Upload folder using huggingface_hub
Browse files- model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +1996 -376
- training_args.bin +1 -1
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343263964
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1b10166652d148fbd27d1954b773e253f10576f6c7fda17948415a9c64376cb
|
| 3 |
size 343263964
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 686648762
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d00ef2e168250876bbb79d1a5fb7b10c466de6ece2faa54db84d38b26515da21
|
| 3 |
size 686648762
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c013855f1f203be97dafecaefb623110a70641991f8c85f3b86fa91a81df5017
|
| 3 |
size 14244
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4885688ad473f2aa742df7331aad39a6db20018a0922147b4d30246c383fc177
|
| 3 |
size 1064
|
trainer_state.json
CHANGED
|
@@ -1,830 +1,2450 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "./vit-indian-food/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 50,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.03,
|
| 13 |
-
"grad_norm":
|
| 14 |
-
"learning_rate": 0.
|
| 15 |
-
"loss": 2.
|
| 16 |
"step": 5
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.05,
|
| 20 |
-
"grad_norm": 6.
|
| 21 |
-
"learning_rate": 0.
|
| 22 |
-
"loss": 1.
|
| 23 |
"step": 10
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.08,
|
| 27 |
-
"grad_norm": 6.
|
| 28 |
-
"learning_rate": 0.
|
| 29 |
-
"loss": 1.
|
| 30 |
"step": 15
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.1,
|
| 34 |
-
"grad_norm":
|
| 35 |
-
"learning_rate": 0.
|
| 36 |
-
"loss": 0.
|
| 37 |
"step": 20
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.13,
|
| 41 |
-
"grad_norm": 6.
|
| 42 |
-
"learning_rate": 0.
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 25
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.16,
|
| 48 |
-
"grad_norm": 4.
|
| 49 |
-
"learning_rate": 0.
|
| 50 |
-
"loss": 0.
|
| 51 |
"step": 30
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.18,
|
| 55 |
-
"grad_norm": 4.
|
| 56 |
-
"learning_rate": 0.
|
| 57 |
-
"loss": 0.
|
| 58 |
"step": 35
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.21,
|
| 62 |
-
"grad_norm":
|
| 63 |
-
"learning_rate": 0.
|
| 64 |
-
"loss": 0.
|
| 65 |
"step": 40
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.24,
|
| 69 |
-
"grad_norm": 4.
|
| 70 |
-
"learning_rate": 0.
|
| 71 |
-
"loss": 0.
|
| 72 |
"step": 45
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.26,
|
| 76 |
-
"grad_norm": 4.
|
| 77 |
-
"learning_rate": 0.
|
| 78 |
-
"loss": 0.
|
| 79 |
"step": 50
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.26,
|
| 83 |
-
"eval_accuracy": 0.
|
| 84 |
-
"eval_loss": 0.
|
| 85 |
-
"eval_precision": 0.
|
| 86 |
-
"eval_recall": 0.
|
| 87 |
-
"eval_runtime": 17.
|
| 88 |
-
"eval_samples_per_second": 43.
|
| 89 |
-
"eval_steps_per_second": 2.
|
| 90 |
"step": 50
|
| 91 |
},
|
| 92 |
{
|
| 93 |
"epoch": 0.29,
|
| 94 |
-
"grad_norm": 4.
|
| 95 |
-
"learning_rate": 0.
|
| 96 |
-
"loss": 0.
|
| 97 |
"step": 55
|
| 98 |
},
|
| 99 |
{
|
| 100 |
"epoch": 0.31,
|
| 101 |
-
"grad_norm":
|
| 102 |
-
"learning_rate": 0.
|
| 103 |
-
"loss": 0.
|
| 104 |
"step": 60
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 0.34,
|
| 108 |
-
"grad_norm":
|
| 109 |
-
"learning_rate": 0.
|
| 110 |
-
"loss": 0.
|
| 111 |
"step": 65
|
| 112 |
},
|
| 113 |
{
|
| 114 |
"epoch": 0.37,
|
| 115 |
-
"grad_norm":
|
| 116 |
-
"learning_rate": 0.
|
| 117 |
-
"loss": 0.
|
| 118 |
"step": 70
|
| 119 |
},
|
| 120 |
{
|
| 121 |
"epoch": 0.39,
|
| 122 |
-
"grad_norm":
|
| 123 |
-
"learning_rate": 0.
|
| 124 |
-
"loss": 0.
|
| 125 |
"step": 75
|
| 126 |
},
|
| 127 |
{
|
| 128 |
"epoch": 0.42,
|
| 129 |
-
"grad_norm": 5.
|
| 130 |
-
"learning_rate": 0.
|
| 131 |
-
"loss": 0.
|
| 132 |
"step": 80
|
| 133 |
},
|
| 134 |
{
|
| 135 |
"epoch": 0.45,
|
| 136 |
-
"grad_norm":
|
| 137 |
-
"learning_rate": 0.
|
| 138 |
-
"loss": 0.
|
| 139 |
"step": 85
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"epoch": 0.47,
|
| 143 |
-
"grad_norm":
|
| 144 |
-
"learning_rate": 0.
|
| 145 |
-
"loss": 0.
|
| 146 |
"step": 90
|
| 147 |
},
|
| 148 |
{
|
| 149 |
"epoch": 0.5,
|
| 150 |
-
"grad_norm":
|
| 151 |
-
"learning_rate": 0.
|
| 152 |
-
"loss": 0.
|
| 153 |
"step": 95
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 0.52,
|
| 157 |
-
"grad_norm":
|
| 158 |
-
"learning_rate": 0.
|
| 159 |
-
"loss": 0.
|
| 160 |
"step": 100
|
| 161 |
},
|
| 162 |
{
|
| 163 |
"epoch": 0.52,
|
| 164 |
-
"eval_accuracy": 0.
|
| 165 |
-
"eval_loss": 0.
|
| 166 |
-
"eval_precision": 0.
|
| 167 |
-
"eval_recall": 0.
|
| 168 |
-
"eval_runtime": 17.
|
| 169 |
-
"eval_samples_per_second":
|
| 170 |
-
"eval_steps_per_second": 2.
|
| 171 |
"step": 100
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"epoch": 0.55,
|
| 175 |
-
"grad_norm":
|
| 176 |
-
"learning_rate": 0.
|
| 177 |
-
"loss": 0.
|
| 178 |
"step": 105
|
| 179 |
},
|
| 180 |
{
|
| 181 |
"epoch": 0.58,
|
| 182 |
-
"grad_norm": 1.
|
| 183 |
-
"learning_rate": 0.
|
| 184 |
-
"loss": 0.
|
| 185 |
"step": 110
|
| 186 |
},
|
| 187 |
{
|
| 188 |
"epoch": 0.6,
|
| 189 |
-
"grad_norm":
|
| 190 |
-
"learning_rate": 0.
|
| 191 |
-
"loss": 0.
|
| 192 |
"step": 115
|
| 193 |
},
|
| 194 |
{
|
| 195 |
"epoch": 0.63,
|
| 196 |
-
"grad_norm":
|
| 197 |
-
"learning_rate": 0.
|
| 198 |
-
"loss": 0.
|
| 199 |
"step": 120
|
| 200 |
},
|
| 201 |
{
|
| 202 |
"epoch": 0.65,
|
| 203 |
-
"grad_norm": 4.
|
| 204 |
-
"learning_rate": 0.
|
| 205 |
-
"loss": 0.
|
| 206 |
"step": 125
|
| 207 |
},
|
| 208 |
{
|
| 209 |
"epoch": 0.68,
|
| 210 |
-
"grad_norm":
|
| 211 |
-
"learning_rate": 0.
|
| 212 |
-
"loss": 0.
|
| 213 |
"step": 130
|
| 214 |
},
|
| 215 |
{
|
| 216 |
"epoch": 0.71,
|
| 217 |
-
"grad_norm":
|
| 218 |
-
"learning_rate": 0.
|
| 219 |
-
"loss": 0.
|
| 220 |
"step": 135
|
| 221 |
},
|
| 222 |
{
|
| 223 |
"epoch": 0.73,
|
| 224 |
-
"grad_norm":
|
| 225 |
-
"learning_rate": 0.
|
| 226 |
-
"loss": 0.
|
| 227 |
"step": 140
|
| 228 |
},
|
| 229 |
{
|
| 230 |
"epoch": 0.76,
|
| 231 |
-
"grad_norm":
|
| 232 |
-
"learning_rate": 0.
|
| 233 |
-
"loss": 0.
|
| 234 |
"step": 145
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"epoch": 0.79,
|
| 238 |
-
"grad_norm": 4.
|
| 239 |
-
"learning_rate": 0.
|
| 240 |
-
"loss": 0.
|
| 241 |
"step": 150
|
| 242 |
},
|
| 243 |
{
|
| 244 |
"epoch": 0.79,
|
| 245 |
-
"eval_accuracy": 0.
|
| 246 |
-
"eval_loss": 0.
|
| 247 |
-
"eval_precision": 0.
|
| 248 |
-
"eval_recall": 0.
|
| 249 |
-
"eval_runtime": 17.
|
| 250 |
-
"eval_samples_per_second": 43.
|
| 251 |
-
"eval_steps_per_second": 2.
|
| 252 |
"step": 150
|
| 253 |
},
|
| 254 |
{
|
| 255 |
"epoch": 0.81,
|
| 256 |
-
"grad_norm":
|
| 257 |
-
"learning_rate": 0.
|
| 258 |
-
"loss": 0.
|
| 259 |
"step": 155
|
| 260 |
},
|
| 261 |
{
|
| 262 |
"epoch": 0.84,
|
| 263 |
-
"grad_norm":
|
| 264 |
-
"learning_rate": 0.
|
| 265 |
-
"loss": 0.
|
| 266 |
"step": 160
|
| 267 |
},
|
| 268 |
{
|
| 269 |
"epoch": 0.86,
|
| 270 |
-
"grad_norm":
|
| 271 |
-
"learning_rate": 0.
|
| 272 |
-
"loss": 0.
|
| 273 |
"step": 165
|
| 274 |
},
|
| 275 |
{
|
| 276 |
"epoch": 0.89,
|
| 277 |
-
"grad_norm":
|
| 278 |
-
"learning_rate": 0.
|
| 279 |
-
"loss": 0.
|
| 280 |
"step": 170
|
| 281 |
},
|
| 282 |
{
|
| 283 |
"epoch": 0.92,
|
| 284 |
-
"grad_norm":
|
| 285 |
-
"learning_rate": 0.
|
| 286 |
-
"loss": 0.
|
| 287 |
"step": 175
|
| 288 |
},
|
| 289 |
{
|
| 290 |
"epoch": 0.94,
|
| 291 |
-
"grad_norm":
|
| 292 |
-
"learning_rate": 0.
|
| 293 |
-
"loss": 0.
|
| 294 |
"step": 180
|
| 295 |
},
|
| 296 |
{
|
| 297 |
"epoch": 0.97,
|
| 298 |
-
"grad_norm":
|
| 299 |
-
"learning_rate": 0.
|
| 300 |
-
"loss": 0.
|
| 301 |
"step": 185
|
| 302 |
},
|
| 303 |
{
|
| 304 |
"epoch": 0.99,
|
| 305 |
-
"grad_norm":
|
| 306 |
-
"learning_rate": 0.
|
| 307 |
-
"loss": 0.
|
| 308 |
"step": 190
|
| 309 |
},
|
| 310 |
{
|
| 311 |
"epoch": 1.02,
|
| 312 |
-
"grad_norm":
|
| 313 |
-
"learning_rate": 0.
|
| 314 |
-
"loss": 0.
|
| 315 |
"step": 195
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"epoch": 1.05,
|
| 319 |
-
"grad_norm":
|
| 320 |
-
"learning_rate": 0.
|
| 321 |
-
"loss": 0.
|
| 322 |
"step": 200
|
| 323 |
},
|
| 324 |
{
|
| 325 |
"epoch": 1.05,
|
| 326 |
-
"eval_accuracy": 0.
|
| 327 |
-
"eval_loss": 0.
|
| 328 |
-
"eval_precision": 0.
|
| 329 |
-
"eval_recall": 0.
|
| 330 |
-
"eval_runtime": 17.
|
| 331 |
-
"eval_samples_per_second": 43.
|
| 332 |
-
"eval_steps_per_second": 2.
|
| 333 |
"step": 200
|
| 334 |
},
|
| 335 |
{
|
| 336 |
"epoch": 1.07,
|
| 337 |
-
"grad_norm": 0.
|
| 338 |
-
"learning_rate": 0.
|
| 339 |
-
"loss": 0.
|
| 340 |
"step": 205
|
| 341 |
},
|
| 342 |
{
|
| 343 |
"epoch": 1.1,
|
| 344 |
-
"grad_norm":
|
| 345 |
-
"learning_rate": 0.
|
| 346 |
-
"loss": 0.
|
| 347 |
"step": 210
|
| 348 |
},
|
| 349 |
{
|
| 350 |
"epoch": 1.13,
|
| 351 |
-
"grad_norm":
|
| 352 |
-
"learning_rate": 0.
|
| 353 |
-
"loss": 0.
|
| 354 |
"step": 215
|
| 355 |
},
|
| 356 |
{
|
| 357 |
"epoch": 1.15,
|
| 358 |
-
"grad_norm":
|
| 359 |
-
"learning_rate": 0.
|
| 360 |
-
"loss": 0.
|
| 361 |
"step": 220
|
| 362 |
},
|
| 363 |
{
|
| 364 |
"epoch": 1.18,
|
| 365 |
-
"grad_norm":
|
| 366 |
-
"learning_rate": 0.
|
| 367 |
-
"loss": 0.
|
| 368 |
"step": 225
|
| 369 |
},
|
| 370 |
{
|
| 371 |
"epoch": 1.2,
|
| 372 |
-
"grad_norm":
|
| 373 |
-
"learning_rate": 0.
|
| 374 |
-
"loss": 0.
|
| 375 |
"step": 230
|
| 376 |
},
|
| 377 |
{
|
| 378 |
"epoch": 1.23,
|
| 379 |
-
"grad_norm":
|
| 380 |
-
"learning_rate": 0.
|
| 381 |
-
"loss": 0.
|
| 382 |
"step": 235
|
| 383 |
},
|
| 384 |
{
|
| 385 |
"epoch": 1.26,
|
| 386 |
-
"grad_norm":
|
| 387 |
-
"learning_rate": 0.
|
| 388 |
-
"loss": 0.
|
| 389 |
"step": 240
|
| 390 |
},
|
| 391 |
{
|
| 392 |
"epoch": 1.28,
|
| 393 |
-
"grad_norm":
|
| 394 |
-
"learning_rate": 0.
|
| 395 |
-
"loss": 0.
|
| 396 |
"step": 245
|
| 397 |
},
|
| 398 |
{
|
| 399 |
"epoch": 1.31,
|
| 400 |
-
"grad_norm":
|
| 401 |
-
"learning_rate": 0.
|
| 402 |
-
"loss": 0.
|
| 403 |
"step": 250
|
| 404 |
},
|
| 405 |
{
|
| 406 |
"epoch": 1.31,
|
| 407 |
-
"eval_accuracy": 0.
|
| 408 |
-
"eval_loss": 0.
|
| 409 |
-
"eval_precision": 0.
|
| 410 |
-
"eval_recall": 0.
|
| 411 |
-
"eval_runtime": 17.
|
| 412 |
-
"eval_samples_per_second": 43.
|
| 413 |
-
"eval_steps_per_second": 2.
|
| 414 |
"step": 250
|
| 415 |
},
|
| 416 |
{
|
| 417 |
"epoch": 1.34,
|
| 418 |
-
"grad_norm":
|
| 419 |
-
"learning_rate": 0.
|
| 420 |
-
"loss": 0.
|
| 421 |
"step": 255
|
| 422 |
},
|
| 423 |
{
|
| 424 |
"epoch": 1.36,
|
| 425 |
-
"grad_norm":
|
| 426 |
-
"learning_rate": 0.
|
| 427 |
-
"loss": 0.
|
| 428 |
"step": 260
|
| 429 |
},
|
| 430 |
{
|
| 431 |
"epoch": 1.39,
|
| 432 |
-
"grad_norm": 0.
|
| 433 |
-
"learning_rate": 0.
|
| 434 |
-
"loss": 0.
|
| 435 |
"step": 265
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 1.41,
|
| 439 |
-
"grad_norm":
|
| 440 |
-
"learning_rate": 0.
|
| 441 |
-
"loss": 0.
|
| 442 |
"step": 270
|
| 443 |
},
|
| 444 |
{
|
| 445 |
"epoch": 1.44,
|
| 446 |
-
"grad_norm":
|
| 447 |
-
"learning_rate": 0.
|
| 448 |
-
"loss": 0.
|
| 449 |
"step": 275
|
| 450 |
},
|
| 451 |
{
|
| 452 |
"epoch": 1.47,
|
| 453 |
-
"grad_norm":
|
| 454 |
-
"learning_rate": 0.
|
| 455 |
-
"loss": 0.
|
| 456 |
"step": 280
|
| 457 |
},
|
| 458 |
{
|
| 459 |
"epoch": 1.49,
|
| 460 |
-
"grad_norm": 0.
|
| 461 |
-
"learning_rate": 0.
|
| 462 |
-
"loss": 0.
