Training in progress, epoch 2, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3132668808
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72e09c96eac9a5a5d12013b41dda13b70836234bc8e79dede1d0e69838b32cd5
|
| 3 |
size 3132668808
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6265677800
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3e0cc1950821aee72f368717c0c4eaca6964baee54bfdd8fe9937bb25df79ba
|
| 3 |
size 6265677800
|
last-checkpoint/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 sha256:714f24020961e064909455be3a37151a09a776324c46a43c77ff89f66b058427
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7bab7b51078791231733fbc4c23771b030e167e47650cf7b4cbbe893dfeb9092
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -332,13 +332,338 @@
|
|
| 332 |
"eval_steps_per_second": 0.302,
|
| 333 |
"eval_translation_length": 5805056,
|
| 334 |
"step": 25511
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 335 |
}
|
| 336 |
],
|
| 337 |
"logging_steps": 500,
|
| 338 |
"max_steps": 127555,
|
| 339 |
"num_train_epochs": 5,
|
| 340 |
"save_steps": 500,
|
| 341 |
-
"total_flos":
|
| 342 |
"trial_name": null,
|
| 343 |
"trial_params": null
|
| 344 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 51022,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 332 |
"eval_steps_per_second": 0.302,
|
| 333 |
"eval_translation_length": 5805056,
|
| 334 |
"step": 25511
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 1.02,
|
| 338 |
+
"learning_rate": 9.038607676811049e-05,
|
| 339 |
+
"loss": 2.6527,
|
| 340 |
+
"step": 26000
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 1.04,
|
| 344 |
+
"learning_rate": 9.00185569894294e-05,
|
| 345 |
+
"loss": 2.5876,
|
| 346 |
+
"step": 26500
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.06,
|
| 350 |
+
"learning_rate": 8.964492058194002e-05,
|
| 351 |
+
"loss": 2.6107,
|
| 352 |
+
"step": 27000
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.08,
|
| 356 |
+
"learning_rate": 8.926522465402872e-05,
|
| 357 |
+
"loss": 2.6123,
|
| 358 |
+
"step": 27500
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 1.1,
|
| 362 |
+
"learning_rate": 8.887952724024808e-05,
|
| 363 |
+
"loss": 2.5845,
|
| 364 |
+
"step": 28000
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 1.12,
|
| 368 |
+
"learning_rate": 8.848788729244675e-05,
|
| 369 |
+
"loss": 2.621,
|
| 370 |
+
"step": 28500
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 1.14,
|
| 374 |
+
"learning_rate": 8.809036467075875e-05,
|
| 375 |
+
"loss": 2.6317,
|
| 376 |
+
"step": 29000
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 1.16,
|
| 380 |
+
"learning_rate": 8.768702013445438e-05,
|
| 381 |
+
"loss": 2.6083,
|
| 382 |
+
"step": 29500
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 1.18,
|
| 386 |
+
"learning_rate": 8.727791533265335e-05,
|
| 387 |
+
"loss": 2.6469,
|
| 388 |
+
"step": 30000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.2,
|
| 392 |
+
"learning_rate": 8.686311279490205e-05,
|
| 393 |
+
"loss": 2.6186,
|
| 394 |
+
"step": 30500
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 1.22,
|
| 398 |
+
"learning_rate": 8.644267592161625e-05,
|
| 399 |
+
"loss": 2.6418,
|
| 400 |
+
"step": 31000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 1.23,
|
| 404 |
+
"learning_rate": 8.601666897439072e-05,
|
| 405 |
+
"loss": 2.6127,
|
| 406 |
+
"step": 31500
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.25,
|
| 410 |
+
"learning_rate": 8.55851570661771e-05,
|
| 411 |
+
"loss": 2.6585,
|
| 412 |
+
"step": 32000
