Ubuntu
commited on
Commit
·
e5a82d8
1
Parent(s):
c7eb97f
update
Browse files- all_results.json +10 -7
- config.json +2 -1
- eval_results.json +6 -5
- pytorch_model.bin +2 -2
- tokenizer.json +0 -0
- train_results.json +5 -3
- trainer_state.json +132 -328
- training_args.bin +2 -2
all_results.json
CHANGED
|
@@ -1,11 +1,14 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss":
|
| 5 |
-
"eval_runtime":
|
| 6 |
"eval_samples": 9832,
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
-
"
|
|
|
|
|
|
|
| 9 |
"train_samples": 392702,
|
| 10 |
-
"train_samples_per_second":
|
|
|
|
| 11 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.9044955248169243,
|
| 4 |
+
"eval_loss": 0.6493760943412781,
|
| 5 |
+
"eval_runtime": 45.8003,
|
| 6 |
"eval_samples": 9832,
|
| 7 |
+
"eval_samples_per_second": 214.671,
|
| 8 |
+
"eval_steps_per_second": 3.362,
|
| 9 |
+
"train_loss": 0.09520160916497164,
|
| 10 |
+
"train_runtime": 17186.139,
|
| 11 |
"train_samples": 392702,
|
| 12 |
+
"train_samples_per_second": 228.499,
|
| 13 |
+
"train_steps_per_second": 1.19
|
| 14 |
}
|
config.json
CHANGED
|
@@ -28,11 +28,12 @@
|
|
| 28 |
"num_hidden_layers": 24,
|
| 29 |
"pad_token_id": 0,
|
| 30 |
"position_embedding_type": "absolute",
|
|
|
|
| 31 |
"summary_activation": "gelu",
|
| 32 |
"summary_last_dropout": 0.1,
|
| 33 |
"summary_type": "first",
|
| 34 |
"summary_use_proj": true,
|
| 35 |
-
"transformers_version": "4.
|
| 36 |
"type_vocab_size": 2,
|
| 37 |
"vocab_size": 30522
|
| 38 |
}
|
|
|
|
| 28 |
"num_hidden_layers": 24,
|
| 29 |
"pad_token_id": 0,
|
| 30 |
"position_embedding_type": "absolute",
|
| 31 |
+
"problem_type": "single_label_classification",
|
| 32 |
"summary_activation": "gelu",
|
| 33 |
"summary_last_dropout": 0.1,
|
| 34 |
"summary_type": "first",
|
| 35 |
"summary_use_proj": true,
|
| 36 |
+
"transformers_version": "4.7.0.dev0",
|
| 37 |
"type_vocab_size": 2,
|
| 38 |
"vocab_size": 30522
|
| 39 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss":
|
| 5 |
-
"eval_runtime":
|
| 6 |
"eval_samples": 9832,
|
| 7 |
-
"eval_samples_per_second":
|
|
|
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.9044955248169243,
|
| 4 |
+
"eval_loss": 0.6493760943412781,
|
| 5 |
+
"eval_runtime": 45.8003,
|
| 6 |
"eval_samples": 9832,
|
| 7 |
+
"eval_samples_per_second": 214.671,
|
| 8 |
+
"eval_steps_per_second": 3.362
|
| 9 |
}
|
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:d1f62640fe9fad5d2a57a0e996b4b4d8dbac6e63e3cef939b7412db85ccd99f3
|
| 3 |
+
size 1340749391
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
train_results.json
CHANGED
|
@@ -1,6 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"
|
|
|
|
| 4 |
"train_samples": 392702,
|
| 5 |
-
"train_samples_per_second":
|
|
|
|
| 6 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 0.09520160916497164,
|
| 4 |
+
"train_runtime": 17186.139,
|
| 5 |
"train_samples": 392702,
|
| 6 |
+
"train_samples_per_second": 228.499,
|
| 7 |
+
"train_steps_per_second": 1.19
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,461 +1,265 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 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.
|
| 12 |
-
"learning_rate": 1.
|
| 13 |
-
"loss": 0.
|
| 14 |
"step": 500
|
| 15 |
},
|
| 16 |
{
|
| 17 |
-
"epoch": 0.
|
| 18 |
-
"learning_rate": 1.