|
| 463 |
"step": 285
|
| 464 |
},
|
| 465 |
{
|
| 466 |
"epoch": 1.52,
|
| 467 |
-
"grad_norm":
|
| 468 |
-
"learning_rate": 0.
|
| 469 |
-
"loss": 0.
|
| 470 |
"step": 290
|
| 471 |
},
|
| 472 |
{
|
| 473 |
"epoch": 1.54,
|
| 474 |
-
"grad_norm":
|
| 475 |
-
"learning_rate": 0.
|
| 476 |
-
"loss": 0.
|
| 477 |
"step": 295
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 1.57,
|
| 481 |
-
"grad_norm":
|
| 482 |
-
"learning_rate": 0.
|
| 483 |
-
"loss": 0.
|
| 484 |
"step": 300
|
| 485 |
},
|
| 486 |
{
|
| 487 |
"epoch": 1.57,
|
| 488 |
-
"eval_accuracy": 0.
|
| 489 |
-
"eval_loss": 0.
|
| 490 |
-
"eval_precision": 0.
|
| 491 |
-
"eval_recall": 0.
|
| 492 |
-
"eval_runtime": 17.
|
| 493 |
-
"eval_samples_per_second": 43.
|
| 494 |
-
"eval_steps_per_second": 2.
|
| 495 |
"step": 300
|
| 496 |
},
|
| 497 |
{
|
| 498 |
"epoch": 1.6,
|
| 499 |
-
"grad_norm":
|
| 500 |
-
"learning_rate": 0.
|
| 501 |
-
"loss": 0.
|
| 502 |
"step": 305
|
| 503 |
},
|
| 504 |
{
|
| 505 |
"epoch": 1.62,
|
| 506 |
-
"grad_norm":
|
| 507 |
-
"learning_rate": 0.
|
| 508 |
-
"loss": 0.
|
| 509 |
"step": 310
|
| 510 |
},
|
| 511 |
{
|
| 512 |
"epoch": 1.65,
|
| 513 |
-
"grad_norm":
|
| 514 |
-
"learning_rate": 0.
|
| 515 |
-
"loss": 0.
|
| 516 |
"step": 315
|
| 517 |
},
|
| 518 |
{
|
| 519 |
"epoch": 1.68,
|
| 520 |
-
"grad_norm":
|
| 521 |
-
"learning_rate": 0.
|
| 522 |
-
"loss": 0.
|
| 523 |
"step": 320
|
| 524 |
},
|
| 525 |
{
|
| 526 |
"epoch": 1.7,
|
| 527 |
-
"grad_norm":
|
| 528 |
-
"learning_rate": 0.
|
| 529 |
-
"loss": 0.
|
| 530 |
"step": 325
|
| 531 |
},
|
| 532 |
{
|
| 533 |
"epoch": 1.73,
|
| 534 |
-
"grad_norm":
|
| 535 |
-
"learning_rate": 0.
|
| 536 |
-
"loss": 0.
|
| 537 |
"step": 330
|
| 538 |
},
|
| 539 |
{
|
| 540 |
"epoch": 1.75,
|
| 541 |
-
"grad_norm": 0.
|
| 542 |
-
"learning_rate": 0.
|
| 543 |
-
"loss": 0.
|
| 544 |
"step": 335
|
| 545 |
},
|
| 546 |
{
|
| 547 |
"epoch": 1.78,
|
| 548 |
-
"grad_norm":
|
| 549 |
-
"learning_rate": 0.
|
| 550 |
-
"loss": 0.
|
| 551 |
"step": 340
|
| 552 |
},
|
| 553 |
{
|
| 554 |
"epoch": 1.81,
|
| 555 |
-
"grad_norm": 0.
|
| 556 |
-
"learning_rate": 0.
|
| 557 |
-
"loss": 0.
|
| 558 |
"step": 345
|
| 559 |
},
|
| 560 |
{
|
| 561 |
"epoch": 1.83,
|
| 562 |
-
"grad_norm":
|
| 563 |
-
"learning_rate": 0.
|
| 564 |
-
"loss": 0.
|
| 565 |
"step": 350
|
| 566 |
},
|
| 567 |
{
|
| 568 |
"epoch": 1.83,
|
| 569 |
-
"eval_accuracy": 0.
|
| 570 |
-
"eval_loss": 0.
|
| 571 |
-
"eval_precision": 0.
|
| 572 |
-
"eval_recall": 0.
|
| 573 |
-
"eval_runtime": 17.
|
| 574 |
-
"eval_samples_per_second": 43.
|
| 575 |
-
"eval_steps_per_second": 2.
|
| 576 |
"step": 350
|
| 577 |
},
|
| 578 |
{
|
| 579 |
"epoch": 1.86,
|
| 580 |
-
"grad_norm":
|
| 581 |
-
"learning_rate": 0.
|
| 582 |
-
"loss": 0.
|
| 583 |
"step": 355
|
| 584 |
},
|
| 585 |
{
|
| 586 |
"epoch": 1.88,
|
| 587 |
-
"grad_norm":
|
| 588 |
-
"learning_rate": 0.
|
| 589 |
-
"loss": 0.
|
| 590 |
"step": 360
|
| 591 |
},
|
| 592 |
{
|
| 593 |
"epoch": 1.91,
|
| 594 |
-
"grad_norm": 4.
|
| 595 |
-
"learning_rate": 0.
|
| 596 |
-
"loss": 0.
|
| 597 |
"step": 365
|
| 598 |
},
|
| 599 |
{
|
| 600 |
"epoch": 1.94,
|
| 601 |
-
"grad_norm":
|
| 602 |
-
"learning_rate": 0.
|
| 603 |
-
"loss": 0.
|
| 604 |
"step": 370
|
| 605 |
},
|
| 606 |
{
|
| 607 |
"epoch": 1.96,
|
| 608 |
-
"grad_norm":
|
| 609 |
-
"learning_rate": 0.
|
| 610 |
-
"loss": 0.
|
| 611 |
"step": 375
|
| 612 |
},
|
| 613 |
{
|
| 614 |
"epoch": 1.99,
|
| 615 |
-
"grad_norm": 0.
|
| 616 |
-
"learning_rate": 0.
|
| 617 |
-
"loss": 0.
|
| 618 |
"step": 380
|
| 619 |
},
|
| 620 |
{
|
| 621 |
"epoch": 2.02,
|
| 622 |
-
"grad_norm":
|
| 623 |
-
"learning_rate": 0.
|
| 624 |
-
"loss": 0.
|
| 625 |
"step": 385
|
| 626 |
},
|
| 627 |
{
|
| 628 |
"epoch": 2.04,
|
| 629 |
-
"grad_norm":
|
| 630 |
-
"learning_rate": 0.
|
| 631 |
-
"loss": 0.
|
| 632 |
"step": 390
|
| 633 |
},
|
| 634 |
{
|
| 635 |
"epoch": 2.07,
|
| 636 |
-
"grad_norm": 0.
|
| 637 |
-
"learning_rate": 0.
|
| 638 |
-
"loss": 0.
|
| 639 |
"step": 395
|
| 640 |
},
|
| 641 |
{
|
| 642 |
"epoch": 2.09,
|
| 643 |
-
"grad_norm": 0.
|
| 644 |
-
"learning_rate": 0.
|
| 645 |
-
"loss": 0.
|
| 646 |
"step": 400
|
| 647 |
},
|
| 648 |
{
|
| 649 |
"epoch": 2.09,
|
| 650 |
-
"eval_accuracy": 0.
|
| 651 |
-
"eval_loss": 0.
|
| 652 |
-
"eval_precision": 0.
|
| 653 |
-
"eval_recall": 0.
|
| 654 |
-
"eval_runtime": 17.
|
| 655 |
-
"eval_samples_per_second": 43.
|
| 656 |
-
"eval_steps_per_second": 2.
|
| 657 |
"step": 400
|
| 658 |
},
|
| 659 |
{
|
| 660 |
"epoch": 2.12,
|
| 661 |
-
"grad_norm": 0.
|
| 662 |
-
"learning_rate": 0.
|
| 663 |
-
"loss": 0.
|
| 664 |
"step": 405
|
| 665 |
},
|
| 666 |
{
|
| 667 |
"epoch": 2.15,
|
| 668 |
-
"grad_norm":
|
| 669 |
-
"learning_rate": 0.
|
| 670 |
-
"loss": 0.
|
| 671 |
"step": 410
|
| 672 |
},
|
| 673 |
{
|
| 674 |
"epoch": 2.17,
|
| 675 |
-
"grad_norm": 0.
|
| 676 |
-
"learning_rate": 0.
|
| 677 |
-
"loss": 0.
|
| 678 |
"step": 415
|
| 679 |
},
|
| 680 |
{
|
| 681 |
"epoch": 2.2,
|
| 682 |
-
"grad_norm": 0.
|
| 683 |
-
"learning_rate": 0.
|
| 684 |
-
"loss": 0.
|
| 685 |
"step": 420
|
| 686 |
},
|
| 687 |
{
|
| 688 |
"epoch": 2.23,
|
| 689 |
-
"grad_norm": 0.
|
| 690 |
-
"learning_rate": 0.
|
| 691 |
-
"loss": 0.
|
| 692 |
"step": 425
|
| 693 |
},
|
| 694 |
{
|
| 695 |
"epoch": 2.25,
|
| 696 |
-
"grad_norm": 0.
|
| 697 |
-
"learning_rate": 0.
|
| 698 |
-
"loss": 0.
|
| 699 |
"step": 430
|
| 700 |
},
|
| 701 |
{
|
| 702 |
"epoch": 2.28,
|
| 703 |
-
"grad_norm": 0.
|
| 704 |
-
"learning_rate": 0.
|
| 705 |
-
"loss": 0.
|
| 706 |
"step": 435
|
| 707 |
},
|
| 708 |
{
|
| 709 |
"epoch": 2.3,
|
| 710 |
-
"grad_norm":
|
| 711 |
-
"learning_rate": 0.
|
| 712 |
-
"loss": 0.
|
| 713 |
"step": 440
|
| 714 |
},
|
| 715 |
{
|
| 716 |
"epoch": 2.33,
|
| 717 |
-
"grad_norm": 0.
|
| 718 |
-
"learning_rate": 0.
|
| 719 |
-
"loss": 0.
|
| 720 |
"step": 445
|
| 721 |
},
|
| 722 |
{
|
| 723 |
"epoch": 2.36,
|
| 724 |
-
"grad_norm": 0.
|
| 725 |
-
"learning_rate": 0.
|
| 726 |
-
"loss": 0.
|
| 727 |
"step": 450
|
| 728 |
},
|
| 729 |
{
|
| 730 |
"epoch": 2.36,
|
| 731 |
-
"eval_accuracy": 0.
|
| 732 |
-
"eval_loss": 0.
|
| 733 |
-
"eval_precision": 0.
|
| 734 |
-
"eval_recall": 0.
|
| 735 |
-
"eval_runtime": 17.
|
| 736 |
-
"eval_samples_per_second": 43.
|
| 737 |
-
"eval_steps_per_second": 2.
|
| 738 |
"step": 450
|
| 739 |
},
|
| 740 |
{
|
| 741 |
"epoch": 2.38,
|
| 742 |
-
"grad_norm":
|
| 743 |
-
"learning_rate": 0.
|
| 744 |
-
"loss": 0.
|
| 745 |
"step": 455
|
| 746 |
},
|
| 747 |
{
|
| 748 |
"epoch": 2.41,
|
| 749 |
-
"grad_norm":
|
| 750 |
-
"learning_rate": 0.
|
| 751 |
-
"loss": 0.
|
| 752 |
"step": 460
|
| 753 |
},
|
| 754 |
{
|
| 755 |
"epoch": 2.43,
|
| 756 |
-
"grad_norm":
|
| 757 |
-
"learning_rate": 0.
|
| 758 |
-
"loss": 0.
|
| 759 |
"step": 465
|
| 760 |
},
|
| 761 |
{
|
| 762 |
"epoch": 2.46,
|
| 763 |
-
"grad_norm": 0.
|
| 764 |
-
"learning_rate": 0.
|
| 765 |
-
"loss": 0.
|
| 766 |
"step": 470
|
| 767 |
},
|
| 768 |
{
|
| 769 |
"epoch": 2.49,
|
| 770 |
-
"grad_norm": 0.
|
| 771 |
-
"learning_rate": 0.
|
| 772 |
-
"loss": 0.
|
| 773 |
"step": 475
|
| 774 |
},
|
| 775 |
{
|
| 776 |
"epoch": 2.51,
|
| 777 |
-
"grad_norm":
|
| 778 |
-
"learning_rate":
|
| 779 |
-
"loss": 0.
|
| 780 |
"step": 480
|
| 781 |
},
|
| 782 |
{
|
| 783 |
"epoch": 2.54,
|
| 784 |
-
"grad_norm": 0.
|
| 785 |
-
"learning_rate":
|
| 786 |
-
"loss": 0.
|
| 787 |
"step": 485
|
| 788 |
},
|
| 789 |
{
|
| 790 |
"epoch": 2.57,
|
| 791 |
-
"grad_norm": 0.
|
| 792 |
-
"learning_rate":
|
| 793 |
-
"loss": 0.
|
| 794 |
"step": 490
|
| 795 |
},
|
| 796 |
{
|
| 797 |
"epoch": 2.59,
|
| 798 |
-
"grad_norm": 0.
|
| 799 |
-
"learning_rate":
|
| 800 |
-
"loss": 0.
|
| 801 |
"step": 495
|
| 802 |
},
|
| 803 |
{
|
| 804 |
"epoch": 2.62,
|
| 805 |
-
"grad_norm": 0.
|
| 806 |
-
"learning_rate":
|
| 807 |
-
"loss": 0.
|
| 808 |
"step": 500
|
| 809 |
},
|
| 810 |
{
|
| 811 |
"epoch": 2.62,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 812 |
"eval_accuracy": 0.963254593175853,
|
| 813 |
-
"eval_loss": 0.
|
| 814 |
-
"eval_precision": 0.
|
| 815 |
"eval_recall": 0.963254593175853,
|
| 816 |
-
"eval_runtime": 17.
|
| 817 |
-
"eval_samples_per_second": 43.
|
| 818 |
-
"eval_steps_per_second": 2.
