |
-
"step":
|
| 177 |
-
},
|
| 178 |
-
{
|
| 179 |
-
"epoch": 0.24,
|
| 180 |
-
"learning_rate": 4.212962962962963e-05,
|
| 181 |
-
"loss": 1.2661,
|
| 182 |
-
"step": 290
|
| 183 |
-
},
|
| 184 |
-
{
|
| 185 |
-
"epoch": 0.25,
|
| 186 |
-
"learning_rate": 4.166666666666667e-05,
|
| 187 |
-
"loss": 1.9142,
|
| 188 |
-
"step": 300
|
| 189 |
},
|
| 190 |
{
|
| 191 |
"epoch": 0.25,
|
| 192 |
-
"eval_accuracy": 0.
|
| 193 |
-
"eval_loss": 1.
|
| 194 |
-
"eval_runtime":
|
| 195 |
-
"eval_samples_per_second":
|
| 196 |
-
"eval_steps_per_second":
|
| 197 |
-
"step":
|
| 198 |
-
},
|
| 199 |
-
{
|
| 200 |
-
"epoch": 1.01,
|
| 201 |
-
"learning_rate": 4.1203703703703705e-05,
|
| 202 |
-
"loss": 1.0597,
|
| 203 |
-
"step": 310
|
| 204 |
},
|
| 205 |
{
|
| 206 |
"epoch": 1.02,
|
| 207 |
"learning_rate": 4.074074074074074e-05,
|
| 208 |
-
"loss": 1.
|
| 209 |
-
"step":
|
| 210 |
-
},
|
| 211 |
-
{
|
| 212 |
-
"epoch": 1.02,
|
| 213 |
-
"learning_rate": 4.027777777777778e-05,
|
| 214 |
-
"loss": 1.66,
|
| 215 |
-
"step": 330
|
| 216 |
-
},
|
| 217 |
-
{
|
| 218 |
-
"epoch": 1.03,
|
| 219 |
-
"learning_rate": 3.981481481481482e-05,
|
| 220 |
-
"loss": 1.2875,
|
| 221 |
-
"step": 340
|
| 222 |
-
},
|
| 223 |
-
{
|
| 224 |
-
"epoch": 1.04,
|
| 225 |
-
"learning_rate": 3.935185185185186e-05,
|
| 226 |
-
"loss": 0.6674,
|
| 227 |
-
"step": 350
|
| 228 |
},
|
| 229 |
{
|
| 230 |
"epoch": 1.05,
|
| 231 |
"learning_rate": 3.888888888888889e-05,
|
| 232 |
-
"loss":
|
| 233 |
-
"step":
|
| 234 |
-
},
|
| 235 |
-
{
|
| 236 |
-
"epoch": 1.06,
|
| 237 |
-
"learning_rate": 3.8425925925925924e-05,
|
| 238 |
-
"loss": 0.9939,
|
| 239 |
-
"step": 370
|
| 240 |
-
},
|
| 241 |
-
{
|
| 242 |
-
"epoch": 1.07,
|
| 243 |
-
"learning_rate": 3.7962962962962964e-05,
|
| 244 |
-
"loss": 1.4937,
|
| 245 |
-
"step": 380
|
| 246 |
-
},
|
| 247 |
-
{
|
| 248 |
-
"epoch": 1.07,
|
| 249 |
-
"learning_rate": 3.7500000000000003e-05,
|
| 250 |
-
"loss": 1.7014,
|
| 251 |
-
"step": 390
|
| 252 |
},
|
| 253 |
{
|
| 254 |
"epoch": 1.08,
|
| 255 |
"learning_rate": 3.7037037037037037e-05,
|
| 256 |
-
"loss": 1.
|
| 257 |
-
"step":
|
| 258 |
-
},
|
| 259 |
-
{
|
| 260 |
-
"epoch": 1.09,
|
| 261 |
-
"learning_rate": 3.6574074074074076e-05,
|
| 262 |
-
"loss": 0.7352,
|
| 263 |
-
"step": 410
|
| 264 |
-
},
|
| 265 |
-
{
|
| 266 |
-
"epoch": 1.1,
|
| 267 |
-
"learning_rate": 3.611111111111111e-05,
|
| 268 |
-
"loss": 1.0035,
|
| 269 |
-
"step": 420
|
| 270 |
-
},
|
| 271 |
-
{
|
| 272 |
-
"epoch": 1.11,
|
| 273 |
-
"learning_rate": 3.564814814814815e-05,
|
| 274 |
-
"loss": 0.897,
|
| 275 |
-
"step": 430
|
| 276 |
},
|
| 277 |
{
|
| 278 |
"epoch": 1.12,
|
| 279 |
"learning_rate": 3.518518518518519e-05,
|
| 280 |
-
"loss": 0.
