caracena
commited on
Commit
•
e9314ad
1
Parent(s):
1d4c154
update model to 10 epochs
Browse files- README.md +3 -3
- all_results.json +5 -5
- pytorch_model.bin +1 -1
- train_results.json +5 -5
- trainer_state.json +390 -12
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -31,12 +31,12 @@ More information needed
|
|
| 31 |
|
| 32 |
The following hyperparameters were used during training:
|
| 33 |
- learning_rate: 5e-05
|
| 34 |
-
- train_batch_size:
|
| 35 |
-
- eval_batch_size:
|
| 36 |
- seed: 42
|
| 37 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 38 |
- lr_scheduler_type: linear
|
| 39 |
-
- num_epochs:
|
| 40 |
|
| 41 |
### Training results
|
| 42 |
|
|
|
|
| 31 |
|
| 32 |
The following hyperparameters were used during training:
|
| 33 |
- learning_rate: 5e-05
|
| 34 |
+
- train_batch_size: 32
|
| 35 |
+
- eval_batch_size: 16
|
| 36 |
- seed: 42
|
| 37 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 38 |
- lr_scheduler_type: linear
|
| 39 |
+
- num_epochs: 10.0
|
| 40 |
|
| 41 |
### Training results
|
| 42 |
|
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 253650,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 2.0376459330797827,
|
| 4 |
+
"train_runtime": 6961.2818,
|
| 5 |
"train_samples": 253650,
|
| 6 |
+
"train_samples_per_second": 364.373,
|
| 7 |
+
"train_steps_per_second": 11.387
|
| 8 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 439605291
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a683a2d389dfd89b799daa6e7f82b778995c5c2d083c9afe6ec12ad006283d1
|
| 3 |
size 439605291
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 253650,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 2.0376459330797827,
|
| 4 |
+
"train_runtime": 6961.2818,
|
| 5 |
"train_samples": 253650,
|
| 6 |
+
"train_samples_per_second": 364.373,
|
| 7 |
+
"train_steps_per_second": 11.387
|
| 8 |
}
|
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,
|
|
@@ -578,18 +578,396 @@
|
|
| 578 |
"step": 47500
|
| 579 |
},
|
| 580 |
{
|
| 581 |
-
"epoch":
|
| 582 |
-
"
|
| 583 |
-
"
|
| 584 |
-
"
|
| 585 |
-
|
| 586 |
-
|
| 587 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 588 |
}
|
| 589 |
],
|
| 590 |
-
"max_steps":
|
| 591 |
-
"num_train_epochs":
|
| 592 |
-
"total_flos":
|
| 593 |
"trial_name": null,
|
| 594 |
"trial_params": null
|
| 595 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 79270,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 578 |
"step": 47500
|
| 579 |
},
|
| 580 |
{
|
| 581 |
+
"epoch": 6.06,
|
| 582 |
+
"learning_rate": 1.9723729027374795e-05,
|
| 583 |
+
"loss": 5.3624,
|
| 584 |
+
"step": 48000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 6.12,
|
| 588 |
+
"learning_rate": 1.9408351204743284e-05,
|
| 589 |
+
"loss": 5.3565,
|
| 590 |
+
"step": 48500
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 6.18,
|
| 594 |
+
"learning_rate": 1.909297338211177e-05,
|
| 595 |
+
"loss": 5.3609,
|
| 596 |
+
"step": 49000
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 6.24,
|
| 600 |
+
"learning_rate": 1.877759555948026e-05,
|
| 601 |
+
"loss": 5.3611,
|
| 602 |
+
"step": 49500
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 6.31,
|
| 606 |
+
"learning_rate": 1.8462217736848747e-05,
|
| 607 |
+
"loss": 5.3563,
|
| 608 |
+
"step": 50000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 6.37,
|
| 612 |
+
"learning_rate": 1.8146839914217233e-05,
|
| 613 |
+