|
| 819 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 820 |
}
|
| 821 |
],
|
| 822 |
"logging_steps": 5,
|
| 823 |
-
"max_steps":
|
| 824 |
"num_input_tokens_seen": 0,
|
| 825 |
-
"num_train_epochs":
|
| 826 |
"save_steps": 500,
|
| 827 |
-
"total_flos":
|
| 828 |
"train_batch_size": 16,
|
| 829 |
"trial_name": null,
|
| 830 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.11646050214767456,
|
| 3 |
+
"best_model_checkpoint": "./vit-indian-food/checkpoint-1500",
|
| 4 |
+
"epoch": 7.853403141361256,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 1500,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.03,
|
| 13 |
+
"grad_norm": 7.558130264282227,
|
| 14 |
+
"learning_rate": 0.00019947643979057592,
|
| 15 |
+
"loss": 2.4369,
|
| 16 |
"step": 5
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.05,
|
| 20 |
+
"grad_norm": 6.5493950843811035,
|
| 21 |
+
"learning_rate": 0.00019895287958115185,
|
| 22 |
+
"loss": 1.6214,
|
| 23 |
"step": 10
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.08,
|
| 27 |
+
"grad_norm": 6.205695629119873,
|
| 28 |
+
"learning_rate": 0.00019842931937172776,
|
| 29 |
+
"loss": 1.197,
|
| 30 |
"step": 15
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.1,
|
| 34 |
+
"grad_norm": 3.8880319595336914,
|
| 35 |
+
"learning_rate": 0.00019790575916230367,
|
| 36 |
+
"loss": 0.7391,
|
| 37 |
"step": 20
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.13,
|
| 41 |
+
"grad_norm": 6.315922260284424,
|
| 42 |
+
"learning_rate": 0.0001973821989528796,
|
| 43 |
+
"loss": 0.6288,
|
| 44 |
"step": 25
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.16,
|
| 48 |
+
"grad_norm": 4.008142471313477,
|
| 49 |
+
"learning_rate": 0.0001968586387434555,
|
| 50 |
+
"loss": 0.3582,
|
| 51 |
"step": 30
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.18,
|
| 55 |
+
"grad_norm": 4.005300998687744,
|
| 56 |
+
"learning_rate": 0.00019633507853403142,
|
| 57 |
+
"loss": 0.3882,
|
| 58 |
"step": 35
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.21,
|
| 62 |
+
"grad_norm": 3.9506969451904297,
|
| 63 |
+
"learning_rate": 0.00019581151832460733,
|
| 64 |
+
"loss": 0.39,
|
| 65 |
"step": 40
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.24,
|
| 69 |
+
"grad_norm": 4.074863910675049,
|
| 70 |
+
"learning_rate": 0.00019528795811518326,
|
| 71 |
+
"loss": 0.3413,
|
| 72 |
"step": 45
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.26,
|
| 76 |
+
"grad_norm": 4.617203712463379,
|
| 77 |
+
"learning_rate": 0.00019476439790575917,
|
| 78 |
+
"loss": 0.358,
|
| 79 |
"step": 50
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.26,
|
| 83 |
+
"eval_accuracy": 0.9081364829396326,
|
| 84 |
+
"eval_loss": 0.32936015725135803,
|
| 85 |
+
"eval_precision": 0.9220515144455581,
|
| 86 |
+
"eval_recall": 0.9081364829396326,
|
| 87 |
+
"eval_runtime": 17.5763,
|
| 88 |
+
"eval_samples_per_second": 43.354,
|
| 89 |
+
"eval_steps_per_second": 2.731,
|
| 90 |
"step": 50
|
| 91 |
},
|
| 92 |
{
|
| 93 |
"epoch": 0.29,
|
| 94 |
+
"grad_norm": 4.685304641723633,
|
| 95 |
+
"learning_rate": 0.0001942408376963351,
|
| 96 |
+
"loss": 0.3669,
|
| 97 |
"step": 55
|
| 98 |
},
|
| 99 |
{
|
| 100 |
"epoch": 0.31,
|
| 101 |
+
"grad_norm": 3.119244337081909,
|
| 102 |
+
"learning_rate": 0.000193717277486911,
|
| 103 |
+
"loss": 0.1722,
|
| 104 |
"step": 60
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 0.34,
|
| 108 |
+
"grad_norm": 6.17639684677124,
|
| 109 |
+
"learning_rate": 0.00019319371727748692,
|
| 110 |
+
"loss": 0.405,
|
| 111 |
"step": 65
|
| 112 |
},
|
| 113 |
{
|
| 114 |
"epoch": 0.37,
|
| 115 |
+
"grad_norm": 4.263852119445801,
|
| 116 |
+
"learning_rate": 0.00019267015706806283,
|
| 117 |
+
"loss": 0.5013,
|
| 118 |
"step": 70
|
| 119 |
},
|
| 120 |
{
|
| 121 |
"epoch": 0.39,
|
| 122 |
+
"grad_norm": 2.03020977973938,
|
| 123 |
+
"learning_rate": 0.00019214659685863877,
|
| 124 |
+
"loss": 0.2251,
|
| 125 |
"step": 75
|
| 126 |
},
|
| 127 |
{
|
| 128 |
"epoch": 0.42,
|
| 129 |
+
"grad_norm": 5.0216193199157715,
|
| 130 |
+
"learning_rate": 0.00019162303664921465,
|
| 131 |
+
"loss": 0.3329,
|
| 132 |
"step": 80
|
| 133 |
},
|
| 134 |
{
|
| 135 |
"epoch": 0.45,
|
| 136 |
+
"grad_norm": 7.692380428314209,
|
| 137 |
+
"learning_rate": 0.00019109947643979058,
|
| 138 |
+
"loss": 0.2191,
|
| 139 |
"step": 85
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"epoch": 0.47,
|
| 143 |
+
"grad_norm": 5.645913600921631,
|
| 144 |
+
"learning_rate": 0.0001905759162303665,
|
| 145 |
+
"loss": 0.3437,
|
| 146 |
"step": 90
|
| 147 |
},
|
| 148 |
{
|
| 149 |
"epoch": 0.5,
|
| 150 |
+
"grad_norm": 5.066718578338623,
|
| 151 |
+
"learning_rate": 0.00019005235602094243,
|
| 152 |
+
"loss": 0.4461,
|
| 153 |
"step": 95
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 0.52,
|
| 157 |
+
"grad_norm": 4.659124851226807,
|
| 158 |
+
"learning_rate": 0.00018952879581151833,
|
| 159 |
+
"loss": 0.5051,
|
| 160 |
"step": 100
|
| 161 |
},
|
| 162 |
{
|
| 163 |
"epoch": 0.52,
|
| 164 |
+
"eval_accuracy": 0.9291338582677166,
|
| 165 |
+
"eval_loss": 0.22470374405384064,
|
| 166 |
+
"eval_precision": 0.9372539303361345,
|
| 167 |
+
"eval_recall": 0.9291338582677166,
|
| 168 |
+
"eval_runtime": 17.4785,
|
| 169 |
+
"eval_samples_per_second": 43.597,
|
| 170 |
+
"eval_steps_per_second": 2.746,
|
| 171 |
"step": 100
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"epoch": 0.55,
|
| 175 |
+
"grad_norm": 4.5200324058532715,
|
| 176 |
+
"learning_rate": 0.00018900523560209424,
|
| 177 |
+
"loss": 0.2615,
|
| 178 |
"step": 105
|
| 179 |
},
|
| 180 |
{
|
| 181 |
"epoch": 0.58,
|
| 182 |
+
"grad_norm": 1.2165738344192505,
|
| 183 |
+
"learning_rate": 0.00018848167539267018,
|
| 184 |
+
"loss": 0.2415,
|
| 185 |
"step": 110
|
| 186 |
},
|
| 187 |
{
|
| 188 |
"epoch": 0.6,
|
| 189 |
+
"grad_norm": 6.801146030426025,
|
| 190 |
+
"learning_rate": 0.00018795811518324608,
|
| 191 |
+
"loss": 0.3234,
|
| 192 |
"step": 115
|
| 193 |
},
|
| 194 |
{
|
| 195 |
"epoch": 0.63,
|
| 196 |
+
"grad_norm": 0.8039401173591614,
|
| 197 |
+
"learning_rate": 0.00018743455497382202,
|
| 198 |
+
"loss": 0.1962,
|
| 199 |
"step": 120
|
| 200 |
},
|
| 201 |
{
|
| 202 |
"epoch": 0.65,
|
| 203 |
+
"grad_norm": 4.639632701873779,
|
| 204 |
+
"learning_rate": 0.0001869109947643979,
|
| 205 |
+
"loss": 0.2755,
|
| 206 |
"step": 125
|
| 207 |
},
|
| 208 |
{
|
| 209 |
"epoch": 0.68,
|
| 210 |
+
"grad_norm": 3.4670636653900146,
|
| 211 |
+
"learning_rate": 0.00018638743455497384,
|
| 212 |
+
"loss": 0.3463,
|
| 213 |
"step": 130
|
| 214 |
},
|
| 215 |
{
|
| 216 |
"epoch": 0.71,
|
| 217 |
+
"grad_norm": 6.07156229019165,
|
| 218 |
+
"learning_rate": 0.00018586387434554974,
|
| 219 |
+
"loss": 0.3047,
|
| 220 |
"step": 135
|
| 221 |
},
|
| 222 |
{
|
| 223 |
"epoch": 0.73,
|
| 224 |
+
"grad_norm": 6.347087860107422,
|
| 225 |
+
"learning_rate": 0.00018534031413612568,
|
| 226 |
+
"loss": 0.2364,
|
| 227 |
"step": 140
|
| 228 |
},
|
| 229 |
{
|
| 230 |
"epoch": 0.76,
|
| 231 |
+
"grad_norm": 5.963706970214844,
|
| 232 |
+
"learning_rate": 0.00018481675392670156,
|
| 233 |
+
"loss": 0.4148,
|
| 234 |
"step": 145
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"epoch": 0.79,
|
| 238 |
+
"grad_norm": 4.037764072418213,
|
| 239 |
+
"learning_rate": 0.0001842931937172775,
|
| 240 |
+
"loss": 0.1361,
|
| 241 |
"step": 150
|
| 242 |
},
|
| 243 |
{
|
| 244 |
"epoch": 0.79,
|
| 245 |
+
"eval_accuracy": 0.9409448818897638,
|
| 246 |
+
"eval_loss": 0.21655863523483276,
|
| 247 |
+
"eval_precision": 0.9454930944052194,
|
| 248 |
+
"eval_recall": 0.9409448818897638,
|
| 249 |
+
"eval_runtime": 17.4607,
|
| 250 |
+
"eval_samples_per_second": 43.641,
|
| 251 |
+
"eval_steps_per_second": 2.749,
|
| 252 |
"step": 150
|
| 253 |
},
|
| 254 |
{
|
| 255 |
"epoch": 0.81,
|
| 256 |
+
"grad_norm": 4.717739582061768,
|
| 257 |
+
"learning_rate": 0.0001837696335078534,
|
| 258 |
+
"loss": 0.1183,
|
| 259 |
"step": 155
|
| 260 |
},
|
| 261 |
{
|
| 262 |
"epoch": 0.84,
|
| 263 |
+
"grad_norm": 3.9427084922790527,
|
| 264 |
+
"learning_rate": 0.00018324607329842934,
|
| 265 |
+
"loss": 0.1138,
|
| 266 |
"step": 160
|
| 267 |
},
|
| 268 |
{
|
| 269 |
"epoch": 0.86,
|
| 270 |
+
"grad_norm": 4.915616989135742,
|
| 271 |
+
"learning_rate": 0.00018272251308900525,
|
| 272 |
+
"loss": 0.2988,
|
| 273 |
"step": 165
|
| 274 |
},
|
| 275 |
{
|
| 276 |
"epoch": 0.89,
|
| 277 |
+
"grad_norm": 6.3770432472229,
|
| 278 |
+
"learning_rate": 0.00018219895287958115,
|
| 279 |
+
"loss": 0.1744,
|
| 280 |
"step": 170
|
| 281 |
},
|
| 282 |
{
|
| 283 |
"epoch": 0.92,
|
| 284 |
+
"grad_norm": 0.7859281301498413,
|
| 285 |
+
"learning_rate": 0.00018167539267015706,
|
| 286 |
+
"loss": 0.2486,
|
| 287 |
"step": 175
|
| 288 |
},
|
| 289 |
{
|
| 290 |
"epoch": 0.94,
|
| 291 |
+
"grad_norm": 3.75736141204834,
|
| 292 |
+
"learning_rate": 0.000181151832460733,
|
| 293 |
+
"loss": 0.2637,
|
| 294 |
"step": 180
|
| 295 |
},
|
| 296 |
{
|
| 297 |
"epoch": 0.97,
|
| 298 |
+
"grad_norm": 6.771958351135254,
|
| 299 |
+
"learning_rate": 0.0001806282722513089,
|
| 300 |
+
"loss": 0.2305,
|
| 301 |
"step": 185
|
| 302 |
},
|
| 303 |
{
|
| 304 |
"epoch": 0.99,
|
| 305 |
+
"grad_norm": 4.951119899749756,
|
| 306 |
+
"learning_rate": 0.0001801047120418848,
|
| 307 |
+
"loss": 0.1108,
|
| 308 |
"step": 190
|
| 309 |
},
|
| 310 |
{
|
| 311 |
"epoch": 1.02,
|
| 312 |
+
"grad_norm": 3.362152576446533,
|
| 313 |
+
"learning_rate": 0.00017958115183246075,
|
| 314 |
+
"loss": 0.133,
|
| 315 |
"step": 195
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"epoch": 1.05,
|
| 319 |
+
"grad_norm": 0.8346299529075623,
|
| 320 |
+
"learning_rate": 0.00017905759162303666,
|
| 321 |
+
"loss": 0.0611,
|
| 322 |
"step": 200
|
| 323 |
},
|
| 324 |
{
|
| 325 |
"epoch": 1.05,
|
| 326 |
+
"eval_accuracy": 0.9488188976377953,
|
| 327 |
+
"eval_loss": 0.18689152598381042,
|
| 328 |
+
"eval_precision": 0.9533647964651322,
|
| 329 |
+
"eval_recall": 0.9488188976377953,
|
| 330 |
+
"eval_runtime": 17.6111,
|
| 331 |
+
"eval_samples_per_second": 43.268,
|
| 332 |
+
"eval_steps_per_second": 2.726,
|
| 333 |
"step": 200
|
| 334 |
},
|
| 335 |
{
|
| 336 |
"epoch": 1.07,
|
| 337 |
+
"grad_norm": 0.5746695399284363,
|
| 338 |
+
"learning_rate": 0.0001785340314136126,
|
| 339 |
+
"loss": 0.0241,
|
| 340 |
"step": 205
|
| 341 |
},
|
| 342 |
{
|
| 343 |
"epoch": 1.1,
|
| 344 |
+
"grad_norm": 2.0743372440338135,
|
| 345 |
+
"learning_rate": 0.0001780104712041885,
|
| 346 |
+
"loss": 0.0662,
|
| 347 |
"step": 210
|
| 348 |
},
|
| 349 |
{
|
| 350 |
"epoch": 1.13,
|
| 351 |
+
"grad_norm": 1.6814557313919067,
|
| 352 |
+
"learning_rate": 0.0001774869109947644,
|
| 353 |
+
"loss": 0.0635,
|
| 354 |
"step": 215
|
| 355 |
},
|
| 356 |
{
|
| 357 |
"epoch": 1.15,
|
| 358 |
+
"grad_norm": 2.118739128112793,
|
| 359 |
+
"learning_rate": 0.00017696335078534032,
|
| 360 |
+
"loss": 0.1024,
|
| 361 |
"step": 220
|
| 362 |
},
|
| 363 |
{
|
| 364 |
"epoch": 1.18,
|
| 365 |
+
"grad_norm": 3.4306182861328125,
|
| 366 |
+
"learning_rate": 0.00017643979057591625,
|
| 367 |
+
"loss": 0.0201,
|
| 368 |
"step": 225
|
| 369 |
},
|
| 370 |
{
|
| 371 |
"epoch": 1.2,
|
| 372 |
+
"grad_norm": 0.28945377469062805,
|
| 373 |
+
"learning_rate": 0.00017591623036649216,
|
| 374 |
+
"loss": 0.1151,
|
| 375 |
"step": 230
|
| 376 |
},
|
| 377 |
{
|
| 378 |
"epoch": 1.23,
|
| 379 |
+
"grad_norm": 4.6208648681640625,
|
| 380 |
+
"learning_rate": 0.00017539267015706807,
|
| 381 |
+
"loss": 0.2324,
|
| 382 |
"step": 235
|
| 383 |
},
|
| 384 |
{
|
| 385 |
"epoch": 1.26,
|
| 386 |
+
"grad_norm": 1.6085395812988281,
|
| 387 |
+
"learning_rate": 0.00017486910994764398,
|
| 388 |
+
"loss": 0.0429,
|
| 389 |
"step": 240
|
| 390 |
},
|
| 391 |
{
|
| 392 |
"epoch": 1.28,
|
| 393 |
+
"grad_norm": 5.860565185546875,
|
| 394 |
+
"learning_rate": 0.0001743455497382199,
|
| 395 |
+
"loss": 0.0567,
|
| 396 |
"step": 245
|
| 397 |
},
|
| 398 |
{
|
| 399 |
"epoch": 1.31,
|
| 400 |
+
"grad_norm": 5.421276092529297,
|
| 401 |
+
"learning_rate": 0.00017382198952879582,
|
| 402 |
+
"loss": 0.1037,
|
| 403 |
"step": 250
|
| 404 |
},
|
| 405 |
{
|
| 406 |
"epoch": 1.31,
|
| 407 |
+
"eval_accuracy": 0.968503937007874,
|
| 408 |
+
"eval_loss": 0.11793948709964752,
|
| 409 |
+
"eval_precision": 0.9693355319509627,
|
| 410 |
+
"eval_recall": 0.968503937007874,
|
| 411 |
+
"eval_runtime": 17.5701,
|
| 412 |
+
"eval_samples_per_second": 43.369,
|
| 413 |
+
"eval_steps_per_second": 2.732,
|
| 414 |
"step": 250
|
| 415 |
},
|
| 416 |
{
|
| 417 |
"epoch": 1.34,
|
| 418 |
+
"grad_norm": 3.9477956295013428,
|
| 419 |
+
"learning_rate": 0.00017329842931937175,
|
| 420 |
+
"loss": 0.0285,
|
| 421 |
"step": 255
|
| 422 |
},
