Commit
•
08158b1
1
Parent(s):
a7a4dd8
End of training
Browse files- README.md +3 -3
- all_results.json +4 -4
- runs/May29_14-33-19_65ed6c0683eb/events.out.tfevents.1717021746.65ed6c0683eb.25.1 +3 -0
- train_results.json +4 -4
- trainer_state.json +573 -573
README.md
CHANGED
|
@@ -22,7 +22,7 @@ model-index:
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
-
value: 0.
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [facebook/convnextv2-base-22k-384](https://huggingface.co/facebook/convnextv2-base-22k-384) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 0.
|
| 36 |
-
- Accuracy: 0.
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
+
value: 0.9448412698412698
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [facebook/convnextv2-base-22k-384](https://huggingface.co/facebook/convnextv2-base-22k-384) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.2376
|
| 36 |
+
- Accuracy: 0.9448
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 15.0,
|
| 3 |
"total_flos": 6.140249030814106e+19,
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second": 9.
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 15.0,
|
| 3 |
"total_flos": 6.140249030814106e+19,
|
| 4 |
+
"train_loss": 0.2960004877096818,
|
| 5 |
+
"train_runtime": 28237.408,
|
| 6 |
+
"train_samples_per_second": 9.339,
|
| 7 |
+
"train_steps_per_second": 0.584
|
| 8 |
}
|
runs/May29_14-33-19_65ed6c0683eb/events.out.tfevents.1717021746.65ed6c0683eb.25.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8cbb6f70a07d8d73098c2f201a996b1418dfbcca515d044e53c63f356c5e11d4
|
| 3 |
+
size 417
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 15.0,
|
| 3 |
"total_flos": 6.140249030814106e+19,
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second": 9.
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 15.0,
|
| 3 |
"total_flos": 6.140249030814106e+19,
|
| 4 |
+
"train_loss": 0.2960004877096818,
|
| 5 |
+
"train_runtime": 28237.408,
|
| 6 |
+
"train_samples_per_second": 9.339,
|
| 7 |
+
"train_steps_per_second": 0.584
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "./convnext-base-15ep/checkpoint-
|
| 4 |
"epoch": 15.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
"global_step": 16485,
|
|
@@ -10,1295 +10,1295 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.09,
|
| 13 |
-
"grad_norm":
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss":
|
| 16 |
"step": 100
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.18,
|
| 20 |
-
"grad_norm": 16.
|
| 21 |
-
"learning_rate":
|
| 22 |
-
"loss":
|
| 23 |
"step": 200
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.27,
|
| 27 |
-
"grad_norm":
|
| 28 |
-
"learning_rate":
|
| 29 |
-
"loss":
|
| 30 |
"step": 300
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.36,
|
| 34 |
-
"grad_norm":
|
| 35 |
-
"learning_rate":
|
| 36 |
-
"loss": 0.
|
| 37 |
"step": 400
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.45,
|
| 41 |
-
"grad_norm":
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 500
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.55,
|
| 48 |
-
"grad_norm":
|
| 49 |
-
"learning_rate":
|
| 50 |
-
"loss": 0.
|
| 51 |
"step": 600
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.64,
|
| 55 |
-
"grad_norm":
|
| 56 |
-
"learning_rate":
|
| 57 |
-
"loss": 0.
|
| 58 |
"step": 700
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.73,
|
| 62 |
-
"grad_norm":
|
| 63 |
-
"learning_rate":
|
| 64 |
-
"loss": 0.
|
| 65 |
"step": 800
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.82,
|
| 69 |
-
"grad_norm":
|
| 70 |
-
"learning_rate":
|
| 71 |
-
"loss": 0.
|
| 72 |
"step": 900
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.91,
|
| 76 |
-
"grad_norm":
|
| 77 |
-
"learning_rate":
|
| 78 |
-
"loss": 0.
|
| 79 |
"step": 1000
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 1.0,
|
| 83 |
-
"eval_accuracy": 0.
|
| 84 |
-
"eval_loss": 0.
|
| 85 |
-
"eval_runtime":
|
| 86 |
-
"eval_samples_per_second":
|
| 87 |
-
"eval_steps_per_second": 1.
|
| 88 |
"step": 1099
|
| 89 |
},
|
| 90 |
{
|
| 91 |
"epoch": 1.0,
|
| 92 |
-
"grad_norm":
|
| 93 |
-
"learning_rate":
|
| 94 |
-
"loss": 0.
|
| 95 |
"step": 1100
|
| 96 |
},
|
| 97 |
{
|
| 98 |
"epoch": 1.09,
|
| 99 |
-
"grad_norm":
|
| 100 |
-
"learning_rate":
|
| 101 |
-
"loss": 0.
|
| 102 |
"step": 1200
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 1.18,
|
| 106 |
-
"grad_norm":
|
| 107 |
-
"learning_rate":
|
| 108 |
-
"loss": 0.
|
| 109 |
"step": 1300
|
| 110 |
},
|
| 111 |
{
|
| 112 |
"epoch": 1.27,
|
| 113 |
-
"grad_norm":
|
| 114 |
-
"learning_rate":
|
| 115 |
-
"loss": 0.
|
| 116 |
"step": 1400
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 1.36,
|
| 120 |
-
"grad_norm":
|
| 121 |
-
"learning_rate":
|
| 122 |
-
"loss": 0.
|
| 123 |
"step": 1500
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 1.46,
|
| 127 |
-
"grad_norm":
|
| 128 |
-
"learning_rate":
|
| 129 |
-
"loss": 0.
|
| 130 |
"step": 1600
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 1.55,
|
| 134 |
-
"grad_norm":
|
| 135 |
-
"learning_rate":
|
| 136 |
-
"loss": 0.
|
| 137 |
"step": 1700
|
| 138 |
},
|
| 139 |
{
|
| 140 |
"epoch": 1.64,
|
| 141 |
-
"grad_norm":
|
| 142 |
-
"learning_rate":
|
| 143 |
-
"loss": 0.
|
| 144 |
"step": 1800
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"epoch": 1.73,
|
| 148 |
-
"grad_norm":
|
| 149 |
-
"learning_rate":
|
| 150 |
-
"loss": 0.
|
| 151 |
"step": 1900
|
| 152 |
},
|
| 153 |
{
|
| 154 |
"epoch": 1.82,
|
| 155 |
-
"grad_norm":
|
| 156 |
-
"learning_rate":
|
| 157 |
-
"loss": 0.
|
| 158 |
"step": 2000
|
| 159 |
},
|
| 160 |
{
|
| 161 |
"epoch": 1.91,
|
| 162 |
-
"grad_norm":
|
| 163 |
-
"learning_rate":
|
| 164 |
-
"loss": 0.
|
| 165 |
"step": 2100
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 2.0,
|
| 169 |
-
"eval_accuracy": 0.
|
| 170 |
-
"eval_loss": 0.
|
| 171 |
-
"eval_runtime":
|
| 172 |
-
"eval_samples_per_second":
|
| 173 |
-
"eval_steps_per_second": 1.
|
| 174 |
"step": 2198
|
| 175 |
},
|
| 176 |
{
|
| 177 |
"epoch": 2.0,
|
| 178 |
-
"grad_norm":
|
| 179 |
-
"learning_rate":
|
| 180 |
-
"loss": 0.
|
| 181 |
"step": 2200
|
| 182 |
},
|
| 183 |
{
|
| 184 |
"epoch": 2.09,
|
| 185 |
-
"grad_norm":
|
| 186 |
-
"learning_rate":
|
| 187 |
-
"loss": 0.
|
| 188 |
"step": 2300
|
| 189 |
},
|
| 190 |
{
|
| 191 |
"epoch": 2.18,
|
| 192 |
-
"grad_norm":
|
| 193 |
-
"learning_rate":
|
| 194 |
-
"loss": 0.
|
| 195 |
"step": 2400
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 2.27,
|
| 199 |
-
"grad_norm":
|
| 200 |
-
"learning_rate":
|
| 201 |
-
"loss": 0.
|
| 202 |
"step": 2500
|
| 203 |
},
|
| 204 |
{
|
| 205 |
"epoch": 2.37,
|
| 206 |
-
"grad_norm":
|
| 207 |
-
"learning_rate":
|
| 208 |
-
"loss": 0.
|
| 209 |
"step": 2600
|
| 210 |
},
|
| 211 |
{
|
| 212 |
"epoch": 2.46,
|
| 213 |
-
"grad_norm":
|
| 214 |
-
"learning_rate":
|
| 215 |
-
"loss": 0.
|
| 216 |
"step": 2700
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"epoch": 2.55,
|
| 220 |
-
"grad_norm":
|
| 221 |
-
"learning_rate":
|
| 222 |
-
"loss": 0.
|
| 223 |
"step": 2800
|
| 224 |
},
|
| 225 |
{
|
| 226 |
"epoch": 2.64,
|
| 227 |
-
"grad_norm":
|
| 228 |
-
"learning_rate":
|
| 229 |
-
"loss": 0.
|
| 230 |
"step": 2900
|
| 231 |
},
|
| 232 |
{
|
| 233 |
"epoch": 2.73,
|
| 234 |
-
"grad_norm":
|
| 235 |
-
"learning_rate":
|
| 236 |
-
"loss": 0.
|
| 237 |
"step": 3000
|
| 238 |
},
|
| 239 |
{
|
| 240 |
"epoch": 2.82,
|
| 241 |
-
"grad_norm":
|
| 242 |
-
"learning_rate":
|
| 243 |
-
"loss": 0.
|
| 244 |
"step": 3100
|
| 245 |
},
|
| 246 |
{
|
| 247 |
"epoch": 2.91,
|
| 248 |
-
"grad_norm":
|
| 249 |
-
"learning_rate":
|
| 250 |
-
"loss": 0.
|
| 251 |
"step": 3200
|
| 252 |
},
|
| 253 |
{
|
| 254 |
"epoch": 3.0,
|
| 255 |
-
"eval_accuracy": 0.
|
| 256 |
-
"eval_loss": 0.
|
| 257 |
-
"eval_runtime":
|
| 258 |
-
"eval_samples_per_second":
|
| 259 |
-
"eval_steps_per_second": 1.
|
| 260 |
"step": 3297
|
| 261 |
},
|
| 262 |
{
|
| 263 |
"epoch": 3.0,
|
| 264 |
-
"grad_norm":
|
| 265 |
-
"learning_rate":
|
| 266 |
-
"loss": 0.
|
| 267 |
"step": 3300
|
| 268 |
},
|
| 269 |
{
|
| 270 |
"epoch": 3.09,
|
| 271 |
-
"grad_norm":
|
| 272 |
-
"learning_rate":
|
| 273 |
-
"loss": 0.
|
| 274 |
"step": 3400
|
| 275 |
},
|
| 276 |
{
|
| 277 |
"epoch": 3.18,
|
| 278 |
-
"grad_norm":
|
| 279 |
-
"learning_rate":
|
| 280 |
-
"loss": 0.
|
| 281 |
"step": 3500
|
| 282 |
},
|
| 283 |
{
|
| 284 |
"epoch": 3.28,
|
| 285 |
-
"grad_norm":
|
| 286 |
-
"learning_rate":
|
| 287 |
-
"loss": 0.
|
| 288 |
"step": 3600
|
| 289 |
},
|
| 290 |
{
|
| 291 |
"epoch": 3.37,
|
| 292 |
-
"grad_norm":
|
| 293 |
-
"learning_rate":
|
| 294 |
-
"loss": 0.
|
| 295 |
"step": 3700
|
| 296 |
},
|
| 297 |
{
|
| 298 |
"epoch": 3.46,
|
| 299 |
-
"grad_norm":
|
| 300 |
-
"learning_rate":
|
| 301 |
-
"loss": 0.
|
| 302 |
"step": 3800
|
| 303 |
},
|
| 304 |
{
|
| 305 |
"epoch": 3.55,
|
| 306 |
-
"grad_norm":
|
| 307 |
-
"learning_rate":
|
| 308 |
-
"loss": 0.
|
| 309 |
"step": 3900
|
| 310 |
},
|
| 311 |
{
|
| 312 |
"epoch": 3.64,
|
| 313 |
-
"grad_norm":
|
| 314 |
-
"learning_rate":
|
| 315 |
-
"loss": 0.
|
| 316 |
"step": 4000
|
| 317 |
},
|
| 318 |
{
|
| 319 |
"epoch": 3.73,
|
| 320 |
-
"grad_norm":
|
| 321 |
-
"learning_rate":
|
| 322 |
-
"loss": 0.
|
| 323 |
"step": 4100
|
| 324 |
},
|
| 325 |
{
|
| 326 |
"epoch": 3.82,
|
| 327 |
-
"grad_norm":
|
| 328 |
-
"learning_rate":
|
| 329 |
-
"loss": 0.
|
| 330 |
"step": 4200
|
| 331 |
},
|
| 332 |
{
|
| 333 |
"epoch": 3.91,
|
| 334 |
-
"grad_norm":
|
| 335 |
-
"learning_rate":
|
| 336 |
-
"loss": 0.
|
| 337 |
"step": 4300
|
| 338 |
},
|
| 339 |
{
|
| 340 |
"epoch": 4.0,
|
| 341 |
-
"eval_accuracy": 0.
|
| 342 |
-
"eval_loss": 0.
|
| 343 |
-
"eval_runtime":
|
| 344 |
-
"eval_samples_per_second":
|
| 345 |
-
"eval_steps_per_second": 1.
|
| 346 |
"step": 4396
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"epoch": 4.0,
|
| 350 |
-
"grad_norm":
|
| 351 |
-
"learning_rate":
|
| 352 |
-
"loss": 0.
|
| 353 |
"step": 4400
|
| 354 |
},
|
| 355 |
{
|
| 356 |
"epoch": 4.09,
|
| 357 |
-
"grad_norm":
|
| 358 |
-
"learning_rate":
|
| 359 |
-
"loss": 0.