|
| 281 |
-
"step":
|
| 282 |
-
},
|
| 283 |
-
{
|
| 284 |
-
"epoch": 1.12,
|
| 285 |
-
"learning_rate": 3.472222222222222e-05,
|
| 286 |
-
"loss": 1.3736,
|
| 287 |
-
"step": 450
|
| 288 |
-
},
|
| 289 |
-
{
|
| 290 |
-
"epoch": 1.13,
|
| 291 |
-
"learning_rate": 3.425925925925926e-05,
|
| 292 |
-
"loss": 0.9104,
|
| 293 |
-
"step": 460
|
| 294 |
-
},
|
| 295 |
-
{
|
| 296 |
-
"epoch": 1.14,
|
| 297 |
-
"learning_rate": 3.3796296296296295e-05,
|
| 298 |
-
"loss": 0.8664,
|
| 299 |
-
"step": 470
|
| 300 |
},
|
| 301 |
{
|
| 302 |
"epoch": 1.15,
|
| 303 |
"learning_rate": 3.3333333333333335e-05,
|
| 304 |
-
"loss": 1.
|
| 305 |
-
"step":
|
| 306 |
-
},
|
| 307 |
-
{
|
| 308 |
-
"epoch": 1.16,
|
| 309 |
-
"learning_rate": 3.2870370370370375e-05,
|
| 310 |
-
"loss": 1.3923,
|
| 311 |
-
"step": 490
|
| 312 |
-
},
|
| 313 |
-
{
|
| 314 |
-
"epoch": 1.17,
|
| 315 |
-
"learning_rate": 3.240740740740741e-05,
|
| 316 |
-
"loss": 0.9565,
|
| 317 |
-
"step": 500
|
| 318 |
-
},
|
| 319 |
-
{
|
| 320 |
-
"epoch": 1.18,
|
| 321 |
-
"learning_rate": 3.194444444444444e-05,
|
| 322 |
-
"loss": 0.5909,
|
| 323 |
-
"step": 510
|
| 324 |
},
|
| 325 |
{
|
| 326 |
"epoch": 1.18,
|
| 327 |
"learning_rate": 3.148148148148148e-05,
|
| 328 |
-
"loss": 0.
|
| 329 |
-
"step":
|
| 330 |
-
},
|
| 331 |
-
{
|
| 332 |
-
"epoch": 1.19,
|
| 333 |
-
"learning_rate": 3.101851851851852e-05,
|
| 334 |
-
"loss": 1.2527,
|
| 335 |
-
"step": 530
|
| 336 |
-
},
|
| 337 |
-
{
|
| 338 |
-
"epoch": 1.2,
|
| 339 |
-
"learning_rate": 3.055555555555556e-05,
|
| 340 |
-
"loss": 1.1361,
|
| 341 |
-
"step": 540
|
| 342 |
-
},
|
| 343 |
-
{
|
| 344 |
-
"epoch": 1.21,
|
| 345 |
-
"learning_rate": 3.0092592592592593e-05,
|
| 346 |
-
"loss": 0.2199,
|
| 347 |
-
"step": 550
|
| 348 |
},
|
| 349 |
{
|
| 350 |
"epoch": 1.22,
|
| 351 |
"learning_rate": 2.962962962962963e-05,
|
| 352 |
-
"loss": 0.
|
| 353 |
-
"step":
|
| 354 |
-
},
|
| 355 |
-
{
|
| 356 |
-
"epoch": 1.23,
|
| 357 |
-
"learning_rate": 2.916666666666667e-05,
|
| 358 |
-
"loss": 1.9032,
|
| 359 |
-
"step": 570
|
| 360 |
-
},
|
| 361 |
-
{
|
| 362 |
-
"epoch": 1.23,
|
| 363 |
-
"learning_rate": 2.8703703703703706e-05,
|
| 364 |
-
"loss": 1.7757,
|
| 365 |
-
"step": 580
|
| 366 |
-
},
|
| 367 |
-
{
|
| 368 |
-
"epoch": 1.24,
|
| 369 |
-
"learning_rate": 2.824074074074074e-05,
|
| 370 |
-
"loss": 1.257,
|
| 371 |
-
"step": 590
|
| 372 |
},
|
| 373 |
{
|
| 374 |
"epoch": 1.25,
|
| 375 |
"learning_rate": 2.777777777777778e-05,
|
| 376 |
-
"loss":
|
| 377 |
-
"step":
|
| 378 |
},
|
| 379 |
{
|
| 380 |
"epoch": 1.25,
|
| 381 |
-
"eval_accuracy": 0.