|
| 423 |
{
|
| 424 |
"epoch": 1.36,
|
| 425 |
+
"grad_norm": 7.515362739562988,
|
| 426 |
+
"learning_rate": 0.00017277486910994763,
|
| 427 |
+
"loss": 0.2195,
|
| 428 |
"step": 260
|
| 429 |
},
|
| 430 |
{
|
| 431 |
"epoch": 1.39,
|
| 432 |
+
"grad_norm": 0.1676739752292633,
|
| 433 |
+
"learning_rate": 0.00017225130890052357,
|
| 434 |
+
"loss": 0.0172,
|
| 435 |
"step": 265
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 1.41,
|
| 439 |
+
"grad_norm": 8.235359191894531,
|
| 440 |
+
"learning_rate": 0.00017172774869109948,
|
| 441 |
+
"loss": 0.1756,
|
| 442 |
"step": 270
|
| 443 |
},
|
| 444 |
{
|
| 445 |
"epoch": 1.44,
|
| 446 |
+
"grad_norm": 7.9198832511901855,
|
| 447 |
+
"learning_rate": 0.0001712041884816754,
|
| 448 |
+
"loss": 0.0663,
|
| 449 |
"step": 275
|
| 450 |
},
|
| 451 |
{
|
| 452 |
"epoch": 1.47,
|
| 453 |
+
"grad_norm": 6.388627529144287,
|
| 454 |
+
"learning_rate": 0.00017068062827225132,
|
| 455 |
+
"loss": 0.1467,
|
| 456 |
"step": 280
|
| 457 |
},
|
| 458 |
{
|
| 459 |
"epoch": 1.49,
|
| 460 |
+
"grad_norm": 0.09213338047266006,
|
| 461 |
+
"learning_rate": 0.00017015706806282723,
|
| 462 |
+
"loss": 0.0684,
|
| 463 |
"step": 285
|
| 464 |
},
|
| 465 |
{
|
| 466 |
"epoch": 1.52,
|
| 467 |
+
"grad_norm": 1.0691012144088745,
|
| 468 |
+
"learning_rate": 0.00016963350785340316,
|
| 469 |
+
"loss": 0.0954,
|
| 470 |
"step": 290
|
| 471 |
},
|
| 472 |
{
|
| 473 |
"epoch": 1.54,
|
| 474 |
+
"grad_norm": 6.120029449462891,
|
| 475 |
+
"learning_rate": 0.00016910994764397907,
|
| 476 |
+
"loss": 0.0587,
|
| 477 |
"step": 295
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 1.57,
|
| 481 |
+
"grad_norm": 0.0928138718008995,
|
| 482 |
+
"learning_rate": 0.00016858638743455498,
|
| 483 |
+
"loss": 0.0294,
|
| 484 |
"step": 300
|
| 485 |
},
|
| 486 |
{
|
| 487 |
"epoch": 1.57,
|
| 488 |
+
"eval_accuracy": 0.963254593175853,
|
| 489 |
+
"eval_loss": 0.11820019036531448,
|
| 490 |
+
"eval_precision": 0.9645155573207865,
|
| 491 |
+
"eval_recall": 0.963254593175853,
|
| 492 |
+
"eval_runtime": 17.5014,
|
| 493 |
+
"eval_samples_per_second": 43.539,
|
| 494 |
+
"eval_steps_per_second": 2.743,
|
| 495 |
"step": 300
|
| 496 |
},
|
| 497 |
{
|
| 498 |
"epoch": 1.6,
|
| 499 |
+
"grad_norm": 0.3131069242954254,
|
| 500 |
+
"learning_rate": 0.0001680628272251309,
|
| 501 |
+
"loss": 0.1184,
|
| 502 |
"step": 305
|
| 503 |
},
|
| 504 |
{
|
| 505 |
"epoch": 1.62,
|
| 506 |
+
"grad_norm": 0.417850524187088,
|
| 507 |
+
"learning_rate": 0.00016753926701570682,
|
| 508 |
+
"loss": 0.0053,
|
| 509 |
"step": 310
|
| 510 |
},
|
| 511 |
{
|
| 512 |
"epoch": 1.65,
|
| 513 |
+
"grad_norm": 5.371811389923096,
|
| 514 |
+
"learning_rate": 0.00016701570680628273,
|
| 515 |
+
"loss": 0.1099,
|
| 516 |
"step": 315
|
| 517 |
},
|
| 518 |
{
|
| 519 |
"epoch": 1.68,
|
| 520 |
+
"grad_norm": 4.09129524230957,
|
| 521 |
+
"learning_rate": 0.00016649214659685867,
|
| 522 |
+
"loss": 0.2501,
|
| 523 |
"step": 320
|
| 524 |
},
|
| 525 |
{
|
| 526 |
"epoch": 1.7,
|
| 527 |
+
"grad_norm": 0.6515682935714722,
|
| 528 |
+
"learning_rate": 0.00016596858638743455,
|
| 529 |
+
"loss": 0.0528,
|
| 530 |
"step": 325
|
| 531 |
},
|
| 532 |
{
|
| 533 |
"epoch": 1.73,
|
| 534 |
+
"grad_norm": 0.5656059384346008,
|
| 535 |
+
"learning_rate": 0.00016544502617801048,
|
| 536 |
+
"loss": 0.1378,
|
| 537 |
"step": 330
|
| 538 |
},
|
| 539 |
{
|
| 540 |
"epoch": 1.75,
|
| 541 |
+
"grad_norm": 0.10378353297710419,
|
| 542 |
+
"learning_rate": 0.0001649214659685864,
|
| 543 |
+
"loss": 0.0329,
|
| 544 |
"step": 335
|
| 545 |
},
|
| 546 |
{
|
| 547 |
"epoch": 1.78,
|
| 548 |
+
"grad_norm": 2.387305736541748,
|
| 549 |
+
"learning_rate": 0.00016439790575916233,
|
| 550 |
+
"loss": 0.0353,
|
| 551 |
"step": 340
|
| 552 |
},
|
| 553 |
{
|
| 554 |
"epoch": 1.81,
|
| 555 |
+
"grad_norm": 0.05628238245844841,
|
| 556 |
+
"learning_rate": 0.0001638743455497382,
|
| 557 |
+
"loss": 0.0138,
|
| 558 |
"step": 345
|
| 559 |
},
|
| 560 |
{
|
| 561 |
"epoch": 1.83,
|
| 562 |
+
"grad_norm": 0.04053734615445137,
|
| 563 |
+
"learning_rate": 0.00016335078534031414,
|
| 564 |
+
"loss": 0.0082,
|
| 565 |
"step": 350
|
| 566 |
},
|
| 567 |
{
|
| 568 |
"epoch": 1.83,
|
| 569 |
+
"eval_accuracy": 0.963254593175853,
|
| 570 |
+
"eval_loss": 0.11838709563016891,
|
| 571 |
+
"eval_precision": 0.9654537871036863,
|
| 572 |
+
"eval_recall": 0.963254593175853,
|
| 573 |
+
"eval_runtime": 17.4034,
|
| 574 |
+
"eval_samples_per_second": 43.785,
|
| 575 |
+
"eval_steps_per_second": 2.758,
|
| 576 |
"step": 350
|
| 577 |
},
|
| 578 |
{
|
| 579 |
"epoch": 1.86,
|
| 580 |
+
"grad_norm": 2.287546396255493,
|
| 581 |
+
"learning_rate": 0.00016282722513089005,
|
| 582 |
+
"loss": 0.02,
|
| 583 |
"step": 355
|
| 584 |
},
|
| 585 |
{
|
| 586 |
"epoch": 1.88,
|
| 587 |
+
"grad_norm": 4.561453342437744,
|
| 588 |
+
"learning_rate": 0.00016230366492146599,
|
| 589 |
+
"loss": 0.203,
|
| 590 |
"step": 360
|
| 591 |
},
|
| 592 |
{
|
| 593 |
"epoch": 1.91,
|
| 594 |
+
"grad_norm": 4.0477294921875,
|
| 595 |
+
"learning_rate": 0.0001617801047120419,
|
| 596 |
+
"loss": 0.0646,
|
| 597 |
"step": 365
|
| 598 |
},
|
| 599 |
{
|
| 600 |
"epoch": 1.94,
|
| 601 |
+
"grad_norm": 1.0380969047546387,
|
| 602 |
+
"learning_rate": 0.0001612565445026178,
|
| 603 |
+
"loss": 0.0848,
|
| 604 |
"step": 370
|
| 605 |
},
|
| 606 |
{
|
| 607 |
"epoch": 1.96,
|
| 608 |
+
"grad_norm": 4.385131359100342,
|
| 609 |
+
"learning_rate": 0.0001607329842931937,
|
| 610 |
+
"loss": 0.166,
|
| 611 |
"step": 375
|
| 612 |
},
|
| 613 |
{
|
| 614 |
"epoch": 1.99,
|
| 615 |
+
"grad_norm": 0.036621347069740295,
|
| 616 |
+
"learning_rate": 0.00016020942408376964,
|
| 617 |
+
"loss": 0.0871,
|
| 618 |
"step": 380
|
| 619 |
},
|
| 620 |
{
|
| 621 |
"epoch": 2.02,
|
| 622 |
+
"grad_norm": 0.5929269194602966,
|
| 623 |
+
"learning_rate": 0.00015968586387434555,
|
| 624 |
+
"loss": 0.1271,
|
| 625 |
"step": 385
|
| 626 |
},
|
| 627 |
{
|
| 628 |
"epoch": 2.04,
|
| 629 |
+
"grad_norm": 0.26594266295433044,
|
| 630 |
+
"learning_rate": 0.00015916230366492146,
|
| 631 |
+
"loss": 0.0114,
|
| 632 |
"step": 390
|
| 633 |
},
|
| 634 |
{
|
| 635 |
"epoch": 2.07,
|
| 636 |
+
"grad_norm": 0.020196596160531044,
|
| 637 |
+
"learning_rate": 0.0001586387434554974,
|
| 638 |
+
"loss": 0.0081,
|
| 639 |
"step": 395
|
| 640 |
},
|
| 641 |
{
|
| 642 |
"epoch": 2.09,
|
| 643 |
+
"grad_norm": 0.6509531140327454,
|
| 644 |
+
"learning_rate": 0.0001581151832460733,
|
| 645 |
+
"loss": 0.0206,
|
| 646 |
"step": 400
|
| 647 |
},
|
| 648 |
{
|
| 649 |
"epoch": 2.09,
|
| 650 |
+
"eval_accuracy": 0.963254593175853,
|
| 651 |
+
"eval_loss": 0.130891352891922,
|
| 652 |
+
"eval_precision": 0.964741369994443,
|
| 653 |
+
"eval_recall": 0.963254593175853,
|
| 654 |
+
"eval_runtime": 17.4584,
|
| 655 |
+
"eval_samples_per_second": 43.647,
|
| 656 |
+
"eval_steps_per_second": 2.749,
|
| 657 |
"step": 400
|
| 658 |
},
|
| 659 |
{
|
| 660 |
"epoch": 2.12,
|
| 661 |
+
"grad_norm": 0.04883525148034096,
|
| 662 |
+
"learning_rate": 0.00015759162303664924,
|
| 663 |
+
"loss": 0.047,
|
| 664 |
"step": 405
|
| 665 |
},
|
| 666 |
{
|
| 667 |
"epoch": 2.15,
|
| 668 |
+
"grad_norm": 1.4584039449691772,
|
| 669 |
+
"learning_rate": 0.00015706806282722515,
|
| 670 |
+
"loss": 0.0393,
|
| 671 |
"step": 410
|
| 672 |
},
|
| 673 |
{
|
| 674 |
"epoch": 2.17,
|
| 675 |
+
"grad_norm": 0.3986053466796875,
|
| 676 |
+
"learning_rate": 0.00015654450261780105,
|
| 677 |
+
"loss": 0.0606,
|
| 678 |
"step": 415
|
| 679 |
},
|
| 680 |
{
|
| 681 |
"epoch": 2.2,
|
| 682 |
+
"grad_norm": 0.11985136568546295,
|
| 683 |
+
"learning_rate": 0.00015602094240837696,
|
| 684 |
+
"loss": 0.0379,
|
| 685 |
"step": 420
|
| 686 |
},
|
| 687 |
{
|
| 688 |
"epoch": 2.23,
|
| 689 |
+
"grad_norm": 0.07443628460168839,
|
| 690 |
+
"learning_rate": 0.0001554973821989529,
|
| 691 |
+
"loss": 0.0157,
|
| 692 |
"step": 425
|
| 693 |
},
|
| 694 |
{
|
| 695 |
"epoch": 2.25,
|
| 696 |
+
"grad_norm": 0.03219376876950264,
|
| 697 |
+
"learning_rate": 0.0001549738219895288,
|
| 698 |
+
"loss": 0.01,
|
| 699 |
"step": 430
|
| 700 |
},
|
| 701 |
{
|
| 702 |
"epoch": 2.28,
|
| 703 |
+
"grad_norm": 0.17020490765571594,
|
| 704 |
+
"learning_rate": 0.00015445026178010471,
|
| 705 |
+
"loss": 0.0093,
|
| 706 |
"step": 435
|
| 707 |
},
|
| 708 |
{
|
| 709 |
"epoch": 2.3,
|
| 710 |
+
"grad_norm": 2.6877171993255615,
|
| 711 |
+
"learning_rate": 0.00015392670157068062,
|
| 712 |
+
"loss": 0.021,
|
| 713 |
"step": 440
|
| 714 |
},
|
| 715 |
{
|
| 716 |
"epoch": 2.33,
|
| 717 |
+
"grad_norm": 0.010094034485518932,
|
| 718 |
+
"learning_rate": 0.00015340314136125656,
|
| 719 |
+
"loss": 0.0083,
|
| 720 |
"step": 445
|
| 721 |
},
|
| 722 |
{
|
| 723 |
"epoch": 2.36,
|
| 724 |
+
"grad_norm": 0.0077184755355119705,
|
| 725 |
+
"learning_rate": 0.00015287958115183247,
|
| 726 |
+
"loss": 0.0246,
|
| 727 |
"step": 450
|
| 728 |
},
|
| 729 |
{
|
| 730 |
"epoch": 2.36,
|
| 731 |
+
"eval_accuracy": 0.9553805774278216,
|
| 732 |
+
"eval_loss": 0.17534801363945007,
|
| 733 |
+
"eval_precision": 0.9586171915743325,
|
| 734 |
+
"eval_recall": 0.9553805774278216,
|
| 735 |
+
"eval_runtime": 17.505,
|
| 736 |
+
"eval_samples_per_second": 43.53,
|
| 737 |
+
"eval_steps_per_second": 2.742,
|
| 738 |
"step": 450
|
| 739 |
},
|
| 740 |
{
|
| 741 |
"epoch": 2.38,
|
| 742 |
+
"grad_norm": 5.202419757843018,
|
| 743 |
+
"learning_rate": 0.0001523560209424084,
|
| 744 |
+
"loss": 0.032,
|
| 745 |
"step": 455
|
| 746 |
},
|
| 747 |
{
|
| 748 |
"epoch": 2.41,
|
| 749 |
+
"grad_norm": 0.018663793802261353,
|
| 750 |
+
"learning_rate": 0.00015183246073298428,
|
| 751 |
+
"loss": 0.0221,
|
| 752 |
"step": 460
|
| 753 |
},
|
| 754 |
{
|
| 755 |
"epoch": 2.43,
|
| 756 |
+
"grad_norm": 1.0761280059814453,
|
| 757 |
+
"learning_rate": 0.00015130890052356022,
|
| 758 |
+
"loss": 0.0055,
|
| 759 |
"step": 465
|
| 760 |
},
|
| 761 |
{
|
| 762 |
"epoch": 2.46,
|
| 763 |
+
"grad_norm": 0.8688761591911316,
|
| 764 |
+
"learning_rate": 0.00015078534031413612,
|
| 765 |
+
"loss": 0.0852,
|
| 766 |
"step": 470
|
| 767 |
},
|
| 768 |
{
|
| 769 |
"epoch": 2.49,
|
| 770 |
+
"grad_norm": 0.06378360092639923,
|
| 771 |
+
"learning_rate": 0.00015026178010471206,
|
| 772 |
+
"loss": 0.0031,
|
| 773 |
"step": 475
|
| 774 |
},
|
| 775 |
{
|
| 776 |
"epoch": 2.51,
|
| 777 |
+
"grad_norm": 7.236721992492676,
|
| 778 |
+
"learning_rate": 0.00014973821989528797,
|
| 779 |
+
"loss": 0.0106,
|
| 780 |
"step": 480
|
| 781 |
},
|
| 782 |
{
|
| 783 |
"epoch": 2.54,
|
| 784 |
+
"grad_norm": 0.013875219039618969,
|
| 785 |
+
"learning_rate": 0.00014921465968586388,
|
| 786 |
+
"loss": 0.0032,
|
| 787 |
"step": 485
|
| 788 |
},
|
| 789 |
{
|
| 790 |
"epoch": 2.57,
|
| 791 |
+
"grad_norm": 0.031233886256814003,
|
| 792 |
+
"learning_rate": 0.0001486910994764398,
|
| 793 |
+
"loss": 0.0047,
|
| 794 |
"step": 490
|
| 795 |
},
|
| 796 |
{
|
| 797 |
"epoch": 2.59,
|
| 798 |
+
"grad_norm": 0.2528940439224243,
|
| 799 |
+
"learning_rate": 0.00014816753926701572,
|
| 800 |
+
"loss": 0.0081,
|
| 801 |
"step": 495
|
| 802 |
},
|
| 803 |
{
|
| 804 |
"epoch": 2.62,
|
| 805 |
+
"grad_norm": 0.02138712629675865,
|
| 806 |
+
"learning_rate": 0.00014764397905759163,
|
| 807 |
+
"loss": 0.0161,
|
| 808 |
"step": 500
|
| 809 |
},
|
| 810 |
{
|
| 811 |
"epoch": 2.62,
|
| 812 |
+
"eval_accuracy": 0.9514435695538058,
|
| 813 |
+
"eval_loss": 0.16896109282970428,
|
| 814 |
+
"eval_precision": 0.9537490891546931,
|
| 815 |
+
"eval_recall": 0.9514435695538058,
|
| 816 |
+
"eval_runtime": 17.5851,
|
| 817 |
+
"eval_samples_per_second": 43.332,
|
| 818 |
+
"eval_steps_per_second": 2.73,
|
| 819 |
+
"step": 500
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 2.64,
|
| 823 |
+
"grad_norm": 5.179097652435303,
|
| 824 |
+
"learning_rate": 0.00014712041884816754,
|
| 825 |
+
"loss": 0.0271,
|
| 826 |
+
"step": 505
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 2.67,
|
| 830 |
+
"grad_norm": 0.06704265624284744,
|
| 831 |
+
"learning_rate": 0.00014659685863874347,
|
| 832 |
+
"loss": 0.0072,
|
| 833 |
+
"step": 510
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 2.7,
|
| 837 |
+
"grad_norm": 0.15809708833694458,
|
| 838 |
+
"learning_rate": 0.00014607329842931938,
|
| 839 |
+
"loss": 0.0027,
|
| 840 |
+
"step": 515
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 2.72,
|
| 844 |
+
"grad_norm": 6.423127174377441,
|
| 845 |
+
"learning_rate": 0.00014554973821989531,
|
| 846 |
+
"loss": 0.0238,
|
| 847 |
+
"step": 520
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 2.75,
|
| 851 |
+
"grad_norm": 0.010630112141370773,
|
| 852 |
+
"learning_rate": 0.0001450261780104712,
|
| 853 |
+
"loss": 0.0271,
|
| 854 |
+
