Commit
·
8f59c29
1
Parent(s):
a66b2ca
Training in progress, step 57000
Browse files- adapter_model.bin +1 -1
- {checkpoint-53000 → checkpoint-56000/adapter_model}/README.md +0 -0
- {checkpoint-53000 → checkpoint-56000/adapter_model}/adapter_config.json +0 -0
- {checkpoint-53000 → checkpoint-56000/adapter_model}/adapter_model.bin +1 -1
- {checkpoint-53000/adapter_model → checkpoint-57000}/README.md +0 -0
- {checkpoint-53000/adapter_model → checkpoint-57000}/adapter_config.json +0 -0
- {checkpoint-53000/adapter_model → checkpoint-57000}/adapter_model.bin +1 -1
- {checkpoint-53000 → checkpoint-57000}/optimizer.pt +1 -1
- {checkpoint-53000 → checkpoint-57000}/rng_state.pth +1 -1
- {checkpoint-53000 → checkpoint-57000}/scheduler.pt +1 -1
- {checkpoint-53000 → checkpoint-57000}/trainer_state.json +277 -5
- {checkpoint-53000 → checkpoint-57000}/training_args.bin +0 -0
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 500897101
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9463fbc37a2c37f850b2aa713212bd675cce373b2a226f9fecf647f60157d1a1
|
| 3 |
size 500897101
|
{checkpoint-53000 → checkpoint-56000/adapter_model}/README.md
RENAMED
|
File without changes
|
{checkpoint-53000 → checkpoint-56000/adapter_model}/adapter_config.json
RENAMED
|
File without changes
|
{checkpoint-53000 → checkpoint-56000/adapter_model}/adapter_model.bin
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 500897101
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d61b2ab661f17f1b28e07a6ea4c559efd2487b69440f512fbda902147b2007f
|
| 3 |
size 500897101
|
{checkpoint-53000/adapter_model → checkpoint-57000}/README.md
RENAMED
|
File without changes
|
{checkpoint-53000/adapter_model → checkpoint-57000}/adapter_config.json
RENAMED
|
File without changes
|
{checkpoint-53000/adapter_model → checkpoint-57000}/adapter_model.bin
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 500897101
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9463fbc37a2c37f850b2aa713212bd675cce373b2a226f9fecf647f60157d1a1
|
| 3 |
size 500897101
|
{checkpoint-53000 → checkpoint-57000}/optimizer.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1001723453
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d85e0cce4ea774ece1bba3b083129dd4ea4f075278346655fd271c9663edf7a0
|
| 3 |
size 1001723453
|
{checkpoint-53000 → checkpoint-57000}/rng_state.pth
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7b0ae395ccd0b4875fa94f8cd4ee3274662f44279f744979610604a15d72da0
|
| 3 |
size 14575
|
{checkpoint-53000 → checkpoint-57000}/scheduler.pt
RENAMED
|
@@ -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 sha256:7c18b73ff8e0ca9bda5d92134e841aafa154377e996a5dd3b1b1a3a0b329e74e
|
| 3 |
size 627
|
{checkpoint-53000 → checkpoint-57000}/trainer_state.json
RENAMED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "./qlora-out/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -3610,11 +3610,283 @@
|
|
| 3610 |
"eval_samples_per_second": 0.439,
|
| 3611 |
"eval_steps_per_second": 0.439,
|
| 3612 |
"step": 53000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3613 |
}
|
| 3614 |
],
|
| 3615 |
"max_steps": 80463,
|
| 3616 |
"num_train_epochs": 3,
|
| 3617 |
-
"total_flos": 1.
