Commit
•
b43c5de
1
Parent(s):
579e08b
End of training
Browse files- README.md +14 -2
- all_results.json +10 -10
- eval_results.json +6 -6
- train_results.json +4 -4
- trainer_state.json +714 -714
README.md
CHANGED
|
@@ -1,11 +1,23 @@
|
|
| 1 |
---
|
| 2 |
tags:
|
| 3 |
- generated_from_trainer
|
|
|
|
|
|
|
| 4 |
metrics:
|
| 5 |
- accuracy
|
| 6 |
model-index:
|
| 7 |
- name: bitllama-goodwiki
|
| 8 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
---
|
| 10 |
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -13,7 +25,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# bitllama-goodwiki
|
| 15 |
|
| 16 |
-
This model was trained from scratch on
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
- Loss: 3.0525
|
| 19 |
- Accuracy: 0.4285
|
|
|
|
| 1 |
---
|
| 2 |
tags:
|
| 3 |
- generated_from_trainer
|
| 4 |
+
datasets:
|
| 5 |
+
- BEE-spoke-data/goodwiki-deduped-split
|
| 6 |
metrics:
|
| 7 |
- accuracy
|
| 8 |
model-index:
|
| 9 |
- name: bitllama-goodwiki
|
| 10 |
+
results:
|
| 11 |
+
- task:
|
| 12 |
+
name: Causal Language Modeling
|
| 13 |
+
type: text-generation
|
| 14 |
+
dataset:
|
| 15 |
+
name: BEE-spoke-data/goodwiki-deduped-split
|
| 16 |
+
type: BEE-spoke-data/goodwiki-deduped-split
|
| 17 |
+
metrics:
|
| 18 |
+
- name: Accuracy
|
| 19 |
+
type: accuracy
|
| 20 |
+
value: 0.4285134482793542
|
| 21 |
---
|
| 22 |
|
| 23 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 25 |
|
| 26 |
# bitllama-goodwiki
|
| 27 |
|
| 28 |
+
This model was trained from scratch on the BEE-spoke-data/goodwiki-deduped-split dataset.
|
| 29 |
It achieves the following results on the evaluation set:
|
| 30 |
- Loss: 3.0525
|
| 31 |
- Accuracy: 0.4285
|
all_results.json
CHANGED
|
@@ -1,15 +1,15 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 3.
|
| 5 |
-
"eval_runtime":
|
| 6 |
"eval_samples": 5065,
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
-
"eval_steps_per_second": 4.
|
| 9 |
-
"perplexity":
|
| 10 |
-
"train_loss": 3.
|
| 11 |
-
"train_runtime":
|
| 12 |
"train_samples": 90649,
|
| 13 |
-
"train_samples_per_second":
|
| 14 |
-
"train_steps_per_second": 0.
|
| 15 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
+
"eval_accuracy": 0.4285134482793542,
|
| 4 |
+
"eval_loss": 3.0525197982788086,
|
| 5 |
+
"eval_runtime": 151.0776,
|
| 6 |
"eval_samples": 5065,
|
| 7 |
+
"eval_samples_per_second": 33.526,
|
| 8 |
+
"eval_steps_per_second": 4.197,
|
| 9 |
+
"perplexity": 21.168617922121435,
|
| 10 |
+
"train_loss": 3.7639108537323183,
|
| 11 |
+
"train_runtime": 10013.9285,
|
| 12 |
"train_samples": 90649,
|
| 13 |
+
"train_samples_per_second": 9.052,
|
| 14 |
+
"train_steps_per_second": 0.283
|
| 15 |
}
|
eval_results.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 3.
|
| 5 |
-
"eval_runtime":
|
| 6 |
"eval_samples": 5065,
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
-
"eval_steps_per_second": 4.
|
| 9 |
-
"perplexity":
|
| 10 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
+
"eval_accuracy": 0.4285134482793542,
|
| 4 |
+
"eval_loss": 3.0525197982788086,
|
| 5 |
+
"eval_runtime": 151.0776,
|
| 6 |
"eval_samples": 5065,
|
| 7 |
+
"eval_samples_per_second": 33.526,
|
| 8 |
+
"eval_steps_per_second": 4.197,
|
| 9 |
+
"perplexity": 21.168617922121435
|
| 10 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
-
"train_loss": 3.
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 90649,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
+
"train_loss": 3.7639108537323183,
|
| 4 |
+
"train_runtime": 10013.9285,
|
| 5 |
"train_samples": 90649,
|
| 6 |
+
"train_samples_per_second": 9.052,
|
| 7 |
+
"train_steps_per_second": 0.283
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -10,1968 +10,1968 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.0,
|
| 13 |
-
"learning_rate":
|
| 14 |
-
"loss": 10.
|
| 15 |
"step": 1
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.0,
|
| 19 |
-
"learning_rate":
|
| 20 |
-
"loss":
|
| 21 |
"step": 10
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.01,
|
| 25 |
-
"learning_rate": 0.
|
| 26 |
-
"loss":
|
| 27 |
"step": 20
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.01,
|
| 31 |
-
"learning_rate": 0.
|
| 32 |
-
"loss": 7.
|
| 33 |
"step": 30
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.01,
|
| 37 |
-
"learning_rate": 0.
|
| 38 |
-
"loss":
|
| 39 |
"step": 40
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.02,
|
| 43 |
-
"learning_rate": 0.
|
| 44 |
-
"loss":
|
| 45 |
"step": 50
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.02,
|
| 49 |
-
"learning_rate": 0.
|
| 50 |
-
"loss": 6.
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.02,
|
| 55 |
-
"learning_rate": 0.
|
| 56 |
-
"loss": 6.
|
| 57 |
"step": 70
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 0.03,
|
| 61 |
-
"learning_rate": 0.
|
| 62 |
-
"loss": 6.
|
| 63 |
"step": 80
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 0.03,
|
| 67 |
-
"learning_rate": 0.
|
| 68 |
-
"loss": 6.
|
| 69 |
"step": 90
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 0.04,
|
| 73 |
"learning_rate": 0.0008,
|
| 74 |
-
"loss":
|
| 75 |
"step": 100
|
| 76 |
},
|
| 77 |
{
|
| 78 |
"epoch": 0.04,
|
| 79 |
-
"eval_accuracy": 0.
|
| 80 |
-
"eval_loss":
|
| 81 |
-
"eval_runtime":
|
| 82 |
-
"eval_samples_per_second":
|
| 83 |
-
"eval_steps_per_second": 4.
|
| 84 |
"step": 100
|
| 85 |
},
|
| 86 |
{
|
| 87 |
"epoch": 0.04,
|
| 88 |
-
"learning_rate": 0.
|
| 89 |
-
"loss":
|
| 90 |
"step": 110
|
| 91 |
},
|
| 92 |
{
|
| 93 |
"epoch": 0.04,
|
| 94 |
-
"learning_rate": 0.
|
| 95 |
-
"loss": 5.
|
| 96 |
"step": 120
|
| 97 |
},
|
| 98 |
{
|
| 99 |
"epoch": 0.05,
|
| 100 |
-
"learning_rate": 0.
|
| 101 |
-
"loss": 5.
|
| 102 |
"step": 130
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 0.05,
|
| 106 |
-
"learning_rate": 0.
|
| 107 |
-
"loss": 5.
|
| 108 |
"step": 140
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 0.05,
|
| 112 |
-
"learning_rate": 0.
|
| 113 |
-
"loss": 5.
|
| 114 |
"step": 150
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.06,
|
| 118 |
-
"learning_rate": 0.
|
| 119 |
-
"loss": 5.
|
| 120 |
"step": 160
|
| 121 |
},
|
| 122 |
{
|
| 123 |
"epoch": 0.06,
|
| 124 |
-
"learning_rate": 0.
|
| 125 |
-
"loss": 5.
|
| 126 |
"step": 170
|
| 127 |
},
|
| 128 |
{
|
| 129 |
"epoch": 0.06,
|
| 130 |
-
"learning_rate": 0.
|
| 131 |
-
"loss": 5.
|
| 132 |
"step": 180
|
| 133 |
},
|
| 134 |
{
|
| 135 |
"epoch": 0.07,
|
| 136 |
-
"learning_rate": 0.
|
| 137 |
-
"loss": 5.
|
| 138 |
"step": 190
|
| 139 |
},
|
| 140 |
{
|
| 141 |
"epoch": 0.07,
|
| 142 |
-
"learning_rate": 0.
|
| 143 |
-
"loss": 5.
|
| 144 |
"step": 200
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"epoch": 0.07,
|
| 148 |
-
"eval_accuracy": 0.
|
| 149 |
-
"eval_loss": 5.
|
| 150 |
-
"eval_runtime":
|
| 151 |
-
"eval_samples_per_second":
|
| 152 |
-
"eval_steps_per_second": 4.
|
| 153 |
"step": 200
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 0.07,
|
| 157 |
-
"learning_rate": 0.
|
| 158 |
-
"loss": 5.
|
| 159 |
"step": 210
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 0.08,
|
| 163 |
-
"learning_rate": 0.
|
| 164 |
-
"loss": 5.
|
| 165 |
"step": 220
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 0.08,
|
| 169 |
-
"learning_rate": 0.
|
| 170 |
-
"loss": 5.
|
| 171 |
"step": 230
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"epoch": 0.08,
|
| 175 |
-
"learning_rate": 0.
|
| 176 |
-
"loss": 5.
|
| 177 |
"step": 240
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 0.09,
|
| 181 |
-
"learning_rate": 0.
|
| 182 |
-
"loss": 5.
|
| 183 |
"step": 250
|
| 184 |
},
|
| 185 |
{
|
| 186 |
"epoch": 0.09,
|
| 187 |
-
"learning_rate": 0.
|
| 188 |
-
"loss":
|
| 189 |
"step": 260
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"epoch": 0.1,
|
| 193 |
-
"learning_rate": 0.
|
| 194 |
-
"loss": 4.
|
| 195 |
"step": 270
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 0.1,
|
| 199 |
-
"learning_rate": 0.
|
| 200 |
-
"loss": 4.
|
| 201 |
"step": 280
|
| 202 |
},
|
| 203 |
{
|
| 204 |
"epoch": 0.1,
|
| 205 |
-
"learning_rate": 0.
|
| 206 |
-
"loss": 4.
|
| 207 |
"step": 290
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 0.11,
|
| 211 |
-
"learning_rate": 0.
|
| 212 |
-
"loss": 4.
|
| 213 |
"step": 300
|
| 214 |
},
|
| 215 |
{
|
| 216 |
"epoch": 0.11,
|
| 217 |
-
"eval_accuracy": 0.
|
| 218 |
-
"eval_loss": 4.
|
| 219 |
-
"eval_runtime":
|
| 220 |
-
"eval_samples_per_second":
|
| 221 |
-
"eval_steps_per_second": 4.
|
| 222 |
"step": 300
|
| 223 |
},
|
| 224 |
{
|
| 225 |
"epoch": 0.11,
|
| 226 |
-
"learning_rate": 0.
|
| 227 |
-
"loss": 4.
|
| 228 |
"step": 310
|
| 229 |
},
|
| 230 |
{
|
| 231 |
"epoch": 0.11,
|
| 232 |
-
"learning_rate": 0.
|
| 233 |
-
"loss": 4.
|
| 234 |
"step": 320
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"epoch": 0.12,
|
| 238 |
-
"learning_rate": 0.
|
| 239 |
-
"loss": 4.
|
| 240 |
"step": 330
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 0.12,
|
| 244 |
-
"learning_rate": 0.
|
| 245 |
-
"loss": 4.
|
| 246 |
"step": 340
|
| 247 |
},
|
| 248 |
{
|
| 249 |
"epoch": 0.12,
|
| 250 |
-
"learning_rate": 0.
|
| 251 |
-
"loss": 4.
|
| 252 |
"step": 350
|
| 253 |
},
|
| 254 |
{
|
| 255 |
"epoch": 0.13,
|
| 256 |
-
"learning_rate": 0.
|
| 257 |
-
"loss": 4.
|
| 258 |
"step": 360
|
| 259 |
},
|
| 260 |
{
|
| 261 |
"epoch": 0.13,
|
| 262 |
-
"learning_rate": 0.
|
| 263 |
-
"loss": 4.
|
| 264 |
"step": 370
|
| 265 |
},
|
| 266 |
{
|
| 267 |
"epoch": 0.13,
|
| 268 |
-
"learning_rate": 0.
|
| 269 |
-
"loss": 4.
|
| 270 |
"step": 380
|
| 271 |
},
|
| 272 |
{
|
| 273 |
"epoch": 0.14,
|
| 274 |
-
"learning_rate": 0.
|
| 275 |
-
"loss": 4.
|
| 276 |
"step": 390
|
| 277 |
},
|
| 278 |
{
|
| 279 |
"epoch": 0.14,
|
| 280 |
-
"learning_rate": 0.
|
| 281 |
-
"loss": 4.
|
| 282 |
"step": 400
|
| 283 |
},
|
| 284 |
{
|
| 285 |
"epoch": 0.14,
|
| 286 |
-
"eval_accuracy": 0.
|
| 287 |
-
"eval_loss": 4.
|
| 288 |
-
"eval_runtime":
|
| 289 |
-
"eval_samples_per_second":
|
| 290 |
-
"eval_steps_per_second": 4.
|
| 291 |
"step": 400
|
| 292 |
},
|
| 293 |
{
|
| 294 |
"epoch": 0.14,
|
| 295 |
-
"learning_rate": 0.
|
| 296 |
-
"loss": 4.
|
| 297 |
"step": 410
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 0.15,
|
| 301 |
-
"learning_rate": 0.
|
| 302 |
-
"loss": 4.
|
| 303 |
"step": 420
|
| 304 |
},
|
| 305 |
{
|
| 306 |
"epoch": 0.15,
|
| 307 |
-
"learning_rate": 0.
|
| 308 |
-
"loss": 4.
|
| 309 |
"step": 430
|
| 310 |
},
|
| 311 |
{
|
| 312 |
"epoch": 0.16,
|
| 313 |
-
"learning_rate": 0.
|
| 314 |
-
"loss": 4.
|
| 315 |
"step": 440
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"epoch": 0.16,
|
| 319 |
-
"learning_rate": 0.
|
| 320 |
-
"loss": 4.
|
| 321 |
"step": 450
|
| 322 |
},
|
| 323 |
{
|
| 324 |
"epoch": 0.16,
|
| 325 |
-
"learning_rate": 0.
|
| 326 |
-
"loss": 4.
|
| 327 |
"step": 460
|
| 328 |
},
|
| 329 |
{
|
| 330 |
"epoch": 0.17,
|
| 331 |
-
"learning_rate": 0.
|
| 332 |
-
"loss": 4.
|
| 333 |
"step": 470
|
| 334 |
},
|
| 335 |
{
|
| 336 |
"epoch": 0.17,
|
| 337 |
-
"learning_rate": 0.
|
| 338 |
-
"loss": 4.
|
| 339 |
"step": 480
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 0.17,
|
| 343 |
-
"learning_rate": 0.
|
| 344 |
-
"loss": 4.
|
| 345 |
"step": 490
|
| 346 |
},
|
| 347 |
{
|
| 348 |
"epoch": 0.18,
|
| 349 |
-
"learning_rate": 0.
|
| 350 |
-
"loss": 4.
|
| 351 |
"step": 500
|
| 352 |
},
|
| 353 |
{
|
| 354 |
"epoch": 0.18,
|
| 355 |
-
"eval_accuracy": 0.
|
| 356 |
-
"eval_loss": 4.
|
| 357 |
-
"eval_runtime":
|
| 358 |
-
"eval_samples_per_second":
|
| 359 |
-
"eval_steps_per_second": 4.
|
| 360 |
"step": 500
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 0.18,
|
| 364 |
-
"learning_rate": 0.
|
| 365 |
-
"loss": 4.
|
| 366 |
"step": 510
|
| 367 |
},
|
| 368 |
{
|
| 369 |
"epoch": 0.18,
|
| 370 |
-
"learning_rate": 0.
|
| 371 |
-
"loss": 4.
|
| 372 |
"step": 520
|
| 373 |
},
|
| 374 |
{
|
| 375 |
"epoch": 0.19,
|
| 376 |
-
"learning_rate": 0.
|
| 377 |
-
"loss": 4.
|
| 378 |
"step": 530
|
| 379 |
},
|
| 380 |
{
|
| 381 |
"epoch": 0.19,
|
| 382 |
-
"learning_rate": 0.
|
| 383 |
-
"loss": 4.
|
| 384 |
"step": 540
|
| 385 |
},
|
| 386 |
{
|
| 387 |
"epoch": 0.19,
|
| 388 |
-
"learning_rate": 0.
|
| 389 |
-
"loss": 4.
|
| 390 |
"step": 550
|
| 391 |
},
|
| 392 |
{
|
| 393 |
"epoch": 0.2,
|
| 394 |
-
"learning_rate": 0.
|
| 395 |
-
"loss": 4.
|
| 396 |
"step": 560
|
| 397 |
},
|
| 398 |
{
|
| 399 |
"epoch": 0.2,
|
| 400 |
-
"learning_rate": 0.
|
| 401 |
-
"loss": 4.
|
| 402 |
"step": 570
|
| 403 |
},
|
| 404 |
{
|
| 405 |
"epoch": 0.2,
|
| 406 |
-
"learning_rate": 0.
|
| 407 |
-
"loss": 4.
|
| 408 |
"step": 580
|
| 409 |
},
|
| 410 |
{
|
| 411 |
"epoch": 0.21,
|
| 412 |
-
"learning_rate": 0.
|
| 413 |
-
"loss": 4.
|
| 414 |
"step": 590
|
| 415 |
},
|
| 416 |
{
|
| 417 |
"epoch": 0.21,
|
| 418 |
-
"learning_rate": 0.
|
| 419 |
-
"loss": 4.
|
| 420 |
"step": 600
|
| 421 |
},
|
| 422 |
{
|
| 423 |
"epoch": 0.21,
|
| 424 |
-
"eval_accuracy": 0.
|
| 425 |
-
"eval_loss": 4.
|
| 426 |
-
"eval_runtime":
|
| 427 |
-
"eval_samples_per_second":
|
| 428 |
-
"eval_steps_per_second": 4.
|
| 429 |
"step": 600
|
| 430 |
},
|
| 431 |
{
|
| 432 |
"epoch": 0.22,
|
| 433 |
-
"learning_rate": 0.
|
| 434 |
-
"loss": 4.
|
| 435 |
"step": 610
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 0.22,
|
| 439 |
-
"learning_rate": 0.
|
| 440 |
-
"loss": 4.
|
| 441 |
"step": 620
|
| 442 |
},
|
| 443 |
{
|
| 444 |
"epoch": 0.22,
|
| 445 |
-
"learning_rate": 0.
|
| 446 |
-
"loss": 4.
|
| 447 |
"step": 630
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 0.23,
|
| 451 |
-
"learning_rate": 0.
|
| 452 |
-
"loss": 4.
|
| 453 |
"step": 640
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 0.23,
|
| 457 |
-
"learning_rate": 0.
|
| 458 |
-
"loss": 4.
|
| 459 |
"step": 650
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 0.23,
|
| 463 |
-
"learning_rate": 0.
|
| 464 |
-
"loss": 4.
|
| 465 |
"step": 660
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 0.24,
|
| 469 |
-
"learning_rate": 0.
|
| 470 |
-
"loss": 4.
|
| 471 |
"step": 670
|
| 472 |
},
|
| 473 |
{
|
| 474 |
"epoch": 0.24,
|
| 475 |
-
"learning_rate": 0.
|
| 476 |
-
"loss": 4.
|
| 477 |
"step": 680
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 0.24,
|
| 481 |
-
"learning_rate": 0.
|
| 482 |
-
"loss": 4.
|
| 483 |
"step": 690
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 0.25,
|
| 487 |
-
"learning_rate": 0.
|
| 488 |
-
"loss": 4.
|
| 489 |
"step": 700
|
| 490 |
},
|
| 491 |
{
|
| 492 |
"epoch": 0.25,
|
| 493 |
-
"eval_accuracy": 0.
|
| 494 |
-
"eval_loss": 4.
|
| 495 |
-
"eval_runtime":
|
| 496 |
-
"eval_samples_per_second":
|
| 497 |
-
"eval_steps_per_second": 4.
|
| 498 |
"step": 700
|
| 499 |
},
|
| 500 |
{
|
| 501 |
"epoch": 0.25,
|
| 502 |
-
"learning_rate": 0.
|
| 503 |
-
"loss": 4.
|
| 504 |
"step": 710
|
| 505 |
},
|
| 506 |
{
|
| 507 |
"epoch": 0.25,
|
| 508 |
-
"learning_rate": 0.
