Training in progress, step 52000, 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 469337272
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e7ba8d2524bc9f928490251d5557e2326e4ee76b8165e53f83fb0334d18ddfe
|
| 3 |
size 469337272
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 938825803
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e7abd1b4dbd4f064e3df76d3ce96cc640fdb83fe12440e34c4e94de5dc9ac01
|
| 3 |
size 938825803
|
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 sha256:99fd3750e2e46b63e97783e1c2d11f0a6d652ae4d1ee48cc27594356ed0fe238
|
| 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:c8715411d67584e8b8ee5de5af78cfc1a263656fc2e3e52390a5b49a21234cc2
|
| 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": 1000,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -3752,6 +3752,318 @@
|
|
| 3752 |
"eval_samples_per_second": 77.404,
|
| 3753 |
"eval_steps_per_second": 19.351,
|
| 3754 |
"step": 48000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3755 |
}
|
| 3756 |
],
|
| 3757 |
"logging_steps": 100,
|
|
@@ -3771,7 +4083,7 @@
|
|
| 3771 |
"attributes": {}
|
| 3772 |
}
|
| 3773 |
},
|
| 3774 |
-
"total_flos": 1.
|
| 3775 |
"train_batch_size": 22,
|
| 3776 |
"trial_name": null,
|
| 3777 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.14545454545454545,
|
| 6 |
"eval_steps": 1000,
|
| 7 |
+
"global_step": 52000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3752 |
"eval_samples_per_second": 77.404,
|
| 3753 |
"eval_steps_per_second": 19.351,
|
| 3754 |
"step": 48000
|
| 3755 |
+
},
|
| 3756 |
+
{
|
| 3757 |
+
"epoch": 0.11,
|
| 3758 |
+
"grad_norm": 0.1616736799478531,
|
| 3759 |
+
"learning_rate": 0.0005990926493458485,
|
| 3760 |
+
"loss": 2.7104031372070314,
|
| 3761 |
+
"step": 48100
|
| 3762 |
+
},
|
| 3763 |
+
{
|
| 3764 |
+
"epoch": 0.11090909090909092,
|
| 3765 |
+
"grad_norm": 0.15068742632865906,
|
| 3766 |
+
"learning_rate": 0.0005976906630331684,
|
| 3767 |
+
"loss": 2.6817190551757815,
|
| 3768 |
+
"step": 48200
|
| 3769 |
+
},
|
| 3770 |
+
{
|
| 3771 |
+
"epoch": 0.11181818181818182,
|
| 3772 |
+
"grad_norm": 0.1564316600561142,
|
| 3773 |
+
"learning_rate": 0.0005962878777101768,
|
| 3774 |
+
"loss": 2.699707336425781,
|
| 3775 |
+
"step": 48300
|
| 3776 |
+
},
|
| 3777 |
+
{
|
| 3778 |
+
"epoch": 0.11272727272727273,
|
| 3779 |
+
"grad_norm": 0.1532757431268692,
|
| 3780 |
+
"learning_rate": 0.0005948843048502316,
|
| 3781 |
+
"loss": 2.7237933349609373,
|
| 3782 |
+
"step": 48400
|
