Upload 12 files
Browse files- config.json +1 -1
- model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- trainer_state.json +979 -979
- training_args.bin +1 -1
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "duyvu8373/vit5-base
|
| 3 |
"architectures": [
|
| 4 |
"T5ForConditionalGeneration"
|
| 5 |
],
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "duyvu8373/multi-task-vit5-base",
|
| 3 |
"architectures": [
|
| 4 |
"T5ForConditionalGeneration"
|
| 5 |
],
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 903834408
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e57bbab697654055aa509ab3a4fccda8b4866ca3cb3a56d421ceac79bcb8977
|
| 3 |
size 903834408
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1807824186
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aaa3ddc50d497f7baa523f553588741d4aa5c987db9f41ad48c618e2f3f9fae4
|
| 3 |
size 1807824186
|
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:bb2293d625f6837f6eefe9f505563f0a094937fc4f424feda9102b4b1beab3b7
|
| 3 |
size 14244
|
trainer_state.json
CHANGED
|
@@ -10,1454 +10,1454 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
-
"eval_bp": 0.
|
| 14 |
"eval_counts": [
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
|
| 19 |
],
|
| 20 |
-
"eval_loss": 0.
|
| 21 |
"eval_precisions": [
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
],
|
| 27 |
-
"eval_ref_len":
|
| 28 |
-
"eval_runtime":
|
| 29 |
-
"eval_samples_per_second":
|
| 30 |
-
"eval_score":
|
| 31 |
-
"eval_steps_per_second": 1.
|
| 32 |
-
"eval_sys_len":
|
| 33 |
"eval_totals": [
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
|
| 38 |
],
|
| 39 |
"step": 129
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 2.0,
|
| 43 |
-
"eval_bp": 0.
|
| 44 |
"eval_counts": [
|
| 45 |
-
|
| 46 |
-
|
| 47 |
-
|
| 48 |
-
|
| 49 |
],
|
| 50 |
-
"eval_loss": 0.
|
| 51 |
"eval_precisions": [
|
| 52 |
-
|
| 53 |
-
|
| 54 |
-
|
| 55 |
-
|
| 56 |
-
],
|
| 57 |
-
"eval_ref_len":
|
| 58 |
-
"eval_runtime":
|
| 59 |
-
"eval_samples_per_second":
|
| 60 |
-
"eval_score":
|
| 61 |
-
"eval_steps_per_second": 1.
|
| 62 |
-
"eval_sys_len":
|
| 63 |
"eval_totals": [
|
| 64 |
-
|
| 65 |
-
|
| 66 |
-
|
| 67 |
-
|
| 68 |
],
|
| 69 |
"step": 258
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 3.0,
|
| 73 |
-
"eval_bp": 0.
|
| 74 |
"eval_counts": [
|
| 75 |
-
|
| 76 |
-
|
| 77 |
-
|
| 78 |
-
|
| 79 |
],
|
| 80 |
-
"eval_loss": 0.
|
| 81 |
"eval_precisions": [
|
| 82 |
-
99.
|
| 83 |
-
|
| 84 |
-
|
| 85 |
-
|
| 86 |
-
],
|
| 87 |
-
"eval_ref_len":
|
| 88 |
-
"eval_runtime":
|
| 89 |
-
"eval_samples_per_second":
|
| 90 |
-
"eval_score":
|
| 91 |
-
"eval_steps_per_second": 1.
|
| 92 |
-
"eval_sys_len":
|
| 93 |
"eval_totals": [
|
| 94 |
-
|
| 95 |
-
|
| 96 |
-
|
| 97 |
-
|
| 98 |
],
|
| 99 |
"step": 387
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 3.88,
|
| 103 |
"learning_rate": 1.8449612403100777e-05,
|
| 104 |
-
"loss": 0.
|
| 105 |
"step": 500
|
| 106 |
},
|
| 107 |
{
|
| 108 |
"epoch": 4.0,
|
| 109 |
-
"eval_bp": 0.
|
| 110 |
"eval_counts": [
|
| 111 |
-
|
| 112 |
-
|
| 113 |
-
|
| 114 |
-
|
| 115 |
],
|
| 116 |
-
"eval_loss": 0.
|
| 117 |
"eval_precisions": [
|
| 118 |
-
99.
|
| 119 |
-
|
| 120 |
-
|
| 121 |
-
|
| 122 |
-
],
|
| 123 |
-
"eval_ref_len":
|
| 124 |
-
"eval_runtime":
|
| 125 |
-
"eval_samples_per_second":
|
| 126 |
-
"eval_score":
|
| 127 |
-
"eval_steps_per_second": 1.
|
| 128 |
-
"eval_sys_len":
|
| 129 |
"eval_totals": [
|
| 130 |
-
|
| 131 |
-
|
| 132 |
-
|
| 133 |
-
|
| 134 |
],
|
| 135 |
"step": 516
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 5.0,
|
| 139 |
-
"eval_bp": 0.
|
| 140 |
"eval_counts": [
|
| 141 |
-
|
| 142 |
-
|
| 143 |
-
|
| 144 |
-
|
| 145 |
],
|
| 146 |
-
"eval_loss": 0.
|
| 147 |
"eval_precisions": [
|
| 148 |
-
99.
|
| 149 |
-
99.
|
| 150 |
-
99.
|
| 151 |
-
|
| 152 |
-
],
|
| 153 |
-
"eval_ref_len":
|
| 154 |
-
"eval_runtime":
|
| 155 |
-
"eval_samples_per_second":
|
| 156 |
-
"eval_score":
|
| 157 |
-
"eval_steps_per_second": 1.
|
| 158 |
-
"eval_sys_len":
|
| 159 |
"eval_totals": [
|
| 160 |
-
|
| 161 |
-
|
| 162 |
-
|
| 163 |
-
|
| 164 |
],
|
| 165 |
"step": 645
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 6.0,
|
| 169 |
-
"eval_bp": 0.
|
| 170 |
"eval_counts": [
|
| 171 |
-
|
| 172 |
-
|
| 173 |
-
|
| 174 |
-
|
| 175 |
],
|
| 176 |
-
"eval_loss": 0.
|
| 177 |
"eval_precisions": [
|
| 178 |
-
99.
|
| 179 |
-
99.
|
| 180 |
-
99.
|
| 181 |
-
99.
|
| 182 |
-
],
|
| 183 |
-
"eval_ref_len":
|
| 184 |
-
"eval_runtime":
|
| 185 |
-
"eval_samples_per_second":
|
| 186 |
-
"eval_score":
|
| 187 |
-
"eval_steps_per_second": 1.
|
| 188 |
-
"eval_sys_len":
|
| 189 |
"eval_totals": [
|
| 190 |
-
|
| 191 |
-
|
| 192 |
-
|
| 193 |
-
|
| 194 |
],
|
| 195 |
"step": 774
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 7.0,
|
| 199 |
-
"eval_bp": 0.
|
| 200 |
"eval_counts": [
|
| 201 |
-
|
| 202 |
-
|
| 203 |
-
|
| 204 |
-
|
| 205 |
],
|
| 206 |
-
"eval_loss": 0.
|
| 207 |
"eval_precisions": [
|
| 208 |
-
99.
|
| 209 |
-
99.
|
| 210 |
-
99.
|
| 211 |
-
99.
|
| 212 |
-
],
|
| 213 |
-
"eval_ref_len":
|
| 214 |
-
"eval_runtime":
|
| 215 |
-
"eval_samples_per_second":
|
| 216 |
-
"eval_score":
|
| 217 |
-
"eval_steps_per_second": 1.
|
| 218 |
-
"eval_sys_len":
|
| 219 |
"eval_totals": [
|
| 220 |
-
|
| 221 |
-
|
| 222 |
-
|
| 223 |
-
|
| 224 |
],
|
| 225 |
"step": 903
|
| 226 |
},
|
| 227 |
{
|
| 228 |
"epoch": 7.75,
|
| 229 |
"learning_rate": 1.689922480620155e-05,
|
| 230 |
-
"loss": 0.
|
| 231 |
"step": 1000
|
| 232 |
},
|
| 233 |
{
|
| 234 |
"epoch": 8.0,
|
| 235 |
-
"eval_bp": 0.
|
| 236 |
"eval_counts": [
|
| 237 |
-
|
| 238 |
-
|
| 239 |
-
|
| 240 |
-
|
| 241 |
],
|
| 242 |
-
"eval_loss": 0.
|
| 243 |
"eval_precisions": [
|
| 244 |
-
99.
|
| 245 |
-
99.
|
| 246 |
-
99.
|
| 247 |
-
99.
|
| 248 |
-
],
|
| 249 |
-
"eval_ref_len":
|
| 250 |
-
"eval_runtime":
|
| 251 |
-
"eval_samples_per_second":
|
| 252 |
-
"eval_score":
|
| 253 |
-
"eval_steps_per_second": 1.
|
| 254 |
-
"eval_sys_len":
|
| 255 |
"eval_totals": [
|
| 256 |
-
|
| 257 |
-
|
| 258 |
-
|
| 259 |
-
|
| 260 |
],
|
| 261 |
"step": 1032
|
| 262 |
},
|
| 263 |
{
|
| 264 |
"epoch": 9.0,
|
| 265 |
-
"eval_bp": 0.
|
| 266 |
"eval_counts": [
|
| 267 |
-
|
| 268 |
-
|
| 269 |
-
|
| 270 |
-
|
| 271 |
],
|
| 272 |
-
"eval_loss": 0.
|
| 273 |
"eval_precisions": [
|
| 274 |
-
99.
|
| 275 |
-
99.
|
| 276 |
-
99.
|
| 277 |
-
99.
|
| 278 |
-
],
|
| 279 |
-
"eval_ref_len":
|
| 280 |
-
"eval_runtime":
|
| 281 |
-
"eval_samples_per_second":
|
| 282 |
-
"eval_score":
|
| 283 |
-
"eval_steps_per_second": 1.
|
| 284 |
-
"eval_sys_len":
|
| 285 |
"eval_totals": [
|
| 286 |
-
|
| 287 |
-
|
| 288 |
-
|
| 289 |
-
|
| 290 |
],
|
| 291 |
"step": 1161
|
| 292 |
},
|
| 293 |
{
|
| 294 |
"epoch": 10.0,
|
| 295 |
-
"eval_bp": 0.
|
| 296 |
"eval_counts": [
|
| 297 |
-
|
| 298 |
-
|
| 299 |
-
|
| 300 |
-
|
| 301 |
],
|
| 302 |
-
"eval_loss": 0.
|
| 303 |
"eval_precisions": [
|
| 304 |
-
99.
|
| 305 |
-
99.
|
| 306 |
-
99.
|
| 307 |
-
99.
|
| 308 |
-
],
|
| 309 |
-
"eval_ref_len":
|
| 310 |
-
"eval_runtime":
|
| 311 |
-
"eval_samples_per_second":
|
| 312 |
-
"eval_score":
|
| 313 |
-
"eval_steps_per_second": 1.
|
| 314 |
-
"eval_sys_len":
|
| 315 |
"eval_totals": [
|
| 316 |
-
|
| 317 |
-
|
| 318 |
-
|
| 319 |
-
|
| 320 |
],
|
| 321 |
"step": 1290
|
| 322 |
},
|
| 323 |
{
|
| 324 |
"epoch": 11.0,
|
| 325 |
-
"eval_bp": 0.
|
| 326 |
"eval_counts": [
|
| 327 |
-
|
| 328 |
-
|
| 329 |
-
|
| 330 |
-
|
| 331 |
],
|
| 332 |
-
"eval_loss": 0.
|
| 333 |
"eval_precisions": [
|
| 334 |
-
99.
|
| 335 |
-
99.
|
| 336 |
-
99.
|
| 337 |
-
99.
|
| 338 |
-
],
|
| 339 |
-
"eval_ref_len":
|
| 340 |
-
"eval_runtime":
|
| 341 |
-
"eval_samples_per_second":
|
| 342 |
-
"eval_score":
|
| 343 |
-
"eval_steps_per_second": 1.
|
| 344 |
-
"eval_sys_len":
|
| 345 |
"eval_totals": [
|
| 346 |
-
|
| 347 |
-
|
| 348 |
-
|
| 349 |
-
|
| 350 |
],
|
| 351 |
"step": 1419
|
| 352 |
},
|
| 353 |
{
|
| 354 |
"epoch": 11.63,
|
| 355 |
"learning_rate": 1.5348837209302328e-05,
|
| 356 |
-
"loss": 0.
|
| 357 |
"step": 1500
|
| 358 |
},
|
| 359 |
{
|
| 360 |
"epoch": 12.0,
|
| 361 |
-
"eval_bp": 0.
|
| 362 |
"eval_counts": [
|
| 363 |
-
|
| 364 |
-
|
| 365 |
-
|
| 366 |
-
|
| 367 |
],
|
| 368 |
-
"eval_loss": 0.
|
| 369 |
"eval_precisions": [
|
| 370 |
-
99.
|
| 371 |
-
99.
|
| 372 |
-
99.
|
| 373 |
-
99.
|
| 374 |
-
],
|
| 375 |
-
"eval_ref_len":
|
| 376 |
-
"eval_runtime":
|
| 377 |
-
"eval_samples_per_second":
|
| 378 |
-
"eval_score":
|
| 379 |
-
"eval_steps_per_second": 1.
|
| 380 |
-
"eval_sys_len":
|
| 381 |
"eval_totals": [
|
| 382 |
-
|
| 383 |
-
|
| 384 |
-
|
| 385 |
-
|
| 386 |
],
|
| 387 |
"step": 1548
|
| 388 |
},
|
| 389 |
{
|
| 390 |
"epoch": 13.0,
|
| 391 |
-
"eval_bp": 0.
|
| 392 |
"eval_counts": [
|
| 393 |
-
|
| 394 |
-
|
| 395 |
-
|
| 396 |
-
|
| 397 |
],
|
| 398 |
-
"eval_loss": 0.
|
| 399 |
"eval_precisions": [
|
| 400 |
-
99.
|
| 401 |
-
99.
|
| 402 |
-
99.
|
| 403 |
-
99.
|
| 404 |
-
],
|
| 405 |
-
"eval_ref_len":
|
| 406 |
-
"eval_runtime":
|
| 407 |
-
"eval_samples_per_second":
|
| 408 |
-
"eval_score":
|
| 409 |
-
"eval_steps_per_second": 1.
|
| 410 |
-
"eval_sys_len":
|
| 411 |
"eval_totals": [
|
| 412 |
-
|
| 413 |
-
|
| 414 |
-
|
| 415 |
-
|
| 416 |
],
|
| 417 |
"step": 1677
|
| 418 |
},
|
| 419 |
{
|
| 420 |
"epoch": 14.0,
|
| 421 |
-
"eval_bp": 0.