|
| 509 |
-
"loss": 4.
|
| 510 |
"step": 720
|
| 511 |
},
|
| 512 |
{
|
| 513 |
"epoch": 0.26,
|
| 514 |
-
"learning_rate": 0.
|
| 515 |
-
"loss": 4.
|
| 516 |
"step": 730
|
| 517 |
},
|
| 518 |
{
|
| 519 |
"epoch": 0.26,
|
| 520 |
-
"learning_rate": 0.
|
| 521 |
-
"loss": 4.
|
| 522 |
"step": 740
|
| 523 |
},
|
| 524 |
{
|
| 525 |
"epoch": 0.26,
|
| 526 |
-
"learning_rate": 0.
|
| 527 |
-
"loss":
|
| 528 |
"step": 750
|
| 529 |
},
|
| 530 |
{
|
| 531 |
"epoch": 0.27,
|
| 532 |
-
"learning_rate": 0.
|
| 533 |
-
"loss": 4.
|
| 534 |
"step": 760
|
| 535 |
},
|
| 536 |
{
|
| 537 |
"epoch": 0.27,
|
| 538 |
-
"learning_rate": 0.
|
| 539 |
-
"loss":
|
| 540 |
"step": 770
|
| 541 |
},
|
| 542 |
{
|
| 543 |
"epoch": 0.28,
|
| 544 |
-
"learning_rate": 0.
|
| 545 |
-
"loss":
|
| 546 |
"step": 780
|
| 547 |
},
|
| 548 |
{
|
| 549 |
"epoch": 0.28,
|
| 550 |
-
"learning_rate": 0.
|
| 551 |
-
"loss":
|
| 552 |
"step": 790
|
| 553 |
},
|
| 554 |
{
|
| 555 |
"epoch": 0.28,
|
| 556 |
-
"learning_rate": 0.
|
| 557 |
-
"loss":
|
| 558 |
"step": 800
|
| 559 |
},
|
| 560 |
{
|
| 561 |
"epoch": 0.28,
|
| 562 |
-
"eval_accuracy": 0.
|
| 563 |
-
"eval_loss":
|
| 564 |
-
"eval_runtime":
|
| 565 |
-
"eval_samples_per_second":
|
| 566 |
-
"eval_steps_per_second": 4.
|
| 567 |
"step": 800
|
| 568 |
},
|
| 569 |
{
|
| 570 |
"epoch": 0.29,
|
| 571 |
-
"learning_rate": 0.
|
| 572 |
-
"loss":
|
| 573 |
"step": 810
|
| 574 |
},
|
| 575 |
{
|
| 576 |
"epoch": 0.29,
|
| 577 |
-
"learning_rate": 0.
|
| 578 |
-
"loss":
|
| 579 |
"step": 820
|
| 580 |
},
|
| 581 |
{
|
| 582 |
"epoch": 0.29,
|
| 583 |
-
"learning_rate": 0.
|
| 584 |
-
"loss":
|
| 585 |
"step": 830
|
| 586 |
},
|
| 587 |
{
|
| 588 |
"epoch": 0.3,
|
| 589 |
-
"learning_rate": 0.
|
| 590 |
-
"loss":
|
| 591 |
"step": 840
|
| 592 |
},
|
| 593 |
{
|
| 594 |
"epoch": 0.3,
|
| 595 |
-
"learning_rate": 0.
|
| 596 |
-
"loss":
|
| 597 |
"step": 850
|
| 598 |
},
|
| 599 |
{
|
| 600 |
"epoch": 0.3,
|
| 601 |
-
"learning_rate": 0.
|
| 602 |
-
"loss":
|
| 603 |
"step": 860
|
| 604 |
},
|
| 605 |
{
|
| 606 |
"epoch": 0.31,
|
| 607 |
-
"learning_rate": 0.
|
| 608 |
-
"loss":
|
| 609 |
"step": 870
|
| 610 |
},
|
| 611 |
{
|
| 612 |
"epoch": 0.31,
|
| 613 |
-
"learning_rate": 0.
|
| 614 |
-
"loss": 3.
|
| 615 |
"step": 880
|
| 616 |
},
|
| 617 |
{
|
| 618 |
"epoch": 0.31,
|
| 619 |
-
"learning_rate": 0.
|
| 620 |
-
"loss":
|
| 621 |
"step": 890
|
| 622 |
},
|
| 623 |
{
|
| 624 |
"epoch": 0.32,
|
| 625 |
-
"learning_rate": 0.
|
| 626 |
-
"loss": 3.
|
| 627 |
"step": 900
|
| 628 |
},
|
| 629 |
{
|
| 630 |
"epoch": 0.32,
|
| 631 |
-
"eval_accuracy": 0.
|
| 632 |
-
"eval_loss": 3.
|
| 633 |
-
"eval_runtime":
|
| 634 |
-
"eval_samples_per_second":
|
| 635 |
-
"eval_steps_per_second": 4.
|
| 636 |
"step": 900
|
| 637 |
},
|
| 638 |
{
|
| 639 |
"epoch": 0.32,
|
| 640 |
-
"learning_rate": 0.
|
| 641 |
-
"loss": 3.
|
| 642 |
"step": 910
|
| 643 |
},
|
| 644 |
{
|
| 645 |
"epoch": 0.32,
|
| 646 |
-
"learning_rate": 0.
|
| 647 |
-
"loss": 3.
|
| 648 |
"step": 920
|
| 649 |
},
|
| 650 |
{
|
| 651 |
"epoch": 0.33,
|
| 652 |
-
"learning_rate": 0.
|
| 653 |
-
"loss": 3.
|
| 654 |
"step": 930
|
| 655 |
},
|
| 656 |
{
|
| 657 |
"epoch": 0.33,
|
| 658 |
-
"learning_rate": 0.
|
| 659 |
-
"loss": 3.
|
| 660 |
"step": 940
|
| 661 |
},
|
| 662 |
{
|
| 663 |
"epoch": 0.34,
|
| 664 |
-
"learning_rate": 0.
|
| 665 |
-
"loss": 3.
|
| 666 |
"step": 950
|
| 667 |
},
|
| 668 |
{
|
| 669 |
"epoch": 0.34,
|
| 670 |
-
"learning_rate": 0.
|
| 671 |
-
"loss": 3.
|
| 672 |
"step": 960
|
| 673 |
},
|
| 674 |
{
|
| 675 |
"epoch": 0.34,
|
| 676 |
-
"learning_rate": 0.
|
| 677 |
-
"loss": 3.
|
| 678 |
"step": 970
|
| 679 |
},
|
| 680 |
{
|
| 681 |
"epoch": 0.35,
|
| 682 |
-
"learning_rate": 0.
|
| 683 |
-
"loss": 3.
|
| 684 |
"step": 980
|
| 685 |
},
|
| 686 |
{
|
| 687 |
"epoch": 0.35,
|
| 688 |
-
"learning_rate": 0.
|
| 689 |
-
"loss": 3.
|
| 690 |
"step": 990
|
| 691 |
},
|
| 692 |
{
|
| 693 |
"epoch": 0.35,
|
| 694 |
-
"learning_rate": 0.
|
| 695 |
-
"loss": 3.
|
| 696 |
"step": 1000
|
| 697 |
},
|
| 698 |
{
|
| 699 |
"epoch": 0.35,
|
| 700 |
-
"eval_accuracy": 0.
|
| 701 |
-
"eval_loss": 3.
|
| 702 |
-
"eval_runtime":
|
| 703 |
-
"eval_samples_per_second":
|
| 704 |
-
"eval_steps_per_second": 4.
|
| 705 |
"step": 1000
|
| 706 |
},
|
| 707 |
{
|
| 708 |
"epoch": 0.36,
|
| 709 |
-
"learning_rate": 0.
|
| 710 |
-
"loss": 3.
|
| 711 |
"step": 1010
|
| 712 |
},
|
| 713 |
{
|
| 714 |
"epoch": 0.36,
|
| 715 |
-
"learning_rate": 0.
|
| 716 |
-
"loss": 3.
|
| 717 |
"step": 1020
|
| 718 |
},
|
| 719 |
{
|
| 720 |
"epoch": 0.36,
|
| 721 |
-
"learning_rate": 0.
|
| 722 |
-
"loss": 3.
|
| 723 |
"step": 1030
|
| 724 |
},
|
| 725 |
{
|
| 726 |
"epoch": 0.37,
|
| 727 |
-
"learning_rate": 0.
|
| 728 |
-
"loss": 3.
|
| 729 |
"step": 1040
|
| 730 |
},
|
| 731 |
{
|
| 732 |
"epoch": 0.37,
|
| 733 |
-
"learning_rate": 0.
|
| 734 |
-
"loss": 3.
|
| 735 |
"step": 1050
|
| 736 |
},
|
| 737 |
{
|
| 738 |
"epoch": 0.37,
|
| 739 |
-
"learning_rate": 0.
|
| 740 |
-
"loss": 3.
|
| 741 |
"step": 1060
|
| 742 |
},
|
| 743 |
{
|
| 744 |
"epoch": 0.38,
|
| 745 |
-
"learning_rate": 0.
|
| 746 |
-
"loss": 3.
|
| 747 |
"step": 1070
|
| 748 |
},
|
| 749 |
{
|
| 750 |
"epoch": 0.38,
|
| 751 |
-
"learning_rate": 0.
|
| 752 |
-
"loss": 3.
|
| 753 |
"step": 1080
|
| 754 |
},
|
| 755 |
{
|
| 756 |
"epoch": 0.38,
|
| 757 |
-
"learning_rate": 0.
|
| 758 |
-
"loss": 3.
|
| 759 |
"step": 1090
|
| 760 |
},
|
| 761 |
{
|
| 762 |
"epoch": 0.39,
|
| 763 |
-
"learning_rate": 0.
|
| 764 |
-
"loss": 3.
|
| 765 |
"step": 1100
|
| 766 |
},
|
| 767 |
{
|
| 768 |
"epoch": 0.39,
|
| 769 |
-
"eval_accuracy": 0.
|
| 770 |
-
"eval_loss": 3.
|
| 771 |
-
"eval_runtime":
|
| 772 |
-
"eval_samples_per_second":
|
| 773 |
-
"eval_steps_per_second": 4.
|
| 774 |
"step": 1100
|
| 775 |
},
|
| 776 |
{
|
| 777 |
"epoch": 0.39,
|
| 778 |
-
"learning_rate": 0.
|
| 779 |
-
"loss": 3.
|
| 780 |
"step": 1110
|
| 781 |
},
|
| 782 |
{
|
| 783 |
"epoch": 0.4,
|
| 784 |
-
"learning_rate": 0.
|
| 785 |
-
"loss": 3.
|
| 786 |
"step": 1120
|
| 787 |
},
|
| 788 |
{
|
| 789 |
"epoch": 0.4,
|
| 790 |
-
"learning_rate": 0.
|
| 791 |
-
"loss": 3.
|
| 792 |
"step": 1130
|
| 793 |
},
|
| 794 |
{
|
| 795 |
"epoch": 0.4,
|
| 796 |
-
"learning_rate": 0.
|
| 797 |
-
"loss": 3.
|
| 798 |
"step": 1140
|
| 799 |
},
|
| 800 |
{
|
| 801 |
"epoch": 0.41,
|
| 802 |
-
"learning_rate": 0.
|
| 803 |
-
"loss": 3.
|
| 804 |
"step": 1150
|
| 805 |
},
|
| 806 |
{
|
| 807 |
"epoch": 0.41,
|
| 808 |
-
"learning_rate": 0.
|
| 809 |
-
"loss": 3.
|
| 810 |
"step": 1160
|
| 811 |
},
|
| 812 |
{
|
| 813 |
"epoch": 0.41,
|
| 814 |
-
"learning_rate": 0.
|
| 815 |
-
"loss": 3.
|
| 816 |
"step": 1170
|
| 817 |
},
|
| 818 |
{
|
| 819 |
"epoch": 0.42,
|
| 820 |
-
"learning_rate": 0.
|
| 821 |
-
"loss": 3.
|
| 822 |
"step": 1180
|
| 823 |
},
|
| 824 |
{
|
| 825 |
"epoch": 0.42,
|
| 826 |
-
"learning_rate": 0.
|
| 827 |
-
"loss": 3.
|
| 828 |
"step": 1190
|
| 829 |
},
|
| 830 |
{
|
| 831 |
"epoch": 0.42,
|
| 832 |
-
"learning_rate": 0.
|
| 833 |
-
"loss": 3.
|
| 834 |
"step": 1200
|
| 835 |
},
|
| 836 |
{
|
| 837 |
"epoch": 0.42,
|
| 838 |
-
"eval_accuracy": 0.
|
| 839 |
-
"eval_loss": 3.
|
| 840 |
-
"eval_runtime":
|
| 841 |
-
"eval_samples_per_second":
|
| 842 |
-
"eval_steps_per_second": 4.
|
| 843 |
"step": 1200
|
| 844 |
},
|
| 845 |
{
|
| 846 |
"epoch": 0.43,
|
| 847 |
-
"learning_rate": 0.
|
| 848 |
-
"loss": 3.
|
| 849 |
"step": 1210
|
| 850 |
},
|
| 851 |
{
|
| 852 |
"epoch": 0.43,
|
| 853 |
-
"learning_rate": 0.
|
| 854 |
-
"loss": 3.
|
| 855 |
"step": 1220
|
| 856 |
},
|
| 857 |
{
|
| 858 |
"epoch": 0.43,
|
| 859 |
-
"learning_rate": 0.
|
| 860 |
-
"loss": 3.
|
| 861 |
"step": 1230
|
| 862 |
},
|
| 863 |
{
|
| 864 |
"epoch": 0.44,
|
| 865 |
-
"learning_rate": 0.
|
| 866 |
-
"loss": 3.
|
| 867 |
"step": 1240
|
| 868 |
},
|
| 869 |
{
|
| 870 |
"epoch": 0.44,
|
| 871 |
-
"learning_rate": 0.
|
| 872 |
-
"loss": 3.
|
| 873 |
"step": 1250
|
| 874 |
},
|
| 875 |
{
|
| 876 |
"epoch": 0.44,
|
| 877 |
-
"learning_rate": 0.
|
| 878 |
-
"loss": 3.
|
| 879 |
"step": 1260
|
| 880 |
},
|
| 881 |
{
|
| 882 |
"epoch": 0.45,
|
| 883 |
-
"learning_rate": 0.
|
| 884 |
-
"loss": 3.
|
| 885 |
"step": 1270
|
| 886 |
},
|
| 887 |
{
|
| 888 |
"epoch": 0.45,
|
| 889 |
-
"learning_rate": 0.
|
| 890 |
-
"loss": 3.
|
| 891 |
"step": 1280
|
| 892 |
},
|
| 893 |
{
|
| 894 |
"epoch": 0.46,
|
| 895 |
-
"learning_rate": 0.
|
| 896 |
-
"loss": 3.
|
| 897 |
"step": 1290
|
| 898 |
},
|
| 899 |
{
|
| 900 |
"epoch": 0.46,
|
| 901 |
-
"learning_rate": 0.
|
| 902 |
-
"loss": 3.
|
| 903 |
"step": 1300
|
| 904 |
},
|
| 905 |
{
|
| 906 |
"epoch": 0.46,
|
| 907 |
-
"eval_accuracy": 0.
|
| 908 |
-
"eval_loss": 3.
|
| 909 |
-
"eval_runtime":
|
| 910 |
-
"eval_samples_per_second":
|
| 911 |
-
"eval_steps_per_second": 4.
|
| 912 |
"step": 1300
|
| 913 |
},
|
| 914 |
{
|
| 915 |
"epoch": 0.46,
|
| 916 |
-
"learning_rate": 0.
|
| 917 |
-
"loss": 3.
|
| 918 |
"step": 1310
|
| 919 |
},
|
| 920 |
{
|
| 921 |
"epoch": 0.47,
|
| 922 |
-
"learning_rate": 0.
|
| 923 |
-
"loss": 3.
|
| 924 |
"step": 1320
|
| 925 |
},
|
| 926 |
{
|
| 927 |
"epoch": 0.47,
|
| 928 |
-
"learning_rate": 0.
|
| 929 |
-
"loss": 3.
|
| 930 |
"step": 1330
|
| 931 |
},
|
| 932 |
{
|
| 933 |
"epoch": 0.47,
|
| 934 |
-
"learning_rate": 0.
|
| 935 |
-
"loss": 3.
|
| 936 |
"step": 1340
|
| 937 |
},
|
| 938 |
{
|
| 939 |
"epoch": 0.48,
|
| 940 |
-
"learning_rate": 0.
|
| 941 |
-
"loss": 3.
|
| 942 |
"step": 1350
|
| 943 |
},
|
| 944 |
{
|
| 945 |
"epoch": 0.48,
|
| 946 |
-
"learning_rate": 0.
|
| 947 |
-
"loss": 3.
|
| 948 |
"step": 1360
|
| 949 |
},
|
| 950 |
{
|
| 951 |
"epoch": 0.48,
|
| 952 |
-
"learning_rate": 0.
|
| 953 |
-
"loss": 3.
|
| 954 |
"step": 1370
|
| 955 |
},
|
| 956 |
{
|
| 957 |
"epoch": 0.49,
|
| 958 |
-
"learning_rate": 0.
|
| 959 |
-
"loss": 3.
|
| 960 |
"step": 1380
|
| 961 |
},
|
| 962 |
{
|
| 963 |
"epoch": 0.49,
|
| 964 |
-
"learning_rate": 0.
|
| 965 |
-
"loss": 3.
|
| 966 |
"step": 1390
|
| 967 |
},
|
| 968 |
{
|
| 969 |
"epoch": 0.49,
|
| 970 |
-
"learning_rate": 0.
|
| 971 |
-
"loss": 3.
|
| 972 |
"step": 1400
|
| 973 |
},
|
| 974 |
{
|
| 975 |
"epoch": 0.49,
|
| 976 |
-
"eval_accuracy": 0.
|
| 977 |
-
"eval_loss": 3.
|
| 978 |
-
"eval_runtime":
|
| 979 |
-
"eval_samples_per_second":
|
| 980 |
-
"eval_steps_per_second": 4.
|
| 981 |
"step": 1400
|
| 982 |
},
|
| 983 |
{
|
| 984 |
"epoch": 0.5,
|
| 985 |
-
"learning_rate": 0.
|
| 986 |
-
"loss": 3.
|
| 987 |
"step": 1410
|
| 988 |
},
|
| 989 |
{
|
| 990 |
"epoch": 0.5,
|
| 991 |
-
"learning_rate": 0.
|
| 992 |
-
"loss": 3.
|
| 993 |
"step": 1420
|
| 994 |
},
|
| 995 |
{
|
| 996 |
"epoch": 0.5,
|
| 997 |
-
"learning_rate": 0.
|
| 998 |
-
"loss": 3.
|
| 999 |
"step": 1430
|
| 1000 |
},
|
| 1001 |
{
|
| 1002 |
"epoch": 0.51,
|
| 1003 |
-
"learning_rate": 0.
|
| 1004 |
-
"loss": 3.
|
| 1005 |
"step": 1440
|
| 1006 |
},
|
| 1007 |
{
|
| 1008 |
"epoch": 0.51,
|
| 1009 |
-
"learning_rate": 0.
|
| 1010 |
-
"loss": 3.
|
| 1011 |
"step": 1450
|
| 1012 |
},
|
| 1013 |
{
|
| 1014 |
"epoch": 0.52,
|
| 1015 |
-
"learning_rate": 0.
|
| 1016 |
-
"loss": 3.
|
| 1017 |
"step": 1460
|
| 1018 |
},
|
| 1019 |
{
|
| 1020 |
"epoch": 0.52,
|
| 1021 |
-
"learning_rate": 0.
|
| 1022 |
-
"loss": 3.
|
| 1023 |
"step": 1470
|
| 1024 |
},
|
| 1025 |
{
|
| 1026 |
"epoch": 0.52,
|
| 1027 |
-
"learning_rate": 0.
|
| 1028 |
-
"loss": 3.
|
| 1029 |
"step": 1480
|
| 1030 |
},
|
| 1031 |
{
|
| 1032 |
"epoch": 0.53,
|
| 1033 |
-
"learning_rate": 0.
|
| 1034 |
-
"loss": 3.
|
| 1035 |
"step": 1490
|
| 1036 |
},
|
| 1037 |
{
|
| 1038 |
"epoch": 0.53,
|
| 1039 |
-
"learning_rate": 0.
|
| 1040 |
-
"loss": 3.
