Training in progress, step 20000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +303 -3
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 100170757
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:efef12e6736ac05b05123978b5a7ba02086375a879e1e08c05db35ff70c647a0
|
| 3 |
size 100170757
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 146774203
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:669ff7fd28968817843d8d3e735a9f1604e6f86bd0620d14ba500c796ee6cb84
|
| 3 |
size 146774203
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14439
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17ed50c4af1d37fb0d41b85169a6f1f89705f404faa32f3817c74e84cd5180c1
|
| 3 |
size 14439
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 246897640
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60920ec13686e98f9f0d129e472adaac1417d4bc756e4485725a87068a11e2f1
|
| 3 |
size 246897640
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -306,11 +306,311 @@
|
|
| 306 |
"learning_rate": 0.0005048929099291249,
|
| 307 |
"loss": 5.0106,
|
| 308 |
"step": 10000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 309 |
}
|
| 310 |
],
|
| 311 |
"max_steps": 500000,
|
| 312 |
"num_train_epochs": 3,
|
| 313 |
-
"total_flos":
|
| 314 |
"trial_name": null,
|
| 315 |
"trial_params": null
|
| 316 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.08594757198109153,
|
| 5 |
+
"global_step": 20000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 306 |
"learning_rate": 0.0005048929099291249,
|
| 307 |
"loss": 5.0106,
|
| 308 |
"step": 10000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.04,
|
| 312 |
+
"learning_rate": 0.0005091144561900837,
|
| 313 |
+
"loss": 5.0155,
|
| 314 |
+
"step": 10200
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.04,
|
| 318 |
+
"learning_rate": 0.0005134183095340927,
|
| 319 |
+
"loss": 4.9817,
|
| 320 |
+
"step": 10400
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.05,
|
| 324 |
+
"learning_rate": 0.0005178043944449977,
|
| 325 |
+
"loss": 4.9742,
|
| 326 |
+
"step": 10600
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.05,
|
| 330 |
+
"learning_rate": 0.0005222726339638023,
|
| 331 |
+
"loss": 4.9299,
|
| 332 |
+
"step": 10800
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.05,
|
| 336 |
+
"learning_rate": 0.0005268229496900086,
|
| 337 |
+
"loss": 4.9208,
|
| 338 |
+
"step": 11000
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.05,
|
| 342 |
+
"learning_rate": 0.0005314552617829947,
|
| 343 |
+
"loss": 4.8617,
|
| 344 |
+
"step": 11200
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.05,
|
| 348 |
+
"learning_rate": 0.0005361694889634196,
|
| 349 |
+
"loss": 4.7952,
|
| 350 |
+
"step": 11400
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.05,
|
| 354 |
+
"learning_rate": 0.0005409655485146408,
|
| 355 |
+
"loss": 4.7641,
|
| 356 |
+
"step": 11600
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.05,
|
| 360 |
+
"learning_rate": 0.0005458433562841782,
|
| 361 |
+
"loss": 4.7361,
|
| 362 |
+
"step": 11800
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.05,
|
| 366 |
+
"learning_rate": 0.0005508028266851747,
|
| 367 |
+
"loss": 4.7023,
|
| 368 |
+
"step": 12000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.05,
|
| 372 |
+
"learning_rate": 0.000555843872697916,
|
| 373 |
+
"loss": 4.6561,
|
| 374 |
+
"step": 12200
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.05,
|
| 378 |
+
"learning_rate": 0.0005609664058713396,
|
| 379 |
+
"loss": 4.63,
|
| 380 |
+
"step": 12400
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.05,
|
| 384 |
+
"learning_rate": 0.0005661703363245996,
|
| 385 |
+
"loss": 4.6307,
|
| 386 |
+
"step": 12600
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.06,
|
| 390 |
+
"learning_rate": 0.0005714555727486404,
|
| 391 |
+
"loss": 4.5881,
|
| 392 |
+
"step": 12800
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.06,
|
| 396 |
+
"learning_rate": 0.0005768220224077955,
|
| 397 |
+
"loss": 4.5489,
|
| 398 |
+
"step": 13000
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.06,
|
| 402 |
+
"learning_rate": 0.0005822695911414169,
|
| 403 |
+
"loss": 4.5521,
|
| 404 |
+
"step": 13200
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.06,
|
| 408 |
+
"learning_rate": 0.0005877981833655298,
|
| 409 |
+
"loss": 4.5165,
|
| 410 |
+
"step": 13400
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.06,
|
| 414 |
+
"learning_rate": 0.0005934077020745051,
|
| 415 |
+
"loss": 4.505,
|
| 416 |
+
"step": 13600
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.06,
|
| 420 |
+
"learning_rate": 0.0005990980488427659,
|
| 421 |
+
"loss": 4.4863,
|
| 422 |
+
"step": 13800
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.06,
|
| 426 |
+
"learning_rate": 0.000604869123826509,
|
| 427 |
+
"loss": 4.5071,
|
| 428 |
+
"step": 14000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.06,
|
| 432 |
+
"learning_rate": 0.0006107208257654633,
|
| 433 |
+
"loss": 4.4501,
|
| 434 |
+
"step": 14200
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.06,
|
| 438 |
+