"step": 525
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 2.77,
|
| 858 |
+
"grad_norm": 2.8193652629852295,
|
| 859 |
+
"learning_rate": 0.00014450261780104713,
|
| 860 |
+
"loss": 0.1816,
|
| 861 |
+
"step": 530
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 2.8,
|
| 865 |
+
"grad_norm": 0.004105111118406057,
|
| 866 |
+
"learning_rate": 0.00014397905759162304,
|
| 867 |
+
"loss": 0.1842,
|
| 868 |
+
"step": 535
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 2.83,
|
| 872 |
+
"grad_norm": 0.20598988234996796,
|
| 873 |
+
"learning_rate": 0.00014345549738219897,
|
| 874 |
+
"loss": 0.0302,
|
| 875 |
+
"step": 540
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 2.85,
|
| 879 |
+
"grad_norm": 0.7738168835639954,
|
| 880 |
+
"learning_rate": 0.00014293193717277485,
|
| 881 |
+
"loss": 0.0256,
|
| 882 |
+
"step": 545
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 2.88,
|
| 886 |
+
"grad_norm": 0.07728663086891174,
|
| 887 |
+
"learning_rate": 0.0001424083769633508,
|
| 888 |
+
"loss": 0.0341,
|
| 889 |
+
"step": 550
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 2.88,
|
| 893 |
+
"eval_accuracy": 0.9488188976377953,
|
| 894 |
+
"eval_loss": 0.18862025439739227,
|
| 895 |
+
"eval_precision": 0.9543073149026239,
|
| 896 |
+
"eval_recall": 0.9488188976377953,
|
| 897 |
+
"eval_runtime": 17.3957,
|
| 898 |
+
"eval_samples_per_second": 43.804,
|
| 899 |
+
"eval_steps_per_second": 2.759,
|
| 900 |
+
"step": 550
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 2.91,
|
| 904 |
+
"grad_norm": 12.730446815490723,
|
| 905 |
+
"learning_rate": 0.0001418848167539267,
|
| 906 |
+
"loss": 0.0664,
|
| 907 |
+
"step": 555
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 2.93,
|
| 911 |
+
"grad_norm": 8.560800552368164,
|
| 912 |
+
"learning_rate": 0.00014136125654450263,
|
| 913 |
+
"loss": 0.0518,
|
| 914 |
+
"step": 560
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 2.96,
|
| 918 |
+
"grad_norm": 1.7465717792510986,
|
| 919 |
+
"learning_rate": 0.00014083769633507854,
|
| 920 |
+
"loss": 0.0236,
|
| 921 |
+
"step": 565
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 2.98,
|
| 925 |
+
"grad_norm": 5.386238098144531,
|
| 926 |
+
"learning_rate": 0.00014031413612565445,
|
| 927 |
+
"loss": 0.0449,
|
| 928 |
+
"step": 570
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 3.01,
|
| 932 |
+
"grad_norm": 0.008860424160957336,
|
| 933 |
+
"learning_rate": 0.00013979057591623038,
|
| 934 |
+
"loss": 0.0168,
|
| 935 |
+
"step": 575
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 3.04,
|
| 939 |
+
"grad_norm": 0.0057926299050450325,
|
| 940 |
+
"learning_rate": 0.0001392670157068063,
|
| 941 |
+
"loss": 0.0191,
|
| 942 |
+
"step": 580
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 3.06,
|
| 946 |
+
"grad_norm": 0.5266512036323547,
|
| 947 |
+
"learning_rate": 0.00013874345549738223,
|
| 948 |
+
"loss": 0.0023,
|
| 949 |
+
"step": 585
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 3.09,
|
| 953 |
+
"grad_norm": 0.03807899355888367,
|
| 954 |
+
"learning_rate": 0.0001382198952879581,
|
| 955 |
+
"loss": 0.0259,
|
| 956 |
+
"step": 590
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 3.12,
|
| 960 |
+
"grad_norm": 0.41590607166290283,
|
| 961 |
+
"learning_rate": 0.00013769633507853404,
|
| 962 |
+
"loss": 0.0224,
|
| 963 |
+
"step": 595
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 3.14,
|
| 967 |
+
"grad_norm": 0.003112237202003598,
|
| 968 |
+
"learning_rate": 0.00013717277486910995,
|
| 969 |
+
"loss": 0.0022,
|
| 970 |
+
"step": 600
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 3.14,
|
| 974 |
"eval_accuracy": 0.963254593175853,
|
| 975 |
+
"eval_loss": 0.1624463051557541,
|
| 976 |
+
"eval_precision": 0.9649964224541913,
|
| 977 |
"eval_recall": 0.963254593175853,
|
| 978 |
+
"eval_runtime": 17.4244,
|
| 979 |
+
"eval_samples_per_second": 43.732,
|
| 980 |
+
"eval_steps_per_second": 2.755,
|
| 981 |
+
"step": 600
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 3.17,
|
| 985 |
+
"grad_norm": 0.013240986503660679,
|
| 986 |
+
"learning_rate": 0.00013664921465968589,
|
| 987 |
+
"loss": 0.0096,
|
| 988 |
+
"step": 605
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 3.19,
|
| 992 |
+
"grad_norm": 0.13229414820671082,
|
| 993 |
+
"learning_rate": 0.0001361256544502618,
|
| 994 |
+
"loss": 0.0016,
|
| 995 |
+
"step": 610
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 3.22,
|
| 999 |
+
"grad_norm": 0.2047564685344696,
|
| 1000 |
+
"learning_rate": 0.0001356020942408377,
|
| 1001 |
+
"loss": 0.0029,
|
| 1002 |
+
"step": 615
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 3.25,
|
| 1006 |
+
"grad_norm": 5.075094699859619,
|
| 1007 |
+
"learning_rate": 0.0001350785340314136,
|
| 1008 |
+
"loss": 0.1541,
|
| 1009 |
+
"step": 620
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 3.27,
|
| 1013 |
+
"grad_norm": 0.11219122260808945,
|
| 1014 |
+
"learning_rate": 0.00013455497382198955,
|
| 1015 |
+
"loss": 0.0016,
|
| 1016 |
+
"step": 625
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 3.3,
|
| 1020 |
+
"grad_norm": 0.0553029403090477,
|
| 1021 |
+
"learning_rate": 0.00013403141361256545,
|
| 1022 |
+
"loss": 0.0016,
|
| 1023 |
+
"step": 630
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 3.32,
|
| 1027 |
+
"grad_norm": 0.1759098470211029,
|
| 1028 |
+
"learning_rate": 0.00013350785340314136,
|
| 1029 |
+
"loss": 0.0616,
|
| 1030 |
+
"step": 635
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 3.35,
|
| 1034 |
+
"grad_norm": 0.29212847352027893,
|
| 1035 |
+
"learning_rate": 0.00013298429319371727,
|
| 1036 |
+
"loss": 0.0074,
|
| 1037 |
+
"step": 640
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 3.38,
|
| 1041 |
+
"grad_norm": 0.02130221202969551,
|
| 1042 |
+
"learning_rate": 0.0001324607329842932,
|
| 1043 |
+
"loss": 0.0013,
|
| 1044 |
+
"step": 645
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 3.4,
|
| 1048 |
+
"grad_norm": 1.0668525695800781,
|
| 1049 |
+
"learning_rate": 0.0001319371727748691,
|
| 1050 |
+
"loss": 0.0044,
|
| 1051 |
+
"step": 650
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 3.4,
|
| 1055 |
+
"eval_accuracy": 0.937007874015748,
|
| 1056 |
+
"eval_loss": 0.22285035252571106,
|
| 1057 |
+
"eval_precision": 0.9410975298976415,
|
| 1058 |
+
"eval_recall": 0.937007874015748,
|
| 1059 |
+
"eval_runtime": 17.5444,
|
| 1060 |
+
"eval_samples_per_second": 43.433,
|
| 1061 |
+
"eval_steps_per_second": 2.736,
|
| 1062 |
+
"step": 650
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 3.43,
|
| 1066 |
+
"grad_norm": 0.27807894349098206,
|
| 1067 |
+
"learning_rate": 0.00013141361256544505,
|
| 1068 |
+
"loss": 0.0669,
|
| 1069 |
+
"step": 655
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 3.46,
|
| 1073 |
+
"grad_norm": 0.17472220957279205,
|
| 1074 |
+
"learning_rate": 0.00013089005235602096,
|
| 1075 |
+
"loss": 0.0066,
|
| 1076 |
+
"step": 660
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 3.48,
|
| 1080 |
+
"grad_norm": 0.07417164742946625,
|
| 1081 |
+
"learning_rate": 0.00013036649214659686,
|
| 1082 |
+
"loss": 0.0045,
|
| 1083 |
+
"step": 665
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 3.51,
|
| 1087 |
+
"grad_norm": 0.007742606569081545,
|
| 1088 |
+
"learning_rate": 0.00012984293193717277,
|
| 1089 |
+
"loss": 0.0008,
|
| 1090 |
+
"step": 670
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 3.53,
|
| 1094 |
+
"grad_norm": 0.00367438024841249,
|
| 1095 |
+
"learning_rate": 0.0001293193717277487,
|
| 1096 |
+
"loss": 0.003,
|
| 1097 |
+
"step": 675
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 3.56,
|
| 1101 |
+
"grad_norm": 0.0222078375518322,
|
| 1102 |
+
"learning_rate": 0.00012879581151832462,
|
| 1103 |
+
"loss": 0.0017,
|
| 1104 |
+
"step": 680
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 3.59,
|
| 1108 |
+
"grad_norm": 6.7436299324035645,
|
| 1109 |
+
"learning_rate": 0.00012827225130890052,
|
| 1110 |
+
"loss": 0.0179,
|
| 1111 |
+
"step": 685
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 3.61,
|
| 1115 |
+
"grad_norm": 0.0018994753481820226,
|
| 1116 |
+
"learning_rate": 0.00012774869109947646,
|
| 1117 |
+
"loss": 0.0008,
|
| 1118 |
+
"step": 690
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 3.64,
|
| 1122 |
+
"grad_norm": 0.005384970456361771,
|
| 1123 |
+
"learning_rate": 0.00012722513089005237,
|
| 1124 |
+
"loss": 0.0018,
|
| 1125 |
+
"step": 695
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 3.66,
|
| 1129 |
+
"grad_norm": 0.0077237836085259914,
|
| 1130 |
+
"learning_rate": 0.00012670157068062827,
|
| 1131 |
+
"loss": 0.0012,
|
| 1132 |
+
"step": 700
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 3.66,
|
| 1136 |
+
"eval_accuracy": 0.9501312335958005,
|
| 1137 |
+
"eval_loss": 0.17090748250484467,
|
| 1138 |
+
"eval_precision": 0.9525764956521452,
|
| 1139 |
+
"eval_recall": 0.9501312335958005,
|
| 1140 |
+
"eval_runtime": 17.5175,
|
| 1141 |
+
"eval_samples_per_second": 43.499,
|
| 1142 |
+
"eval_steps_per_second": 2.74,
|
| 1143 |
+
"step": 700
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 3.69,
|
| 1147 |
+
"grad_norm": 0.016971301287412643,
|
| 1148 |
+
"learning_rate": 0.00012617801047120418,
|
| 1149 |
+
"loss": 0.0672,
|
| 1150 |
+
"step": 705
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 3.72,
|
| 1154 |
+
"grad_norm": 0.37131184339523315,
|
| 1155 |
+
"learning_rate": 0.00012565445026178012,
|
| 1156 |
+
"loss": 0.0032,
|
| 1157 |
+
"step": 710
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 3.74,
|
| 1161 |
+
"grad_norm": 0.020785262808203697,
|
| 1162 |
+
"learning_rate": 0.00012513089005235603,
|
| 1163 |
+
"loss": 0.0036,
|
| 1164 |
+
"step": 715
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 3.77,
|
| 1168 |
+
"grad_norm": 0.003909711726009846,
|
| 1169 |
+
"learning_rate": 0.00012460732984293196,
|
| 1170 |
+
"loss": 0.0005,
|
| 1171 |
+
"step": 720
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 3.8,
|
| 1175 |
+
"grad_norm": 0.32289111614227295,
|
| 1176 |
+
"learning_rate": 0.00012408376963350784,
|
| 1177 |
+
"loss": 0.0067,
|
| 1178 |
+
"step": 725
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 3.82,
|
| 1182 |
+
"grad_norm": 0.011649747379124165,
|
| 1183 |
+
"learning_rate": 0.00012356020942408378,
|
| 1184 |
+
"loss": 0.0004,
|
| 1185 |
+
"step": 730
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 3.85,
|
| 1189 |
+
"grad_norm": 0.009505286812782288,
|
| 1190 |
+
"learning_rate": 0.00012303664921465968,
|
| 1191 |
+
"loss": 0.0004,
|
| 1192 |
+
"step": 735
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 3.87,
|
| 1196 |
+
"grad_norm": 0.016009971499443054,
|
| 1197 |
+
"learning_rate": 0.00012251308900523562,
|
| 1198 |
+
"loss": 0.0132,
|
| 1199 |
+
"step": 740
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 3.9,
|
| 1203 |
+
"grad_norm": 0.07612348347902298,
|
| 1204 |
+
"learning_rate": 0.00012198952879581151,
|
| 1205 |
+
"loss": 0.0012,
|
| 1206 |
+
"step": 745
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 3.93,
|
| 1210 |
+
"grad_norm": 0.05622846260666847,
|
| 1211 |
+
"learning_rate": 0.00012146596858638744,
|
| 1212 |
+
"loss": 0.0058,
|
| 1213 |
+
"step": 750
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 3.93,
|
| 1217 |
+
"eval_accuracy": 0.958005249343832,
|
| 1218 |
+
"eval_loss": 0.17302347719669342,
|
| 1219 |
+
"eval_precision": 0.9602924010464745,
|
| 1220 |
+
"eval_recall": 0.958005249343832,
|
| 1221 |
+
"eval_runtime": 17.4895,
|
| 1222 |
+
"eval_samples_per_second": 43.569,
|
| 1223 |
+
"eval_steps_per_second": 2.744,
|
| 1224 |
+
"step": 750
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 3.95,
|
| 1228 |
+
"grad_norm": 0.050630178302526474,
|
| 1229 |
+
"learning_rate": 0.00012094240837696336,
|
| 1230 |
+
"loss": 0.0008,
|
| 1231 |
+
"step": 755
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 3.98,
|
| 1235 |
+
"grad_norm": 0.02956685610115528,
|
| 1236 |
+
"learning_rate": 0.00012041884816753928,
|
| 1237 |
+
"loss": 0.0017,
|
| 1238 |
+
"step": 760
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 4.01,
|
| 1242 |
+
"grad_norm": 0.038056932389736176,
|
| 1243 |
+
"learning_rate": 0.0001198952879581152,
|
| 1244 |
+
"loss": 0.001,
|
| 1245 |
+
"step": 765
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 4.03,
|
| 1249 |
+
"grad_norm": 0.006303295027464628,
|
| 1250 |
+
"learning_rate": 0.0001193717277486911,
|
| 1251 |
+
"loss": 0.0003,
|
| 1252 |
+
"step": 770
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 4.06,
|
| 1256 |
+
"grad_norm": 0.019060682505369186,
|
| 1257 |
+
"learning_rate": 0.00011884816753926702,
|
| 1258 |
+
"loss": 0.0005,