|
| 1041 |
"step": 1500
|
| 1042 |
},
|
| 1043 |
{
|
| 1044 |
"epoch": 0.53,
|
| 1045 |
-
"eval_accuracy": 0.
|
| 1046 |
-
"eval_loss": 3.
|
| 1047 |
-
"eval_runtime":
|
| 1048 |
-
"eval_samples_per_second":
|
| 1049 |
-
"eval_steps_per_second": 4.
|
| 1050 |
"step": 1500
|
| 1051 |
},
|
| 1052 |
{
|
| 1053 |
"epoch": 0.53,
|
| 1054 |
-
"learning_rate": 0.
|
| 1055 |
-
"loss": 3.
|
| 1056 |
"step": 1510
|
| 1057 |
},
|
| 1058 |
{
|
| 1059 |
"epoch": 0.54,
|
| 1060 |
-
"learning_rate": 0.
|
| 1061 |
-
"loss": 3.
|
| 1062 |
"step": 1520
|
| 1063 |
},
|
| 1064 |
{
|
| 1065 |
"epoch": 0.54,
|
| 1066 |
-
"learning_rate": 0.
|
| 1067 |
-
"loss": 3.
|
| 1068 |
"step": 1530
|
| 1069 |
},
|
| 1070 |
{
|
| 1071 |
"epoch": 0.54,
|
| 1072 |
-
"learning_rate": 0.
|
| 1073 |
-
"loss": 3.
|
| 1074 |
"step": 1540
|
| 1075 |
},
|
| 1076 |
{
|
| 1077 |
"epoch": 0.55,
|
| 1078 |
-
"learning_rate": 0.
|
| 1079 |
-
"loss": 3.
|
| 1080 |
"step": 1550
|
| 1081 |
},
|
| 1082 |
{
|
| 1083 |
"epoch": 0.55,
|
| 1084 |
-
"learning_rate": 0.
|
| 1085 |
-
"loss": 3.
|
| 1086 |
"step": 1560
|
| 1087 |
},
|
| 1088 |
{
|
| 1089 |
"epoch": 0.55,
|
| 1090 |
-
"learning_rate": 0.
|
| 1091 |
-
"loss": 3.
|
| 1092 |
"step": 1570
|
| 1093 |
},
|
| 1094 |
{
|
| 1095 |
"epoch": 0.56,
|
| 1096 |
-
"learning_rate": 0.
|
| 1097 |
-
"loss": 3.
|
| 1098 |
"step": 1580
|
| 1099 |
},
|
| 1100 |
{
|
| 1101 |
"epoch": 0.56,
|
| 1102 |
-
"learning_rate": 0.
|
| 1103 |
-
"loss": 3.
|
| 1104 |
"step": 1590
|
| 1105 |
},
|
| 1106 |
{
|
| 1107 |
"epoch": 0.56,
|
| 1108 |
-
"learning_rate": 0.
|
| 1109 |
-
"loss": 3.
|
| 1110 |
"step": 1600
|
| 1111 |
},
|
| 1112 |
{
|
| 1113 |
"epoch": 0.56,
|
| 1114 |
-
"eval_accuracy": 0.
|
| 1115 |
-
"eval_loss": 3.
|
| 1116 |
-
"eval_runtime":
|
| 1117 |
-
"eval_samples_per_second":
|
| 1118 |
-
"eval_steps_per_second": 4.
|
| 1119 |
"step": 1600
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
"epoch": 0.57,
|
| 1123 |
-
"learning_rate": 0.
|
| 1124 |
-
"loss": 3.
|
| 1125 |
"step": 1610
|
| 1126 |
},
|
| 1127 |
{
|
| 1128 |
"epoch": 0.57,
|
| 1129 |
-
"learning_rate": 0.
|
| 1130 |
-
"loss": 3.
|
| 1131 |
"step": 1620
|
| 1132 |
},
|
| 1133 |
{
|
| 1134 |
"epoch": 0.58,
|
| 1135 |
-
"learning_rate": 0.
|
| 1136 |
-
"loss": 3.
|
| 1137 |
"step": 1630
|
| 1138 |
},
|
| 1139 |
{
|
| 1140 |
"epoch": 0.58,
|
| 1141 |
-
"learning_rate": 0.
|
| 1142 |
-
"loss": 3.
|
| 1143 |
"step": 1640
|
| 1144 |
},
|
| 1145 |
{
|
| 1146 |
"epoch": 0.58,
|
| 1147 |
-
"learning_rate": 0.
|
| 1148 |
-
"loss": 3.
|
| 1149 |
"step": 1650
|
| 1150 |
},
|
| 1151 |
{
|
| 1152 |
"epoch": 0.59,
|
| 1153 |
-
"learning_rate": 0.
|
| 1154 |
-
"loss": 3.
|
| 1155 |
"step": 1660
|
| 1156 |
},
|
| 1157 |
{
|
| 1158 |
"epoch": 0.59,
|
| 1159 |
-
"learning_rate": 0.
|
| 1160 |
-
"loss": 3.
|
| 1161 |
"step": 1670
|
| 1162 |
},
|
| 1163 |
{
|
| 1164 |
"epoch": 0.59,
|
| 1165 |
-
"learning_rate": 0.
|
| 1166 |
-
"loss": 3.
|
| 1167 |
"step": 1680
|
| 1168 |
},
|
| 1169 |
{
|
| 1170 |
"epoch": 0.6,
|
| 1171 |
-
"learning_rate": 0.
|
| 1172 |
-
"loss": 3.
|
| 1173 |
"step": 1690
|
| 1174 |
},
|
| 1175 |
{
|
| 1176 |
"epoch": 0.6,
|
| 1177 |
-
"learning_rate": 0.
|
| 1178 |
-
"loss": 3.
|
| 1179 |
"step": 1700
|
| 1180 |
},
|
| 1181 |
{
|
| 1182 |
"epoch": 0.6,
|
| 1183 |
-
"eval_accuracy": 0.
|
| 1184 |
-
"eval_loss": 3.
|
| 1185 |
-
"eval_runtime":
|
| 1186 |
-
"eval_samples_per_second":
|
| 1187 |
-
"eval_steps_per_second": 4.
|
| 1188 |
"step": 1700
|
| 1189 |
},
|
| 1190 |
{
|
| 1191 |
"epoch": 0.6,
|
| 1192 |
-
"learning_rate": 0.
|
| 1193 |
-
"loss": 3.
|
| 1194 |
"step": 1710
|
| 1195 |
},
|
| 1196 |
{
|
| 1197 |
"epoch": 0.61,
|
| 1198 |
-
"learning_rate": 0.
|
| 1199 |
-
"loss": 3.
|
| 1200 |
"step": 1720
|
| 1201 |
},
|
| 1202 |
{
|
| 1203 |
"epoch": 0.61,
|
| 1204 |
-
"learning_rate": 0.
|
| 1205 |
-
"loss": 3.
|
| 1206 |
"step": 1730
|
| 1207 |
},
|
| 1208 |
{
|
| 1209 |
"epoch": 0.61,
|
| 1210 |
-
"learning_rate": 0.
|
| 1211 |
-
"loss": 3.
|
| 1212 |
"step": 1740
|
| 1213 |
},
|
| 1214 |
{
|
| 1215 |
"epoch": 0.62,
|
| 1216 |
-
"learning_rate": 0.
|
| 1217 |
-
"loss": 3.
|
| 1218 |
"step": 1750
|
| 1219 |
},
|
| 1220 |
{
|
| 1221 |
"epoch": 0.62,
|
| 1222 |
-
"learning_rate": 0.
|
| 1223 |
-
"loss": 3.
|
| 1224 |
"step": 1760
|
| 1225 |
},
|
| 1226 |
{
|
| 1227 |
"epoch": 0.62,
|
| 1228 |
-
"learning_rate": 0.
|
| 1229 |
-
"loss": 3.
|
| 1230 |
"step": 1770
|
| 1231 |
},
|
| 1232 |
{
|
| 1233 |
"epoch": 0.63,
|
| 1234 |
-
"learning_rate": 0.
|
| 1235 |
-
"loss": 3.
|
| 1236 |
"step": 1780
|
| 1237 |
},
|
| 1238 |
{
|
| 1239 |
"epoch": 0.63,
|
| 1240 |
-
"learning_rate": 0.
|
| 1241 |
-
"loss": 3.
|
| 1242 |
"step": 1790
|
| 1243 |
},
|
| 1244 |
{
|
| 1245 |
"epoch": 0.64,
|
| 1246 |
-
"learning_rate": 0.
|
| 1247 |
-
"loss": 3.
|
| 1248 |
"step": 1800
|
| 1249 |
},
|
| 1250 |
{
|
| 1251 |
"epoch": 0.64,
|
| 1252 |
-
"eval_accuracy": 0.
|
| 1253 |
-
"eval_loss": 3.
|
| 1254 |
-
"eval_runtime":
|
| 1255 |
-
"eval_samples_per_second":
|
| 1256 |
-
"eval_steps_per_second": 4.
|
| 1257 |
"step": 1800
|
| 1258 |
},
|
| 1259 |
{
|
| 1260 |
"epoch": 0.64,
|
| 1261 |
-
"learning_rate": 0.
|
| 1262 |
-
"loss": 3.
|
| 1263 |
"step": 1810
|
| 1264 |
},
|
| 1265 |
{
|
| 1266 |
"epoch": 0.64,
|
| 1267 |
-
"learning_rate": 0.
|
| 1268 |
-
"loss": 3.
|
| 1269 |
"step": 1820
|
| 1270 |
},
|
| 1271 |
{
|
| 1272 |
"epoch": 0.65,
|
| 1273 |
-
"learning_rate": 0.
|
| 1274 |
-
"loss": 3.
|
| 1275 |
"step": 1830
|
| 1276 |
},
|
| 1277 |
{
|
| 1278 |
"epoch": 0.65,
|
| 1279 |
-
"learning_rate": 0.
|
| 1280 |
-
"loss": 3.
|
| 1281 |
"step": 1840
|
| 1282 |
},
|
| 1283 |
{
|
| 1284 |
"epoch": 0.65,
|
| 1285 |
-
"learning_rate": 0.
|
| 1286 |
-
"loss": 3.
|
| 1287 |
"step": 1850
|
| 1288 |
},
|
| 1289 |
{
|
| 1290 |
"epoch": 0.66,
|
| 1291 |
-
"learning_rate": 0.
|
| 1292 |
-
"loss": 3.
|
| 1293 |
"step": 1860
|
| 1294 |
},
|
| 1295 |
{
|
| 1296 |
"epoch": 0.66,
|
| 1297 |
-
"learning_rate": 0.
|
| 1298 |
-
"loss": 3.
|
| 1299 |
"step": 1870
|
| 1300 |
},
|
| 1301 |
{
|
| 1302 |
"epoch": 0.66,
|
| 1303 |
-
"learning_rate": 0.
|
| 1304 |
-
"loss": 3.
|
| 1305 |
"step": 1880
|
| 1306 |
},
|
| 1307 |
{
|
| 1308 |
"epoch": 0.67,
|
| 1309 |
-
"learning_rate": 0.
|
| 1310 |
-
"loss": 3.
|
| 1311 |
"step": 1890
|
| 1312 |
},
|
| 1313 |
{
|
| 1314 |
"epoch": 0.67,
|
| 1315 |
-
"learning_rate": 0.
|
| 1316 |
-
"loss": 3.
|
| 1317 |
"step": 1900
|
| 1318 |
},
|
| 1319 |
{
|
| 1320 |
"epoch": 0.67,
|
| 1321 |
-
"eval_accuracy": 0.
|
| 1322 |
-
"eval_loss": 3.
|
| 1323 |
-
"eval_runtime":
|
| 1324 |
-
"eval_samples_per_second":
|
| 1325 |
-
"eval_steps_per_second": 4.
|
| 1326 |
"step": 1900
|
| 1327 |
},
|
| 1328 |
{
|
| 1329 |
"epoch": 0.67,
|
| 1330 |
-
"learning_rate": 0.
|
| 1331 |
-
"loss": 3.
|
| 1332 |
"step": 1910
|
| 1333 |
},
|
| 1334 |
{
|
| 1335 |
"epoch": 0.68,
|
| 1336 |
-
"learning_rate": 0.
|
| 1337 |
-
"loss": 3.
|
| 1338 |
"step": 1920
|
| 1339 |
},
|
| 1340 |
{
|
| 1341 |
"epoch": 0.68,
|
| 1342 |
-
"learning_rate": 0.
|
| 1343 |
-
"loss": 3.
|
| 1344 |
"step": 1930
|
| 1345 |
},
|
| 1346 |
{
|
| 1347 |
"epoch": 0.68,
|
| 1348 |
-
"learning_rate": 0.
|
| 1349 |
-
"loss": 3.
|
| 1350 |
"step": 1940
|
| 1351 |
},
|
| 1352 |
{
|
| 1353 |
"epoch": 0.69,
|
| 1354 |
-
"learning_rate": 0.
|
| 1355 |
-
"loss": 3.
|
| 1356 |
"step": 1950
|
| 1357 |
},
|
| 1358 |
{
|
| 1359 |
"epoch": 0.69,
|
| 1360 |
-
"learning_rate": 0.
|
| 1361 |
-
"loss": 3.
|
| 1362 |
"step": 1960
|
| 1363 |
},
|
| 1364 |
{
|
| 1365 |
"epoch": 0.7,
|
| 1366 |
-
"learning_rate": 0.
|
| 1367 |
-
"loss": 3.
|
| 1368 |
"step": 1970
|
| 1369 |
},
|
| 1370 |
{
|
| 1371 |
"epoch": 0.7,
|
| 1372 |
-
"learning_rate": 0.
|
| 1373 |
-
"loss": 3.
|
| 1374 |
"step": 1980
|
| 1375 |
},
|
| 1376 |
{
|
| 1377 |
"epoch": 0.7,
|
| 1378 |
-
"learning_rate": 0.
|
| 1379 |
-
"loss": 3.
|
| 1380 |
"step": 1990
|
| 1381 |
},
|
| 1382 |
{
|
| 1383 |
"epoch": 0.71,
|
| 1384 |
-
"learning_rate": 0.
|
| 1385 |
-
"loss": 3.
|
| 1386 |
"step": 2000
|
| 1387 |
},
|
| 1388 |
{
|
| 1389 |
"epoch": 0.71,
|
| 1390 |
-
"eval_accuracy": 0.
|
| 1391 |
-
"eval_loss": 3.
|
| 1392 |
-
"eval_runtime":
|
| 1393 |
-
"eval_samples_per_second":
|
| 1394 |
-
"eval_steps_per_second": 4.
|
| 1395 |
"step": 2000
|
| 1396 |
},
|
| 1397 |
{
|
| 1398 |
"epoch": 0.71,
|
| 1399 |
-
"learning_rate": 0.
|
| 1400 |
-
"loss": 3.
|
| 1401 |
"step": 2010
|
| 1402 |
},
|
| 1403 |
{
|
| 1404 |
"epoch": 0.71,
|
| 1405 |
-
"learning_rate": 0.
|
| 1406 |
-
"loss": 3.
|
| 1407 |
"step": 2020
|
| 1408 |
},
|
| 1409 |
{
|
| 1410 |
"epoch": 0.72,
|
| 1411 |
-
"learning_rate": 0.
|
| 1412 |
-
"loss": 3.
|
| 1413 |
"step": 2030
|
| 1414 |
},
|
| 1415 |
{
|
| 1416 |
"epoch": 0.72,
|
| 1417 |
-
"learning_rate": 0.
|
| 1418 |
-
"loss": 3.
|
| 1419 |
"step": 2040
|
| 1420 |
},
|
| 1421 |
{
|
| 1422 |
"epoch": 0.72,
|
| 1423 |
-
"learning_rate": 0.
|
| 1424 |
-
"loss": 3.
|
| 1425 |
"step": 2050
|
| 1426 |
},
|
| 1427 |
{
|
| 1428 |
"epoch": 0.73,
|
| 1429 |
-
"learning_rate": 0.
|
| 1430 |
-
"loss": 3.
|
| 1431 |
"step": 2060
|
| 1432 |
},
|
| 1433 |
{
|
| 1434 |
"epoch": 0.73,
|
| 1435 |
-
"learning_rate": 0.
|
| 1436 |
-
"loss": 3.
|
| 1437 |
"step": 2070
|
| 1438 |
},
|
| 1439 |
{
|
| 1440 |
"epoch": 0.73,
|
| 1441 |
-
"learning_rate": 0.
|
| 1442 |
-
"loss": 3.
|
| 1443 |
"step": 2080
|
| 1444 |
},
|
| 1445 |
{
|
| 1446 |
"epoch": 0.74,
|
| 1447 |
-
"learning_rate": 0.
|
| 1448 |
-
"loss": 3.
|
| 1449 |
"step": 2090
|
| 1450 |
},
|
| 1451 |
{
|
| 1452 |
"epoch": 0.74,
|
| 1453 |
-
"learning_rate": 0.
|
| 1454 |
-
"loss": 3.
|
| 1455 |
"step": 2100
|
| 1456 |
},
|
| 1457 |
{
|
| 1458 |
"epoch": 0.74,
|
| 1459 |
-
"eval_accuracy": 0.
|
| 1460 |
-
"eval_loss": 3.
|
| 1461 |
-
"eval_runtime":
|
| 1462 |
-
"eval_samples_per_second":
|
| 1463 |
-
"eval_steps_per_second": 4.
|
| 1464 |
"step": 2100
|
| 1465 |
},
|
| 1466 |
{
|
| 1467 |
"epoch": 0.74,
|
| 1468 |
-
"learning_rate": 0.
|
| 1469 |
-
"loss": 3.
|
| 1470 |
"step": 2110
|
| 1471 |
},
|
| 1472 |
{
|
| 1473 |
"epoch": 0.75,
|
| 1474 |
-
"learning_rate": 0.
|
| 1475 |
-
"loss": 3.
|
| 1476 |
"step": 2120
|
| 1477 |
},
|
| 1478 |
{
|
| 1479 |
"epoch": 0.75,
|
| 1480 |
-
"learning_rate": 0.
|
| 1481 |
-
"loss": 3.
|
| 1482 |
"step": 2130
|
| 1483 |
},
|
| 1484 |
{
|
| 1485 |
"epoch": 0.76,
|
| 1486 |
-
"learning_rate": 0.
|
| 1487 |
-
"loss": 3.
|
| 1488 |
"step": 2140
|
| 1489 |
},
|
| 1490 |
{
|
| 1491 |
"epoch": 0.76,
|
| 1492 |
-
"learning_rate": 0.
|
| 1493 |
-
"loss": 3.
|
| 1494 |
"step": 2150
|
| 1495 |
},
|
| 1496 |
{
|
| 1497 |
"epoch": 0.76,
|
| 1498 |
-
"learning_rate": 0.
|
| 1499 |
-
"loss": 3.
|
| 1500 |
"step": 2160
|
| 1501 |
},
|
| 1502 |
{
|
| 1503 |
"epoch": 0.77,
|
| 1504 |
-
"learning_rate": 0.
|
| 1505 |
-
"loss": 3.
|
| 1506 |
"step": 2170
|
| 1507 |
},
|
| 1508 |
{
|
| 1509 |
"epoch": 0.77,
|
| 1510 |
-
"learning_rate": 0.
|
| 1511 |
-
"loss": 3.
|
| 1512 |
"step": 2180
|
| 1513 |
},
|
| 1514 |
{
|
| 1515 |
"epoch": 0.77,
|
| 1516 |
-
"learning_rate": 0.
|
| 1517 |
-
"loss": 3.
|
| 1518 |
"step": 2190
|
| 1519 |
},
|
| 1520 |
{
|
| 1521 |
"epoch": 0.78,
|
| 1522 |
-
"learning_rate": 0.
|
| 1523 |
-
"loss": 3.
|
| 1524 |
"step": 2200
|
| 1525 |
},
|
| 1526 |
{
|
| 1527 |
"epoch": 0.78,
|
| 1528 |
-
"eval_accuracy": 0.
|
| 1529 |
-
"eval_loss": 3.
|
| 1530 |
-
"eval_runtime":
|
| 1531 |
-
"eval_samples_per_second":
|
| 1532 |
-
"eval_steps_per_second": 4.
|
| 1533 |
"step": 2200
|
| 1534 |
},
|
| 1535 |
{
|
| 1536 |
"epoch": 0.78,
|
| 1537 |
-
"learning_rate":
|
| 1538 |
-
"loss": 3.
|
| 1539 |
"step": 2210
|
| 1540 |
},
|
| 1541 |
{
|
| 1542 |
"epoch": 0.78,
|
| 1543 |
-
"learning_rate":
|
| 1544 |
-
"loss": 3.