"learning_rate": 0.0006166530519846631,
|
| 439 |
+
"loss": 4.4623,
|
| 440 |
+
"step": 14400
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 0.06,
|
| 444 |
+
"learning_rate": 0.0006226656983962468,
|
| 445 |
+
"loss": 4.4336,
|
| 446 |
+
"step": 14600
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.06,
|
| 450 |
+
"learning_rate": 0.0006287586595012887,
|
| 451 |
+
"loss": 4.4335,
|
| 452 |
+
"step": 14800
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.06,
|
| 456 |
+
"learning_rate": 0.000634931828391647,
|
| 457 |
+
"loss": 4.4142,
|
| 458 |
+
"step": 15000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.07,
|
| 462 |
+
"learning_rate": 0.0006411850967518416,
|
| 463 |
+
"loss": 4.4145,
|
| 464 |
+
"step": 15200
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.07,
|
| 468 |
+
"learning_rate": 0.0006475183548609511,
|
| 469 |
+
"loss": 4.3842,
|
| 470 |
+
"step": 15400
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.07,
|
| 474 |
+
"learning_rate": 0.0006539314915945428,
|
| 475 |
+
"loss": 4.3748,
|
| 476 |
+
"step": 15600
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 0.07,
|
| 480 |
+
"learning_rate": 0.0006604243944266178,
|
| 481 |
+
"loss": 4.3815,
|
| 482 |
+
"step": 15800
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.07,
|
| 486 |
+
"learning_rate": 0.0006669969494315867,
|
| 487 |
+
"loss": 4.352,
|
| 488 |
+
"step": 16000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.07,
|
| 492 |
+
"learning_rate": 0.0006736490412862749,
|
| 493 |
+
"loss": 4.3575,
|
| 494 |
+
"step": 16200
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.07,
|
| 498 |
+
"learning_rate": 0.000680380553271933,
|
| 499 |
+
"loss": 4.3416,
|
| 500 |
+
"step": 16400
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.07,
|
| 504 |
+
"learning_rate": 0.0006871913672762998,
|
| 505 |
+
"loss": 4.341,
|
| 506 |
+
"step": 16600
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.07,
|
| 510 |
+
"learning_rate": 0.0006940813637956594,
|
| 511 |
+
"loss": 4.3183,
|
| 512 |
+
"step": 16800
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 0.07,
|
| 516 |
+
"learning_rate": 0.0007010504219369541,
|
| 517 |
+
"loss": 4.3145,
|
| 518 |
+
"step": 17000
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.07,
|
| 522 |
+
"learning_rate": 0.0007080984194198885,
|
| 523 |
+
"loss": 4.3065,
|
| 524 |
+
"step": 17200
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 0.07,
|
| 528 |
+
"learning_rate": 0.0007152252325790948,
|
| 529 |
+
"loss": 4.2805,
|
| 530 |
+
"step": 17400
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.08,
|
| 534 |
+
"learning_rate": 0.0007224307363662818,
|
| 535 |
+
"loss": 4.2804,
|
| 536 |
+
"step": 17600
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.08,
|
| 540 |
+
"learning_rate": 0.0007297148043524434,
|
| 541 |
+
"loss": 4.2996,
|
| 542 |
+
"step": 17800
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.08,
|
| 546 |
+
"learning_rate": 0.0007370773087300737,
|
| 547 |
+
"loss": 4.2743,
|
| 548 |
+
"step": 18000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.08,
|
| 552 |
+
"learning_rate": 0.0007445181203154048,
|
| 553 |
+
"loss": 4.2621,
|
| 554 |
+
"step": 18200
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.08,
|
| 558 |
+
"learning_rate": 0.0007520371085506811,
|
| 559 |
+
"loss": 4.2548,
|
| 560 |
+
"step": 18400
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.08,
|
| 564 |
+
"learning_rate": 0.0007596341415064441,
|
| 565 |
+
"loss": 4.2643,
|
| 566 |
+
"step": 18600
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.08,
|
| 570 |
+
"learning_rate": 0.0007673090858838494,
|
| 571 |
+
"loss": 4.266,
|
| 572 |
+
"step": 18800
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.08,
|
| 576 |
+
"learning_rate": 0.0007750618070170041,
|
| 577 |
+
"loss": 4.2503,
|
| 578 |
+
"step": 19000
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.08,
|
| 582 |
+
"learning_rate": 0.0007828921688753324,
|
| 583 |
+
"loss": 4.2093,
|
| 584 |
+
"step": 19200
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.08,
|
| 588 |
+
"learning_rate": 0.0007908000340659631,
|
| 589 |
+
"loss": 4.2449,
|
| 590 |
+
"step": 19400
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.08,
|
| 594 |
+
"learning_rate": 0.0007987852638361333,
|
| 595 |
+
"loss": 4.2158,
|
| 596 |
+
"step": 19600
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.09,
|
| 600 |
+
"learning_rate": 0.0008068477180756314,
|
| 601 |
+
"loss": 4.202,
|
| 602 |
+
"step": 19800
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.09,
|
| 606 |
+
"learning_rate": 0.0008149872553192515,
|
| 607 |
+
"loss": 4.2065,
|
| 608 |
+
"step": 20000
|
| 609 |
}
|
| 610 |
],
|
| 611 |
"max_steps": 500000,
|
| 612 |
"num_train_epochs": 3,
|
| 613 |
+
"total_flos": 3.187659964416e+16,
|
| 614 |
"trial_name": null,
|
| 615 |
"trial_params": null
|
| 616 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 146774203
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:669ff7fd28968817843d8d3e735a9f1604e6f86bd0620d14ba500c796ee6cb84
|
| 3 |
size 146774203
|