"loss": 5.3578,
|
| 614 |
+
"step": 50500
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 6.43,
|
| 618 |
+
"learning_rate": 1.783146209158572e-05,
|
| 619 |
+
"loss": 5.3396,
|
| 620 |
+
"step": 51000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 6.5,
|
| 624 |
+
"learning_rate": 1.7516084268954207e-05,
|
| 625 |
+
"loss": 5.3496,
|
| 626 |
+
"step": 51500
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 6.56,
|
| 630 |
+
"learning_rate": 1.7200706446322696e-05,
|
| 631 |
+
"loss": 5.3486,
|
| 632 |
+
"step": 52000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 6.62,
|
| 636 |
+
"learning_rate": 1.688532862369118e-05,
|
| 637 |
+
"loss": 5.3449,
|
| 638 |
+
"step": 52500
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 6.69,
|
| 642 |
+
"learning_rate": 1.656995080105967e-05,
|
| 643 |
+
"loss": 5.336,
|
| 644 |
+
"step": 53000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 6.75,
|
| 648 |
+
"learning_rate": 1.6254572978428156e-05,
|
| 649 |
+
"loss": 5.3289,
|
| 650 |
+
"step": 53500
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 6.81,
|
| 654 |
+
"learning_rate": 1.5939195155796645e-05,
|
| 655 |
+
"loss": 5.3335,
|
| 656 |
+
"step": 54000
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 6.88,
|
| 660 |
+
"learning_rate": 1.5623817333165134e-05,
|
| 661 |
+
"loss": 5.3298,
|
| 662 |
+
"step": 54500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 6.94,
|
| 666 |
+
"learning_rate": 1.530843951053362e-05,
|
| 667 |
+
"loss": 5.3302,
|
| 668 |
+
"step": 55000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 7.0,
|
| 672 |
+
"learning_rate": 1.4993061687902108e-05,
|
| 673 |
+
"loss": 5.3275,
|
| 674 |
+
"step": 55500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 7.06,
|
| 678 |
+
"learning_rate": 1.4677683865270595e-05,
|
| 679 |
+
"loss": 5.3219,
|
| 680 |
+
"step": 56000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 7.13,
|
| 684 |
+
"learning_rate": 1.4362306042639082e-05,
|
| 685 |
+
"loss": 5.3179,
|
| 686 |
+
"step": 56500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 7.19,
|
| 690 |
+
"learning_rate": 1.4046928220007568e-05,
|
| 691 |
+
"loss": 5.3064,
|
| 692 |
+
"step": 57000
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 7.25,
|
| 696 |
+
"learning_rate": 1.3731550397376058e-05,
|
| 697 |
+
"loss": 5.312,
|
| 698 |
+
"step": 57500
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 7.32,
|
| 702 |
+
"learning_rate": 1.3416172574744546e-05,
|
| 703 |
+
"loss": 5.3166,
|
| 704 |
+
"step": 58000
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 7.38,
|
| 708 |
+
"learning_rate": 1.3100794752113033e-05,
|
| 709 |
+
"loss": 5.308,
|
| 710 |
+
"step": 58500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 7.44,
|
| 714 |
+
"learning_rate": 1.278541692948152e-05,
|
| 715 |
+
"loss": 5.2994,
|
| 716 |
+
"step": 59000
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 7.51,
|
| 720 |
+
"learning_rate": 1.2470039106850007e-05,
|
| 721 |
+
"loss": 5.2991,
|
| 722 |
+
"step": 59500
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 7.57,
|
| 726 |
+
"learning_rate": 1.2154661284218494e-05,
|
| 727 |
+
"loss": 5.2917,
|
| 728 |
+
"step": 60000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 7.63,
|
| 732 |
+
"learning_rate": 1.1839283461586981e-05,
|
| 733 |
+
"loss": 5.2962,
|
| 734 |
+
"step": 60500
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 7.7,