|
| 1259 |
+
"step": 775
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 4.08,
|
| 1263 |
+
"grad_norm": 0.9220014810562134,
|
| 1264 |
+
"learning_rate": 0.00011832460732984294,
|
| 1265 |
+
"loss": 0.0014,
|
| 1266 |
+
"step": 780
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 4.11,
|
| 1270 |
+
"grad_norm": 0.0184442438185215,
|
| 1271 |
+
"learning_rate": 0.00011780104712041886,
|
| 1272 |
+
"loss": 0.0003,
|
| 1273 |
+
"step": 785
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 4.14,
|
| 1277 |
+
"grad_norm": 0.003219619393348694,
|
| 1278 |
+
"learning_rate": 0.00011727748691099475,
|
| 1279 |
+
"loss": 0.0003,
|
| 1280 |
+
"step": 790
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 4.16,
|
| 1284 |
+
"grad_norm": 0.006713965907692909,
|
| 1285 |
+
"learning_rate": 0.00011675392670157068,
|
| 1286 |
+
"loss": 0.0044,
|
| 1287 |
+
"step": 795
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 4.19,
|
| 1291 |
+
"grad_norm": 0.0026614165399223566,
|
| 1292 |
+
"learning_rate": 0.0001162303664921466,
|
| 1293 |
+
"loss": 0.0003,
|
| 1294 |
+
"step": 800
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 4.19,
|
| 1298 |
+
"eval_accuracy": 0.9488188976377953,
|
| 1299 |
+
"eval_loss": 0.20851939916610718,
|
| 1300 |
+
"eval_precision": 0.9513993632135537,
|
| 1301 |
+
"eval_recall": 0.9488188976377953,
|
| 1302 |
+
"eval_runtime": 17.4973,
|
| 1303 |
+
"eval_samples_per_second": 43.55,
|
| 1304 |
+
"eval_steps_per_second": 2.743,
|
| 1305 |
+
"step": 800
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 4.21,
|
| 1309 |
+
"grad_norm": 0.2586454749107361,
|
| 1310 |
+
"learning_rate": 0.00011570680628272252,
|
| 1311 |
+
"loss": 0.001,
|
| 1312 |
+
"step": 805
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 4.24,
|
| 1316 |
+
"grad_norm": 0.005604247096925974,
|
| 1317 |
+
"learning_rate": 0.00011518324607329844,
|
| 1318 |
+
"loss": 0.0027,
|
| 1319 |
+
"step": 810
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 4.27,
|
| 1323 |
+
"grad_norm": 0.00321913487277925,
|
| 1324 |
+
"learning_rate": 0.00011465968586387435,
|
| 1325 |
+
"loss": 0.0002,
|
| 1326 |
+
"step": 815
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 4.29,
|
| 1330 |
+
"grad_norm": 0.00729359732940793,
|
| 1331 |
+
"learning_rate": 0.00011413612565445027,
|
| 1332 |
+
"loss": 0.0068,
|
| 1333 |
+
"step": 820
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 4.32,
|
| 1337 |
+
"grad_norm": 2.0007290840148926,
|
| 1338 |
+
"learning_rate": 0.00011361256544502619,
|
| 1339 |
+
"loss": 0.002,
|
| 1340 |
+
"step": 825
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 4.35,
|
| 1344 |
+
"grad_norm": 0.0031692993361502886,
|
| 1345 |
+
"learning_rate": 0.00011308900523560211,
|
| 1346 |
+
"loss": 0.0005,
|
| 1347 |
+
"step": 830
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 4.37,
|
| 1351 |
+
"grad_norm": 0.007637929171323776,
|
| 1352 |
+
"learning_rate": 0.00011256544502617801,
|
| 1353 |
+
"loss": 0.0002,
|
| 1354 |
+
"step": 835
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 4.4,
|
| 1358 |
+
"grad_norm": 0.003380405716598034,
|
| 1359 |
+
"learning_rate": 0.00011204188481675393,
|
| 1360 |
+
"loss": 0.0002,
|
| 1361 |
+
"step": 840
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 4.42,
|
| 1365 |
+
"grad_norm": 0.0019728606566786766,
|
| 1366 |
+
"learning_rate": 0.00011151832460732985,
|
| 1367 |
+
"loss": 0.0005,
|
| 1368 |
+
"step": 845
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 4.45,
|
| 1372 |
+
"grad_norm": 0.0047022090293467045,
|
| 1373 |
+
"learning_rate": 0.00011099476439790577,
|
| 1374 |
+
"loss": 0.0003,
|
| 1375 |
+
"step": 850
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 4.45,
|
| 1379 |
+
"eval_accuracy": 0.9698162729658792,
|
| 1380 |
+
"eval_loss": 0.1316651999950409,
|
| 1381 |
+
"eval_precision": 0.9708177710817824,
|
| 1382 |
+
"eval_recall": 0.9698162729658792,
|
| 1383 |
+
"eval_runtime": 17.4736,
|
| 1384 |
+
"eval_samples_per_second": 43.609,
|
| 1385 |
+
"eval_steps_per_second": 2.747,
|
| 1386 |
+
"step": 850
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 4.48,
|
| 1390 |
+
"grad_norm": 0.003034041728824377,
|
| 1391 |
+
"learning_rate": 0.0001104712041884817,
|
| 1392 |
+
"loss": 0.0002,
|
| 1393 |
+
"step": 855
|
| 1394 |
+
},
|
| 1395 |
+
{
|
| 1396 |
+
"epoch": 4.5,
|
| 1397 |
+
"grad_norm": 0.0816386267542839,
|
| 1398 |
+
"learning_rate": 0.00010994764397905759,
|
| 1399 |
+
"loss": 0.0005,
|
| 1400 |
+
"step": 860
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 4.53,
|
| 1404 |
+
"grad_norm": 0.010150614194571972,
|
| 1405 |
+
"learning_rate": 0.00010942408376963351,
|
| 1406 |
+
"loss": 0.0004,
|
| 1407 |
+
"step": 865
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 4.55,
|
| 1411 |
+
"grad_norm": 0.003652422921732068,
|
| 1412 |
+
"learning_rate": 0.00010890052356020943,
|
| 1413 |
+
"loss": 0.0002,
|
| 1414 |
+
"step": 870
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"epoch": 4.58,
|
| 1418 |
+
"grad_norm": 0.0027291346341371536,
|
| 1419 |
+
"learning_rate": 0.00010837696335078535,
|
| 1420 |
+
"loss": 0.0002,
|
| 1421 |
+
"step": 875
|
| 1422 |
+
},
|
| 1423 |
+
{
|
| 1424 |
+
"epoch": 4.61,
|
| 1425 |
+
"grad_norm": 0.0021885058376938105,
|
| 1426 |
+
"learning_rate": 0.00010785340314136125,
|
| 1427 |
+
"loss": 0.0002,
|
| 1428 |
+
"step": 880
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 4.63,
|
| 1432 |
+
"grad_norm": 0.0019014202989637852,
|
| 1433 |
+
"learning_rate": 0.00010732984293193717,
|
| 1434 |
+
"loss": 0.0002,
|
| 1435 |
+
"step": 885
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 4.66,
|
| 1439 |
+
"grad_norm": 0.9188545942306519,
|
| 1440 |
+
"learning_rate": 0.00010680628272251309,
|
| 1441 |
+
"loss": 0.0032,
|
| 1442 |
+
"step": 890
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 4.69,
|
| 1446 |
+
"grad_norm": 0.0015793447382748127,
|
| 1447 |
+
"learning_rate": 0.00010628272251308901,
|
| 1448 |
+
"loss": 0.0002,
|
| 1449 |
+
"step": 895
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 4.71,
|
| 1453 |
+
"grad_norm": 0.0016003657365217805,
|
| 1454 |
+
"learning_rate": 0.00010575916230366492,
|
| 1455 |
+
"loss": 0.0002,
|
| 1456 |
+
"step": 900
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 4.71,
|
| 1460 |
+
"eval_accuracy": 0.9698162729658792,
|
| 1461 |
+
"eval_loss": 0.12266764789819717,
|
| 1462 |
+
"eval_precision": 0.9709897987678096,
|
| 1463 |
+
"eval_recall": 0.9698162729658792,
|
| 1464 |
+
"eval_runtime": 17.6013,
|
| 1465 |
+
"eval_samples_per_second": 43.292,
|
| 1466 |
+
"eval_steps_per_second": 2.727,
|
| 1467 |
+
"step": 900
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 4.74,
|
| 1471 |
+
"grad_norm": 0.001760563114657998,
|
| 1472 |
+
"learning_rate": 0.00010523560209424084,
|
| 1473 |
+
"loss": 0.0002,
|
| 1474 |
+
"step": 905
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 4.76,
|
| 1478 |
+
"grad_norm": 0.14921420812606812,
|
| 1479 |
+
"learning_rate": 0.00010471204188481676,
|
| 1480 |
+
"loss": 0.0007,
|
| 1481 |
+
"step": 910
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 4.79,
|
| 1485 |
+
"grad_norm": 0.008730238303542137,
|
| 1486 |
+
"learning_rate": 0.00010418848167539269,
|
| 1487 |
+
"loss": 0.0005,
|
| 1488 |
+
"step": 915
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 4.82,
|
| 1492 |
+
"grad_norm": 0.0021068351343274117,
|
| 1493 |
+
"learning_rate": 0.0001036649214659686,
|
| 1494 |
+
"loss": 0.0004,
|
| 1495 |
+
"step": 920
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 4.84,
|
| 1499 |
+
"grad_norm": 0.0018881463911384344,
|
| 1500 |
+
"learning_rate": 0.0001031413612565445,
|
| 1501 |
+
"loss": 0.0002,
|
| 1502 |
+
"step": 925
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 4.87,
|
| 1506 |
+
"grad_norm": 0.010380023159086704,
|
| 1507 |
+
"learning_rate": 0.00010261780104712042,
|
| 1508 |
+
"loss": 0.0002,
|
| 1509 |
+
"step": 930
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 4.9,
|
| 1513 |
+
"grad_norm": 0.005413604434579611,
|
| 1514 |
+
"learning_rate": 0.00010209424083769635,
|
| 1515 |
+
"loss": 0.0435,
|
| 1516 |
+
"step": 935
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 4.92,
|
| 1520 |
+
"grad_norm": 0.013811178505420685,
|
| 1521 |
+
"learning_rate": 0.00010157068062827227,
|
| 1522 |
+
"loss": 0.0002,
|
| 1523 |
+
"step": 940
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 4.95,
|
| 1527 |
+
"grad_norm": 0.0024414085783064365,
|
| 1528 |
+
"learning_rate": 0.00010104712041884816,
|
| 1529 |
+
"loss": 0.0014,
|
| 1530 |
+
"step": 945
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 4.97,
|
| 1534 |
+
"grad_norm": 0.00615642499178648,
|
| 1535 |
+
"learning_rate": 0.00010052356020942408,
|
| 1536 |
+
"loss": 0.0004,
|
| 1537 |
+
"step": 950
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 4.97,
|
| 1541 |
+
"eval_accuracy": 0.9711286089238845,
|
| 1542 |
+
"eval_loss": 0.12034053355455399,
|
| 1543 |
+
"eval_precision": 0.9732646926949845,
|
| 1544 |
+
"eval_recall": 0.9711286089238845,
|
| 1545 |
+
"eval_runtime": 17.6401,
|
| 1546 |
+
"eval_samples_per_second": 43.197,
|
| 1547 |
+
"eval_steps_per_second": 2.721,
|
| 1548 |
+
"step": 950
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 5.0,
|
| 1552 |
+
"grad_norm": 1.5034066438674927,
|
| 1553 |
+
"learning_rate": 0.0001,
|
| 1554 |
+
"loss": 0.0035,
|
| 1555 |
+
"step": 955
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"epoch": 5.03,
|
| 1559 |
+
"grad_norm": 0.0023136490490287542,
|
| 1560 |
+
"learning_rate": 9.947643979057593e-05,
|
| 1561 |
+
"loss": 0.0002,
|
| 1562 |
+
"step": 960
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 5.05,
|
| 1566 |
+
"grad_norm": 0.025553325191140175,
|
| 1567 |
+
"learning_rate": 9.895287958115183e-05,
|
| 1568 |
+
"loss": 0.0003,
|
| 1569 |
+
"step": 965
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 5.08,
|
| 1573 |
+
"grad_norm": 0.0021953664254397154,
|
| 1574 |
+
"learning_rate": 9.842931937172776e-05,
|
| 1575 |
+
"loss": 0.0002,
|
| 1576 |
+
"step": 970
|
| 1577 |
+
},
|
| 1578 |
+
{
|
| 1579 |
+
"epoch": 5.1,
|
| 1580 |
+
"grad_norm": 0.0016761135775595903,
|
| 1581 |
+
"learning_rate": 9.790575916230366e-05,
|
| 1582 |
+
"loss": 0.0002,
|
| 1583 |
+
"step": 975
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 5.13,
|
| 1587 |
+
"grad_norm": 0.001983917085453868,
|
| 1588 |
+
"learning_rate": 9.738219895287959e-05,
|
| 1589 |
+
"loss": 0.0002,
|
| 1590 |
+
"step": 980
|
| 1591 |
+
},
|
| 1592 |
+
{
|
| 1593 |
+
"epoch": 5.16,
|
| 1594 |
+
"grad_norm": 0.008785477839410305,
|
| 1595 |
+
"learning_rate": 9.68586387434555e-05,
|
| 1596 |
+
"loss": 0.0003,
|
| 1597 |
+
"step": 985
|
| 1598 |
+
},
|
| 1599 |
+
{
|
| 1600 |
+
"epoch": 5.18,
|
| 1601 |
+
"grad_norm": 0.00397130474448204,
|
| 1602 |
+
"learning_rate": 9.633507853403142e-05,
|
| 1603 |
+
"loss": 0.0002,
|
| 1604 |
+
"step": 990
|
| 1605 |
+
},
|
| 1606 |
+
{
|
| 1607 |
+
"epoch": 5.21,
|
| 1608 |
+
"grad_norm": 0.0015918458811938763,
|
| 1609 |
+
"learning_rate": 9.581151832460732e-05,
|
| 1610 |
+
"loss": 0.0003,
|
| 1611 |
+
"step": 995
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 5.24,
|
| 1615 |
+
"grad_norm": 0.0018075347179546952,
|
| 1616 |
+
"learning_rate": 9.528795811518324e-05,
|
| 1617 |
+
"loss": 0.0002,
|
| 1618 |
+
"step": 1000
|
| 1619 |
+
},
|
| 1620 |
+
{
|
| 1621 |
+
"epoch": 5.24,
|
| 1622 |
+
"eval_accuracy": 0.958005249343832,
|
| 1623 |
+
"eval_loss": 0.19232842326164246,
|
| 1624 |
+
"eval_precision": 0.960493858579392,
|
| 1625 |
+
"eval_recall": 0.958005249343832,
|
| 1626 |
+
"eval_runtime": 17.4659,
|
| 1627 |
+
"eval_samples_per_second": 43.628,
|
| 1628 |
+
"eval_steps_per_second": 2.748,
|
| 1629 |
+
"step": 1000
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 5.26,
|
| 1633 |
+
"grad_norm": 0.0014983582077547908,
|
| 1634 |
+
"learning_rate": 9.476439790575917e-05,
|
| 1635 |
+
"loss": 0.0003,
|
| 1636 |
+
"step": 1005
|
| 1637 |
+
},
|
| 1638 |
+
{
|
| 1639 |
+
"epoch": 5.29,
|
| 1640 |
+
"grad_norm": 0.004939761478453875,
|
| 1641 |
+
"learning_rate": 9.424083769633509e-05,
|
| 1642 |
+
"loss": 0.0025,
|
| 1643 |
+
"step": 1010
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 5.31,
|
| 1647 |
+
"grad_norm": 0.003176321741193533,
|
| 1648 |
+
"learning_rate": 9.371727748691101e-05,
|
| 1649 |
+
"loss": 0.0002,
|
| 1650 |
+
"step": 1015
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 5.34,
|
| 1654 |
+
"grad_norm": 0.008645892143249512,
|
| 1655 |
+
"learning_rate": 9.319371727748692e-05,
|
| 1656 |
+
"loss": 0.0002,
|
| 1657 |
+
"step": 1020
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 5.37,