|
| 422 |
"eval_counts": [
|
| 423 |
-
|
| 424 |
-
|
| 425 |
-
|
| 426 |
-
|
| 427 |
],
|
| 428 |
-
"eval_loss": 0.
|
| 429 |
"eval_precisions": [
|
| 430 |
-
99.
|
| 431 |
-
99.
|
| 432 |
-
99.
|
| 433 |
-
99.
|
| 434 |
-
],
|
| 435 |
-
"eval_ref_len":
|
| 436 |
-
"eval_runtime":
|
| 437 |
-
"eval_samples_per_second":
|
| 438 |
-
"eval_score":
|
| 439 |
-
"eval_steps_per_second": 1.
|
| 440 |
-
"eval_sys_len":
|
| 441 |
"eval_totals": [
|
| 442 |
-
|
| 443 |
-
|
| 444 |
-
|
| 445 |
-
|
| 446 |
],
|
| 447 |
"step": 1806
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 15.0,
|
| 451 |
-
"eval_bp": 0.
|
| 452 |
"eval_counts": [
|
| 453 |
-
|
| 454 |
-
|
| 455 |
-
|
| 456 |
-
|
| 457 |
],
|
| 458 |
-
"eval_loss": 0.
|
| 459 |
"eval_precisions": [
|
| 460 |
-
99.
|
| 461 |
-
99.
|
| 462 |
-
99.
|
| 463 |
-
99.
|
| 464 |
-
],
|
| 465 |
-
"eval_ref_len":
|
| 466 |
-
"eval_runtime":
|
| 467 |
-
"eval_samples_per_second":
|
| 468 |
-
"eval_score":
|
| 469 |
-
"eval_steps_per_second": 1.
|
| 470 |
-
"eval_sys_len":
|
| 471 |
"eval_totals": [
|
| 472 |
-
|
| 473 |
-
|
| 474 |
-
|
| 475 |
-
|
| 476 |
],
|
| 477 |
"step": 1935
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 15.5,
|
| 481 |
"learning_rate": 1.3798449612403102e-05,
|
| 482 |
-
"loss": 0.
|
| 483 |
"step": 2000
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 16.0,
|
| 487 |
-
"eval_bp": 0.
|
| 488 |
"eval_counts": [
|
| 489 |
-
|
| 490 |
-
|
| 491 |
-
|
| 492 |
-
|
| 493 |
],
|
| 494 |
-
"eval_loss": 0.
|
| 495 |
"eval_precisions": [
|
| 496 |
-
99.
|
| 497 |
-
99.
|
| 498 |
-
99.
|
| 499 |
-
99.
|
| 500 |
-
],
|
| 501 |
-
"eval_ref_len":
|
| 502 |
-
"eval_runtime":
|
| 503 |
-
"eval_samples_per_second":
|
| 504 |
-
"eval_score":
|
| 505 |
-
"eval_steps_per_second": 1.
|
| 506 |
-
"eval_sys_len":
|
| 507 |
"eval_totals": [
|
| 508 |
-
|
| 509 |
-
|
| 510 |
-
|
| 511 |
-
|
| 512 |
],
|
| 513 |
"step": 2064
|
| 514 |
},
|
| 515 |
{
|
| 516 |
"epoch": 17.0,
|
| 517 |
-
"eval_bp": 0.
|
| 518 |
"eval_counts": [
|
| 519 |
-
|
| 520 |
-
|
| 521 |
-
|
| 522 |
-
|
| 523 |
],
|
| 524 |
-
"eval_loss": 0.
|
| 525 |
"eval_precisions": [
|
| 526 |
-
99.
|
| 527 |
-
99.
|
| 528 |
-
99.
|
| 529 |
-
99.
|
| 530 |
-
],
|
| 531 |
-
"eval_ref_len":
|
| 532 |
-
"eval_runtime":
|
| 533 |
-
"eval_samples_per_second":
|
| 534 |
-
"eval_score":
|
| 535 |
-
"eval_steps_per_second": 1.
|
| 536 |
-
"eval_sys_len":
|
| 537 |
"eval_totals": [
|
| 538 |
-
|
| 539 |
-
|
| 540 |
-
|
| 541 |
-
|
| 542 |
],
|
| 543 |
"step": 2193
|
| 544 |
},
|
| 545 |
{
|
| 546 |
"epoch": 18.0,
|
| 547 |
-
"eval_bp": 0.
|
| 548 |
"eval_counts": [
|
| 549 |
-
|
| 550 |
-
|
| 551 |
-
|
| 552 |
-
|
| 553 |
],
|
| 554 |
-
"eval_loss": 0.
|
| 555 |
"eval_precisions": [
|
| 556 |
-
99.
|
| 557 |
-
99.
|
| 558 |
-
99.
|
| 559 |
-
99.
|
| 560 |
-
],
|
| 561 |
-
"eval_ref_len":
|
| 562 |
-
"eval_runtime":
|
| 563 |
-
"eval_samples_per_second":
|
| 564 |
-
"eval_score":
|
| 565 |
-
"eval_steps_per_second": 1.
|
| 566 |
-
"eval_sys_len":
|
| 567 |
"eval_totals": [
|
| 568 |
-
|
| 569 |
-
|
| 570 |
-
|
| 571 |
-
|
| 572 |
],
|
| 573 |
"step": 2322
|
| 574 |
},
|
| 575 |
{
|
| 576 |
"epoch": 19.0,
|
| 577 |
-
"eval_bp": 0.
|
| 578 |
"eval_counts": [
|
| 579 |
-
|
| 580 |
-
|
| 581 |
-
|
| 582 |
-
|
| 583 |
],
|
| 584 |
-
"eval_loss":
|
| 585 |
"eval_precisions": [
|
| 586 |
-
99.
|
| 587 |
-
99.
|
| 588 |
-
99.
|
| 589 |
-
99.
|
| 590 |
-
],
|
| 591 |
-
"eval_ref_len":
|
| 592 |
-
"eval_runtime":
|
| 593 |
-
"eval_samples_per_second":
|
| 594 |
-
"eval_score":
|
| 595 |
-
"eval_steps_per_second": 1.
|
| 596 |
-
"eval_sys_len":
|
| 597 |
"eval_totals": [
|
| 598 |
-
|
| 599 |
-
|
| 600 |
-
|
| 601 |
-
|
| 602 |
],
|
| 603 |
"step": 2451
|
| 604 |
},
|
| 605 |
{
|
| 606 |
"epoch": 19.38,
|
| 607 |
"learning_rate": 1.2248062015503876e-05,
|
| 608 |
-
"loss": 0.
|
| 609 |
"step": 2500
|
| 610 |
},
|
| 611 |
{
|
| 612 |
"epoch": 20.0,
|
| 613 |
-
"eval_bp": 0.
|
| 614 |
"eval_counts": [
|
| 615 |
-
|
| 616 |
-
|
| 617 |
-
|
| 618 |
-
|
| 619 |
],
|
| 620 |
-
"eval_loss":
|
| 621 |
"eval_precisions": [
|
| 622 |
-
99.
|
| 623 |
-
99.
|
| 624 |
-
99.
|
| 625 |
-
99.
|
| 626 |
-
],
|
| 627 |
-
"eval_ref_len":
|
| 628 |
-
"eval_runtime":
|
| 629 |
-
"eval_samples_per_second":
|
| 630 |
-
"eval_score":
|
| 631 |
-
"eval_steps_per_second": 1.
|
| 632 |
-
"eval_sys_len":
|
| 633 |
"eval_totals": [
|
| 634 |
-
|
| 635 |
-
|
| 636 |
-
|
| 637 |
-
|
| 638 |
],
|
| 639 |
"step": 2580
|
| 640 |
},
|
| 641 |
{
|
| 642 |
"epoch": 21.0,
|
| 643 |
-
"eval_bp": 0.
|
| 644 |
"eval_counts": [
|
| 645 |
-
|
| 646 |
-
|
| 647 |
-
|
| 648 |
-
|
| 649 |
],
|
| 650 |
-
"eval_loss":
|
| 651 |
"eval_precisions": [
|
| 652 |
-
99.
|
| 653 |
-
99.
|
| 654 |
-
99.
|
| 655 |
-
99.
|
| 656 |
-
],
|
| 657 |
-
"eval_ref_len":
|
| 658 |
-
"eval_runtime":
|
| 659 |
-
"eval_samples_per_second":
|
| 660 |
-
"eval_score":
|
| 661 |
-
"eval_steps_per_second": 1.
|
| 662 |
-
"eval_sys_len":
|
| 663 |
"eval_totals": [
|
| 664 |
-
|
| 665 |
-
|
| 666 |
-
|
| 667 |
-
|
| 668 |
],
|
| 669 |
"step": 2709
|
| 670 |
},
|
| 671 |
{
|
| 672 |
"epoch": 22.0,
|
| 673 |
-
"eval_bp": 0.
|
| 674 |
"eval_counts": [
|
| 675 |
-
|
| 676 |
-
|
| 677 |
-
|
| 678 |
-
|
| 679 |
],
|
| 680 |
-
"eval_loss": 0.
|
| 681 |
"eval_precisions": [
|
| 682 |
-
99.
|
| 683 |
-
99.
|
| 684 |
-
99.
|
| 685 |
-
99.
|
| 686 |
-
],
|
| 687 |
-
"eval_ref_len":
|
| 688 |
-
"eval_runtime":
|
| 689 |
-
"eval_samples_per_second":
|
| 690 |
-
"eval_score":
|
| 691 |
-
"eval_steps_per_second": 1.
|
| 692 |
-
"eval_sys_len":
|
| 693 |
"eval_totals": [
|
| 694 |
-
|
| 695 |
-
|
| 696 |
-
|
| 697 |
-
|
| 698 |
],
|
| 699 |
"step": 2838
|
| 700 |
},
|
| 701 |
{
|
| 702 |
"epoch": 23.0,
|
| 703 |
-
"eval_bp": 0.
|
| 704 |
"eval_counts": [
|
| 705 |
-
|
| 706 |
-
|
| 707 |
-
|
| 708 |
-
|
| 709 |
],
|
| 710 |
-
"eval_loss": 0.
|
| 711 |
"eval_precisions": [
|
| 712 |
-
99.
|
| 713 |
-
99.
|
| 714 |
-
99.
|
| 715 |
-
99.
|
| 716 |
-
],
|
| 717 |
-
"eval_ref_len":
|
| 718 |
-
"eval_runtime":
|
| 719 |
-
"eval_samples_per_second":
|
| 720 |
-
"eval_score":
|
| 721 |
-
"eval_steps_per_second": 1.
|
| 722 |
-
"eval_sys_len":
|
| 723 |
"eval_totals": [
|
| 724 |
-
|
| 725 |
-
|
| 726 |
-
|
| 727 |
-
|
| 728 |
],
|
| 729 |
"step": 2967
|
| 730 |
},
|
| 731 |
{
|
| 732 |
"epoch": 23.26,
|
| 733 |
"learning_rate": 1.0697674418604651e-05,
|
| 734 |
-
"loss": 0.
|
| 735 |
"step": 3000
|
| 736 |
},
|
| 737 |
{
|
| 738 |
"epoch": 24.0,
|
| 739 |
-
"eval_bp": 0.
|
| 740 |
"eval_counts": [
|
| 741 |
-
|
| 742 |
-
|
| 743 |
-
|
| 744 |
-
|
| 745 |
],
|
| 746 |
-
"eval_loss":
|
| 747 |
"eval_precisions": [
|
| 748 |
-
99.
|
| 749 |
-
99.
|
| 750 |
-
99.
|
| 751 |
-
99.
|
| 752 |
-
],
|
| 753 |
-
"eval_ref_len":
|
| 754 |
-
"eval_runtime":
|
| 755 |
-
"eval_samples_per_second":
|
| 756 |
-
"eval_score":
|
| 757 |
-
"eval_steps_per_second": 1.
|
| 758 |
-
"eval_sys_len":
|
| 759 |
"eval_totals": [
|
| 760 |
-
|
| 761 |
-
|
| 762 |
-
|
| 763 |
-
|
| 764 |
],
|
| 765 |
"step": 3096
|
| 766 |
},
|
| 767 |
{
|
| 768 |
"epoch": 25.0,
|
| 769 |
-
"eval_bp": 0.
|
| 770 |
"eval_counts": [
|
| 771 |
-
|
| 772 |
-
|
| 773 |
-
|
| 774 |
-
|
| 775 |
],
|
| 776 |
-
"eval_loss": 0.
|
| 777 |
"eval_precisions": [
|
| 778 |
-
99.
|
| 779 |
-
99.
|
| 780 |
-
99.
|
| 781 |
-
99.
|
| 782 |
-
],
|
| 783 |
-
"eval_ref_len":
|
| 784 |
-
"eval_runtime":
|
| 785 |
-
"eval_samples_per_second":
|
| 786 |
-
"eval_score":
|
| 787 |
-
"eval_steps_per_second": 1.
|
| 788 |
-
"eval_sys_len":
|
| 789 |
"eval_totals": [
|
| 790 |
-
|
| 791 |
-
|
| 792 |
-
|
| 793 |
-
|
| 794 |
],
|
| 795 |
"step": 3225
|
| 796 |
},
|
| 797 |
{
|
| 798 |
"epoch": 26.0,
|
| 799 |
-
"eval_bp": 0.
|
| 800 |
"eval_counts": [
|
| 801 |
-
|
| 802 |
-
|
| 803 |
-
|
| 804 |
-
|
| 805 |
],
|
| 806 |
-
"eval_loss":
|
| 807 |
"eval_precisions": [
|
| 808 |
-
99.
|
| 809 |
-
99.
|
| 810 |
-
99.
|
| 811 |
-
99.
|
| 812 |
-
],
|
| 813 |
-
"eval_ref_len":
|
| 814 |
-
"eval_runtime":
|
| 815 |
-
"eval_samples_per_second":
|
| 816 |
-
"eval_score":
|
| 817 |
-
"eval_steps_per_second": 1.
|
| 818 |
-
"eval_sys_len":
|
| 819 |
"eval_totals": [
|
| 820 |
-
|
| 821 |
-
|
| 822 |
-
|
| 823 |
-
|
| 824 |
],
|
| 825 |
"step": 3354
|
| 826 |
},
|
| 827 |
{
|
| 828 |
"epoch": 27.0,
|
| 829 |
-
"eval_bp": 0.
|
| 830 |
"eval_counts": [
|
| 831 |
-
|
| 832 |
-
|
| 833 |
-
|
| 834 |
-
|
| 835 |
],
|
| 836 |
-
"eval_loss":
|
| 837 |
"eval_precisions": [
|
| 838 |
-
99.
