Training in progress, step 23000, 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 301235464
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a89c4f48dabf89d1fc21772e7a1dc1e6cc0f954906bef9f4e533a0c70e16ee0b
|
| 3 |
size 301235464
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 602335994
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:363ed73f7ff31d612484ab3e02ee2db34b4cf1e7c3b74bd25f1240b2334fd50d
|
| 3 |
size 602335994
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa984124f826975d2e762cc5a5a6288e4a0450c71c7198693c0e6b43694d5846
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d95e34f92e07ac3fca3b42c6f704d96b3191058ad871fb9d07f6b2779013efbe
|
| 3 |
size 1064
|
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": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -3746,11 +3746,367 @@
|
|
| 3746 |
"eval_steps_per_second": 24.902,
|
| 3747 |
"num_input_tokens_seen": 5505024000,
|
| 3748 |
"step": 21000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3749 |
}
|
| 3750 |
],
|
| 3751 |
"logging_steps": 50,
|
| 3752 |
"max_steps": 70000,
|
| 3753 |
-
"num_input_tokens_seen":
|
| 3754 |
"num_train_epochs": 1,
|
| 3755 |
"save_steps": 1000,
|
| 3756 |
"stateful_callbacks": {
|
|
@@ -3765,7 +4121,7 @@
|
|
| 3765 |
"attributes": {}
|
| 3766 |
}
|
| 3767 |
},
|
| 3768 |
-
"total_flos": 1.
|
| 3769 |
"train_batch_size": 64,
|
| 3770 |
"trial_name": null,
|
| 3771 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.10971057872330277,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 23000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3746 |
"eval_steps_per_second": 24.902,
|
| 3747 |
"num_input_tokens_seen": 5505024000,
|
| 3748 |
"step": 21000
|
| 3749 |
+
},
|
| 3750 |
+
{
|
| 3751 |
+
"epoch": 0.10040902965763145,
|
| 3752 |
+
"grad_norm": 0.1723284274339676,
|
| 3753 |
+
"learning_rate": 0.001,
|
| 3754 |
+
"loss": 2.694,
|
| 3755 |
+
"num_input_tokens_seen": 5518131200,
|
| 3756 |
+
"step": 21050
|
| 3757 |
+
},
|
| 3758 |
+
{
|
| 3759 |
+
"epoch": 0.10064753091572558,
|
| 3760 |
+
"grad_norm": 0.1627894937992096,
|
| 3761 |
+
"learning_rate": 0.001,
|
| 3762 |
+
"loss": 2.6866,
|
| 3763 |
+
"num_input_tokens_seen": 5531238400,
|
| 3764 |
+
"step": 21100
|
| 3765 |
+
},
|
| 3766 |
+
{
|
| 3767 |
+
"epoch": 0.10088603217381972,
|
| 3768 |
+
"grad_norm": 0.20949719846248627,
|
| 3769 |
+
"learning_rate": 0.001,
|
| 3770 |
+
"loss": 2.6915,
|
| 3771 |
+
"num_input_tokens_seen": 5544345600,
|
| 3772 |
+
"step": 21150
|
| 3773 |
+
},
|
| 3774 |
+
{
|
| 3775 |
+
"epoch": 0.10112453343191385,
|
| 3776 |
+
"grad_norm": 0.1980736404657364,
|
| 3777 |
+
"learning_rate": 0.001,
|
| 3778 |
+
"loss": 2.7076,
|
| 3779 |
+
"num_input_tokens_seen": 5557452800,
|
| 3780 |
+
"step": 21200
|
| 3781 |
+
},
|
| 3782 |
+
{
|
| 3783 |