| 3783 |
+
},
|
| 3784 |
+
{
|
| 3785 |
+
"epoch": 0.11363636363636363,
|
| 3786 |
+
"grad_norm": 0.18864984810352325,
|
| 3787 |
+
"learning_rate": 0.0005934799559331318,
|
| 3788 |
+
"loss": 2.7044161987304687,
|
| 3789 |
+
"step": 48500
|
| 3790 |
+
},
|
| 3791 |
+
{
|
| 3792 |
+
"epoch": 0.11454545454545455,
|
| 3793 |
+
"grad_norm": 0.1558079868555069,
|
| 3794 |
+
"learning_rate": 0.0005920748424450241,
|
| 3795 |
+
"loss": 2.7322943115234377,
|
| 3796 |
+
"step": 48600
|
| 3797 |
+
},
|
| 3798 |
+
{
|
| 3799 |
+
"epoch": 0.11545454545454545,
|
| 3800 |
+
"grad_norm": 0.14599354565143585,
|
| 3801 |
+
"learning_rate": 0.0005906689758783081,
|
| 3802 |
+
"loss": 2.6957037353515627,
|
| 3803 |
+
"step": 48700
|
| 3804 |
+
},
|
| 3805 |
+
{
|
| 3806 |
+
"epoch": 0.11636363636363636,
|
| 3807 |
+
"grad_norm": 0.16394606232643127,
|
| 3808 |
+
"learning_rate": 0.0005892623677315435,
|
| 3809 |
+
"loss": 2.735413818359375,
|
| 3810 |
+
"step": 48800
|
| 3811 |
+
},
|
| 3812 |
+
{
|
| 3813 |
+
"epoch": 0.11727272727272728,
|
| 3814 |
+
"grad_norm": 0.16016560792922974,
|
| 3815 |
+
"learning_rate": 0.0005878550295093547,
|
| 3816 |
+
"loss": 2.743086853027344,
|
| 3817 |
+
"step": 48900
|
| 3818 |
+
},
|
| 3819 |
+
{
|
| 3820 |
+
"epoch": 0.11818181818181818,
|
| 3821 |
+
"grad_norm": 0.1616428941488266,
|
| 3822 |
+
"learning_rate": 0.0005864469727223377,
|
| 3823 |
+
"loss": 2.6787353515625,
|
| 3824 |
+
"step": 49000
|
| 3825 |
+
},
|
| 3826 |
+
{
|
| 3827 |
+
"epoch": 0.11818181818181818,
|
| 3828 |
+
"eval_loss": 3.087231159210205,
|
| 3829 |
+
"eval_runtime": 7.451,
|
| 3830 |
+
"eval_samples_per_second": 77.305,
|
| 3831 |
+
"eval_steps_per_second": 19.326,
|
| 3832 |
+
"step": 49000
|
| 3833 |
+
},
|
| 3834 |
+
{
|
| 3835 |
+
"epoch": 0.1190909090909091,
|
| 3836 |
+
"grad_norm": 0.1776418387889862,
|
| 3837 |
+
"learning_rate": 0.0005850382088869656,
|
| 3838 |
+
"loss": 2.6989129638671874,
|
| 3839 |
+
"step": 49100
|
| 3840 |
+
},
|
| 3841 |
+
{
|
| 3842 |
+
"epoch": 0.12,
|
| 3843 |
+
"grad_norm": 0.14982151985168457,
|
| 3844 |
+
"learning_rate": 0.0005836287495254947,
|
| 3845 |
+
"loss": 2.6925369262695313,
|
| 3846 |
+
"step": 49200
|
| 3847 |
+
},
|
| 3848 |
+
{
|
| 3849 |
+
"epoch": 0.12090909090909091,
|
| 3850 |
+
"grad_norm": 0.15882854163646698,
|
| 3851 |
+
"learning_rate": 0.0005822186061658693,
|
| 3852 |
+
"loss": 2.7088381958007814,
|
| 3853 |
+
"step": 49300
|
| 3854 |
+
},
|
| 3855 |
+
{
|
| 3856 |
+
"epoch": 0.12181818181818181,