|
| 1545 |
"step": 2220
|
| 1546 |
},
|
| 1547 |
{
|
| 1548 |
"epoch": 0.79,
|
| 1549 |
-
"learning_rate":
|
| 1550 |
-
"loss": 3.
|
| 1551 |
"step": 2230
|
| 1552 |
},
|
| 1553 |
{
|
| 1554 |
"epoch": 0.79,
|
| 1555 |
-
"learning_rate":
|
| 1556 |
-
"loss": 3.
|
| 1557 |
"step": 2240
|
| 1558 |
},
|
| 1559 |
{
|
| 1560 |
"epoch": 0.79,
|
| 1561 |
-
"learning_rate":
|
| 1562 |
-
"loss": 3.
|
| 1563 |
"step": 2250
|
| 1564 |
},
|
| 1565 |
{
|
| 1566 |
"epoch": 0.8,
|
| 1567 |
-
"learning_rate":
|
| 1568 |
-
"loss": 3.
|
| 1569 |
"step": 2260
|
| 1570 |
},
|
| 1571 |
{
|
| 1572 |
"epoch": 0.8,
|
| 1573 |
-
"learning_rate":
|
| 1574 |
-
"loss": 3.
|
| 1575 |
"step": 2270
|
| 1576 |
},
|
| 1577 |
{
|
| 1578 |
"epoch": 0.8,
|
| 1579 |
-
"learning_rate":
|
| 1580 |
-
"loss": 3.
|
| 1581 |
"step": 2280
|
| 1582 |
},
|
| 1583 |
{
|
| 1584 |
"epoch": 0.81,
|
| 1585 |
-
"learning_rate":
|
| 1586 |
-
"loss": 3.
|
| 1587 |
"step": 2290
|
| 1588 |
},
|
| 1589 |
{
|
| 1590 |
"epoch": 0.81,
|
| 1591 |
-
"learning_rate":
|
| 1592 |
-
"loss": 3.
|
| 1593 |
"step": 2300
|
| 1594 |
},
|
| 1595 |
{
|
| 1596 |
"epoch": 0.81,
|
| 1597 |
-
"eval_accuracy": 0.
|
| 1598 |
-
"eval_loss": 3.
|
| 1599 |
-
"eval_runtime":
|
| 1600 |
-
"eval_samples_per_second":
|
| 1601 |
-
"eval_steps_per_second": 4.
|
| 1602 |
"step": 2300
|
| 1603 |
},
|
| 1604 |
{
|
| 1605 |
"epoch": 0.82,
|
| 1606 |
-
"learning_rate":
|
| 1607 |
-
"loss": 3.
|
| 1608 |
"step": 2310
|
| 1609 |
},
|
| 1610 |
{
|
| 1611 |
"epoch": 0.82,
|
| 1612 |
-
"learning_rate":
|
| 1613 |
-
"loss": 3.
|
| 1614 |
"step": 2320
|
| 1615 |
},
|
| 1616 |
{
|
| 1617 |
"epoch": 0.82,
|
| 1618 |
-
"learning_rate":
|
| 1619 |
-
"loss": 3.
|
| 1620 |
"step": 2330
|
| 1621 |
},
|
| 1622 |
{
|
| 1623 |
"epoch": 0.83,
|
| 1624 |
-
"learning_rate":
|
| 1625 |
-
"loss": 3.
|
| 1626 |
"step": 2340
|
| 1627 |
},
|
| 1628 |
{
|
| 1629 |
"epoch": 0.83,
|
| 1630 |
-
"learning_rate":
|
| 1631 |
-
"loss": 3.
|
| 1632 |
"step": 2350
|
| 1633 |
},
|
| 1634 |
{
|
| 1635 |
"epoch": 0.83,
|
| 1636 |
-
"learning_rate":
|
| 1637 |
-
"loss": 3.
|
| 1638 |
"step": 2360
|
| 1639 |
},
|
| 1640 |
{
|
| 1641 |
"epoch": 0.84,
|
| 1642 |
-
"learning_rate":
|
| 1643 |
-
"loss": 3.
|
| 1644 |
"step": 2370
|
| 1645 |
},
|
| 1646 |
{
|
| 1647 |
"epoch": 0.84,
|
| 1648 |
-
"learning_rate":
|
| 1649 |
-
"loss": 3.
|
| 1650 |
"step": 2380
|
| 1651 |
},
|
| 1652 |
{
|
| 1653 |
"epoch": 0.84,
|
| 1654 |
-
"learning_rate":
|
| 1655 |
-
"loss": 3.
|
| 1656 |
"step": 2390
|
| 1657 |
},
|
| 1658 |
{
|
| 1659 |
"epoch": 0.85,
|
| 1660 |
-
"learning_rate":
|
| 1661 |
-
"loss": 3.
|
| 1662 |
"step": 2400
|
| 1663 |
},
|
| 1664 |
{
|
| 1665 |
"epoch": 0.85,
|
| 1666 |
-
"eval_accuracy": 0.
|
| 1667 |
-
"eval_loss": 3.
|
| 1668 |
-
"eval_runtime":
|
| 1669 |
-
"eval_samples_per_second":
|
| 1670 |
-
"eval_steps_per_second": 4.
|
| 1671 |
"step": 2400
|
| 1672 |
},
|
| 1673 |
{
|
| 1674 |
"epoch": 0.85,
|
| 1675 |
-
"learning_rate":
|
| 1676 |
-
"loss": 3.
|
| 1677 |
"step": 2410
|
| 1678 |
},
|
| 1679 |
{
|
| 1680 |
"epoch": 0.85,
|
| 1681 |
-
"learning_rate":
|
| 1682 |
-
"loss": 3.
|
| 1683 |
"step": 2420
|
| 1684 |
},
|
| 1685 |
{
|
| 1686 |
"epoch": 0.86,
|
| 1687 |
-
"learning_rate":
|
| 1688 |
-
"loss": 3.
|
| 1689 |
"step": 2430
|
| 1690 |
},
|
| 1691 |
{
|
| 1692 |
"epoch": 0.86,
|
| 1693 |
-
"learning_rate":
|
| 1694 |
-
"loss": 3.
|
| 1695 |
"step": 2440
|
| 1696 |
},
|
| 1697 |
{
|
| 1698 |
"epoch": 0.86,
|
| 1699 |
-
"learning_rate":
|
| 1700 |
-
"loss": 3.
|
| 1701 |
"step": 2450
|
| 1702 |
},
|
| 1703 |
{
|
| 1704 |
"epoch": 0.87,
|
| 1705 |
-
"learning_rate":
|
| 1706 |
-
"loss": 3.
|
| 1707 |
"step": 2460
|
| 1708 |
},
|
| 1709 |
{
|
| 1710 |
"epoch": 0.87,
|
| 1711 |
-
"learning_rate":
|
| 1712 |
-
"loss": 3.
|
| 1713 |
"step": 2470
|
| 1714 |
},
|
| 1715 |
{
|
| 1716 |
"epoch": 0.88,
|
| 1717 |
-
"learning_rate":
|
| 1718 |
-
"loss": 3.
|
| 1719 |
"step": 2480
|
| 1720 |
},
|
| 1721 |
{
|
| 1722 |
"epoch": 0.88,
|
| 1723 |
-
"learning_rate":
|
| 1724 |
-
"loss": 3.
|
| 1725 |
"step": 2490
|
| 1726 |
},
|
| 1727 |
{
|
| 1728 |
"epoch": 0.88,
|
| 1729 |
-
"learning_rate":
|
| 1730 |
-
"loss": 3.
|
| 1731 |
"step": 2500
|
| 1732 |
},
|
| 1733 |
{
|
| 1734 |
"epoch": 0.88,
|
| 1735 |
-
"eval_accuracy": 0.
|
| 1736 |
-
"eval_loss": 3.
|
| 1737 |
-
"eval_runtime":
|
| 1738 |
-
"eval_samples_per_second":
|
| 1739 |
-
"eval_steps_per_second": 4.
|
| 1740 |
"step": 2500
|
| 1741 |
},
|
| 1742 |
{
|
| 1743 |
"epoch": 0.89,
|
| 1744 |
-
"learning_rate":
|
| 1745 |
-
"loss": 3.
|
| 1746 |
"step": 2510
|
| 1747 |
},
|
| 1748 |
{
|
| 1749 |
"epoch": 0.89,
|
| 1750 |
-
"learning_rate":
|
| 1751 |
-
"loss": 3.
|
| 1752 |
"step": 2520
|
| 1753 |
},
|
| 1754 |
{
|
| 1755 |
"epoch": 0.89,
|
| 1756 |
-
"learning_rate":
|
| 1757 |
-
"loss": 3.
|
| 1758 |
"step": 2530
|
| 1759 |
},
|
| 1760 |
{
|
| 1761 |
"epoch": 0.9,
|
| 1762 |
-
"learning_rate":
|
| 1763 |
-
"loss": 3.
|
| 1764 |
"step": 2540
|
| 1765 |
},
|
| 1766 |
{
|
| 1767 |
"epoch": 0.9,
|
| 1768 |
-
"learning_rate":
|
| 1769 |
-
"loss": 3.
|
| 1770 |
"step": 2550
|
| 1771 |
},
|
| 1772 |
{
|
| 1773 |
"epoch": 0.9,
|
| 1774 |
-
"learning_rate":
|
| 1775 |
-
"loss": 3.
|
| 1776 |
"step": 2560
|
| 1777 |
},
|
| 1778 |
{
|
| 1779 |
"epoch": 0.91,
|
| 1780 |
-
"learning_rate":
|
| 1781 |
-
"loss": 3.
|
| 1782 |
"step": 2570
|
| 1783 |
},
|
| 1784 |
{
|
| 1785 |
"epoch": 0.91,
|
| 1786 |
-
"learning_rate":
|
| 1787 |
-
"loss": 3.
|
| 1788 |
"step": 2580
|
| 1789 |
},
|
| 1790 |
{
|
| 1791 |
"epoch": 0.91,
|
| 1792 |
-
"learning_rate":
|
| 1793 |
-
"loss": 3.
|
| 1794 |
"step": 2590
|
| 1795 |
},
|
| 1796 |
{
|
| 1797 |
"epoch": 0.92,
|
| 1798 |
-
"learning_rate":
|
| 1799 |
-
"loss": 3.
|
| 1800 |
"step": 2600
|
| 1801 |
},
|
| 1802 |
{
|
| 1803 |
"epoch": 0.92,
|
| 1804 |
-
"eval_accuracy": 0.
|
| 1805 |
-
"eval_loss": 3.
|
| 1806 |
-
"eval_runtime":
|
| 1807 |
-
"eval_samples_per_second":
|
| 1808 |
-
"eval_steps_per_second": 4.
|
| 1809 |
"step": 2600
|
| 1810 |
},
|
| 1811 |
{
|
| 1812 |
"epoch": 0.92,
|
| 1813 |
-
"learning_rate":
|
| 1814 |
-
"loss": 3.
|
| 1815 |
"step": 2610
|
| 1816 |
},
|
| 1817 |
{
|
| 1818 |
"epoch": 0.92,
|
| 1819 |
-
"learning_rate":
|
| 1820 |
-
"loss": 3.
|
| 1821 |
"step": 2620
|
| 1822 |
},
|
| 1823 |
{
|
| 1824 |
"epoch": 0.93,
|
| 1825 |
-
"learning_rate":
|
| 1826 |
-
"loss": 3.
|
| 1827 |
"step": 2630
|
| 1828 |
},
|
| 1829 |
{
|
| 1830 |
"epoch": 0.93,
|
| 1831 |
-
"learning_rate":
|
| 1832 |
-
"loss": 3.
|
| 1833 |
"step": 2640
|
| 1834 |
},
|
| 1835 |
{
|
| 1836 |
"epoch": 0.94,
|
| 1837 |
-
"learning_rate":
|
| 1838 |
-
"loss": 3.
|
| 1839 |
"step": 2650
|
| 1840 |
},
|
| 1841 |
{
|
| 1842 |
"epoch": 0.94,
|
| 1843 |
-
"learning_rate":
|
| 1844 |
-
"loss": 3.
|
| 1845 |
"step": 2660
|
| 1846 |
},
|
| 1847 |
{
|
| 1848 |
"epoch": 0.94,
|
| 1849 |
-
"learning_rate":
|
| 1850 |
-
"loss": 3.
|
| 1851 |
"step": 2670
|
| 1852 |
},
|
| 1853 |
{
|
| 1854 |
"epoch": 0.95,
|
| 1855 |
-
"learning_rate":
|
| 1856 |
-
"loss": 3.
|
| 1857 |
"step": 2680
|
| 1858 |
},
|
| 1859 |
{
|
| 1860 |
"epoch": 0.95,
|
| 1861 |
-
"learning_rate":
|
| 1862 |
-
"loss": 3.
|
| 1863 |
"step": 2690
|
| 1864 |
},
|
| 1865 |
{
|
| 1866 |
"epoch": 0.95,
|
| 1867 |
-
"learning_rate":
|
| 1868 |
-
"loss": 3.
|
| 1869 |
"step": 2700
|
| 1870 |
},
|
| 1871 |
{
|
| 1872 |
"epoch": 0.95,
|
| 1873 |
-
"eval_accuracy": 0.
|
| 1874 |
-
"eval_loss": 3.
|
| 1875 |
-
"eval_runtime":
|
| 1876 |
-
"eval_samples_per_second":
|
| 1877 |
-
"eval_steps_per_second": 4.
|
| 1878 |
"step": 2700
|
| 1879 |
},
|
| 1880 |
{
|
| 1881 |
"epoch": 0.96,
|
| 1882 |
-
"learning_rate":
|
| 1883 |
-
"loss": 3.
|
| 1884 |
"step": 2710
|
| 1885 |
},
|
| 1886 |
{
|
| 1887 |
"epoch": 0.96,
|
| 1888 |
-
"learning_rate":
|
| 1889 |
-
"loss": 3.
|
| 1890 |
"step": 2720
|
| 1891 |
},
|
| 1892 |
{
|
| 1893 |
"epoch": 0.96,
|
| 1894 |
-
"learning_rate":
|
| 1895 |
-
"loss": 3.
|
| 1896 |
"step": 2730
|
| 1897 |
},
|
| 1898 |
{
|
| 1899 |
"epoch": 0.97,
|
| 1900 |
-
"learning_rate":
|
| 1901 |
-
"loss": 3.
|
| 1902 |
"step": 2740
|
| 1903 |
},
|
| 1904 |
{
|
| 1905 |
"epoch": 0.97,
|
| 1906 |
-
"learning_rate":
|
| 1907 |
-
"loss": 3.
|
| 1908 |
"step": 2750
|
| 1909 |
},
|
| 1910 |
{
|
| 1911 |
"epoch": 0.97,
|
| 1912 |
-
"learning_rate":
|
| 1913 |
-
"loss": 3.
|
| 1914 |
"step": 2760
|
| 1915 |
},
|
| 1916 |
{
|
| 1917 |
"epoch": 0.98,
|
| 1918 |
-
"learning_rate":
|
| 1919 |
-
"loss": 3.
|
| 1920 |
"step": 2770
|
| 1921 |
},
|
| 1922 |
{
|
| 1923 |
"epoch": 0.98,
|
| 1924 |
-
"learning_rate":
|
| 1925 |
-
"loss": 3.
|
| 1926 |
"step": 2780
|
| 1927 |
},
|
| 1928 |
{
|
| 1929 |
"epoch": 0.98,
|
| 1930 |
-
"learning_rate":
|
| 1931 |
-
"loss": 3.
|
| 1932 |
"step": 2790
|
| 1933 |
},
|
| 1934 |
{
|
| 1935 |
"epoch": 0.99,
|
| 1936 |
-
"learning_rate":
|
| 1937 |
-
"loss": 3.
|
| 1938 |
"step": 2800
|
| 1939 |
},
|
| 1940 |
{
|
| 1941 |
"epoch": 0.99,
|
| 1942 |
-
"eval_accuracy": 0.
|
| 1943 |
-
"eval_loss": 3.
|
| 1944 |
-
"eval_runtime":
|
| 1945 |
-
"eval_samples_per_second":
|
| 1946 |
-
"eval_steps_per_second": 4.
|
| 1947 |
"step": 2800
|
| 1948 |
},
|
| 1949 |
{
|
| 1950 |
"epoch": 0.99,
|
| 1951 |
-
"learning_rate":
|
| 1952 |
-
"loss": 3.
|
| 1953 |
"step": 2810
|
| 1954 |
},
|
| 1955 |
{
|
| 1956 |
"epoch": 1.0,
|
| 1957 |
-
"learning_rate":
|
| 1958 |
-
"loss":
|
| 1959 |
"step": 2820
|
| 1960 |
},
|
| 1961 |
{
|
| 1962 |
"epoch": 1.0,
|
| 1963 |
-
"learning_rate":
|
| 1964 |
-
"loss": 3.
|
| 1965 |
"step": 2830
|
| 1966 |
},
|
| 1967 |
{
|
| 1968 |
"epoch": 1.0,
|
| 1969 |
"step": 2833,
|
| 1970 |
-
"total_flos":
|
| 1971 |
-
"train_loss": 3.
|
| 1972 |
-
"train_runtime":
|
| 1973 |
-
"train_samples_per_second":
|
| 1974 |
-
"train_steps_per_second": 0.