|
| 19 |
-
"loss": 0.
|
| 20 |
"step": 1000
|
| 21 |
},
|
| 22 |
{
|
| 23 |
-
"epoch": 0.
|
| 24 |
-
"learning_rate": 1.
|
| 25 |
-
"loss": 0.
|
| 26 |
"step": 1500
|
| 27 |
},
|
| 28 |
{
|
| 29 |
-
"epoch": 0.
|
| 30 |
-
"learning_rate": 1.
|
| 31 |
-
"loss":
|
| 32 |
"step": 2000
|
| 33 |
},
|
| 34 |
{
|
| 35 |
-
"epoch":
|
| 36 |
-
"learning_rate": 1.
|
| 37 |
-
"loss":
|
| 38 |
"step": 2500
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch":
|
| 42 |
-
"learning_rate": 1.
|
| 43 |
-
"loss":
|
| 44 |
"step": 3000
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch":
|
| 48 |
-
"learning_rate": 1.
|
| 49 |
-
"loss":
|
| 50 |
"step": 3500
|
| 51 |
},
|
| 52 |
{
|
| 53 |
-
"epoch":
|
| 54 |
-
"learning_rate": 1.
|
| 55 |
-
"loss":
|
| 56 |
"step": 4000
|
| 57 |
},
|
| 58 |
{
|
| 59 |
-
"epoch":
|
| 60 |
-
"learning_rate": 1.
|
| 61 |
-
"loss":
|
| 62 |
"step": 4500
|
| 63 |
},
|
| 64 |
{
|
| 65 |
-
"epoch":
|
| 66 |
-
"learning_rate": 1.
|
| 67 |
-
"loss":
|
| 68 |
"step": 5000
|
| 69 |
},
|
| 70 |
{
|
| 71 |
-
"epoch":
|
| 72 |
-
"learning_rate": 1.
|
| 73 |
-
"loss":
|
| 74 |
"step": 5500
|
| 75 |
},
|
| 76 |
{
|
| 77 |
-
"epoch":
|
| 78 |
-
"learning_rate": 1.
|
| 79 |
-
"loss":
|
| 80 |
"step": 6000
|
| 81 |
},
|
| 82 |
{
|
| 83 |
-
"epoch":
|
| 84 |
-
"learning_rate": 1.
|
| 85 |
-
"loss":
|
| 86 |
"step": 6500
|
| 87 |
},
|
| 88 |
{
|
| 89 |
-
"epoch":
|
| 90 |
-
"learning_rate": 1.
|
| 91 |
-
"loss":
|
| 92 |
"step": 7000
|
| 93 |
},
|
| 94 |
{
|
| 95 |
-
"epoch":
|
| 96 |
-
"learning_rate": 1.
|
| 97 |
-
"loss":
|
| 98 |
"step": 7500
|
| 99 |
},
|
| 100 |
{
|
| 101 |
-
"epoch":
|
| 102 |
-
"learning_rate": 1.
|
| 103 |
-
"loss":
|
| 104 |
"step": 8000
|
| 105 |
},
|
| 106 |
{
|
| 107 |
-
"epoch":
|
| 108 |
-
"learning_rate": 1.
|
| 109 |
-
"loss":
|
| 110 |
"step": 8500
|
| 111 |
},
|
| 112 |
{
|
| 113 |
-
"epoch":
|
| 114 |
-
"learning_rate": 1.
|
| 115 |
-
"loss":
|
| 116 |
"step": 9000
|
| 117 |
},
|
| 118 |
{
|
| 119 |
-
"epoch":
|
| 120 |
-
"learning_rate": 1.
|
| 121 |
-
"loss":
|
| 122 |
"step": 9500
|
| 123 |
},
|
| 124 |
{
|
| 125 |
-
"epoch":
|
| 126 |
-
"learning_rate": 1.
