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 541154336
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:279e32c6f744dd4b5ca0a4e0bdac260e9eb02f261d15119109be31afee7016e6
|
| 3 |
size 541154336
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1082379659
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1a242dc9694cfbb9560ec117c694c45ba481f843b0c63ef925a82069fa1e1ba
|
| 3 |
size 1082379659
|
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:d8e9bb6fca478bc46cc9aedfa2ff02f10ac93eb3ef848bec3ae25bcbbb5f8b50
|
| 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 sha256:71595add9463a6fb13f2baa718469da29cdbbd86c903fff1dc29e53d6a8513e1
|
| 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": 36.675,
|
| 3753 |
"eval_steps_per_second": 9.169,
|
| 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": 0.6753246753246753,
|
| 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": 36.675,
|
| 3753 |
"eval_steps_per_second": 9.169,
|
| 3754 |
"step": 48000
|
| 3755 |
+
},
|
| 3756 |
+
{
|
| 3757 |
+
"epoch": 0.6246753246753247,
|
| 3758 |
+
"grad_norm": 0.2436034381389618,
|
| 3759 |
+
"learning_rate": 0.0006062487050017348,
|
| 3760 |
+
"loss": 2.7583,
|
| 3761 |
+
"step": 48100
|
| 3762 |
+
},
|
| 3763 |
+
{
|
| 3764 |
+
"epoch": 0.625974025974026,
|
| 3765 |
+
"grad_norm": 0.25060826539993286,
|
| 3766 |
+
"learning_rate": 0.0006048394337614477,
|
| 3767 |
+
"loss": 2.7889,
|
| 3768 |
+
"step": 48200
|
| 3769 |
+
},
|
| 3770 |
+
{
|
| 3771 |
+
"epoch": 0.6272727272727273,
|
| 3772 |
+
"grad_norm": 0.23102222383022308,
|
| 3773 |
+
"learning_rate": 0.0006034292908159502,
|
| 3774 |
+
"loss": 2.777,
|
| 3775 |
+
"step": 48300
|
| 3776 |
+
},
|
| 3777 |
+
{
|
| 3778 |
+
"epoch": 0.6285714285714286,
|
| 3779 |
+
"grad_norm": 0.2651401460170746,
|
| 3780 |
+
"learning_rate": 0.000602018287890114,
|
| 3781 |
+
"loss": 2.753,
|
| 3782 |
+
"step": 48400
|
| 3783 |
+
},
|
| 3784 |
+
{
|
| 3785 |
+
"epoch": 0.6298701298701299,
|
| 3786 |
+
"grad_norm": 0.2365243136882782,
|
| 3787 |
+
"learning_rate": 0.000600606436715962,
|
| 3788 |
+
"loss": 2.7541,
|
| 3789 |
+
"step": 48500
|
| 3790 |
+
},
|
| 3791 |
+
{
|
| 3792 |
+
"epoch": 0.6311688311688312,
|
| 3793 |
+
"grad_norm": 0.2493165135383606,
|
| 3794 |
+
"learning_rate": 0.0005991937490325696,
|
| 3795 |
+
"loss": 2.7529,
|
| 3796 |
+
"step": 48600
|
| 3797 |
+
},
|
| 3798 |
+
{
|
| 3799 |
+
"epoch": 0.6324675324675325,
|
| 3800 |
+
"grad_norm": 0.24916312098503113,
|
| 3801 |
+
"learning_rate": 0.0005977802365859677,
|
| 3802 |
+
"loss": 2.7335,
|
| 3803 |
+
"step": 48700
|
| 3804 |
+
},
|
| 3805 |
+
{
|
| 3806 |
+
"epoch": 0.6337662337662338,
|
| 3807 |
+
"grad_norm": 0.38456228375434875,
|
| 3808 |
+
"learning_rate": 0.0005963659111290444,
|
| 3809 |
+
"loss": 2.7492,
|
| 3810 |
+
"step": 48800
|
| 3811 |
+
},
|
| 3812 |
+
{
|
| 3813 |
+
"epoch": 0.6350649350649351,