|
| 3857 |
+
"grad_norm": 0.17874722182750702,
|
| 3858 |
+
"learning_rate": 0.0005808077903416286,
|
| 3859 |
+
"loss": 2.6966705322265625,
|
| 3860 |
+
"step": 49400
|
| 3861 |
+
},
|
| 3862 |
+
{
|
| 3863 |
+
"epoch": 0.12272727272727273,
|
| 3864 |
+
"grad_norm": 0.17074082791805267,
|
| 3865 |
+
"learning_rate": 0.0005793963135918122,
|
| 3866 |
+
"loss": 2.7259332275390626,
|
| 3867 |
+
"step": 49500
|
| 3868 |
+
},
|
| 3869 |
+
{
|
| 3870 |
+
"epoch": 0.12363636363636364,
|
| 3871 |
+
"grad_norm": 0.15236154198646545,
|
| 3872 |
+
"learning_rate": 0.0005779841874608646,
|
| 3873 |
+
"loss": 2.7060787963867186,
|
| 3874 |
+
"step": 49600
|
| 3875 |
+
},
|
| 3876 |
+
{
|
| 3877 |
+
"epoch": 0.12454545454545454,
|
| 3878 |
+
"grad_norm": 0.15823383629322052,
|
| 3879 |
+
"learning_rate": 0.0005765714234985422,
|
| 3880 |
+
"loss": 2.681339111328125,
|
| 3881 |
+
"step": 49700
|
| 3882 |
+
},
|
| 3883 |
+
{
|
| 3884 |
+
"epoch": 0.12545454545454546,
|
| 3885 |
+
"grad_norm": 0.21889136731624603,
|
| 3886 |
+
"learning_rate": 0.0005751580332598178,
|
| 3887 |
+
"loss": 2.693275146484375,
|
| 3888 |
+
"step": 49800
|
| 3889 |
+
},
|
| 3890 |
+
{
|
| 3891 |
+
"epoch": 0.12636363636363637,
|
| 3892 |
+
"grad_norm": 0.1490192860364914,
|
| 3893 |
+
"learning_rate": 0.000573744028304787,
|
| 3894 |
+
"loss": 2.6937310791015623,
|
| 3895 |
+
"step": 49900
|
| 3896 |
+
},
|
| 3897 |
+
{
|
| 3898 |
+
"epoch": 0.12727272727272726,
|
| 3899 |
+
"grad_norm": 0.1623009741306305,
|
| 3900 |
+
"learning_rate": 0.0005723294201985724,
|
| 3901 |
+
"loss": 2.678116760253906,
|
| 3902 |
+
"step": 50000
|
| 3903 |
+
},
|
| 3904 |
+
{
|
| 3905 |
+
"epoch": 0.12727272727272726,
|
| 3906 |
+
"eval_loss": 3.082812786102295,
|
| 3907 |
+
"eval_runtime": 7.4452,
|
| 3908 |
+
"eval_samples_per_second": 77.366,
|
| 3909 |
+
"eval_steps_per_second": 19.341,
|
| 3910 |
+
"step": 50000
|
| 3911 |
+
},
|
| 3912 |
+
{
|
| 3913 |
+
"epoch": 0.12818181818181817,
|
| 3914 |
+
"grad_norm": 0.1424219161272049,
|
| 3915 |
+
"learning_rate": 0.0005709142205112308,
|
| 3916 |
+
"loss": 2.690723876953125,
|
| 3917 |
+
"step": 50100
|
| 3918 |
+
},
|
| 3919 |
+
{
|
| 3920 |
+
"epoch": 0.1290909090909091,
|
| 3921 |
+
"grad_norm": 0.15792372822761536,
|
| 3922 |
+
"learning_rate": 0.0005694984408176566,
|
| 3923 |
+
"loss": 2.7299853515625,
|
| 3924 |
+
"step": 50200
|
| 3925 |
+
},
|
| 3926 |
+
{
|
| 3927 |
+
"epoch": 0.13,
|
| 3928 |
+
"grad_norm": 0.151839479804039,
|
| 3929 |
+