|
| 127 |
-
"loss":
|
| 128 |
"step": 10000
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"epoch":
|
| 132 |
-
"learning_rate":
|
| 133 |
-
"loss":
|
| 134 |
"step": 10500
|
| 135 |
},
|
| 136 |
{
|
| 137 |
-
"epoch":
|
| 138 |
-
"learning_rate":
|
| 139 |
-
"loss":
|
| 140 |
"step": 11000
|
| 141 |
},
|
| 142 |
{
|
| 143 |
-
"epoch":
|
| 144 |
-
"learning_rate":
|
| 145 |
-
"loss":
|
| 146 |
"step": 11500
|
| 147 |
},
|
| 148 |
{
|
| 149 |
-
"epoch":
|
| 150 |
-
"learning_rate":
|
| 151 |
-
"loss":
|
| 152 |
"step": 12000
|
| 153 |
},
|
| 154 |
{
|
| 155 |
-
"epoch":
|
| 156 |
-
"learning_rate":
|
| 157 |
-
"loss":
|
| 158 |
"step": 12500
|
| 159 |
},
|
| 160 |
{
|
| 161 |
-
"epoch":
|
| 162 |
-
"learning_rate":
|
| 163 |
-
"loss":
|
| 164 |
"step": 13000
|
| 165 |
},
|
| 166 |
{
|
| 167 |
-
"epoch":
|
| 168 |
-
"learning_rate":
|
| 169 |
-
"loss":
|
| 170 |
"step": 13500
|
| 171 |
},
|
| 172 |
{
|
| 173 |
-
"epoch":
|
| 174 |
-
"learning_rate":
|
| 175 |
-
"loss":
|
| 176 |
"step": 14000
|
| 177 |
},
|
| 178 |
{
|
| 179 |
-
"epoch":
|
| 180 |
-
"learning_rate":
|
| 181 |
-
"loss":
|
| 182 |
"step": 14500
|
| 183 |
},
|
| 184 |
{
|
| 185 |
-
"epoch":
|
| 186 |
-
"learning_rate":
|
| 187 |
-
"loss":
|
| 188 |
"step": 15000
|
| 189 |
},
|
| 190 |
{
|
| 191 |
-
"epoch":
|
| 192 |
-
"learning_rate":
|
| 193 |
-
"loss":
|
| 194 |
"step": 15500
|
| 195 |
},
|
| 196 |
{
|
| 197 |
-
"epoch":
|
| 198 |
-
"learning_rate":
|
| 199 |
-
"loss":
|
| 200 |
"step": 16000
|
| 201 |
},
|
| 202 |
{
|
| 203 |
-
"epoch":
|
| 204 |
-
"learning_rate":
|
| 205 |
-
"loss":
|
| 206 |
"step": 16500
|
| 207 |
},
|
| 208 |
{
|
| 209 |
-
"epoch":
|
| 210 |
-
"learning_rate":
|
| 211 |
-
"loss":
|
| 212 |
"step": 17000
|
| 213 |
},
|
| 214 |
{
|
| 215 |
-
"epoch":
|
| 216 |
-
"learning_rate":
|
| 217 |
-
"loss":
|
| 218 |
"step": 17500
|
| 219 |
},
|
| 220 |
{
|
| 221 |
-
"epoch":
|
| 222 |
-
"learning_rate":
|
| 223 |
-
"loss":
|
| 224 |
"step": 18000
|
| 225 |
},
|
| 226 |
{
|
| 227 |
-
"epoch":
|
| 228 |
-
"learning_rate":
|
| 229 |
-
"loss":
|
| 230 |
"step": 18500
|
| 231 |
},
|
| 232 |
{
|
| 233 |
-
"epoch":
|
| 234 |
-
"learning_rate":
|
| 235 |
-
"loss":
|
| 236 |
"step": 19000
|
| 237 |
},
|
| 238 |
{
|
| 239 |
-
"epoch":
|
| 240 |
-
"learning_rate": 9.