+
"epoch": 0.10136303469000799,
|
| 3784 |
+
"grad_norm": 0.20961201190948486,
|
| 3785 |
+
"learning_rate": 0.001,
|
| 3786 |
+
"loss": 2.6978,
|
| 3787 |
+
"num_input_tokens_seen": 5570560000,
|
| 3788 |
+
"step": 21250
|
| 3789 |
+
},
|
| 3790 |
+
{
|
| 3791 |
+
"epoch": 0.10160153594810213,
|
| 3792 |
+
"grad_norm": 0.18137700855731964,
|
| 3793 |
+
"learning_rate": 0.001,
|
| 3794 |
+
"loss": 2.7029,
|
| 3795 |
+
"num_input_tokens_seen": 5583667200,
|
| 3796 |
+
"step": 21300
|
| 3797 |
+
},
|
| 3798 |
+
{
|
| 3799 |
+
"epoch": 0.10184003720619626,
|
| 3800 |
+
"grad_norm": 0.17235560715198517,
|
| 3801 |
+
"learning_rate": 0.001,
|
| 3802 |
+
"loss": 2.6979,
|
| 3803 |
+
"num_input_tokens_seen": 5596774400,
|
| 3804 |
+
"step": 21350
|
| 3805 |
+
},
|
| 3806 |
+
{
|
| 3807 |
+
"epoch": 0.1020785384642904,
|
| 3808 |
+
"grad_norm": 0.17818449437618256,
|
| 3809 |
+
"learning_rate": 0.001,
|
| 3810 |
+
"loss": 2.6987,
|
| 3811 |
+
"num_input_tokens_seen": 5609881600,
|
| 3812 |
+
"step": 21400
|
| 3813 |
+
},
|
| 3814 |
+
{
|
| 3815 |
+
"epoch": 0.10231703972238454,
|
| 3816 |
+
"grad_norm": 0.1798463761806488,
|
| 3817 |
+
"learning_rate": 0.001,
|
| 3818 |
+
"loss": 2.693,
|
| 3819 |
+
"num_input_tokens_seen": 5622988800,
|
| 3820 |
+
"step": 21450
|
| 3821 |
+
},
|
| 3822 |
+
{
|
| 3823 |
+
"epoch": 0.10255554098047867,
|
| 3824 |
+
"grad_norm": 0.19028444588184357,
|
| 3825 |
+
"learning_rate": 0.001,
|
| 3826 |
+
"loss": 2.7079,
|
| 3827 |
+
"num_input_tokens_seen": 5636096000,
|
| 3828 |
+
"step": 21500
|
| 3829 |
+
},
|
| 3830 |
+
{
|
| 3831 |
+
"epoch": 0.10255554098047867,
|
| 3832 |
+
"eval_loss": 2.5816380977630615,
|
| 3833 |
+
"eval_runtime": 50.7808,
|
| 3834 |
+
"eval_samples_per_second": 98.462,
|
| 3835 |
+
"eval_steps_per_second": 24.616,
|
| 3836 |
+
"num_input_tokens_seen": 5636096000,
|
| 3837 |
+
"step": 21500
|
| 3838 |
+
},
|
| 3839 |
+
{
|
| 3840 |
+
"epoch": 0.1027940422385728,
|
| 3841 |
+
"grad_norm": 0.1831275075674057,
|
| 3842 |
+
"learning_rate": 0.001,
|
| 3843 |
+
"loss": 2.7038,
|
| 3844 |
+
"num_input_tokens_seen": 5649203200,
|
| 3845 |
+
"step": 21550
|
| 3846 |
+
},
|
| 3847 |
+
{
|
| 3848 |
+
"epoch": 0.10303254349666695,
|
| 3849 |
+
"grad_norm": 0.17404012382030487,
|
| 3850 |
+
"learning_rate": 0.001,
|
| 3851 |
+
"loss": 2.7071,
|
| 3852 |
+
"num_input_tokens_seen": 5662310400,
|
| 3853 |
+
"step": 21600
|
| 3854 |
+
},
|
| 3855 |
+
{
|
| 3856 |
+
"epoch": 0.10327104475476108,
|
| 3857 |
+
"grad_norm": 0.1652098149061203,
|
| 3858 |
+
"learning_rate": 0.001,
|
| 3859 |
+
"loss": 2.7033,
|
| 3860 |
+
"num_input_tokens_seen": 5675417600,
|
| 3861 |
+
"step": 21650
|
| 3862 |
+
},
|
| 3863 |
+
{
|
| 3864 |
+
"epoch": 0.10350954601285522,
|
| 3865 |
+
"grad_norm": 0.1914501190185547,
|
| 3866 |
+