|
| 839 |
-
99.
|
| 840 |
-
99.
|
| 841 |
-
99.
|
| 842 |
-
],
|
| 843 |
-
"eval_ref_len":
|
| 844 |
-
"eval_runtime":
|
| 845 |
-
"eval_samples_per_second":
|
| 846 |
-
"eval_score":
|
| 847 |
-
"eval_steps_per_second": 1.
|
| 848 |
-
"eval_sys_len":
|
| 849 |
"eval_totals": [
|
| 850 |
-
|
| 851 |
-
|
| 852 |
-
|
| 853 |
-
|
| 854 |
],
|
| 855 |
"step": 3483
|
| 856 |
},
|
| 857 |
{
|
| 858 |
"epoch": 27.13,
|
| 859 |
"learning_rate": 9.147286821705427e-06,
|
| 860 |
-
"loss": 0.
|
| 861 |
"step": 3500
|
| 862 |
},
|
| 863 |
{
|
| 864 |
"epoch": 28.0,
|
| 865 |
-
"eval_bp": 0.
|
| 866 |
"eval_counts": [
|
| 867 |
-
|
| 868 |
-
|
| 869 |
-
|
| 870 |
-
|
| 871 |
],
|
| 872 |
-
"eval_loss":
|
| 873 |
"eval_precisions": [
|
| 874 |
-
99.
|
| 875 |
-
99.
|
| 876 |
-
99.
|
| 877 |
-
99.
|
| 878 |
-
],
|
| 879 |
-
"eval_ref_len":
|
| 880 |
-
"eval_runtime":
|
| 881 |
-
"eval_samples_per_second":
|
| 882 |
-
"eval_score":
|
| 883 |
-
"eval_steps_per_second": 1.
|
| 884 |
-
"eval_sys_len":
|
| 885 |
"eval_totals": [
|
| 886 |
-
|
| 887 |
-
|
| 888 |
-
|
| 889 |
-
|
| 890 |
],
|
| 891 |
"step": 3612
|
| 892 |
},
|
| 893 |
{
|
| 894 |
"epoch": 29.0,
|
| 895 |
-
"eval_bp": 0.
|
| 896 |
"eval_counts": [
|
| 897 |
-
|
| 898 |
-
|
| 899 |
-
|
| 900 |
-
|
| 901 |
],
|
| 902 |
-
"eval_loss":
|
| 903 |
"eval_precisions": [
|
| 904 |
-
99.
|
| 905 |
-
99.
|
| 906 |
-
99.
|
| 907 |
-
99.
|
| 908 |
-
],
|
| 909 |
-
"eval_ref_len":
|
| 910 |
-
"eval_runtime":
|
| 911 |
-
"eval_samples_per_second":
|
| 912 |
-
"eval_score":
|
| 913 |
-
"eval_steps_per_second": 1.
|
| 914 |
-
"eval_sys_len":
|
| 915 |
"eval_totals": [
|
| 916 |
-
|
| 917 |
-
|
| 918 |
-
|
| 919 |
-
|
| 920 |
],
|
| 921 |
"step": 3741
|
| 922 |
},
|
| 923 |
{
|
| 924 |
"epoch": 30.0,
|
| 925 |
-
"eval_bp": 0.
|
| 926 |
"eval_counts": [
|
| 927 |
-
|
| 928 |
-
|
| 929 |
-
|
| 930 |
-
|
| 931 |
],
|
| 932 |
-
"eval_loss":
|
| 933 |
"eval_precisions": [
|
| 934 |
-
99.
|
| 935 |
-
99.
|
| 936 |
-
99.
|
| 937 |
-
99.
|
| 938 |
-
],
|
| 939 |
-
"eval_ref_len":
|
| 940 |
-
"eval_runtime":
|
| 941 |
-
"eval_samples_per_second":
|
| 942 |
-
"eval_score":
|
| 943 |
-
"eval_steps_per_second": 1.
|
| 944 |
-
"eval_sys_len":
|
| 945 |
"eval_totals": [
|
| 946 |
-
|
| 947 |
-
|
| 948 |
-
|
| 949 |
-
|
| 950 |
],
|
| 951 |
"step": 3870
|
| 952 |
},
|
| 953 |
{
|
| 954 |
"epoch": 31.0,
|
| 955 |
-
"eval_bp": 0.
|
| 956 |
"eval_counts": [
|
| 957 |
-
|
| 958 |
-
|
| 959 |
-
|
| 960 |
-
|
| 961 |
],
|
| 962 |
-
"eval_loss":
|
| 963 |
"eval_precisions": [
|
| 964 |
-
99.
|
| 965 |
-
99.
|
| 966 |
-
99.
|
| 967 |
-
99.
|
| 968 |
-
],
|
| 969 |
-
"eval_ref_len":
|
| 970 |
-
"eval_runtime":
|
| 971 |
-
"eval_samples_per_second":
|
| 972 |
-
"eval_score":
|
| 973 |
-
"eval_steps_per_second": 1.
|
| 974 |
-
"eval_sys_len":
|
| 975 |
"eval_totals": [
|
| 976 |
-
|
| 977 |
-
|
| 978 |
-
|
| 979 |
-
|
| 980 |
],
|
| 981 |
"step": 3999
|
| 982 |
},
|
| 983 |
{
|
| 984 |
"epoch": 31.01,
|
| 985 |
"learning_rate": 7.596899224806202e-06,
|
| 986 |
-
"loss": 0.
|
| 987 |
"step": 4000
|
| 988 |
},
|
| 989 |
{
|
| 990 |
"epoch": 32.0,
|
| 991 |
-
"eval_bp": 0.
|
| 992 |
"eval_counts": [
|
| 993 |
-
|
| 994 |
-
|
| 995 |
-
|
| 996 |
-
|
| 997 |
],
|
| 998 |
-
"eval_loss":
|
| 999 |
"eval_precisions": [
|
| 1000 |
-
99.
|
| 1001 |
-
99.
|
| 1002 |
-
99.
|
| 1003 |
-
99.
|
| 1004 |
-
],
|
| 1005 |
-
"eval_ref_len":
|
| 1006 |
-
"eval_runtime":
|
| 1007 |
-
"eval_samples_per_second":
|
| 1008 |
-
"eval_score":
|
| 1009 |
-
"eval_steps_per_second": 1.
|
| 1010 |
-
"eval_sys_len":
|
| 1011 |
"eval_totals": [
|
| 1012 |
-
|
| 1013 |
-
|
| 1014 |
-
|
| 1015 |
-
|
| 1016 |
],
|
| 1017 |
"step": 4128
|
| 1018 |
},
|
| 1019 |
{
|
| 1020 |
"epoch": 33.0,
|
| 1021 |
-
"eval_bp": 0.
|
| 1022 |
"eval_counts": [
|
| 1023 |
-
|
| 1024 |
-
|
| 1025 |
-
|
| 1026 |
-
|
| 1027 |
],
|
| 1028 |
-
"eval_loss": 4.
|
| 1029 |
"eval_precisions": [
|
| 1030 |
-
99.
|
| 1031 |
-
99.
|
| 1032 |
-
99.
|
| 1033 |
-
99.
|
| 1034 |
-
],
|
| 1035 |
-
"eval_ref_len":
|
| 1036 |
-
"eval_runtime":
|
| 1037 |
-
"eval_samples_per_second":
|
| 1038 |
-
"eval_score":
|
| 1039 |
-
"eval_steps_per_second": 1.
|
| 1040 |
-
"eval_sys_len":
|
| 1041 |
"eval_totals": [
|
| 1042 |
-
|
| 1043 |
-
|
| 1044 |
-
|
| 1045 |
-
|
| 1046 |
],
|
| 1047 |
"step": 4257
|
| 1048 |
},
|
| 1049 |
{
|
| 1050 |
"epoch": 34.0,
|
| 1051 |
-
"eval_bp": 0.
|
| 1052 |
"eval_counts": [
|
| 1053 |
-
|
| 1054 |
-
|
| 1055 |
-
|
| 1056 |
-
|
| 1057 |
],
|
| 1058 |
-
"eval_loss":
|
| 1059 |
"eval_precisions": [
|
| 1060 |
-
99.
|
| 1061 |
-
99.
|
| 1062 |
-
99.
|
| 1063 |
-
99.
|
| 1064 |
-
],
|
| 1065 |
-
"eval_ref_len":
|
| 1066 |
-
"eval_runtime":
|
| 1067 |
-
"eval_samples_per_second":
|
| 1068 |
-
"eval_score":
|
| 1069 |
-
"eval_steps_per_second": 1.
|
| 1070 |
-
"eval_sys_len":
|
| 1071 |
"eval_totals": [
|
| 1072 |
-
|
| 1073 |
-
|
| 1074 |
-
|
| 1075 |
-
|
| 1076 |
],
|
| 1077 |
"step": 4386
|
| 1078 |
},
|
| 1079 |
{
|
| 1080 |
"epoch": 34.88,
|
| 1081 |
"learning_rate": 6.046511627906977e-06,
|
| 1082 |
-
"loss": 0.
|
| 1083 |
"step": 4500
|
| 1084 |
},
|
| 1085 |
{
|
| 1086 |
"epoch": 35.0,
|
| 1087 |
-
"eval_bp": 0.
|
| 1088 |
"eval_counts": [
|
| 1089 |
-
|
| 1090 |
-
|
| 1091 |
-
|
| 1092 |
-
|
| 1093 |
],
|
| 1094 |
-
"eval_loss":
|
| 1095 |
"eval_precisions": [
|
| 1096 |
-
99.
|
| 1097 |
-
99.
|
| 1098 |
-
99.
|
| 1099 |
-
99.
|
| 1100 |
-
],
|
| 1101 |
-
"eval_ref_len":
|
| 1102 |
-
"eval_runtime":
|
| 1103 |
-
"eval_samples_per_second":
|
| 1104 |
-
"eval_score":
|
| 1105 |
-
"eval_steps_per_second": 1.
|
| 1106 |
-
"eval_sys_len":
|
| 1107 |
"eval_totals": [
|
| 1108 |
-
|
| 1109 |
-
|
| 1110 |
-
|
| 1111 |
-
|
| 1112 |
],
|
| 1113 |
"step": 4515
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
"epoch": 36.0,
|
| 1117 |
-
"eval_bp": 0.
|
| 1118 |
"eval_counts": [
|
| 1119 |
-
|
| 1120 |
-
|
| 1121 |
-
|
| 1122 |
-
|
| 1123 |
],
|
| 1124 |
-
"eval_loss": 1.
|
| 1125 |
"eval_precisions": [
|
| 1126 |
-
99.
|
| 1127 |
-
99.
|
| 1128 |
-
99.
|
| 1129 |
-
99.
|
| 1130 |
-
],
|
| 1131 |
-
"eval_ref_len":
|
| 1132 |
-
"eval_runtime":
|
| 1133 |
-
"eval_samples_per_second":
|
| 1134 |
-
"eval_score":
|
| 1135 |
-
"eval_steps_per_second": 1.
|
| 1136 |
-
"eval_sys_len":
|
| 1137 |
"eval_totals": [
|
| 1138 |
-
|
| 1139 |
-
|
| 1140 |
-
|
| 1141 |
-
|
| 1142 |
],
|
| 1143 |
"step": 4644
|
| 1144 |
},
|
| 1145 |
{
|
| 1146 |
"epoch": 37.0,
|
| 1147 |
-
"eval_bp": 0.
|
| 1148 |
"eval_counts": [
|
| 1149 |
-
|
| 1150 |
-
|
| 1151 |
-
|
| 1152 |
-
|
| 1153 |
],
|
| 1154 |
-
"eval_loss":
|
| 1155 |
"eval_precisions": [
|
| 1156 |
-
99.
|
| 1157 |
-
99.
|
| 1158 |
-
99.
|
| 1159 |
-
99.
|
| 1160 |
-
],
|
| 1161 |
-
"eval_ref_len":
|
| 1162 |
-
"eval_runtime":
|
| 1163 |
-
"eval_samples_per_second":
|
| 1164 |
-
"eval_score":
|
| 1165 |
-
"eval_steps_per_second": 1.
|
| 1166 |
-
"eval_sys_len":
|
| 1167 |
"eval_totals": [
|
| 1168 |
-
|
| 1169 |
-
|
| 1170 |
-
|
| 1171 |
-
|
| 1172 |
],
|
| 1173 |
"step": 4773
|
| 1174 |
},
|
| 1175 |
{
|
| 1176 |
"epoch": 38.0,
|
| 1177 |
-
"eval_bp": 0.
|
| 1178 |
"eval_counts": [
|
| 1179 |
-
|
| 1180 |
-
|
| 1181 |
-
|
| 1182 |
-
|
| 1183 |
],
|
| 1184 |
-
"eval_loss":
|
| 1185 |
"eval_precisions": [
|
| 1186 |
-
99.
|
| 1187 |
-
99.
|
| 1188 |
-
99.
|
| 1189 |
-
99.
|
| 1190 |
-
],
|
| 1191 |
-
"eval_ref_len":
|
| 1192 |
-
"eval_runtime":
|
| 1193 |
-
"eval_samples_per_second":
|
| 1194 |
-
"eval_score":
|
| 1195 |
-
"eval_steps_per_second": 1.
|
| 1196 |
-
"eval_sys_len":
|
| 1197 |
"eval_totals": [
|
| 1198 |
-
|
| 1199 |
-
|
| 1200 |
-
|
| 1201 |
-
|
| 1202 |
],
|
| 1203 |
"step": 4902
|
| 1204 |
},
|
| 1205 |
{
|
| 1206 |
"epoch": 38.76,
|
| 1207 |
"learning_rate": 4.4961240310077525e-06,
|
| 1208 |
-
"loss": 0.
|
| 1209 |
"step": 5000
|
| 1210 |
},
|
| 1211 |
{
|
| 1212 |
"epoch": 39.0,
|
| 1213 |
-
"eval_bp": 0.
|
| 1214 |
"eval_counts": [
|
| 1215 |
-
|
| 1216 |
-
|
| 1217 |
-
|
| 1218 |
-
|
| 1219 |
],
|
| 1220 |
-
"eval_loss":
|
| 1221 |
"eval_precisions": [
|
| 1222 |
-
99.
|
| 1223 |
-
99.
|
| 1224 |
-
99.
|
| 1225 |
-
99.
|
| 1226 |
-
],
|
| 1227 |
-
"eval_ref_len":
|
| 1228 |
-
"eval_runtime":
|
| 1229 |
-
"eval_samples_per_second":
|
| 1230 |
-
"eval_score":
|
| 1231 |
-
"eval_steps_per_second": 1.