|
| 1975 |
}
|
| 1976 |
],
|
| 1977 |
"logging_steps": 10,
|
|
@@ -1979,8 +1979,8 @@
|
|
| 1979 |
"num_input_tokens_seen": 0,
|
| 1980 |
"num_train_epochs": 1,
|
| 1981 |
"save_steps": 1000.0,
|
| 1982 |
-
"total_flos":
|
| 1983 |
-
"train_batch_size":
|
| 1984 |
"trial_name": null,
|
| 1985 |
"trial_params": null
|
| 1986 |
}
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 8.000000000000001e-06,
|
| 14 |
+
"loss": 10.5725,
|
| 15 |
"step": 1
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.0,
|
| 19 |
+
"learning_rate": 8e-05,
|
| 20 |
+
"loss": 9.6876,
|
| 21 |
"step": 10
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 0.00016,
|
| 26 |
+
"loss": 8.4164,
|
| 27 |
"step": 20
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.01,
|
| 31 |
+
"learning_rate": 0.00024,
|
| 32 |
+
"loss": 7.5148,
|
| 33 |
"step": 30
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.01,
|
| 37 |
+
"learning_rate": 0.00032,
|
| 38 |
+
"loss": 7.2623,
|
| 39 |
"step": 40
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.02,
|
| 43 |
+
"learning_rate": 0.0004,
|
| 44 |
+
"loss": 7.0235,
|
| 45 |
"step": 50
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.02,
|
| 49 |
+
"learning_rate": 0.00048,
|
| 50 |
+
"loss": 6.7411,
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.02,
|
| 55 |
+
"learning_rate": 0.00056,
|
| 56 |
+
"loss": 6.535,
|
| 57 |
"step": 70
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 0.03,
|
| 61 |
+
"learning_rate": 0.00064,
|
| 62 |
+
"loss": 6.3619,
|
| 63 |
"step": 80
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 0.03,
|
| 67 |
+
"learning_rate": 0.00072,
|
| 68 |
+
"loss": 6.285,
|
| 69 |
"step": 90
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 0.04,
|
| 73 |
"learning_rate": 0.0008,
|
| 74 |
+
"loss": 6.1199,
|
| 75 |
"step": 100
|
| 76 |
},
|
| 77 |
{
|
| 78 |
"epoch": 0.04,
|
| 79 |
+
"eval_accuracy": 0.15415359968673006,
|
| 80 |
+
"eval_loss": 6.0748748779296875,
|
| 81 |
+
"eval_runtime": 149.9041,
|
| 82 |
+
"eval_samples_per_second": 33.788,
|
| 83 |
+
"eval_steps_per_second": 4.229,
|
| 84 |
"step": 100
|
| 85 |
},
|
| 86 |
{
|
| 87 |
"epoch": 0.04,
|
| 88 |
+
"learning_rate": 0.0007999735731319962,
|
| 89 |
+
"loss": 6.0192,
|
| 90 |
"step": 110
|
| 91 |
},
|
| 92 |
{
|
| 93 |
"epoch": 0.04,
|
| 94 |
+
"learning_rate": 0.0007998942960198819,
|
| 95 |
+
"loss": 5.9528,
|
| 96 |
"step": 120
|
| 97 |
},
|
| 98 |
{
|
| 99 |
"epoch": 0.05,
|
| 100 |
+
"learning_rate": 0.0007997621791388858,
|
| 101 |
+
"loss": 5.8808,
|
| 102 |
"step": 130
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 0.05,
|
| 106 |
+
"learning_rate": 0.0007995772399461845,
|
| 107 |
+
"loss": 5.7862,
|
| 108 |
"step": 140
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 0.05,
|
| 112 |
+
"learning_rate": 0.0007993395028785968,
|
| 113 |
+
"loss": 5.7041,
|
| 114 |
"step": 150
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.06,
|
| 118 |
+
"learning_rate": 0.0007990489993493526,
|
| 119 |
+
"loss": 5.6365,
|
| 120 |
"step": 160
|
| 121 |
},
|
| 122 |
{
|
| 123 |
"epoch": 0.06,
|
| 124 |
+
"learning_rate": 0.0007987057677439444,
|
| 125 |
+
"loss": 5.5384,
|
| 126 |
"step": 170
|
| 127 |
},
|
| 128 |
{
|
| 129 |
"epoch": 0.06,
|
| 130 |
+
"learning_rate": 0.0007983098534150538,
|
| 131 |
+
"loss": 5.5325,
|
| 132 |
"step": 180
|
| 133 |
},
|
| 134 |
{
|
| 135 |
"epoch": 0.07,
|
| 136 |
+
"learning_rate": 0.0007978613086765592,
|
| 137 |
+
"loss": 5.4794,
|
| 138 |
"step": 190
|
| 139 |
},
|
| 140 |
{
|
| 141 |
"epoch": 0.07,
|
| 142 |
+
"learning_rate": 0.0007973601927966237,
|
| 143 |
+
"loss": 5.3869,
|
| 144 |
"step": 200
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"epoch": 0.07,
|
| 148 |
+
"eval_accuracy": 0.20318275703591465,
|
| 149 |
+
"eval_loss": 5.326748371124268,
|
| 150 |
+
"eval_runtime": 149.8598,
|
| 151 |
+
"eval_samples_per_second": 33.798,
|
| 152 |
+
"eval_steps_per_second": 4.231,
|
| 153 |
"step": 200
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 0.07,
|
| 157 |
+
"learning_rate": 0.0007968065719898634,
|
| 158 |
+
"loss": 5.3202,
|
| 159 |
"step": 210
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 0.08,
|
| 163 |
+
"learning_rate": 0.0007962005194085981,
|
| 164 |
+
"loss": 5.2673,
|
| 165 |
"step": 220
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 0.08,
|
| 169 |
+
"learning_rate": 0.0007955421151331857,
|
| 170 |
+
"loss": 5.2441,
|
| 171 |
"step": 230
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"epoch": 0.08,
|
| 175 |
+
"learning_rate": 0.0007948314461614408,
|
| 176 |
+
"loss": 5.1405,
|
| 177 |
"step": 240
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 0.09,
|
| 181 |
+
"learning_rate": 0.0007940686063971387,
|
| 182 |
+
"loss": 5.1529,
|
| 183 |
"step": 250
|
| 184 |
},
|
| 185 |
{
|
| 186 |
"epoch": 0.09,
|
| 187 |
+
"learning_rate": 0.0007932536966376081,
|
| 188 |
+
"loss": 5.1036,
|
| 189 |
"step": 260
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"epoch": 0.1,
|
| 193 |
+
"learning_rate": 0.0007923868245604124,
|
| 194 |
+
"loss": 4.9852,
|
| 195 |
"step": 270
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 0.1,
|
| 199 |
+
"learning_rate": 0.0007914681047091216,
|
| 200 |
+
"loss": 4.9747,
|
| 201 |
"step": 280
|
| 202 |
},
|
| 203 |
{
|
| 204 |
"epoch": 0.1,
|
| 205 |
+
"learning_rate": 0.0007904976584781766,
|
| 206 |
+
"loss": 4.9381,
|
| 207 |
"step": 290
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 0.11,
|
| 211 |
+
"learning_rate": 0.0007894756140968497,
|
| 212 |
+
"loss": 4.9187,
|
| 213 |
"step": 300
|
| 214 |
},
|
| 215 |
{
|
| 216 |
"epoch": 0.11,
|
| 217 |
+
"eval_accuracy": 0.23856663569010775,
|
| 218 |
+
"eval_loss": 4.856618404388428,
|
| 219 |
+
"eval_runtime": 149.2653,
|
| 220 |
+
"eval_samples_per_second": 33.933,
|
| 221 |
+
"eval_steps_per_second": 4.247,
|
| 222 |
"step": 300
|
| 223 |
},
|
| 224 |
{
|
| 225 |
"epoch": 0.11,
|
| 226 |
+
"learning_rate": 0.0007884021066123009,
|
| 227 |
+
"loss": 4.8608,
|
| 228 |
"step": 310
|
| 229 |
},
|
| 230 |
{
|
| 231 |
"epoch": 0.11,
|
| 232 |
+
"learning_rate": 0.0007872772778717331,
|
| 233 |
+
"loss": 4.8439,
|
| 234 |
"step": 320
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"epoch": 0.12,
|
| 238 |
+
"learning_rate": 0.0007861012765036494,
|
| 239 |
+
"loss": 4.7976,
|
| 240 |
"step": 330
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 0.12,
|
| 244 |
+
"learning_rate": 0.0007848742578982146,
|
| 245 |
+
"loss": 4.752,
|
| 246 |
"step": 340
|
| 247 |
},
|
| 248 |
{
|
| 249 |
"epoch": 0.12,
|
| 250 |
+
"learning_rate": 0.0007835963841867223,
|
| 251 |
+
"loss": 4.7569,
|
| 252 |
"step": 350
|
| 253 |
},
|
| 254 |
{
|
| 255 |
"epoch": 0.13,
|
| 256 |
+
"learning_rate": 0.0007822678242201718,
|
| 257 |
+
"loss": 4.698,
|
| 258 |
"step": 360
|
| 259 |
},
|
| 260 |
{
|
| 261 |
"epoch": 0.13,
|
| 262 |
+
"learning_rate": 0.0007808887535469578,
|
| 263 |
+
"loss": 4.6793,
|
| 264 |
"step": 370
|
| 265 |
},
|
| 266 |
{
|
| 267 |
"epoch": 0.13,
|
| 268 |
+
"learning_rate": 0.0007794593543896733,
|
| 269 |
+
"loss": 4.6234,
|
| 270 |
"step": 380
|
| 271 |
},
|
| 272 |
{
|
| 273 |
"epoch": 0.14,
|
| 274 |
+
"learning_rate": 0.0007779798156210327,
|
| 275 |
+
"loss": 4.6046,
|
| 276 |
"step": 390
|
| 277 |
},
|
| 278 |
{
|
| 279 |
"epoch": 0.14,
|
| 280 |
+
"learning_rate": 0.0007764503327389145,
|
| 281 |
+
"loss": 4.6185,
|
| 282 |
"step": 400
|
| 283 |
},
|
| 284 |
{
|
| 285 |
"epoch": 0.14,
|
| 286 |
+
"eval_accuracy": 0.2624355291325133,
|
| 287 |
+
"eval_loss": 4.553475379943848,
|
| 288 |
+
"eval_runtime": 149.5941,
|
| 289 |
+
"eval_samples_per_second": 33.858,
|
| 290 |
+
"eval_steps_per_second": 4.238,
|
| 291 |
"step": 400
|
| 292 |
},
|
| 293 |
{
|
| 294 |
"epoch": 0.14,
|
| 295 |
+
"learning_rate": 0.00077487110784053,
|
| 296 |
+
"loss": 4.551,
|
| 297 |
"step": 410
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 0.15,
|
| 301 |
+
"learning_rate": 0.0007732423495957192,
|
| 302 |
+
"loss": 4.5083,
|
| 303 |
"step": 420
|
| 304 |
},
|
| 305 |
{
|
| 306 |
"epoch": 0.15,
|
| 307 |
+
"learning_rate": 0.0007715642732193774,
|
| 308 |
+
"loss": 4.522,
|
| 309 |
"step": 430
|
| 310 |
},
|
| 311 |
{
|
| 312 |
"epoch": 0.16,
|
| 313 |
+
"learning_rate": 0.0007698371004430193,
|
| 314 |
+
"loss": 4.4942,
|
| 315 |
"step": 440
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"epoch": 0.16,
|
| 319 |
+
"learning_rate": 0.0007680610594854798,
|
| 320 |
+
"loss": 4.5164,
|
| 321 |
"step": 450
|
| 322 |
},
|
| 323 |
{
|
| 324 |
"epoch": 0.16,
|
| 325 |
+
"learning_rate": 0.0007662363850227587,
|
| 326 |
+
"loss": 4.4405,
|
| 327 |
"step": 460
|
| 328 |
},
|
| 329 |
{
|
| 330 |
"epoch": 0.17,
|
| 331 |
+
"learning_rate": 0.0007643633181570117,
|
| 332 |
+
"loss": 4.3987,
|
| 333 |
"step": 470
|
| 334 |
},
|
| 335 |
{
|
| 336 |
"epoch": 0.17,
|
| 337 |
+
"learning_rate": 0.000762442106384693,
|
| 338 |
+
"loss": 4.4089,
|
| 339 |
"step": 480
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 0.17,
|
| 343 |
+
"learning_rate": 0.0007604730035638523,
|
| 344 |
+
"loss": 4.3598,
|
| 345 |
"step": 490
|
| 346 |
},
|
| 347 |
{
|
| 348 |
"epoch": 0.18,
|
| 349 |
+
"learning_rate": 0.0007584562698805911,
|
| 350 |
+
"loss": 4.3509,
|
| 351 |
"step": 500
|
| 352 |
},
|
| 353 |
{
|
| 354 |
"epoch": 0.18,
|
| 355 |
+
"eval_accuracy": 0.2801221637037998,
|
| 356 |
+
"eval_loss": 4.338791847229004,
|
| 357 |
+
"eval_runtime": 148.9964,
|
| 358 |
+
"eval_samples_per_second": 33.994,
|
| 359 |
+
"eval_steps_per_second": 4.255,
|
| 360 |
"step": 500
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 0.18,
|
| 364 |
+
"learning_rate": 0.0007563921718146838,
|
| 365 |
+
"loss": 4.3866,
|
| 366 |
"step": 510
|
| 367 |
},
|
| 368 |
{
|
| 369 |
"epoch": 0.18,
|
| 370 |
+
"learning_rate": 0.0007542809821043658,
|
| 371 |
+
"loss": 4.3586,
|
| 372 |
"step": 520
|
| 373 |
},
|
| 374 |
{
|
| 375 |
"epoch": 0.19,
|
| 376 |
+
"learning_rate": 0.0007521229797102965,
|
| 377 |
+
"loss": 4.319,
|
| 378 |
"step": 530
|
| 379 |
},
|
| 380 |
{
|
| 381 |
"epoch": 0.19,
|
| 382 |
+
"learning_rate": 0.0007499184497786977,
|
| 383 |
+
"loss": 4.3143,
|
| 384 |
"step": 540
|
| 385 |
},
|
| 386 |
{
|
| 387 |
"epoch": 0.19,
|
| 388 |
+
"learning_rate": 0.0007476676836036771,
|
| 389 |
+
"loss": 4.2326,
|
| 390 |
"step": 550
|
| 391 |
},
|
| 392 |
{
|
| 393 |
"epoch": 0.2,
|
| 394 |
+
"learning_rate": 0.0007453709785887376,
|
| 395 |
+
"loss": 4.2689,
|
| 396 |
"step": 560
|
| 397 |
},
|
| 398 |
{
|
| 399 |
"epoch": 0.2,
|
| 400 |
+
"learning_rate": 0.0007430286382074807,
|
| 401 |
+
"loss": 4.2383,
|
| 402 |
"step": 570
|
| 403 |
},
|
| 404 |
{
|
| 405 |
"epoch": 0.2,
|
| 406 |
+
"learning_rate": 0.0007406409719635068,
|
| 407 |
+
"loss": 4.232,
|
| 408 |
"step": 580
|
| 409 |
},
|
| 410 |
{
|
| 411 |
"epoch": 0.21,
|
| 412 |
+
"learning_rate": 0.0007382082953495193,
|
| 413 |
+
"loss": 4.1941,
|
| 414 |
"step": 590
|
| 415 |
},
|
| 416 |
{
|
| 417 |
"epoch": 0.21,
|
| 418 |
+
"learning_rate": 0.0007357309298056369,
|
| 419 |
+
"loss": 4.1666,
|
| 420 |
"step": 600
|
| 421 |
},
|
| 422 |
{
|
| 423 |
"epoch": 0.21,
|
| 424 |
+
"eval_accuracy": 0.2955689374718788,
|
| 425 |
+
"eval_loss": 4.16923713684082,
|
| 426 |
+
"eval_runtime": 148.9107,
|
| 427 |
+
"eval_samples_per_second": 34.014,
|
| 428 |
+
"eval_steps_per_second": 4.258,
|
| 429 |
"step": 600
|
| 430 |
},
|
| 431 |
{
|
| 432 |
"epoch": 0.22,
|
| 433 |
+
"learning_rate": 0.0007332092026769209,
|
| 434 |
+
"loss": 4.1266,
|
| 435 |
"step": 610
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 0.22,
|
| 439 |
+
"learning_rate": 0.0007306434471701209,
|
| 440 |
+
"loss": 4.1373,
|
| 441 |
"step": 620
|
| 442 |
},
|
| 443 |
{
|
| 444 |
"epoch": 0.22,
|
| 445 |
+
"learning_rate": 0.0007280340023096477,
|
| 446 |
+
"loss": 4.1767,
|
| 447 |
"step": 630
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 0.23,
|
| 451 |
+
"learning_rate": 0.0007253812128927756,
|
| 452 |
+
"loss": 4.139,
|
| 453 |
"step": 640
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 0.23,
|
| 457 |
+
"learning_rate": 0.0007226854294440834,
|
| 458 |
+
"loss": 4.0591,
|
| 459 |
"step": 650
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 0.23,
|
| 463 |
+
"learning_rate": 0.0007199470081691381,
|
| 464 |
+
"loss": 4.1488,
|
| 465 |
"step": 660
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 0.24,
|
| 469 |
+
"learning_rate": 0.0007171663109074274,
|
| 470 |
+
"loss": 4.1125,
|
| 471 |
"step": 670
|
| 472 |
},
|
| 473 |
{
|
| 474 |
"epoch": 0.24,
|
| 475 |
+
"learning_rate": 0.0007143437050845489,
|
| 476 |
+
"loss": 4.1009,
|
| 477 |
"step": 680
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 0.24,
|
| 481 |
+
"learning_rate": 0.0007114795636636599,
|
| 482 |
+
"loss": 4.085,
|
| 483 |
"step": 690
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 0.25,
|
| 487 |
+
"learning_rate": 0.000708574265096197,
|
| 488 |
+
"loss": 4.0456,
|
| 489 |
"step": 700
|
| 490 |
},
|
| 491 |
{
|
| 492 |
"epoch": 0.25,
|
| 493 |
+
"eval_accuracy": 0.3088623661815066,
|
| 494 |
+
"eval_loss": 4.03993558883667,
|
| 495 |
+
"eval_runtime": 148.8369,
|
| 496 |
+
"eval_samples_per_second": 34.031,
|
| 497 |
+
"eval_steps_per_second": 4.26,
|
| 498 |
"step": 700
|
| 499 |
},
|
| 500 |
{
|
| 501 |
"epoch": 0.25,
|
| 502 |
+
"learning_rate": 0.0007056281932718689,
|
| 503 |
+
"loss": 4.0732,
|
| 504 |
"step": 710
|
| 505 |
},
