Training in progress, step 6000, 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 737580392
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bea384ab228f9e4e48eb09750911bf53afac4e27ba8e57f44979634ad866b1c1
|
| 3 |
size 737580392
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1475248442
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a64a6a144fbcea9043ebf95d58cf6dc0de1643977d324340c43b19a2a87324c9
|
| 3 |
size 1475248442
|
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 sha256:1e59fd29507b0a3f94de60acf1485068cfbd28d4220459a98545dc01f241293d
|
| 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 1000
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:923c446f373ad2f0ffab5651c7c112ff9f6139581eac3a16834e284a234062e7
|
| 3 |
size 1000
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 2.
|
| 5 |
"eval_steps": 250,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -3827,6 +3827,770 @@
|
|
| 3827 |
"eval_spearman_manhattan": 0.807850996089844,
|
| 3828 |
"eval_steps_per_second": 28.467,
|
| 3829 |
"step": 5000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3830 |
}
|
| 3831 |
],
|
| 3832 |
"logging_steps": 10,
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.8116213683223994,
|
| 5 |
"eval_steps": 250,
|
| 6 |
+
"global_step": 6000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 3827 |
"eval_spearman_manhattan": 0.807850996089844,
|
| 3828 |
"eval_steps_per_second": 28.467,
|
| 3829 |
"step": 5000
|
| 3830 |
+
},
|
| 3831 |
+
{
|
| 3832 |
+
"epoch": 2.3477038425492034,
|
| 3833 |
+
"grad_norm": 1.9489047527313232,
|
| 3834 |
+
"learning_rate": 1.8532685098406748e-05,
|
| 3835 |
+
"loss": 0.1478,
|
| 3836 |
+
"step": 5010
|
| 3837 |
+
},
|
| 3838 |
+
{
|
| 3839 |
+
"epoch": 2.352389878163074,
|
| 3840 |
+
"grad_norm": 1.7943733930587769,
|
| 3841 |
+
"learning_rate": 1.852975632614808e-05,
|
| 3842 |
+
"loss": 0.1447,
|
| 3843 |
+
"step": 5020
|
| 3844 |
+
},
|
| 3845 |
+
{
|
| 3846 |
+
"epoch": 2.357075913776945,
|
| 3847 |
+
"grad_norm": 1.9680578708648682,
|
| 3848 |
+
"learning_rate": 1.852682755388941e-05,
|
| 3849 |
+
"loss": 0.158,
|
| 3850 |
+
"step": 5030
|
| 3851 |
+
},
|
| 3852 |
+
{
|
| 3853 |
+
"epoch": 2.3617619493908153,
|
| 3854 |
+
"grad_norm": 1.76882004737854,
|
| 3855 |
+
"learning_rate": 1.8523898781630743e-05,
|
| 3856 |
+
"loss": 0.1616,
|
| 3857 |
+
"step": 5040
|
| 3858 |
+
},
|
| 3859 |
+
{
|
| 3860 |
+
"epoch": 2.3664479850046862,
|
| 3861 |
+
"grad_norm": 1.7545366287231445,
|
| 3862 |
+
"learning_rate": 1.8520970009372073e-05,
|
| 3863 |
+
"loss": 0.1748,
|
| 3864 |
+
"step": 5050
|
| 3865 |
+
},
|
| 3866 |
+
{
|
| 3867 |
+
"epoch": 2.3711340206185567,
|
| 3868 |
+
"grad_norm": 1.8479957580566406,
|
| 3869 |
+