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 1.27,
|
| 416 |
+
"learning_rate": 8.514820615133171e-05,
|
| 417 |
+
"loss": 2.6329,
|
| 418 |
+
"step": 32500
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 1.29,
|
| 422 |
+
"learning_rate": 8.47058830155349e-05,
|
| 423 |
+
"loss": 2.6495,
|
| 424 |
+
"step": 33000
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 1.31,
|
| 428 |
+
"learning_rate": 8.425825526558306e-05,
|
| 429 |
+
"loss": 2.6859,
|
| 430 |
+
"step": 33500
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.33,
|
| 434 |
+
"learning_rate": 8.380539131905538e-05,
|
| 435 |
+
"loss": 2.6083,
|
| 436 |
+
"step": 34000
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.35,
|
| 440 |
+
"learning_rate": 8.334736039385647e-05,
|
| 441 |
+
"loss": 2.6761,
|
| 442 |
+
"step": 34500
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 1.37,
|
| 446 |
+
"learning_rate": 8.288423249763687e-05,
|
| 447 |
+
"loss": 2.5866,
|
| 448 |
+
"step": 35000
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 1.39,
|
| 452 |
+
"learning_rate": 8.241607841709266e-05,
|
| 453 |
+
"loss": 2.7219,
|
| 454 |
+
"step": 35500
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 1.41,
|
| 458 |
+
"learning_rate": 8.194296970714615e-05,
|
| 459 |
+
"loss": 2.6395,
|
| 460 |
+
"step": 36000
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 1.43,
|
| 464 |
+
"learning_rate": 8.146497868000903e-05,
|
| 465 |
+
"loss": 2.6553,
|
| 466 |
+
"step": 36500
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 1.45,
|
| 470 |
+
"learning_rate": 8.098217839412985e-05,
|
| 471 |
+
"loss": 2.6139,
|
| 472 |
+
"step": 37000
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.47,
|
| 476 |
+
"learning_rate": 8.049464264302741e-05,
|
| 477 |
+
"loss": 2.6203,
|
| 478 |
+
"step": 37500
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.49,
|
| 482 |
+
"learning_rate": 8.000244594401178e-05,
|
| 483 |
+
"loss": 2.729,
|
| 484 |
+
"step": 38000
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 1.51,
|
| 488 |
+
"learning_rate": 7.950566352679475e-05,
|
| 489 |
+
"loss": 2.607,
|
| 490 |
+
"step": 38500
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 1.53,
|
| 494 |
+
"learning_rate": 7.900437132199135e-05,
|
| 495 |
+
"loss": 2.7186,
|
| 496 |
+
"step": 39000
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 1.55,
|
| 500 |
+
"learning_rate": 7.849864594951422e-05,
|
| 501 |
+
"loss": 2.6396,
|
| 502 |
+
"step": 39500
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 1.57,
|
| 506 |
+
"learning_rate": 7.798856470686275e-05,
|
| 507 |
+
"loss": 2.6618,
|
| 508 |
+
"step": 40000
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 1.59,
|
| 512 |
+
"learning_rate": 7.747420555730837e-05,
|
| 513 |
+
"loss": 2.595,
|
| 514 |
+
"step": 40500
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.61,
|
| 518 |
+
"learning_rate": 7.695564711797849e-05,
|
| 519 |
+
"loss": 2.6412,
|
| 520 |
+
"step": 41000
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.63,
|
| 524 |
+
"learning_rate": 7.643296864784011e-05,
|
| 525 |
+
"loss": 2.6468,
|
| 526 |
+
"step": 41500
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 1.65,
|
| 530 |
+
"learning_rate": 7.590625003558561e-05,
|
| 531 |
+
"loss": 2.5908,
|
| 532 |
+
"step": 42000
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 1.67,
|
| 536 |
+
"learning_rate": 7.53755717874221e-05,
|
| 537 |
+
"loss": 2.6129,
|
| 538 |
+
"step": 42500
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 1.69,
|
| 542 |
+
"learning_rate": 7.484101501476649e-05,