|
| 3814 |
+
"grad_norm": 0.23968328535556793,
|
| 3815 |
+
"learning_rate": 0.0005949507844214482,
|
| 3816 |
+
"loss": 2.729,
|
| 3817 |
+
"step": 48900
|
| 3818 |
+
},
|
| 3819 |
+
{
|
| 3820 |
+
"epoch": 0.6363636363636364,
|
| 3821 |
+
"grad_norm": 0.27702993154525757,
|
| 3822 |
+
"learning_rate": 0.0005935348682294894,
|
| 3823 |
+
"loss": 2.7453,
|
| 3824 |
+
"step": 49000
|
| 3825 |
+
},
|
| 3826 |
+
{
|
| 3827 |
+
"epoch": 0.6363636363636364,
|
| 3828 |
+
"eval_loss": 3.0973825454711914,
|
| 3829 |
+
"eval_runtime": 15.2932,
|
| 3830 |
+
"eval_samples_per_second": 37.664,
|
| 3831 |
+
"eval_steps_per_second": 9.416,
|
| 3832 |
+
"step": 49000
|
| 3833 |
+
},
|
| 3834 |
+
{
|
| 3835 |
+
"epoch": 0.6376623376623377,
|
| 3836 |
+
"grad_norm": 0.2538464367389679,
|
| 3837 |
+
"learning_rate": 0.000592118174326043,
|
| 3838 |
+
"loss": 2.7291,
|
| 3839 |
+
"step": 49100
|
| 3840 |
+
},
|
| 3841 |
+
{
|
| 3842 |
+
"epoch": 0.638961038961039,
|
| 3843 |
+
"grad_norm": 0.27856433391571045,
|
| 3844 |
+
"learning_rate": 0.0005907007144904501,
|
| 3845 |
+
"loss": 2.7324,
|
| 3846 |
+
"step": 49200
|
| 3847 |
+
},
|
| 3848 |
+
{
|
| 3849 |
+
"epoch": 0.6402597402597403,
|
| 3850 |
+
"grad_norm": 0.26114940643310547,
|
| 3851 |
+
"learning_rate": 0.0005892825005084202,
|
| 3852 |
+
"loss": 2.7777,
|
| 3853 |
+
"step": 49300
|
| 3854 |
+
},
|
| 3855 |
+
{
|
| 3856 |
+
"epoch": 0.6415584415584416,
|
| 3857 |
+
"grad_norm": 0.25457167625427246,
|
| 3858 |
+
"learning_rate": 0.0005878635441719333,
|
| 3859 |
+
"loss": 2.7273,
|
| 3860 |
+
"step": 49400
|
| 3861 |
+
},
|
| 3862 |
+
{
|
| 3863 |
+
"epoch": 0.6428571428571429,
|
| 3864 |
+
"grad_norm": 0.24550481140613556,
|
| 3865 |
+
"learning_rate": 0.0005864438572791422,
|
| 3866 |
+
"loss": 2.7641,
|
| 3867 |
+
"step": 49500
|
| 3868 |
+
},
|
| 3869 |
+
{
|
| 3870 |
+
"epoch": 0.6441558441558441,
|
| 3871 |
+
"grad_norm": 0.2586402893066406,
|
| 3872 |
+
"learning_rate": 0.0005850234516342739,
|
| 3873 |
+
"loss": 2.7115,
|
| 3874 |
+
"step": 49600
|
| 3875 |
+
},
|
| 3876 |
+
{
|
| 3877 |
+
"epoch": 0.6454545454545455,
|
| 3878 |
+
"grad_norm": 0.25716432929039,
|
| 3879 |
+
"learning_rate": 0.000583602339047531,
|
| 3880 |
+
"loss": 2.7164,
|
| 3881 |
+
"step": 49700
|
| 3882 |
+
},
|
| 3883 |
+
{
|
| 3884 |
+
"epoch": 0.6467532467532467,
|
| 3885 |
+
"grad_norm": 0.26527953147888184,
|
| 3886 |
+
"learning_rate": 0.0005821805313349947,
|
| 3887 |
+
"loss": 2.752,
|
| 3888 |
+
"step": 49800
|
| 3889 |
+
},
|
| 3890 |
+
{
|
| 3891 |
+
"epoch": 0.6480519480519481,
|
| 3892 |
+
"grad_norm": 0.24985221028327942,
|
| 3893 |
+
"learning_rate": 0.000580758040318526,
|
| 3894 |
+
"loss": 2.7468,
|
| 3895 |
+
"step": 49900
|
| 3896 |
+
},
|
| 3897 |
+
{
|
| 3898 |
+
"epoch": 0.6493506493506493,
|
| 3899 |
+
"grad_norm": 0.23009921610355377,
|
| 3900 |
+