"learning_rate": 1.8518041237113406e-05,
|
| 3870 |
+
"loss": 0.1536,
|
| 3871 |
+
"step": 5060
|
| 3872 |
+
},
|
| 3873 |
+
{
|
| 3874 |
+
"epoch": 2.375820056232427,
|
| 3875 |
+
"grad_norm": 2.2647321224212646,
|
| 3876 |
+
"learning_rate": 1.8515112464854735e-05,
|
| 3877 |
+
"loss": 0.169,
|
| 3878 |
+
"step": 5070
|
| 3879 |
+
},
|
| 3880 |
+
{
|
| 3881 |
+
"epoch": 2.380506091846298,
|
| 3882 |
+
"grad_norm": 2.5361509323120117,
|
| 3883 |
+
"learning_rate": 1.8512183692596065e-05,
|
| 3884 |
+
"loss": 0.1664,
|
| 3885 |
+
"step": 5080
|
| 3886 |
+
},
|
| 3887 |
+
{
|
| 3888 |
+
"epoch": 2.3851921274601686,
|
| 3889 |
+
"grad_norm": 1.6961290836334229,
|
| 3890 |
+
"learning_rate": 1.8509254920337398e-05,
|
| 3891 |
+
"loss": 0.1581,
|
| 3892 |
+
"step": 5090
|
| 3893 |
+
},
|
| 3894 |
+
{
|
| 3895 |
+
"epoch": 2.3898781630740396,
|
| 3896 |
+
"grad_norm": 2.0420143604278564,
|
| 3897 |
+
"learning_rate": 1.8506326148078727e-05,
|
| 3898 |
+
"loss": 0.1761,
|
| 3899 |
+
"step": 5100
|
| 3900 |
+
},
|
| 3901 |
+
{
|
| 3902 |
+
"epoch": 2.39456419868791,
|
| 3903 |
+
"grad_norm": 1.5825088024139404,
|
| 3904 |
+
"learning_rate": 1.8503397375820057e-05,
|
| 3905 |
+
"loss": 0.1462,
|
| 3906 |
+
"step": 5110
|
| 3907 |
+
},
|
| 3908 |
+
{
|
| 3909 |
+
"epoch": 2.3992502343017805,
|
| 3910 |
+
"grad_norm": 1.1550185680389404,
|
| 3911 |
+
"learning_rate": 1.8500468603561386e-05,
|
| 3912 |
+
"loss": 0.1612,
|
| 3913 |
+
"step": 5120
|
| 3914 |
+
},
|
| 3915 |
+
{
|
| 3916 |
+
"epoch": 2.4039362699156515,
|
| 3917 |
+
"grad_norm": 1.1477668285369873,
|
| 3918 |
+
"learning_rate": 1.849753983130272e-05,
|
| 3919 |
+
"loss": 0.168,
|
| 3920 |
+
"step": 5130
|
| 3921 |
+
},
|
| 3922 |
+
{
|
| 3923 |
+
"epoch": 2.408622305529522,
|
| 3924 |
+
"grad_norm": 2.5751688480377197,
|
| 3925 |
+
"learning_rate": 1.849461105904405e-05,
|
| 3926 |
+
"loss": 0.1737,
|
| 3927 |
+
"step": 5140
|
| 3928 |
+
},
|
| 3929 |
+
{
|
| 3930 |
+
"epoch": 2.413308341143393,
|
| 3931 |
+
"grad_norm": 0.8213298916816711,
|
| 3932 |
+
"learning_rate": 1.849168228678538e-05,
|
| 3933 |
+
"loss": 0.1528,
|
| 3934 |
+
"step": 5150
|
| 3935 |
+
},
|
| 3936 |
+
{
|
| 3937 |
+
"epoch": 2.4179943767572634,
|
| 3938 |
+
"grad_norm": 2.1841747760772705,
|
| 3939 |
+
"learning_rate": 1.848875351452671e-05,
|
| 3940 |
+
"loss": 0.1658,
|
| 3941 |
+
"step": 5160
|
| 3942 |
+
},
|
| 3943 |
+
{
|
| 3944 |
+
"epoch": 2.422680412371134,
|
| 3945 |
+
"grad_norm": 1.1756603717803955,
|
| 3946 |
+
"learning_rate": 1.8485824742268044e-05,
|
| 3947 |
+
"loss": 0.1593,
|
| 3948 |
+
"step": 5170
|
| 3949 |
+
},
|
| 3950 |
+
{
|
| 3951 |
+
"epoch": 2.427366447985005,
|
| 3952 |
+
"grad_norm": 1.4406476020812988,
|
| 3953 |
+
"learning_rate": 1.8482895970009373e-05,