|
| 382 |
-
"eval_loss":
|
| 383 |
-
"eval_runtime":
|
| 384 |
-
"eval_samples_per_second":
|
| 385 |
-
"eval_steps_per_second":
|
| 386 |
-
"step":
|
| 387 |
-
},
|
| 388 |
-
{
|
| 389 |
-
"epoch": 2.01,
|
| 390 |
-
"learning_rate": 2.7314814814814816e-05,
|
| 391 |
-
"loss": 0.5868,
|
| 392 |
-
"step": 610
|
| 393 |
-
},
|
| 394 |
-
{
|
| 395 |
-
"epoch": 2.02,
|
| 396 |
-
"learning_rate": 2.6851851851851855e-05,
|
| 397 |
-
"loss": 0.3039,
|
| 398 |
-
"step": 620
|
| 399 |
-
},
|
| 400 |
-
{
|
| 401 |
-
"epoch": 2.02,
|
| 402 |
-
"learning_rate": 2.6388888888888892e-05,
|
| 403 |
-
"loss": 0.0372,
|
| 404 |
-
"step": 630
|
| 405 |
},
|
| 406 |
{
|
| 407 |
"epoch": 2.03,
|
| 408 |
"learning_rate": 2.5925925925925925e-05,
|
| 409 |
-
"loss": 0.
|
| 410 |
-
"step":
|
| 411 |
-
},
|
| 412 |
-
{
|
| 413 |
-
"epoch": 2.04,
|
| 414 |
-
"learning_rate": 2.5462962962962965e-05,
|
| 415 |
-
"loss": 0.4467,
|
| 416 |
-
"step": 650
|
| 417 |
-
},
|
| 418 |
-
{
|
| 419 |
-
"epoch": 2.05,
|
| 420 |
-
"learning_rate": 2.5e-05,
|
| 421 |
-
"loss": 0.6143,
|
| 422 |
-
"step": 660
|
| 423 |
-
},
|
| 424 |
-
{
|
| 425 |
-
"epoch": 2.06,
|
| 426 |
-
"learning_rate": 2.4537037037037038e-05,
|
| 427 |
-
"loss": 0.2268,
|
| 428 |
-
"step": 670
|
| 429 |
},
|
| 430 |
{
|
| 431 |
"epoch": 2.07,
|
| 432 |
"learning_rate": 2.4074074074074074e-05,
|
| 433 |
-
"loss": 0.
|
| 434 |
-
"step":
|
| 435 |
-
},
|
| 436 |
-
{
|
| 437 |
-
"epoch": 2.08,
|
| 438 |
-
"learning_rate": 2.361111111111111e-05,
|
| 439 |
-
"loss": 0.315,
|
| 440 |
-
"step": 690
|
| 441 |
-
},
|
| 442 |
-
{
|
| 443 |
-
"epoch": 2.08,
|
| 444 |
-
"learning_rate": 2.314814814814815e-05,
|
| 445 |
-
"loss": 0.2197,
|
| 446 |
-
"step": 700
|
| 447 |
-
},
|
| 448 |
-
{
|
| 449 |
-
"epoch": 2.09,
|
| 450 |
-
"learning_rate": 2.2685185185185187e-05,
|
| 451 |
-
"loss": 0.0526,
|
| 452 |
-
"step": 710
|
| 453 |
},
|
| 454 |
{
|
| 455 |
"epoch": 2.1,
|
| 456 |
"learning_rate": 2.2222222222222223e-05,
|
| 457 |
-
"loss": 0.
|
| 458 |
-
"step":
|
| 459 |
-
},
|
| 460 |
-
{
|
| 461 |
-
"epoch": 2.11,
|
| 462 |
-
"learning_rate": 2.175925925925926e-05,
|
| 463 |
-
"loss": 0.8258,
|
| 464 |
-
"step": 730
|
| 465 |
-
},
|
| 466 |
-
{
|
| 467 |
-
"epoch": 2.12,
|
| 468 |
-
"learning_rate": 2.1296296296296296e-05,
|
| 469 |
-
"loss": 0.0145,
|
| 470 |
-
"step": 740
|
| 471 |
-
},
|
| 472 |
-
{
|
| 473 |
-
"epoch": 2.12,
|
| 474 |
-
"learning_rate": 2.0833333333333336e-05,
|
| 475 |
-
"loss": 0.4996,
|
| 476 |
-
"step": 750
|
| 477 |
},
|
| 478 |
{
|
| 479 |
"epoch": 2.13,
|
| 480 |
"learning_rate": 2.037037037037037e-05,
|
| 481 |
-
"loss": 0.
|
| 482 |
-
"step":
|
| 483 |
-
},
|
| 484 |
-
{
|
| 485 |
-
"epoch": 2.14,
|
| 486 |
-
"learning_rate": 1.990740740740741e-05,
|
| 487 |
-
"loss": 0.2202,
|
| 488 |
-
"step": 770
|
| 489 |
-
},
|
| 490 |
-
{
|
| 491 |
-
"epoch": 2.15,
|
| 492 |
-
"learning_rate": 1.9444444444444445e-05,
|
| 493 |
-
"loss": 0.3831,
|
| 494 |
-
"step": 780
|
| 495 |
-
},
|
| 496 |
-
{
|
| 497 |
-
"epoch": 2.16,
|
| 498 |
-
"learning_rate": 1.8981481481481482e-05,
|
| 499 |
-
"loss": 0.5722,
|
| 500 |
-
"step": 790
|
| 501 |
},
|
| 502 |
{
|
| 503 |
"epoch": 2.17,
|
| 504 |
"learning_rate": 1.8518518518518518e-05,
|
| 505 |
-
"loss": 0.