|
| 1232 |
-
"eval_sys_len":
|
| 1233 |
"eval_totals": [
|
| 1234 |
-
|
| 1235 |
-
|
| 1236 |
-
|
| 1237 |
-
|
| 1238 |
],
|
| 1239 |
"step": 5031
|
| 1240 |
},
|
| 1241 |
{
|
| 1242 |
"epoch": 40.0,
|
| 1243 |
-
"eval_bp": 0.
|
| 1244 |
"eval_counts": [
|
| 1245 |
-
|
| 1246 |
-
|
| 1247 |
-
|
| 1248 |
-
|
| 1249 |
],
|
| 1250 |
-
"eval_loss":
|
| 1251 |
"eval_precisions": [
|
| 1252 |
-
99.
|
| 1253 |
-
99.
|
| 1254 |
-
99.
|
| 1255 |
-
99.
|
| 1256 |
-
],
|
| 1257 |
-
"eval_ref_len":
|
| 1258 |
-
"eval_runtime":
|
| 1259 |
-
"eval_samples_per_second":
|
| 1260 |
-
"eval_score":
|
| 1261 |
-
"eval_steps_per_second": 1.
|
| 1262 |
-
"eval_sys_len":
|
| 1263 |
"eval_totals": [
|
| 1264 |
-
|
| 1265 |
-
|
| 1266 |
-
|
| 1267 |
-
|
| 1268 |
],
|
| 1269 |
"step": 5160
|
| 1270 |
},
|
| 1271 |
{
|
| 1272 |
"epoch": 41.0,
|
| 1273 |
-
"eval_bp": 0.
|
| 1274 |
"eval_counts": [
|
| 1275 |
-
|
| 1276 |
-
|
| 1277 |
-
|
| 1278 |
-
|
| 1279 |
],
|
| 1280 |
-
"eval_loss":
|
| 1281 |
"eval_precisions": [
|
| 1282 |
-
99.
|
| 1283 |
-
99.
|
| 1284 |
-
99.
|
| 1285 |
-
99.
|
| 1286 |
-
],
|
| 1287 |
-
"eval_ref_len":
|
| 1288 |
-
"eval_runtime":
|
| 1289 |
-
"eval_samples_per_second":
|
| 1290 |
-
"eval_score":
|
| 1291 |
-
"eval_steps_per_second": 1.
|
| 1292 |
-
"eval_sys_len":
|
| 1293 |
"eval_totals": [
|
| 1294 |
-
|
| 1295 |
-
|
| 1296 |
-
|
| 1297 |
-
|
| 1298 |
],
|
| 1299 |
"step": 5289
|
| 1300 |
},
|
| 1301 |
{
|
| 1302 |
"epoch": 42.0,
|
| 1303 |
-
"eval_bp": 0.
|
| 1304 |
"eval_counts": [
|
| 1305 |
-
|
| 1306 |
-
|
| 1307 |
-
|
| 1308 |
-
|
| 1309 |
],
|
| 1310 |
-
"eval_loss":
|
| 1311 |
"eval_precisions": [
|
| 1312 |
-
99.
|
| 1313 |
-
99.
|
| 1314 |
-
99.
|
| 1315 |
-
99.
|
| 1316 |
-
],
|
| 1317 |
-
"eval_ref_len":
|
| 1318 |
-
"eval_runtime":
|
| 1319 |
-
"eval_samples_per_second":
|
| 1320 |
-
"eval_score":
|
| 1321 |
-
"eval_steps_per_second": 1.
|
| 1322 |
-
"eval_sys_len":
|
| 1323 |
"eval_totals": [
|
| 1324 |
-
|
| 1325 |
-
|
| 1326 |
-
|
| 1327 |
-
|
| 1328 |
],
|
| 1329 |
"step": 5418
|
| 1330 |
},
|
| 1331 |
{
|
| 1332 |
"epoch": 42.64,
|
| 1333 |
"learning_rate": 2.9457364341085276e-06,
|
| 1334 |
-
"loss": 0.
|
| 1335 |
"step": 5500
|
| 1336 |
},
|
| 1337 |
{
|
| 1338 |
"epoch": 43.0,
|
| 1339 |
-
"eval_bp": 0.
|
| 1340 |
"eval_counts": [
|
| 1341 |
-
|
| 1342 |
-
|
| 1343 |
-
|
| 1344 |
-
|
| 1345 |
],
|
| 1346 |
-
"eval_loss":
|
| 1347 |
"eval_precisions": [
|
| 1348 |
-
99.
|
| 1349 |
-
99.
|
| 1350 |
-
99.
|
| 1351 |
-
99.
|
| 1352 |
-
],
|
| 1353 |
-
"eval_ref_len":
|
| 1354 |
-
"eval_runtime":
|
| 1355 |
-
"eval_samples_per_second":
|
| 1356 |
-
"eval_score":
|
| 1357 |
-
"eval_steps_per_second": 1.
|
| 1358 |
-
"eval_sys_len":
|
| 1359 |
"eval_totals": [
|
| 1360 |
-
|
| 1361 |
-
|
| 1362 |
-
|
| 1363 |
-
|
| 1364 |
],
|
| 1365 |
"step": 5547
|
| 1366 |
},
|
| 1367 |
{
|
| 1368 |
"epoch": 44.0,
|
| 1369 |
-
"eval_bp": 0.
|
| 1370 |
"eval_counts": [
|
| 1371 |
-
|
| 1372 |
-
|
| 1373 |
-
|
| 1374 |
-
|
| 1375 |
],
|
| 1376 |
-
"eval_loss":
|
| 1377 |
"eval_precisions": [
|
| 1378 |
-
99.
|
| 1379 |
-
99.
|
| 1380 |
-
99.
|
| 1381 |
-
99.
|
| 1382 |
-
],
|
| 1383 |
-
"eval_ref_len":
|
| 1384 |
-
"eval_runtime":
|
| 1385 |
-
"eval_samples_per_second":
|
| 1386 |
-
"eval_score":
|
| 1387 |
-
"eval_steps_per_second": 1.
|
| 1388 |
-
"eval_sys_len":
|
| 1389 |
"eval_totals": [
|
| 1390 |
-
|
| 1391 |
-
|
| 1392 |
-
|
| 1393 |
-
|
| 1394 |
],
|
| 1395 |
"step": 5676
|
| 1396 |
},
|
| 1397 |
{
|
| 1398 |
"epoch": 45.0,
|
| 1399 |
-
"eval_bp": 0.
|
| 1400 |
"eval_counts": [
|
| 1401 |
-
|
| 1402 |
-
|
| 1403 |
-
|
| 1404 |
-
|
| 1405 |
],
|
| 1406 |
-
"eval_loss":
|
| 1407 |
"eval_precisions": [
|
| 1408 |
-
99.
|
| 1409 |
-
99.
|
| 1410 |
-
99.
|
| 1411 |
-
99.
|
| 1412 |
-
],
|
| 1413 |
-
"eval_ref_len":
|
| 1414 |
-
"eval_runtime":
|
| 1415 |
-
"eval_samples_per_second":
|
| 1416 |
-
"eval_score":
|
| 1417 |
-
"eval_steps_per_second": 1.
|
| 1418 |
-
"eval_sys_len":
|
| 1419 |
"eval_totals": [
|
| 1420 |
-
|
| 1421 |
-
|
| 1422 |
-
|
| 1423 |
-
|
| 1424 |
],
|
| 1425 |
"step": 5805
|
| 1426 |
},
|
| 1427 |
{
|
| 1428 |
"epoch": 46.0,
|
| 1429 |
-
"eval_bp": 0.
|
| 1430 |
"eval_counts": [
|
| 1431 |
-
|
| 1432 |
-
|
| 1433 |
-
|
| 1434 |
-
|
| 1435 |
],
|
| 1436 |
-
"eval_loss":
|
| 1437 |
"eval_precisions": [
|
| 1438 |
-
99.
|
| 1439 |
-
99.
|
| 1440 |
-
99.
|
| 1441 |
-
99.
|
| 1442 |
-
],
|
| 1443 |
-
"eval_ref_len":
|
| 1444 |
-
"eval_runtime":
|
| 1445 |
-
"eval_samples_per_second":
|
| 1446 |
-
"eval_score":
|
| 1447 |
-
"eval_steps_per_second": 1.
|
| 1448 |
-
"eval_sys_len":
|
| 1449 |
"eval_totals": [
|
| 1450 |
-
|
| 1451 |
-
|
| 1452 |
-
|
| 1453 |
-
|
| 1454 |
],
|
| 1455 |
"step": 5934
|
| 1456 |
},
|
| 1457 |
{
|
| 1458 |
"epoch": 46.51,
|
| 1459 |
"learning_rate": 1.3953488372093025e-06,
|
| 1460 |
-
"loss": 0.
|
| 1461 |
"step": 6000
|
| 1462 |
}
|
| 1463 |
],
|
|
@@ -1466,7 +1466,7 @@
|
|
| 1466 |
"num_input_tokens_seen": 0,
|
| 1467 |
"num_train_epochs": 50,
|
| 1468 |
"save_steps": 500,
|
| 1469 |
-
"total_flos": 2.
|
| 1470 |
"train_batch_size": 32,
|
| 1471 |
"trial_name": null,
|
| 1472 |
"trial_params": null
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
+
"eval_bp": 0.8731878729849682,
|
| 14 |
"eval_counts": [
|
| 15 |
+
4461,
|
| 16 |
+
3931,
|
| 17 |
+
3406,
|
| 18 |
+
2881
|
| 19 |
],
|
| 20 |
+
"eval_loss": 0.004611688666045666,
|
| 21 |
"eval_precisions": [
|
| 22 |
+
99.33199732798931,
|
| 23 |
+
99.14249684741488,
|
| 24 |
+
99.04041872637394,
|
| 25 |
+
98.90147614143494
|
| 26 |
+
],
|
| 27 |
+
"eval_ref_len": 5100,
|
| 28 |
+
"eval_runtime": 16.8,
|
| 29 |
+
"eval_samples_per_second": 31.31,
|
| 30 |
+
"eval_score": 86.5363874068898,
|
| 31 |
+
"eval_steps_per_second": 1.012,
|
| 32 |
+
"eval_sys_len": 4491,
|
| 33 |
"eval_totals": [
|
| 34 |
+
4491,
|
| 35 |
+
3965,
|
| 36 |
+
3439,
|
| 37 |
+
2913
|
| 38 |
],
|
| 39 |
"step": 129
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 2.0,
|
| 43 |
+
"eval_bp": 0.869649689238195,
|
| 44 |
"eval_counts": [
|
| 45 |
+
4458,
|
| 46 |
+
3930,
|
| 47 |
+
3403,
|
| 48 |
+
2876
|
| 49 |
],
|
| 50 |
+
"eval_loss": 0.00696711428463459,
|
| 51 |
"eval_precisions": [
|
| 52 |
+
99.62011173184358,
|
| 53 |
+
99.51886553557863,
|
| 54 |
+
99.41571720712825,
|
| 55 |
+
99.27511218501898
|
| 56 |
+
],
|
| 57 |
+
"eval_ref_len": 5100,
|
| 58 |
+
"eval_runtime": 13.788,
|
| 59 |
+
"eval_samples_per_second": 38.149,
|
| 60 |
+
"eval_score": 86.49307063670169,
|
| 61 |
+
"eval_steps_per_second": 1.233,
|
| 62 |
+
"eval_sys_len": 4475,
|
| 63 |
"eval_totals": [
|
| 64 |
+
4475,
|
| 65 |
+
3949,
|
| 66 |
+
3423,
|
| 67 |
+
2897
|
| 68 |
],
|
| 69 |
"step": 258
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 3.0,
|
| 73 |
+
"eval_bp": 0.8727461954138965,
|
| 74 |
"eval_counts": [
|
| 75 |
+
4463,
|
| 76 |
+
3936,
|
| 77 |
+
3409,
|
| 78 |
+
2882
|
| 79 |
],
|
| 80 |
+
"eval_loss": 0.0054754531010985374,
|
| 81 |
"eval_precisions": [
|
| 82 |
+
99.42080641568278,
|
| 83 |
+
99.31869795609387,
|
| 84 |
+
99.18533604887983,
|
| 85 |
+
99.00377877018207
|
| 86 |
+
],
|
| 87 |
+
"eval_ref_len": 5100,
|
| 88 |
+
"eval_runtime": 13.887,
|
| 89 |
+
"eval_samples_per_second": 37.877,
|
| 90 |
+
"eval_score": 86.60437841944254,
|
| 91 |
+
"eval_steps_per_second": 1.224,
|
| 92 |
+
"eval_sys_len": 4489,
|
| 93 |
"eval_totals": [
|
| 94 |
+
4489,
|
| 95 |
+
3963,
|
| 96 |
+
3437,
|
| 97 |
+
2911
|
| 98 |
],
|
| 99 |
"step": 387
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 3.88,
|
| 103 |
"learning_rate": 1.8449612403100777e-05,
|
| 104 |
+
"loss": 0.0338,
|
| 105 |
"step": 500
|
| 106 |
},
|
| 107 |
{
|
| 108 |
"epoch": 4.0,
|
| 109 |
+
"eval_bp": 0.8703139283627056,
|
| 110 |
"eval_counts": [
|
| 111 |
+
4464,
|
| 112 |
+
3938,
|
| 113 |
+
3409,
|
| 114 |
+
2881
|
| 115 |
],
|
| 116 |
+
"eval_loss": 0.0021970090456306934,
|
| 117 |
"eval_precisions": [
|
| 118 |
+
99.68736042876284,
|
| 119 |
+
99.64574898785425,
|
| 120 |
+
99.50379451255108,
|
| 121 |
+
99.34482758620689
|
| 122 |
+
],
|
| 123 |
+
"eval_ref_len": 5100,
|
| 124 |
+
"eval_runtime": 14.1368,
|
| 125 |
+
"eval_samples_per_second": 37.208,
|
| 126 |
+
"eval_score": 86.63569782205596,
|
| 127 |
+
"eval_steps_per_second": 1.203,
|
| 128 |
+
"eval_sys_len": 4478,
|
| 129 |
"eval_totals": [
|
| 130 |
+
4478,
|
| 131 |
+
3952,
|
| 132 |
+
3426,
|
| 133 |
+
2900
|
| 134 |
],
|
| 135 |
"step": 516
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 5.0,
|
| 139 |
+
"eval_bp": 0.8707565416150743,
|
| 140 |
"eval_counts": [
|
| 141 |
+
4461,
|
| 142 |
+
3933,
|
| 143 |
+
3406,
|
| 144 |
+
2880
|
| 145 |
],
|
| 146 |
+
"eval_loss": 0.0019001211039721966,
|
| 147 |
"eval_precisions": [
|
| 148 |
+
99.57589285714286,
|
| 149 |
+
99.46889226100151,
|
| 150 |
+
99.35822637106185,
|
| 151 |
+
99.24190213645761
|
| 152 |
+
],
|
| 153 |
+
"eval_ref_len": 5100,