"learning_rate": 0.0005793348778256671,
|
| 3901 |
+
"loss": 2.7323,
|
| 3902 |
+
"step": 50000
|
| 3903 |
+
},
|
| 3904 |
+
{
|
| 3905 |
+
"epoch": 0.6493506493506493,
|
| 3906 |
+
"eval_loss": 3.0897603034973145,
|
| 3907 |
+
"eval_runtime": 14.9478,
|
| 3908 |
+
"eval_samples_per_second": 38.534,
|
| 3909 |
+
"eval_steps_per_second": 9.634,
|
| 3910 |
+
"step": 50000
|
| 3911 |
+
},
|
| 3912 |
+
{
|
| 3913 |
+
"epoch": 0.6506493506493507,
|
| 3914 |
+
"grad_norm": 0.227068230509758,
|
| 3915 |
+
"learning_rate": 0.0005779110556895433,
|
| 3916 |
+
"loss": 2.7248,
|
| 3917 |
+
"step": 50100
|
| 3918 |
+
},
|
| 3919 |
+
{
|
| 3920 |
+
"epoch": 0.6519480519480519,
|
| 3921 |
+
"grad_norm": 0.22547580301761627,
|
| 3922 |
+
"learning_rate": 0.0005764865857487646,
|
| 3923 |
+
"loss": 2.7372,
|
| 3924 |
+
"step": 50200
|
| 3925 |
+
},
|
| 3926 |
+
{
|
| 3927 |
+
"epoch": 0.6532467532467533,
|
| 3928 |
+
"grad_norm": 0.2620651423931122,
|
| 3929 |
+
"learning_rate": 0.0005750614798473273,
|
| 3930 |
+
"loss": 2.7249,
|
| 3931 |
+
"step": 50300
|
| 3932 |
+
},
|
| 3933 |
+
{
|
| 3934 |
+
"epoch": 0.6545454545454545,
|
| 3935 |
+
"grad_norm": 0.26259052753448486,
|
| 3936 |
+
"learning_rate": 0.0005736357498345156,
|
| 3937 |
+
"loss": 2.6864,
|
| 3938 |
+
"step": 50400
|
| 3939 |
+
},
|
| 3940 |
+
{
|
| 3941 |
+
"epoch": 0.6558441558441559,
|
| 3942 |
+
"grad_norm": 0.24948278069496155,
|
| 3943 |
+
"learning_rate": 0.0005722094075648032,
|
| 3944 |
+
"loss": 2.7276,
|
| 3945 |
+
"step": 50500
|
| 3946 |
+
},
|
| 3947 |
+
{
|
| 3948 |
+
"epoch": 0.6571428571428571,
|
| 3949 |
+
"grad_norm": 0.23260965943336487,
|
| 3950 |
+
"learning_rate": 0.0005707824648977536,
|
| 3951 |
+
"loss": 2.7114,
|
| 3952 |
+
"step": 50600
|
| 3953 |
+
},
|
| 3954 |
+
{
|
| 3955 |
+
"epoch": 0.6584415584415585,
|
| 3956 |
+
"grad_norm": 0.253491073846817,
|
| 3957 |
+
"learning_rate": 0.0005693549336979236,
|
| 3958 |
+
"loss": 2.7156,
|
| 3959 |
+
"step": 50700
|
| 3960 |
+
},
|
| 3961 |
+
{
|
| 3962 |
+
"epoch": 0.6597402597402597,
|
| 3963 |
+
"grad_norm": 0.24990208446979523,
|
| 3964 |
+
"learning_rate": 0.0005679268258347626,
|
| 3965 |
+
"loss": 2.7319,
|
| 3966 |
+
"step": 50800
|
| 3967 |
+
},
|
| 3968 |
+
{
|
| 3969 |
+
"epoch": 0.6610389610389611,
|
| 3970 |
+
"grad_norm": 0.24773485958576202,
|
| 3971 |
+
"learning_rate": 0.0005664981531825152,
|
| 3972 |
+
"loss": 2.7356,
|
| 3973 |
+
"step": 50900
|
| 3974 |
+
},
|
| 3975 |
+
{
|
| 3976 |
+
"epoch": 0.6623376623376623,
|
| 3977 |
+
"grad_norm": 0.23747920989990234,
|
| 3978 |
+
"learning_rate": 0.0005650689276201219,
|
| 3979 |
+
"loss": 2.7497,
|
| 3980 |
+
"step": 51000
|
| 3981 |
+
},
|
| 3982 |
+
{
|
| 3983 |
+
"epoch": 0.6623376623376623,
|
| 3984 |
+
"eval_loss": 3.0903031826019287,
|
| 3985 |
+
"eval_runtime": 14.4116,
|
| 3986 |
+
"eval_samples_per_second": 39.968,
|
| 3987 |
+
