Training in progress, epoch 2
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +288 -3
- pytorch_model.bin +1 -1
- runs/Feb20_18-29-06_ubuntu-2004/events.out.tfevents.1676885357.ubuntu-2004.887393.0 +2 -2
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 236491077
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fe7b93abf02af995010aa8e52e985082cb35427475535754ba46e0f79bfe6b7
|
| 3 |
size 236491077
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 118253458
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc972ecc1329e0803175ccbf8d455608f73797136d228b25b2d6c64e55403179
|
| 3 |
size 118253458
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15597
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9fa70ecb25666f6769a2077ed150c9e52861a4143626716aebc146c3d3d8cd65
|
| 3 |
size 15597
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 557
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27f16da81f42c208591e42d4a624accc6adcfabf4b156667c067c8a5a08012ca
|
| 3 |
size 557
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4e814a01103e7d042492e6a27b7700dc34e66d68095fbabd7c929b5bd6b2625
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -285,11 +285,296 @@
|
|
| 285 |
"eval_samples_per_second": 603.699,
|
| 286 |
"eval_steps_per_second": 37.731,
|
| 287 |
"step": 22940
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 288 |
}
|
| 289 |
],
|
| 290 |
"max_steps": 321160,
|
| 291 |
"num_train_epochs": 14,
|
| 292 |
-
"total_flos":
|
| 293 |
"trial_name": null,
|
| 294 |
"trial_params": null
|
| 295 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 45880,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 285 |
"eval_samples_per_second": 603.699,
|
| 286 |
"eval_steps_per_second": 37.731,
|
| 287 |
"step": 22940
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 1.0,
|
| 291 |
+
"learning_rate": 9.377822788632103e-05,
|
| 292 |
+
"loss": 2.1305,
|
| 293 |
+
"step": 23000
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.02,
|
| 297 |
+
"learning_rate": 9.362096946670525e-05,
|
| 298 |
+
"loss": 2.1245,
|
| 299 |
+
"step": 23500
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.05,
|
| 303 |
+
"learning_rate": 9.346371104708946e-05,
|
| 304 |
+
"loss": 2.1178,
|
| 305 |
+
"step": 24000
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.07,
|
| 309 |
+
"learning_rate": 9.330676714431291e-05,
|
| 310 |
+
"loss": 2.1102,
|
| 311 |
+
"step": 24500
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.09,
|
| 315 |
+
"learning_rate": 9.314950872469712e-05,
|
| 316 |
+
"loss": 2.1007,
|
| 317 |
+
"step": 25000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.11,
|
| 321 |
+
"learning_rate": 9.299225030508134e-05,
|
| 322 |
+
"loss": 2.0966,
|
| 323 |
+
"step": 25500
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 1.13,
|
| 327 |
+
"learning_rate": 9.283499188546555e-05,
|
| 328 |
+
"loss": 2.0878,
|
| 329 |
+
"step": 26000
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.16,
|
| 333 |
+
"learning_rate": 9.2678047982689e-05,
|
| 334 |
+
"loss": 2.0814,
|
| 335 |
+
"step": 26500
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 1.18,
|
| 339 |
+
"learning_rate": 9.252078956307321e-05,
|
| 340 |
+
"loss": 2.0756,
|
| 341 |
+
"step": 27000
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 1.2,
|
| 345 |
+
"learning_rate": 9.236353114345743e-05,
|
| 346 |
+
"loss": 2.0685,
|
| 347 |
+
"step": 27500
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 1.22,
|
| 351 |
+
"learning_rate": 9.220627272384163e-05,
|
| 352 |
+
"loss": 2.065,
|
| 353 |
+
"step": 28000
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.24,
|
| 357 |
+
"learning_rate": 9.204932882106509e-05,
|
| 358 |
+
"loss": 2.0592,
|
| 359 |
+
"step": 28500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.26,
|
| 363 |
+
"learning_rate": 9.18920704014493e-05,
|
| 364 |
+
"loss": 2.0527,
|
| 365 |
+
"step": 29000
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 1.29,
|
| 369 |
+
"learning_rate": 9.173481198183351e-05,
|
| 370 |
+
"loss": 2.0459,
|
| 371 |
+
"step": 29500
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 1.31,
|
| 375 |
+
"learning_rate": 9.157755356221772e-05,
|
| 376 |
+
"loss": 2.0443,
|
| 377 |
+
"step": 30000
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.33,
|
| 381 |
+
"learning_rate": 9.142060965944116e-05,
|
| 382 |
+
"loss": 2.0367,
|
| 383 |
+
"step": 30500
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.35,
|
| 387 |
+
"learning_rate": 9.126366575666462e-05,
|
| 388 |
+
"loss": 2.0322,
|
| 389 |
+
"step": 31000
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.37,
|
| 393 |
+
"learning_rate": 9.110640733704882e-05,
|
| 394 |
+
"loss": 2.0228,
|
| 395 |
+
"step": 31500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.39,
|
| 399 |
+
"learning_rate": 9.094914891743304e-05,
|
| 400 |
+
"loss": 2.0209,
|
| 401 |
+
"step": 32000
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.42,
|
| 405 |
+
"learning_rate": 9.079189049781725e-05,
|
| 406 |
+
"loss": 2.0156,
|
| 407 |
+
"step": 32500
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 1.44,
|
| 411 |
+