|
| 3618 |
"trial_name": null,
|
| 3619 |
"trial_params": null
|
| 3620 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.49361398816108704,
|
| 3 |
+
"best_model_checkpoint": "./qlora-out/checkpoint-57000",
|
| 4 |
+
"epoch": 2.12520040266955,
|
| 5 |
+
"global_step": 57000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 3610 |
"eval_samples_per_second": 0.439,
|
| 3611 |
"eval_steps_per_second": 0.439,
|
| 3612 |
"step": 53000
|
| 3613 |
+
},
|
| 3614 |
+
{
|
| 3615 |
+
"epoch": 1.98,
|
| 3616 |
+
"learning_rate": 5.185536396102946e-05,
|
| 3617 |
+
"loss": 0.4352,
|
| 3618 |
+
"step": 53100
|
| 3619 |
+
},
|
| 3620 |
+
{
|
| 3621 |
+
"epoch": 1.98,
|
| 3622 |
+
"learning_rate": 5.1513478749077274e-05,
|
| 3623 |
+
"loss": 0.4801,
|
| 3624 |
+
"step": 53200
|
| 3625 |
+
},
|
| 3626 |
+
{
|
| 3627 |
+
"epoch": 1.99,
|
| 3628 |
+
"learning_rate": 5.1172332862706376e-05,
|
| 3629 |
+
"loss": 0.4315,
|
| 3630 |
+
"step": 53300
|
| 3631 |
+
},
|
| 3632 |
+
{
|
| 3633 |
+
"epoch": 1.99,
|
| 3634 |
+
"learning_rate": 5.0831931503731065e-05,
|
| 3635 |
+
"loss": 0.4443,
|
| 3636 |
+
"step": 53400
|
| 3637 |
+
},
|
| 3638 |
+
{
|
| 3639 |
+
"epoch": 1.99,
|
| 3640 |
+
"learning_rate": 5.049227986261302e-05,
|
| 3641 |
+
"loss": 0.4597,
|
| 3642 |
+
"step": 53500
|
| 3643 |
+
},
|
| 3644 |
+
{
|
| 3645 |
+
"epoch": 2.0,
|
| 3646 |
+
"learning_rate": 5.0153383118382355e-05,
|
| 3647 |
+
"loss": 0.4519,
|
| 3648 |
+
"step": 53600
|
| 3649 |
+
},
|
| 3650 |
+
{
|
| 3651 |
+
"epoch": 2.0,
|
| 3652 |
+
"learning_rate": 4.9815246438558264e-05,
|
| 3653 |
+
"loss": 0.4314,
|
| 3654 |
+
"step": 53700
|
| 3655 |
+
},
|
| 3656 |
+
{
|
| 3657 |
+
"epoch": 2.01,
|
| 3658 |
+
"learning_rate": 4.9477874979070474e-05,
|
| 3659 |
+
"loss": 0.3999,
|
| 3660 |
+
"step": 53800
|
| 3661 |
+
},
|
| 3662 |
+
{
|
| 3663 |
+
"epoch": 2.01,
|
| 3664 |
+
"learning_rate": 4.914127388418062e-05,
|
| 3665 |
+
"loss": 0.3937,
|
| 3666 |
+
"step": 53900
|
| 3667 |
+
},
|
| 3668 |
+
{
|
| 3669 |
+
"epoch": 2.01,
|
| 3670 |
+
"learning_rate": 4.880544828640372e-05,
|
| 3671 |
+
"loss": 0.3597,
|
| 3672 |
+
"step": 54000
|
| 3673 |
+
},
|
| 3674 |
+
{
|
| 3675 |
+
"epoch": 2.01,
|
| 3676 |
+
"eval_loss": 0.49871668219566345,
|
| 3677 |
+
"eval_runtime": 1230.6045,
|
| 3678 |
+
"eval_samples_per_second": 0.44,
|
| 3679 |
+
"eval_steps_per_second": 0.44,
|
| 3680 |
+
"step": 54000
|
| 3681 |
+
},
|
| 3682 |
+
{
|
| 3683 |
+
"epoch": 2.02,
|
| 3684 |
+
"learning_rate": 4.8470403306430056e-05,
|
| 3685 |
+
"loss": 0.4075,
|
| 3686 |
+
"step": 54100
|
| 3687 |
+
},
|
| 3688 |
+
{
|
| 3689 |
+
"epoch": 2.02,
|
| 3690 |
+
"learning_rate": 4.813614405304693e-05,
|
| 3691 |
+
"loss": 0.383,
|
| 3692 |
+
"step": 54200
|
| 3693 |
+
},
|
| 3694 |
+
{
|
| 3695 |
+
"epoch": 2.02,
|
| 3696 |
+
"learning_rate": 4.780267562306081e-05,
|
| 3697 |