|
| 506 |
-
"step":
|
| 507 |
-
},
|
| 508 |
-
{
|
| 509 |
-
"epoch": 2.17,
|
| 510 |
-
"learning_rate": 1.8055555555555555e-05,
|
| 511 |
-
"loss": 0.0518,
|
| 512 |
-
"step": 810
|
| 513 |
-
},
|
| 514 |
-
{
|
| 515 |
-
"epoch": 2.18,
|
| 516 |
-
"learning_rate": 1.7592592592592595e-05,
|
| 517 |
-
"loss": 0.0928,
|
| 518 |
-
"step": 820
|
| 519 |
-
},
|
| 520 |
-
{
|
| 521 |
-
"epoch": 2.19,
|
| 522 |
-
"learning_rate": 1.712962962962963e-05,
|
| 523 |
-
"loss": 0.3528,
|
| 524 |
-
"step": 830
|
| 525 |
},
|
| 526 |
{
|
| 527 |
"epoch": 2.2,
|
| 528 |
"learning_rate": 1.6666666666666667e-05,
|
| 529 |
-
"loss": 0.
|
| 530 |
-
"step":
|
| 531 |
-
},
|
| 532 |
-
{
|
| 533 |
-
"epoch": 2.21,
|
| 534 |
-
"learning_rate": 1.6203703703703704e-05,
|
| 535 |
-
"loss": 0.5542,
|
| 536 |
-
"step": 850
|
| 537 |
-
},
|
| 538 |
-
{
|
| 539 |
-
"epoch": 2.22,
|
| 540 |
-
"learning_rate": 1.574074074074074e-05,
|
| 541 |
-
"loss": 0.6221,
|
| 542 |
-
"step": 860
|
| 543 |
-
},
|
| 544 |
-
{
|
| 545 |
-
"epoch": 2.23,
|
| 546 |
-
"learning_rate": 1.527777777777778e-05,
|
| 547 |
-
"loss": 0.0083,
|
| 548 |
-
"step": 870
|
| 549 |
},
|
| 550 |
{
|
| 551 |
"epoch": 2.23,
|
| 552 |
"learning_rate": 1.4814814814814815e-05,
|
| 553 |
-
"loss": 0.
|
| 554 |
-
"step":
|
| 555 |
-
},
|
| 556 |
-
{
|
| 557 |
-
"epoch": 2.24,
|
| 558 |
-
"learning_rate": 1.4351851851851853e-05,
|
| 559 |
-
"loss": 0.2397,
|
| 560 |
-
"step": 890
|
| 561 |
-
},
|
| 562 |
-
{
|
| 563 |
-
"epoch": 2.25,
|
| 564 |
-
"learning_rate": 1.388888888888889e-05,
|
| 565 |
-
"loss": 0.1054,
|
| 566 |
-
"step": 900
|
| 567 |
},
|
| 568 |
{
|
| 569 |
"epoch": 2.25,
|
| 570 |
-
"eval_accuracy": 0.
|
| 571 |
-
"eval_loss": 0.
|
| 572 |
-
"eval_runtime":
|
| 573 |
-
"eval_samples_per_second":
|
| 574 |
-
"eval_steps_per_second":
|
| 575 |
-
"step":
|
| 576 |
-
},
|
| 577 |
-
{
|
| 578 |
-
"epoch": 3.01,
|
| 579 |
-
"learning_rate": 1.3425925925925928e-05,
|
| 580 |
-
"loss": 0.0559,
|
| 581 |
-
"step": 910
|
| 582 |
},
|
| 583 |
{
|
| 584 |
"epoch": 3.02,
|
| 585 |
"learning_rate": 1.2962962962962962e-05,
|
| 586 |
-
"loss": 0.
|
| 587 |
-
"step":
|
| 588 |
-
},
|
| 589 |
-
{
|
| 590 |
-
"epoch": 3.02,
|
| 591 |
-
"learning_rate": 1.25e-05,
|
| 592 |
-
"loss": 0.0173,
|
| 593 |
-
"step": 930
|
| 594 |
-
},
|
| 595 |
-
{
|
| 596 |
-
"epoch": 3.03,
|
| 597 |
-
"learning_rate": 1.2037037037037037e-05,
|
| 598 |
-
"loss": 0.017,
|
| 599 |
-
"step": 940
|
| 600 |
-
},
|
| 601 |
-
{
|
| 602 |
-
"epoch": 3.04,
|
| 603 |
-
"learning_rate": 1.1574074074074075e-05,
|
| 604 |
-
"loss": 0.1396,
|
| 605 |
-
"step": 950
|
| 606 |
},
|
| 607 |
{
|
| 608 |
"epoch": 3.05,
|
| 609 |
"learning_rate": 1.1111111111111112e-05,
|
| 610 |
-
"loss": 0.