"eval_steps_per_second": 9.992,
|
| 3988 |
+
"step": 51000
|
| 3989 |
+
},
|
| 3990 |
+
{
|
| 3991 |
+
"epoch": 0.6636363636363637,
|
| 3992 |
+
"grad_norm": 0.24378643929958344,
|
| 3993 |
+
"learning_rate": 0.0005636391610311204,
|
| 3994 |
+
"loss": 2.7239,
|
| 3995 |
+
"step": 51100
|
| 3996 |
+
},
|
| 3997 |
+
{
|
| 3998 |
+
"epoch": 0.6649350649350649,
|
| 3999 |
+
"grad_norm": 0.2741662561893463,
|
| 4000 |
+
"learning_rate": 0.0005622088653035469,
|
| 4001 |
+
"loss": 2.7161,
|
| 4002 |
+
"step": 51200
|
| 4003 |
+
},
|
| 4004 |
+
{
|
| 4005 |
+
"epoch": 0.6662337662337663,
|
| 4006 |
+
"grad_norm": 0.25329113006591797,
|
| 4007 |
+
"learning_rate": 0.0005607780523298372,
|
| 4008 |
+
"loss": 2.7301,
|
| 4009 |
+
"step": 51300
|
| 4010 |
+
},
|
| 4011 |
+
{
|
| 4012 |
+
"epoch": 0.6675324675324675,
|
| 4013 |
+
"grad_norm": 0.2747024893760681,
|
| 4014 |
+
"learning_rate": 0.0005593467340067282,
|
| 4015 |
+
"loss": 2.7312,
|
| 4016 |
+
"step": 51400
|
| 4017 |
+
},
|
| 4018 |
+
{
|
| 4019 |
+
"epoch": 0.6688311688311688,
|
| 4020 |
+
"grad_norm": 0.24558883905410767,
|
| 4021 |
+
"learning_rate": 0.0005579149222351577,
|
| 4022 |
+
"loss": 2.75,
|
| 4023 |
+
"step": 51500
|
| 4024 |
+
},
|
| 4025 |
+
{
|
| 4026 |
+
"epoch": 0.6701298701298701,
|
| 4027 |
+
"grad_norm": 0.24378612637519836,
|
| 4028 |
+
"learning_rate": 0.0005564826289201674,
|
| 4029 |
+
"loss": 2.742,
|
| 4030 |
+
"step": 51600
|
| 4031 |
+
},
|
| 4032 |
+
{
|
| 4033 |
+
"epoch": 0.6714285714285714,
|
| 4034 |
+
"grad_norm": 0.24434533715248108,
|
| 4035 |
+
"learning_rate": 0.0005550498659708022,
|
| 4036 |
+
"loss": 2.7085,
|
| 4037 |
+
"step": 51700
|
| 4038 |
+
},
|
| 4039 |
+
{
|
| 4040 |
+
"epoch": 0.6727272727272727,
|
| 4041 |
+
"grad_norm": 0.26504042744636536,
|
| 4042 |
+
"learning_rate": 0.000553616645300012,
|
| 4043 |
+
"loss": 2.7147,
|
| 4044 |
+
"step": 51800
|
| 4045 |
+
},
|
| 4046 |
+
{
|
| 4047 |
+
"epoch": 0.674025974025974,
|
| 4048 |
+
"grad_norm": 0.24731750786304474,
|
| 4049 |
+
"learning_rate": 0.0005521829788245528,
|
| 4050 |
+
"loss": 2.7433,
|
| 4051 |
+
"step": 51900
|
| 4052 |
+
},
|
| 4053 |
+
{
|
| 4054 |
+
"epoch": 0.6753246753246753,
|
| 4055 |
+
"grad_norm": 0.23254041373729706,
|
| 4056 |
+
"learning_rate": 0.0005507488784648869,
|
| 4057 |
+
"loss": 2.7326,
|
| 4058 |
+
"step": 52000
|
| 4059 |
+
},
|
| 4060 |
+
{
|
| 4061 |
+
"epoch": 0.6753246753246753,
|
| 4062 |
+
"eval_loss": 3.080451011657715,
|
| 4063 |
+
"eval_runtime": 18.0502,
|
| 4064 |
+
"eval_samples_per_second": 31.911,
|
| 4065 |
+
"eval_steps_per_second": 7.978,
|
| 4066 |
+
"step": 52000
|
| 4067 |
}
|
| 4068 |
],
|
| 4069 |
"logging_steps": 100,
|
|
|
|
| 4083 |
"attributes": {}
|
| 4084 |
}
|
| 4085 |
},
|
| 4086 |
+
"total_flos": 1.54800431824896e+18,
|
| 4087 |
"train_batch_size": 22,
|
| 4088 |
"trial_name": null,
|
| 4089 |
"trial_params": null
|