|
| 1661 |
+
"grad_norm": 0.009872050024569035,
|
| 1662 |
+
"learning_rate": 9.267015706806284e-05,
|
| 1663 |
+
"loss": 0.0002,
|
| 1664 |
+
"step": 1025
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 5.39,
|
| 1668 |
+
"grad_norm": 0.0015197212342172861,
|
| 1669 |
+
"learning_rate": 9.214659685863875e-05,
|
| 1670 |
+
"loss": 0.0001,
|
| 1671 |
+
"step": 1030
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 5.42,
|
| 1675 |
+
"grad_norm": 0.0035685019101947546,
|
| 1676 |
+
"learning_rate": 9.162303664921467e-05,
|
| 1677 |
+
"loss": 0.0002,
|
| 1678 |
+
"step": 1035
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 5.45,
|
| 1682 |
+
"grad_norm": 0.0015960617456585169,
|
| 1683 |
+
"learning_rate": 9.109947643979058e-05,
|
| 1684 |
+
"loss": 0.0002,
|
| 1685 |
+
"step": 1040
|
| 1686 |
+
},
|
| 1687 |
+
{
|
| 1688 |
+
"epoch": 5.47,
|
| 1689 |
+
"grad_norm": 0.0019863061606884003,
|
| 1690 |
+
"learning_rate": 9.05759162303665e-05,
|
| 1691 |
+
"loss": 0.0036,
|
| 1692 |
+
"step": 1045
|
| 1693 |
+
},
|
| 1694 |
+
{
|
| 1695 |
+
"epoch": 5.5,
|
| 1696 |
+
"grad_norm": 0.0011158788111060858,
|
| 1697 |
+
"learning_rate": 9.00523560209424e-05,
|
| 1698 |
+
"loss": 0.0001,
|
| 1699 |
+
"step": 1050
|
| 1700 |
+
},
|
| 1701 |
+
{
|
| 1702 |
+
"epoch": 5.5,
|
| 1703 |
+
"eval_accuracy": 0.9711286089238845,
|
| 1704 |
+
"eval_loss": 0.11267632246017456,
|
| 1705 |
+
"eval_precision": 0.9717079331418645,
|
| 1706 |
+
"eval_recall": 0.9711286089238845,
|
| 1707 |
+
"eval_runtime": 17.5861,
|
| 1708 |
+
"eval_samples_per_second": 43.33,
|
| 1709 |
+
"eval_steps_per_second": 2.729,
|
| 1710 |
+
"step": 1050
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 5.52,
|
| 1714 |
+
"grad_norm": 0.003642949042841792,
|
| 1715 |
+
"learning_rate": 8.952879581151833e-05,
|
| 1716 |
+
"loss": 0.0002,
|
| 1717 |
+
"step": 1055
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 5.55,
|
| 1721 |
+
"grad_norm": 2.638040781021118,
|
| 1722 |
+
"learning_rate": 8.900523560209425e-05,
|
| 1723 |
+
"loss": 0.0021,
|
| 1724 |
+
"step": 1060
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 5.58,
|
| 1728 |
+
"grad_norm": 5.575833320617676,
|
| 1729 |
+
"learning_rate": 8.848167539267016e-05,
|
| 1730 |
+
"loss": 0.0068,
|
| 1731 |
+
"step": 1065
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 5.6,
|
| 1735 |
+
"grad_norm": 0.0017755662556737661,
|
| 1736 |
+
"learning_rate": 8.795811518324608e-05,
|
| 1737 |
+
"loss": 0.0001,
|
| 1738 |
+
"step": 1070
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 5.63,
|
| 1742 |
+
"grad_norm": 0.0034077195450663567,
|
| 1743 |
+
"learning_rate": 8.743455497382199e-05,
|
| 1744 |
+
"loss": 0.0003,
|
| 1745 |
+
"step": 1075
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 5.65,
|
| 1749 |
+
"grad_norm": 0.003383865812793374,
|
| 1750 |
+
"learning_rate": 8.691099476439791e-05,
|
| 1751 |
+
"loss": 0.0004,
|
| 1752 |
+
"step": 1080
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 5.68,
|
| 1756 |
+
"grad_norm": 0.0037927927915006876,
|
| 1757 |
+
"learning_rate": 8.638743455497382e-05,
|
| 1758 |
+
"loss": 0.0025,
|
| 1759 |
+
"step": 1085
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 5.71,
|
| 1763 |
+
"grad_norm": 0.008559320122003555,
|
| 1764 |
+
"learning_rate": 8.586387434554974e-05,
|
| 1765 |
+
"loss": 0.0002,
|
| 1766 |
+
"step": 1090
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 5.73,
|
| 1770 |
+
"grad_norm": 0.0041591702029109,
|
| 1771 |
+
"learning_rate": 8.534031413612566e-05,
|
| 1772 |
+
"loss": 0.0002,
|
| 1773 |
+
"step": 1095
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 5.76,
|
| 1777 |
+
"grad_norm": 0.0011583847226575017,
|
| 1778 |
+
"learning_rate": 8.481675392670158e-05,
|
| 1779 |
+
"loss": 0.0003,
|
| 1780 |
+
"step": 1100
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 5.76,
|
| 1784 |
+
"eval_accuracy": 0.9711286089238845,
|
| 1785 |
+
"eval_loss": 0.13462768495082855,
|
| 1786 |
+
"eval_precision": 0.9722333613195212,
|
| 1787 |
+
"eval_recall": 0.9711286089238845,
|
| 1788 |
+
"eval_runtime": 17.6983,
|
| 1789 |
+
"eval_samples_per_second": 43.055,
|
| 1790 |
+
"eval_steps_per_second": 2.712,
|
| 1791 |
+
"step": 1100
|
| 1792 |
+
},
|
| 1793 |
+
{
|
| 1794 |
+
"epoch": 5.79,
|
| 1795 |
+
"grad_norm": 0.0030487922485917807,
|
| 1796 |
+
"learning_rate": 8.429319371727749e-05,
|
| 1797 |
+
"loss": 0.0002,
|
| 1798 |
+
"step": 1105
|
| 1799 |
+
},
|
| 1800 |
+
{
|
| 1801 |
+
"epoch": 5.81,
|
| 1802 |
+
"grad_norm": 0.003955108113586903,
|
| 1803 |
+
"learning_rate": 8.376963350785341e-05,
|
| 1804 |
+
"loss": 0.0002,
|
| 1805 |
+
"step": 1110
|
| 1806 |
+
},
|
| 1807 |
+
{
|
| 1808 |
+
"epoch": 5.84,
|
| 1809 |
+
"grad_norm": 0.002146199345588684,
|
| 1810 |
+
"learning_rate": 8.324607329842933e-05,
|
| 1811 |
+
"loss": 0.0001,
|
| 1812 |
+
"step": 1115
|
| 1813 |
+
},
|
| 1814 |
+
{
|
| 1815 |
+
"epoch": 5.86,
|
| 1816 |
+
"grad_norm": 0.0010180504759773612,
|
| 1817 |
+
"learning_rate": 8.272251308900524e-05,
|
| 1818 |
+
"loss": 0.0002,
|
| 1819 |
+
"step": 1120
|
| 1820 |
+
},
|
| 1821 |
+
{
|
| 1822 |
+
"epoch": 5.89,
|
| 1823 |
+
"grad_norm": 0.0008741291239857674,
|
| 1824 |
+
"learning_rate": 8.219895287958116e-05,
|
| 1825 |
+
"loss": 0.0001,
|
| 1826 |
+
"step": 1125
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 5.92,
|
| 1830 |
+
"grad_norm": 0.0017273599514737725,
|
| 1831 |
+
"learning_rate": 8.167539267015707e-05,
|
| 1832 |
+
"loss": 0.0071,
|
| 1833 |
+
"step": 1130
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 5.94,
|
| 1837 |
+
"grad_norm": 0.003460003063082695,
|
| 1838 |
+
"learning_rate": 8.115183246073299e-05,
|
| 1839 |
+
"loss": 0.0006,
|
| 1840 |
+
"step": 1135
|
| 1841 |
+
},
|
| 1842 |
+
{
|
| 1843 |
+
"epoch": 5.97,
|
| 1844 |
+
"grad_norm": 0.0010187524603679776,
|
| 1845 |
+
"learning_rate": 8.06282722513089e-05,
|
| 1846 |
+
"loss": 0.0001,
|
| 1847 |
+
"step": 1140
|
| 1848 |
+
},
|
| 1849 |
+
{
|
| 1850 |
+
"epoch": 5.99,
|
| 1851 |
+
"grad_norm": 0.0035252266097813845,
|
| 1852 |
+
"learning_rate": 8.010471204188482e-05,
|
| 1853 |
+
"loss": 0.0009,
|
| 1854 |
+
"step": 1145
|
| 1855 |
+
},
|
| 1856 |
+
{
|
| 1857 |
+
"epoch": 6.02,
|
| 1858 |
+
"grad_norm": 0.0013756396947428584,
|
| 1859 |
+
"learning_rate": 7.958115183246073e-05,
|
| 1860 |
+
"loss": 0.0001,
|
| 1861 |
+
"step": 1150
|
| 1862 |
+
},
|
| 1863 |
+
{
|
| 1864 |
+
"epoch": 6.02,
|
| 1865 |
+
"eval_accuracy": 0.9711286089238845,
|
| 1866 |
+
"eval_loss": 0.11907853186130524,
|
| 1867 |
+
"eval_precision": 0.9719758650287736,
|
| 1868 |
+
"eval_recall": 0.9711286089238845,
|
| 1869 |
+
"eval_runtime": 18.1879,
|
| 1870 |
+
"eval_samples_per_second": 41.896,
|
| 1871 |
+
"eval_steps_per_second": 2.639,
|
| 1872 |
+
"step": 1150
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 6.05,
|
| 1876 |
+
"grad_norm": 0.0016478670295327902,
|
| 1877 |
+
"learning_rate": 7.905759162303665e-05,
|
| 1878 |
+
"loss": 0.0001,
|
| 1879 |
+
"step": 1155
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 6.07,
|
| 1883 |
+
"grad_norm": 0.0019091927679255605,
|
| 1884 |
+
"learning_rate": 7.853403141361257e-05,
|
| 1885 |
+
"loss": 0.0001,
|
| 1886 |
+
"step": 1160
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 6.1,
|
| 1890 |
+
"grad_norm": 0.00418177992105484,
|
| 1891 |
+
"learning_rate": 7.801047120418848e-05,
|
| 1892 |
+
"loss": 0.0001,
|
| 1893 |
+
"step": 1165
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 6.13,
|
| 1897 |
+
"grad_norm": 0.0010454648872837424,
|
| 1898 |
+
"learning_rate": 7.74869109947644e-05,
|
| 1899 |
+
"loss": 0.0001,
|
| 1900 |
+
"step": 1170
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 6.15,
|
| 1904 |
+
"grad_norm": 0.003557993331924081,
|
| 1905 |
+
"learning_rate": 7.696335078534031e-05,
|
| 1906 |
+
"loss": 0.0001,
|
| 1907 |
+
"step": 1175
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 6.18,
|
| 1911 |
+
"grad_norm": 0.00358203100040555,
|
| 1912 |
+
"learning_rate": 7.643979057591623e-05,
|
| 1913 |
+
"loss": 0.0002,
|
| 1914 |
+
"step": 1180
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 6.2,
|
| 1918 |
+
"grad_norm": 0.0017727952217683196,
|
| 1919 |
+
"learning_rate": 7.591623036649214e-05,
|
| 1920 |
+
"loss": 0.0002,
|
| 1921 |
+
"step": 1185
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 6.23,
|
| 1925 |
+
"grad_norm": 0.056761130690574646,
|
| 1926 |
+
"learning_rate": 7.539267015706806e-05,
|
| 1927 |
+
"loss": 0.0003,
|
| 1928 |
+
"step": 1190
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 6.26,
|
| 1932 |
+
"grad_norm": 0.0010181496618315578,
|
| 1933 |
+
"learning_rate": 7.486910994764398e-05,
|
| 1934 |
+
"loss": 0.0003,
|
| 1935 |
+
"step": 1195
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 6.28,
|
| 1939 |
+
"grad_norm": 0.003052978776395321,
|
| 1940 |
+
"learning_rate": 7.43455497382199e-05,
|
| 1941 |
+
"loss": 0.0001,
|
| 1942 |
+
"step": 1200
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 6.28,
|
| 1946 |
+
"eval_accuracy": 0.968503937007874,
|
| 1947 |
+
"eval_loss": 0.1217927485704422,
|
| 1948 |
+
"eval_precision": 0.9692342594033277,
|
| 1949 |
+
"eval_recall": 0.968503937007874,
|
| 1950 |
+
"eval_runtime": 17.611,
|
| 1951 |
+
"eval_samples_per_second": 43.268,
|
| 1952 |
+
"eval_steps_per_second": 2.726,
|
| 1953 |
+
"step": 1200
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 6.31,
|
| 1957 |
+
"grad_norm": 0.0031509266700595617,
|
| 1958 |
+
"learning_rate": 7.382198952879581e-05,
|
| 1959 |
+
"loss": 0.0002,
|
| 1960 |
+
"step": 1205
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"epoch": 6.34,
|
| 1964 |
+
"grad_norm": 0.0011931936023756862,
|
| 1965 |
+
"learning_rate": 7.329842931937174e-05,
|
| 1966 |
+
"loss": 0.0002,
|
| 1967 |
+
"step": 1210
|
| 1968 |
+
},
|
| 1969 |
+
{
|
| 1970 |
+
"epoch": 6.36,
|
| 1971 |
+
"grad_norm": 0.0014170074136927724,
|
| 1972 |
+
"learning_rate": 7.277486910994766e-05,
|
| 1973 |
+
"loss": 0.0002,
|
| 1974 |
+
"step": 1215
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 6.39,
|
| 1978 |
+
"grad_norm": 0.0008681151666678488,
|
| 1979 |
+
"learning_rate": 7.225130890052356e-05,
|
| 1980 |
+
"loss": 0.0002,
|
| 1981 |
+
"step": 1220
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"epoch": 6.41,
|
| 1985 |
+
"grad_norm": 0.0015088602667674422,
|
| 1986 |
+
"learning_rate": 7.172774869109949e-05,
|
| 1987 |
+
"loss": 0.0002,
|
| 1988 |
+
"step": 1225
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 6.44,
|
| 1992 |
+
"grad_norm": 0.0011560139246284962,
|
| 1993 |
+
"learning_rate": 7.12041884816754e-05,
|
| 1994 |
+
"loss": 0.0002,
|
| 1995 |
+
"step": 1230
|
| 1996 |
+
},
|
| 1997 |
+
{
|
| 1998 |
+
"epoch": 6.47,
|
| 1999 |
+
"grad_norm": 0.0059287999756634235,
|
| 2000 |
+
"learning_rate": 7.068062827225132e-05,
|
| 2001 |
+
"loss": 0.0002,
|
| 2002 |
+
"step": 1235
|
| 2003 |
+
},
|
| 2004 |
+
{
|
| 2005 |
+
"epoch": 6.49,
|
| 2006 |
+
"grad_norm": 0.0017274218844249845,
|
| 2007 |
+
"learning_rate": 7.015706806282722e-05,
|
| 2008 |
+
"loss": 0.0002,
|
| 2009 |
+
"step": 1240
|
| 2010 |
+
},
|
| 2011 |
+
{
|
| 2012 |
+
"epoch": 6.52,
|
| 2013 |
+
"grad_norm": 0.000886244117282331,
|
| 2014 |
+
"learning_rate": 6.963350785340315e-05,
|
| 2015 |
+
"loss": 0.0001,
|
| 2016 |
+
"step": 1245
|
| 2017 |
+
},
|
| 2018 |
+
{
|
| 2019 |
+
"epoch": 6.54,
|
| 2020 |
+
"grad_norm": 0.0028559649363160133,
|
| 2021 |
+
"learning_rate": 6.910994764397905e-05,
|
| 2022 |
+
"loss": 0.0002,
|
| 2023 |
+
"step": 1250
|
| 2024 |
+
},
|
| 2025 |
+
{
|
| 2026 |
+
"epoch": 6.54,
|
| 2027 |
+
"eval_accuracy": 0.968503937007874,
|
| 2028 |
+
"eval_loss": 0.11844318360090256,
|
| 2029 |
+
"eval_precision": 0.9692177012971396,
|
| 2030 |
+
"eval_recall": 0.968503937007874,
|
| 2031 |
+
"eval_runtime": 17.5917,
|
| 2032 |
+
"eval_samples_per_second": 43.316,
|
| 2033 |
+
"eval_steps_per_second": 2.729,
|
| 2034 |
+
"step": 1250
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 6.57,
|
| 2038 |
+
"grad_norm": 0.0011471702018752694,
|
| 2039 |
+
"learning_rate": 6.858638743455498e-05,
|
| 2040 |
+
"loss": 0.0001,
|
| 2041 |
+
"step": 1255
|
| 2042 |
+
},
|
| 2043 |
+
{
|
| 2044 |
+
"epoch": 6.6,
|
| 2045 |
+
"grad_norm": 0.0015491463709622622,
|
| 2046 |
+
"learning_rate": 6.80628272251309e-05,
|
| 2047 |
+
"loss": 0.0001,
|
| 2048 |
+
"step": 1260
|
| 2049 |
+
},
|
| 2050 |
+
{
|
| 2051 |
+
"epoch": 6.62,
|
| 2052 |
+
"grad_norm": 0.0011632316745817661,
|
| 2053 |
+
"learning_rate": 6.75392670157068e-05,
|
| 2054 |
+
"loss": 0.0001,
|
| 2055 |
+
"step": 1265
|
| 2056 |
+
},
|
| 2057 |
+
{
|
| 2058 |
+
"epoch": 6.65,
|
| 2059 |
+