|
| 543 |
+
"loss": 2.6015,
|
| 544 |
+
"step": 43000
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 1.71,
|
| 548 |
+
"learning_rate": 7.430266142184806e-05,
|
| 549 |
+
"loss": 2.6249,
|
| 550 |
+
"step": 43500
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 1.72,
|
| 554 |
+
"learning_rate": 7.376059329322036e-05,
|
| 555 |
+
"loss": 2.6027,
|
| 556 |
+
"step": 44000
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.74,
|
| 560 |
+
"learning_rate": 7.321489348118445e-05,
|
| 561 |
+
"loss": 2.5851,
|
| 562 |
+
"step": 44500
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.76,
|
| 566 |
+
"learning_rate": 7.266564539312535e-05,
|
| 567 |
+
"loss": 2.6235,
|
| 568 |
+
"step": 45000
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 1.78,
|
| 572 |
+
"learning_rate": 7.211293297876365e-05,
|
| 573 |
+
"loss": 2.6393,
|
| 574 |
+
"step": 45500
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 1.8,
|
| 578 |
+
"learning_rate": 7.155684071732431e-05,
|
| 579 |
+
"loss": 2.5699,
|
| 580 |
+
"step": 46000
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 1.82,
|
| 584 |
+
"learning_rate": 7.099745360462426e-05,
|
| 585 |
+
"loss": 2.6722,
|
| 586 |
+
"step": 46500
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 1.84,
|
| 590 |
+
"learning_rate": 7.043485714008147e-05,
|
| 591 |
+
"loss": 2.6375,
|
| 592 |
+
"step": 47000
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 1.86,
|
| 596 |
+
"learning_rate": 6.98691373136466e-05,
|
| 597 |
+
"loss": 2.6718,
|
| 598 |
+
"step": 47500
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.88,
|
| 602 |
+
"learning_rate": 6.930038059266004e-05,
|
| 603 |
+
"loss": 2.6249,
|
| 604 |
+
"step": 48000
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.9,
|
| 608 |
+
"learning_rate": 6.872867390863569e-05,
|
| 609 |
+
"loss": 2.6526,
|
| 610 |
+
"step": 48500
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 1.92,
|
| 614 |
+
"learning_rate": 6.815410464397405e-05,
|
| 615 |
+
"loss": 2.6139,
|
| 616 |
+
"step": 49000
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 1.94,
|
| 620 |
+
"learning_rate": 6.757676061860619e-05,
|
| 621 |
+
"loss": 2.5463,
|
| 622 |
+
"step": 49500
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 1.96,
|
| 626 |
+
"learning_rate": 6.699673007657097e-05,
|
| 627 |
+
"loss": 2.6163,
|
| 628 |
+
"step": 50000
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 1.98,
|
| 632 |
+
"learning_rate": 6.641410167252738e-05,
|
| 633 |
+
"loss": 2.6282,
|
| 634 |
+
"step": 50500
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.0,
|
| 638 |
+
"learning_rate": 6.582896445820412e-05,
|
| 639 |
+
"loss": 2.5324,
|
| 640 |
+
"step": 51000
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 2.0,
|
| 644 |
+
"eval_bleu": 1.0,
|
| 645 |
+
"eval_brevity_penalty": 1.0,
|
| 646 |
+
"eval_length_ratio": 1.0,
|
| 647 |
+
"eval_loss": 2.711536407470703,
|
| 648 |
+
"eval_precisions": [
|
| 649 |
+
1.0,
|
| 650 |
+
1.0,
|
| 651 |
+
1.0,
|
| 652 |
+
1.0
|
| 653 |
+
],
|
| 654 |
+
"eval_reference_length": 5805056,
|
| 655 |
+
"eval_runtime": 9329.1164,
|
| 656 |
+
"eval_samples_per_second": 1.215,
|
| 657 |
+
"eval_steps_per_second": 0.304,
|
| 658 |
+
"eval_translation_length": 5805056,
|
| 659 |
+
"step": 51022
|
| 660 |
}
|
| 661 |
],
|
| 662 |
"logging_steps": 500,
|
| 663 |
"max_steps": 127555,
|
| 664 |
"num_train_epochs": 5,
|
| 665 |
"save_steps": 500,
|
| 666 |
+
"total_flos": 4.703662624808632e+17,
|
| 667 |
"trial_name": null,
|
| 668 |
"trial_params": null
|
| 669 |
}
|