|
| 611 |
-
"step":
|
| 612 |
-
},
|
| 613 |
-
{
|
| 614 |
-
"epoch": 3.06,
|
| 615 |
-
"learning_rate": 1.0648148148148148e-05,
|
| 616 |
-
"loss": 0.0069,
|
| 617 |
-
"step": 970
|
| 618 |
-
},
|
| 619 |
-
{
|
| 620 |
-
"epoch": 3.07,
|
| 621 |
-
"learning_rate": 1.0185185185185185e-05,
|
| 622 |
-
"loss": 0.0354,
|
| 623 |
-
"step": 980
|
| 624 |
-
},
|
| 625 |
-
{
|
| 626 |
-
"epoch": 3.08,
|
| 627 |
-
"learning_rate": 9.722222222222223e-06,
|
| 628 |
-
"loss": 0.0286,
|
| 629 |
-
"step": 990
|
| 630 |
},
|
| 631 |
{
|
| 632 |
"epoch": 3.08,
|
| 633 |
"learning_rate": 9.259259259259259e-06,
|
| 634 |
-
"loss": 0.
|
| 635 |
-
"step":
|
| 636 |
-
},
|
| 637 |
-
{
|
| 638 |
-
"epoch": 3.09,
|
| 639 |
-
"learning_rate": 8.796296296296297e-06,
|
| 640 |
-
"loss": 0.3499,
|
| 641 |
-
"step": 1010
|
| 642 |
-
},
|
| 643 |
-
{
|
| 644 |
-
"epoch": 3.1,
|
| 645 |
-
"learning_rate": 8.333333333333334e-06,
|
| 646 |
-
"loss": 0.0078,
|
| 647 |
-
"step": 1020
|
| 648 |
-
},
|
| 649 |
-
{
|
| 650 |
-
"epoch": 3.11,
|
| 651 |
-
"learning_rate": 7.87037037037037e-06,
|
| 652 |
-
"loss": 0.1362,
|
| 653 |
-
"step": 1030
|
| 654 |
},
|
| 655 |
{
|
| 656 |
"epoch": 3.12,
|
| 657 |
"learning_rate": 7.4074074074074075e-06,
|
| 658 |
-
"loss": 0.
|
| 659 |
-
"step":
|
| 660 |
-
},
|
| 661 |
-
{
|
| 662 |
-
"epoch": 3.12,
|
| 663 |
-
"learning_rate": 6.944444444444445e-06,
|
| 664 |
-
"loss": 0.0396,
|
| 665 |
-
"step": 1050
|
| 666 |
-
},
|
| 667 |
-
{
|
| 668 |
-
"epoch": 3.13,
|
| 669 |
-
"learning_rate": 6.481481481481481e-06,
|
| 670 |
-
"loss": 0.0284,
|
| 671 |
-
"step": 1060
|
| 672 |
-
},
|
| 673 |
-
{
|
| 674 |
-
"epoch": 3.14,
|
| 675 |
-
"learning_rate": 6.0185185185185185e-06,
|
| 676 |
-
"loss": 0.4627,
|
| 677 |
-
"step": 1070
|
| 678 |
},
|
| 679 |
{
|
| 680 |
"epoch": 3.15,
|
| 681 |
"learning_rate": 5.555555555555556e-06,
|
| 682 |
-
"loss": 0.
|
| 683 |
-
"step":
|
| 684 |
-
},
|
| 685 |
-
{
|
| 686 |
-
"epoch": 3.16,
|
| 687 |
-
"learning_rate": 5.092592592592592e-06,
|
| 688 |
-
"loss": 0.3487,
|
| 689 |
-
"step": 1090
|
| 690 |
-
},
|
| 691 |
-
{
|
| 692 |
-
"epoch": 3.17,
|
| 693 |
-
"learning_rate": 4.6296296296296296e-06,
|
| 694 |
-
"loss": 0.0043,
|
| 695 |
-
"step": 1100
|
| 696 |
-
},
|
| 697 |
-
{
|
| 698 |
-
"epoch": 3.17,
|
| 699 |
-
"learning_rate": 4.166666666666667e-06,
|
| 700 |
-
"loss": 0.0374,
|
| 701 |
-
"step": 1110
|
| 702 |
},
|
| 703 |
{
|
| 704 |
"epoch": 3.18,
|
| 705 |
"learning_rate": 3.7037037037037037e-06,
|
| 706 |
-
"loss": 0.