+
"loss": 0.3833,
|
| 3698 |
+
"step": 54300
|
| 3699 |
+
},
|
| 3700 |
+
{
|
| 3701 |
+
"epoch": 2.03,
|
| 3702 |
+
"learning_rate": 4.7470003101219664e-05,
|
| 3703 |
+
"loss": 0.3828,
|
| 3704 |
+
"step": 54400
|
| 3705 |
+
},
|
| 3706 |
+
{
|
| 3707 |
+
"epoch": 2.03,
|
| 3708 |
+
"learning_rate": 4.713813156013548e-05,
|
| 3709 |
+
"loss": 0.3864,
|
| 3710 |
+
"step": 54500
|
| 3711 |
+
},
|
| 3712 |
+
{
|
| 3713 |
+
"epoch": 2.04,
|
| 3714 |
+
"learning_rate": 4.680706606020668e-05,
|
| 3715 |
+
"loss": 0.3805,
|
| 3716 |
+
"step": 54600
|
| 3717 |
+
},
|
| 3718 |
+
{
|
| 3719 |
+
"epoch": 2.04,
|
| 3720 |
+
"learning_rate": 4.64768116495413e-05,
|
| 3721 |
+
"loss": 0.3934,
|
| 3722 |
+
"step": 54700
|
| 3723 |
+
},
|
| 3724 |
+
{
|
| 3725 |
+
"epoch": 2.04,
|
| 3726 |
+
"learning_rate": 4.61473733638797e-05,
|
| 3727 |
+
"loss": 0.3842,
|
| 3728 |
+
"step": 54800
|
| 3729 |
+
},
|
| 3730 |
+
{
|
| 3731 |
+
"epoch": 2.05,
|
| 3732 |
+
"learning_rate": 4.5818756226517924e-05,
|
| 3733 |
+
"loss": 0.3783,
|
| 3734 |
+
"step": 54900
|
| 3735 |
+
},
|
| 3736 |
+
{
|
| 3737 |
+
"epoch": 2.05,
|
| 3738 |
+
"learning_rate": 4.54909652482312e-05,
|
| 3739 |
+
"loss": 0.3912,
|
| 3740 |
+
"step": 55000
|
| 3741 |
+
},
|
| 3742 |
+
{
|
| 3743 |
+
"epoch": 2.05,
|
| 3744 |
+
"eval_loss": 0.49695634841918945,
|
| 3745 |
+
"eval_runtime": 1220.9853,
|
| 3746 |
+
"eval_samples_per_second": 0.444,
|
| 3747 |
+
"eval_steps_per_second": 0.444,
|
| 3748 |
+
"step": 55000
|
| 3749 |
+
},
|
| 3750 |
+
{
|
| 3751 |
+
"epoch": 2.05,
|
| 3752 |
+
"learning_rate": 4.516400542719733e-05,
|
| 3753 |
+
"loss": 0.3941,
|
| 3754 |
+
"step": 55100
|
| 3755 |
+
},
|
| 3756 |
+
{
|
| 3757 |
+
"epoch": 2.06,
|
| 3758 |
+
"learning_rate": 4.4837881748920594e-05,
|
| 3759 |
+
"loss": 0.366,
|
| 3760 |
+
"step": 55200
|
| 3761 |
+
},
|
| 3762 |
+
{
|
| 3763 |
+
"epoch": 2.06,
|
| 3764 |
+
"learning_rate": 4.451259918615569e-05,
|
| 3765 |
+
"loss": 0.4203,
|
| 3766 |
+
"step": 55300
|
| 3767 |
+
},
|
| 3768 |
+
{
|
| 3769 |
+
"epoch": 2.07,
|
| 3770 |
+
"learning_rate": 4.418816269883204e-05,
|
| 3771 |
+
"loss": 0.3613,
|
| 3772 |
+
"step": 55400
|
| 3773 |
+
},
|
| 3774 |
+
{
|
| 3775 |
+
"epoch": 2.07,
|
| 3776 |
+
"learning_rate": 4.386457723397794e-05,
|
| 3777 |
+
"loss": 0.3825,
|
| 3778 |
+
"step": 55500
|
| 3779 |
+
},
|
| 3780 |
+
{
|
| 3781 |
+
"epoch": 2.07,
|
| 3782 |
+
"learning_rate": 4.354184772564526e-05,
|
| 3783 |
+
"loss": 0.4147,
|
| 3784 |
+
"step": 55600
|
| 3785 |
+
},
|
| 3786 |
+
{
|
| 3787 |
+
"epoch": 2.08,
|
| 3788 |
+
"learning_rate": 4.3219979094834275e-05,
|
| 3789 |
+
"loss": 0.3812,
|
| 3790 |
+
"step": 55700
|
| 3791 |
+
},
|
| 3792 |
+
{
|
| 3793 |
+
"epoch": 2.08,
|
| 3794 |
+
"learning_rate": 4.289897624941841e-05,
|
| 3795 |
+
"loss": 0.3926,
|
| 3796 |
+
"step": 55800
|
| 3797 |