|
| 360 |
"step": 4500
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 4.19,
|
| 364 |
-
"grad_norm":
|
| 365 |
-
"learning_rate":
|
| 366 |
-
"loss": 0.
|
| 367 |
"step": 4600
|
| 368 |
},
|
| 369 |
{
|
| 370 |
"epoch": 4.28,
|
| 371 |
-
"grad_norm":
|
| 372 |
-
"learning_rate":
|
| 373 |
-
"loss": 0.
|
| 374 |
"step": 4700
|
| 375 |
},
|
| 376 |
{
|
| 377 |
"epoch": 4.37,
|
| 378 |
-
"grad_norm":
|
| 379 |
-
"learning_rate":
|
| 380 |
-
"loss": 0.
|
| 381 |
"step": 4800
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 4.46,
|
| 385 |
-
"grad_norm":
|
| 386 |
-
"learning_rate":
|
| 387 |
-
"loss": 0.
|
| 388 |
"step": 4900
|
| 389 |
},
|
| 390 |
{
|
| 391 |
"epoch": 4.55,
|
| 392 |
-
"grad_norm":
|
| 393 |
-
"learning_rate":
|
| 394 |
-
"loss": 0.
|
| 395 |
"step": 5000
|
| 396 |
},
|
| 397 |
{
|
| 398 |
"epoch": 4.64,
|
| 399 |
-
"grad_norm":
|
| 400 |
-
"learning_rate":
|
| 401 |
-
"loss": 0.
|
| 402 |
"step": 5100
|
| 403 |
},
|
| 404 |
{
|
| 405 |
"epoch": 4.73,
|
| 406 |
-
"grad_norm":
|
| 407 |
-
"learning_rate":
|
| 408 |
-
"loss": 0.
|
| 409 |
"step": 5200
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"epoch": 4.82,
|
| 413 |
-
"grad_norm":
|
| 414 |
-
"learning_rate":
|
| 415 |
-
"loss": 0.
|
| 416 |
"step": 5300
|
| 417 |
},
|
| 418 |
{
|
| 419 |
"epoch": 4.91,
|
| 420 |
-
"grad_norm": 16.
|
| 421 |
-
"learning_rate":
|
| 422 |
-
"loss": 0.
|
| 423 |
"step": 5400
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"epoch": 5.0,
|
| 427 |
-
"eval_accuracy": 0.
|
| 428 |
-
"eval_loss": 0.
|
| 429 |
-
"eval_runtime":
|
| 430 |
-
"eval_samples_per_second":
|
| 431 |
-
"eval_steps_per_second": 1.
|
| 432 |
"step": 5495
|
| 433 |
},
|
| 434 |
{
|
| 435 |
"epoch": 5.0,
|
| 436 |
-
"grad_norm":
|
| 437 |
-
"learning_rate":
|
| 438 |
-
"loss": 0.
|
| 439 |
"step": 5500
|
| 440 |
},
|
| 441 |
{
|
| 442 |
"epoch": 5.1,
|
| 443 |
-
"grad_norm":
|
| 444 |
-
"learning_rate":
|
| 445 |
-
"loss": 0.
|
| 446 |
"step": 5600
|
| 447 |
},
|
| 448 |
{
|
| 449 |
"epoch": 5.19,
|
| 450 |
-
"grad_norm":
|
| 451 |
-
"learning_rate":
|
| 452 |
-
"loss": 0.
|
| 453 |
"step": 5700
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 5.28,
|
| 457 |
-
"grad_norm":
|
| 458 |
-
"learning_rate":
|
| 459 |
-
"loss": 0.
|
| 460 |
"step": 5800
|
| 461 |
},
|
| 462 |
{
|
| 463 |
"epoch": 5.37,
|
| 464 |
-
"grad_norm":
|
| 465 |
-
"learning_rate":
|
| 466 |
-
"loss": 0.
|
| 467 |
"step": 5900
|
| 468 |
},
|
| 469 |
{
|
| 470 |
"epoch": 5.46,
|
| 471 |
-
"grad_norm":
|
| 472 |
-
"learning_rate":
|
| 473 |
-
"loss": 0.
|
| 474 |
"step": 6000
|
| 475 |
},
|
| 476 |
{
|
| 477 |
"epoch": 5.55,
|
| 478 |
-
"grad_norm":
|
| 479 |
-
"learning_rate":
|
| 480 |
-
"loss": 0.
|
| 481 |
"step": 6100
|
| 482 |
},
|
| 483 |
{
|
| 484 |
"epoch": 5.64,
|
| 485 |
-
"grad_norm":
|
| 486 |
-
"learning_rate":
|
| 487 |
-
"loss": 0.
|
| 488 |
"step": 6200
|
| 489 |
},
|
| 490 |
{
|
| 491 |
"epoch": 5.73,
|
| 492 |
-
"grad_norm":
|
| 493 |
-
"learning_rate":
|
| 494 |
-
"loss": 0.
|
| 495 |
"step": 6300
|
| 496 |
},
|
| 497 |
{
|
| 498 |
"epoch": 5.82,
|
| 499 |
-
"grad_norm":
|
| 500 |
-
"learning_rate":
|
| 501 |
-
"loss": 0.
|
| 502 |
"step": 6400
|
| 503 |
},
|
| 504 |
{
|
| 505 |
"epoch": 5.91,
|
| 506 |
-
"grad_norm":
|
| 507 |
-
"learning_rate":
|
| 508 |
-
"loss": 0.
|
| 509 |
"step": 6500
|
| 510 |
},
|
| 511 |
{
|
| 512 |
"epoch": 6.0,
|
| 513 |
-
"eval_accuracy": 0.
|
| 514 |
-
"eval_loss": 0.
|
| 515 |
-
"eval_runtime":
|
| 516 |
-
"eval_samples_per_second":
|
| 517 |
-
"eval_steps_per_second": 1.
|
| 518 |
"step": 6594
|
| 519 |
},
|
| 520 |
{
|
| 521 |
"epoch": 6.01,
|
| 522 |
-
"grad_norm":
|
| 523 |
-
"learning_rate":
|
| 524 |
-
"loss": 0.
|
| 525 |
"step": 6600
|
| 526 |
},
|
| 527 |
{
|
| 528 |
"epoch": 6.1,
|
| 529 |
-
"grad_norm":
|
| 530 |
-
"learning_rate":
|
| 531 |
-
"loss": 0.
|
| 532 |
"step": 6700
|
| 533 |
},
|
| 534 |
{
|
| 535 |
"epoch": 6.19,
|
| 536 |
-
"grad_norm":
|
| 537 |
-
"learning_rate":
|
| 538 |
-
"loss": 0.
|
| 539 |
"step": 6800
|
| 540 |
},
|
| 541 |
{
|
| 542 |
"epoch": 6.28,
|
| 543 |
-
"grad_norm":
|
| 544 |
-
"learning_rate":
|
| 545 |
-
"loss": 0.
|
| 546 |
"step": 6900
|
| 547 |
},
|
| 548 |
{
|
| 549 |
"epoch": 6.37,
|
| 550 |
-
"grad_norm":
|
| 551 |
-
"learning_rate":
|
| 552 |
-
"loss": 0.
|
| 553 |
"step": 7000
|
| 554 |
},
|
| 555 |
{
|
| 556 |
"epoch": 6.46,
|
| 557 |
-
"grad_norm":
|
| 558 |
-
"learning_rate":
|
| 559 |
-
"loss": 0.
|
| 560 |
"step": 7100
|
| 561 |
},
|
| 562 |
{
|
| 563 |
"epoch": 6.55,
|
| 564 |
-
"grad_norm":
|
| 565 |
-
"learning_rate":
|
| 566 |
-
"loss": 0.
|
| 567 |
"step": 7200
|
| 568 |
},
|
| 569 |
{
|
| 570 |
"epoch": 6.64,
|
| 571 |
-
"grad_norm":
|
| 572 |
-
"learning_rate":
|
| 573 |
-
"loss": 0.
|
| 574 |
"step": 7300
|
| 575 |
},
|
| 576 |
{
|
| 577 |
"epoch": 6.73,
|
| 578 |
-
"grad_norm":
|
| 579 |
-
"learning_rate":
|
| 580 |
-
"loss": 0.
|
| 581 |
"step": 7400
|
| 582 |
},
|
| 583 |
{
|
| 584 |
"epoch": 6.82,
|
| 585 |
-
"grad_norm":
|
| 586 |
-
"learning_rate":
|
| 587 |
-
"loss": 0.
|
| 588 |
"step": 7500
|
| 589 |
},
|
| 590 |
{
|
| 591 |
"epoch": 6.92,
|
| 592 |
-
"grad_norm":
|
| 593 |
-
"learning_rate":
|
| 594 |
-
"loss": 0.
|
| 595 |
"step": 7600
|
| 596 |
},
|
| 597 |
{
|
| 598 |
"epoch": 7.0,
|
| 599 |
-
"eval_accuracy": 0.
|
| 600 |
-
"eval_loss": 0.
|
| 601 |
-
"eval_runtime":
|
| 602 |
-
"eval_samples_per_second":
|
| 603 |
-
"eval_steps_per_second": 1.
|
| 604 |
"step": 7693
|
| 605 |
},
|
| 606 |
{
|
| 607 |
"epoch": 7.01,
|
| 608 |
-
"grad_norm":
|
| 609 |
-
"learning_rate":
|
| 610 |
-
"loss": 0.
|
| 611 |
"step": 7700
|
| 612 |
},
|
| 613 |
{
|
| 614 |
"epoch": 7.1,
|
| 615 |
-
"grad_norm":
|
| 616 |
-
"learning_rate":
|
| 617 |
-
"loss": 0.
|
| 618 |
"step": 7800
|
| 619 |
},
|
| 620 |
{
|
| 621 |
"epoch": 7.19,
|
| 622 |
-
"grad_norm":
|
| 623 |
-
"learning_rate":
|
| 624 |
-
"loss": 0.
|
| 625 |
"step": 7900
|
| 626 |
},
|
| 627 |
{
|
| 628 |
"epoch": 7.28,
|
| 629 |
-
"grad_norm":
|
| 630 |
-
"learning_rate":
|
| 631 |
-
"loss": 0.
|
| 632 |
"step": 8000
|
| 633 |
},
|
| 634 |
{
|
| 635 |
"epoch": 7.37,
|
| 636 |
-
"grad_norm":
|
| 637 |
-
"learning_rate":
|
| 638 |
-
"loss": 0.
|
| 639 |
"step": 8100
|
| 640 |
},
|
| 641 |
{
|
| 642 |
"epoch": 7.46,
|
| 643 |
-
"grad_norm":
|
| 644 |
-
"learning_rate":
|
| 645 |
-
"loss": 0.
|
| 646 |
"step": 8200
|
| 647 |
},
|
| 648 |
{
|
| 649 |
"epoch": 7.55,
|
| 650 |
-
"grad_norm":
|
| 651 |
-
"learning_rate":
|
| 652 |
-
"loss": 0.
|
| 653 |
"step": 8300
|
| 654 |
},
|
| 655 |
{
|
| 656 |
"epoch": 7.64,
|
| 657 |
-
"grad_norm":
|
| 658 |
-
"learning_rate":
|
| 659 |
-
"loss": 0.
|
| 660 |
"step": 8400
|
| 661 |
},
|
| 662 |
{
|
| 663 |
"epoch": 7.73,
|
| 664 |
-
"grad_norm":
|
| 665 |
-
"learning_rate":
|
| 666 |
-
"loss": 0.
|
| 667 |
"step": 8500
|
| 668 |
},
|
| 669 |
{
|
| 670 |
"epoch": 7.83,
|
| 671 |
-
"grad_norm":
|
| 672 |
-
"learning_rate":
|
| 673 |
-
"loss": 0.
|
| 674 |
"step": 8600
|
| 675 |
},
|
| 676 |
{
|
| 677 |
"epoch": 7.92,
|
| 678 |
-
"grad_norm":
|
| 679 |
-
"learning_rate":
|
| 680 |
-
"loss": 0.
|
| 681 |
"step": 8700
|
| 682 |
},
|
| 683 |
{
|
| 684 |
"epoch": 8.0,
|
| 685 |
-
"eval_accuracy": 0.
|
| 686 |
-
"eval_loss": 0.
|
| 687 |
-
"eval_runtime":
|
| 688 |
-
"eval_samples_per_second":
|
| 689 |
-
"eval_steps_per_second": 1.
|
| 690 |
"step": 8792
|
| 691 |
},
|
| 692 |
{
|
| 693 |
"epoch": 8.01,
|
| 694 |
-
"grad_norm":
|
| 695 |
-
"learning_rate":
|
| 696 |
-
"loss": 0.
|
| 697 |
"step": 8800
|
| 698 |
},
|
| 699 |
{
|
| 700 |
"epoch": 8.1,
|
| 701 |
-
"grad_norm":
|
| 702 |
-
"learning_rate":
|
| 703 |
-
"loss": 0.
|
| 704 |
"step": 8900
|
| 705 |
},
|
| 706 |
{
|
| 707 |
"epoch": 8.19,
|
| 708 |
-
"grad_norm":
|
| 709 |
-
"learning_rate":
|
| 710 |
-
"loss": 0.
|
| 711 |
"step": 9000
|
| 712 |
},
|
| 713 |
{
|
| 714 |
"epoch": 8.28,
|
| 715 |
-
"grad_norm":
|
| 716 |
-
"learning_rate":
|
| 717 |
-
"loss": 0.
|
| 718 |
"step": 9100
|
| 719 |
},
|
| 720 |
{
|
| 721 |
"epoch": 8.37,
|
| 722 |
-
"grad_norm": 0.
|
| 723 |
-
"learning_rate":
|
| 724 |
-
"loss": 0.
