Training in progress, step 1000, 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 234681136
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6474fca5a3c5baba3de6445b1ebdccd489d640243fc43690efa828d0c4fe3868
|
| 3 |
size 234681136
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 469516363
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e45d306cbed8140a90bd411a1fece5d9556ba1ea6e19977f26931c3c04004bd4
|
| 3 |
size 469516363
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1b8777afaf65f04eb18ddaf41f68fd24275d3e886bf75d506bd86a6d10df7f8
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dfc5c6949cf8a9eca4d88710f0c9c06f410fb63454fb60c644727889ad457648
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 100,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -398,6 +398,396 @@
|
|
| 398 |
"eval_samples_per_second": 67.447,
|
| 399 |
"eval_steps_per_second": 3.848,
|
| 400 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 401 |
}
|
| 402 |
],
|
| 403 |
"logging_steps": 10,
|
|
@@ -417,7 +807,7 @@
|
|
| 417 |
"attributes": {}
|
| 418 |
}
|
| 419 |
},
|
| 420 |
-
"total_flos":
|
| 421 |
"train_batch_size": 18,
|
| 422 |
"trial_name": null,
|
| 423 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.2,
|
| 6 |
"eval_steps": 100,
|
| 7 |
+
"global_step": 1000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 398 |
"eval_samples_per_second": 67.447,
|
| 399 |
"eval_steps_per_second": 3.848,
|
| 400 |
"step": 500
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 0.102,
|
| 404 |
+
"grad_norm": 0.66796875,
|
| 405 |
+
"learning_rate": 0.0003,
|
| 406 |
+
"loss": 2.6653621673583983,
|
| 407 |
+
"step": 510
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.104,
|
| 411 |
+
"grad_norm": 2.53125,
|
| 412 |
+
"learning_rate": 0.0003,
|
| 413 |
+
"loss": 2.6938413619995116,
|
| 414 |
+
"step": 520
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.106,
|
| 418 |
+
"grad_norm": 1.578125,
|
| 419 |
+
"learning_rate": 0.0003,
|
| 420 |
+
"loss": 2.6589494705200196,
|
| 421 |
+
"step": 530
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.108,
|
| 425 |
+
"grad_norm": 1.453125,
|
| 426 |
+
"learning_rate": 0.0003,
|
| 427 |
+
"loss": 2.6775186538696287,
|
| 428 |
+
"step": 540
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.11,
|
| 432 |
+
"grad_norm": 0.1806640625,
|
| 433 |
+
"learning_rate": 0.0003,
|
| 434 |
+
"loss": 2.659619140625,
|
| 435 |
+
"step": 550
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.112,
|
| 439 |
+
"grad_norm": 0.212890625,
|
| 440 |
+
"learning_rate": 0.0003,
|
| 441 |
+
"loss": 2.644103240966797,
|
| 442 |
+
"step": 560
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.114,
|
| 446 |
+
"grad_norm": 0.73046875,
|
| 447 |
+
"learning_rate": 0.0003,
|
| 448 |
+
"loss": 2.65213565826416,
|
| 449 |
+
"step": 570
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.116,
|
| 453 |
+
"grad_norm": 1.1796875,
|
| 454 |
+
"learning_rate": 0.0003,
|
| 455 |
+
"loss": 2.6230279922485353,
|
| 456 |
+
"step": 580
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.118,
|
| 460 |
+
"grad_norm": 0.166015625,
|
| 461 |
+
"learning_rate": 0.0003,
|
| 462 |
+
"loss": 2.6443111419677736,
|
| 463 |
+
"step": 590
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 0.12,
|
| 467 |
+
"grad_norm": 0.8203125,
|
| 468 |
+
"learning_rate": 0.0003,
|
| 469 |
+
"loss": 2.6569570541381835,
|
| 470 |
+
"step": 600
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.12,
|
| 474 |
+
"eval_loss": 3.0349245071411133,
|
| 475 |
+
"eval_runtime": 4.4206,
|
| 476 |
+
"eval_samples_per_second": 67.412,
|
| 477 |
+
"eval_steps_per_second": 3.846,
|
| 478 |
+
"step": 600
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.122,
|
| 482 |
+
"grad_norm": 0.1181640625,
|
| 483 |
+
"learning_rate": 0.0003,
|
| 484 |
+
"loss": 2.6595781326293944,
|
| 485 |
+
"step": 610
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.124,
|
| 489 |
+
"grad_norm": 0.232421875,
|
| 490 |
+
"learning_rate": 0.0003,
|
| 491 |
+
"loss": 2.610936737060547,
|
| 492 |
+
"step": 620
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.126,
|
| 496 |
+
"grad_norm": 0.1435546875,
|
| 497 |
+
"learning_rate": 0.0003,
|
| 498 |
+
"loss": 2.6387302398681642,
|
| 499 |
+
"step": 630