|
| 3954 |
+
"loss": 0.1725,
|
| 3955 |
+
"step": 5180
|
| 3956 |
+
},
|
| 3957 |
+
{
|
| 3958 |
+
"epoch": 2.4320524835988753,
|
| 3959 |
+
"grad_norm": 1.0863920450210571,
|
| 3960 |
+
"learning_rate": 1.8479967197750703e-05,
|
| 3961 |
+
"loss": 0.1629,
|
| 3962 |
+
"step": 5190
|
| 3963 |
+
},
|
| 3964 |
+
{
|
| 3965 |
+
"epoch": 2.436738519212746,
|
| 3966 |
+
"grad_norm": 1.736379861831665,
|
| 3967 |
+
"learning_rate": 1.8477038425492036e-05,
|
| 3968 |
+
"loss": 0.1452,
|
| 3969 |
+
"step": 5200
|
| 3970 |
+
},
|
| 3971 |
+
{
|
| 3972 |
+
"epoch": 2.4414245548266167,
|
| 3973 |
+
"grad_norm": 1.3213779926300049,
|
| 3974 |
+
"learning_rate": 1.8474109653233365e-05,
|
| 3975 |
+
"loss": 0.1654,
|
| 3976 |
+
"step": 5210
|
| 3977 |
+
},
|
| 3978 |
+
{
|
| 3979 |
+
"epoch": 2.446110590440487,
|
| 3980 |
+
"grad_norm": 1.8341721296310425,
|
| 3981 |
+
"learning_rate": 1.8471180880974698e-05,
|
| 3982 |
+
"loss": 0.149,
|
| 3983 |
+
"step": 5220
|
| 3984 |
+
},
|
| 3985 |
+
{
|
| 3986 |
+
"epoch": 2.450796626054358,
|
| 3987 |
+
"grad_norm": 1.6373144388198853,
|
| 3988 |
+
"learning_rate": 1.8468252108716028e-05,
|
| 3989 |
+
"loss": 0.1769,
|
| 3990 |
+
"step": 5230
|
| 3991 |
+
},
|
| 3992 |
+
{
|
| 3993 |
+
"epoch": 2.4554826616682286,
|
| 3994 |
+
"grad_norm": 1.9199351072311401,
|
| 3995 |
+
"learning_rate": 1.846532333645736e-05,
|
| 3996 |
+
"loss": 0.1848,
|
| 3997 |
+
"step": 5240
|
| 3998 |
+
},
|
| 3999 |
+
{
|
| 4000 |
+
"epoch": 2.4601686972820995,
|
| 4001 |
+
"grad_norm": 1.5321757793426514,
|
| 4002 |
+
"learning_rate": 1.846239456419869e-05,
|
| 4003 |
+
"loss": 0.166,
|
| 4004 |
+
"step": 5250
|
| 4005 |
+
},
|
| 4006 |
+
{
|
| 4007 |
+
"epoch": 2.4601686972820995,
|
| 4008 |
+
"eval_loss": 0.033459678292274475,
|
| 4009 |
+
"eval_pearson_cosine": 0.81833954439713,
|
| 4010 |
+
"eval_pearson_dot": 0.7450131051603677,
|
| 4011 |
+
"eval_pearson_euclidean": 0.7997398913396002,
|
| 4012 |
+
"eval_pearson_manhattan": 0.8015232151946456,
|
| 4013 |
+
"eval_runtime": 3.3372,
|
| 4014 |
+
"eval_samples_per_second": 449.478,
|
| 4015 |
+
"eval_spearman_cosine": 0.818760866631701,
|
| 4016 |
+
"eval_spearman_dot": 0.7445336159751238,
|
| 4017 |
+
"eval_spearman_euclidean": 0.8090651280572486,
|
| 4018 |
+
"eval_spearman_manhattan": 0.8107108068343578,
|
| 4019 |
+
"eval_steps_per_second": 28.167,
|
| 4020 |
+
"step": 5250
|
| 4021 |
+
},
|
| 4022 |
+
{
|
| 4023 |
+
"epoch": 2.46485473289597,
|
| 4024 |
+
"grad_norm": 2.2415823936462402,
|
| 4025 |
+
"learning_rate": 1.845946579194002e-05,
|
| 4026 |
+
"loss": 0.1606,
|
| 4027 |
+
"step": 5260
|
| 4028 |
+
},
|
| 4029 |
+
{
|
| 4030 |
+
"epoch": 2.4695407685098405,
|
| 4031 |
+
"grad_norm": 0.9711971879005432,
|
| 4032 |
+