|
| 241 |
-
"loss":
|
| 242 |
"step": 19500
|
| 243 |
},
|
| 244 |
{
|
| 245 |
-
"epoch":
|
| 246 |
-
"learning_rate":
|
| 247 |
-
"loss":
|
| 248 |
"step": 20000
|
| 249 |
},
|
| 250 |
{
|
| 251 |
-
"epoch":
|
| 252 |
-
"
|
| 253 |
-
"
|
| 254 |
-
"
|
| 255 |
-
|
| 256 |
-
|
| 257 |
-
"
|
| 258 |
-
"learning_rate": 8.591916558018254e-06,
|
| 259 |
-
"loss": 1.0987,
|
| 260 |
-
"step": 21000
|
| 261 |
-
},
|
| 262 |
-
{
|
| 263 |
-
"epoch": 1.75,
|
| 264 |
-
"learning_rate": 8.320295523685355e-06,
|
| 265 |
-
"loss": 1.0986,
|
| 266 |
-
"step": 21500
|
| 267 |
-
},
|
| 268 |
-
{
|
| 269 |
-
"epoch": 1.79,
|
| 270 |
-
"learning_rate": 8.048674489352455e-06,
|
| 271 |
-
"loss": 1.0988,
|
| 272 |
-
"step": 22000
|
| 273 |
-
},
|
| 274 |
-
{
|
| 275 |
-
"epoch": 1.83,
|
| 276 |
-
"learning_rate": 7.777053455019557e-06,
|
| 277 |
-
"loss": 1.0988,
|
| 278 |
-
"step": 22500
|
| 279 |
-
},
|
| 280 |
-
{
|
| 281 |
-
"epoch": 1.87,
|
| 282 |
-
"learning_rate": 7.505432420686659e-06,
|
| 283 |
-
"loss": 1.0986,
|
| 284 |
-
"step": 23000
|
| 285 |
-
},
|
| 286 |
-
{
|
| 287 |
-
"epoch": 1.91,
|
| 288 |
-
"learning_rate": 7.23381138635376e-06,
|
| 289 |
-
"loss": 1.0988,
|
| 290 |
-
"step": 23500
|
| 291 |
-
},
|
| 292 |
-
{
|
| 293 |
-
"epoch": 1.96,
|
| 294 |
-
"learning_rate": 6.962190352020861e-06,
|
| 295 |
-
"loss": 1.0988,
|
| 296 |
-
"step": 24000
|
| 297 |
-
},
|
| 298 |
-
{
|
| 299 |
-
"epoch": 2.0,
|
| 300 |
-
"learning_rate": 6.690569317687963e-06,
|
| 301 |
-
"loss": 1.0988,
|
| 302 |
-
"step": 24500
|
| 303 |
-
},
|
| 304 |
-
{
|
| 305 |
-
"epoch": 2.04,
|
| 306 |
-
"learning_rate": 6.418948283355063e-06,
|
| 307 |
-
"loss": 1.0987,
|
| 308 |
-
"step": 25000
|
| 309 |
-
},
|
| 310 |
-
{
|
| 311 |
-
"epoch": 2.08,
|
| 312 |
-
"learning_rate": 6.147327249022165e-06,
|
| 313 |
-
"loss": 1.0988,
|
| 314 |
-
"step": 25500
|
| 315 |
-
},
|
| 316 |
-
{
|
| 317 |
-
"epoch": 2.12,
|
| 318 |
-
"learning_rate": 5.8757062146892665e-06,
|
| 319 |
-
"loss": 1.0985,
|
| 320 |
-
"step": 26000
|
| 321 |
-
},
|
| 322 |
-
{
|
| 323 |
-
"epoch": 2.16,
|
| 324 |
-
"learning_rate": 5.6040851803563665e-06,
|
| 325 |
-
"loss": 1.0989,
|
| 326 |
-
"step": 26500
|
| 327 |
-
},
|
| 328 |
-
{
|
| 329 |
-
"epoch": 2.2,
|
| 330 |
-
"learning_rate": 5.332464146023468e-06,
|
| 331 |
-
"loss": 1.0988,
|
| 332 |
-
"step": 27000
|
| 333 |
-
},
|
| 334 |
-
{
|
| 335 |
-
"epoch": 2.24,
|
| 336 |
-
"learning_rate": 5.06084311169057e-06,
|
| 337 |
-
"loss": 1.0987,
|
| 338 |
-
"step": 27500
|
| 339 |
-
},
|
| 340 |
-
{
|
| 341 |
-
"epoch": 2.28,
|
| 342 |