"grad_norm": 0.006089572329074144,
|
| 2060 |
+
"learning_rate": 6.701570680628273e-05,
|
| 2061 |
+
"loss": 0.0001,
|
| 2062 |
+
"step": 1270
|
| 2063 |
+
},
|
| 2064 |
+
{
|
| 2065 |
+
"epoch": 6.68,
|
| 2066 |
+
"grad_norm": 0.0025600052904337645,
|
| 2067 |
+
"learning_rate": 6.649214659685863e-05,
|
| 2068 |
+
"loss": 0.0001,
|
| 2069 |
+
"step": 1275
|
| 2070 |
+
},
|
| 2071 |
+
{
|
| 2072 |
+
"epoch": 6.7,
|
| 2073 |
+
"grad_norm": 0.001310704043135047,
|
| 2074 |
+
"learning_rate": 6.596858638743456e-05,
|
| 2075 |
+
"loss": 0.0001,
|
| 2076 |
+
"step": 1280
|
| 2077 |
+
},
|
| 2078 |
+
{
|
| 2079 |
+
"epoch": 6.73,
|
| 2080 |
+
"grad_norm": 0.0050185080617666245,
|
| 2081 |
+
"learning_rate": 6.544502617801048e-05,
|
| 2082 |
+
"loss": 0.0001,
|
| 2083 |
+
"step": 1285
|
| 2084 |
+
},
|
| 2085 |
+
{
|
| 2086 |
+
"epoch": 6.75,
|
| 2087 |
+
"grad_norm": 0.0030103351455181837,
|
| 2088 |
+
"learning_rate": 6.492146596858639e-05,
|
| 2089 |
+
"loss": 0.0001,
|
| 2090 |
+
"step": 1290
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"epoch": 6.78,
|
| 2094 |
+
"grad_norm": 0.0009425992611795664,
|
| 2095 |
+
"learning_rate": 6.439790575916231e-05,
|
| 2096 |
+
"loss": 0.0001,
|
| 2097 |
+
"step": 1295
|
| 2098 |
+
},
|
| 2099 |
+
{
|
| 2100 |
+
"epoch": 6.81,
|
| 2101 |
+
"grad_norm": 0.0016329910140484571,
|
| 2102 |
+
"learning_rate": 6.387434554973823e-05,
|
| 2103 |
+
"loss": 0.0002,
|
| 2104 |
+
"step": 1300
|
| 2105 |
+
},
|
| 2106 |
+
{
|
| 2107 |
+
"epoch": 6.81,
|
| 2108 |
+
"eval_accuracy": 0.9698162729658792,
|
| 2109 |
+
"eval_loss": 0.11775030940771103,
|
| 2110 |
+
"eval_precision": 0.9703878401175062,
|
| 2111 |
+
"eval_recall": 0.9698162729658792,
|
| 2112 |
+
"eval_runtime": 17.4725,
|
| 2113 |
+
"eval_samples_per_second": 43.611,
|
| 2114 |
+
"eval_steps_per_second": 2.747,
|
| 2115 |
+
"step": 1300
|
| 2116 |
+
},
|
| 2117 |
+
{
|
| 2118 |
+
"epoch": 6.83,
|
| 2119 |
+
"grad_norm": 0.0049902000464499,
|
| 2120 |
+
"learning_rate": 6.335078534031414e-05,
|
| 2121 |
+
"loss": 0.0002,
|
| 2122 |
+
"step": 1305
|
| 2123 |
+
},
|
| 2124 |
+
{
|
| 2125 |
+
"epoch": 6.86,
|
| 2126 |
+
"grad_norm": 0.0012894049286842346,
|
| 2127 |
+
"learning_rate": 6.282722513089006e-05,
|
| 2128 |
+
"loss": 0.0001,
|
| 2129 |
+
"step": 1310
|
| 2130 |
+
},
|
| 2131 |
+
{
|
| 2132 |
+
"epoch": 6.88,
|
| 2133 |
+
"grad_norm": 0.0013533816672861576,
|
| 2134 |
+
"learning_rate": 6.230366492146598e-05,
|
| 2135 |
+
"loss": 0.0001,
|
| 2136 |
+
"step": 1315
|
| 2137 |
+
},
|
| 2138 |
+
{
|
| 2139 |
+
"epoch": 6.91,
|
| 2140 |
+
"grad_norm": 0.0015272346790879965,
|
| 2141 |
+
"learning_rate": 6.178010471204189e-05,
|
| 2142 |
+
"loss": 0.0001,
|
| 2143 |
+
"step": 1320
|
| 2144 |
+
},
|
| 2145 |
+
{
|
| 2146 |
+
"epoch": 6.94,
|
| 2147 |
+
"grad_norm": 0.0021596469450742006,
|
| 2148 |
+
"learning_rate": 6.125654450261781e-05,
|
| 2149 |
+
"loss": 0.0001,
|
| 2150 |
+
"step": 1325
|
| 2151 |
+
},
|
| 2152 |
+
{
|
| 2153 |
+
"epoch": 6.96,
|
| 2154 |
+
"grad_norm": 0.0010469523258507252,
|
| 2155 |
+
"learning_rate": 6.073298429319372e-05,
|
| 2156 |
+
"loss": 0.0001,
|
| 2157 |
+
"step": 1330
|
| 2158 |
+
},
|
| 2159 |
+
{
|
| 2160 |
+
"epoch": 6.99,
|
| 2161 |
+
"grad_norm": 0.004506214987486601,
|
| 2162 |
+
"learning_rate": 6.020942408376964e-05,
|
| 2163 |
+
"loss": 0.0001,
|
| 2164 |
+
"step": 1335
|
| 2165 |
+
},
|
| 2166 |
+
{
|
| 2167 |
+
"epoch": 7.02,
|
| 2168 |
+
"grad_norm": 0.002483614254742861,
|
| 2169 |
+
"learning_rate": 5.968586387434555e-05,
|
| 2170 |
+
"loss": 0.0001,
|
| 2171 |
+
"step": 1340
|
| 2172 |
+
},
|
| 2173 |
+
{
|
| 2174 |
+
"epoch": 7.04,
|
| 2175 |
+
"grad_norm": 0.0011110632913187146,
|
| 2176 |
+
"learning_rate": 5.916230366492147e-05,
|
| 2177 |
+
"loss": 0.0001,
|
| 2178 |
+
"step": 1345
|
| 2179 |
+
},
|
| 2180 |
+
{
|
| 2181 |
+
"epoch": 7.07,
|
| 2182 |
+
"grad_norm": 0.0009813542710617185,
|
| 2183 |
+
"learning_rate": 5.863874345549738e-05,
|
| 2184 |
+
"loss": 0.0001,
|
| 2185 |
+
"step": 1350
|
| 2186 |
+
},
|
| 2187 |
+
{
|
| 2188 |
+
"epoch": 7.07,
|
| 2189 |
+
"eval_accuracy": 0.9698162729658792,
|
| 2190 |
+
"eval_loss": 0.1171058714389801,
|
| 2191 |
+
"eval_precision": 0.9703878401175062,
|
| 2192 |
+
"eval_recall": 0.9698162729658792,
|
| 2193 |
+
"eval_runtime": 17.4755,
|
| 2194 |
+
"eval_samples_per_second": 43.604,
|
| 2195 |
+
"eval_steps_per_second": 2.747,
|
| 2196 |
+
"step": 1350
|
| 2197 |
+
},
|
| 2198 |
+
{
|
| 2199 |
+
"epoch": 7.09,
|
| 2200 |
+
"grad_norm": 0.0015625334344804287,
|
| 2201 |
+
"learning_rate": 5.81151832460733e-05,
|
| 2202 |
+
"loss": 0.0001,
|
| 2203 |
+
"step": 1355
|
| 2204 |
+
},
|
| 2205 |
+
{
|
| 2206 |
+
"epoch": 7.12,
|
| 2207 |
+
"grad_norm": 0.0011336584575474262,
|
| 2208 |
+
"learning_rate": 5.759162303664922e-05,
|
| 2209 |
+
"loss": 0.0001,
|
| 2210 |
+
"step": 1360
|
| 2211 |
+
},
|
| 2212 |
+
{
|
| 2213 |
+
"epoch": 7.15,
|
| 2214 |
+
"grad_norm": 0.002448306418955326,
|
| 2215 |
+
"learning_rate": 5.7068062827225135e-05,
|
| 2216 |
+
"loss": 0.0001,
|
| 2217 |
+
"step": 1365
|
| 2218 |
+
},
|
| 2219 |
+
{
|
| 2220 |
+
"epoch": 7.17,
|
| 2221 |
+
"grad_norm": 0.003220533486455679,
|
| 2222 |
+
"learning_rate": 5.654450261780106e-05,
|
| 2223 |
+
"loss": 0.0001,
|
| 2224 |
+
"step": 1370
|
| 2225 |
+
},
|
| 2226 |
+
{
|
| 2227 |
+
"epoch": 7.2,
|
| 2228 |
+
"grad_norm": 0.0035826002713292837,
|
| 2229 |
+
"learning_rate": 5.6020942408376965e-05,
|
| 2230 |
+
"loss": 0.0001,
|
| 2231 |
+
"step": 1375
|
| 2232 |
+
},
|
| 2233 |
+
{
|
| 2234 |
+
"epoch": 7.23,
|
| 2235 |
+
"grad_norm": 0.0011589195346459746,
|
| 2236 |
+
"learning_rate": 5.5497382198952887e-05,
|
| 2237 |
+
"loss": 0.0001,
|
| 2238 |
+
"step": 1380
|
| 2239 |
+
},
|
| 2240 |
+
{
|
| 2241 |
+
"epoch": 7.25,
|
| 2242 |
+
"grad_norm": 0.00346089294180274,
|
| 2243 |
+
"learning_rate": 5.4973821989528795e-05,
|
| 2244 |
+
"loss": 0.0001,
|
| 2245 |
+
"step": 1385
|
| 2246 |
+
},
|
| 2247 |
+
{
|
| 2248 |
+
"epoch": 7.28,
|
| 2249 |
+
"grad_norm": 0.0009584302315488458,
|
| 2250 |
+
"learning_rate": 5.4450261780104716e-05,
|
| 2251 |
+
"loss": 0.0001,
|
| 2252 |
+
"step": 1390
|
| 2253 |
+
},
|
| 2254 |
+
{
|
| 2255 |
+
"epoch": 7.3,
|
| 2256 |
+
"grad_norm": 0.0017620971193537116,
|
| 2257 |
+
"learning_rate": 5.3926701570680624e-05,
|
| 2258 |
+
"loss": 0.0001,
|
| 2259 |
+
"step": 1395
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 7.33,
|
| 2263 |
+
"grad_norm": 0.0009925129124894738,
|
| 2264 |
+
"learning_rate": 5.3403141361256546e-05,
|
| 2265 |
+
"loss": 0.0001,
|
| 2266 |
+
"step": 1400
|
| 2267 |
+
},
|
| 2268 |
+
{
|
| 2269 |
+
"epoch": 7.33,
|
| 2270 |
+
"eval_accuracy": 0.9698162729658792,
|
| 2271 |
+
"eval_loss": 0.11688791215419769,
|
| 2272 |
+
"eval_precision": 0.9704864266182309,
|
| 2273 |
+
"eval_recall": 0.9698162729658792,
|
| 2274 |
+
"eval_runtime": 17.5351,
|
| 2275 |
+
"eval_samples_per_second": 43.456,
|
| 2276 |
+
"eval_steps_per_second": 2.737,
|
| 2277 |
+
"step": 1400
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 7.36,
|
| 2281 |
+
"grad_norm": 0.0010989775182679296,
|
| 2282 |
+
"learning_rate": 5.287958115183246e-05,
|
| 2283 |
+
"loss": 0.0001,
|
| 2284 |
+
"step": 1405
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 7.38,
|
| 2288 |
+
"grad_norm": 0.001141382148489356,
|
| 2289 |
+
"learning_rate": 5.235602094240838e-05,
|
| 2290 |
+
"loss": 0.0001,
|
| 2291 |
+
"step": 1410
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 7.41,
|
| 2295 |
+
"grad_norm": 0.0018131214892491698,
|
| 2296 |
+
"learning_rate": 5.18324607329843e-05,
|
| 2297 |
+
"loss": 0.0001,
|
| 2298 |
+
"step": 1415
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 7.43,
|
| 2302 |
+
"grad_norm": 0.0016311927465721965,
|
| 2303 |
+
"learning_rate": 5.130890052356021e-05,
|
| 2304 |
+
"loss": 0.0002,
|
| 2305 |
+
"step": 1420
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 7.46,
|
| 2309 |
+
"grad_norm": 0.0019679146353155375,
|
| 2310 |
+
"learning_rate": 5.0785340314136134e-05,
|
| 2311 |
+
"loss": 0.0001,
|
| 2312 |
+
"step": 1425
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 7.49,
|
| 2316 |
+
"grad_norm": 0.0030663602519780397,
|
| 2317 |
+
"learning_rate": 5.026178010471204e-05,
|
| 2318 |
+
"loss": 0.0001,
|
| 2319 |
+
"step": 1430
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 7.51,
|
| 2323 |
+
"grad_norm": 0.0022476576268672943,
|
| 2324 |
+
"learning_rate": 4.973821989528796e-05,
|
| 2325 |
+
"loss": 0.0001,
|
| 2326 |
+
"step": 1435
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 7.54,
|
| 2330 |
+
"grad_norm": 0.001257985015399754,
|
| 2331 |
+
"learning_rate": 4.921465968586388e-05,
|
| 2332 |
+
"loss": 0.0001,
|
| 2333 |
+
"step": 1440
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 7.57,
|
| 2337 |
+
"grad_norm": 0.002487305086106062,
|
| 2338 |
+
"learning_rate": 4.869109947643979e-05,
|
| 2339 |
+
"loss": 0.0001,
|
| 2340 |
+
"step": 1445
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 7.59,
|
| 2344 |
+
"grad_norm": 0.0023026170674711466,
|
| 2345 |
+
"learning_rate": 4.816753926701571e-05,
|
| 2346 |
+
"loss": 0.0001,
|
| 2347 |
+
"step": 1450
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 7.59,
|
| 2351 |
+
"eval_accuracy": 0.9711286089238845,
|
| 2352 |
+
"eval_loss": 0.11671730875968933,
|
| 2353 |
+
"eval_precision": 0.9718133010833329,
|
| 2354 |
+
"eval_recall": 0.9711286089238845,
|
| 2355 |
+
"eval_runtime": 17.5661,
|
| 2356 |
+
"eval_samples_per_second": 43.379,
|
| 2357 |
+
"eval_steps_per_second": 2.733,
|
| 2358 |
+
"step": 1450
|
| 2359 |
+
},
|
| 2360 |
+
{
|
| 2361 |
+
"epoch": 7.62,
|
| 2362 |
+
"grad_norm": 0.0014070291072130203,
|
| 2363 |
+
"learning_rate": 4.764397905759162e-05,
|
| 2364 |
+
"loss": 0.0001,
|
| 2365 |
+
"step": 1455
|
| 2366 |
+
},
|
| 2367 |
+
{
|
| 2368 |
+
"epoch": 7.64,
|
| 2369 |
+
"grad_norm": 0.0011672518448904157,
|
| 2370 |
+
"learning_rate": 4.7120418848167544e-05,
|
| 2371 |
+
"loss": 0.0001,
|
| 2372 |
+
"step": 1460
|
| 2373 |
+
},
|
| 2374 |
+
{
|
| 2375 |
+
"epoch": 7.67,
|
| 2376 |
+
"grad_norm": 0.0015011669602245092,
|
| 2377 |
+
"learning_rate": 4.659685863874346e-05,
|
| 2378 |
+
"loss": 0.0001,
|
| 2379 |
+
"step": 1465
|
| 2380 |
+
},
|
| 2381 |
+
{
|
| 2382 |
+
"epoch": 7.7,
|
| 2383 |
+
"grad_norm": 0.001993841025978327,
|
| 2384 |
+
"learning_rate": 4.6073298429319374e-05,
|
| 2385 |
+
"loss": 0.0001,
|
| 2386 |
+
"step": 1470
|
| 2387 |
+
},
|
| 2388 |
+
{
|
| 2389 |
+
"epoch": 7.72,
|
| 2390 |
+
"grad_norm": 0.0008604762842878699,
|
| 2391 |
+
"learning_rate": 4.554973821989529e-05,
|
| 2392 |
+
"loss": 0.0001,
|
| 2393 |
+
"step": 1475
|
| 2394 |
+
},
|
| 2395 |
+
{
|
| 2396 |
+
"epoch": 7.75,
|
| 2397 |
+
"grad_norm": 0.002782499184831977,
|
| 2398 |
+
"learning_rate": 4.50261780104712e-05,
|
| 2399 |
+
"loss": 0.0001,
|
| 2400 |
+
"step": 1480
|
| 2401 |
+
},
|
| 2402 |
+
{
|
| 2403 |
+
"epoch": 7.77,
|
| 2404 |
+
"grad_norm": 0.002074967371299863,
|
| 2405 |
+
"learning_rate": 4.4502617801047125e-05,
|
| 2406 |
+
"loss": 0.0001,
|
| 2407 |
+
"step": 1485
|
| 2408 |
+
},
|
| 2409 |
+
{
|
| 2410 |
+
"epoch": 7.8,
|
| 2411 |
+
"grad_norm": 0.0031987845432013273,
|
| 2412 |
+
"learning_rate": 4.397905759162304e-05,
|
| 2413 |
+
"loss": 0.0001,
|
| 2414 |
+
"step": 1490
|
| 2415 |
+
},
|
| 2416 |
+
{
|
| 2417 |
+
"epoch": 7.83,
|
| 2418 |
+
"grad_norm": 0.0007084137760102749,
|
| 2419 |
+
"learning_rate": 4.3455497382198955e-05,
|
| 2420 |
+
"loss": 0.0001,
|
| 2421 |
+
"step": 1495
|
| 2422 |
+
},
|
| 2423 |
+
{
|
| 2424 |
+
"epoch": 7.85,
|
| 2425 |
+
"grad_norm": 0.0019736553076654673,
|
| 2426 |
+
"learning_rate": 4.293193717277487e-05,
|
| 2427 |
+
"loss": 0.0001,
|
| 2428 |
+
"step": 1500
|
| 2429 |
+
},
|
| 2430 |
+
{
|
| 2431 |
+
"epoch": 7.85,
|
| 2432 |
+
"eval_accuracy": 0.9711286089238845,
|
| 2433 |
+
"eval_loss": 0.11646050214767456,
|
| 2434 |
+
"eval_precision": 0.9718133010833329,
|
| 2435 |
+
"eval_recall": 0.9711286089238845,
|
| 2436 |
+
"eval_runtime": 17.4763,
|
| 2437 |
+
"eval_samples_per_second": 43.602,
|
| 2438 |
+
"eval_steps_per_second": 2.747,
|
| 2439 |
+
"step": 1500
|
| 2440 |
}
|
| 2441 |
],
|
| 2442 |
"logging_steps": 5,
|
| 2443 |
+
"max_steps": 1910,
|
| 2444 |
"num_input_tokens_seen": 0,
|
| 2445 |
+
"num_train_epochs": 10,
|
| 2446 |
"save_steps": 500,
|
| 2447 |
+
"total_flos": 1.8551418818712515e+18,
|
| 2448 |
"train_batch_size": 16,
|
| 2449 |
"trial_name": null,
|
| 2450 |
"trial_params": null
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4856
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20978be5af09aa5e062dc23ab1ae5cd2911d62519dbe8c26b70e5d2de0491f9b
|
| 3 |
size 4856
|