|
| 707 |
-
"step":
|
| 708 |
-
},
|
| 709 |
-
{
|
| 710 |
-
"epoch": 3.19,
|
| 711 |
-
"learning_rate": 3.2407407407407406e-06,
|
| 712 |
-
"loss": 0.0039,
|
| 713 |
-
"step": 1130
|
| 714 |
-
},
|
| 715 |
-
{
|
| 716 |
-
"epoch": 3.2,
|
| 717 |
-
"learning_rate": 2.777777777777778e-06,
|
| 718 |
-
"loss": 0.3257,
|
| 719 |
-
"step": 1140
|
| 720 |
-
},
|
| 721 |
-
{
|
| 722 |
-
"epoch": 3.21,
|
| 723 |
-
"learning_rate": 2.3148148148148148e-06,
|
| 724 |
-
"loss": 0.0092,
|
| 725 |
-
"step": 1150
|
| 726 |
},
|
| 727 |
{
|
| 728 |
"epoch": 3.22,
|
| 729 |
"learning_rate": 1.8518518518518519e-06,
|
| 730 |
-
"loss": 0.
|
| 731 |
-
"step":
|
| 732 |
-
},
|
| 733 |
-
{
|
| 734 |
-
"epoch": 3.23,
|
| 735 |
-
"learning_rate": 1.388888888888889e-06,
|
| 736 |
-
"loss": 0.1857,
|
| 737 |
-
"step": 1170
|
| 738 |
-
},
|
| 739 |
-
{
|
| 740 |
-
"epoch": 3.23,
|
| 741 |
-
"learning_rate": 9.259259259259259e-07,
|
| 742 |
-
"loss": 0.1795,
|
| 743 |
-
"step": 1180
|
| 744 |
-
},
|
| 745 |
-
{
|
| 746 |
-
"epoch": 3.24,
|
| 747 |
-
"learning_rate": 4.6296296296296297e-07,
|
| 748 |
-
"loss": 0.0069,
|
| 749 |
-
"step": 1190
|
| 750 |
},
|
| 751 |
{
|
| 752 |
"epoch": 3.25,
|
| 753 |
"learning_rate": 0.0,
|
| 754 |
-
"loss":
|
| 755 |
-
"step":
|
| 756 |
},
|
| 757 |
{
|
| 758 |
"epoch": 3.25,
|
| 759 |
-
"eval_accuracy": 0.
|
| 760 |
-
"eval_loss": 0.
|
| 761 |
-
"eval_runtime":
|
| 762 |
-
"eval_samples_per_second":
|
| 763 |
-
"eval_steps_per_second":
|
| 764 |
-
"step":
|
| 765 |
},
|
| 766 |
{
|
| 767 |
"epoch": 3.25,
|
| 768 |
-
"step":
|
| 769 |
"total_flos": 1.495384188125184e+18,
|
| 770 |
-
"train_loss": 0.
|
| 771 |
-
"train_runtime":
|
| 772 |
-
"train_samples_per_second":
|
| 773 |
-
"train_steps_per_second": 1.
|
| 774 |
},
|
| 775 |
{
|
| 776 |
"epoch": 3.25,
|
| 777 |
-
"eval_accuracy": 0.
|
| 778 |
-
"eval_loss": 0.
|
| 779 |
-
"eval_runtime":
|
| 780 |
-
"eval_samples_per_second":
|
| 781 |
-
"eval_steps_per_second":
|
| 782 |
-
"step":
|
| 783 |
},
|
| 784 |
{
|
| 785 |
"epoch": 3.25,
|
| 786 |
-
"eval_accuracy": 0.
|
| 787 |
-
"eval_loss": 0.