"learning_rate": 0.001,
|
| 3867 |
+
"loss": 2.6844,
|
| 3868 |
+
"num_input_tokens_seen": 5688524800,
|
| 3869 |
+
"step": 21700
|
| 3870 |
+
},
|
| 3871 |
+
{
|
| 3872 |
+
"epoch": 0.10374804727094936,
|
| 3873 |
+
"grad_norm": 0.19169588387012482,
|
| 3874 |
+
"learning_rate": 0.001,
|
| 3875 |
+
"loss": 2.6793,
|
| 3876 |
+
"num_input_tokens_seen": 5701632000,
|
| 3877 |
+
"step": 21750
|
| 3878 |
+
},
|
| 3879 |
+
{
|
| 3880 |
+
"epoch": 0.10398654852904349,
|
| 3881 |
+
"grad_norm": 0.17937491834163666,
|
| 3882 |
+
"learning_rate": 0.001,
|
| 3883 |
+
"loss": 2.6972,
|
| 3884 |
+
"num_input_tokens_seen": 5714739200,
|
| 3885 |
+
"step": 21800
|
| 3886 |
+
},
|
| 3887 |
+
{
|
| 3888 |
+
"epoch": 0.10422504978713763,
|
| 3889 |
+
"grad_norm": 0.17515376210212708,
|
| 3890 |
+
"learning_rate": 0.001,
|
| 3891 |
+
"loss": 2.6995,
|
| 3892 |
+
"num_input_tokens_seen": 5727846400,
|
| 3893 |
+
"step": 21850
|
| 3894 |
+
},
|
| 3895 |
+
{
|
| 3896 |
+
"epoch": 0.10446355104523176,
|
| 3897 |
+
"grad_norm": 0.18881027400493622,
|
| 3898 |
+
"learning_rate": 0.001,
|
| 3899 |
+
"loss": 2.7097,
|
| 3900 |
+
"num_input_tokens_seen": 5740953600,
|
| 3901 |
+
"step": 21900
|
| 3902 |
+
},
|
| 3903 |
+
{
|
| 3904 |
+
"epoch": 0.1047020523033259,
|
| 3905 |
+
"grad_norm": 0.19030135869979858,
|
| 3906 |
+
"learning_rate": 0.001,
|
| 3907 |
+
"loss": 2.6801,
|
| 3908 |
+
"num_input_tokens_seen": 5754060800,
|
| 3909 |
+
"step": 21950
|
| 3910 |
+
},
|
| 3911 |
+
{
|
| 3912 |
+
"epoch": 0.10494055356142004,
|
| 3913 |
+
"grad_norm": 0.17325563728809357,
|
| 3914 |
+
"learning_rate": 0.001,
|
| 3915 |
+
"loss": 2.6803,
|
| 3916 |
+
"num_input_tokens_seen": 5767168000,
|
| 3917 |
+
"step": 22000
|
| 3918 |
+
},
|
| 3919 |
+
{
|
| 3920 |
+
"epoch": 0.10494055356142004,
|
| 3921 |
+
"eval_loss": 2.577341318130493,
|
| 3922 |
+
"eval_runtime": 50.8482,
|
| 3923 |
+
"eval_samples_per_second": 98.332,
|
| 3924 |
+
"eval_steps_per_second": 24.583,
|
| 3925 |
+
"num_input_tokens_seen": 5767168000,
|
| 3926 |
+
"step": 22000
|
| 3927 |
+
},
|
| 3928 |
+
{
|
| 3929 |
+
"epoch": 0.10517905481951417,
|
| 3930 |
+
"grad_norm": 0.19298380613327026,
|
| 3931 |
+
"learning_rate": 0.001,
|
| 3932 |
+
"loss": 2.6966,
|
| 3933 |
+
"num_input_tokens_seen": 5780275200,
|
| 3934 |
+
"step": 22050
|
| 3935 |
+
},
|
| 3936 |
+
{
|
| 3937 |
+
"epoch": 0.1054175560776083,
|
| 3938 |
+
"grad_norm": 0.1772100180387497,
|
| 3939 |
+
"learning_rate": 0.001,
|
| 3940 |
+
"loss": 2.6851,
|
| 3941 |
+
"num_input_tokens_seen": 5793382400,
|
| 3942 |
+
"step": 22100
|
| 3943 |
+
},
|
| 3944 |
+
{
|
| 3945 |
+
"epoch": 0.10565605733570245,
|
| 3946 |
+
"grad_norm": 0.18548481166362762,
|
| 3947 |
+
"learning_rate": 0.001,
|
| 3948 |
+
"loss": 2.7028,
|
| 3949 |
+
"num_input_tokens_seen": 5806489600,
|