-
"learning_rate": 4.789222077357671e-06,
|
| 343 |
-
"loss": 1.0987,
|
| 344 |
-
"step": 28000
|
| 345 |
-
},
|
| 346 |
-
{
|
| 347 |
-
"epoch": 2.32,
|
| 348 |
-
"learning_rate": 4.5176010430247726e-06,
|
| 349 |
-
"loss": 1.0986,
|
| 350 |
-
"step": 28500
|
| 351 |
-
},
|
| 352 |
-
{
|
| 353 |
-
"epoch": 2.36,
|
| 354 |
-
"learning_rate": 4.2459800086918734e-06,
|
| 355 |
-
"loss": 1.0987,
|
| 356 |
-
"step": 29000
|
| 357 |
-
},
|
| 358 |
-
{
|
| 359 |
-
"epoch": 2.4,
|
| 360 |
-
"learning_rate": 3.974358974358974e-06,
|
| 361 |
-
"loss": 1.0987,
|
| 362 |
-
"step": 29500
|
| 363 |
-
},
|
| 364 |
-
{
|
| 365 |
-
"epoch": 2.44,
|
| 366 |
-
"learning_rate": 3.702737940026076e-06,
|
| 367 |
-
"loss": 1.0988,
|
| 368 |
-
"step": 30000
|
| 369 |
-
},
|
| 370 |
-
{
|
| 371 |
-
"epoch": 2.49,
|
| 372 |
-
"learning_rate": 3.431116905693177e-06,
|
| 373 |
-
"loss": 1.0988,
|
| 374 |
-
"step": 30500
|
| 375 |
-
},
|
| 376 |
-
{
|
| 377 |
-
"epoch": 2.53,
|
| 378 |
-
"learning_rate": 3.1594958713602786e-06,
|
| 379 |
-
"loss": 1.0986,
|
| 380 |
-
"step": 31000
|
| 381 |
-
},
|
| 382 |
-
{
|
| 383 |
-
"epoch": 2.57,
|
| 384 |
-
"learning_rate": 2.8878748370273795e-06,
|
| 385 |
-
"loss": 1.0988,
|
| 386 |
-
"step": 31500
|
| 387 |
-
},
|
| 388 |
-
{
|
| 389 |
-
"epoch": 2.61,
|
| 390 |
-
"learning_rate": 2.6162538026944812e-06,
|
| 391 |
-
"loss": 1.0987,
|
| 392 |
-
"step": 32000
|
| 393 |
-
},
|
| 394 |
-
{
|
| 395 |
-
"epoch": 2.65,
|
| 396 |
-
"learning_rate": 2.344632768361582e-06,
|
| 397 |
-
"loss": 1.0987,
|
| 398 |
-
"step": 32500
|
| 399 |
-
},
|
| 400 |
-
{
|
| 401 |
-
"epoch": 2.69,
|
| 402 |
-
"learning_rate": 2.0730117340286834e-06,
|
| 403 |
-
"loss": 1.0987,
|
| 404 |
-
"step": 33000
|
| 405 |
-
},
|
| 406 |
-
{
|
| 407 |
-
"epoch": 2.73,
|
| 408 |
-
"learning_rate": 1.8013906996957845e-06,
|
| 409 |
-
"loss": 1.0987,
|
| 410 |
-
"step": 33500
|
| 411 |
-
},
|
| 412 |
-
{
|
| 413 |
-
"epoch": 2.77,
|
| 414 |
-
"learning_rate": 1.5297696653628858e-06,
|
| 415 |
-
"loss": 1.0987,
|
| 416 |
-
"step": 34000
|
| 417 |
-
},
|
| 418 |
-
{
|
| 419 |
-
"epoch": 2.81,
|
| 420 |
-
"learning_rate": 1.258148631029987e-06,
|
| 421 |
-
"loss": 1.0986,
|
| 422 |
-
"step": 34500
|
| 423 |
-
},
|
| 424 |
-
{
|
| 425 |
-
"epoch": 2.85,
|
| 426 |
-
"learning_rate": 9.865275966970884e-07,
|
| 427 |
-
"loss": 1.0986,
|
| 428 |
-
"step": 35000
|
| 429 |
-
},
|
| 430 |
-
{
|
| 431 |
-
"epoch": 2.89,
|
| 432 |
-
"learning_rate": 7.149065623641896e-07,
|
| 433 |
-
"loss": 1.0986,
|
| 434 |
-
"step": 35500
|
| 435 |
-
},
|
| 436 |
-
{