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.128,
|
| 503 |
+
"grad_norm": 0.14453125,
|
| 504 |
+
"learning_rate": 0.0003,
|
| 505 |
+
"loss": 2.62979793548584,
|
| 506 |
+
"step": 640
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.13,
|
| 510 |
+
"grad_norm": 2.34375,
|
| 511 |
+
"learning_rate": 0.0003,
|
| 512 |
+
"loss": 2.649636650085449,
|
| 513 |
+
"step": 650
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.132,
|
| 517 |
+
"grad_norm": 0.2041015625,
|
| 518 |
+
"learning_rate": 0.0003,
|
| 519 |
+
"loss": 2.622520637512207,
|
| 520 |
+
"step": 660
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.134,
|
| 524 |
+
"grad_norm": 0.97265625,
|
| 525 |
+
"learning_rate": 0.0003,
|
| 526 |
+
"loss": 2.646112823486328,
|
| 527 |
+
"step": 670
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.136,
|
| 531 |
+
"grad_norm": 5.8125,
|
| 532 |
+
"learning_rate": 0.0003,
|
| 533 |
+
"loss": 2.6434356689453127,
|
| 534 |
+
"step": 680
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.138,
|
| 538 |
+
"grad_norm": 0.10693359375,
|
| 539 |
+
"learning_rate": 0.0003,
|
| 540 |
+
"loss": 2.623065376281738,
|
| 541 |
+
"step": 690
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.14,
|
| 545 |
+
"grad_norm": 0.90625,
|
| 546 |
+
"learning_rate": 0.0003,
|
| 547 |
+
"loss": 2.6090648651123045,
|
| 548 |
+
"step": 700
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.14,
|
| 552 |
+
"eval_loss": 3.0306036472320557,
|
| 553 |
+
"eval_runtime": 4.4176,
|
| 554 |
+
"eval_samples_per_second": 67.457,
|
| 555 |
+
"eval_steps_per_second": 3.848,
|
| 556 |
+
"step": 700
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.142,
|
| 560 |
+
"grad_norm": 0.6328125,
|
| 561 |
+
"learning_rate": 0.0003,
|
| 562 |
+
"loss": 2.6384559631347657,
|
| 563 |
+
"step": 710
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.144,
|
| 567 |
+
"grad_norm": 0.640625,
|
| 568 |
+
"learning_rate": 0.0003,
|
| 569 |
+
"loss": 2.6472700119018553,
|
| 570 |
+
"step": 720
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.146,
|
| 574 |
+
"grad_norm": 0.07177734375,
|
| 575 |
+
"learning_rate": 0.0003,
|
| 576 |
+
"loss": 2.6483619689941404,
|
| 577 |
+
"step": 730
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.148,
|
| 581 |
+
"grad_norm": 0.322265625,
|
| 582 |
+
"learning_rate": 0.0003,
|
| 583 |
+
"loss": 2.626618766784668,
|
| 584 |
+
"step": 740
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.15,
|
| 588 |
+
"grad_norm": 0.099609375,
|
| 589 |
+
"learning_rate": 0.0003,
|
| 590 |
+
"loss": 2.6325525283813476,
|
| 591 |
+
"step": 750
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.152,
|
| 595 |
+
"grad_norm": 0.1611328125,
|
| 596 |
+
"learning_rate": 0.0003,
|
| 597 |
+
"loss": 2.6193023681640626,
|
| 598 |
+
"step": 760
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.154,
|
| 602 |
+
"grad_norm": 0.072265625,
|
| 603 |
+
"learning_rate": 0.0003,
|
| 604 |
+
"loss": 2.618332862854004,
|
| 605 |
+
"step": 770
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.156,
|
| 609 |
+
"grad_norm": 0.87109375,
|
| 610 |
+
"learning_rate": 0.0003,
|
| 611 |
+
"loss": 2.610393524169922,
|
| 612 |
+
"step": 780
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.158,
|
| 616 |
+
"grad_norm": 0.09716796875,
|
| 617 |
+
"learning_rate": 0.0003,
|
| 618 |
+
"loss": 2.6242008209228516,
|
| 619 |
+
"step": 790
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.16,
|
| 623 |
+
"grad_norm": 0.072265625,
|
| 624 |
+
"learning_rate": 0.0003,
|
| 625 |
+
"loss": 2.638929748535156,
|
| 626 |
+
"step": 800
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.16,
|
| 630 |
+
"eval_loss": 3.0286974906921387,
|
| 631 |
+
"eval_runtime": 4.4633,
|
| 632 |
+
"eval_samples_per_second": 66.766,
|
| 633 |
+
"eval_steps_per_second": 3.809,
|
| 634 |
+
"step": 800
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.162,
|
| 638 |
+
"grad_norm": 0.29296875,
|
| 639 |
+
"learning_rate": 0.0003,
|
| 640 |
+
"loss": 2.638911247253418,
|
| 641 |
+
"step": 810
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.164,
|
| 645 |
+
"grad_norm": 0.62890625,
|
| 646 |
+
"learning_rate": 0.0003,
|
| 647 |
+
"loss": 2.6282770156860353,
|
| 648 |
+
"step": 820
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.166,