|
| 506 |
{
|
| 507 |
"epoch": 0.25,
|
| 508 |
+
"learning_rate": 0.0007026417374679316,
|
| 509 |
+
"loss": 4.0439,
|
| 510 |
"step": 720
|
| 511 |
},
|
| 512 |
{
|
| 513 |
"epoch": 0.26,
|
| 514 |
+
"learning_rate": 0.000699615292297752,
|
| 515 |
+
"loss": 4.0528,
|
| 516 |
"step": 730
|
| 517 |
},
|
| 518 |
{
|
| 519 |
"epoch": 0.26,
|
| 520 |
+
"learning_rate": 0.0006965492576586652,
|
| 521 |
+
"loss": 4.05,
|
| 522 |
"step": 740
|
| 523 |
},
|
| 524 |
{
|
| 525 |
"epoch": 0.26,
|
| 526 |
+
"learning_rate": 0.0006934440386791345,
|
| 527 |
+
"loss": 3.9947,
|
| 528 |
"step": 750
|
| 529 |
},
|
| 530 |
{
|
| 531 |
"epoch": 0.27,
|
| 532 |
+
"learning_rate": 0.0006903000456652207,
|
| 533 |
+
"loss": 4.002,
|
| 534 |
"step": 760
|
| 535 |
},
|
| 536 |
{
|
| 537 |
"epoch": 0.27,
|
| 538 |
+
"learning_rate": 0.0006871176940463655,
|
| 539 |
+
"loss": 3.937,
|
| 540 |
"step": 770
|
| 541 |
},
|
| 542 |
{
|
| 543 |
"epoch": 0.28,
|
| 544 |
+
"learning_rate": 0.0006838974043204999,
|
| 545 |
+
"loss": 3.949,
|
| 546 |
"step": 780
|
| 547 |
},
|
| 548 |
{
|
| 549 |
"epoch": 0.28,
|
| 550 |
+
"learning_rate": 0.0006806396019984811,
|
| 551 |
+
"loss": 3.9419,
|
| 552 |
"step": 790
|
| 553 |
},
|
| 554 |
{
|
| 555 |
"epoch": 0.28,
|
| 556 |
+
"learning_rate": 0.0006773447175478696,
|
| 557 |
+
"loss": 3.9273,
|
| 558 |
"step": 800
|
| 559 |
},
|
| 560 |
{
|
| 561 |
"epoch": 0.28,
|
| 562 |
+
"eval_accuracy": 0.31934504591266155,
|
| 563 |
+
"eval_loss": 3.9317612648010254,
|
| 564 |
+
"eval_runtime": 150.5837,
|
| 565 |
+
"eval_samples_per_second": 33.636,
|
| 566 |
+
"eval_steps_per_second": 4.21,
|
| 567 |
"step": 800
|
| 568 |
},
|
| 569 |
{
|
| 570 |
"epoch": 0.29,
|
| 571 |
+
"learning_rate": 0.000674013186336047,
|
| 572 |
+
"loss": 3.9558,
|
| 573 |
"step": 810
|
| 574 |
},
|
| 575 |
{
|
| 576 |
"epoch": 0.29,
|
| 577 |
+
"learning_rate": 0.0006706454485726915,
|
| 578 |
+
"loss": 3.9083,
|
| 579 |
"step": 820
|
| 580 |
},
|
| 581 |
{
|
| 582 |
"epoch": 0.29,
|
| 583 |
+
"learning_rate": 0.0006672419492516099,
|
| 584 |
+
"loss": 3.9169,
|
| 585 |
"step": 830
|
| 586 |
},
|
| 587 |
{
|
| 588 |
"epoch": 0.3,
|
| 589 |
+
"learning_rate": 0.0006638031380919385,
|
| 590 |
+
"loss": 3.9215,
|
| 591 |
"step": 840
|
| 592 |
},
|
| 593 |
{
|
| 594 |
"epoch": 0.3,
|
| 595 |
+
"learning_rate": 0.0006603294694787206,
|
| 596 |
+
"loss": 3.9422,
|
| 597 |
"step": 850
|
| 598 |
},
|
| 599 |
{
|
| 600 |
"epoch": 0.3,
|
| 601 |
+
"learning_rate": 0.0006568214024028656,
|
| 602 |
+
"loss": 3.9031,
|
| 603 |
"step": 860
|
| 604 |
},
|
| 605 |
{
|
| 606 |
"epoch": 0.31,
|
| 607 |
+
"learning_rate": 0.0006532794004005016,
|
| 608 |
+
"loss": 3.8931,
|
| 609 |
"step": 870
|
| 610 |
},
|
| 611 |
{
|
| 612 |
"epoch": 0.31,
|
| 613 |
+
"learning_rate": 0.0006497039314917254,
|
| 614 |
+
"loss": 3.871,
|
| 615 |
"step": 880
|
| 616 |
},
|
| 617 |
{
|
| 618 |
"epoch": 0.31,
|
| 619 |
+
"learning_rate": 0.0006460954681187614,
|
| 620 |
+
"loss": 3.878,
|
| 621 |
"step": 890
|
| 622 |
},
|
| 623 |
{
|
| 624 |
"epoch": 0.32,
|
| 625 |
+
"learning_rate": 0.0006424544870835359,
|
| 626 |
+
"loss": 3.8447,
|
| 627 |
"step": 900
|
| 628 |
},
|
| 629 |
{
|
| 630 |
"epoch": 0.32,
|
| 631 |
+
"eval_accuracy": 0.3326595971954238,
|
| 632 |
+
"eval_loss": 3.817286968231201,
|
| 633 |
+
"eval_runtime": 151.9107,
|
| 634 |
+
"eval_samples_per_second": 33.342,
|
| 635 |
+
"eval_steps_per_second": 4.174,
|
| 636 |
"step": 900
|
| 637 |
},
|
| 638 |
{
|
| 639 |
"epoch": 0.32,
|
| 640 |
+
"learning_rate": 0.0006387814694846751,
|
| 641 |
+
"loss": 3.7965,
|
| 642 |
"step": 910
|
| 643 |
},
|
| 644 |
{
|
| 645 |
"epoch": 0.32,
|
| 646 |
+
"learning_rate": 0.0006350769006539354,
|
| 647 |
+
"loss": 3.7753,
|
| 648 |
"step": 920
|
| 649 |
},
|
| 650 |
{
|
| 651 |
"epoch": 0.33,
|
| 652 |
+
"learning_rate": 0.000631341270092074,
|
| 653 |
+
"loss": 3.7734,
|
| 654 |
"step": 930
|
| 655 |
},
|
| 656 |
{
|
| 657 |
"epoch": 0.33,
|
| 658 |
+
"learning_rate": 0.00062757507140417,
|
| 659 |
+
"loss": 3.8001,
|
| 660 |
"step": 940
|
| 661 |
},
|
| 662 |
{
|
| 663 |
"epoch": 0.34,
|
| 664 |
+
"learning_rate": 0.0006237788022344014,
|
| 665 |
+
"loss": 3.7775,
|
| 666 |
"step": 950
|
| 667 |
},
|
| 668 |
{
|
| 669 |
"epoch": 0.34,
|
| 670 |
+
"learning_rate": 0.0006199529642002892,
|
| 671 |
+
"loss": 3.7659,
|
| 672 |
"step": 960
|
| 673 |
},
|
| 674 |
{
|
| 675 |
"epoch": 0.34,
|
| 676 |
+
"learning_rate": 0.0006160980628264175,
|
| 677 |
+
"loss": 3.7701,
|
| 678 |
"step": 970
|
| 679 |
},
|
| 680 |
{
|
| 681 |
"epoch": 0.35,
|
| 682 |
+
"learning_rate": 0.0006122146074776347,
|
| 683 |
+
"loss": 3.7496,
|
| 684 |
"step": 980
|
| 685 |
},
|
| 686 |
{
|
| 687 |
"epoch": 0.35,
|
| 688 |
+
"learning_rate": 0.0006083031112917506,
|
| 689 |
+
"loss": 3.7569,
|
| 690 |
"step": 990
|
| 691 |
},
|
| 692 |
{
|
| 693 |
"epoch": 0.35,
|
| 694 |
+
"learning_rate": 0.0006043640911117322,
|
| 695 |
+
"loss": 3.7143,
|
| 696 |
"step": 1000
|
| 697 |
},
|
| 698 |
{
|
| 699 |
"epoch": 0.35,
|
| 700 |
+
"eval_accuracy": 0.3461449616152692,
|
| 701 |
+
"eval_loss": 3.7108187675476074,
|
| 702 |
+
"eval_runtime": 150.717,
|
| 703 |
+
"eval_samples_per_second": 33.606,
|
| 704 |
+
"eval_steps_per_second": 4.207,
|
| 705 |
"step": 1000
|
| 706 |
},
|
| 707 |
{
|
| 708 |
"epoch": 0.36,
|
| 709 |
+
"learning_rate": 0.0006003980674174113,
|
| 710 |
+
"loss": 3.727,
|
| 711 |
"step": 1010
|
| 712 |
},
|
| 713 |
{
|
| 714 |
"epoch": 0.36,
|
| 715 |
+
"learning_rate": 0.0005964055642567111,
|
| 716 |
+
"loss": 3.7216,
|
| 717 |
"step": 1020
|
| 718 |
},
|
| 719 |
{
|
| 720 |
"epoch": 0.36,
|
| 721 |
+
"learning_rate": 0.0005923871091764019,
|
| 722 |
+
"loss": 3.6425,
|
| 723 |
"step": 1030
|
| 724 |
},
|
| 725 |
{
|
| 726 |
"epoch": 0.37,
|
| 727 |
+
"learning_rate": 0.0005883432331523935,
|
| 728 |
+
"loss": 3.656,
|
| 729 |
"step": 1040
|
| 730 |
},
|
| 731 |
{
|
| 732 |
"epoch": 0.37,
|
| 733 |
+
"learning_rate": 0.0005842744705195756,
|
| 734 |
+
"loss": 3.6711,
|
| 735 |
"step": 1050
|
| 736 |
},
|
| 737 |
{
|
| 738 |
"epoch": 0.37,
|
| 739 |
+
"learning_rate": 0.0005801813589012133,
|
| 740 |
+
"loss": 3.6739,
|
| 741 |
"step": 1060
|
| 742 |
},
|
| 743 |
{
|
| 744 |
"epoch": 0.38,
|
| 745 |
+
"learning_rate": 0.0005760644391379089,
|
| 746 |
+
"loss": 3.6481,
|
| 747 |
"step": 1070
|
| 748 |
},
|
| 749 |
{
|
| 750 |
"epoch": 0.38,
|
| 751 |
+
"learning_rate": 0.0005719242552161383,
|
| 752 |
+
"loss": 3.6327,
|
| 753 |
"step": 1080
|
| 754 |
},
|
| 755 |
{
|
| 756 |
"epoch": 0.38,
|
| 757 |
+
"learning_rate": 0.0005677613541963716,
|
| 758 |
+
"loss": 3.6286,
|
| 759 |
"step": 1090
|
| 760 |
},
|
| 761 |
{
|
| 762 |
"epoch": 0.39,
|
| 763 |
+
"learning_rate": 0.0005635762861407874,
|
| 764 |
+
"loss": 3.6485,
|
| 765 |
"step": 1100
|
| 766 |
},
|
| 767 |
{
|
| 768 |
"epoch": 0.39,
|
| 769 |
+
"eval_accuracy": 0.3589528604931205,
|
| 770 |
+
"eval_loss": 3.6115522384643555,
|
| 771 |
+
"eval_runtime": 151.483,
|
| 772 |
+
"eval_samples_per_second": 33.436,
|
| 773 |
+
"eval_steps_per_second": 4.185,
|
| 774 |
"step": 1100
|
| 775 |
},
|
| 776 |
{
|
| 777 |
"epoch": 0.39,
|
| 778 |
+
"learning_rate": 0.0005593696040405915,
|
| 779 |
+
"loss": 3.6201,
|
| 780 |
"step": 1110
|
| 781 |
},
|
| 782 |
{
|
| 783 |
"epoch": 0.4,
|
| 784 |
+
"learning_rate": 0.0005551418637429465,
|
| 785 |
+
"loss": 3.5593,
|
| 786 |
"step": 1120
|
| 787 |
},
|
| 788 |
{
|
| 789 |
"epoch": 0.4,
|
| 790 |
+
"learning_rate": 0.0005508936238775265,
|
| 791 |
+
"loss": 3.6036,
|
| 792 |
"step": 1130
|
| 793 |
},
|
| 794 |
{
|
| 795 |
"epoch": 0.4,
|
| 796 |
+
"learning_rate": 0.0005466254457827025,
|
| 797 |
+
"loss": 3.6029,
|
| 798 |
"step": 1140
|
| 799 |
},
|
| 800 |
{
|
| 801 |
"epoch": 0.41,
|
| 802 |
+
"learning_rate": 0.0005423378934313702,
|
| 803 |
+
"loss": 3.585,
|
| 804 |
"step": 1150
|
| 805 |
},
|
| 806 |
{
|
| 807 |
"epoch": 0.41,
|
| 808 |
+
"learning_rate": 0.0005380315333564296,
|
| 809 |
+
"loss": 3.5505,
|
| 810 |
"step": 1160
|
| 811 |
},
|
| 812 |
{
|
| 813 |
"epoch": 0.41,
|
| 814 |
+
"learning_rate": 0.0005337069345759272,
|
| 815 |
+
"loss": 3.5358,
|
| 816 |
"step": 1170
|
| 817 |
},
|
| 818 |
{
|
| 819 |
"epoch": 0.42,
|
| 820 |
+
"learning_rate": 0.0005293646685178686,
|
| 821 |
+
"loss": 3.5578,
|
| 822 |
"step": 1180
|
| 823 |
},
|
| 824 |
{
|
| 825 |
"epoch": 0.42,
|
| 826 |
+
"learning_rate": 0.0005250053089447138,
|
| 827 |
+
"loss": 3.5917,
|
| 828 |
"step": 1190
|
| 829 |
},
|
| 830 |
{
|
| 831 |
"epoch": 0.42,
|
| 832 |
+
"learning_rate": 0.0005206294318775628,
|
| 833 |
+
"loss": 3.5171,
|
| 834 |
"step": 1200
|
| 835 |
},
|
| 836 |
{
|
| 837 |
"epoch": 0.42,
|
| 838 |
+
"eval_accuracy": 0.36927514369860115,
|
| 839 |
+
"eval_loss": 3.530304431915283,
|
| 840 |
+
"eval_runtime": 151.4072,
|
| 841 |
+
"eval_samples_per_second": 33.453,
|
| 842 |
+
"eval_steps_per_second": 4.187,
|
| 843 |
"step": 1200
|
| 844 |
},
|
| 845 |
{
|
| 846 |
"epoch": 0.43,
|
| 847 |
+
"learning_rate": 0.0005162376155200437,
|
| 848 |
+
"loss": 3.5322,
|
| 849 |
"step": 1210
|
| 850 |
},
|
| 851 |
{
|
| 852 |
"epoch": 0.43,
|
| 853 |
+
"learning_rate": 0.0005118304401819125,
|
| 854 |
+
"loss": 3.5639,
|
| 855 |
"step": 1220
|
| 856 |
},
|
| 857 |
{
|
| 858 |
"epoch": 0.43,
|
| 859 |
+
"learning_rate": 0.0005074084882023739,
|
| 860 |
+
"loss": 3.5472,
|
| 861 |
"step": 1230
|
| 862 |
},
|
| 863 |
{
|
| 864 |
"epoch": 0.44,
|
| 865 |
+
"learning_rate": 0.0005029723438731346,
|
| 866 |
+
"loss": 3.4967,
|
| 867 |
"step": 1240
|
| 868 |
},
|
| 869 |
{
|
| 870 |
"epoch": 0.44,
|
| 871 |
+
"learning_rate": 0.0004985225933611971,
|
| 872 |
+
"loss": 3.466,
|
| 873 |
"step": 1250
|
| 874 |
},
|
| 875 |
{
|
| 876 |
"epoch": 0.44,
|
| 877 |
+
"learning_rate": 0.000494059824631409,
|
| 878 |
+
"loss": 3.4608,
|
| 879 |
"step": 1260
|
| 880 |
},
|
| 881 |
{
|
| 882 |
"epoch": 0.45,
|
| 883 |
+
"learning_rate": 0.0004895846273687709,
|
| 884 |
+
"loss": 3.5004,
|
| 885 |
"step": 1270
|
| 886 |
},
|
| 887 |
{
|
| 888 |
"epoch": 0.45,
|
| 889 |
+
"learning_rate": 0.0004850975929005197,
|
| 890 |
+
"loss": 3.4747,
|
| 891 |
"step": 1280
|
| 892 |
},
|
| 893 |
{
|
| 894 |
"epoch": 0.46,
|
| 895 |
+
"learning_rate": 0.00048059931411799335,
|
| 896 |
+
"loss": 3.5048,
|
| 897 |
"step": 1290
|
| 898 |
},
|
| 899 |
{
|
| 900 |
"epoch": 0.46,
|
| 901 |
+
"learning_rate": 0.00047609038539829,
|
| 902 |
+
"loss": 3.4464,
|
| 903 |
"step": 1300
|
| 904 |
},
|
| 905 |
{
|
| 906 |
"epoch": 0.46,
|
| 907 |
+
"eval_accuracy": 0.3779672272186056,
|
| 908 |
+
"eval_loss": 3.455420970916748,
|
| 909 |
+
"eval_runtime": 151.2649,
|
| 910 |
+
"eval_samples_per_second": 33.484,
|
| 911 |
+
"eval_steps_per_second": 4.191,
|
| 912 |
"step": 1300
|
| 913 |
},
|
| 914 |
{
|
| 915 |
"epoch": 0.46,
|
| 916 |
+
"learning_rate": 0.0004715714025257304,
|
| 917 |
+
"loss": 3.4953,
|
| 918 |
"step": 1310
|
| 919 |
},
|
| 920 |
{
|
| 921 |
"epoch": 0.47,
|
| 922 |
+
"learning_rate": 0.00046704296261313393,
|
| 923 |
+
"loss": 3.471,
|
| 924 |
"step": 1320
|
| 925 |
},
|
| 926 |
{
|
| 927 |
"epoch": 0.47,
|
| 928 |
+
"learning_rate": 0.0004625056640229197,
|
| 929 |
+
"loss": 3.4471,
|
| 930 |
"step": 1330
|
| 931 |
},
|
| 932 |
{
|
| 933 |
"epoch": 0.47,
|
| 934 |
+
"learning_rate": 0.0004579601062880422,
|
| 935 |
+
"loss": 3.4493,
|
| 936 |
"step": 1340
|
| 937 |
},
|
| 938 |
{
|
| 939 |
"epoch": 0.48,
|
| 940 |
+
"learning_rate": 0.00045340689003277285,
|
| 941 |
+
"loss": 3.4145,
|
| 942 |
"step": 1350
|
| 943 |
},
|
| 944 |
{
|
| 945 |
"epoch": 0.48,
|
| 946 |
+
"learning_rate": 0.0004488466168933368,
|
| 947 |
+
"loss": 3.4739,
|
| 948 |
"step": 1360
|
| 949 |
},
|
| 950 |
{
|
| 951 |
"epoch": 0.48,
|
| 952 |
+
"learning_rate": 0.00044427988943841534,
|
| 953 |
+
"loss": 3.3819,
|
| 954 |
"step": 1370
|
| 955 |
},
|
| 956 |
{
|
| 957 |
"epoch": 0.49,
|
| 958 |
+
"learning_rate": 0.0004397073110895268,
|
| 959 |
+
"loss": 3.3975,
|
| 960 |
"step": 1380
|
| 961 |
},
|
| 962 |
{
|
| 963 |
"epoch": 0.49,
|
| 964 |
+
"learning_rate": 0.0004351294860412936,
|
| 965 |
+
"loss": 3.4112,
|
| 966 |
"step": 1390
|
| 967 |
},
|
| 968 |
{
|
| 969 |
"epoch": 0.49,
|
| 970 |
+
"learning_rate": 0.000430547019181607,
|
| 971 |
+
"loss": 3.3955,
|
| 972 |
"step": 1400
|
| 973 |
},
|
| 974 |
{
|
| 975 |
"epoch": 0.49,
|
| 976 |
+
"eval_accuracy": 0.38511794160042556,
|
| 977 |
+
"eval_loss": 3.3999252319335938,
|
| 978 |
+
"eval_runtime": 150.5869,
|
| 979 |
+
"eval_samples_per_second": 33.635,
|
| 980 |
+
"eval_steps_per_second": 4.21,
|
| 981 |
"step": 1400
|
| 982 |
},
|
| 983 |
{
|
| 984 |
"epoch": 0.5,
|
| 985 |
+
"learning_rate": 0.00042596051601170143,
|
| 986 |
+
"loss": 3.3769,
|
| 987 |
"step": 1410
|
| 988 |
},
|
| 989 |
{
|
| 990 |
"epoch": 0.5,
|
| 991 |
+
"learning_rate": 0.00042137058256614605,
|
| 992 |
+
"loss": 3.389,
|
| 993 |
"step": 1420
|
| 994 |
},
|
| 995 |
{
|
| 996 |
"epoch": 0.5,
|
| 997 |
+
"learning_rate": 0.00041677782533276747,
|
| 998 |
+
"loss": 3.3465,
|
| 999 |
"step": 1430
|
| 1000 |
},
|
| 1001 |
{
|
| 1002 |
"epoch": 0.51,
|
| 1003 |
+
"learning_rate": 0.00041218285117251163,
|
| 1004 |
+
"loss": 3.3847,
|
| 1005 |
"step": 1440
|
| 1006 |
},
|
| 1007 |
{
|
| 1008 |
"epoch": 0.51,
|
| 1009 |
+
"learning_rate": 0.0004075862672392566,
|
| 1010 |
+
"loss": 3.3683,
|
| 1011 |
"step": 1450
|
| 1012 |
},
|
| 1013 |
{
|
| 1014 |
"epoch": 0.52,
|
| 1015 |
+