|
| 437 |
-
"epoch": 2.93,
|
| 438 |
-
"learning_rate": 4.432855280312908e-07,
|
| 439 |
-
"loss": 1.0988,
|
| 440 |
-
"step": 36000
|
| 441 |
-
},
|
| 442 |
-
{
|
| 443 |
-
"epoch": 2.97,
|
| 444 |
-
"learning_rate": 1.7166449369839202e-07,
|
| 445 |
-
"loss": 1.0986,
|
| 446 |
-
"step": 36500
|
| 447 |
-
},
|
| 448 |
-
{
|
| 449 |
-
"epoch": 3.0,
|
| 450 |
-
"step": 36816,
|
| 451 |
-
"total_flos": 3.032342720870999e+17,
|
| 452 |
-
"train_runtime": 27042.3264,
|
| 453 |
-
"train_samples_per_second": 1.361
|
| 454 |
}
|
| 455 |
],
|
| 456 |
-
"max_steps":
|
| 457 |
-
"num_train_epochs":
|
| 458 |
-
"total_flos":
|
| 459 |
"trial_name": null,
|
| 460 |
"trial_params": null
|
| 461 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 20460,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
+
"epoch": 0.24,
|
| 12 |
+
"learning_rate": 1.951124144672532e-05,
|
| 13 |
+
"loss": 0.4464,
|
| 14 |
"step": 500
|
| 15 |
},
|
| 16 |
{
|
| 17 |
+
"epoch": 0.49,
|
| 18 |
+
"learning_rate": 1.9022482893450638e-05,
|
| 19 |
+
"loss": 0.3259,
|
| 20 |
"step": 1000
|
| 21 |
},
|
| 22 |
{
|
| 23 |
+
"epoch": 0.73,
|
| 24 |
+
"learning_rate": 1.8533724340175954e-05,
|
| 25 |
+
"loss": 0.2927,
|
| 26 |
"step": 1500
|
| 27 |
},
|
| 28 |
{
|
| 29 |
+
"epoch": 0.98,
|
| 30 |
+
"learning_rate": 1.804496578690127e-05,
|
| 31 |
+
"loss": 0.2837,
|
| 32 |
"step": 2000
|
| 33 |
},
|
| 34 |
{
|
| 35 |
+
"epoch": 1.22,
|
| 36 |
+
"learning_rate": 1.755620723362659e-05,
|
| 37 |
+
"loss": 0.2107,
|
| 38 |
"step": 2500
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 1.47,
|
| 42 |
+
"learning_rate": 1.7067448680351906e-05,
|
| 43 |
+
"loss": 0.2035,
|
| 44 |
"step": 3000
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 1.71,
|
| 48 |
+
"learning_rate": 1.6578690127077226e-05,
|
| 49 |
+
"loss": 0.204,
|
| 50 |
"step": 3500
|
| 51 |
},
|
| 52 |
{
|
| 53 |
+
"epoch": 1.96,
|
| 54 |
+
"learning_rate": 1.6089931573802543e-05,
|
| 55 |
+
"loss": 0.2023,
|
| 56 |
"step": 4000
|
| 57 |
},
|
| 58 |
{
|
| 59 |
+
"epoch": 2.2,
|
| 60 |
+
"learning_rate": 1.560117302052786e-05,
|
| 61 |
+
"loss": 0.1456,
|
| 62 |
"step": 4500
|
| 63 |
},
|
| 64 |
{
|
| 65 |
+
"epoch": 2.44,
|
| 66 |
+
"learning_rate": 1.5112414467253179e-05,
|
| 67 |
+
"loss": 0.1295,
|
| 68 |
"step": 5000
|
| 69 |
},
|
| 70 |
{
|
| 71 |
+
"epoch": 2.69,
|
| 72 |
+
"learning_rate": 1.4623655913978497e-05,
|
| 73 |
+
"loss": 0.1347,
|
| 74 |
"step": 5500
|
| 75 |
},
|
| 76 |
{
|
| 77 |
+
"epoch": 2.93,
|
| 78 |
+
"learning_rate": 1.4134897360703815e-05,
|
| 79 |
+
"loss": 0.1382,