"learning_rate": 9.063463207820148e-05,
|
| 412 |
+
"loss": 2.0141,
|
| 413 |
+
"step": 33000
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 1.46,
|
| 417 |
+
"learning_rate": 9.047737365858569e-05,
|
| 418 |
+
"loss": 2.0093,
|
| 419 |
+
"step": 33500
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 1.48,
|
| 423 |
+
"learning_rate": 9.032042975580913e-05,
|
| 424 |
+
"loss": 2.0052,
|
| 425 |
+
"step": 34000
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 1.5,
|
| 429 |
+
"learning_rate": 9.016317133619334e-05,
|
| 430 |
+
"loss": 1.9973,
|
| 431 |
+
"step": 34500
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 1.53,
|
| 435 |
+
"learning_rate": 9.000591291657756e-05,
|
| 436 |
+
"loss": 1.995,
|
| 437 |
+
"step": 35000
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.55,
|
| 441 |
+
"learning_rate": 8.984865449696177e-05,
|
| 442 |
+
"loss": 1.9908,
|
| 443 |
+
"step": 35500
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.57,
|
| 447 |
+
"learning_rate": 8.969139607734599e-05,
|
| 448 |
+
"loss": 1.986,
|
| 449 |
+
"step": 36000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.59,
|
| 453 |
+
"learning_rate": 8.95341376577302e-05,
|
| 454 |
+
"loss": 1.9825,
|
| 455 |
+
"step": 36500
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 1.61,
|
| 459 |
+
"learning_rate": 8.937687923811441e-05,
|
| 460 |
+
"loss": 1.9754,
|
| 461 |
+
"step": 37000
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 1.63,
|
| 465 |
+
"learning_rate": 8.921993533533786e-05,
|
| 466 |
+
"loss": 1.9733,
|
| 467 |
+
"step": 37500
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 1.66,
|
| 471 |
+
"learning_rate": 8.906267691572208e-05,
|
| 472 |
+
"loss": 1.9679,
|
| 473 |
+
"step": 38000
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 1.68,
|
| 477 |
+
"learning_rate": 8.890541849610629e-05,
|
| 478 |
+
"loss": 1.9611,
|
| 479 |
+
"step": 38500
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.7,
|
| 483 |
+
"learning_rate": 8.87481600764905e-05,
|
| 484 |
+
"loss": 1.961,
|
| 485 |
+
"step": 39000
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.72,
|
| 489 |
+
"learning_rate": 8.859121617371395e-05,
|
| 490 |
+
"loss": 1.9588,
|
| 491 |
+
"step": 39500
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 1.74,
|
| 495 |
+
"learning_rate": 8.843395775409816e-05,
|
| 496 |
+
"loss": 1.9578,
|
| 497 |
+
"step": 40000
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 1.77,
|
| 501 |
+
"learning_rate": 8.827669933448237e-05,
|
| 502 |
+
"loss": 1.9528,
|
| 503 |
+
"step": 40500
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 1.79,
|
| 507 |
+
"learning_rate": 8.811944091486659e-05,
|
| 508 |
+
"loss": 1.9486,
|
| 509 |
+
"step": 41000
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.81,
|
| 513 |
+
"learning_rate": 8.796249701209002e-05,
|
| 514 |
+
"loss": 1.9443,
|
| 515 |
+
"step": 41500
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.83,
|
| 519 |
+
"learning_rate": 8.780523859247425e-05,
|
| 520 |
+
"loss": 1.9406,
|
| 521 |
+
"step": 42000
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.85,
|
| 525 |
+
"learning_rate": 8.764798017285846e-05,
|
| 526 |
+
"loss": 1.9372,
|
| 527 |
+
"step": 42500
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.87,
|
| 531 |
+
"learning_rate": 8.749072175324268e-05,
|
| 532 |
+
"loss": 1.9351,
|
| 533 |
+
"step": 43000
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 1.9,
|
| 537 |
+
"learning_rate": 8.733346333362689e-05,
|
| 538 |
+
"loss": 1.9265,
|
| 539 |
+
"step": 43500
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 1.92,
|
| 543 |
+
"learning_rate": 8.717651943085034e-05,
|
| 544 |
+
"loss": 1.9272,
|
| 545 |
+
"step": 44000
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 1.94,
|
| 549 |
+
"learning_rate": 8.701926101123455e-05,
|
| 550 |
+
"loss": 1.9268,
|
| 551 |
+
"step": 44500
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 1.96,
|
| 555 |
+
"learning_rate": 8.686200259161877e-05,
|
| 556 |
+
"loss": 1.9242,
|
| 557 |
+
"step": 45000
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 1.98,
|
| 561 |
+
"learning_rate": 8.670474417200297e-05,
|
| 562 |
+
"loss": 1.9234,
|
| 563 |
+
"step": 45500
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 2.0,
|
| 567 |
+
"eval_accuracy": 0.6411638490813204,
|
| 568 |
+
"eval_loss": 1.785447597503662,
|
| 569 |
+
"eval_runtime": 294.391,
|
| 570 |
+
"eval_samples_per_second": 604.475,
|
| 571 |
+
"eval_steps_per_second": 37.78,
|
| 572 |
+
"step": 45880
|
| 573 |
}
|
| 574 |
],
|
| 575 |
"max_steps": 321160,
|
| 576 |
"num_train_epochs": 14,
|
| 577 |
+
"total_flos": 3.488545026395035e+17,
|
| 578 |
"trial_name": null,
|
| 579 |
"trial_params": null
|
| 580 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 118253458
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc972ecc1329e0803175ccbf8d455608f73797136d228b25b2d6c64e55403179
|
| 3 |
size 118253458
|
runs/Feb20_18-29-06_ubuntu-2004/events.out.tfevents.1676885357.ubuntu-2004.887393.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:666ec60d0078a18e9ab7268ca3acc069e6bcfd168d1a61b253913169617035c1
|
| 3 |
+
size 18890
|