|
| 738 |
+
"learning_rate": 1.1523905638955469e-05,
|
| 739 |
+
"loss": 5.2927,
|
| 740 |
+
"step": 61000
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 7.76,
|
| 744 |
+
"learning_rate": 1.1208527816323956e-05,
|
| 745 |
+
"loss": 5.2901,
|
| 746 |
+
"step": 61500
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 7.82,
|
| 750 |
+
"learning_rate": 1.0893149993692445e-05,
|
| 751 |
+
"loss": 5.2726,
|
| 752 |
+
"step": 62000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 7.88,
|
| 756 |
+
"learning_rate": 1.0577772171060932e-05,
|
| 757 |
+
"loss": 5.2586,
|
| 758 |
+
"step": 62500
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 7.95,
|
| 762 |
+
"learning_rate": 1.0262394348429419e-05,
|
| 763 |
+
"loss": 5.2408,
|
| 764 |
+
"step": 63000
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 8.01,
|
| 768 |
+
"learning_rate": 9.947016525797906e-06,
|
| 769 |
+
"loss": 5.2086,
|
| 770 |
+
"step": 63500
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 8.07,
|
| 774 |
+
"learning_rate": 9.631638703166395e-06,
|
| 775 |
+
"loss": 5.1942,
|
| 776 |
+
"step": 64000
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 8.14,
|
| 780 |
+
"learning_rate": 9.31626088053488e-06,
|
| 781 |
+
"loss": 5.1737,
|
| 782 |
+
"step": 64500
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 8.2,
|
| 786 |
+
"learning_rate": 9.000883057903368e-06,
|
| 787 |
+
"loss": 5.1362,
|
| 788 |
+
"step": 65000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 8.26,
|
| 792 |
+
"learning_rate": 8.685505235271855e-06,
|
| 793 |
+
"loss": 5.1235,
|
| 794 |
+
"step": 65500
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 8.33,
|
| 798 |
+
"learning_rate": 8.370127412640344e-06,
|
| 799 |
+
"loss": 5.0998,
|
| 800 |
+
"step": 66000
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 8.39,
|
| 804 |
+
"learning_rate": 8.054749590008831e-06,
|
| 805 |
+
"loss": 5.0742,
|
| 806 |
+
"step": 66500
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 8.45,
|
| 810 |
+
"learning_rate": 7.739371767377318e-06,
|
| 811 |
+
"loss": 5.0369,
|
| 812 |
+
"step": 67000
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 8.52,
|
| 816 |
+
"learning_rate": 7.423993944745806e-06,
|
| 817 |
+
"loss": 5.0226,
|
| 818 |
+
"step": 67500
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 8.58,
|
| 822 |
+
"learning_rate": 7.108616122114293e-06,
|
| 823 |
+
"loss": 4.9907,
|
| 824 |
+
"step": 68000
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 8.64,
|
| 828 |
+
"learning_rate": 6.7932382994827806e-06,
|
| 829 |
+
"loss": 4.9742,
|
| 830 |
+
"step": 68500
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 8.7,
|
| 834 |
+
"learning_rate": 6.477860476851268e-06,
|
| 835 |
+
"loss": 4.9379,
|
| 836 |
+
"step": 69000
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 8.77,
|
| 840 |
+
"learning_rate": 6.162482654219756e-06,
|
| 841 |
+
"loss": 4.9064,
|
| 842 |
+
"step": 69500
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 8.83,
|
| 846 |
+
"learning_rate": 5.847104831588243e-06,
|
| 847 |
+
"loss": 4.8912,
|
| 848 |
+
"step": 70000
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 8.89,
|
| 852 |
+
"learning_rate": 5.53172700895673e-06,
|
| 853 |
+
"loss": 4.8666,
|
| 854 |
+
"step": 70500
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 8.96,
|
| 858 |
+
"learning_rate": 5.216349186325218e-06,
|
| 859 |
+
"loss": 4.835,
|