|
| 725 |
"step": 9200
|
| 726 |
},
|
| 727 |
{
|
| 728 |
"epoch": 8.46,
|
| 729 |
-
"grad_norm":
|
| 730 |
-
"learning_rate":
|
| 731 |
-
"loss": 0.
|
| 732 |
"step": 9300
|
| 733 |
},
|
| 734 |
{
|
| 735 |
"epoch": 8.55,
|
| 736 |
-
"grad_norm":
|
| 737 |
-
"learning_rate":
|
| 738 |
-
"loss": 0.
|
| 739 |
"step": 9400
|
| 740 |
},
|
| 741 |
{
|
| 742 |
"epoch": 8.64,
|
| 743 |
-
"grad_norm":
|
| 744 |
-
"learning_rate":
|
| 745 |
-
"loss": 0.
|
| 746 |
"step": 9500
|
| 747 |
},
|
| 748 |
{
|
| 749 |
"epoch": 8.74,
|
| 750 |
-
"grad_norm":
|
| 751 |
-
"learning_rate":
|
| 752 |
-
"loss": 0.
|
| 753 |
"step": 9600
|
| 754 |
},
|
| 755 |
{
|
| 756 |
"epoch": 8.83,
|
| 757 |
-
"grad_norm":
|
| 758 |
-
"learning_rate":
|
| 759 |
-
"loss": 0.
|
| 760 |
"step": 9700
|
| 761 |
},
|
| 762 |
{
|
| 763 |
"epoch": 8.92,
|
| 764 |
-
"grad_norm":
|
| 765 |
-
"learning_rate":
|
| 766 |
-
"loss": 0.
|
| 767 |
"step": 9800
|
| 768 |
},
|
| 769 |
{
|
| 770 |
"epoch": 9.0,
|
| 771 |
-
"eval_accuracy": 0.
|
| 772 |
-
"eval_loss": 0.
|
| 773 |
-
"eval_runtime":
|
| 774 |
-
"eval_samples_per_second":
|
| 775 |
-
"eval_steps_per_second": 1.
|
| 776 |
"step": 9891
|
| 777 |
},
|
| 778 |
{
|
| 779 |
"epoch": 9.01,
|
| 780 |
-
"grad_norm":
|
| 781 |
-
"learning_rate":
|
| 782 |
-
"loss": 0.
|
| 783 |
"step": 9900
|
| 784 |
},
|
| 785 |
{
|
| 786 |
"epoch": 9.1,
|
| 787 |
-
"grad_norm":
|
| 788 |
-
"learning_rate":
|
| 789 |
-
"loss": 0.
|
| 790 |
"step": 10000
|
| 791 |
},
|
| 792 |
{
|
| 793 |
"epoch": 9.19,
|
| 794 |
-
"grad_norm":
|
| 795 |
-
"learning_rate":
|
| 796 |
-
"loss": 0.
|
| 797 |
"step": 10100
|
| 798 |
},
|
| 799 |
{
|
| 800 |
"epoch": 9.28,
|
| 801 |
-
"grad_norm":
|
| 802 |
-
"learning_rate":
|
| 803 |
-
"loss": 0.
|
| 804 |
"step": 10200
|
| 805 |
},
|
| 806 |
{
|
| 807 |
"epoch": 9.37,
|
| 808 |
-
"grad_norm":
|
| 809 |
-
"learning_rate":
|
| 810 |
-
"loss": 0.
|
| 811 |
"step": 10300
|
| 812 |
},
|
| 813 |
{
|
| 814 |
"epoch": 9.46,
|
| 815 |
-
"grad_norm":
|
| 816 |
-
"learning_rate":
|
| 817 |
-
"loss": 0.
|
| 818 |
"step": 10400
|
| 819 |
},
|
| 820 |
{
|
| 821 |
"epoch": 9.55,
|
| 822 |
-
"grad_norm":
|
| 823 |
-
"learning_rate":
|
| 824 |
-
"loss": 0.
|
| 825 |
"step": 10500
|
| 826 |
},
|
| 827 |
{
|
| 828 |
"epoch": 9.65,
|
| 829 |
-
"grad_norm":
|
| 830 |
-
"learning_rate":
|
| 831 |
-
"loss": 0.
|
| 832 |
"step": 10600
|
| 833 |
},
|
| 834 |
{
|
| 835 |
"epoch": 9.74,
|
| 836 |
-
"grad_norm":
|
| 837 |
-
"learning_rate":
|
| 838 |
-
"loss": 0.
|
| 839 |
"step": 10700
|
| 840 |
},
|
| 841 |
{
|
| 842 |
"epoch": 9.83,
|
| 843 |
-
"grad_norm":
|
| 844 |
-
"learning_rate":
|
| 845 |
-
"loss": 0.
|
| 846 |
"step": 10800
|
| 847 |
},
|
| 848 |
{
|
| 849 |
"epoch": 9.92,
|
| 850 |
-
"grad_norm":
|
| 851 |
-
"learning_rate":
|
| 852 |
-
"loss": 0.
|
| 853 |
"step": 10900
|
| 854 |
},
|
| 855 |
{
|
| 856 |
"epoch": 10.0,
|
| 857 |
-
"eval_accuracy": 0.
|
| 858 |
-
"eval_loss": 0.
|
| 859 |
-
"eval_runtime":
|
| 860 |
-
"eval_samples_per_second":
|
| 861 |
-
"eval_steps_per_second": 1.
|
| 862 |
"step": 10990
|
| 863 |
},
|
| 864 |
{
|
| 865 |
"epoch": 10.01,
|
| 866 |
-
"grad_norm": 0.
|
| 867 |
-
"learning_rate":
|
| 868 |
-
"loss": 0.
|
| 869 |
"step": 11000
|
| 870 |
},
|
| 871 |
{
|
| 872 |
"epoch": 10.1,
|
| 873 |
-
"grad_norm":
|
| 874 |
-
"learning_rate":
|
| 875 |
-
"loss": 0.
|
| 876 |
"step": 11100
|
| 877 |
},
|
| 878 |
{
|
| 879 |
"epoch": 10.19,
|
| 880 |
-
"grad_norm":
|
| 881 |
-
"learning_rate":
|
| 882 |
-
"loss": 0.
|
| 883 |
"step": 11200
|
| 884 |
},
|
| 885 |
{
|
| 886 |
"epoch": 10.28,
|
| 887 |
-
"grad_norm":
|
| 888 |
-
"learning_rate":
|
| 889 |
-
"loss": 0.
|
| 890 |
"step": 11300
|
| 891 |
},
|
| 892 |
{
|
| 893 |
"epoch": 10.37,
|
| 894 |
-
"grad_norm":
|
| 895 |
-
"learning_rate":
|
| 896 |
-
"loss": 0.
|
| 897 |
"step": 11400
|
| 898 |
},
|
| 899 |
{
|
| 900 |
"epoch": 10.46,
|
| 901 |
-
"grad_norm":
|
| 902 |
-
"learning_rate":
|
| 903 |
-
"loss": 0.
|
| 904 |
"step": 11500
|
| 905 |
},
|
| 906 |
{
|
| 907 |
"epoch": 10.56,
|
| 908 |
-
"grad_norm":
|
| 909 |
-
"learning_rate":
|
| 910 |
-
"loss": 0.
|
| 911 |
"step": 11600
|
| 912 |
},
|
| 913 |
{
|
| 914 |
"epoch": 10.65,
|
| 915 |
-
"grad_norm":
|
| 916 |
-
"learning_rate":
|
| 917 |
-
"loss": 0.
|
| 918 |
"step": 11700
|
| 919 |
},
|
| 920 |
{
|
| 921 |
"epoch": 10.74,
|
| 922 |
-
"grad_norm": 8.
|
| 923 |
-
"learning_rate":
|
| 924 |
-
"loss": 0.
|
| 925 |
"step": 11800
|
| 926 |
},
|
| 927 |
{
|
| 928 |
"epoch": 10.83,
|
| 929 |
-
"grad_norm":
|
| 930 |
-
"learning_rate":
|
| 931 |
-
"loss": 0.
|
| 932 |
"step": 11900
|
| 933 |
},
|
| 934 |
{
|
| 935 |
"epoch": 10.92,
|
| 936 |
-
"grad_norm":
|
| 937 |
-
"learning_rate":
|
| 938 |
-
"loss": 0.
|
| 939 |
"step": 12000
|
| 940 |
},
|
| 941 |
{
|
| 942 |
"epoch": 11.0,
|
| 943 |
-
"eval_accuracy": 0.
|
| 944 |
-
"eval_loss": 0.
|
| 945 |
-
"eval_runtime":
|
| 946 |
-
"eval_samples_per_second":
|
| 947 |
-
"eval_steps_per_second": 1.
|
| 948 |
"step": 12089
|
| 949 |
},
|
| 950 |
{
|
| 951 |
"epoch": 11.01,
|
| 952 |
-
"grad_norm": 0.
|
| 953 |
-
"learning_rate":
|
| 954 |
-
"loss": 0.
|
| 955 |
"step": 12100
|
| 956 |
},
|
| 957 |
{
|
| 958 |
"epoch": 11.1,
|
| 959 |
-
"grad_norm":
|
| 960 |
-
"learning_rate":
|
| 961 |
-
"loss": 0.
|
| 962 |
"step": 12200
|
| 963 |
},
|
| 964 |
{
|
| 965 |
"epoch": 11.19,
|
| 966 |
-
"grad_norm": 0.
|
| 967 |
-
"learning_rate":
|
| 968 |
-
"loss": 0.
|
| 969 |
"step": 12300
|
| 970 |
},
|
| 971 |
{
|
| 972 |
"epoch": 11.28,
|
| 973 |
-
"grad_norm":
|
| 974 |
-
"learning_rate":
|
| 975 |
-
"loss": 0.
|
| 976 |
"step": 12400
|
| 977 |
},
|
| 978 |
{
|
| 979 |
"epoch": 11.37,
|
| 980 |
-
"grad_norm":
|
| 981 |
-
"learning_rate":
|
| 982 |
-
"loss": 0.
|
| 983 |
"step": 12500
|
| 984 |
},
|
| 985 |
{
|
| 986 |
"epoch": 11.46,
|
| 987 |
-
"grad_norm":
|
| 988 |
-
"learning_rate":
|
| 989 |
-
"loss": 0.
|
| 990 |
"step": 12600
|
| 991 |
},
|
| 992 |
{
|
| 993 |
"epoch": 11.56,
|
| 994 |
-
"grad_norm":
|
| 995 |
-
"learning_rate":
|
| 996 |
-
"loss": 0.
|
| 997 |
"step": 12700
|
| 998 |
},
|
| 999 |
{
|
| 1000 |
"epoch": 11.65,
|
| 1001 |
-
"grad_norm":
|
| 1002 |
-
"learning_rate":
|
| 1003 |
-
"loss": 0.
|
| 1004 |
"step": 12800
|
| 1005 |
},
|
| 1006 |
{
|
| 1007 |
"epoch": 11.74,
|
| 1008 |
-
"grad_norm":
|
| 1009 |
-
"learning_rate":
|
| 1010 |
-
"loss": 0.
|
| 1011 |
"step": 12900
|
| 1012 |
},
|
| 1013 |
{
|
| 1014 |
"epoch": 11.83,
|
| 1015 |
-
"grad_norm":
|
| 1016 |
-
"learning_rate":
|
| 1017 |
-
"loss": 0.
|
| 1018 |
"step": 13000
|
| 1019 |
},
|
| 1020 |
{
|
| 1021 |
"epoch": 11.92,
|
| 1022 |
-
"grad_norm":
|
| 1023 |
-
"learning_rate":
|
| 1024 |
-
"loss": 0.
|
| 1025 |
"step": 13100
|
| 1026 |
},
|
| 1027 |
{
|
| 1028 |
"epoch": 12.0,
|
| 1029 |
-
"eval_accuracy": 0.
|
| 1030 |
-
"eval_loss": 0.
|
| 1031 |
-
"eval_runtime":
|
| 1032 |
-
"eval_samples_per_second":
|
| 1033 |
-
"eval_steps_per_second": 1.
|
| 1034 |
"step": 13188
|
| 1035 |
},
|
| 1036 |
{
|
| 1037 |
"epoch": 12.01,
|
| 1038 |
-
"grad_norm":
|
| 1039 |
-
"learning_rate":
|
| 1040 |
-
"loss": 0.
|
| 1041 |
"step": 13200
|
| 1042 |
},
|
| 1043 |
{
|
| 1044 |
"epoch": 12.1,
|
| 1045 |
-
"grad_norm":
|
| 1046 |
-
"learning_rate":
|
| 1047 |
-
"loss": 0.
|
| 1048 |
"step": 13300
|
| 1049 |
},
|
| 1050 |
{
|
| 1051 |
"epoch": 12.19,
|
| 1052 |
-
"grad_norm":
|
| 1053 |
-
"learning_rate":
|
| 1054 |
-
"loss": 0.
|
| 1055 |
"step": 13400
|
| 1056 |
},
|
| 1057 |
{
|
| 1058 |
"epoch": 12.28,
|
| 1059 |
-
"grad_norm":
|
| 1060 |
-
"learning_rate":
|
| 1061 |
-
"loss": 0.
|
| 1062 |
"step": 13500
|
| 1063 |
},
|
| 1064 |
{
|
| 1065 |
"epoch": 12.37,
|
| 1066 |
-
"grad_norm": 3.
|
| 1067 |
-
"learning_rate":
|
| 1068 |
-
"loss": 0.
|
| 1069 |
"step": 13600
|
| 1070 |
},
|
| 1071 |
{
|
| 1072 |
"epoch": 12.47,
|
| 1073 |
-
"grad_norm":
|
| 1074 |
-
"learning_rate":
|
| 1075 |
-
"loss": 0.
|
| 1076 |
"step": 13700
|
| 1077 |
},
|
| 1078 |
{
|
| 1079 |
"epoch": 12.56,
|
| 1080 |
-
"grad_norm":
|
| 1081 |
-
"learning_rate":
|
| 1082 |
-
"loss": 0.