|
| 652 |
+
"grad_norm": 0.0859375,
|
| 653 |
+
"learning_rate": 0.0003,
|
| 654 |
+
"loss": 2.668540382385254,
|
| 655 |
+
"step": 830
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.168,
|
| 659 |
+
"grad_norm": 0.08349609375,
|
| 660 |
+
"learning_rate": 0.0003,
|
| 661 |
+
"loss": 2.6025644302368165,
|
| 662 |
+
"step": 840
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.17,
|
| 666 |
+
"grad_norm": 0.251953125,
|
| 667 |
+
"learning_rate": 0.0003,
|
| 668 |
+
"loss": 2.614345932006836,
|
| 669 |
+
"step": 850
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.172,
|
| 673 |
+
"grad_norm": 1.2421875,
|
| 674 |
+
"learning_rate": 0.0003,
|
| 675 |
+
"loss": 2.6097484588623048,
|
| 676 |
+
"step": 860
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.174,
|
| 680 |
+
"grad_norm": 0.10107421875,
|
| 681 |
+
"learning_rate": 0.0003,
|
| 682 |
+
"loss": 2.5976139068603517,
|
| 683 |
+
"step": 870
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.176,
|
| 687 |
+
"grad_norm": 0.0634765625,
|
| 688 |
+
"learning_rate": 0.0003,
|
| 689 |
+
"loss": 2.609291648864746,
|
| 690 |
+
"step": 880
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.178,
|
| 694 |
+
"grad_norm": 0.060302734375,
|
| 695 |
+
"learning_rate": 0.0003,
|
| 696 |
+
"loss": 2.6136356353759767,
|
| 697 |
+
"step": 890
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.18,
|
| 701 |
+
"grad_norm": 0.306640625,
|
| 702 |
+
"learning_rate": 0.0003,
|
| 703 |
+
"loss": 2.6354192733764648,
|
| 704 |
+
"step": 900
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.18,
|
| 708 |
+
"eval_loss": 3.028738021850586,
|
| 709 |
+
"eval_runtime": 4.4125,
|
| 710 |
+
"eval_samples_per_second": 67.536,
|
| 711 |
+
"eval_steps_per_second": 3.853,
|
| 712 |
+
"step": 900
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 0.182,
|
| 716 |
+
"grad_norm": 0.65234375,
|
| 717 |
+
"learning_rate": 0.0003,
|
| 718 |
+
"loss": 2.6325847625732424,
|
| 719 |
+
"step": 910
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 0.184,
|
| 723 |
+
"grad_norm": 0.4921875,
|
| 724 |
+
"learning_rate": 0.0003,
|
| 725 |
+
"loss": 2.6379472732543947,
|
| 726 |
+
"step": 920
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 0.186,
|
| 730 |
+
"grad_norm": 0.216796875,
|
| 731 |
+
"learning_rate": 0.0003,
|
| 732 |
+
"loss": 2.647774505615234,
|
| 733 |
+
"step": 930
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.188,
|
| 737 |
+
"grad_norm": 0.083984375,
|
| 738 |
+
"learning_rate": 0.0003,
|
| 739 |
+
"loss": 2.628580665588379,
|
| 740 |
+
"step": 940
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.19,
|
| 744 |
+
"grad_norm": 0.09033203125,
|
| 745 |
+
"learning_rate": 0.0003,
|
| 746 |
+
"loss": 2.63638973236084,
|
| 747 |
+
"step": 950
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.192,
|
| 751 |
+
"grad_norm": 0.08056640625,
|
| 752 |
+
"learning_rate": 0.0003,
|
| 753 |
+
"loss": 2.628683853149414,
|
| 754 |
+
"step": 960
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.194,
|
| 758 |
+
"grad_norm": 0.06787109375,
|
| 759 |
+
"learning_rate": 0.0003,
|
| 760 |
+
"loss": 2.628560256958008,
|
| 761 |
+
"step": 970
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.196,
|
| 765 |
+
"grad_norm": 0.1328125,
|
| 766 |
+
"learning_rate": 0.0003,
|
| 767 |
+
"loss": 2.627498435974121,
|
| 768 |
+
"step": 980
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.198,
|
| 772 |
+
"grad_norm": 0.1796875,
|
| 773 |
+
"learning_rate": 0.0003,
|
| 774 |
+
"loss": 2.613533782958984,
|
| 775 |
+
"step": 990
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.2,
|
| 779 |
+
"grad_norm": 0.265625,
|
| 780 |
+
"learning_rate": 0.0003,
|
| 781 |
+
"loss": 2.615587615966797,
|
| 782 |
+
"step": 1000
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.2,
|
| 786 |
+
"eval_loss": 3.0314836502075195,
|
| 787 |
+
"eval_runtime": 4.4355,
|
| 788 |
+
"eval_samples_per_second": 67.186,
|
| 789 |
+
"eval_steps_per_second": 3.833,
|
| 790 |
+
"step": 1000
|
| 791 |
}
|
| 792 |
],
|
| 793 |
"logging_steps": 10,
|
|
|
|
| 807 |
"attributes": {}
|
| 808 |
}
|
| 809 |
},
|
| 810 |
+
"total_flos": 3.26154514857984e+17,
|
| 811 |
"train_batch_size": 18,
|
| 812 |
"trial_name": null,
|
| 813 |
"trial_params": null
|