"learning_rate": 0.0005680820926974884,
|
| 3930 |
+
"loss": 2.665604248046875,
|
| 3931 |
+
"step": 50300
|
| 3932 |
+
},
|
| 3933 |
+
{
|
| 3934 |
+
"epoch": 0.13090909090909092,
|
| 3935 |
+
"grad_norm": 0.1519307941198349,
|
| 3936 |
+
"learning_rate": 0.0005666651877350139,
|
| 3937 |
+
"loss": 2.6907989501953127,
|
| 3938 |
+
"step": 50400
|
| 3939 |
+
},
|
| 3940 |
+
{
|
| 3941 |
+
"epoch": 0.1318181818181818,
|
| 3942 |
+
"grad_norm": 0.14843234419822693,
|
| 3943 |
+
"learning_rate": 0.0005652477375190755,
|
| 3944 |
+
"loss": 2.684622802734375,
|
| 3945 |
+
"step": 50500
|
| 3946 |
+
},
|
| 3947 |
+
{
|
| 3948 |
+
"epoch": 0.13272727272727272,
|
| 3949 |
+
"grad_norm": 0.1492377370595932,
|
| 3950 |
+
"learning_rate": 0.000563829753642975,
|
| 3951 |
+
"loss": 2.68843994140625,
|
| 3952 |
+
"step": 50600
|
| 3953 |
+
},
|
| 3954 |
+
{
|
| 3955 |
+
"epoch": 0.13363636363636364,
|
| 3956 |
+
"grad_norm": 0.1397194117307663,
|
| 3957 |
+
"learning_rate": 0.0005624112477043789,
|
| 3958 |
+
"loss": 2.6910018920898438,
|
| 3959 |
+
"step": 50700
|
| 3960 |
+
},
|
| 3961 |
+
{
|
| 3962 |
+
"epoch": 0.13454545454545455,
|
| 3963 |
+
"grad_norm": 0.14176790416240692,
|
| 3964 |
+
"learning_rate": 0.0005609922313052237,
|
| 3965 |
+
"loss": 2.6935055541992186,
|
| 3966 |
+
"step": 50800
|
| 3967 |
+
},
|
| 3968 |
+
{
|
| 3969 |
+
"epoch": 0.13545454545454547,
|
| 3970 |
+
"grad_norm": 0.16330276429653168,
|
| 3971 |
+
"learning_rate": 0.0005595727160516208,
|
| 3972 |
+
"loss": 2.6888656616210938,
|
| 3973 |
+
"step": 50900
|
| 3974 |
+
},
|
| 3975 |
+
{
|
| 3976 |
+
"epoch": 0.13636363636363635,
|
| 3977 |
+
"grad_norm": 0.1529064178466797,
|
| 3978 |
+
"learning_rate": 0.0005581527135537623,
|
| 3979 |
+
"loss": 2.709434814453125,
|
| 3980 |
+
"step": 51000
|
| 3981 |
+
},
|
| 3982 |
+
{
|
| 3983 |
+
"epoch": 0.13636363636363635,
|
| 3984 |
+
"eval_loss": 3.07966685295105,
|
| 3985 |
+
"eval_runtime": 7.3998,
|
| 3986 |
+
"eval_samples_per_second": 77.84,
|
| 3987 |
+
"eval_steps_per_second": 19.46,
|
| 3988 |
+
"step": 51000
|
| 3989 |
+
},
|
| 3990 |
+
{
|
| 3991 |
+
"epoch": 0.13727272727272727,
|
| 3992 |
+
"grad_norm": 0.1499529331922531,
|
| 3993 |
+
"learning_rate": 0.0005567322354258249,
|
| 3994 |
+
"loss": 2.694036560058594,
|
| 3995 |
+
"step": 51100
|
| 3996 |
+
},
|
| 3997 |
+
{
|
| 3998 |
+
"epoch": 0.13818181818181818,
|
| 3999 |
+
"grad_norm": 0.1941758096218109,
|
| 4000 |
+
"learning_rate": 0.0005553112932858754,
|
| 4001 |
+