|
| 788 |
-
"eval_runtime":
|
| 789 |
-
"eval_samples_per_second":
|
| 790 |
-
"eval_steps_per_second":
|
| 791 |
-
"step":
|
| 792 |
}
|
| 793 |
],
|
| 794 |
-
"max_steps":
|
| 795 |
"num_train_epochs": 9223372036854775807,
|
| 796 |
"total_flos": 1.495384188125184e+18,
|
| 797 |
"trial_name": null,
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.9285714285714286,
|
| 3 |
+
"best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-225",
|
| 4 |
"epoch": 3.25,
|
| 5 |
+
"global_step": 300,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
{
|
| 11 |
"epoch": 0.03,
|
| 12 |
"learning_rate": 1.6666666666666667e-05,
|
| 13 |
+
"loss": 2.3532,
|
| 14 |
+
"step": 10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.07,
|
| 18 |
"learning_rate": 3.3333333333333335e-05,
|
| 19 |
+
"loss": 2.3027,
|
| 20 |
+
"step": 20
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.1,
|
| 24 |
"learning_rate": 5e-05,
|
| 25 |
+
"loss": 2.2167,
|
| 26 |
+
"step": 30
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.13,
|
| 30 |
"learning_rate": 4.814814814814815e-05,
|
| 31 |
+
"loss": 2.019,
|
| 32 |
+
"step": 40
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.17,
|
| 36 |
"learning_rate": 4.62962962962963e-05,
|
| 37 |
+
"loss": 2.0514,
|
| 38 |
+
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.2,
|
| 42 |
"learning_rate": 4.4444444444444447e-05,
|
| 43 |
+
"loss": 1.7294,
|
| 44 |
+
"step": 60
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.23,
|
| 48 |
"learning_rate": 4.259259259259259e-05,
|
| 49 |
+
"loss": 1.6613,
|
| 50 |
+
"step": 70
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.25,
|
| 54 |
+
"eval_accuracy": 0.5285714285714286,
|
| 55 |
+
"eval_loss": 1.3506253957748413,
|
| 56 |
+
"eval_runtime": 6.0005,
|
| 57 |
+
"eval_samples_per_second": 11.666,
|
| 58 |
+
"eval_steps_per_second": 3.0,
|
| 59 |
+
"step": 75
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 60 |
},
|
| 61 |
{
|
| 62 |
"epoch": 1.02,
|
| 63 |
"learning_rate": 4.074074074074074e-05,
|
| 64 |
+
"loss": 1.2301,
|
| 65 |
+
"step": 80
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 1.05,
|
| 69 |
"learning_rate": 3.888888888888889e-05,
|
| 70 |
+
"loss": 0.9771,
|
| 71 |
+
"step": 90
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 72 |
},
|
| 73 |
{
|
| 74 |
"epoch": 1.08,
|
| 75 |
"learning_rate": 3.7037037037037037e-05,
|
| 76 |
+
"loss": 1.0313,
|
| 77 |
+
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 78 |
},
|
| 79 |
{
|
| 80 |
"epoch": 1.12,
|
| 81 |
"learning_rate": 3.518518518518519e-05,
|
| 82 |
+
"loss": 0.6111,
|
| 83 |
+
"step": 110
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 84 |
},
|
| 85 |
{
|
| 86 |
"epoch": 1.15,
|
| 87 |
"learning_rate": 3.3333333333333335e-05,
|
| 88 |
+
"loss": 1.0471,
|
| 89 |
+
"step": 120
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 90 |
},
|
| 91 |
{
|
| 92 |
"epoch": 1.18,
|
| 93 |
"learning_rate": 3.148148148148148e-05,
|
| 94 |
+
"loss": 0.8325,
|
| 95 |
+
"step": 130
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 96 |
},
|
| 97 |
{
|
| 98 |
"epoch": 1.22,
|
| 99 |
"learning_rate": 2.962962962962963e-05,
|
| 100 |
+
"loss": 0.8005,
|
| 101 |
+
"step": 140
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 102 |
},
|
| 103 |
{
|
| 104 |
"epoch": 1.25,
|
| 105 |
"learning_rate": 2.777777777777778e-05,
|
| 106 |
+
"loss": 0.4175,
|
| 107 |
+
"step": 150
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 1.25,
|
| 111 |
+
"eval_accuracy": 0.7285714285714285,
|
| 112 |
+
"eval_loss": 0.5572353601455688,
|
| 113 |
+
"eval_runtime": 5.7245,
|
| 114 |
+
"eval_samples_per_second": 12.228,
|
| 115 |
+
"eval_steps_per_second": 3.144,
|
| 116 |
+
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 2.03,
|
| 120 |
"learning_rate": 2.5925925925925925e-05,
|
| 121 |
+
"loss": 0.5881,
|
| 122 |
+
"step": 160
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 2.07,
|
| 126 |
"learning_rate": 2.4074074074074074e-05,
|
| 127 |
+
"loss": 0.402,
|
| 128 |
+
"step": 170
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 2.1,
|
| 132 |
"learning_rate": 2.2222222222222223e-05,
|
| 133 |
+
"loss": 0.2738,
|
| 134 |
+
"step": 180