|
| 1083 |
"step": 13800
|
| 1084 |
},
|
| 1085 |
{
|
| 1086 |
"epoch": 12.65,
|
| 1087 |
-
"grad_norm":
|
| 1088 |
-
"learning_rate":
|
| 1089 |
-
"loss": 0.
|
| 1090 |
"step": 13900
|
| 1091 |
},
|
| 1092 |
{
|
| 1093 |
"epoch": 12.74,
|
| 1094 |
-
"grad_norm":
|
| 1095 |
-
"learning_rate":
|
| 1096 |
-
"loss": 0.
|
| 1097 |
"step": 14000
|
| 1098 |
},
|
| 1099 |
{
|
| 1100 |
"epoch": 12.83,
|
| 1101 |
-
"grad_norm": 0.
|
| 1102 |
-
"learning_rate":
|
| 1103 |
-
"loss": 0.
|
| 1104 |
"step": 14100
|
| 1105 |
},
|
| 1106 |
{
|
| 1107 |
"epoch": 12.92,
|
| 1108 |
-
"grad_norm":
|
| 1109 |
-
"learning_rate":
|
| 1110 |
-
"loss": 0.
|
| 1111 |
"step": 14200
|
| 1112 |
},
|
| 1113 |
{
|
| 1114 |
"epoch": 13.0,
|
| 1115 |
-
"eval_accuracy": 0.
|
| 1116 |
-
"eval_loss": 0.
|
| 1117 |
-
"eval_runtime":
|
| 1118 |
-
"eval_samples_per_second":
|
| 1119 |
-
"eval_steps_per_second": 1.
|
| 1120 |
"step": 14287
|
| 1121 |
},
|
| 1122 |
{
|
| 1123 |
"epoch": 13.01,
|
| 1124 |
-
"grad_norm":
|
| 1125 |
-
"learning_rate":
|
| 1126 |
-
"loss": 0.
|
| 1127 |
"step": 14300
|
| 1128 |
},
|
| 1129 |
{
|
| 1130 |
"epoch": 13.1,
|
| 1131 |
-
"grad_norm": 0.
|
| 1132 |
-
"learning_rate":
|
| 1133 |
-
"loss": 0.
|
| 1134 |
"step": 14400
|
| 1135 |
},
|
| 1136 |
{
|
| 1137 |
"epoch": 13.19,
|
| 1138 |
-
"grad_norm":
|
| 1139 |
-
"learning_rate":
|
| 1140 |
-
"loss": 0.
|
| 1141 |
"step": 14500
|
| 1142 |
},
|
| 1143 |
{
|
| 1144 |
"epoch": 13.28,
|
| 1145 |
-
"grad_norm":
|
| 1146 |
-
"learning_rate":
|
| 1147 |
-
"loss": 0.
|
| 1148 |
"step": 14600
|
| 1149 |
},
|
| 1150 |
{
|
| 1151 |
"epoch": 13.38,
|
| 1152 |
-
"grad_norm":
|
| 1153 |
-
"learning_rate":
|
| 1154 |
-
"loss": 0.
|
| 1155 |
"step": 14700
|
| 1156 |
},
|
| 1157 |
{
|
| 1158 |
"epoch": 13.47,
|
| 1159 |
-
"grad_norm":
|
| 1160 |
-
"learning_rate":
|
| 1161 |
-
"loss": 0.
|
| 1162 |
"step": 14800
|
| 1163 |
},
|
| 1164 |
{
|
| 1165 |
"epoch": 13.56,
|
| 1166 |
-
"grad_norm":
|
| 1167 |
-
"learning_rate":
|
| 1168 |
-
"loss": 0.
|
| 1169 |
"step": 14900
|
| 1170 |
},
|
| 1171 |
{
|
| 1172 |
"epoch": 13.65,
|
| 1173 |
-
"grad_norm":
|
| 1174 |
-
"learning_rate":
|
| 1175 |
-
"loss": 0.
|
| 1176 |
"step": 15000
|
| 1177 |
},
|
| 1178 |
{
|
| 1179 |
"epoch": 13.74,
|
| 1180 |
-
"grad_norm":
|
| 1181 |
-
"learning_rate":
|
| 1182 |
-
"loss": 0.
|
| 1183 |
"step": 15100
|
| 1184 |
},
|
| 1185 |
{
|
| 1186 |
"epoch": 13.83,
|
| 1187 |
-
"grad_norm":
|
| 1188 |
-
"learning_rate":
|
| 1189 |
-
"loss": 0.
|
| 1190 |
"step": 15200
|
| 1191 |
},
|
| 1192 |
{
|
| 1193 |
"epoch": 13.92,
|
| 1194 |
-
"grad_norm":
|
| 1195 |
-
"learning_rate":
|
| 1196 |
-
"loss": 0.
|
| 1197 |
"step": 15300
|
| 1198 |
},
|
| 1199 |
{
|
| 1200 |
"epoch": 14.0,
|
| 1201 |
-
"eval_accuracy": 0.
|
| 1202 |
-
"eval_loss": 0.
|
| 1203 |
-
"eval_runtime":
|
| 1204 |
-
"eval_samples_per_second":
|
| 1205 |
-
"eval_steps_per_second": 1.
|
| 1206 |
"step": 15386
|
| 1207 |
},
|
| 1208 |
{
|
| 1209 |
"epoch": 14.01,
|
| 1210 |
-
"grad_norm":
|
| 1211 |
-
"learning_rate":
|
| 1212 |
-
"loss": 0.
|
| 1213 |
"step": 15400
|
| 1214 |
},
|
| 1215 |
{
|
| 1216 |
"epoch": 14.1,
|
| 1217 |
-
"grad_norm":
|
| 1218 |
-
"learning_rate":
|
| 1219 |
-
"loss": 0.
|
| 1220 |
"step": 15500
|
| 1221 |
},
|
| 1222 |
{
|
| 1223 |
"epoch": 14.19,
|
| 1224 |
-
"grad_norm":
|
| 1225 |
-
"learning_rate":
|
| 1226 |
-
"loss": 0.
|
| 1227 |
"step": 15600
|
| 1228 |
},
|
| 1229 |
{
|
| 1230 |
"epoch": 14.29,
|
| 1231 |
-
"grad_norm":
|
| 1232 |
-
"learning_rate":
|
| 1233 |
-
"loss": 0.
|
| 1234 |
"step": 15700
|
| 1235 |
},
|
| 1236 |
{
|
| 1237 |
"epoch": 14.38,
|
| 1238 |
-
"grad_norm":
|
| 1239 |
-
"learning_rate":
|
| 1240 |
-
"loss": 0.
|
| 1241 |
"step": 15800
|
| 1242 |
},
|
| 1243 |
{
|
| 1244 |
"epoch": 14.47,
|
| 1245 |
-
"grad_norm":
|
| 1246 |
-
"learning_rate":
|
| 1247 |
-
"loss": 0.
|
| 1248 |
"step": 15900
|
| 1249 |
},
|
| 1250 |
{
|
| 1251 |
"epoch": 14.56,
|
| 1252 |
-
"grad_norm":
|
| 1253 |
-
"learning_rate":
|
| 1254 |
-
"loss": 0.
|
| 1255 |
"step": 16000
|
| 1256 |
},
|
| 1257 |
{
|
| 1258 |
"epoch": 14.65,
|
| 1259 |
-
"grad_norm":
|
| 1260 |
-
"learning_rate":
|
| 1261 |
-
"loss": 0.
|
| 1262 |
"step": 16100
|
| 1263 |
},
|
| 1264 |
{
|
| 1265 |
"epoch": 14.74,
|
| 1266 |
-
"grad_norm":
|
| 1267 |
-
"learning_rate":
|
| 1268 |
-
"loss": 0.
|
| 1269 |
"step": 16200
|
| 1270 |
},
|
| 1271 |
{
|
| 1272 |
"epoch": 14.83,
|
| 1273 |
-
"grad_norm":
|
| 1274 |
-
"learning_rate":
|
| 1275 |
-
"loss": 0.
|
| 1276 |
"step": 16300
|
| 1277 |
},
|
| 1278 |
{
|
| 1279 |
"epoch": 14.92,
|
| 1280 |
-
"grad_norm":
|
| 1281 |
-
"learning_rate":
|
| 1282 |
-
"loss": 0.
|
| 1283 |
"step": 16400
|
| 1284 |
},
|
| 1285 |
{
|
| 1286 |
"epoch": 15.0,
|
| 1287 |
-
"eval_accuracy": 0.
|
| 1288 |
-
"eval_loss": 0.
|
| 1289 |
-
"eval_runtime":
|
| 1290 |
-
"eval_samples_per_second": 23.
|
| 1291 |
-
"eval_steps_per_second": 1.
|
| 1292 |
"step": 16485
|
| 1293 |
},
|
| 1294 |
{
|
| 1295 |
"epoch": 15.0,
|
| 1296 |
"step": 16485,
|
| 1297 |
"total_flos": 6.140249030814106e+19,
|
| 1298 |
-
"train_loss": 0.
|
| 1299 |
-
"train_runtime":
|
| 1300 |
-
"train_samples_per_second": 9.
|
| 1301 |
-
"train_steps_per_second": 0.
|
| 1302 |
}
|
| 1303 |
],
|
| 1304 |
"logging_steps": 100,
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.23529192805290222,
|
| 3 |
+
"best_model_checkpoint": "./convnext-base-15ep/checkpoint-9891",
|
| 4 |
"epoch": 15.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
"global_step": 16485,
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.09,
|
| 13 |
+
"grad_norm": 23.461017608642578,
|
| 14 |
+
"learning_rate": 2.999727623294975e-05,
|
| 15 |
+
"loss": 2.6353,
|
| 16 |
"step": 100
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.18,
|
| 20 |
+
"grad_norm": 16.223487854003906,
|
| 21 |
+
"learning_rate": 2.9989105920986585e-05,
|
| 22 |
+
"loss": 1.496,
|
| 23 |
"step": 200
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.27,
|
| 27 |
+
"grad_norm": 21.04163932800293,
|
| 28 |
+
"learning_rate": 2.9975492031314045e-05,
|
| 29 |
+
"loss": 1.1313,
|
| 30 |
"step": 300
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.36,
|
| 34 |
+
"grad_norm": 34.1530647277832,
|
| 35 |
+
"learning_rate": 2.995643950807401e-05,
|
| 36 |
+
"loss": 0.8547,
|
| 37 |
"step": 400
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.45,
|
| 41 |
+
"grad_norm": 19.99446678161621,
|
| 42 |
+
"learning_rate": 2.9931955270551154e-05,
|
| 43 |
+
"loss": 0.8017,
|
| 44 |
"step": 500
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.55,
|
| 48 |
+
"grad_norm": 19.548385620117188,
|
| 49 |
+
"learning_rate": 2.990204821066006e-05,
|
| 50 |
+
"loss": 0.691,
|
| 51 |
"step": 600
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.64,
|
| 55 |
+
"grad_norm": 27.656845092773438,
|
| 56 |
+
"learning_rate": 2.9866729189715972e-05,
|
| 57 |
+
"loss": 0.7105,
|
| 58 |
"step": 700
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.73,
|
| 62 |
+
"grad_norm": 14.135828971862793,
|
| 63 |
+
"learning_rate": 2.982601103449029e-05,
|
| 64 |
+
"loss": 0.6394,
|
| 65 |
"step": 800
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.82,
|
| 69 |
+
"grad_norm": 11.512890815734863,
|
| 70 |
+
"learning_rate": 2.977990853255228e-05,
|
| 71 |
+
"loss": 0.6012,
|
| 72 |
"step": 900
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.91,
|
| 76 |
+
"grad_norm": 12.752175331115723,
|
| 77 |
+
"learning_rate": 2.972843842689871e-05,
|
| 78 |
+
"loss": 0.6099,
|
| 79 |
"step": 1000
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 1.0,
|
| 83 |
+
"eval_accuracy": 0.8934393638170974,
|
| 84 |
+
"eval_loss": 0.3667598366737366,
|
| 85 |
+
"eval_runtime": 105.5376,
|
| 86 |
+
"eval_samples_per_second": 23.83,
|
| 87 |
+
"eval_steps_per_second": 1.497,
|
| 88 |
"step": 1099
|
| 89 |
},
|
| 90 |
{
|
| 91 |
"epoch": 1.0,
|
| 92 |
+
"grad_norm": 32.5348014831543,
|
| 93 |
+
"learning_rate": 2.9671619409873295e-05,
|
| 94 |
+
"loss": 0.639,
|
| 95 |
"step": 1100
|
| 96 |
},
|
| 97 |
{
|
| 98 |
"epoch": 1.09,
|
| 99 |
+
"grad_norm": 16.545459747314453,
|
| 100 |
+
"learning_rate": 2.9609472116378222e-05,
|
| 101 |
+
"loss": 0.5358,
|
| 102 |
"step": 1200
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 1.18,
|
| 106 |
+
"grad_norm": 25.811128616333008,
|
| 107 |
+
"learning_rate": 2.954201911638019e-05,
|
| 108 |
+
"loss": 0.518,
|
| 109 |
"step": 1300
|
| 110 |
},
|
| 111 |
{
|
| 112 |
"epoch": 1.27,
|
| 113 |
+
"grad_norm": 18.66850471496582,
|
| 114 |
+
"learning_rate": 2.9469284906713715e-05,
|
| 115 |
+
"loss": 0.4844,
|
| 116 |
"step": 1400
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 1.36,
|
| 120 |
+