"loss": 2.679619140625,
|
| 4002 |
+
"step": 51200
|
| 4003 |
+
},
|
| 4004 |
+
{
|
| 4005 |
+
"epoch": 0.1390909090909091,
|
| 4006 |
+
"grad_norm": 0.1703883409500122,
|
| 4007 |
+
"learning_rate": 0.0005538898987557763,
|
| 4008 |
+
"loss": 2.7490829467773437,
|
| 4009 |
+
"step": 51300
|
| 4010 |
+
},
|
| 4011 |
+
{
|
| 4012 |
+
"epoch": 0.14,
|
| 4013 |
+
"grad_norm": 0.1707204133272171,
|
| 4014 |
+
"learning_rate": 0.0005524680634610897,
|
| 4015 |
+
"loss": 2.701058349609375,
|
| 4016 |
+
"step": 51400
|
| 4017 |
+
},
|
| 4018 |
+
{
|
| 4019 |
+
"epoch": 0.1409090909090909,
|
| 4020 |
+
"grad_norm": 0.1748669594526291,
|
| 4021 |
+
"learning_rate": 0.0005510457990309829,
|
| 4022 |
+
"loss": 2.6962744140625,
|
| 4023 |
+
"step": 51500
|
| 4024 |
+
},
|
| 4025 |
+
{
|
| 4026 |
+
"epoch": 0.14181818181818182,
|
| 4027 |
+
"grad_norm": 0.16774185001850128,
|
| 4028 |
+
"learning_rate": 0.0005496231170981329,
|
| 4029 |
+
"loss": 2.6645233154296877,
|
| 4030 |
+
"step": 51600
|
| 4031 |
+
},
|
| 4032 |
+
{
|
| 4033 |
+
"epoch": 0.14272727272727273,
|
| 4034 |
+
"grad_norm": 0.15208636224269867,
|
| 4035 |
+
"learning_rate": 0.000548200029298632,
|
| 4036 |
+
"loss": 2.6871743774414063,
|
| 4037 |
+
"step": 51700
|
| 4038 |
+
},
|
| 4039 |
+
{
|
| 4040 |
+
"epoch": 0.14363636363636365,
|
| 4041 |
+
"grad_norm": 0.17048777639865875,
|
| 4042 |
+
"learning_rate": 0.0005467765472718914,
|
| 4043 |
+
"loss": 2.6941012573242187,
|
| 4044 |
+
"step": 51800
|
| 4045 |
+
},
|
| 4046 |
+
{
|
| 4047 |
+
"epoch": 0.14454545454545453,
|
| 4048 |
+
"grad_norm": 0.1853557974100113,
|
| 4049 |
+
"learning_rate": 0.000545352682660547,
|
| 4050 |
+
"loss": 2.669810791015625,
|
| 4051 |
+
"step": 51900
|
| 4052 |
+
},
|
| 4053 |
+
{
|
| 4054 |
+
"epoch": 0.14545454545454545,
|
| 4055 |
+
"grad_norm": 0.18524755537509918,
|
| 4056 |
+
"learning_rate": 0.0005439284471103641,
|
| 4057 |
+
"loss": 2.714384765625,
|
| 4058 |
+
"step": 52000
|
| 4059 |
+
},
|
| 4060 |
+
{
|
| 4061 |
+
"epoch": 0.14545454545454545,
|
| 4062 |
+
"eval_loss": 3.08223819732666,
|
| 4063 |
+
"eval_runtime": 7.441,
|
| 4064 |
+
"eval_samples_per_second": 77.409,
|
| 4065 |
+
"eval_steps_per_second": 19.352,
|
| 4066 |
+
"step": 52000
|
| 4067 |
}
|
| 4068 |
],
|
| 4069 |
"logging_steps": 100,
|
|
|
|
| 4083 |
"attributes": {}
|
| 4084 |
}
|
| 4085 |
},
|
| 4086 |
+
"total_flos": 1.295558211796992e+18,
|
| 4087 |
"train_batch_size": 22,
|
| 4088 |
"trial_name": null,
|
| 4089 |
"trial_params": null
|