|
| 154 |
+
"eval_runtime": 13.879,
|
| 155 |
+
"eval_samples_per_second": 37.899,
|
| 156 |
+
"eval_score": 86.56290964643597,
|
| 157 |
+
"eval_steps_per_second": 1.225,
|
| 158 |
+
"eval_sys_len": 4480,
|
| 159 |
"eval_totals": [
|
| 160 |
+
4480,
|
| 161 |
+
3954,
|
| 162 |
+
3428,
|
| 163 |
+
2902
|
| 164 |
],
|
| 165 |
"step": 645
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 6.0,
|
| 169 |
+
"eval_bp": 0.8700925578924447,
|
| 170 |
"eval_counts": [
|
| 171 |
+
4463,
|
| 172 |
+
3937,
|
| 173 |
+
3411,
|
| 174 |
+
2885
|
| 175 |
],
|
| 176 |
+
"eval_loss": 0.0021749669685959816,
|
| 177 |
"eval_precisions": [
|
| 178 |
+
99.6872905963815,
|
| 179 |
+
99.64565932675272,
|
| 180 |
+
99.5912408759124,
|
| 181 |
+
99.51707485339773
|
| 182 |
+
],
|
| 183 |
+
"eval_ref_len": 5100,
|
| 184 |
+
"eval_runtime": 14.1959,
|
| 185 |
+
"eval_samples_per_second": 37.053,
|
| 186 |
+
"eval_score": 86.6701772747815,
|
| 187 |
+
"eval_steps_per_second": 1.198,
|
| 188 |
+
"eval_sys_len": 4477,
|
| 189 |
"eval_totals": [
|
| 190 |
+
4477,
|
| 191 |
+
3951,
|
| 192 |
+
3425,
|
| 193 |
+
2899
|
| 194 |
],
|
| 195 |
"step": 774
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 7.0,
|
| 199 |
+
"eval_bp": 0.8703139283627056,
|
| 200 |
"eval_counts": [
|
| 201 |
+
4464,
|
| 202 |
+
3938,
|
| 203 |
+
3412,
|
| 204 |
+
2886
|
| 205 |
],
|
| 206 |
+
"eval_loss": 0.0006092642433941364,
|
| 207 |
"eval_precisions": [
|
| 208 |
+
99.68736042876284,
|
| 209 |
+
99.64574898785425,
|
| 210 |
+
99.59136018680677,
|
| 211 |
+
99.51724137931035
|
| 212 |
+
],
|
| 213 |
+
"eval_ref_len": 5100,
|
| 214 |
+
"eval_runtime": 13.778,
|
| 215 |
+
"eval_samples_per_second": 38.177,
|
| 216 |
+
"eval_score": 86.69232496739014,
|
| 217 |
+
"eval_steps_per_second": 1.234,
|
| 218 |
+
"eval_sys_len": 4478,
|
| 219 |
"eval_totals": [
|
| 220 |
+
4478,
|
| 221 |
+
3952,
|
| 222 |
+
3426,
|
| 223 |
+
2900
|
| 224 |
],
|
| 225 |
"step": 903
|
| 226 |
},
|
| 227 |
{
|
| 228 |
"epoch": 7.75,
|
| 229 |
"learning_rate": 1.689922480620155e-05,
|
| 230 |
+
"loss": 0.0059,
|
| 231 |
"step": 1000
|
| 232 |
},
|
| 233 |
{
|
| 234 |
"epoch": 8.0,
|
| 235 |
+
"eval_bp": 0.8714201423501817,
|
| 236 |
"eval_counts": [
|
| 237 |
+
4460,
|
| 238 |
+
3930,
|
| 239 |
+
3404,
|
| 240 |
+
2878
|
| 241 |
],
|
| 242 |
+
"eval_loss": 0.0026030810549855232,
|
| 243 |
"eval_precisions": [
|
| 244 |
+
99.48695070265447,
|
| 245 |
+
99.31766489764973,
|
| 246 |
+
99.21305741766248,
|
| 247 |
+
99.07056798623064
|
| 248 |
+
],
|
| 249 |
+
"eval_ref_len": 5100,
|
| 250 |
+
"eval_runtime": 14.1647,
|
| 251 |
+
"eval_samples_per_second": 37.135,
|
| 252 |
+
"eval_score": 86.50757156803533,
|
| 253 |
+
"eval_steps_per_second": 1.2,
|
| 254 |
+
"eval_sys_len": 4483,
|
| 255 |
"eval_totals": [
|
| 256 |
+
4483,
|
| 257 |
+
3957,
|
| 258 |
+
3431,
|
| 259 |
+
2905
|
| 260 |
],
|
| 261 |
"step": 1032
|
| 262 |
},
|
| 263 |
{
|
| 264 |
"epoch": 9.0,
|
| 265 |
+
"eval_bp": 0.8711989846507546,
|
| 266 |
"eval_counts": [
|
| 267 |
+
4459,
|
| 268 |
+
3929,
|
| 269 |
+
3403,
|
| 270 |
+
2877
|
| 271 |
],
|
| 272 |
+
"eval_loss": 0.00256777903996408,
|
| 273 |
"eval_precisions": [
|
| 274 |
+
99.48683623382419,
|
| 275 |
+
99.31749241658241,
|
| 276 |
+
99.21282798833819,
|
| 277 |
+
99.0702479338843
|
| 278 |
+
],
|
| 279 |
+
"eval_ref_len": 5100,
|
| 280 |
+
"eval_runtime": 13.7621,
|
| 281 |
+
"eval_samples_per_second": 38.221,
|
| 282 |
+
"eval_score": 86.4854345384993,
|
| 283 |
+
"eval_steps_per_second": 1.235,
|
| 284 |
+
"eval_sys_len": 4482,
|
| 285 |
"eval_totals": [
|
| 286 |
+
4482,
|
| 287 |
+
3956,
|
| 288 |
+
3430,
|
| 289 |
+
2904
|
| 290 |
],
|
| 291 |
"step": 1161
|
| 292 |
},
|
| 293 |
{
|
| 294 |
"epoch": 10.0,
|
| 295 |
+
"eval_bp": 0.8700925578924447,
|
| 296 |
"eval_counts": [
|
| 297 |
+
4463,
|
| 298 |
+
3937,
|
| 299 |
+
3410,
|
| 300 |
+
2883
|
| 301 |
],
|
| 302 |
+
"eval_loss": 0.0008762977086007595,
|
| 303 |
"eval_precisions": [
|
| 304 |
+
99.6872905963815,
|
| 305 |
+
99.64565932675272,
|
| 306 |
+
99.56204379562044,
|
| 307 |
+
99.44808554674026
|
| 308 |
+
],
|
| 309 |
+
"eval_ref_len": 5100,
|
| 310 |
+
"eval_runtime": 14.033,
|
| 311 |
+
"eval_samples_per_second": 37.483,
|
| 312 |
+
"eval_score": 86.64880068746125,
|
| 313 |
+
"eval_steps_per_second": 1.211,
|
| 314 |
+
"eval_sys_len": 4477,
|
| 315 |
"eval_totals": [
|
| 316 |
+
4477,
|
| 317 |
+
3951,
|
| 318 |
+
3425,
|
| 319 |
+
2899
|
| 320 |
],
|
| 321 |
"step": 1290
|
| 322 |
},
|
| 323 |
{
|
| 324 |
"epoch": 11.0,
|
| 325 |
+
"eval_bp": 0.8707565416150743,
|
| 326 |
"eval_counts": [
|
| 327 |
+
4462,
|
| 328 |
+
3935,
|
| 329 |
+
3408,
|
| 330 |
+
2881
|
| 331 |
],
|
| 332 |
+
"eval_loss": 0.0005689110257662833,
|
| 333 |
"eval_precisions": [
|
| 334 |
+
99.59821428571429,
|
| 335 |
+
99.51947395042994,
|
| 336 |
+
99.41656942823803,
|
| 337 |
+
99.276361130255
|
| 338 |
+
],
|
| 339 |
+
"eval_ref_len": 5100,
|
| 340 |
+
"eval_runtime": 13.8477,
|
| 341 |
+
"eval_samples_per_second": 37.985,
|
| 342 |
+
"eval_score": 86.5989861295871,
|
| 343 |
+
"eval_steps_per_second": 1.228,
|
| 344 |
+
"eval_sys_len": 4480,
|
| 345 |
"eval_totals": [
|
| 346 |
+
4480,
|
| 347 |
+
3954,
|
| 348 |
+
3428,
|
| 349 |
+
2902
|
| 350 |
],
|
| 351 |
"step": 1419
|
| 352 |
},
|
| 353 |
{
|
| 354 |
"epoch": 11.63,
|
| 355 |
"learning_rate": 1.5348837209302328e-05,
|
| 356 |
+
"loss": 0.0042,
|
| 357 |
"step": 1500
|
| 358 |
},
|
| 359 |
{
|
| 360 |
"epoch": 12.0,
|
| 361 |
+
"eval_bp": 0.8711989846507546,
|
| 362 |
"eval_counts": [
|
| 363 |
+
4459,
|
| 364 |
+
3929,
|
| 365 |
+
3403,
|
| 366 |
+
2877
|
| 367 |
],
|
| 368 |
+
"eval_loss": 0.0013145459815859795,
|
| 369 |
"eval_precisions": [
|
| 370 |
+
99.48683623382419,
|
| 371 |
+
99.31749241658241,
|
| 372 |
+
99.21282798833819,
|
| 373 |
+
99.0702479338843
|
| 374 |
+
],
|
| 375 |
+
"eval_ref_len": 5100,
|
| 376 |
+
"eval_runtime": 13.7281,
|
| 377 |
+
"eval_samples_per_second": 38.316,
|
| 378 |
+
"eval_score": 86.4854345384993,
|
| 379 |
+
"eval_steps_per_second": 1.238,
|
| 380 |
+
"eval_sys_len": 4482,
|
| 381 |
"eval_totals": [
|
| 382 |
+
4482,
|
| 383 |
+
3956,
|
| 384 |
+
3430,
|
| 385 |
+
2904
|
| 386 |
],
|
| 387 |
"step": 1548
|
| 388 |
},
|
| 389 |
{
|
| 390 |
"epoch": 13.0,
|
| 391 |
+
"eval_bp": 0.8700925578924447,
|
| 392 |
"eval_counts": [
|
| 393 |
+
4463,
|
| 394 |
+
3937,
|
| 395 |
+
3410,
|
| 396 |
+
2883
|
| 397 |
],
|
| 398 |
+
"eval_loss": 0.0008758930489420891,
|
| 399 |
"eval_precisions": [
|
| 400 |
+
99.6872905963815,
|
| 401 |
+
99.64565932675272,
|
| 402 |
+
99.56204379562044,
|
| 403 |
+
99.44808554674026
|
| 404 |
+
],
|
| 405 |
+
"eval_ref_len": 5100,
|
| 406 |
+
"eval_runtime": 13.731,
|
| 407 |
+
"eval_samples_per_second": 38.308,
|
| 408 |
+
"eval_score": 86.64880068746125,
|
| 409 |
+
"eval_steps_per_second": 1.238,
|
| 410 |
+
"eval_sys_len": 4477,
|
| 411 |
"eval_totals": [
|
| 412 |
+
4477,
|
| 413 |
+
3951,
|
| 414 |
+
3425,
|
| 415 |
+
2899
|
| 416 |
],
|
| 417 |
"step": 1677
|
| 418 |
},
|
| 419 |
{
|
| 420 |
"epoch": 14.0,
|
| 421 |
+
"eval_bp": 0.8700925578924447,
|
| 422 |
"eval_counts": [
|
| 423 |
+
4463,
|
| 424 |
+
3937,
|
| 425 |
+
3411,
|
| 426 |
+
2885
|
| 427 |
],
|
| 428 |
+
"eval_loss": 0.0003304094134364277,
|
| 429 |
"eval_precisions": [
|
| 430 |
+
99.6872905963815,
|
| 431 |
+
99.64565932675272,
|
| 432 |
+
99.5912408759124,
|
| 433 |
+
99.51707485339773
|
| 434 |
+
],
|
| 435 |
+
"eval_ref_len": 5100,
|
| 436 |
+
"eval_runtime": 14.021,
|
| 437 |
+
"eval_samples_per_second": 37.515,
|
| 438 |
+
"eval_score": 86.6701772747815,
|
| 439 |
+
"eval_steps_per_second": 1.212,
|
| 440 |
+
"eval_sys_len": 4477,
|
| 441 |
"eval_totals": [
|
| 442 |
+
4477,
|
| 443 |
+
3951,
|
| 444 |
+
3425,
|
| 445 |
+
2899
|
| 446 |
],
|
| 447 |
"step": 1806
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 15.0,
|
| 451 |
+
"eval_bp": 0.8700925578924447,
|
| 452 |
"eval_counts": [
|
| 453 |
+
4463,
|
| 454 |
+
3937,
|
| 455 |
+
3411,
|
| 456 |
+
2885
|
| 457 |
],
|
| 458 |
+
"eval_loss": 0.0008369011338800192,
|
| 459 |
"eval_precisions": [
|
| 460 |
+
99.6872905963815,
|
| 461 |
+
99.64565932675272,
|
| 462 |
+
99.5912408759124,
|
| 463 |
+
99.51707485339773
|
| 464 |
+
],
|
| 465 |
+
"eval_ref_len": 5100,
|
| 466 |
+
"eval_runtime": 13.8925,
|
| 467 |
+
"eval_samples_per_second": 37.862,
|
| 468 |
+
"eval_score": 86.6701772747815,
|
| 469 |
+
"eval_steps_per_second": 1.224,
|
| 470 |
+
"eval_sys_len": 4477,
|
| 471 |
"eval_totals": [
|
| 472 |
+
4477,
|
| 473 |
+
3951,
|
| 474 |
+
3425,
|
| 475 |
+
2899
|
| 476 |
],
|
| 477 |
"step": 1935
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 15.5,
|
| 481 |
"learning_rate": 1.3798449612403102e-05,
|
| 482 |
+
"loss": 0.0027,
|
| 483 |
"step": 2000
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 16.0,
|
| 487 |
+
"eval_bp": 0.8700925578924447,