"grad_norm": 19.064212799072266,
|
| 121 |
+
"learning_rate": 2.9391295902184625e-05,
|
| 122 |
+
"loss": 0.5122,
|
| 123 |
"step": 1500
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 1.46,
|
| 127 |
+
"grad_norm": 20.12409210205078,
|
| 128 |
+
"learning_rate": 2.930808042597703e-05,
|
| 129 |
+
"loss": 0.474,
|
| 130 |
"step": 1600
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 1.55,
|
| 134 |
+
"grad_norm": 13.67546272277832,
|
| 135 |
+
"learning_rate": 2.9219668699367213e-05,
|
| 136 |
+
"loss": 0.5351,
|
| 137 |
"step": 1700
|
| 138 |
},
|
| 139 |
{
|
| 140 |
"epoch": 1.64,
|
| 141 |
+
"grad_norm": 21.155534744262695,
|
| 142 |
+
"learning_rate": 2.9126092830748217e-05,
|
| 143 |
+
"loss": 0.4939,
|
| 144 |
"step": 1800
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"epoch": 1.73,
|
| 148 |
+
"grad_norm": 20.379898071289062,
|
| 149 |
+
"learning_rate": 2.9027386803969068e-05,
|
| 150 |
+
"loss": 0.4351,
|
| 151 |
"step": 1900
|
| 152 |
},
|
| 153 |
{
|
| 154 |
"epoch": 1.82,
|
| 155 |
+
"grad_norm": 18.86287498474121,
|
| 156 |
+
"learning_rate": 2.8923586465992876e-05,
|
| 157 |
+
"loss": 0.4853,
|
| 158 |
"step": 2000
|
| 159 |
},
|
| 160 |
{
|
| 161 |
"epoch": 1.91,
|
| 162 |
+
"grad_norm": 16.228618621826172,
|
| 163 |
+
"learning_rate": 2.8814729513878365e-05,
|
| 164 |
+
"loss": 0.5086,
|
| 165 |
"step": 2100
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 2.0,
|
| 169 |
+
"eval_accuracy": 0.927634194831014,
|
| 170 |
+
"eval_loss": 0.27727919816970825,
|
| 171 |
+
"eval_runtime": 105.4061,
|
| 172 |
+
"eval_samples_per_second": 23.86,
|
| 173 |
+
"eval_steps_per_second": 1.499,
|
| 174 |
"step": 2198
|
| 175 |
},
|
| 176 |
{
|
| 177 |
"epoch": 2.0,
|
| 178 |
+
"grad_norm": 28.413759231567383,
|
| 179 |
+
"learning_rate": 2.8700855481089444e-05,
|
| 180 |
+
"loss": 0.4694,
|
| 181 |
"step": 2200
|
| 182 |
},
|
| 183 |
{
|
| 184 |
"epoch": 2.09,
|
| 185 |
+
"grad_norm": 16.885929107666016,
|
| 186 |
+
"learning_rate": 2.8582005723137908e-05,
|
| 187 |
+
"loss": 0.3474,
|
| 188 |
"step": 2300
|
| 189 |
},
|
| 190 |
{
|
| 191 |
"epoch": 2.18,
|
| 192 |
+
"grad_norm": 21.655845642089844,
|
| 193 |
+
"learning_rate": 2.8458223402564366e-05,
|
| 194 |
+
"loss": 0.4257,
|
| 195 |
"step": 2400
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 2.27,
|
| 199 |
+
"grad_norm": 20.78180503845215,
|
| 200 |
+
"learning_rate": 2.8329553473262978e-05,
|
| 201 |
+
"loss": 0.3752,
|
| 202 |
"step": 2500
|
| 203 |
},
|
| 204 |
{
|
| 205 |
"epoch": 2.37,
|
| 206 |
+
"grad_norm": 13.279301643371582,
|
| 207 |
+
"learning_rate": 2.8196042664155587e-05,
|
| 208 |
+
"loss": 0.4485,
|
| 209 |
"step": 2600
|
| 210 |
},
|
| 211 |
{
|
| 212 |
"epoch": 2.46,
|
| 213 |
+
"grad_norm": 35.08995056152344,
|
| 214 |
+
"learning_rate": 2.8057739462221215e-05,
|
| 215 |
+
"loss": 0.3814,
|
| 216 |
"step": 2700
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"epoch": 2.55,
|
| 220 |
+
"grad_norm": 6.2748332023620605,
|
| 221 |
+
"learning_rate": 2.791469409488711e-05,
|
| 222 |
+
"loss": 0.4063,
|
| 223 |
"step": 2800
|
| 224 |
},
|
| 225 |
{
|
| 226 |
"epoch": 2.64,
|
| 227 |
+
"grad_norm": 34.69600296020508,
|
| 228 |
+
"learning_rate": 2.7766958511787707e-05,
|
| 229 |
+
"loss": 0.392,
|
| 230 |
"step": 2900
|
| 231 |
},
|
| 232 |
{
|
| 233 |
"epoch": 2.73,
|
| 234 |
+
"grad_norm": 19.070589065551758,
|
| 235 |
+
"learning_rate": 2.761458636589813e-05,
|
| 236 |
+
"loss": 0.4298,
|
| 237 |
"step": 3000
|
| 238 |
},
|
| 239 |
{
|
| 240 |
"epoch": 2.82,
|
| 241 |
+
"grad_norm": 18.813634872436523,
|
| 242 |
+
"learning_rate": 2.7457632994049085e-05,
|
| 243 |
+
"loss": 0.4147,
|
| 244 |
"step": 3100
|
| 245 |
},
|
| 246 |
{
|
| 247 |
"epoch": 2.91,
|
| 248 |
+
"grad_norm": 21.774486541748047,
|
| 249 |
+
"learning_rate": 2.7296155396830262e-05,
|
| 250 |
+
"loss": 0.386,
|
| 251 |
"step": 3200
|
| 252 |
},
|
| 253 |
{
|
| 254 |
"epoch": 3.0,
|
| 255 |
+
"eval_accuracy": 0.9324055666003976,
|
| 256 |
+
"eval_loss": 0.2586577832698822,
|
| 257 |
+
"eval_runtime": 105.5285,
|
| 258 |
+
"eval_samples_per_second": 23.832,
|
| 259 |
+
"eval_steps_per_second": 1.497,
|
| 260 |
"step": 3297
|
| 261 |
},
|
| 262 |
{
|
| 263 |
"epoch": 3.0,
|
| 264 |
+
"grad_norm": 10.948277473449707,
|
| 265 |
+
"learning_rate": 2.7130212217889484e-05,
|
| 266 |
+
"loss": 0.3943,
|
| 267 |
"step": 3300
|
| 268 |
},
|
| 269 |
{
|
| 270 |
"epoch": 3.09,
|
| 271 |
+
"grad_norm": 9.30019760131836,
|
| 272 |
+
"learning_rate": 2.6959863722635152e-05,
|
| 273 |
+
"loss": 0.3148,
|
| 274 |
"step": 3400
|
| 275 |
},
|
| 276 |
{
|
| 277 |
"epoch": 3.18,
|
| 278 |
+
"grad_norm": 20.882099151611328,
|
| 279 |
+
"learning_rate": 2.6785171776349725e-05,
|
| 280 |
+
"loss": 0.375,
|
| 281 |
"step": 3500
|
| 282 |
},
|
| 283 |
{
|
| 284 |
"epoch": 3.28,
|
| 285 |
+
"grad_norm": 25.736265182495117,
|
| 286 |
+
"learning_rate": 2.6606199821722166e-05,
|
| 287 |
+
"loss": 0.3827,
|
| 288 |
"step": 3600
|
| 289 |
},
|
| 290 |
{
|
| 291 |
"epoch": 3.37,
|
| 292 |
+
"grad_norm": 22.133760452270508,
|
| 293 |
+
"learning_rate": 2.6423012855807538e-05,
|
| 294 |
+
"loss": 0.3239,
|
| 295 |
"step": 3700
|
| 296 |
},
|
| 297 |
{
|
| 298 |
"epoch": 3.46,
|
| 299 |
+
"grad_norm": 10.715078353881836,
|
| 300 |
+
"learning_rate": 2.6235677406422072e-05,
|
| 301 |
+
"loss": 0.3671,
|
| 302 |
"step": 3800
|
| 303 |
},
|
| 304 |
{
|
| 305 |
"epoch": 3.55,
|
| 306 |
+
"grad_norm": 7.383324146270752,
|
| 307 |
+
"learning_rate": 2.6044261507982356e-05,
|
| 308 |
+
"loss": 0.3623,
|
| 309 |
"step": 3900
|
| 310 |
},
|
| 311 |
{
|
| 312 |
"epoch": 3.64,
|
| 313 |
+
"grad_norm": 13.652631759643555,
|
| 314 |
+
"learning_rate": 2.5848834676797335e-05,
|
| 315 |
+
"loss": 0.382,
|
| 316 |
"step": 4000
|
| 317 |
},
|
| 318 |
{
|
| 319 |
"epoch": 3.73,
|
| 320 |
+
"grad_norm": 14.792743682861328,
|
| 321 |
+
"learning_rate": 2.5649467885822135e-05,
|
| 322 |
+
"loss": 0.3719,
|
| 323 |
"step": 4100
|
| 324 |
},
|
| 325 |
{
|
| 326 |
"epoch": 3.82,
|
| 327 |
+
"grad_norm": 2.3243019580841064,
|
| 328 |
+
"learning_rate": 2.5446233538882924e-05,
|
| 329 |
+
"loss": 0.3439,
|
| 330 |
"step": 4200
|
| 331 |
},
|
| 332 |
{
|
| 333 |
"epoch": 3.91,
|
| 334 |
+
"grad_norm": 39.48076248168945,
|
| 335 |
+
"learning_rate": 2.5239205444382054e-05,
|
| 336 |
+
"loss": 0.335,
|
| 337 |
"step": 4300
|
| 338 |
},
|
| 339 |
{
|
| 340 |
"epoch": 4.0,
|
| 341 |
+
"eval_accuracy": 0.9347912524850894,
|
| 342 |
+
"eval_loss": 0.2400086522102356,
|
| 343 |
+
"eval_runtime": 105.8322,
|
| 344 |
+
"eval_samples_per_second": 23.764,
|
| 345 |
+
"eval_steps_per_second": 1.493,
|
| 346 |
"step": 4396
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"epoch": 4.0,
|
| 350 |
+
"grad_norm": 13.311861038208008,
|
| 351 |
+
"learning_rate": 2.5028458788493163e-05,
|
| 352 |
+
"loss": 0.2904,
|
| 353 |
"step": 4400
|
| 354 |
},
|
| 355 |
{
|
| 356 |
"epoch": 4.09,
|
| 357 |
+
"grad_norm": 16.158748626708984,
|
| 358 |
+
"learning_rate": 2.4814070107855878e-05,
|
| 359 |
+
"loss": 0.3153,
|
| 360 |
"step": 4500
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 4.19,
|
| 364 |
+
"grad_norm": 22.555923461914062,
|
| 365 |
+
"learning_rate": 2.4596117261780113e-05,
|
| 366 |
+
"loss": 0.3329,
|
| 367 |
"step": 4600
|
| 368 |
},
|
| 369 |
{
|
| 370 |
"epoch": 4.28,
|
| 371 |
+
"grad_norm": 27.752666473388672,
|
| 372 |
+
"learning_rate": 2.4374679403969946e-05,
|
| 373 |
+
"loss": 0.3047,
|
| 374 |
"step": 4700
|
| 375 |
},
|
| 376 |
{
|
| 377 |
"epoch": 4.37,
|
| 378 |
+
"grad_norm": 20.464553833007812,
|
| 379 |
+
"learning_rate": 2.4149836953777488e-05,
|
| 380 |
+
"loss": 0.2973,
|
| 381 |
"step": 4800
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 4.46,
|
| 385 |
+
"grad_norm": 12.999048233032227,
|
| 386 |
+
"learning_rate": 2.3921671566997044e-05,
|
| 387 |
+
"loss": 0.2756,
|
| 388 |
"step": 4900
|
| 389 |
},
|
| 390 |
{
|
| 391 |
"epoch": 4.55,
|
| 392 |
+
"grad_norm": 24.010915756225586,
|
| 393 |
+
"learning_rate": 2.3690266106210284e-05,
|
| 394 |
+
"loss": 0.3108,
|
| 395 |
"step": 5000
|
| 396 |
},
|
| 397 |
{
|
| 398 |
"epoch": 4.64,
|
| 399 |
+
"grad_norm": 19.249290466308594,
|
| 400 |
+
"learning_rate": 2.345570461069312e-05,
|
| 401 |
+
"loss": 0.2996,
|
| 402 |
"step": 5100
|
| 403 |
},
|
| 404 |
{
|
| 405 |
"epoch": 4.73,
|
| 406 |
+
"grad_norm": 33.51617431640625,
|
| 407 |
+
"learning_rate": 2.3218072265895257e-05,
|
| 408 |
+
"loss": 0.3192,
|
| 409 |
"step": 5200
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"epoch": 4.82,
|
| 413 |
+
"grad_norm": 26.002756118774414,
|
| 414 |
+
"learning_rate": 2.297745537250347e-05,
|
| 415 |
+
"loss": 0.3396,
|
| 416 |
"step": 5300