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 135 |
},
|
| 136 |
{
|
| 137 |
"epoch": 2.13,
|
| 138 |
"learning_rate": 2.037037037037037e-05,
|
| 139 |
+
"loss": 0.3433,
|
| 140 |
+
"step": 190
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 141 |
},
|
| 142 |
{
|
| 143 |
"epoch": 2.17,
|
| 144 |
"learning_rate": 1.8518518518518518e-05,
|
| 145 |
+
"loss": 0.4863,
|
| 146 |
+
"step": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 147 |
},
|
| 148 |
{
|
| 149 |
"epoch": 2.2,
|
| 150 |
"learning_rate": 1.6666666666666667e-05,
|
| 151 |
+
"loss": 0.2916,
|
| 152 |
+
"step": 210
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 153 |
},
|
| 154 |
{
|
| 155 |
"epoch": 2.23,
|
| 156 |
"learning_rate": 1.4814814814814815e-05,
|
| 157 |
+
"loss": 0.3592,
|
| 158 |
+
"step": 220
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 159 |
},
|
| 160 |
{
|
| 161 |
"epoch": 2.25,
|
| 162 |
+
"eval_accuracy": 0.9285714285714286,
|
| 163 |
+
"eval_loss": 0.24635276198387146,
|
| 164 |
+
"eval_runtime": 5.6321,
|
| 165 |
+
"eval_samples_per_second": 12.429,
|
| 166 |
+
"eval_steps_per_second": 3.196,
|
| 167 |
+
"step": 225
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 168 |
},
|
| 169 |
{
|
| 170 |
"epoch": 3.02,
|
| 171 |
"learning_rate": 1.2962962962962962e-05,
|
| 172 |
+
"loss": 0.2532,
|
| 173 |
+
"step": 230
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 174 |
},
|
| 175 |
{
|
| 176 |
"epoch": 3.05,
|
| 177 |
"learning_rate": 1.1111111111111112e-05,
|
| 178 |
+
"loss": 0.3399,
|
| 179 |
+
"step": 240
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 180 |
},
|
| 181 |
{
|
| 182 |
"epoch": 3.08,
|
| 183 |
"learning_rate": 9.259259259259259e-06,
|
| 184 |
+
"loss": 0.1234,
|
| 185 |
+
"step": 250
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 186 |
},
|
| 187 |
{
|
| 188 |
"epoch": 3.12,
|
| 189 |
"learning_rate": 7.4074074074074075e-06,
|
| 190 |
+
"loss": 0.2255,
|
| 191 |
+
"step": 260
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 3.15,
|
| 195 |
"learning_rate": 5.555555555555556e-06,
|
| 196 |
+
"loss": 0.2442,
|
| 197 |
+
"step": 270
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 198 |
},
|
| 199 |
{
|
| 200 |
"epoch": 3.18,
|
| 201 |
"learning_rate": 3.7037037037037037e-06,
|
| 202 |
+
"loss": 0.087,
|
| 203 |
+
"step": 280
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 204 |
},
|
| 205 |
{
|
| 206 |
"epoch": 3.22,
|
| 207 |
"learning_rate": 1.8518518518518519e-06,
|
| 208 |
+
"loss": 0.1592,
|
| 209 |
+
"step": 290
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 210 |
},
|
| 211 |
{
|
| 212 |
"epoch": 3.25,
|
| 213 |
"learning_rate": 0.0,
|
| 214 |
+
"loss": 0.1935,
|
| 215 |
+
"step": 300
|
| 216 |
},
|
| 217 |
{
|
| 218 |
"epoch": 3.25,
|
| 219 |
+
"eval_accuracy": 0.9,
|
| 220 |
+
"eval_loss": 0.260299414396286,
|
| 221 |
+
"eval_runtime": 6.0335,
|
| 222 |
+
"eval_samples_per_second": 11.602,
|
| 223 |
+
"eval_steps_per_second": 2.983,
|
| 224 |
+
"step": 300
|
| 225 |
},
|
| 226 |
{
|
| 227 |
"epoch": 3.25,
|
| 228 |
+
"step": 300,
|
| 229 |
"total_flos": 1.495384188125184e+18,
|
| 230 |
+
"train_loss": 0.8550392069419225,
|
| 231 |
+
"train_runtime": 221.509,
|
| 232 |
+
"train_samples_per_second": 5.417,
|
| 233 |
+
"train_steps_per_second": 1.354
|
| 234 |
},
|
| 235 |
{
|
| 236 |
"epoch": 3.25,
|
| 237 |
+
"eval_accuracy": 0.8387096774193549,
|
| 238 |
+
"eval_loss": 0.4286609888076782,
|
| 239 |
+
"eval_runtime": 13.9577,
|
| 240 |
+
"eval_samples_per_second": 11.105,
|
| 241 |
+
"eval_steps_per_second": 2.794,
|
| 242 |
+
"step": 300
|
| 243 |
},
|
| 244 |
{
|
| 245 |
"epoch": 3.25,
|
| 246 |
+
"eval_accuracy": 0.8387096774193549,
|
| 247 |
+
"eval_loss": 0.4286610186100006,
|
| 248 |
+
"eval_runtime": 12.6984,
|
| 249 |
+
"eval_samples_per_second": 12.206,
|
| 250 |
+
"eval_steps_per_second": 3.071,
|
| 251 |
+
"step": 300
|
| 252 |
}
|
| 253 |
],
|
| 254 |
+
"max_steps": 300,
|
| 255 |
"num_train_epochs": 9223372036854775807,
|
| 256 |
"total_flos": 1.495384188125184e+18,
|
| 257 |
"trial_name": null,
|
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:db98e461593c9f94e624b2505bcf86db00ab67fbc2dbba21490949385c2ccf65
|
| 3 |
size 3439
|