|
| 488 |
"eval_counts": [
|
| 489 |
+
4463,
|
| 490 |
+
3937,
|
| 491 |
+
3411,
|
| 492 |
+
2885
|
| 493 |
],
|
| 494 |
+
"eval_loss": 0.00020534679060801864,
|
| 495 |
"eval_precisions": [
|
| 496 |
+
99.6872905963815,
|
| 497 |
+
99.64565932675272,
|
| 498 |
+
99.5912408759124,
|
| 499 |
+
99.51707485339773
|
| 500 |
+
],
|
| 501 |
+
"eval_ref_len": 5100,
|
| 502 |
+
"eval_runtime": 13.9128,
|
| 503 |
+
"eval_samples_per_second": 37.807,
|
| 504 |
+
"eval_score": 86.6701772747815,
|
| 505 |
+
"eval_steps_per_second": 1.222,
|
| 506 |
+
"eval_sys_len": 4477,
|
| 507 |
"eval_totals": [
|
| 508 |
+
4477,
|
| 509 |
+
3951,
|
| 510 |
+
3425,
|
| 511 |
+
2899
|
| 512 |
],
|
| 513 |
"step": 2064
|
| 514 |
},
|
| 515 |
{
|
| 516 |
"epoch": 17.0,
|
| 517 |
+
"eval_bp": 0.8700925578924447,
|
| 518 |
"eval_counts": [
|
| 519 |
+
4463,
|
| 520 |
+
3937,
|
| 521 |
+
3411,
|
| 522 |
+
2885
|
| 523 |
],
|
| 524 |
+
"eval_loss": 0.001328099868260324,
|
| 525 |
"eval_precisions": [
|
| 526 |
+
99.6872905963815,
|
| 527 |
+
99.64565932675272,
|
| 528 |
+
99.5912408759124,
|
| 529 |
+
99.51707485339773
|
| 530 |
+
],
|
| 531 |
+
"eval_ref_len": 5100,
|
| 532 |
+
"eval_runtime": 13.6909,
|
| 533 |
+
"eval_samples_per_second": 38.42,
|
| 534 |
+
"eval_score": 86.6701772747815,
|
| 535 |
+
"eval_steps_per_second": 1.242,
|
| 536 |
+
"eval_sys_len": 4477,
|
| 537 |
"eval_totals": [
|
| 538 |
+
4477,
|
| 539 |
+
3951,
|
| 540 |
+
3425,
|
| 541 |
+
2899
|
| 542 |
],
|
| 543 |
"step": 2193
|
| 544 |
},
|
| 545 |
{
|
| 546 |
"epoch": 18.0,
|
| 547 |
+
"eval_bp": 0.8700925578924447,
|
| 548 |
"eval_counts": [
|
| 549 |
+
4463,
|
| 550 |
+
3937,
|
| 551 |
+
3411,
|
| 552 |
+
2885
|
| 553 |
],
|
| 554 |
+
"eval_loss": 0.0003365726734045893,
|
| 555 |
"eval_precisions": [
|
| 556 |
+
99.6872905963815,
|
| 557 |
+
99.64565932675272,
|
| 558 |
+
99.5912408759124,
|
| 559 |
+
99.51707485339773
|
| 560 |
+
],
|
| 561 |
+
"eval_ref_len": 5100,
|
| 562 |
+
"eval_runtime": 13.7109,
|
| 563 |
+
"eval_samples_per_second": 38.364,
|
| 564 |
+
"eval_score": 86.6701772747815,
|
| 565 |
+
"eval_steps_per_second": 1.24,
|
| 566 |
+
"eval_sys_len": 4477,
|
| 567 |
"eval_totals": [
|
| 568 |
+
4477,
|
| 569 |
+
3951,
|
| 570 |
+
3425,
|
| 571 |
+
2899
|
| 572 |
],
|
| 573 |
"step": 2322
|
| 574 |
},
|
| 575 |
{
|
| 576 |
"epoch": 19.0,
|
| 577 |
+
"eval_bp": 0.8700925578924447,
|
| 578 |
"eval_counts": [
|
| 579 |
+
4463,
|
| 580 |
+
3937,
|
| 581 |
+
3411,
|
| 582 |
+
2885
|
| 583 |
],
|
| 584 |
+
"eval_loss": 8.775618334766477e-05,
|
| 585 |
"eval_precisions": [
|
| 586 |
+
99.6872905963815,
|
| 587 |
+
99.64565932675272,
|
| 588 |
+
99.5912408759124,
|
| 589 |
+
99.51707485339773
|
| 590 |
+
],
|
| 591 |
+
"eval_ref_len": 5100,
|
| 592 |
+
"eval_runtime": 14.0994,
|
| 593 |
+
"eval_samples_per_second": 37.307,
|
| 594 |
+
"eval_score": 86.6701772747815,
|
| 595 |
+
"eval_steps_per_second": 1.206,
|
| 596 |
+
"eval_sys_len": 4477,
|
| 597 |
"eval_totals": [
|
| 598 |
+
4477,
|
| 599 |
+
3951,
|
| 600 |
+
3425,
|
| 601 |
+
2899
|
| 602 |
],
|
| 603 |
"step": 2451
|
| 604 |
},
|
| 605 |
{
|
| 606 |
"epoch": 19.38,
|
| 607 |
"learning_rate": 1.2248062015503876e-05,
|
| 608 |
+
"loss": 0.002,
|
| 609 |
"step": 2500
|
| 610 |
},
|
| 611 |
{
|
| 612 |
"epoch": 20.0,
|
| 613 |
+
"eval_bp": 0.8700925578924447,
|
| 614 |
"eval_counts": [
|
| 615 |
+
4463,
|
| 616 |
+
3937,
|
| 617 |
+
3411,
|
| 618 |
+
2885
|
| 619 |
],
|
| 620 |
+
"eval_loss": 8.96168130566366e-05,
|
| 621 |
"eval_precisions": [
|
| 622 |
+
99.6872905963815,
|
| 623 |
+
99.64565932675272,
|
| 624 |
+
99.5912408759124,
|
| 625 |
+
99.51707485339773
|
| 626 |
+
],
|
| 627 |
+
"eval_ref_len": 5100,
|
| 628 |
+
"eval_runtime": 13.8102,
|
| 629 |
+
"eval_samples_per_second": 38.088,
|
| 630 |
+
"eval_score": 86.6701772747815,
|
| 631 |
+
"eval_steps_per_second": 1.231,
|
| 632 |
+
"eval_sys_len": 4477,
|
| 633 |
"eval_totals": [
|
| 634 |
+
4477,
|
| 635 |
+
3951,
|
| 636 |
+
3425,
|
| 637 |
+
2899
|
| 638 |
],
|
| 639 |
"step": 2580
|
| 640 |
},
|
| 641 |
{
|
| 642 |
"epoch": 21.0,
|
| 643 |
+
"eval_bp": 0.8700925578924447,
|
| 644 |
"eval_counts": [
|
| 645 |
+
4463,
|
| 646 |
+
3937,
|
| 647 |
+
3411,
|
| 648 |
+
2885
|
| 649 |
],
|
| 650 |
+
"eval_loss": 0.0007285438477993011,
|
| 651 |
"eval_precisions": [
|
| 652 |
+
99.6872905963815,
|
| 653 |
+
99.64565932675272,
|
| 654 |
+
99.5912408759124,
|
| 655 |
+
99.51707485339773
|
| 656 |
+
],
|
| 657 |
+
"eval_ref_len": 5100,
|
| 658 |
+
"eval_runtime": 13.7462,
|
| 659 |
+
"eval_samples_per_second": 38.265,
|
| 660 |
+
"eval_score": 86.6701772747815,
|
| 661 |
+
"eval_steps_per_second": 1.237,
|
| 662 |
+
"eval_sys_len": 4477,
|
| 663 |
"eval_totals": [
|
| 664 |
+
4477,
|
| 665 |
+
3951,
|
| 666 |
+
3425,
|
| 667 |
+
2899
|
| 668 |
],
|
| 669 |
"step": 2709
|
| 670 |
},
|
| 671 |
{
|
| 672 |
"epoch": 22.0,
|
| 673 |
+
"eval_bp": 0.8703139283627056,
|
| 674 |
"eval_counts": [
|
| 675 |
+
4464,
|
| 676 |
+
3938,
|
| 677 |
+
3412,
|
| 678 |
+
2886
|
| 679 |
],
|
| 680 |
+
"eval_loss": 0.0018083422910422087,
|
| 681 |
"eval_precisions": [
|
| 682 |
+
99.68736042876284,
|
| 683 |
+
99.64574898785425,
|
| 684 |
+
99.59136018680677,
|
| 685 |
+
99.51724137931035
|
| 686 |
+
],
|
| 687 |
+
"eval_ref_len": 5100,
|
| 688 |
+
"eval_runtime": 13.8084,
|
| 689 |
+
"eval_samples_per_second": 38.093,
|
| 690 |
+
"eval_score": 86.69232496739014,
|
| 691 |
+
"eval_steps_per_second": 1.231,
|
| 692 |
+
"eval_sys_len": 4478,
|
| 693 |
"eval_totals": [
|
| 694 |
+
4478,
|
| 695 |
+
3952,
|
| 696 |
+
3426,
|
| 697 |
+
2900
|
| 698 |
],
|
| 699 |
"step": 2838
|
| 700 |
},
|
| 701 |
{
|
| 702 |
"epoch": 23.0,
|
| 703 |
+
"eval_bp": 0.8700925578924447,
|
| 704 |
"eval_counts": [
|
| 705 |
+
4463,
|
| 706 |
+
3937,
|
| 707 |
+
3411,
|
| 708 |
+
2885
|
| 709 |
],
|
| 710 |
+
"eval_loss": 0.000638504687231034,
|
| 711 |
"eval_precisions": [
|
| 712 |
+
99.6872905963815,
|
| 713 |
+
99.64565932675272,
|
| 714 |
+
99.5912408759124,
|
| 715 |
+
99.51707485339773
|
| 716 |
+
],
|
| 717 |
+
"eval_ref_len": 5100,
|
| 718 |
+
"eval_runtime": 13.995,
|
| 719 |
+
"eval_samples_per_second": 37.585,
|
| 720 |
+
"eval_score": 86.6701772747815,
|
| 721 |
+
"eval_steps_per_second": 1.215,
|
| 722 |
+
"eval_sys_len": 4477,
|
| 723 |
"eval_totals": [
|
| 724 |
+
4477,
|
| 725 |
+
3951,
|
| 726 |
+
3425,
|
| 727 |
+
2899
|
| 728 |
],
|
| 729 |
"step": 2967
|
| 730 |
},
|
| 731 |
{
|
| 732 |
"epoch": 23.26,
|
| 733 |
"learning_rate": 1.0697674418604651e-05,
|
| 734 |
+
"loss": 0.0015,
|
| 735 |
"step": 3000
|
| 736 |
},
|
| 737 |
{
|
| 738 |
"epoch": 24.0,
|
| 739 |
+
"eval_bp": 0.8700925578924447,
|
| 740 |
"eval_counts": [
|
| 741 |
+
4463,
|
| 742 |
+
3937,
|
| 743 |
+
3411,
|
| 744 |
+
2885
|
| 745 |
],
|
| 746 |
+
"eval_loss": 0.00022906862432137132,
|
| 747 |
"eval_precisions": [
|
| 748 |
+
99.6872905963815,
|
| 749 |
+
99.64565932675272,
|
| 750 |
+
99.5912408759124,
|
| 751 |
+
99.51707485339773
|
| 752 |
+
],
|
| 753 |
+
"eval_ref_len": 5100,
|
| 754 |
+
"eval_runtime": 13.7342,
|
| 755 |
+
"eval_samples_per_second": 38.299,
|
| 756 |
+
"eval_score": 86.6701772747815,
|
| 757 |
+
"eval_steps_per_second": 1.238,
|
| 758 |
+
"eval_sys_len": 4477,
|
| 759 |
"eval_totals": [
|
| 760 |
+
4477,
|
| 761 |
+
3951,
|
| 762 |
+
3425,
|
| 763 |
+
2899
|
| 764 |
],
|
| 765 |
"step": 3096
|
| 766 |
},
|
| 767 |
{
|
| 768 |
"epoch": 25.0,
|
| 769 |
+
"eval_bp": 0.8700925578924447,
|
| 770 |
"eval_counts": [
|
| 771 |
+
4463,
|
| 772 |
+
3937,
|
| 773 |
+
3411,
|
| 774 |
+
2885
|
| 775 |
],
|
| 776 |
+
"eval_loss": 0.000275774480542168,
|
| 777 |
"eval_precisions": [
|
| 778 |
+
99.6872905963815,
|
| 779 |
+
99.64565932675272,
|
| 780 |
+
99.5912408759124,
|
| 781 |
+
99.51707485339773
|
| 782 |
+
],
|
| 783 |
+
"eval_ref_len": 5100,
|
| 784 |
+
"eval_runtime": 14.1769,
|
| 785 |
+
"eval_samples_per_second": 37.103,
|
| 786 |
+
"eval_score": 86.6701772747815,
|
| 787 |
+
"eval_steps_per_second": 1.199,
|
| 788 |
+
"eval_sys_len": 4477,
|
| 789 |
"eval_totals": [
|
| 790 |
+
4477,
|
| 791 |
+
3951,
|
| 792 |
+
3425,
|
| 793 |
+
2899
|
| 794 |
],
|
| 795 |
"step": 3225
|
| 796 |
},
|
| 797 |
{
|
| 798 |
"epoch": 26.0,
|
| 799 |
+
"eval_bp": 0.8700925578924447,
|
| 800 |
"eval_counts": [
|
| 801 |
+
4463,
|
| 802 |
+
3937,
|
| 803 |
+
3411,
|
| 804 |
+
2885
|
| 805 |
],
|
| 806 |
+
"eval_loss": 0.00025378959253430367,
|
| 807 |
"eval_precisions": [
|
| 808 |
+
99.6872905963815,
|
| 809 |
+
99.64565932675272,
|
| 810 |
+
99.5912408759124,
|
| 811 |
+
99.51707485339773
|
| 812 |
+
],
|
| 813 |
+
"eval_ref_len": 5100,
|
| 814 |
+
"eval_runtime": 13.944,
|
| 815 |
+
"eval_samples_per_second": 37.722,
|
| 816 |
+
"eval_score": 86.6701772747815,
|
| 817 |
+
"eval_steps_per_second": 1.219,
|
| 818 |
+
"eval_sys_len": 4477,
|
| 819 |
"eval_totals": [
|
| 820 |
+
4477,
|
| 821 |
+
3951,