| 3950 |
+
"step": 22150
|
| 3951 |
+
},
|
| 3952 |
+
{
|
| 3953 |
+
"epoch": 0.10589455859379658,
|
| 3954 |
+
"grad_norm": 0.20102089643478394,
|
| 3955 |
+
"learning_rate": 0.001,
|
| 3956 |
+
"loss": 2.6915,
|
| 3957 |
+
"num_input_tokens_seen": 5819596800,
|
| 3958 |
+
"step": 22200
|
| 3959 |
+
},
|
| 3960 |
+
{
|
| 3961 |
+
"epoch": 0.10613305985189071,
|
| 3962 |
+
"grad_norm": 0.1833849996328354,
|
| 3963 |
+
"learning_rate": 0.001,
|
| 3964 |
+
"loss": 2.6872,
|
| 3965 |
+
"num_input_tokens_seen": 5832704000,
|
| 3966 |
+
"step": 22250
|
| 3967 |
+
},
|
| 3968 |
+
{
|
| 3969 |
+
"epoch": 0.10637156110998486,
|
| 3970 |
+
"grad_norm": 0.17730027437210083,
|
| 3971 |
+
"learning_rate": 0.001,
|
| 3972 |
+
"loss": 2.6811,
|
| 3973 |
+
"num_input_tokens_seen": 5845811200,
|
| 3974 |
+
"step": 22300
|
| 3975 |
+
},
|
| 3976 |
+
{
|
| 3977 |
+
"epoch": 0.10661006236807899,
|
| 3978 |
+
"grad_norm": 0.1818256825208664,
|
| 3979 |
+
"learning_rate": 0.001,
|
| 3980 |
+
"loss": 2.7,
|
| 3981 |
+
"num_input_tokens_seen": 5858918400,
|
| 3982 |
+
"step": 22350
|
| 3983 |
+
},
|
| 3984 |
+
{
|
| 3985 |
+
"epoch": 0.10684856362617313,
|
| 3986 |
+
"grad_norm": 0.16850312054157257,
|
| 3987 |
+
"learning_rate": 0.001,
|
| 3988 |
+
"loss": 2.6927,
|
| 3989 |
+
"num_input_tokens_seen": 5872025600,
|
| 3990 |
+
"step": 22400
|
| 3991 |
+
},
|
| 3992 |
+
{
|
| 3993 |
+
"epoch": 0.10708706488426727,
|
| 3994 |
+
"grad_norm": 0.209822878241539,
|
| 3995 |
+
"learning_rate": 0.001,
|
| 3996 |
+
"loss": 2.6881,
|
| 3997 |
+
"num_input_tokens_seen": 5885132800,
|
| 3998 |
+
"step": 22450
|
| 3999 |
+
},
|
| 4000 |
+
{
|
| 4001 |
+
"epoch": 0.1073255661423614,
|
| 4002 |
+
"grad_norm": 0.2131560891866684,
|
| 4003 |
+
"learning_rate": 0.001,
|
| 4004 |
+
"loss": 2.6797,
|
| 4005 |
+
"num_input_tokens_seen": 5898240000,
|
| 4006 |
+
"step": 22500
|
| 4007 |
+
},
|
| 4008 |
+
{
|
| 4009 |
+
"epoch": 0.1073255661423614,
|
| 4010 |
+
"eval_loss": 2.575388193130493,
|
| 4011 |
+
"eval_runtime": 50.9696,
|
| 4012 |
+
"eval_samples_per_second": 98.098,
|
| 4013 |
+
"eval_steps_per_second": 24.524,
|
| 4014 |
+
"num_input_tokens_seen": 5898240000,
|
| 4015 |
+
"step": 22500
|
| 4016 |
+
},
|
| 4017 |
+
{
|
| 4018 |
+
"epoch": 0.10756406740045554,
|
| 4019 |
+
"grad_norm": 0.18200135231018066,
|
| 4020 |
+
"learning_rate": 0.001,
|
| 4021 |
+
"loss": 2.6837,
|
| 4022 |
+
"num_input_tokens_seen": 5911347200,
|
| 4023 |
+
"step": 22550
|
| 4024 |
+
},
|
| 4025 |
+
{
|
| 4026 |
+
"epoch": 0.10780256865854967,
|
| 4027 |
+
"grad_norm": 0.1830984354019165,
|
| 4028 |
+
"learning_rate": 0.001,
|
| 4029 |
+
"loss": 2.7159,
|
| 4030 |
+
"num_input_tokens_seen": 5924454400,
|
| 4031 |
+
"step": 22600
|
| 4032 |
+
},
|
| 4033 |
+
{
|
| 4034 |
+
"epoch": 0.1080410699166438,
|
| 4035 |