+
},
|
| 3798 |
+
{
|
| 3799 |
+
"epoch": 2.08,
|
| 3800 |
+
"learning_rate": 4.257884408406968e-05,
|
| 3801 |
+
"loss": 0.4103,
|
| 3802 |
+
"step": 55900
|
| 3803 |
+
},
|
| 3804 |
+
{
|
| 3805 |
+
"epoch": 2.09,
|
| 3806 |
+
"learning_rate": 4.225958748018381e-05,
|
| 3807 |
+
"loss": 0.4009,
|
| 3808 |
+
"step": 56000
|
| 3809 |
+
},
|
| 3810 |
+
{
|
| 3811 |
+
"epoch": 2.09,
|
| 3812 |
+
"eval_loss": 0.49594032764434814,
|
| 3813 |
+
"eval_runtime": 1218.3341,
|
| 3814 |
+
"eval_samples_per_second": 0.445,
|
| 3815 |
+
"eval_steps_per_second": 0.445,
|
| 3816 |
+
"step": 56000
|
| 3817 |
+
},
|
| 3818 |
+
{
|
| 3819 |
+
"epoch": 2.09,
|
| 3820 |
+
"learning_rate": 4.194121130580594e-05,
|
| 3821 |
+
"loss": 0.3779,
|
| 3822 |
+
"step": 56100
|
| 3823 |
+
},
|
| 3824 |
+
{
|
| 3825 |
+
"epoch": 2.1,
|
| 3826 |
+
"learning_rate": 4.1623720415556336e-05,
|
| 3827 |
+
"loss": 0.3651,
|
| 3828 |
+
"step": 56200
|
| 3829 |
+
},
|
| 3830 |
+
{
|
| 3831 |
+
"epoch": 2.1,
|
| 3832 |
+
"learning_rate": 4.1307119650556494e-05,
|
| 3833 |
+
"loss": 0.3754,
|
| 3834 |
+
"step": 56300
|
| 3835 |
+
},
|
| 3836 |
+
{
|
| 3837 |
+
"epoch": 2.1,
|
| 3838 |
+
"learning_rate": 4.099141383835512e-05,
|
| 3839 |
+
"loss": 0.3887,
|
| 3840 |
+
"step": 56400
|
| 3841 |
+
},
|
| 3842 |
+
{
|
| 3843 |
+
"epoch": 2.11,
|
| 3844 |
+
"learning_rate": 4.067660779285465e-05,
|
| 3845 |
+
"loss": 0.3739,
|
| 3846 |
+
"step": 56500
|
| 3847 |
+
},
|
| 3848 |
+
{
|
| 3849 |
+
"epoch": 2.11,
|
| 3850 |
+
"learning_rate": 4.036270631423781e-05,
|
| 3851 |
+
"loss": 0.3842,
|
| 3852 |
+
"step": 56600
|
| 3853 |
+
},
|
| 3854 |
+
{
|
| 3855 |
+
"epoch": 2.11,
|
| 3856 |
+
"learning_rate": 4.004971418889447e-05,
|
| 3857 |
+
"loss": 0.3723,
|
| 3858 |
+
"step": 56700
|
| 3859 |
+
},
|
| 3860 |
+
{
|
| 3861 |
+
"epoch": 2.12,
|
| 3862 |
+
"learning_rate": 3.9737636189348634e-05,
|
| 3863 |
+
"loss": 0.3889,
|
| 3864 |
+
"step": 56800
|
| 3865 |
+
},
|
| 3866 |
+
{
|
| 3867 |
+
"epoch": 2.12,
|
| 3868 |
+
"learning_rate": 3.942647707418561e-05,
|
| 3869 |
+
"loss": 0.3897,
|
| 3870 |
+
"step": 56900
|
| 3871 |
+
},
|
| 3872 |
+
{
|
| 3873 |
+
"epoch": 2.13,
|
| 3874 |
+
"learning_rate": 3.9116241587979496e-05,
|
| 3875 |
+
"loss": 0.3592,
|
| 3876 |
+
"step": 57000
|
| 3877 |
+
},
|
| 3878 |
+
{
|
| 3879 |
+
"epoch": 2.13,
|
| 3880 |
+
"eval_loss": 0.49361398816108704,
|
| 3881 |
+
"eval_runtime": 1208.1063,
|
| 3882 |
+
"eval_samples_per_second": 0.449,
|
| 3883 |
+
"eval_steps_per_second": 0.449,
|
| 3884 |
+
"step": 57000
|
| 3885 |
}
|
| 3886 |
],
|
| 3887 |
"max_steps": 80463,
|
| 3888 |
"num_train_epochs": 3,
|
| 3889 |
+
"total_flos": 1.5981607298407956e+19,
|
| 3890 |
"trial_name": null,
|
| 3891 |
"trial_params": null
|
| 3892 |
}
|
{checkpoint-53000 → checkpoint-57000}/training_args.bin
RENAMED
|
File without changes
|