|
| 822 |
+
3425,
|
| 823 |
+
2899
|
| 824 |
],
|
| 825 |
"step": 3354
|
| 826 |
},
|
| 827 |
{
|
| 828 |
"epoch": 27.0,
|
| 829 |
+
"eval_bp": 0.8700925578924447,
|
| 830 |
"eval_counts": [
|
| 831 |
+
4463,
|
| 832 |
+
3937,
|
| 833 |
+
3411,
|
| 834 |
+
2885
|
| 835 |
],
|
| 836 |
+
"eval_loss": 2.7398107704357244e-05,
|
| 837 |
"eval_precisions": [
|
| 838 |
+
99.6872905963815,
|
| 839 |
+
99.64565932675272,
|
| 840 |
+
99.5912408759124,
|
| 841 |
+
99.51707485339773
|
| 842 |
+
],
|
| 843 |
+
"eval_ref_len": 5100,
|
| 844 |
+
"eval_runtime": 13.9791,
|
| 845 |
+
"eval_samples_per_second": 37.628,
|
| 846 |
+
"eval_score": 86.6701772747815,
|
| 847 |
+
"eval_steps_per_second": 1.216,
|
| 848 |
+
"eval_sys_len": 4477,
|
| 849 |
"eval_totals": [
|
| 850 |
+
4477,
|
| 851 |
+
3951,
|
| 852 |
+
3425,
|
| 853 |
+
2899
|
| 854 |
],
|
| 855 |
"step": 3483
|
| 856 |
},
|
| 857 |
{
|
| 858 |
"epoch": 27.13,
|
| 859 |
"learning_rate": 9.147286821705427e-06,
|
| 860 |
+
"loss": 0.0014,
|
| 861 |
"step": 3500
|
| 862 |
},
|
| 863 |
{
|
| 864 |
"epoch": 28.0,
|
| 865 |
+
"eval_bp": 0.8700925578924447,
|
| 866 |
"eval_counts": [
|
| 867 |
+
4463,
|
| 868 |
+
3937,
|
| 869 |
+
3411,
|
| 870 |
+
2885
|
| 871 |
],
|
| 872 |
+
"eval_loss": 6.660177314188331e-05,
|
| 873 |
"eval_precisions": [
|
| 874 |
+
99.6872905963815,
|
| 875 |
+
99.64565932675272,
|
| 876 |
+
99.5912408759124,
|
| 877 |
+
99.51707485339773
|
| 878 |
+
],
|
| 879 |
+
"eval_ref_len": 5100,
|
| 880 |
+
"eval_runtime": 14.1404,
|
| 881 |
+
"eval_samples_per_second": 37.198,
|
| 882 |
+
"eval_score": 86.6701772747815,
|
| 883 |
+
"eval_steps_per_second": 1.202,
|
| 884 |
+
"eval_sys_len": 4477,
|
| 885 |
"eval_totals": [
|
| 886 |
+
4477,
|
| 887 |
+
3951,
|
| 888 |
+
3425,
|
| 889 |
+
2899
|
| 890 |
],
|
| 891 |
"step": 3612
|
| 892 |
},
|
| 893 |
{
|
| 894 |
"epoch": 29.0,
|
| 895 |
+
"eval_bp": 0.8700925578924447,
|
| 896 |
"eval_counts": [
|
| 897 |
+
4463,
|
| 898 |
+
3937,
|
| 899 |
+
3411,
|
| 900 |
+
2885
|
| 901 |
],
|
| 902 |
+
"eval_loss": 0.00022675798390991986,
|
| 903 |
"eval_precisions": [
|
| 904 |
+
99.6872905963815,
|
| 905 |
+
99.64565932675272,
|
| 906 |
+
99.5912408759124,
|
| 907 |
+
99.51707485339773
|
| 908 |
+
],
|
| 909 |
+
"eval_ref_len": 5100,
|
| 910 |
+
"eval_runtime": 13.9231,
|
| 911 |
+
"eval_samples_per_second": 37.779,
|
| 912 |
+
"eval_score": 86.6701772747815,
|
| 913 |
+
"eval_steps_per_second": 1.221,
|
| 914 |
+
"eval_sys_len": 4477,
|
| 915 |
"eval_totals": [
|
| 916 |
+
4477,
|
| 917 |
+
3951,
|
| 918 |
+
3425,
|
| 919 |
+
2899
|
| 920 |
],
|
| 921 |
"step": 3741
|
| 922 |
},
|
| 923 |
{
|
| 924 |
"epoch": 30.0,
|
| 925 |
+
"eval_bp": 0.8700925578924447,
|
| 926 |
"eval_counts": [
|
| 927 |
+
4463,
|
| 928 |
+
3937,
|
| 929 |
+
3411,
|
| 930 |
+
2885
|
| 931 |
],
|
| 932 |
+
"eval_loss": 5.096692984807305e-05,
|
| 933 |
"eval_precisions": [
|
| 934 |
+
99.6872905963815,
|
| 935 |
+
99.64565932675272,
|
| 936 |
+
99.5912408759124,
|
| 937 |
+
99.51707485339773
|
| 938 |
+
],
|
| 939 |
+
"eval_ref_len": 5100,
|
| 940 |
+
"eval_runtime": 14.3573,
|
| 941 |
+
"eval_samples_per_second": 36.636,
|
| 942 |
+
"eval_score": 86.6701772747815,
|
| 943 |
+
"eval_steps_per_second": 1.184,
|
| 944 |
+
"eval_sys_len": 4477,
|
| 945 |
"eval_totals": [
|
| 946 |
+
4477,
|
| 947 |
+
3951,
|
| 948 |
+
3425,
|
| 949 |
+
2899
|
| 950 |
],
|
| 951 |
"step": 3870
|
| 952 |
},
|
| 953 |
{
|
| 954 |
"epoch": 31.0,
|
| 955 |
+
"eval_bp": 0.8700925578924447,
|
| 956 |
"eval_counts": [
|
| 957 |
+
4463,
|
| 958 |
+
3937,
|
| 959 |
+
3411,
|
| 960 |
+
2885
|
| 961 |
],
|
| 962 |
+
"eval_loss": 9.942305041477084e-05,
|
| 963 |
"eval_precisions": [
|
| 964 |
+
99.6872905963815,
|
| 965 |
+
99.64565932675272,
|
| 966 |
+
99.5912408759124,
|
| 967 |
+
99.51707485339773
|
| 968 |
+
],
|
| 969 |
+
"eval_ref_len": 5100,
|
| 970 |
+
"eval_runtime": 13.7812,
|
| 971 |
+
"eval_samples_per_second": 38.168,
|
| 972 |
+
"eval_score": 86.6701772747815,
|
| 973 |
+
"eval_steps_per_second": 1.234,
|
| 974 |
+
"eval_sys_len": 4477,
|
| 975 |
"eval_totals": [
|
| 976 |
+
4477,
|
| 977 |
+
3951,
|
| 978 |
+
3425,
|
| 979 |
+
2899
|
| 980 |
],
|
| 981 |
"step": 3999
|
| 982 |
},
|
| 983 |
{
|
| 984 |
"epoch": 31.01,
|
| 985 |
"learning_rate": 7.596899224806202e-06,
|
| 986 |
+
"loss": 0.0009,
|
| 987 |
"step": 4000
|
| 988 |
},
|
| 989 |
{
|
| 990 |
"epoch": 32.0,
|
| 991 |
+
"eval_bp": 0.8700925578924447,
|
| 992 |
"eval_counts": [
|
| 993 |
+
4463,
|
| 994 |
+
3937,
|
| 995 |
+
3411,
|
| 996 |
+
2885
|
| 997 |
],
|
| 998 |
+
"eval_loss": 0.00020378571934998035,
|
| 999 |
"eval_precisions": [
|
| 1000 |
+
99.6872905963815,
|
| 1001 |
+
99.64565932675272,
|
| 1002 |
+
99.5912408759124,
|
| 1003 |
+
99.51707485339773
|
| 1004 |
+
],
|
| 1005 |
+
"eval_ref_len": 5100,
|
| 1006 |
+
"eval_runtime": 14.1117,
|
| 1007 |
+
"eval_samples_per_second": 37.274,
|
| 1008 |
+
"eval_score": 86.6701772747815,
|
| 1009 |
+
"eval_steps_per_second": 1.205,
|
| 1010 |
+
"eval_sys_len": 4477,
|
| 1011 |
"eval_totals": [
|
| 1012 |
+
4477,
|
| 1013 |
+
3951,
|
| 1014 |
+
3425,
|
| 1015 |
+
2899
|
| 1016 |
],
|
| 1017 |
"step": 4128
|
| 1018 |
},
|
| 1019 |
{
|
| 1020 |
"epoch": 33.0,
|
| 1021 |
+
"eval_bp": 0.8700925578924447,
|
| 1022 |
"eval_counts": [
|
| 1023 |
+
4463,
|
| 1024 |
+
3937,
|
| 1025 |
+
3411,
|
| 1026 |
+
2885
|
| 1027 |
],
|
| 1028 |
+
"eval_loss": 4.814989733858965e-05,
|
| 1029 |
"eval_precisions": [
|
| 1030 |
+
99.6872905963815,
|
| 1031 |
+
99.64565932675272,
|
| 1032 |
+
99.5912408759124,
|
| 1033 |
+
99.51707485339773
|
| 1034 |
+
],
|
| 1035 |
+
"eval_ref_len": 5100,
|
| 1036 |
+
"eval_runtime": 13.7623,
|
| 1037 |
+
"eval_samples_per_second": 38.22,
|
| 1038 |
+
"eval_score": 86.6701772747815,
|
| 1039 |
+
"eval_steps_per_second": 1.235,
|
| 1040 |
+
"eval_sys_len": 4477,
|
| 1041 |
"eval_totals": [
|
| 1042 |
+
4477,
|
| 1043 |
+
3951,
|
| 1044 |
+
3425,
|
| 1045 |
+
2899
|
| 1046 |
],
|
| 1047 |
"step": 4257
|
| 1048 |
},
|
| 1049 |
{
|
| 1050 |
"epoch": 34.0,
|
| 1051 |
+
"eval_bp": 0.8700925578924447,
|
| 1052 |
"eval_counts": [
|
| 1053 |
+
4463,
|
| 1054 |
+
3937,
|
| 1055 |
+
3411,
|
| 1056 |
+
2885
|
| 1057 |
],
|
| 1058 |
+
"eval_loss": 5.921188130741939e-05,
|
| 1059 |
"eval_precisions": [
|
| 1060 |
+
99.6872905963815,
|
| 1061 |
+
99.64565932675272,
|
| 1062 |
+
99.5912408759124,
|
| 1063 |
+
99.51707485339773
|
| 1064 |
+
],
|
| 1065 |
+
"eval_ref_len": 5100,
|
| 1066 |
+
"eval_runtime": 13.904,
|
| 1067 |
+
"eval_samples_per_second": 37.831,
|
| 1068 |
+
"eval_score": 86.6701772747815,
|
| 1069 |
+
"eval_steps_per_second": 1.223,
|
| 1070 |
+
"eval_sys_len": 4477,
|
| 1071 |
"eval_totals": [
|
| 1072 |
+
4477,
|
| 1073 |
+
3951,
|
| 1074 |
+
3425,
|
| 1075 |
+
2899
|
| 1076 |
],
|
| 1077 |
"step": 4386
|
| 1078 |
},
|
| 1079 |
{
|
| 1080 |
"epoch": 34.88,
|
| 1081 |
"learning_rate": 6.046511627906977e-06,
|
| 1082 |
+
"loss": 0.0008,
|
| 1083 |
"step": 4500
|
| 1084 |
},
|
| 1085 |
{
|
| 1086 |
"epoch": 35.0,
|
| 1087 |
+
"eval_bp": 0.8700925578924447,
|
| 1088 |
"eval_counts": [
|
| 1089 |
+
4463,
|
| 1090 |
+
3937,
|
| 1091 |
+
3411,
|
| 1092 |
+
2885
|
| 1093 |
],
|
| 1094 |
+
"eval_loss": 2.948127621493768e-05,
|
| 1095 |
"eval_precisions": [
|
| 1096 |
+
99.6872905963815,
|
| 1097 |
+
99.64565932675272,
|
| 1098 |
+
99.5912408759124,
|
| 1099 |
+
99.51707485339773
|
| 1100 |
+
],
|
| 1101 |
+
"eval_ref_len": 5100,
|
| 1102 |
+
"eval_runtime": 14.005,
|
| 1103 |
+
"eval_samples_per_second": 37.558,
|
| 1104 |
+
"eval_score": 86.6701772747815,
|
| 1105 |
+
"eval_steps_per_second": 1.214,
|
| 1106 |
+
"eval_sys_len": 4477,
|
| 1107 |
"eval_totals": [
|
| 1108 |
+
4477,
|
| 1109 |
+
3951,
|
| 1110 |
+
3425,
|
| 1111 |
+
2899
|
| 1112 |
],
|
| 1113 |
"step": 4515
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
"epoch": 36.0,
|
| 1117 |
+
"eval_bp": 0.8700925578924447,
|
| 1118 |
"eval_counts": [
|
| 1119 |
+
4463,
|
| 1120 |
+
3937,
|
| 1121 |
+
3411,
|
| 1122 |
+
2885
|
| 1123 |
],
|
| 1124 |
+
"eval_loss": 1.501874066889286e-05,
|
| 1125 |
"eval_precisions": [
|
| 1126 |
+
99.6872905963815,
|
| 1127 |
+
99.64565932675272,
|
| 1128 |
+
99.5912408759124,
|
| 1129 |
+
99.51707485339773
|
| 1130 |
+
],
|
| 1131 |
+
"eval_ref_len": 5100,
|
| 1132 |
+
"eval_runtime": 13.8563,
|
| 1133 |
+
"eval_samples_per_second": 37.961,
|
| 1134 |
+
"eval_score": 86.6701772747815,
|
| 1135 |
+
"eval_steps_per_second": 1.227,
|
| 1136 |
+
"eval_sys_len": 4477,
|
| 1137 |
"eval_totals": [
|
| 1138 |
+
4477,
|
| 1139 |
+
3951,
|
| 1140 |
+
3425,
|
| 1141 |
+
2899
|
| 1142 |
],
|
| 1143 |
"step": 4644
|
| 1144 |
},
|
| 1145 |
{
|
| 1146 |
"epoch": 37.0,
|
| 1147 |
+
"eval_bp": 0.8700925578924447,
|
| 1148 |
"eval_counts": [
|
| 1149 |
+
4463,
|
| 1150 |
+
3937,
|
| 1151 |
+
3411,
|
| 1152 |
+
2885
|
| 1153 |
],
|
| 1154 |
+
"eval_loss": 3.573419598978944e-05,