|
| 417 |
},
|
| 418 |
{
|
| 419 |
"epoch": 4.91,
|
| 420 |
+
"grad_norm": 16.87458038330078,
|
| 421 |
+
"learning_rate": 2.2733941315099883e-05,
|
| 422 |
+
"loss": 0.3167,
|
| 423 |
"step": 5400
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"epoch": 5.0,
|
| 427 |
+
"eval_accuracy": 0.9339960238568589,
|
| 428 |
+
"eval_loss": 0.25986233353614807,
|
| 429 |
+
"eval_runtime": 105.6337,
|
| 430 |
+
"eval_samples_per_second": 23.809,
|
| 431 |
+
"eval_steps_per_second": 1.496,
|
| 432 |
"step": 5495
|
| 433 |
},
|
| 434 |
{
|
| 435 |
"epoch": 5.0,
|
| 436 |
+
"grad_norm": 16.456005096435547,
|
| 437 |
+
"learning_rate": 2.2487618530426604e-05,
|
| 438 |
+
"loss": 0.3225,
|
| 439 |
"step": 5500
|
| 440 |
},
|
| 441 |
{
|
| 442 |
"epoch": 5.1,
|
| 443 |
+
"grad_norm": 14.056130409240723,
|
| 444 |
+
"learning_rate": 2.2238576475268268e-05,
|
| 445 |
+
"loss": 0.256,
|
| 446 |
"step": 5600
|
| 447 |
},
|
| 448 |
{
|
| 449 |
"epoch": 5.19,
|
| 450 |
+
"grad_norm": 17.51475715637207,
|
| 451 |
+
"learning_rate": 2.1986905593964048e-05,
|
| 452 |
+
"loss": 0.2478,
|
| 453 |
"step": 5700
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 5.28,
|
| 457 |
+
"grad_norm": 23.06650161743164,
|
| 458 |
+
"learning_rate": 2.173269728556115e-05,
|
| 459 |
+
"loss": 0.2827,
|
| 460 |
"step": 5800
|
| 461 |
},
|
| 462 |
{
|
| 463 |
"epoch": 5.37,
|
| 464 |
+
"grad_norm": 24.29911231994629,
|
| 465 |
+
"learning_rate": 2.147604387062149e-05,
|
| 466 |
+
"loss": 0.2836,
|
| 467 |
"step": 5900
|
| 468 |
},
|
| 469 |
{
|
| 470 |
"epoch": 5.46,
|
| 471 |
+
"grad_norm": 16.115610122680664,
|
| 472 |
+
"learning_rate": 2.121703855769373e-05,
|
| 473 |
+
"loss": 0.271,
|
| 474 |
"step": 6000
|
| 475 |
},
|
| 476 |
{
|
| 477 |
"epoch": 5.55,
|
| 478 |
+
"grad_norm": 16.511001586914062,
|
| 479 |
+
"learning_rate": 2.0955775409462816e-05,
|
| 480 |
+
"loss": 0.2915,
|
| 481 |
"step": 6100
|
| 482 |
},
|
| 483 |
{
|
| 484 |
"epoch": 5.64,
|
| 485 |
+
"grad_norm": 34.321468353271484,
|
| 486 |
+
"learning_rate": 2.0692349308589375e-05,
|
| 487 |
+
"loss": 0.2576,
|
| 488 |
"step": 6200
|
| 489 |
},
|
| 490 |
{
|
| 491 |
"epoch": 5.73,
|
| 492 |
+
"grad_norm": 22.157716751098633,
|
| 493 |
+
"learning_rate": 2.042685592325123e-05,
|
| 494 |
+
"loss": 0.2954,
|
| 495 |
"step": 6300
|
| 496 |
},
|
| 497 |
{
|
| 498 |
"epoch": 5.82,
|
| 499 |
+
"grad_norm": 19.21451759338379,
|
| 500 |
+
"learning_rate": 2.0159391672399725e-05,
|
| 501 |
+
"loss": 0.2857,
|
| 502 |
"step": 6400
|
| 503 |
},
|
| 504 |
{
|
| 505 |
"epoch": 5.91,
|
| 506 |
+
"grad_norm": 28.460418701171875,
|
| 507 |
+
"learning_rate": 1.9890053690743337e-05,
|
| 508 |
+
"loss": 0.2703,
|
| 509 |
"step": 6500
|
| 510 |
},
|
| 511 |
{
|
| 512 |
"epoch": 6.0,
|
| 513 |
+
"eval_accuracy": 0.941948310139165,
|
| 514 |
+
"eval_loss": 0.24395686388015747,
|
| 515 |
+
"eval_runtime": 104.8687,
|
| 516 |
+
"eval_samples_per_second": 23.982,
|
| 517 |
+
"eval_steps_per_second": 1.507,
|
| 518 |
"step": 6594
|
| 519 |
},
|
| 520 |
{
|
| 521 |
"epoch": 6.01,
|
| 522 |
+
"grad_norm": 16.289432525634766,
|
| 523 |
+
"learning_rate": 1.961893979347137e-05,
|
| 524 |
+
"loss": 0.306,
|
| 525 |
"step": 6600
|
| 526 |
},
|
| 527 |
{
|
| 528 |
"epoch": 6.1,
|
| 529 |
+
"grad_norm": 27.070125579833984,
|
| 530 |
+
"learning_rate": 1.934614844073054e-05,
|
| 531 |
+
"loss": 0.2425,
|
| 532 |
"step": 6700
|
| 533 |
},
|
| 534 |
{
|
| 535 |
"epoch": 6.19,
|
| 536 |
+
"grad_norm": 14.10284423828125,
|
| 537 |
+
"learning_rate": 1.9071778701867247e-05,
|
| 538 |
+
"loss": 0.2729,
|
| 539 |
"step": 6800
|
| 540 |
},
|
| 541 |
{
|
| 542 |
"epoch": 6.28,
|
| 543 |
+
"grad_norm": 8.3997220993042,
|
| 544 |
+
"learning_rate": 1.879593021944875e-05,
|
| 545 |
+
"loss": 0.2816,
|
| 546 |
"step": 6900
|
| 547 |
},
|
| 548 |
{
|
| 549 |
"epoch": 6.37,
|
| 550 |
+
"grad_norm": 8.656745910644531,
|
| 551 |
+
"learning_rate": 1.851870317307602e-05,
|
| 552 |
+
"loss": 0.2411,
|
| 553 |
"step": 7000
|
| 554 |
},
|
| 555 |
{
|
| 556 |
"epoch": 6.46,
|
| 557 |
+
"grad_norm": 1.0716943740844727,
|
| 558 |
+
"learning_rate": 1.8240198243001623e-05,
|
| 559 |
+
"loss": 0.2689,
|
| 560 |
"step": 7100
|
| 561 |
},
|
| 562 |
{
|
| 563 |
"epoch": 6.55,
|
| 564 |
+
"grad_norm": 3.0549349784851074,
|
| 565 |
+
"learning_rate": 1.796051657356582e-05,
|
| 566 |
+
"loss": 0.2435,
|
| 567 |
"step": 7200
|
| 568 |
},
|
| 569 |
{
|
| 570 |
"epoch": 6.64,
|
| 571 |
+
"grad_norm": 23.518062591552734,
|
| 572 |
+
"learning_rate": 1.7679759736464045e-05,
|
| 573 |
+
"loss": 0.2346,
|
| 574 |
"step": 7300
|
| 575 |
},
|
| 576 |
{
|
| 577 |
"epoch": 6.73,
|
| 578 |
+
"grad_norm": 31.476299285888672,
|
| 579 |
+
"learning_rate": 1.739802969385923e-05,
|
| 580 |
+
"loss": 0.2478,
|
| 581 |
"step": 7400
|
| 582 |
},
|
| 583 |
{
|
| 584 |
"epoch": 6.82,
|
| 585 |
+
"grad_norm": 14.344544410705566,
|
| 586 |
+
"learning_rate": 1.711542876135233e-05,
|
| 587 |
+
"loss": 0.2377,
|
| 588 |
"step": 7500
|
| 589 |
},
|
| 590 |
{
|
| 591 |
"epoch": 6.92,
|
| 592 |
+
"grad_norm": 0.6573715209960938,
|
| 593 |
+
"learning_rate": 1.6832059570824453e-05,
|
| 594 |
+
"loss": 0.2638,
|
| 595 |
"step": 7600
|
| 596 |
},
|
| 597 |
{
|
| 598 |
"epoch": 7.0,
|
| 599 |
+
"eval_accuracy": 0.9407554671968191,
|
| 600 |
+
"eval_loss": 0.2496492713689804,
|
| 601 |
+
"eval_runtime": 104.4088,
|
| 602 |
+
"eval_samples_per_second": 24.088,
|
| 603 |
+
"eval_steps_per_second": 1.513,
|
| 604 |
"step": 7693
|
| 605 |
},
|
| 606 |
{
|
| 607 |
"epoch": 7.01,
|
| 608 |
+
"grad_norm": 33.705074310302734,
|
| 609 |
+
"learning_rate": 1.654802503316416e-05,
|
| 610 |
+
"loss": 0.2077,
|
| 611 |
"step": 7700
|
| 612 |
},
|
| 613 |
{
|
| 614 |
"epoch": 7.1,
|
| 615 |
+
"grad_norm": 33.48544692993164,
|
| 616 |
+
"learning_rate": 1.6263428300893422e-05,
|
| 617 |
+
"loss": 0.2398,
|
| 618 |
"step": 7800
|
| 619 |
},
|
| 620 |
{
|
| 621 |
"epoch": 7.19,
|
| 622 |
+
"grad_norm": 18.51409149169922,
|
| 623 |
+
"learning_rate": 1.597837273070585e-05,
|
| 624 |
+
"loss": 0.217,
|
| 625 |
"step": 7900
|
| 626 |
},
|
| 627 |
{
|
| 628 |
"epoch": 7.28,
|
| 629 |
+
"grad_norm": 8.902990341186523,
|
| 630 |
+
"learning_rate": 1.5692961845930704e-05,
|
| 631 |
+
"loss": 0.2538,
|
| 632 |
"step": 8000
|
| 633 |
},
|
| 634 |
{
|
| 635 |
"epoch": 7.37,
|
| 636 |
+
"grad_norm": 19.85183334350586,
|
| 637 |
+
"learning_rate": 1.540729929893649e-05,
|
| 638 |
+
"loss": 0.2362,
|
| 639 |
"step": 8100
|
| 640 |
},
|
| 641 |
{
|
| 642 |
"epoch": 7.46,
|
| 643 |
+
"grad_norm": 8.387295722961426,
|
| 644 |
+
"learning_rate": 1.51214888334876e-05,
|
| 645 |
+
"loss": 0.2415,
|
| 646 |
"step": 8200
|
| 647 |
},
|
| 648 |
{
|
| 649 |
"epoch": 7.55,
|
| 650 |
+
"grad_norm": 20.70574378967285,
|
| 651 |
+
"learning_rate": 1.4835634247067834e-05,
|
| 652 |
+
"loss": 0.2109,
|
| 653 |
"step": 8300
|
| 654 |
},
|
| 655 |
{
|
| 656 |
"epoch": 7.64,
|
| 657 |
+
"grad_norm": 18.571918487548828,
|
| 658 |
+
"learning_rate": 1.454983935318433e-05,
|
| 659 |
+
"loss": 0.242,
|
| 660 |
"step": 8400
|
| 661 |
},
|
| 662 |
{
|
| 663 |
"epoch": 7.73,
|
| 664 |
+
"grad_norm": 15.444602012634277,
|
| 665 |
+
"learning_rate": 1.426420794366578e-05,
|
| 666 |
+
"loss": 0.1971,
|
| 667 |
"step": 8500
|
| 668 |
},
|
| 669 |
{
|
| 670 |
"epoch": 7.83,
|
| 671 |
+
"grad_norm": 10.603649139404297,
|
| 672 |
+
"learning_rate": 1.3978843750968413e-05,
|
| 673 |
+
"loss": 0.2519,
|
| 674 |
"step": 8600
|
| 675 |
},
|
| 676 |
{
|
| 677 |
"epoch": 7.92,
|
| 678 |
+
"grad_norm": 1.8435286283493042,
|
| 679 |
+
"learning_rate": 1.3693850410503614e-05,
|
| 680 |
+
"loss": 0.1938,
|
| 681 |
"step": 8700
|
| 682 |
},
|
| 683 |
{
|
| 684 |
"epoch": 8.0,
|
| 685 |
+
"eval_accuracy": 0.9431411530815109,
|
| 686 |
+
"eval_loss": 0.23655731976032257,
|
| 687 |
+
"eval_runtime": 104.2878,
|
| 688 |
+
"eval_samples_per_second": 24.116,
|
| 689 |
+
"eval_steps_per_second": 1.515,
|
| 690 |
"step": 8792
|
| 691 |
},
|
| 692 |
{
|
| 693 |
"epoch": 8.01,
|
| 694 |
+
"grad_norm": 16.798791885375977,
|
| 695 |
+
"learning_rate": 1.3409331423000765e-05,
|
| 696 |
+
"loss": 0.2356,
|
| 697 |
"step": 8800
|
| 698 |
},
|
| 699 |
{
|
| 700 |
"epoch": 8.1,
|
| 701 |
+
"grad_norm": 18.694393157958984,
|
| 702 |
+
"learning_rate": 1.3125390116918962e-05,
|
| 703 |
+
"loss": 0.2057,
|
| 704 |
"step": 8900
|
| 705 |
},
|
| 706 |
{
|
| 707 |
"epoch": 8.19,
|
| 708 |
+
"grad_norm": 2.4685895442962646,
|
| 709 |
+
"learning_rate": 1.2842129610921378e-05,
|
| 710 |
+
"loss": 0.1852,
|
| 711 |
"step": 9000
|
| 712 |
},
|
| 713 |
{
|
| 714 |
"epoch": 8.28,
|
| 715 |
+
"grad_norm": 14.801736831665039,
|
| 716 |
+
"learning_rate": 1.255965277642572e-05,