|
| 80 |
"step": 6000
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"epoch": 3.18,
|
| 84 |
+
"learning_rate": 1.364613880742913e-05,
|
| 85 |
+
"loss": 0.0994,
|
| 86 |
"step": 6500
|
| 87 |
},
|
| 88 |
{
|
| 89 |
+
"epoch": 3.42,
|
| 90 |
+
"learning_rate": 1.3157380254154449e-05,
|
| 91 |
+
"loss": 0.0875,
|
| 92 |
"step": 7000
|
| 93 |
},
|
| 94 |
{
|
| 95 |
+
"epoch": 3.67,
|
| 96 |
+
"learning_rate": 1.2668621700879767e-05,
|
| 97 |
+
"loss": 0.0886,
|
| 98 |
"step": 7500
|
| 99 |
},
|
| 100 |
{
|
| 101 |
+
"epoch": 3.91,
|
| 102 |
+
"learning_rate": 1.2179863147605085e-05,
|
| 103 |
+
"loss": 0.0903,
|
| 104 |
"step": 8000
|
| 105 |
},
|
| 106 |
{
|
| 107 |
+
"epoch": 4.15,
|
| 108 |
+
"learning_rate": 1.1691104594330403e-05,
|
| 109 |
+
"loss": 0.0699,
|
| 110 |
"step": 8500
|
| 111 |
},
|
| 112 |
{
|
| 113 |
+
"epoch": 4.4,
|
| 114 |
+
"learning_rate": 1.1202346041055718e-05,
|
| 115 |
+
"loss": 0.06,
|
| 116 |
"step": 9000
|
| 117 |
},
|
| 118 |
{
|
| 119 |
+
"epoch": 4.64,
|
| 120 |
+
"learning_rate": 1.0713587487781036e-05,
|
| 121 |
+
"loss": 0.0626,
|
| 122 |
"step": 9500
|
| 123 |
},
|
| 124 |
{
|
| 125 |
+
"epoch": 4.89,
|
| 126 |
+
"learning_rate": 1.0224828934506354e-05,
|
| 127 |
+
"loss": 0.0599,
|
| 128 |
"step": 10000
|
| 129 |
},
|
| 130 |
{
|
| 131 |
+
"epoch": 5.13,
|
| 132 |
+
"learning_rate": 9.736070381231672e-06,
|
| 133 |
+
"loss": 0.0506,
|
| 134 |
"step": 10500
|
| 135 |
},
|
| 136 |
{
|
| 137 |
+
"epoch": 5.38,
|
| 138 |
+
"learning_rate": 9.24731182795699e-06,
|
| 139 |
+
"loss": 0.0431,
|
| 140 |
"step": 11000
|
| 141 |
},
|
| 142 |
{
|
| 143 |
+
"epoch": 5.62,
|
| 144 |
+
"learning_rate": 8.758553274682308e-06,
|
| 145 |
+
"loss": 0.0449,
|
| 146 |
"step": 11500
|
| 147 |
},
|
| 148 |
{
|
| 149 |
+
"epoch": 5.87,
|
| 150 |
+
"learning_rate": 8.269794721407626e-06,
|
| 151 |
+
"loss": 0.0433,
|
| 152 |
"step": 12000
|
| 153 |
},
|
| 154 |
{
|
| 155 |
+
"epoch": 6.11,
|
| 156 |
+
"learning_rate": 7.781036168132942e-06,
|
| 157 |
+
"loss": 0.0377,
|
| 158 |
"step": 12500
|
| 159 |
},
|
| 160 |
{
|
| 161 |
+
"epoch": 6.35,
|
| 162 |
+
"learning_rate": 7.292277614858261e-06,
|
| 163 |
+
"loss": 0.0334,
|
| 164 |
"step": 13000
|
| 165 |
},
|
| 166 |
{
|
| 167 |
+
"epoch": 6.6,
|
| 168 |
+
"learning_rate": 6.8035190615835775e-06,
|
| 169 |
+
"loss": 0.0325,
|
| 170 |
"step": 13500
|
| 171 |
},
|
| 172 |
{
|
| 173 |
+
"epoch": 6.84,
|
| 174 |
+
"learning_rate": 6.3147605083088955e-06,
|
| 175 |
+
"loss": 0.0312,
|
| 176 |
"step": 14000
|
| 177 |
},
|
| 178 |
{
|
| 179 |
+
"epoch": 7.09,