|
| 1155 |
"eval_precisions": [
|
| 1156 |
+
99.6872905963815,
|
| 1157 |
+
99.64565932675272,
|
| 1158 |
+
99.5912408759124,
|
| 1159 |
+
99.51707485339773
|
| 1160 |
+
],
|
| 1161 |
+
"eval_ref_len": 5100,
|
| 1162 |
+
"eval_runtime": 14.0819,
|
| 1163 |
+
"eval_samples_per_second": 37.353,
|
| 1164 |
+
"eval_score": 86.6701772747815,
|
| 1165 |
+
"eval_steps_per_second": 1.207,
|
| 1166 |
+
"eval_sys_len": 4477,
|
| 1167 |
"eval_totals": [
|
| 1168 |
+
4477,
|
| 1169 |
+
3951,
|
| 1170 |
+
3425,
|
| 1171 |
+
2899
|
| 1172 |
],
|
| 1173 |
"step": 4773
|
| 1174 |
},
|
| 1175 |
{
|
| 1176 |
"epoch": 38.0,
|
| 1177 |
+
"eval_bp": 0.8700925578924447,
|
| 1178 |
"eval_counts": [
|
| 1179 |
+
4463,
|
| 1180 |
+
3937,
|
| 1181 |
+
3411,
|
| 1182 |
+
2885
|
| 1183 |
],
|
| 1184 |
+
"eval_loss": 1.292789511353476e-05,
|
| 1185 |
"eval_precisions": [
|
| 1186 |
+
99.6872905963815,
|
| 1187 |
+
99.64565932675272,
|
| 1188 |
+
99.5912408759124,
|
| 1189 |
+
99.51707485339773
|
| 1190 |
+
],
|
| 1191 |
+
"eval_ref_len": 5100,
|
| 1192 |
+
"eval_runtime": 13.8393,
|
| 1193 |
+
"eval_samples_per_second": 38.008,
|
| 1194 |
+
"eval_score": 86.6701772747815,
|
| 1195 |
+
"eval_steps_per_second": 1.228,
|
| 1196 |
+
"eval_sys_len": 4477,
|
| 1197 |
"eval_totals": [
|
| 1198 |
+
4477,
|
| 1199 |
+
3951,
|
| 1200 |
+
3425,
|
| 1201 |
+
2899
|
| 1202 |
],
|
| 1203 |
"step": 4902
|
| 1204 |
},
|
| 1205 |
{
|
| 1206 |
"epoch": 38.76,
|
| 1207 |
"learning_rate": 4.4961240310077525e-06,
|
| 1208 |
+
"loss": 0.0006,
|
| 1209 |
"step": 5000
|
| 1210 |
},
|
| 1211 |
{
|
| 1212 |
"epoch": 39.0,
|
| 1213 |
+
"eval_bp": 0.8700925578924447,
|
| 1214 |
"eval_counts": [
|
| 1215 |
+
4463,
|
| 1216 |
+
3937,
|
| 1217 |
+
3411,
|
| 1218 |
+
2885
|
| 1219 |
],
|
| 1220 |
+
"eval_loss": 2.826396666932851e-05,
|
| 1221 |
"eval_precisions": [
|
| 1222 |
+
99.6872905963815,
|
| 1223 |
+
99.64565932675272,
|
| 1224 |
+
99.5912408759124,
|
| 1225 |
+
99.51707485339773
|
| 1226 |
+
],
|
| 1227 |
+
"eval_ref_len": 5100,
|
| 1228 |
+
"eval_runtime": 14.2505,
|
| 1229 |
+
"eval_samples_per_second": 36.911,
|
| 1230 |
+
"eval_score": 86.6701772747815,
|
| 1231 |
+
"eval_steps_per_second": 1.193,
|
| 1232 |
+
"eval_sys_len": 4477,
|
| 1233 |
"eval_totals": [
|
| 1234 |
+
4477,
|
| 1235 |
+
3951,
|
| 1236 |
+
3425,
|
| 1237 |
+
2899
|
| 1238 |
],
|
| 1239 |
"step": 5031
|
| 1240 |
},
|
| 1241 |
{
|
| 1242 |
"epoch": 40.0,
|
| 1243 |
+
"eval_bp": 0.8700925578924447,
|
| 1244 |
"eval_counts": [
|
| 1245 |
+
4463,
|
| 1246 |
+
3937,
|
| 1247 |
+
3411,
|
| 1248 |
+
2885
|
| 1249 |
],
|
| 1250 |
+
"eval_loss": 9.735503226693254e-06,
|
| 1251 |
"eval_precisions": [
|
| 1252 |
+
99.6872905963815,
|
| 1253 |
+
99.64565932675272,
|
| 1254 |
+
99.5912408759124,
|
| 1255 |
+
99.51707485339773
|
| 1256 |
+
],
|
| 1257 |
+
"eval_ref_len": 5100,
|
| 1258 |
+
"eval_runtime": 13.8339,
|
| 1259 |
+
"eval_samples_per_second": 38.023,
|
| 1260 |
+
"eval_score": 86.6701772747815,
|
| 1261 |
+
"eval_steps_per_second": 1.229,
|
| 1262 |
+
"eval_sys_len": 4477,
|
| 1263 |
"eval_totals": [
|
| 1264 |
+
4477,
|
| 1265 |
+
3951,
|
| 1266 |
+
3425,
|
| 1267 |
+
2899
|
| 1268 |
],
|
| 1269 |
"step": 5160
|
| 1270 |
},
|
| 1271 |
{
|
| 1272 |
"epoch": 41.0,
|
| 1273 |
+
"eval_bp": 0.8700925578924447,
|
| 1274 |
"eval_counts": [
|
| 1275 |
+
4463,
|
| 1276 |
+
3937,
|
| 1277 |
+
3411,
|
| 1278 |
+
2885
|
| 1279 |
],
|
| 1280 |
+
"eval_loss": 5.421350579126738e-06,
|
| 1281 |
"eval_precisions": [
|
| 1282 |
+
99.6872905963815,
|
| 1283 |
+
99.64565932675272,
|
| 1284 |
+
99.5912408759124,
|
| 1285 |
+
99.51707485339773
|
| 1286 |
+
],
|
| 1287 |
+
"eval_ref_len": 5100,
|
| 1288 |
+
"eval_runtime": 13.9445,
|
| 1289 |
+
"eval_samples_per_second": 37.721,
|
| 1290 |
+
"eval_score": 86.6701772747815,
|
| 1291 |
+
"eval_steps_per_second": 1.219,
|
| 1292 |
+
"eval_sys_len": 4477,
|
| 1293 |
"eval_totals": [
|
| 1294 |
+
4477,
|
| 1295 |
+
3951,
|
| 1296 |
+
3425,
|
| 1297 |
+
2899
|
| 1298 |
],
|
| 1299 |
"step": 5289
|
| 1300 |
},
|
| 1301 |
{
|
| 1302 |
"epoch": 42.0,
|
| 1303 |
+
"eval_bp": 0.8700925578924447,
|
| 1304 |
"eval_counts": [
|
| 1305 |
+
4463,
|
| 1306 |
+
3937,
|
| 1307 |
+
3411,
|
| 1308 |
+
2885
|
| 1309 |
],
|
| 1310 |
+
"eval_loss": 1.1437254215707071e-05,
|
| 1311 |
"eval_precisions": [
|
| 1312 |
+
99.6872905963815,
|
| 1313 |
+
99.64565932675272,
|
| 1314 |
+
99.5912408759124,
|
| 1315 |
+
99.51707485339773
|
| 1316 |
+
],
|
| 1317 |
+
"eval_ref_len": 5100,
|
| 1318 |
+
"eval_runtime": 13.8327,
|
| 1319 |
+
"eval_samples_per_second": 38.026,
|
| 1320 |
+
"eval_score": 86.6701772747815,
|
| 1321 |
+
"eval_steps_per_second": 1.229,
|
| 1322 |
+
"eval_sys_len": 4477,
|
| 1323 |
"eval_totals": [
|
| 1324 |
+
4477,
|
| 1325 |
+
3951,
|
| 1326 |
+
3425,
|
| 1327 |
+
2899
|
| 1328 |
],
|
| 1329 |
"step": 5418
|
| 1330 |
},
|
| 1331 |
{
|
| 1332 |
"epoch": 42.64,
|
| 1333 |
"learning_rate": 2.9457364341085276e-06,
|
| 1334 |
+
"loss": 0.0004,
|
| 1335 |
"step": 5500
|
| 1336 |
},
|
| 1337 |
{
|
| 1338 |
"epoch": 43.0,
|
| 1339 |
+
"eval_bp": 0.8700925578924447,
|
| 1340 |
"eval_counts": [
|
| 1341 |
+
4463,
|
| 1342 |
+
3937,
|
| 1343 |
+
3411,
|
| 1344 |
+
2885
|
| 1345 |
],
|
| 1346 |
+
"eval_loss": 1.4262999684433453e-05,
|
| 1347 |
"eval_precisions": [
|
| 1348 |
+
99.6872905963815,
|
| 1349 |
+
99.64565932675272,
|
| 1350 |
+
99.5912408759124,
|
| 1351 |
+
99.51707485339773
|
| 1352 |
+
],
|
| 1353 |
+
"eval_ref_len": 5100,
|
| 1354 |
+
"eval_runtime": 13.8768,
|
| 1355 |
+
"eval_samples_per_second": 37.905,
|
| 1356 |
+
"eval_score": 86.6701772747815,
|
| 1357 |
+
"eval_steps_per_second": 1.225,
|
| 1358 |
+
"eval_sys_len": 4477,
|
| 1359 |
"eval_totals": [
|
| 1360 |
+
4477,
|
| 1361 |
+
3951,
|
| 1362 |
+
3425,
|
| 1363 |
+
2899
|
| 1364 |
],
|
| 1365 |
"step": 5547
|
| 1366 |
},
|
| 1367 |
{
|
| 1368 |
"epoch": 44.0,
|
| 1369 |
+
"eval_bp": 0.8700925578924447,
|
| 1370 |
"eval_counts": [
|
| 1371 |
+
4463,
|
| 1372 |
+
3937,
|
| 1373 |
+
3411,
|
| 1374 |
+
2885
|
| 1375 |
],
|
| 1376 |
+
"eval_loss": 3.849239874398336e-06,
|
| 1377 |
"eval_precisions": [
|
| 1378 |
+
99.6872905963815,
|
| 1379 |
+
99.64565932675272,
|
| 1380 |
+
99.5912408759124,
|
| 1381 |
+
99.51707485339773
|
| 1382 |
+
],
|
| 1383 |
+
"eval_ref_len": 5100,
|
| 1384 |
+
"eval_runtime": 13.9608,
|
| 1385 |
+
"eval_samples_per_second": 37.677,
|
| 1386 |
+
"eval_score": 86.6701772747815,
|
| 1387 |
+
"eval_steps_per_second": 1.218,
|
| 1388 |
+
"eval_sys_len": 4477,
|
| 1389 |
"eval_totals": [
|
| 1390 |
+
4477,
|
| 1391 |
+
3951,
|
| 1392 |
+
3425,
|
| 1393 |
+
2899
|
| 1394 |
],
|
| 1395 |
"step": 5676
|
| 1396 |
},
|
| 1397 |
{
|
| 1398 |
"epoch": 45.0,
|
| 1399 |
+
"eval_bp": 0.8700925578924447,
|
| 1400 |
"eval_counts": [
|
| 1401 |
+
4463,
|
| 1402 |
+
3937,
|
| 1403 |
+
3411,
|
| 1404 |
+
2885
|
| 1405 |
],
|
| 1406 |
+
"eval_loss": 1.1063038982683793e-05,
|
| 1407 |
"eval_precisions": [
|
| 1408 |
+
99.6872905963815,
|
| 1409 |
+
99.64565932675272,
|
| 1410 |
+
99.5912408759124,
|
| 1411 |
+
99.51707485339773
|
| 1412 |
+
],
|
| 1413 |
+
"eval_ref_len": 5100,
|
| 1414 |
+
"eval_runtime": 13.8436,
|
| 1415 |
+
"eval_samples_per_second": 37.996,
|
| 1416 |
+
"eval_score": 86.6701772747815,
|
| 1417 |
+
"eval_steps_per_second": 1.228,
|
| 1418 |
+
"eval_sys_len": 4477,
|
| 1419 |
"eval_totals": [
|
| 1420 |
+
4477,
|
| 1421 |
+
3951,
|
| 1422 |
+
3425,
|
| 1423 |
+
2899
|
| 1424 |
],
|
| 1425 |
"step": 5805
|
| 1426 |
},
|
| 1427 |
{
|
| 1428 |
"epoch": 46.0,
|
| 1429 |
+
"eval_bp": 0.8700925578924447,
|
| 1430 |
"eval_counts": [
|
| 1431 |
+
4463,
|
| 1432 |
+
3937,
|
| 1433 |
+
3411,
|
| 1434 |
+
2885
|
| 1435 |
],
|
| 1436 |
+
"eval_loss": 7.035921953502111e-06,
|
| 1437 |
"eval_precisions": [
|
| 1438 |
+
99.6872905963815,
|
| 1439 |
+
99.64565932675272,
|
| 1440 |
+
99.5912408759124,
|
| 1441 |
+
99.51707485339773
|
| 1442 |
+
],
|
| 1443 |
+
"eval_ref_len": 5100,
|
| 1444 |
+
"eval_runtime": 14.1871,
|
| 1445 |
+
"eval_samples_per_second": 37.076,
|
| 1446 |
+
"eval_score": 86.6701772747815,
|
| 1447 |
+
"eval_steps_per_second": 1.198,
|
| 1448 |
+
"eval_sys_len": 4477,
|
| 1449 |
"eval_totals": [
|
| 1450 |
+
4477,
|
| 1451 |
+
3951,
|
| 1452 |
+
3425,
|
| 1453 |
+
2899
|
| 1454 |
],
|
| 1455 |
"step": 5934
|
| 1456 |
},
|
| 1457 |
{
|
| 1458 |
"epoch": 46.51,
|
| 1459 |
"learning_rate": 1.3953488372093025e-06,
|
| 1460 |
+
"loss": 0.0002,
|
| 1461 |
"step": 6000
|
| 1462 |
}
|
| 1463 |
],
|
|
|
|
| 1466 |
"num_input_tokens_seen": 0,
|
| 1467 |
"num_train_epochs": 50,
|
| 1468 |
"save_steps": 500,
|
| 1469 |
+
"total_flos": 2.06928054010368e+16,
|
| 1470 |
"train_batch_size": 32,
|
| 1471 |
"trial_name": null,
|
| 1472 |
"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:cabe380e4e6dc1d9abdb4a06b79362daebcc59f39eeff81c6e1fbf03582c7bc2
|
| 3 |
size 4856
|