"learning_rate": 1.8456537019681352e-05,
|
| 4033 |
+
"loss": 0.1546,
|
| 4034 |
+
"step": 5270
|
| 4035 |
+
},
|
| 4036 |
+
{
|
| 4037 |
+
"epoch": 2.4742268041237114,
|
| 4038 |
+
"grad_norm": 1.7712616920471191,
|
| 4039 |
+
"learning_rate": 1.8453608247422682e-05,
|
| 4040 |
+
"loss": 0.1725,
|
| 4041 |
+
"step": 5280
|
| 4042 |
+
},
|
| 4043 |
+
{
|
| 4044 |
+
"epoch": 2.478912839737582,
|
| 4045 |
+
"grad_norm": 1.9109606742858887,
|
| 4046 |
+
"learning_rate": 1.845067947516401e-05,
|
| 4047 |
+
"loss": 0.175,
|
| 4048 |
+
"step": 5290
|
| 4049 |
+
},
|
| 4050 |
+
{
|
| 4051 |
+
"epoch": 2.483598875351453,
|
| 4052 |
+
"grad_norm": 1.4726054668426514,
|
| 4053 |
+
"learning_rate": 1.8447750702905344e-05,
|
| 4054 |
+
"loss": 0.1432,
|
| 4055 |
+
"step": 5300
|
| 4056 |
+
},
|
| 4057 |
+
{
|
| 4058 |
+
"epoch": 2.4882849109653233,
|
| 4059 |
+
"grad_norm": 1.5022660493850708,
|
| 4060 |
+
"learning_rate": 1.8444821930646674e-05,
|
| 4061 |
+
"loss": 0.1682,
|
| 4062 |
+
"step": 5310
|
| 4063 |
+
},
|
| 4064 |
+
{
|
| 4065 |
+
"epoch": 2.492970946579194,
|
| 4066 |
+
"grad_norm": 2.4403464794158936,
|
| 4067 |
+
"learning_rate": 1.8441893158388003e-05,
|
| 4068 |
+
"loss": 0.1554,
|
| 4069 |
+
"step": 5320
|
| 4070 |
+
},
|
| 4071 |
+
{
|
| 4072 |
+
"epoch": 2.4976569821930648,
|
| 4073 |
+
"grad_norm": 2.6438190937042236,
|
| 4074 |
+
"learning_rate": 1.8438964386129336e-05,
|
| 4075 |
+
"loss": 0.1874,
|
| 4076 |
+
"step": 5330
|
| 4077 |
+
},
|
| 4078 |
+
{
|
| 4079 |
+
"epoch": 2.5023430178069352,
|
| 4080 |
+
"grad_norm": 1.2486696243286133,
|
| 4081 |
+
"learning_rate": 1.8436035613870666e-05,
|
| 4082 |
+
"loss": 0.179,
|
| 4083 |
+
"step": 5340
|
| 4084 |
+
},
|
| 4085 |
+
{
|
| 4086 |
+
"epoch": 2.5070290534208057,
|
| 4087 |
+
"grad_norm": 1.551320195198059,
|
| 4088 |
+
"learning_rate": 1.8433106841612e-05,
|
| 4089 |
+
"loss": 0.1498,
|
| 4090 |
+
"step": 5350
|
| 4091 |
+
},
|
| 4092 |
+
{
|
| 4093 |
+
"epoch": 2.5117150890346767,
|
| 4094 |
+
"grad_norm": 1.7184678316116333,
|
| 4095 |
+
"learning_rate": 1.8430178069353328e-05,
|
| 4096 |
+
"loss": 0.1643,
|
| 4097 |
+
"step": 5360
|
| 4098 |
+
},
|
| 4099 |
+
{
|
| 4100 |
+
"epoch": 2.5164011246485476,
|
| 4101 |
+
"grad_norm": 1.7342448234558105,
|
| 4102 |
+
"learning_rate": 1.842724929709466e-05,
|
| 4103 |
+
"loss": 0.158,
|
| 4104 |
+
"step": 5370
|
| 4105 |
+
},
|
| 4106 |
+
{
|
| 4107 |
+
"epoch": 2.521087160262418,
|
| 4108 |
+
"grad_norm": 1.900806188583374,
|
| 4109 |
+
"learning_rate": 1.842432052483599e-05,
|
| 4110 |
+
"loss": 0.1706,
|
| 4111 |
+
"step": 5380
|
| 4112 |
+
},
|
| 4113 |
+
{
|
| 4114 |
+
"epoch": 2.5257731958762886,
|
| 4115 |
+
"grad_norm": 1.599795937538147,
|
| 4116 |
+
"learning_rate": 1.842139175257732e-05,