|
| 717 |
+
"loss": 0.1627,
|
| 718 |
"step": 9100
|
| 719 |
},
|
| 720 |
{
|
| 721 |
"epoch": 8.37,
|
| 722 |
+
"grad_norm": 0.14111284911632538,
|
| 723 |
+
"learning_rate": 1.2278062200244565e-05,
|
| 724 |
+
"loss": 0.2274,
|
| 725 |
"step": 9200
|
| 726 |
},
|
| 727 |
{
|
| 728 |
"epoch": 8.46,
|
| 729 |
+
"grad_norm": 2.3665616512298584,
|
| 730 |
+
"learning_rate": 1.1997460147328984e-05,
|
| 731 |
+
"loss": 0.19,
|
| 732 |
"step": 9300
|
| 733 |
},
|
| 734 |
{
|
| 735 |
"epoch": 8.55,
|
| 736 |
+
"grad_norm": 10.016236305236816,
|
| 737 |
+
"learning_rate": 1.1717948523629107e-05,
|
| 738 |
+
"loss": 0.1982,
|
| 739 |
"step": 9400
|
| 740 |
},
|
| 741 |
{
|
| 742 |
"epoch": 8.64,
|
| 743 |
+
"grad_norm": 9.423545837402344,
|
| 744 |
+
"learning_rate": 1.1439628839085037e-05,
|
| 745 |
+
"loss": 0.2109,
|
| 746 |
"step": 9500
|
| 747 |
},
|
| 748 |
{
|
| 749 |
"epoch": 8.74,
|
| 750 |
+
"grad_norm": 7.491578578948975,
|
| 751 |
+
"learning_rate": 1.1162602170761611e-05,
|
| 752 |
+
"loss": 0.2033,
|
| 753 |
"step": 9600
|
| 754 |
},
|
| 755 |
{
|
| 756 |
"epoch": 8.83,
|
| 757 |
+
"grad_norm": 1.5837846994400024,
|
| 758 |
+
"learning_rate": 1.0886969126140309e-05,
|
| 759 |
+
"loss": 0.2583,
|
| 760 |
"step": 9700
|
| 761 |
},
|
| 762 |
{
|
| 763 |
"epoch": 8.92,
|
| 764 |
+
"grad_norm": 30.90834617614746,
|
| 765 |
+
"learning_rate": 1.0612829806581792e-05,
|
| 766 |
+
"loss": 0.1789,
|
| 767 |
"step": 9800
|
| 768 |
},
|
| 769 |
{
|
| 770 |
"epoch": 9.0,
|
| 771 |
+
"eval_accuracy": 0.9487077534791253,
|
| 772 |
+
"eval_loss": 0.23529192805290222,
|
| 773 |
+
"eval_runtime": 104.3958,
|
| 774 |
+
"eval_samples_per_second": 24.091,
|
| 775 |
+
"eval_steps_per_second": 1.513,
|
| 776 |
"step": 9891
|
| 777 |
},
|
| 778 |
{
|
| 779 |
"epoch": 9.01,
|
| 780 |
+
"grad_norm": 9.547430038452148,
|
| 781 |
+
"learning_rate": 1.0340283770972167e-05,
|
| 782 |
+
"loss": 0.1811,
|
| 783 |
"step": 9900
|
| 784 |
},
|
| 785 |
{
|
| 786 |
"epoch": 9.1,
|
| 787 |
+
"grad_norm": 3.7667858600616455,
|
| 788 |
+
"learning_rate": 1.0069429999566298e-05,
|
| 789 |
+
"loss": 0.1631,
|
| 790 |
"step": 10000
|
| 791 |
},
|
| 792 |
{
|
| 793 |
"epoch": 9.19,
|
| 794 |
+
"grad_norm": 35.338844299316406,
|
| 795 |
+
"learning_rate": 9.800366858041242e-06,
|
| 796 |
+
"loss": 0.1908,
|
| 797 |
"step": 10100
|
| 798 |
},
|
| 799 |
{
|
| 800 |
"epoch": 9.28,
|
| 801 |
+
"grad_norm": 19.66462516784668,
|
| 802 |
+
"learning_rate": 9.533192061772919e-06,
|
| 803 |
+
"loss": 0.1571,
|
| 804 |
"step": 10200
|
| 805 |
},
|
| 806 |
{
|
| 807 |
"epoch": 9.37,
|
| 808 |
+
"grad_norm": 9.39445686340332,
|
| 809 |
+
"learning_rate": 9.268002640348889e-06,
|
| 810 |
+
"loss": 0.1904,
|
| 811 |
"step": 10300
|
| 812 |
},
|
| 813 |
{
|
| 814 |
"epoch": 9.46,
|
| 815 |
+
"grad_norm": 4.144321441650391,
|
| 816 |
+
"learning_rate": 9.004894902330242e-06,
|
| 817 |
+
"loss": 0.1559,
|
| 818 |
"step": 10400
|
| 819 |
},
|
| 820 |
{
|
| 821 |
"epoch": 9.55,
|
| 822 |
+
"grad_norm": 10.969382286071777,
|
| 823 |
+
"learning_rate": 8.743964400275304e-06,
|
| 824 |
+
"loss": 0.2004,
|
| 825 |
"step": 10500
|
| 826 |
},
|
| 827 |
{
|
| 828 |
"epoch": 9.65,
|
| 829 |
+
"grad_norm": 24.618282318115234,
|
| 830 |
+
"learning_rate": 8.485305896037929e-06,
|
| 831 |
+
"loss": 0.2064,
|
| 832 |
"step": 10600
|
| 833 |
},
|
| 834 |
{
|
| 835 |
"epoch": 9.74,
|
| 836 |
+
"grad_norm": 25.1768856048584,
|
| 837 |
+
"learning_rate": 8.229013326352934e-06,
|
| 838 |
+
"loss": 0.1981,
|
| 839 |
"step": 10700
|
| 840 |
},
|
| 841 |
{
|
| 842 |
"epoch": 9.83,
|
| 843 |
+
"grad_norm": 10.52382755279541,
|
| 844 |
+
"learning_rate": 7.975179768721187e-06,
|
| 845 |
+
"loss": 0.2,
|
| 846 |
"step": 10800
|
| 847 |
},
|
| 848 |
{
|
| 849 |
"epoch": 9.92,
|
| 850 |
+
"grad_norm": 15.742509841918945,
|
| 851 |
+
"learning_rate": 7.723897407606758e-06,
|
| 852 |
+
"loss": 0.1738,
|
| 853 |
"step": 10900
|
| 854 |
},
|
| 855 |
{
|
| 856 |
"epoch": 10.0,
|
| 857 |
+
"eval_accuracy": 0.9499005964214712,
|
| 858 |
+
"eval_loss": 0.237999826669693,
|
| 859 |
+
"eval_runtime": 107.0756,
|
| 860 |
+
"eval_samples_per_second": 23.488,
|
| 861 |
+
"eval_steps_per_second": 1.476,
|
| 862 |
"step": 10990
|
| 863 |
},
|
| 864 |
{
|
| 865 |
"epoch": 10.01,
|
| 866 |
+
"grad_norm": 0.739620566368103,
|
| 867 |
+
"learning_rate": 7.475257500958387e-06,
|
| 868 |
+
"loss": 0.1941,
|
| 869 |
"step": 11000
|
| 870 |
},
|
| 871 |
{
|
| 872 |
"epoch": 10.1,
|
| 873 |
+
"grad_norm": 15.124515533447266,
|
| 874 |
+
"learning_rate": 7.229350347067426e-06,
|
| 875 |
+
"loss": 0.1358,
|
| 876 |
"step": 11100
|
| 877 |
},
|
| 878 |
{
|
| 879 |
"epoch": 10.19,
|
| 880 |
+
"grad_norm": 16.16267204284668,
|
| 881 |
+
"learning_rate": 6.986265251774287e-06,
|
| 882 |
+
"loss": 0.1634,
|
| 883 |
"step": 11200
|
| 884 |
},
|
| 885 |
{
|
| 886 |
"epoch": 10.28,
|
| 887 |
+
"grad_norm": 9.51611614227295,
|
| 888 |
+
"learning_rate": 6.746090496035372e-06,
|
| 889 |
+
"loss": 0.1561,
|
| 890 |
"step": 11300
|
| 891 |
},
|
| 892 |
{
|
| 893 |
"epoch": 10.37,
|
| 894 |
+
"grad_norm": 17.76508140563965,
|
| 895 |
+
"learning_rate": 6.508913303862144e-06,
|
| 896 |
+
"loss": 0.1767,
|
| 897 |
"step": 11400
|
| 898 |
},
|
| 899 |
{
|
| 900 |
"epoch": 10.46,
|
| 901 |
+
"grad_norm": 9.271286964416504,
|
| 902 |
+
"learning_rate": 6.274819810644087e-06,
|
| 903 |
+
"loss": 0.1907,
|
| 904 |
"step": 11500
|
| 905 |
},
|
| 906 |
{
|
| 907 |
"epoch": 10.56,
|
| 908 |
+
"grad_norm": 47.73799514770508,
|
| 909 |
+
"learning_rate": 6.043895031866995e-06,
|
| 910 |
+
"loss": 0.1628,
|
| 911 |
"step": 11600
|
| 912 |
},
|
| 913 |
{
|
| 914 |
"epoch": 10.65,
|
| 915 |
+
"grad_norm": 31.59560775756836,
|
| 916 |
+
"learning_rate": 5.8162228322380155e-06,
|
| 917 |
+
"loss": 0.1618,
|
| 918 |
"step": 11700
|
| 919 |
},
|
| 920 |
{
|
| 921 |
"epoch": 10.74,
|
| 922 |
+
"grad_norm": 8.150809288024902,
|
| 923 |
+
"learning_rate": 5.591885895228557e-06,
|
| 924 |
+
"loss": 0.1795,
|
| 925 |
"step": 11800
|
| 926 |
},
|
| 927 |
{
|
| 928 |
"epoch": 10.83,
|
| 929 |
+
"grad_norm": 9.975177764892578,
|
| 930 |
+
"learning_rate": 5.370965693046249e-06,
|
| 931 |
+
"loss": 0.1705,
|
| 932 |
"step": 11900
|
| 933 |
},
|
| 934 |
{
|
| 935 |
"epoch": 10.92,
|
| 936 |
+
"grad_norm": 39.83053207397461,
|
| 937 |
+
"learning_rate": 5.153542457046737e-06,
|
| 938 |
+
"loss": 0.1924,
|
| 939 |
"step": 12000
|
| 940 |
},
|
| 941 |
{
|
| 942 |
"epoch": 11.0,
|
| 943 |
+
"eval_accuracy": 0.9463220675944334,
|
| 944 |
+
"eval_loss": 0.24584931135177612,
|
| 945 |
+
"eval_runtime": 105.078,
|
| 946 |
+
"eval_samples_per_second": 23.935,
|
| 947 |
+
"eval_steps_per_second": 1.504,
|
| 948 |
"step": 12089
|
| 949 |
},
|
| 950 |
{
|
| 951 |
"epoch": 11.01,
|
| 952 |
+
"grad_norm": 0.06365140527486801,
|
| 953 |
+
"learning_rate": 4.9396951485961885e-06,
|
| 954 |
+
"loss": 0.1239,
|
| 955 |
"step": 12100
|
| 956 |
},
|
| 957 |
{
|
| 958 |
"epoch": 11.1,
|
| 959 |
+
"grad_norm": 7.116461277008057,
|
| 960 |
+
"learning_rate": 4.729501430394933e-06,
|
| 961 |
+
"loss": 0.1739,
|
| 962 |
"step": 12200
|
| 963 |
},
|
| 964 |
{
|
| 965 |
"epoch": 11.19,
|
| 966 |
+
"grad_norm": 0.722091019153595,
|
| 967 |
+
"learning_rate": 4.523037638272822e-06,
|
| 968 |
+
"loss": 0.1611,
|
| 969 |
"step": 12300
|
| 970 |
},
|
| 971 |
{
|
| 972 |
"epoch": 11.28,
|
| 973 |
+
"grad_norm": 15.62628173828125,
|
| 974 |
+
"learning_rate": 4.320378753466392e-06,
|
| 975 |
+
"loss": 0.1386,
|
| 976 |
"step": 12400
|
| 977 |
},
|
| 978 |
{
|
| 979 |
"epoch": 11.37,
|
| 980 |
+
"grad_norm": 29.914321899414062,
|
| 981 |
+
"learning_rate": 4.121598375388027e-06,
|
| 982 |
+
"loss": 0.129,
|
| 983 |
"step": 12500
|
| 984 |
},
|
| 985 |
{
|
| 986 |
"epoch": 11.46,
|
| 987 |
+
"grad_norm": 16.476482391357422,
|
| 988 |
+
"learning_rate": 3.926768694896931e-06,
|
| 989 |
+
"loss": 0.1358,
|
| 990 |
"step": 12600
|
| 991 |
},
|
| 992 |
{
|
| 993 |
"epoch": 11.56,
|
| 994 |
+
"grad_norm": 13.462120056152344,
|
| 995 |
+
"learning_rate": 3.7359604680816612e-06,
|
| 996 |
+
"loss": 0.151,
|
| 997 |
"step": 12700
|
| 998 |
},
|
| 999 |
{
|
| 1000 |
"epoch": 11.65,
|
| 1001 |
+
"grad_norm": 19.780019760131836,
|
| 1002 |
+
"learning_rate": 3.5492429905636857e-06,
|
| 1003 |
+
"loss": 0.1715,
|
| 1004 |
"step": 12800
|
| 1005 |
},
|
| 1006 |
{
|
| 1007 |
"epoch": 11.74,
|
| 1008 |
+
"grad_norm": 2.3141283988952637,
|
| 1009 |
+
"learning_rate": 3.3666840723314145e-06,
|
| 1010 |
+
"loss": 0.1304,
|
| 1011 |
"step": 12900
|
| 1012 |
},
|
| 1013 |
{
|
| 1014 |
"epoch": 11.83,
|
| 1015 |
+
"grad_norm": 14.787359237670898,
|
| 1016 |
+
"learning_rate": 3.188350013113671e-06,
|