| 860 |
+
"step": 71000
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 9.02,
|
| 864 |
+
"learning_rate": 4.900971363693705e-06,
|
| 865 |
+
"loss": 4.8144,
|
| 866 |
+
"step": 71500
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 9.08,
|
| 870 |
+
"learning_rate": 4.5855935410621925e-06,
|
| 871 |
+
"loss": 4.7944,
|
| 872 |
+
"step": 72000
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 9.15,
|
| 876 |
+
"learning_rate": 4.27021571843068e-06,
|
| 877 |
+
"loss": 4.7744,
|
| 878 |
+
"step": 72500
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 9.21,
|
| 882 |
+
"learning_rate": 3.954837895799168e-06,
|
| 883 |
+
"loss": 4.7491,
|
| 884 |
+
"step": 73000
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 9.27,
|
| 888 |
+
"learning_rate": 3.6394600731676553e-06,
|
| 889 |
+
"loss": 4.723,
|
| 890 |
+
"step": 73500
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 9.34,
|
| 894 |
+
"learning_rate": 3.3240822505361425e-06,
|
| 895 |
+
"loss": 4.7129,
|
| 896 |
+
"step": 74000
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 9.4,
|
| 900 |
+
"learning_rate": 3.0087044279046297e-06,
|
| 901 |
+
"loss": 4.6943,
|
| 902 |
+
"step": 74500
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 9.46,
|
| 906 |
+
"learning_rate": 2.6933266052731173e-06,
|
| 907 |
+
"loss": 4.6951,
|
| 908 |
+
"step": 75000
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 9.52,
|
| 912 |
+
"learning_rate": 2.3779487826416044e-06,
|
| 913 |
+
"loss": 4.6809,
|
| 914 |
+
"step": 75500
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 9.59,
|
| 918 |
+
"learning_rate": 2.062570960010092e-06,
|
| 919 |
+
"loss": 4.6689,
|
| 920 |
+
"step": 76000
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 9.65,
|
| 924 |
+
"learning_rate": 1.7471931373785799e-06,
|
| 925 |
+
"loss": 4.6579,
|
| 926 |
+
"step": 76500
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 9.71,
|
| 930 |
+
"learning_rate": 1.431815314747067e-06,
|
| 931 |
+
"loss": 4.6334,
|
| 932 |
+
"step": 77000
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 9.78,
|
| 936 |
+
"learning_rate": 1.1164374921155544e-06,
|
| 937 |
+
"loss": 4.6372,
|
| 938 |
+
"step": 77500
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 9.84,
|
| 942 |
+
"learning_rate": 8.01059669484042e-07,
|
| 943 |
+
"loss": 4.6378,
|
| 944 |
+
"step": 78000
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 9.9,
|
| 948 |
+
"learning_rate": 4.856818468525293e-07,
|
| 949 |
+
"loss": 4.6323,
|
| 950 |
+
"step": 78500
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 9.97,
|
| 954 |
+
"learning_rate": 1.7030402422101678e-07,
|
| 955 |
+
"loss": 4.6307,
|
| 956 |
+
"step": 79000
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 10.0,
|
| 960 |
+
"step": 79270,
|
| 961 |
+
"total_flos": 4.675970241591091e+17,
|
| 962 |
+
"train_loss": 2.0376459330797827,
|
| 963 |
+
"train_runtime": 6961.2818,
|
| 964 |
+
"train_samples_per_second": 364.373,
|
| 965 |
+
"train_steps_per_second": 11.387
|
| 966 |
}
|
| 967 |
],
|
| 968 |
+
"max_steps": 79270,
|
| 969 |
+
"num_train_epochs": 10,
|
| 970 |
+
"total_flos": 4.675970241591091e+17,
|
| 971 |
"trial_name": null,
|
| 972 |
"trial_params": null
|
| 973 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3247
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3078cc244d536a8e922884b143b7b3668c2b157ea7e14f35d8933d887ab2d074
|
| 3 |
size 3247
|