"learning_rate": 0.0004029886808995867,
|
| 1016 |
+
"loss": 3.3386,
|
| 1017 |
"step": 1460
|
| 1018 |
},
|
| 1019 |
{
|
| 1020 |
"epoch": 0.52,
|
| 1021 |
+
"learning_rate": 0.00039839069965253864,
|
| 1022 |
+
"loss": 3.3675,
|
| 1023 |
"step": 1470
|
| 1024 |
},
|
| 1025 |
{
|
| 1026 |
"epoch": 0.52,
|
| 1027 |
+
"learning_rate": 0.0003937929310493297,
|
| 1028 |
+
"loss": 3.3393,
|
| 1029 |
"step": 1480
|
| 1030 |
},
|
| 1031 |
{
|
| 1032 |
"epoch": 0.53,
|
| 1033 |
+
"learning_rate": 0.0003891959826130802,
|
| 1034 |
+
"loss": 3.4105,
|
| 1035 |
"step": 1490
|
| 1036 |
},
|
| 1037 |
{
|
| 1038 |
"epoch": 0.53,
|
| 1039 |
+
"learning_rate": 0.0003846004617585376,
|
| 1040 |
+
"loss": 3.3551,
|
| 1041 |
"step": 1500
|
| 1042 |
},
|
| 1043 |
{
|
| 1044 |
"epoch": 0.53,
|
| 1045 |
+
"eval_accuracy": 0.39192461845543836,
|
| 1046 |
+
"eval_loss": 3.3431735038757324,
|
| 1047 |
+
"eval_runtime": 150.786,
|
| 1048 |
+
"eval_samples_per_second": 33.591,
|
| 1049 |
+
"eval_steps_per_second": 4.205,
|
| 1050 |
"step": 1500
|
| 1051 |
},
|
| 1052 |
{
|
| 1053 |
"epoch": 0.53,
|
| 1054 |
+
"learning_rate": 0.00038000697571181723,
|
| 1055 |
+
"loss": 3.3163,
|
| 1056 |
"step": 1510
|
| 1057 |
},
|
| 1058 |
{
|
| 1059 |
"epoch": 0.54,
|
| 1060 |
+
"learning_rate": 0.00037541613143016596,
|
| 1061 |
+
"loss": 3.2978,
|
| 1062 |
"step": 1520
|
| 1063 |
},
|
| 1064 |
{
|
| 1065 |
"epoch": 0.54,
|
| 1066 |
+
"learning_rate": 0.00037082853552176324,
|
| 1067 |
+
"loss": 3.3012,
|
| 1068 |
"step": 1530
|
| 1069 |
},
|
| 1070 |
{
|
| 1071 |
"epoch": 0.54,
|
| 1072 |
+
"learning_rate": 0.0003662447941655669,
|
| 1073 |
+
"loss": 3.3617,
|
| 1074 |
"step": 1540
|
| 1075 |
},
|
| 1076 |
{
|
| 1077 |
"epoch": 0.55,
|
| 1078 |
+
"learning_rate": 0.00036166551303121566,
|
| 1079 |
+
"loss": 3.2746,
|
| 1080 |
"step": 1550
|
| 1081 |
},
|
| 1082 |
{
|
| 1083 |
"epoch": 0.55,
|
| 1084 |
+
"learning_rate": 0.00035709129719900003,
|
| 1085 |
+
"loss": 3.312,
|
| 1086 |
"step": 1560
|
| 1087 |
},
|
| 1088 |
{
|
| 1089 |
"epoch": 0.55,
|
| 1090 |
+
"learning_rate": 0.0003525227510799099,
|
| 1091 |
+
"loss": 3.3274,
|
| 1092 |
"step": 1570
|
| 1093 |
},
|
| 1094 |
{
|
| 1095 |
"epoch": 0.56,
|
| 1096 |
+
"learning_rate": 0.0003479604783357719,
|
| 1097 |
+
"loss": 3.2888,
|
| 1098 |
"step": 1580
|
| 1099 |
},
|
| 1100 |
{
|
| 1101 |
"epoch": 0.56,
|
| 1102 |
+
"learning_rate": 0.0003434050817994838,
|
| 1103 |
+
"loss": 3.3067,
|
| 1104 |
"step": 1590
|
| 1105 |
},
|
| 1106 |
{
|
| 1107 |
"epoch": 0.56,
|
| 1108 |
+
"learning_rate": 0.00033885716339536047,
|
| 1109 |
+
"loss": 3.2787,
|
| 1110 |
"step": 1600
|
| 1111 |
},
|
| 1112 |
{
|
| 1113 |
"epoch": 0.56,
|
| 1114 |
+
"eval_accuracy": 0.39735948545797645,
|
| 1115 |
+
"eval_loss": 3.2980780601501465,
|
| 1116 |
+
"eval_runtime": 151.955,
|
| 1117 |
+
"eval_samples_per_second": 33.332,
|
| 1118 |
+
"eval_steps_per_second": 4.172,
|
| 1119 |
"step": 1600
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
"epoch": 0.57,
|
| 1123 |
+
"learning_rate": 0.00033431732405959886,
|
| 1124 |
+
"loss": 3.3245,
|
| 1125 |
"step": 1610
|
| 1126 |
},
|
| 1127 |
{
|
| 1128 |
"epoch": 0.57,
|
| 1129 |
+
"learning_rate": 0.0003297861636608732,
|
| 1130 |
+
"loss": 3.328,
|
| 1131 |
"step": 1620
|
| 1132 |
},
|
| 1133 |
{
|
| 1134 |
"epoch": 0.58,
|
| 1135 |
+
"learning_rate": 0.00032526428092107256,
|
| 1136 |
+
"loss": 3.2773,
|
| 1137 |
"step": 1630
|
| 1138 |
},
|
| 1139 |
{
|
| 1140 |
"epoch": 0.58,
|
| 1141 |
+
"learning_rate": 0.0003207522733361881,
|
| 1142 |
+
"loss": 3.2792,
|
| 1143 |
"step": 1640
|
| 1144 |
},
|
| 1145 |
{
|
| 1146 |
"epoch": 0.58,
|
| 1147 |
+
"learning_rate": 0.00031625073709736444,
|
| 1148 |
+
"loss": 3.2355,
|
| 1149 |
"step": 1650
|
| 1150 |
},
|
| 1151 |
{
|
| 1152 |
"epoch": 0.59,
|
| 1153 |
+
"learning_rate": 0.00031176026701212125,
|
| 1154 |
+
"loss": 3.2635,
|
| 1155 |
"step": 1660
|
| 1156 |
},
|
| 1157 |
{
|
| 1158 |
"epoch": 0.59,
|
| 1159 |
+
"learning_rate": 0.00030728145642576,
|
| 1160 |
+
"loss": 3.226,
|
| 1161 |
"step": 1670
|
| 1162 |
},
|
| 1163 |
{
|
| 1164 |
"epoch": 0.59,
|
| 1165 |
+
"learning_rate": 0.0003028148971429614,
|
| 1166 |
+
"loss": 3.2433,
|
| 1167 |
"step": 1680
|
| 1168 |
},
|
| 1169 |
{
|
| 1170 |
"epoch": 0.6,
|
| 1171 |
+
"learning_rate": 0.00029836117934958843,
|
| 1172 |
+
"loss": 3.2282,
|
| 1173 |
"step": 1690
|
| 1174 |
},
|
| 1175 |
{
|
| 1176 |
"epoch": 0.6,
|
| 1177 |
+
"learning_rate": 0.00029392089153470243,
|
| 1178 |
+
"loss": 3.2705,
|
| 1179 |
"step": 1700
|
| 1180 |
},
|
| 1181 |
{
|
| 1182 |
"epoch": 0.6,
|
| 1183 |
+
"eval_accuracy": 0.4022830704505329,
|
| 1184 |
+
"eval_loss": 3.2566046714782715,
|
| 1185 |
+
"eval_runtime": 151.1757,
|
| 1186 |
+
"eval_samples_per_second": 33.504,
|
| 1187 |
+
"eval_steps_per_second": 4.194,
|
| 1188 |
"step": 1700
|
| 1189 |
},
|
| 1190 |
{
|
| 1191 |
"epoch": 0.6,
|
| 1192 |
+
"learning_rate": 0.0002894946204128031,
|
| 1193 |
+
"loss": 3.2523,
|
| 1194 |
"step": 1710
|
| 1195 |
},
|
| 1196 |
{
|
| 1197 |
"epoch": 0.61,
|
| 1198 |
+
"learning_rate": 0.00028508295084630423,
|
| 1199 |
+
"loss": 3.2703,
|
| 1200 |
"step": 1720
|
| 1201 |
},
|
| 1202 |
{
|
| 1203 |
"epoch": 0.61,
|
| 1204 |
+
"learning_rate": 0.0002806864657682521,
|
| 1205 |
+
"loss": 3.2855,
|
| 1206 |
"step": 1730
|
| 1207 |
},
|
| 1208 |
{
|
| 1209 |
"epoch": 0.61,
|
| 1210 |
+
"learning_rate": 0.0002763057461053008,
|
| 1211 |
+
"loss": 3.2752,
|
| 1212 |
"step": 1740
|
| 1213 |
},
|
| 1214 |
{
|
| 1215 |
"epoch": 0.62,
|
| 1216 |
+
"learning_rate": 0.00027194137070095224,
|
| 1217 |
+
"loss": 3.2225,
|
| 1218 |
"step": 1750
|
| 1219 |
},
|
| 1220 |
{
|
| 1221 |
"epoch": 0.62,
|
| 1222 |
+
"learning_rate": 0.0002675939162390696,
|
| 1223 |
+
"loss": 3.2595,
|
| 1224 |
"step": 1760
|
| 1225 |
},
|
| 1226 |
{
|
| 1227 |
"epoch": 0.62,
|
| 1228 |
+
"learning_rate": 0.0002632639571676793,
|
| 1229 |
+
"loss": 3.2349,
|
| 1230 |
"step": 1770
|
| 1231 |
},
|
| 1232 |
{
|
| 1233 |
"epoch": 0.63,
|
| 1234 |
+
"learning_rate": 0.0002589520656230653,
|
| 1235 |
+
"loss": 3.1926,
|
| 1236 |
"step": 1780
|
| 1237 |
},
|
| 1238 |
{
|
| 1239 |
"epoch": 0.63,
|
| 1240 |
+
"learning_rate": 0.00025465881135417135,
|
| 1241 |
+
"loss": 3.2271,
|
| 1242 |
"step": 1790
|
| 1243 |
},
|
| 1244 |
{
|
| 1245 |
"epoch": 0.64,
|
| 1246 |
+
"learning_rate": 0.00025038476164731643,
|
| 1247 |
+
"loss": 3.2281,
|
| 1248 |
"step": 1800
|
| 1249 |
},
|
| 1250 |
{
|
| 1251 |
"epoch": 0.64,
|
| 1252 |
+
"eval_accuracy": 0.40748857910186626,
|
| 1253 |
+
"eval_loss": 3.217235803604126,
|
| 1254 |
+
"eval_runtime": 151.2208,
|
| 1255 |
+
"eval_samples_per_second": 33.494,
|
| 1256 |
+
"eval_steps_per_second": 4.193,
|
| 1257 |
"step": 1800
|
| 1258 |
},
|
| 1259 |
{
|
| 1260 |
"epoch": 0.64,
|
| 1261 |
+
"learning_rate": 0.00024613048125123803,
|
| 1262 |
+
"loss": 3.2461,
|
| 1263 |
"step": 1810
|
| 1264 |
},
|
| 1265 |
{
|
| 1266 |
"epoch": 0.64,
|
| 1267 |
+
"learning_rate": 0.00024189653230246853,
|
| 1268 |
+
"loss": 3.2236,
|
| 1269 |
"step": 1820
|
| 1270 |
},
|
| 1271 |
{
|
| 1272 |
"epoch": 0.65,
|
| 1273 |
+
"learning_rate": 0.0002376834742510578,
|
| 1274 |
+
"loss": 3.2269,
|
| 1275 |
"step": 1830
|
| 1276 |
},
|
| 1277 |
{
|
| 1278 |
"epoch": 0.65,
|
| 1279 |
+
"learning_rate": 0.00023349186378665126,
|
| 1280 |
+
"loss": 3.1916,
|
| 1281 |
"step": 1840
|
| 1282 |
},
|
| 1283 |
{
|
| 1284 |
"epoch": 0.65,
|
| 1285 |
+
"learning_rate": 0.00022932225476493065,
|
| 1286 |
+
"loss": 3.2088,
|
| 1287 |
"step": 1850
|
| 1288 |
},
|
| 1289 |
{
|
| 1290 |
"epoch": 0.66,
|
| 1291 |
+
"learning_rate": 0.00022517519813443292,
|
| 1292 |
+
"loss": 3.212,
|
| 1293 |
"step": 1860
|
| 1294 |
},
|
| 1295 |
{
|
| 1296 |
"epoch": 0.66,
|
| 1297 |
+
"learning_rate": 0.00022105124186374818,
|
| 1298 |
+
"loss": 3.2159,
|
| 1299 |
"step": 1870
|
| 1300 |
},
|
| 1301 |
{
|
| 1302 |
"epoch": 0.66,
|
| 1303 |
+
"learning_rate": 0.0002169509308691171,
|
| 1304 |
+
"loss": 3.2286,
|
| 1305 |
"step": 1880
|
| 1306 |
},
|
| 1307 |
{
|
| 1308 |
"epoch": 0.67,
|
| 1309 |
+
"learning_rate": 0.0002128748069424268,
|
| 1310 |
+
"loss": 3.1553,
|
| 1311 |
"step": 1890
|
| 1312 |
},
|
| 1313 |
{
|
| 1314 |
"epoch": 0.67,
|
| 1315 |
+
"learning_rate": 0.00020882340867962174,
|
| 1316 |
+
"loss": 3.1759,
|
| 1317 |
"step": 1900
|
| 1318 |
},
|
| 1319 |
{
|
| 1320 |
"epoch": 0.67,
|
| 1321 |
+
"eval_accuracy": 0.41184416942232654,
|
| 1322 |
+
"eval_loss": 3.1826136112213135,
|
| 1323 |
+
"eval_runtime": 150.8644,
|
| 1324 |
+
"eval_samples_per_second": 33.573,
|
| 1325 |
+
"eval_steps_per_second": 4.202,
|
| 1326 |
"step": 1900
|
| 1327 |
},
|
| 1328 |
{
|
| 1329 |
"epoch": 0.67,
|
| 1330 |
+
"learning_rate": 0.00020479727140953813,
|
| 1331 |
+
"loss": 3.1996,
|
| 1332 |
"step": 1910
|
| 1333 |
},
|
| 1334 |
{
|
| 1335 |
"epoch": 0.68,
|
| 1336 |
+
"learning_rate": 0.00020079692712316648,
|
| 1337 |
+
"loss": 3.207,
|
| 1338 |
"step": 1920
|
| 1339 |
},
|
| 1340 |
{
|
| 1341 |
"epoch": 0.68,
|
| 1342 |
+
"learning_rate": 0.00019682290440335907,
|
| 1343 |
+
"loss": 3.1934,
|
| 1344 |
"step": 1930
|
| 1345 |
},
|
| 1346 |
{
|
| 1347 |
"epoch": 0.68,
|
| 1348 |
+
"learning_rate": 0.00019287572835498522,
|
| 1349 |
+
"loss": 3.2055,
|
| 1350 |
"step": 1940
|
| 1351 |
},
|
| 1352 |
{
|
| 1353 |
"epoch": 0.69,
|
| 1354 |
+
"learning_rate": 0.0001889559205355469,
|
| 1355 |
+
"loss": 3.165,
|
| 1356 |
"step": 1950
|
| 1357 |
},
|
| 1358 |
{
|
| 1359 |
"epoch": 0.69,
|
| 1360 |
+
"learning_rate": 0.00018506399888626373,
|
| 1361 |
+
"loss": 3.2182,
|
| 1362 |
"step": 1960
|
| 1363 |
},
|
| 1364 |
{
|
| 1365 |
"epoch": 0.7,
|
| 1366 |
+
"learning_rate": 0.00018120047766363384,
|
| 1367 |
+
"loss": 3.173,
|
| 1368 |
"step": 1970
|
| 1369 |
},
|
| 1370 |
{
|
| 1371 |
"epoch": 0.7,
|
| 1372 |
+
"learning_rate": 0.0001773658673714842,
|
| 1373 |
+
"loss": 3.1718,
|
| 1374 |
"step": 1980
|
| 1375 |
},
|
| 1376 |
{
|
| 1377 |
"epoch": 0.7,
|
| 1378 |
+
"learning_rate": 0.0001735606746935151,
|
| 1379 |
+
"loss": 3.1621,
|
| 1380 |
"step": 1990
|
| 1381 |
},
|
| 1382 |
{
|
| 1383 |
"epoch": 0.71,
|
| 1384 |
+
"learning_rate": 0.00016978540242634958,
|
| 1385 |
+
"loss": 3.1603,
|
| 1386 |
"step": 2000
|
| 1387 |
},
|
| 1388 |
{
|
| 1389 |
"epoch": 0.71,
|
| 1390 |
+
"eval_accuracy": 0.4152190550686701,
|
| 1391 |
+
"eval_loss": 3.1547319889068604,
|
| 1392 |
+
"eval_runtime": 150.8119,
|
| 1393 |
+
"eval_samples_per_second": 33.585,
|
| 1394 |
+
"eval_steps_per_second": 4.204,
|
| 1395 |
"step": 2000
|
| 1396 |
},
|
| 1397 |
{
|
| 1398 |
"epoch": 0.71,
|
| 1399 |
+
"learning_rate": 0.00016604054941309713,
|
| 1400 |
+
"loss": 3.1781,
|
| 1401 |
"step": 2010
|
| 1402 |
},
|
| 1403 |
{
|
| 1404 |
"epoch": 0.71,
|
| 1405 |
+
"learning_rate": 0.0001623266104774391,
|
| 1406 |
+
"loss": 3.1261,
|
| 1407 |
"step": 2020
|
| 1408 |
},
|
| 1409 |
{
|
| 1410 |
"epoch": 0.72,
|
| 1411 |
+
"learning_rate": 0.00015864407635824562,
|
| 1412 |
+
"loss": 3.1293,
|
| 1413 |
"step": 2030
|
| 1414 |
},
|
| 1415 |
{
|
| 1416 |
"epoch": 0.72,
|
| 1417 |
+
"learning_rate": 0.0001549934336447321,
|
| 1418 |
+
"loss": 3.1486,
|
| 1419 |
"step": 2040
|
| 1420 |
},
|
| 1421 |
{
|
| 1422 |
"epoch": 0.72,
|
| 1423 |
+
"learning_rate": 0.00015137516471216422,
|
| 1424 |
+
"loss": 3.1247,
|
| 1425 |
"step": 2050
|
| 1426 |
},
|
| 1427 |
{
|
| 1428 |
"epoch": 0.73,
|
| 1429 |
+
"learning_rate": 0.00014778974765811928,
|
| 1430 |
+
"loss": 3.0984,
|
| 1431 |
"step": 2060
|
| 1432 |
},
|
| 1433 |
{
|
| 1434 |
"epoch": 0.73,
|
| 1435 |
+
"learning_rate": 0.00014423765623931364,
|
| 1436 |
+
"loss": 3.1173,
|
| 1437 |
"step": 2070
|
| 1438 |
},
|
| 1439 |
{
|
| 1440 |
"epoch": 0.73,
|
| 1441 |
+
"learning_rate": 0.0001407193598090021,
|
| 1442 |
+
"loss": 3.147,
|
| 1443 |
"step": 2080
|
| 1444 |
},
|
| 1445 |
{
|
| 1446 |
"epoch": 0.74,
|
| 1447 |
+
"learning_rate": 0.000137235323254962,
|
| 1448 |
+
"loss": 3.147,
|
| 1449 |
"step": 2090
|
| 1450 |
},
|
| 1451 |
{
|
| 1452 |
"epoch": 0.74,
|
| 1453 |
+
"learning_rate": 0.00013378600693806378,
|
| 1454 |
+
"loss": 3.1328,
|
| 1455 |
"step": 2100
|
| 1456 |
},
|
| 1457 |
{
|
| 1458 |
"epoch": 0.74,
|
| 1459 |
+
"eval_accuracy": 0.4185663559848014,
|
| 1460 |
+
"eval_loss": 3.1282718181610107,
|
| 1461 |
+
"eval_runtime": 150.9461,
|
| 1462 |
+
"eval_samples_per_second": 33.555,
|
| 1463 |
+
"eval_steps_per_second": 4.2,
|
| 1464 |
"step": 2100
|
| 1465 |
},
|
| 1466 |
{
|
| 1467 |
"epoch": 0.74,
|
| 1468 |
+
"learning_rate": 0.0001303718666314425,
|
| 1469 |
+
"loss": 3.1565,
|
| 1470 |
"step": 2110
|
| 1471 |
},
|
| 1472 |
{
|
| 1473 |
"epoch": 0.75,
|
| 1474 |
+
"learning_rate": 0.00012699335346027447,
|
| 1475 |
+
"loss": 3.1537,
|
| 1476 |
"step": 2120
|
| 1477 |
},
|
| 1478 |
{
|
| 1479 |
"epoch": 0.75,
|
| 1480 |
+
"learning_rate": 0.0001236509138421674,
|
| 1481 |
+
"loss": 3.1268,
|
| 1482 |
"step": 2130
|
| 1483 |
},
|
| 1484 |
{
|
| 1485 |
"epoch": 0.76,
|
| 1486 |
+
"learning_rate": 0.00012034498942817482,
|
| 1487 |
+
"loss": 3.1449,
|
| 1488 |
"step": 2140
|
| 1489 |
},
|
| 1490 |
{
|
| 1491 |
"epoch": 0.76,
|
| 1492 |
+
"learning_rate": 0.0001170760170444369,
|
| 1493 |
+
"loss": 3.1358,
|
| 1494 |
"step": 2150
|
| 1495 |
},
|
| 1496 |
{
|
| 1497 |
"epoch": 0.76,
|
| 1498 |
+
"learning_rate": 0.00011384442863446211,
|
| 1499 |
+
"loss": 3.0987,
|
| 1500 |
"step": 2160
|
| 1501 |
},
|
| 1502 |