| 1017 |
+
"loss": 0.1528,
|
| 1018 |
"step": 13000
|
| 1019 |
},
|
| 1020 |
{
|
| 1021 |
"epoch": 11.92,
|
| 1022 |
+
"grad_norm": 20.494741439819336,
|
| 1023 |
+
"learning_rate": 3.014305578301712e-06,
|
| 1024 |
+
"loss": 0.1628,
|
| 1025 |
"step": 13100
|
| 1026 |
},
|
| 1027 |
{
|
| 1028 |
"epoch": 12.0,
|
| 1029 |
+
"eval_accuracy": 0.9491053677932405,
|
| 1030 |
+
"eval_loss": 0.2434205859899521,
|
| 1031 |
+
"eval_runtime": 105.1912,
|
| 1032 |
+
"eval_samples_per_second": 23.909,
|
| 1033 |
+
"eval_steps_per_second": 1.502,
|
| 1034 |
"step": 13188
|
| 1035 |
},
|
| 1036 |
{
|
| 1037 |
"epoch": 12.01,
|
| 1038 |
+
"grad_norm": 11.916013717651367,
|
| 1039 |
+
"learning_rate": 2.8446139754284486e-06,
|
| 1040 |
+
"loss": 0.1375,
|
| 1041 |
"step": 13200
|
| 1042 |
},
|
| 1043 |
{
|
| 1044 |
"epoch": 12.1,
|
| 1045 |
+
"grad_norm": 0.6161535978317261,
|
| 1046 |
+
"learning_rate": 2.6793368312134275e-06,
|
| 1047 |
+
"loss": 0.1324,
|
| 1048 |
"step": 13300
|
| 1049 |
},
|
| 1050 |
{
|
| 1051 |
"epoch": 12.19,
|
| 1052 |
+
"grad_norm": 21.261964797973633,
|
| 1053 |
+
"learning_rate": 2.5185341691819315e-06,
|
| 1054 |
+
"loss": 0.1538,
|
| 1055 |
"step": 13400
|
| 1056 |
},
|
| 1057 |
{
|
| 1058 |
"epoch": 12.28,
|
| 1059 |
+
"grad_norm": 1.320718765258789,
|
| 1060 |
+
"learning_rate": 2.36226438786627e-06,
|
| 1061 |
+
"loss": 0.1647,
|
| 1062 |
"step": 13500
|
| 1063 |
},
|
| 1064 |
{
|
| 1065 |
"epoch": 12.37,
|
| 1066 |
+
"grad_norm": 3.367286205291748,
|
| 1067 |
+
"learning_rate": 2.210584239597296e-06,
|
| 1068 |
+
"loss": 0.1459,
|
| 1069 |
"step": 13600
|
| 1070 |
},
|
| 1071 |
{
|
| 1072 |
"epoch": 12.47,
|
| 1073 |
+
"grad_norm": 25.336097717285156,
|
| 1074 |
+
"learning_rate": 2.063548809893678e-06,
|
| 1075 |
+
"loss": 0.1299,
|
| 1076 |
"step": 13700
|
| 1077 |
},
|
| 1078 |
{
|
| 1079 |
"epoch": 12.56,
|
| 1080 |
+
"grad_norm": 29.0968074798584,
|
| 1081 |
+
"learning_rate": 1.9212114974565664e-06,
|
| 1082 |
+
"loss": 0.15,
|
| 1083 |
"step": 13800
|
| 1084 |
},
|
| 1085 |
{
|
| 1086 |
"epoch": 12.65,
|
| 1087 |
+
"grad_norm": 10.785637855529785,
|
| 1088 |
+
"learning_rate": 1.783623994776848e-06,
|
| 1089 |
+
"loss": 0.122,
|
| 1090 |
"step": 13900
|
| 1091 |
},
|
| 1092 |
{
|
| 1093 |
"epoch": 12.74,
|
| 1094 |
+
"grad_norm": 6.101187229156494,
|
| 1095 |
+
"learning_rate": 1.6508362693620305e-06,
|
| 1096 |
+
"loss": 0.1714,
|
| 1097 |
"step": 14000
|
| 1098 |
},
|
| 1099 |
{
|
| 1100 |
"epoch": 12.83,
|
| 1101 |
+
"grad_norm": 0.2466667890548706,
|
| 1102 |
+
"learning_rate": 1.5228965455896054e-06,
|
| 1103 |
+
"loss": 0.1639,
|
| 1104 |
"step": 14100
|
| 1105 |
},
|
| 1106 |
{
|
| 1107 |
"epoch": 12.92,
|
| 1108 |
+
"grad_norm": 17.598079681396484,
|
| 1109 |
+
"learning_rate": 1.3998512871934415e-06,
|
| 1110 |
+
"loss": 0.1431,
|
| 1111 |
"step": 14200
|
| 1112 |
},
|
| 1113 |
{
|
| 1114 |
"epoch": 13.0,
|
| 1115 |
+
"eval_accuracy": 0.9499005964214712,
|
| 1116 |
+
"eval_loss": 0.23904123902320862,
|
| 1117 |
+
"eval_runtime": 105.0334,
|
| 1118 |
+
"eval_samples_per_second": 23.945,
|
| 1119 |
+
"eval_steps_per_second": 1.504,
|
| 1120 |
"step": 14287
|
| 1121 |
},
|
| 1122 |
{
|
| 1123 |
"epoch": 13.01,
|
| 1124 |
+
"grad_norm": 4.807325839996338,
|
| 1125 |
+
"learning_rate": 1.2817451803896063e-06,
|
| 1126 |
+
"loss": 0.1444,
|
| 1127 |
"step": 14300
|
| 1128 |
},
|
| 1129 |
{
|
| 1130 |
"epoch": 13.1,
|
| 1131 |
+
"grad_norm": 0.20366211235523224,
|
| 1132 |
+
"learning_rate": 1.1686211176477208e-06,
|
| 1133 |
+
"loss": 0.1555,
|
| 1134 |
"step": 14400
|
| 1135 |
},
|
| 1136 |
{
|
| 1137 |
"epoch": 13.19,
|
| 1138 |
+
"grad_norm": 16.46355628967285,
|
| 1139 |
+
"learning_rate": 1.0605201821137417e-06,
|
| 1140 |
+
"loss": 0.1512,
|
| 1141 |
"step": 14500
|
| 1142 |
},
|
| 1143 |
{
|
| 1144 |
"epoch": 13.28,
|
| 1145 |
+
"grad_norm": 11.976471900939941,
|
| 1146 |
+
"learning_rate": 9.57481632689845e-07,
|
| 1147 |
+
"loss": 0.1741,
|
| 1148 |
"step": 14600
|
| 1149 |
},
|
| 1150 |
{
|
| 1151 |
"epoch": 13.38,
|
| 1152 |
+
"grad_norm": 27.499574661254883,
|
| 1153 |
+
"learning_rate": 8.595428897768071e-07,
|
| 1154 |
+
"loss": 0.1509,
|
| 1155 |
"step": 14700
|
| 1156 |
},
|
| 1157 |
{
|
| 1158 |
"epoch": 13.47,
|
| 1159 |
+
"grad_norm": 2.7120893001556396,
|
| 1160 |
+
"learning_rate": 7.66739521684079e-07,
|
| 1161 |
+
"loss": 0.1601,
|
| 1162 |
"step": 14800
|
| 1163 |
},
|
| 1164 |
{
|
| 1165 |
"epoch": 13.56,
|
| 1166 |
+
"grad_norm": 37.196876525878906,
|
| 1167 |
+
"learning_rate": 6.791052317124824e-07,
|
| 1168 |
+
"loss": 0.131,
|
| 1169 |
"step": 14900
|
| 1170 |
},
|
| 1171 |
{
|
| 1172 |
"epoch": 13.65,
|
| 1173 |
+
"grad_norm": 9.931727409362793,
|
| 1174 |
+
"learning_rate": 5.966718459142196e-07,
|
| 1175 |
+
"loss": 0.1411,
|
| 1176 |
"step": 15000
|
| 1177 |
},
|
| 1178 |
{
|
| 1179 |
"epoch": 13.74,
|
| 1180 |
+
"grad_norm": 10.333179473876953,
|
| 1181 |
+
"learning_rate": 5.194693015346313e-07,
|
| 1182 |
+
"loss": 0.1452,
|
| 1183 |
"step": 15100
|
| 1184 |
},
|
| 1185 |
{
|
| 1186 |
"epoch": 13.83,
|
| 1187 |
+
"grad_norm": 4.551497936248779,
|
| 1188 |
+
"learning_rate": 4.4752563613992993e-07,
|
| 1189 |
+
"loss": 0.142,
|
| 1190 |
"step": 15200
|
| 1191 |
},
|
| 1192 |
{
|
| 1193 |
"epoch": 13.92,
|
| 1194 |
+
"grad_norm": 19.9360408782959,
|
| 1195 |
+
"learning_rate": 3.808669774348167e-07,
|
| 1196 |
+
"loss": 0.1432,
|
| 1197 |
"step": 15300
|
| 1198 |
},
|
| 1199 |
{
|
| 1200 |
"epoch": 14.0,
|
| 1201 |
+
"eval_accuracy": 0.9502982107355865,
|
| 1202 |
+
"eval_loss": 0.23912423849105835,
|
| 1203 |
+
"eval_runtime": 104.6114,
|
| 1204 |
+
"eval_samples_per_second": 24.041,
|
| 1205 |
+
"eval_steps_per_second": 1.51,
|
| 1206 |
"step": 15386
|
| 1207 |
},
|
| 1208 |
{
|
| 1209 |
"epoch": 14.01,
|
| 1210 |
+
"grad_norm": 10.347683906555176,
|
| 1211 |
+
"learning_rate": 3.195175337737194e-07,
|
| 1212 |
+
"loss": 0.1464,
|
| 1213 |
"step": 15400
|
| 1214 |
},
|
| 1215 |
{
|
| 1216 |
"epoch": 14.1,
|
| 1217 |
+
"grad_norm": 14.291678428649902,
|
| 1218 |
+
"learning_rate": 2.6349958536906303e-07,
|
| 1219 |
+
"loss": 0.1387,
|
| 1220 |
"step": 15500
|
| 1221 |
},
|
| 1222 |
{
|
| 1223 |
"epoch": 14.19,
|
| 1224 |
+
"grad_norm": 5.145290851593018,
|
| 1225 |
+
"learning_rate": 2.1283347619979243e-07,
|
| 1226 |
+
"loss": 0.1493,
|
| 1227 |
"step": 15600
|
| 1228 |
},
|
| 1229 |
{
|
| 1230 |
"epoch": 14.29,
|
| 1231 |
+
"grad_norm": 9.14526653289795,
|
| 1232 |
+
"learning_rate": 1.6753760662307217e-07,
|
| 1233 |
+
"loss": 0.1488,
|
| 1234 |
"step": 15700
|
| 1235 |
},
|
| 1236 |
{
|
| 1237 |
"epoch": 14.38,
|
| 1238 |
+
"grad_norm": 0.8332547545433044,
|
| 1239 |
+
"learning_rate": 1.2762842669184205e-07,
|
| 1240 |
+
"loss": 0.1489,
|
| 1241 |
"step": 15800
|
| 1242 |
},
|
| 1243 |
{
|
| 1244 |
"epoch": 14.47,
|
| 1245 |
+
"grad_norm": 5.39556884765625,
|
| 1246 |
+
"learning_rate": 9.312043018067762e-08,
|
| 1247 |
+
"loss": 0.1606,
|
| 1248 |
"step": 15900
|
| 1249 |
},
|
| 1250 |
{
|
| 1251 |
"epoch": 14.56,
|
| 1252 |
+
"grad_norm": 26.057680130004883,
|
| 1253 |
+
"learning_rate": 6.402614932209228e-08,
|
| 1254 |
+
"loss": 0.1411,
|
| 1255 |
"step": 16000
|
| 1256 |
},
|
| 1257 |
{
|
| 1258 |
"epoch": 14.65,
|
| 1259 |
+
"grad_norm": 33.924278259277344,
|
| 1260 |
+
"learning_rate": 4.035615025522632e-08,
|
| 1261 |
+
"loss": 0.1347,
|
| 1262 |
"step": 16100
|
| 1263 |
},
|
| 1264 |
{
|
| 1265 |
"epoch": 14.74,
|
| 1266 |
+
"grad_norm": 1.6821552515029907,
|
| 1267 |
+
"learning_rate": 2.211902918855313e-08,
|
| 1268 |
+
"loss": 0.1498,
|
| 1269 |
"step": 16200
|
| 1270 |
},
|
| 1271 |
{
|
| 1272 |
"epoch": 14.83,
|
| 1273 |
+
"grad_norm": 50.973289489746094,
|
| 1274 |
+
"learning_rate": 9.321409277999738e-09,
|
| 1275 |
+
"loss": 0.1481,
|
| 1276 |
"step": 16300
|
| 1277 |
},
|
| 1278 |
{
|
| 1279 |
"epoch": 14.92,
|
| 1280 |
+
"grad_norm": 7.030074119567871,
|
| 1281 |
+
"learning_rate": 1.9679382216242213e-09,
|
| 1282 |
+
"loss": 0.1297,
|
| 1283 |
"step": 16400
|
| 1284 |
},
|
| 1285 |
{
|
| 1286 |
"epoch": 15.0,
|
| 1287 |
+
"eval_accuracy": 0.9499005964214712,
|
| 1288 |
+
"eval_loss": 0.23844709992408752,
|
| 1289 |
+
"eval_runtime": 105.2757,
|
| 1290 |
+
"eval_samples_per_second": 23.89,
|
| 1291 |
+
"eval_steps_per_second": 1.501,
|
| 1292 |
"step": 16485
|
| 1293 |
},
|
| 1294 |
{
|
| 1295 |
"epoch": 15.0,
|
| 1296 |
"step": 16485,
|
| 1297 |
"total_flos": 6.140249030814106e+19,
|
| 1298 |
+
"train_loss": 0.2960004877096818,
|
| 1299 |
+
"train_runtime": 28237.408,
|
| 1300 |
+
"train_samples_per_second": 9.339,
|
| 1301 |
+
"train_steps_per_second": 0.584
|
| 1302 |
}
|
| 1303 |
],
|
| 1304 |
"logging_steps": 100,
|