|
| 180 |
+
"learning_rate": 5.8260019550342136e-06,
|
| 181 |
+
"loss": 0.0295,
|
| 182 |
"step": 14500
|
| 183 |
},
|
| 184 |
{
|
| 185 |
+
"epoch": 7.33,
|
| 186 |
+
"learning_rate": 5.337243401759531e-06,
|
| 187 |
+
"loss": 0.0238,
|
| 188 |
"step": 15000
|
| 189 |
},
|
| 190 |
{
|
| 191 |
+
"epoch": 7.58,
|
| 192 |
+
"learning_rate": 4.848484848484849e-06,
|
| 193 |
+
"loss": 0.0259,
|
| 194 |
"step": 15500
|
| 195 |
},
|
| 196 |
{
|
| 197 |
+
"epoch": 7.82,
|
| 198 |
+
"learning_rate": 4.359726295210167e-06,
|
| 199 |
+
"loss": 0.0221,
|
| 200 |
"step": 16000
|
| 201 |
},
|
| 202 |
{
|
| 203 |
+
"epoch": 8.06,
|
| 204 |
+
"learning_rate": 3.870967741935484e-06,
|
| 205 |
+
"loss": 0.021,
|
| 206 |
"step": 16500
|
| 207 |
},
|
| 208 |
{
|
| 209 |
+
"epoch": 8.31,
|
| 210 |
+
"learning_rate": 3.3822091886608016e-06,
|
| 211 |
+
"loss": 0.0175,
|
| 212 |
"step": 17000
|
| 213 |
},
|
| 214 |
{
|
| 215 |
+
"epoch": 8.55,
|
| 216 |
+
"learning_rate": 2.8934506353861196e-06,
|
| 217 |
+
"loss": 0.0184,
|
| 218 |
"step": 17500
|
| 219 |
},
|
| 220 |
{
|
| 221 |
+
"epoch": 8.8,
|
| 222 |
+
"learning_rate": 2.4046920821114372e-06,
|
| 223 |
+
"loss": 0.0175,
|
| 224 |
"step": 18000
|
| 225 |
},
|
| 226 |
{
|
| 227 |
+
"epoch": 9.04,
|
| 228 |
+
"learning_rate": 1.915933528836755e-06,
|
| 229 |
+
"loss": 0.0167,
|
| 230 |
"step": 18500
|
| 231 |
},
|
| 232 |
{
|
| 233 |
+
"epoch": 9.29,
|
| 234 |
+
"learning_rate": 1.4271749755620727e-06,
|
| 235 |
+
"loss": 0.0133,
|
| 236 |
"step": 19000
|
| 237 |
},
|
| 238 |
{
|
| 239 |
+
"epoch": 9.53,
|
| 240 |
+
"learning_rate": 9.384164222873901e-07,
|
| 241 |
+
"loss": 0.0125,
|
| 242 |
"step": 19500
|
| 243 |
},
|
| 244 |
{
|
| 245 |
+
"epoch": 9.78,
|
| 246 |
+
"learning_rate": 4.496578690127078e-07,
|
| 247 |
+
"loss": 0.0139,
|
| 248 |
"step": 20000
|
| 249 |
},
|
| 250 |
{
|
| 251 |
+
"epoch": 10.0,
|
| 252 |
+
"step": 20460,
|
| 253 |
+
"total_flos": 1.0107809069569997e+18,
|
| 254 |
+
"train_loss": 0.09520160916497164,
|
| 255 |
+
"train_runtime": 17186.139,
|
| 256 |
+
"train_samples_per_second": 228.499,
|
| 257 |
+
"train_steps_per_second": 1.19
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 258 |
}
|
| 259 |
],
|
| 260 |
+
"max_steps": 20460,
|
| 261 |
+
"num_train_epochs": 10,
|
| 262 |
+
"total_flos": 1.0107809069569997e+18,
|
| 263 |
"trial_name": null,
|
| 264 |
"trial_params": null
|
| 265 |
}
|
training_args.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 sha256:8c5d1c4fa88b00fea08f1074d32ea0432ea2ffc01aa3e6e8654fb213f55f8e61
|
| 3 |
+
size 2479
|