{
|
| 1503 |
"epoch": 0.77,
|
| 1504 |
+
"learning_rate": 0.00011065065120205264,
|
| 1505 |
+
"loss": 3.1229,
|
| 1506 |
"step": 2170
|
| 1507 |
},
|
| 1508 |
{
|
| 1509 |
"epoch": 0.77,
|
| 1510 |
+
"learning_rate": 0.00010749510675488115,
|
| 1511 |
+
"loss": 3.0585,
|
| 1512 |
"step": 2180
|
| 1513 |
},
|
| 1514 |
{
|
| 1515 |
"epoch": 0.77,
|
| 1516 |
+
"learning_rate": 0.00010437821224873104,
|
| 1517 |
+
"loss": 3.1092,
|
| 1518 |
"step": 2190
|
| 1519 |
},
|
| 1520 |
{
|
| 1521 |
"epoch": 0.78,
|
| 1522 |
+
"learning_rate": 0.00010130037953240043,
|
| 1523 |
+
"loss": 3.0916,
|
| 1524 |
"step": 2200
|
| 1525 |
},
|
| 1526 |
{
|
| 1527 |
"epoch": 0.78,
|
| 1528 |
+
"eval_accuracy": 0.4215069268054616,
|
| 1529 |
+
"eval_loss": 3.105459690093994,
|
| 1530 |
+
"eval_runtime": 151.0796,
|
| 1531 |
+
"eval_samples_per_second": 33.525,
|
| 1532 |
+
"eval_steps_per_second": 4.196,
|
| 1533 |
"step": 2200
|
| 1534 |
},
|
| 1535 |
{
|
| 1536 |
"epoch": 0.78,
|
| 1537 |
+
"learning_rate": 9.826201529328414e-05,
|
| 1538 |
+
"loss": 3.1225,
|
| 1539 |
"step": 2210
|
| 1540 |
},
|
| 1541 |
{
|
| 1542 |
"epoch": 0.78,
|
| 1543 |
+
"learning_rate": 9.526352100363562e-05,
|
| 1544 |
+
"loss": 3.0914,
|
| 1545 |
"step": 2220
|
| 1546 |
},
|
| 1547 |
{
|
| 1548 |
"epoch": 0.79,
|
| 1549 |
+
"learning_rate": 9.230529286751886e-05,
|
| 1550 |
+
"loss": 3.1395,
|
| 1551 |
"step": 2230
|
| 1552 |
},
|
| 1553 |
{
|
| 1554 |
"epoch": 0.79,
|
| 1555 |
+
"learning_rate": 8.938772176845631e-05,
|
| 1556 |
+
"loss": 3.0953,
|
| 1557 |
"step": 2240
|
| 1558 |
},
|
| 1559 |
{
|
| 1560 |
"epoch": 0.79,
|
| 1561 |
+
"learning_rate": 8.651119321777952e-05,
|
| 1562 |
+
"loss": 3.0434,
|
| 1563 |
"step": 2250
|
| 1564 |
},
|
| 1565 |
{
|
| 1566 |
"epoch": 0.8,
|
| 1567 |
+
"learning_rate": 8.367608730369015e-05,
|
| 1568 |
+
"loss": 3.0658,
|
| 1569 |
"step": 2260
|
| 1570 |
},
|
| 1571 |
{
|
| 1572 |
"epoch": 0.8,
|
| 1573 |
+
"learning_rate": 8.088277864103697e-05,
|
| 1574 |
+
"loss": 3.0928,
|
| 1575 |
"step": 2270
|
| 1576 |
},
|
| 1577 |
{
|
| 1578 |
"epoch": 0.8,
|
| 1579 |
+
"learning_rate": 7.81316363218167e-05,
|
| 1580 |
+
"loss": 3.0746,
|
| 1581 |
"step": 2280
|
| 1582 |
},
|
| 1583 |
{
|
| 1584 |
"epoch": 0.81,
|
| 1585 |
+
"learning_rate": 7.542302386640385e-05,
|
| 1586 |
+
"loss": 3.0813,
|
| 1587 |
"step": 2290
|
| 1588 |
},
|
| 1589 |
{
|
| 1590 |
"epoch": 0.81,
|
| 1591 |
+
"learning_rate": 7.27572991755178e-05,
|
| 1592 |
+
"loss": 3.0939,
|
| 1593 |
"step": 2300
|
| 1594 |
},
|
| 1595 |
{
|
| 1596 |
"epoch": 0.81,
|
| 1597 |
+
"eval_accuracy": 0.42381410978240375,
|
| 1598 |
+
"eval_loss": 3.0875043869018555,
|
| 1599 |
+
"eval_runtime": 152.0694,
|
| 1600 |
+
"eval_samples_per_second": 33.307,
|
| 1601 |
+
"eval_steps_per_second": 4.169,
|
| 1602 |
"step": 2300
|
| 1603 |
},
|
| 1604 |
{
|
| 1605 |
"epoch": 0.82,
|
| 1606 |
+
"learning_rate": 7.013481448293085e-05,
|
| 1607 |
+
"loss": 3.0575,
|
| 1608 |
"step": 2310
|
| 1609 |
},
|
| 1610 |
{
|
| 1611 |
"epoch": 0.82,
|
| 1612 |
+
"learning_rate": 6.755591630892744e-05,
|
| 1613 |
+
"loss": 3.0907,
|
| 1614 |
"step": 2320
|
| 1615 |
},
|
| 1616 |
{
|
| 1617 |
"epoch": 0.82,
|
| 1618 |
+
"learning_rate": 6.502094541451573e-05,
|
| 1619 |
+
"loss": 3.0385,
|
| 1620 |
"step": 2330
|
| 1621 |
},
|
| 1622 |
{
|
| 1623 |
"epoch": 0.83,
|
| 1624 |
+
"learning_rate": 6.253023675640158e-05,
|
| 1625 |
+
"loss": 3.1125,
|
| 1626 |
"step": 2340
|
| 1627 |
},
|
| 1628 |
{
|
| 1629 |
"epoch": 0.83,
|
| 1630 |
+
"learning_rate": 6.008411944273e-05,
|
| 1631 |
+
"loss": 3.0955,
|
| 1632 |
"step": 2350
|
| 1633 |
},
|
| 1634 |
{
|
| 1635 |
"epoch": 0.83,
|
| 1636 |
+
"learning_rate": 5.7682916689597535e-05,
|
| 1637 |
+
"loss": 3.0929,
|
| 1638 |
"step": 2360
|
| 1639 |
},
|
| 1640 |
{
|
| 1641 |
"epoch": 0.84,
|
| 1642 |
+
"learning_rate": 5.5326945778345586e-05,
|
| 1643 |
+
"loss": 3.0564,
|
| 1644 |
"step": 2370
|
| 1645 |
},
|
| 1646 |
{
|
| 1647 |
"epoch": 0.84,
|
| 1648 |
+
"learning_rate": 5.301651801363528e-05,
|
| 1649 |
+
"loss": 3.0774,
|
| 1650 |
"step": 2380
|
| 1651 |
},
|
| 1652 |
{
|
| 1653 |
"epoch": 0.84,
|
| 1654 |
+
"learning_rate": 5.075193868231454e-05,
|
| 1655 |
+
"loss": 3.0838,
|
| 1656 |
"step": 2390
|
| 1657 |
},
|
| 1658 |
{
|
| 1659 |
"epoch": 0.85,
|
| 1660 |
+
"learning_rate": 4.853350701307897e-05,
|
| 1661 |
+
"loss": 3.0584,
|
| 1662 |
"step": 2400
|
| 1663 |
},
|
| 1664 |
{
|
| 1665 |
"epoch": 0.85,
|
| 1666 |
+
"eval_accuracy": 0.42569305429031773,
|
| 1667 |
+
"eval_loss": 3.073211431503296,
|
| 1668 |
+
"eval_runtime": 151.0975,
|
| 1669 |
+
"eval_samples_per_second": 33.521,
|
| 1670 |
+
"eval_steps_per_second": 4.196,
|
| 1671 |
"step": 2400
|
| 1672 |
},
|
| 1673 |
{
|
| 1674 |
"epoch": 0.85,
|
| 1675 |
+
"learning_rate": 4.636151613693276e-05,
|
| 1676 |
+
"loss": 3.0236,
|
| 1677 |
"step": 2410
|
| 1678 |
},
|
| 1679 |
{
|
| 1680 |
"epoch": 0.85,
|
| 1681 |
+
"learning_rate": 4.423625304845702e-05,
|
| 1682 |
+
"loss": 3.0852,
|
| 1683 |
"step": 2420
|
| 1684 |
},
|
| 1685 |
{
|
| 1686 |
"epoch": 0.86,
|
| 1687 |
+
"learning_rate": 4.215799856788727e-05,
|
| 1688 |
+
"loss": 3.1131,
|
| 1689 |
"step": 2430
|
| 1690 |
},
|
| 1691 |
{
|
| 1692 |
"epoch": 0.86,
|
| 1693 |
+
"learning_rate": 4.012702730400766e-05,
|
| 1694 |
+
"loss": 3.0559,
|
| 1695 |
"step": 2440
|
| 1696 |
},
|
| 1697 |
{
|
| 1698 |
"epoch": 0.86,
|
| 1699 |
+
"learning_rate": 3.8143607617865796e-05,
|
| 1700 |
+
"loss": 3.0686,
|
| 1701 |
"step": 2450
|
| 1702 |
},
|
| 1703 |
{
|
| 1704 |
"epoch": 0.87,
|
| 1705 |
+
"learning_rate": 3.620800158731288e-05,
|
| 1706 |
+
"loss": 3.0508,
|
| 1707 |
"step": 2460
|
| 1708 |
},
|
| 1709 |
{
|
| 1710 |
"epoch": 0.87,
|
| 1711 |
+
"learning_rate": 3.4320464972374246e-05,
|
| 1712 |
+
"loss": 3.0623,
|
| 1713 |
"step": 2470
|
| 1714 |
},
|
| 1715 |
{
|
| 1716 |
"epoch": 0.88,
|
| 1717 |
+
"learning_rate": 3.24812471814548e-05,
|
| 1718 |
+
"loss": 3.0673,
|
| 1719 |
"step": 2480
|
| 1720 |
},
|
| 1721 |
{
|
| 1722 |
"epoch": 0.88,
|
| 1723 |
+
"learning_rate": 3.069059123838347e-05,
|
| 1724 |
+
"loss": 3.0689,
|
| 1725 |
"step": 2490
|
| 1726 |
},
|
| 1727 |
{
|
| 1728 |
"epoch": 0.88,
|
| 1729 |
+
"learning_rate": 2.894873375030156e-05,
|
| 1730 |
+
"loss": 3.0711,
|
| 1731 |
"step": 2500
|
| 1732 |
},
|
| 1733 |
{
|
| 1734 |
"epoch": 0.88,
|
| 1735 |
+
"eval_accuracy": 0.42705097532758074,
|
| 1736 |
+
"eval_loss": 3.0630664825439453,
|
| 1737 |
+
"eval_runtime": 151.1382,
|
| 1738 |
+
"eval_samples_per_second": 33.512,
|
| 1739 |
+
"eval_steps_per_second": 4.195,
|
| 1740 |
"step": 2500
|
| 1741 |
},
|
| 1742 |
{
|
| 1743 |
"epoch": 0.89,
|
| 1744 |
+
"learning_rate": 2.7255904876398687e-05,
|
| 1745 |
+
"loss": 3.0574,
|
| 1746 |
"step": 2510
|
| 1747 |
},
|
| 1748 |
{
|
| 1749 |
"epoch": 0.89,
|
| 1750 |
+
"learning_rate": 2.5612328297500663e-05,
|
| 1751 |
+
"loss": 3.0566,
|
| 1752 |
"step": 2520
|
| 1753 |
},
|
| 1754 |
{
|
| 1755 |
"epoch": 0.89,
|
| 1756 |
+
"learning_rate": 2.4018221186514223e-05,
|
| 1757 |
+
"loss": 3.0702,
|
| 1758 |
"step": 2530
|
| 1759 |
},
|
| 1760 |
{
|
| 1761 |
"epoch": 0.9,
|
| 1762 |
+
"learning_rate": 2.2473794179730344e-05,
|
| 1763 |
+
"loss": 3.0446,
|
| 1764 |
"step": 2540
|
| 1765 |
},
|
| 1766 |
{
|
| 1767 |
"epoch": 0.9,
|
| 1768 |
+
"learning_rate": 2.0979251348992235e-05,
|
| 1769 |
+
"loss": 3.0475,
|
| 1770 |
"step": 2550
|
| 1771 |
},
|
| 1772 |
{
|
| 1773 |
"epoch": 0.9,
|
| 1774 |
+
"learning_rate": 1.953479017473052e-05,
|
| 1775 |
+
"loss": 3.065,
|
| 1776 |
"step": 2560
|
| 1777 |
},
|
| 1778 |
{
|
| 1779 |
"epoch": 0.91,
|
| 1780 |
+
"learning_rate": 1.8140601519869026e-05,
|
| 1781 |
+
"loss": 3.0562,
|
| 1782 |
"step": 2570
|
| 1783 |
},
|
| 1784 |
{
|
| 1785 |
"epoch": 0.91,
|
| 1786 |
+
"learning_rate": 1.6796869604605735e-05,
|
| 1787 |
+
"loss": 3.0301,
|
| 1788 |
"step": 2580
|
| 1789 |
},
|
| 1790 |
{
|
| 1791 |
"epoch": 0.91,
|
| 1792 |
+
"learning_rate": 1.5503771982070226e-05,
|
| 1793 |
+
"loss": 3.0694,
|
| 1794 |
"step": 2590
|
| 1795 |
},
|
| 1796 |
{
|
| 1797 |
"epoch": 0.92,
|
| 1798 |
+
"learning_rate": 1.4261479514863452e-05,
|
| 1799 |
+
"loss": 3.0612,
|
| 1800 |
"step": 2600
|
| 1801 |
},
|
| 1802 |
{
|
| 1803 |
"epoch": 0.92,
|
| 1804 |
+
"eval_accuracy": 0.4279909780571187,
|
| 1805 |
+
"eval_loss": 3.0565025806427,
|
| 1806 |
+
"eval_runtime": 151.9486,
|
| 1807 |
+
"eval_samples_per_second": 33.334,
|
| 1808 |
+
"eval_steps_per_second": 4.172,
|
| 1809 |
"step": 2600
|
| 1810 |
},
|
| 1811 |
{
|
| 1812 |
"epoch": 0.92,
|
| 1813 |
+
"learning_rate": 1.3070156352480877e-05,
|
| 1814 |
+
"loss": 3.0469,
|
| 1815 |
"step": 2610
|
| 1816 |
},
|
| 1817 |
{
|
| 1818 |
"epoch": 0.92,
|
| 1819 |
+
"learning_rate": 1.1929959909622045e-05,
|
| 1820 |
+
"loss": 3.0645,
|
| 1821 |
"step": 2620
|
| 1822 |
},
|
| 1823 |
{
|
| 1824 |
"epoch": 0.93,
|
| 1825 |
+
"learning_rate": 1.084104084539166e-05,
|
| 1826 |
+
"loss": 3.0639,
|
| 1827 |
"step": 2630
|
| 1828 |
},
|
| 1829 |
{
|
| 1830 |
"epoch": 0.93,
|
| 1831 |
+
"learning_rate": 9.803543043391417e-06,
|
| 1832 |
+
"loss": 3.0735,
|
| 1833 |
"step": 2640
|
| 1834 |
},
|
| 1835 |
{
|
| 1836 |
"epoch": 0.94,
|
| 1837 |
+
"learning_rate": 8.817603592708779e-06,
|
| 1838 |
+
"loss": 3.02,
|
| 1839 |
"step": 2650
|
| 1840 |
},
|
| 1841 |
{
|
| 1842 |
"epoch": 0.94,
|
| 1843 |
+
"learning_rate": 7.8833527698023e-06,
|
| 1844 |
+
"loss": 3.0485,
|
| 1845 |
"step": 2660
|
| 1846 |
},
|
| 1847 |
{
|
| 1848 |
"epoch": 0.94,
|
| 1849 |
+
"learning_rate": 7.0009140212878854e-06,
|
| 1850 |
+
"loss": 3.0469,
|
| 1851 |
"step": 2670
|
| 1852 |
},
|
| 1853 |
{
|
| 1854 |
"epoch": 0.95,
|
| 1855 |
+
"learning_rate": 6.170403947627179e-06,
|
| 1856 |
+
"loss": 3.033,
|
| 1857 |
"step": 2680
|
| 1858 |
},
|
| 1859 |
{
|
| 1860 |
"epoch": 0.95,
|
| 1861 |
+
"learning_rate": 5.39193228772068e-06,
|
| 1862 |
+
"loss": 3.0413,
|
| 1863 |
"step": 2690
|
| 1864 |
},
|
| 1865 |
{
|
| 1866 |
"epoch": 0.95,
|
| 1867 |
+
"learning_rate": 4.665601904407347e-06,
|
| 1868 |
+
"loss": 3.081,
|
| 1869 |
"step": 2700
|
| 1870 |
},
|
| 1871 |
{
|
| 1872 |
"epoch": 0.95,
|
| 1873 |
+
"eval_accuracy": 0.42835112275156717,
|
| 1874 |
+
"eval_loss": 3.0534024238586426,
|
| 1875 |
+
"eval_runtime": 151.3942,
|
| 1876 |
+
"eval_samples_per_second": 33.456,
|
| 1877 |
+
"eval_steps_per_second": 4.188,
|
| 1878 |
"step": 2700
|
| 1879 |
},
|
| 1880 |
{
|
| 1881 |
"epoch": 0.96,
|
| 1882 |
+
"learning_rate": 3.99150877087302e-06,
|
| 1883 |
+
"loss": 3.0195,
|
| 1884 |
"step": 2710
|
| 1885 |
},
|
| 1886 |
{
|
| 1887 |
"epoch": 0.96,
|
| 1888 |
+
"learning_rate": 3.3697419579690194e-06,
|
| 1889 |
+
"loss": 3.0411,
|
| 1890 |
"step": 2720
|
| 1891 |
},
|
| 1892 |
{
|
| 1893 |
"epoch": 0.96,
|
| 1894 |
+
"learning_rate": 2.800383622442837e-06,
|
| 1895 |
+
"loss": 3.0234,
|
| 1896 |
"step": 2730
|
| 1897 |
},
|
| 1898 |
{
|
| 1899 |
"epoch": 0.97,
|
| 1900 |
+
"learning_rate": 2.2835089960823395e-06,
|
| 1901 |
+
"loss": 3.0571,
|
| 1902 |
"step": 2740
|
| 1903 |
},
|
| 1904 |
{
|
| 1905 |
"epoch": 0.97,
|
| 1906 |
+
"learning_rate": 1.8191863757751392e-06,
|
| 1907 |
+
"loss": 3.0598,
|
| 1908 |
"step": 2750
|
| 1909 |
},
|
| 1910 |
{
|
| 1911 |
"epoch": 0.97,
|
| 1912 |
+
"learning_rate": 1.4074771144842568e-06,
|
| 1913 |
+
"loss": 3.0829,
|
| 1914 |
"step": 2760
|
| 1915 |
},
|
| 1916 |
{
|
| 1917 |
"epoch": 0.98,
|
| 1918 |
+
"learning_rate": 1.04843561314123e-06,
|
| 1919 |
+
"loss": 3.0236,
|
| 1920 |
"step": 2770
|
| 1921 |
},
|
| 1922 |
{
|
| 1923 |
"epoch": 0.98,
|
| 1924 |
+
"learning_rate": 7.421093134578616e-07,
|
| 1925 |
+
"loss": 3.0504,
|
| 1926 |
"step": 2780
|
| 1927 |
},
|
| 1928 |
{
|
| 1929 |
"epoch": 0.98,
|
| 1930 |
+
"learning_rate": 4.885386916575474e-07,
|
| 1931 |
+
"loss": 3.0446,
|
| 1932 |
"step": 2790
|
| 1933 |
},
|
| 1934 |
{
|
| 1935 |
"epoch": 0.99,
|
| 1936 |
+
"learning_rate": 2.877572531271078e-07,
|
| 1937 |
+
"loss": 3.0378,
|
| 1938 |
"step": 2800
|
| 1939 |
},
|
| 1940 |
{
|
| 1941 |
"epoch": 0.99,
|
| 1942 |
+
"eval_accuracy": 0.4284987878632974,
|
| 1943 |
+
"eval_loss": 3.052541494369507,
|
| 1944 |
+
"eval_runtime": 151.2777,
|
| 1945 |
+
"eval_samples_per_second": 33.481,
|
| 1946 |
+
"eval_steps_per_second": 4.191,
|
| 1947 |
"step": 2800
|
| 1948 |
},
|
| 1949 |
{
|
| 1950 |
"epoch": 0.99,
|
| 1951 |
+
"learning_rate": 1.3979152798935247e-07,
|
| 1952 |
+
"loss": 3.0729,
|
| 1953 |
"step": 2810
|
| 1954 |
},
|
| 1955 |
{
|
| 1956 |
"epoch": 1.0,
|
| 1957 |
+
"learning_rate": 4.4661067597751015e-08,
|
| 1958 |
+
"loss": 2.9979,
|
| 1959 |
"step": 2820
|
| 1960 |
},
|
| 1961 |
{
|
| 1962 |
"epoch": 1.0,
|
| 1963 |
+
"learning_rate": 2.3784419529437883e-09,
|
| 1964 |
+
"loss": 3.1122,
|
| 1965 |
"step": 2830
|
| 1966 |
},
|
| 1967 |
{
|
| 1968 |
"epoch": 1.0,
|
| 1969 |
"step": 2833,
|
| 1970 |
+
"total_flos": 4.4316720769479475e+17,
|
| 1971 |
+
"train_loss": 3.7639108537323183,
|
| 1972 |
+
"train_runtime": 10013.9285,
|
| 1973 |
+
"train_samples_per_second": 9.052,
|
| 1974 |
+
"train_steps_per_second": 0.283
|
| 1975 |
}
|
| 1976 |
],
|
| 1977 |
"logging_steps": 10,
|
|
|
|
| 1979 |
"num_input_tokens_seen": 0,
|
| 1980 |
"num_train_epochs": 1,
|
| 1981 |
"save_steps": 1000.0,
|
| 1982 |
+
"total_flos": 4.4316720769479475e+17,
|
| 1983 |
+
"train_batch_size": 8,
|
| 1984 |
"trial_name": null,
|
| 1985 |
"trial_params": null
|
| 1986 |
}
|