+
"grad_norm": 0.1700614094734192,
|
| 4036 |
+
"learning_rate": 0.001,
|
| 4037 |
+
"loss": 2.6852,
|
| 4038 |
+
"num_input_tokens_seen": 5937561600,
|
| 4039 |
+
"step": 22650
|
| 4040 |
+
},
|
| 4041 |
+
{
|
| 4042 |
+
"epoch": 0.10827957117473795,
|
| 4043 |
+
"grad_norm": 0.18473868072032928,
|
| 4044 |
+
"learning_rate": 0.001,
|
| 4045 |
+
"loss": 2.6857,
|
| 4046 |
+
"num_input_tokens_seen": 5950668800,
|
| 4047 |
+
"step": 22700
|
| 4048 |
+
},
|
| 4049 |
+
{
|
| 4050 |
+
"epoch": 0.10851807243283208,
|
| 4051 |
+
"grad_norm": 0.19345365464687347,
|
| 4052 |
+
"learning_rate": 0.001,
|
| 4053 |
+
"loss": 2.69,
|
| 4054 |
+
"num_input_tokens_seen": 5963776000,
|
| 4055 |
+
"step": 22750
|
| 4056 |
+
},
|
| 4057 |
+
{
|
| 4058 |
+
"epoch": 0.10875657369092621,
|
| 4059 |
+
"grad_norm": 0.18807141482830048,
|
| 4060 |
+
"learning_rate": 0.001,
|
| 4061 |
+
"loss": 2.6897,
|
| 4062 |
+
"num_input_tokens_seen": 5976883200,
|
| 4063 |
+
"step": 22800
|
| 4064 |
+
},
|
| 4065 |
+
{
|
| 4066 |
+
"epoch": 0.10899507494902036,
|
| 4067 |
+
"grad_norm": 0.18426446616649628,
|
| 4068 |
+
"learning_rate": 0.001,
|
| 4069 |
+
"loss": 2.6855,
|
| 4070 |
+
"num_input_tokens_seen": 5989990400,
|
| 4071 |
+
"step": 22850
|
| 4072 |
+
},
|
| 4073 |
+
{
|
| 4074 |
+
"epoch": 0.10923357620711449,
|
| 4075 |
+
"grad_norm": 0.19184571504592896,
|
| 4076 |
+
"learning_rate": 0.001,
|
| 4077 |
+
"loss": 2.6914,
|
| 4078 |
+
"num_input_tokens_seen": 6003097600,
|
| 4079 |
+
"step": 22900
|
| 4080 |
+
},
|
| 4081 |
+
{
|
| 4082 |
+
"epoch": 0.10947207746520862,
|
| 4083 |
+
"grad_norm": 0.22897471487522125,
|
| 4084 |
+
"learning_rate": 0.001,
|
| 4085 |
+
"loss": 2.6812,
|
| 4086 |
+
"num_input_tokens_seen": 6016204800,
|
| 4087 |
+
"step": 22950
|
| 4088 |
+
},
|
| 4089 |
+
{
|
| 4090 |
+
"epoch": 0.10971057872330277,
|
| 4091 |
+
"grad_norm": 0.1939724087715149,
|
| 4092 |
+
"learning_rate": 0.001,
|
| 4093 |
+
"loss": 2.6836,
|
| 4094 |
+
"num_input_tokens_seen": 6029312000,
|
| 4095 |
+
"step": 23000
|
| 4096 |
+
},
|
| 4097 |
+
{
|
| 4098 |
+
"epoch": 0.10971057872330277,
|
| 4099 |
+
"eval_loss": 2.570572853088379,
|
| 4100 |
+
"eval_runtime": 50.0606,
|
| 4101 |
+
"eval_samples_per_second": 99.879,
|
| 4102 |
+
"eval_steps_per_second": 24.97,
|
| 4103 |
+
"num_input_tokens_seen": 6029312000,
|
| 4104 |
+
"step": 23000
|
| 4105 |
}
|
| 4106 |
],
|
| 4107 |
"logging_steps": 50,
|
| 4108 |
"max_steps": 70000,
|
| 4109 |
+
"num_input_tokens_seen": 6029312000,
|
| 4110 |
"num_train_epochs": 1,
|
| 4111 |
"save_steps": 1000,
|
| 4112 |
"stateful_callbacks": {
|
|
|
|
| 4121 |
"attributes": {}
|
| 4122 |
}
|
| 4123 |
},
|
| 4124 |
+
"total_flos": 1.61289980608512e+18,
|
| 4125 |
"train_batch_size": 64,
|
| 4126 |
"trial_name": null,
|
| 4127 |
"trial_params": null
|