|
| 4117 |
+
"loss": 0.1878,
|
| 4118 |
+
"step": 5390
|
| 4119 |
+
},
|
| 4120 |
+
{
|
| 4121 |
+
"epoch": 2.530459231490159,
|
| 4122 |
+
"grad_norm": 1.4454323053359985,
|
| 4123 |
+
"learning_rate": 1.8418462980318653e-05,
|
| 4124 |
+
"loss": 0.1655,
|
| 4125 |
+
"step": 5400
|
| 4126 |
+
},
|
| 4127 |
+
{
|
| 4128 |
+
"epoch": 2.53514526710403,
|
| 4129 |
+
"grad_norm": 1.7434407472610474,
|
| 4130 |
+
"learning_rate": 1.8415534208059982e-05,
|
| 4131 |
+
"loss": 0.1503,
|
| 4132 |
+
"step": 5410
|
| 4133 |
+
},
|
| 4134 |
+
{
|
| 4135 |
+
"epoch": 2.539831302717901,
|
| 4136 |
+
"grad_norm": 2.328422784805298,
|
| 4137 |
+
"learning_rate": 1.8412605435801315e-05,
|
| 4138 |
+
"loss": 0.1702,
|
| 4139 |
+
"step": 5420
|
| 4140 |
+
},
|
| 4141 |
+
{
|
| 4142 |
+
"epoch": 2.5445173383317714,
|
| 4143 |
+
"grad_norm": 1.7260003089904785,
|
| 4144 |
+
"learning_rate": 1.8409676663542645e-05,
|
| 4145 |
+
"loss": 0.1624,
|
| 4146 |
+
"step": 5430
|
| 4147 |
+
},
|
| 4148 |
+
{
|
| 4149 |
+
"epoch": 2.549203373945642,
|
| 4150 |
+
"grad_norm": 1.7711926698684692,
|
| 4151 |
+
"learning_rate": 1.8406747891283974e-05,
|
| 4152 |
+
"loss": 0.1609,
|
| 4153 |
+
"step": 5440
|
| 4154 |
+
},
|
| 4155 |
+
{
|
| 4156 |
+
"epoch": 2.5538894095595124,
|
| 4157 |
+
"grad_norm": 1.963535189628601,
|
| 4158 |
+
"learning_rate": 1.8403819119025307e-05,
|
| 4159 |
+
"loss": 0.1881,
|
| 4160 |
+
"step": 5450
|
| 4161 |
+
},
|
| 4162 |
+
{
|
| 4163 |
+
"epoch": 2.5585754451733833,
|
| 4164 |
+
"grad_norm": 1.5332142114639282,
|
| 4165 |
+
"learning_rate": 1.8400890346766637e-05,
|
| 4166 |
+
"loss": 0.1891,
|
| 4167 |
+
"step": 5460
|
| 4168 |
+
},
|
| 4169 |
+
{
|
| 4170 |
+
"epoch": 2.5632614807872542,
|
| 4171 |
+
"grad_norm": 1.4771735668182373,
|
| 4172 |
+
"learning_rate": 1.8397961574507966e-05,
|
| 4173 |
+
"loss": 0.1455,
|
| 4174 |
+
"step": 5470
|
| 4175 |
+
},
|
| 4176 |
+
{
|
| 4177 |
+
"epoch": 2.5679475164011247,
|
| 4178 |
+
"grad_norm": 1.3587532043457031,
|
| 4179 |
+
"learning_rate": 1.83950328022493e-05,
|
| 4180 |
+
"loss": 0.1579,
|
| 4181 |
+
"step": 5480
|
| 4182 |
+
},
|
| 4183 |
+
{
|
| 4184 |
+
"epoch": 2.572633552014995,
|
| 4185 |
+
"grad_norm": 1.5083823204040527,
|
| 4186 |
+
"learning_rate": 1.839210402999063e-05,
|
| 4187 |
+
"loss": 0.1624,
|
| 4188 |
+
"step": 5490
|
| 4189 |
+
},
|
| 4190 |
+
{
|
| 4191 |
+
"epoch": 2.5773195876288657,
|
| 4192 |
+
"grad_norm": 2.0399646759033203,
|
| 4193 |
+
"learning_rate": 1.8389175257731958e-05,
|
| 4194 |
+
"loss": 0.1572,
|
| 4195 |
+
"step": 5500
|
| 4196 |
+
},
|
| 4197 |
+
{
|
| 4198 |
+
"epoch": 2.5773195876288657,
|
| 4199 |
+
"eval_loss": 0.03521975129842758,
|
| 4200 |
+
"eval_pearson_cosine": 0.8123064687585853,
|
| 4201 |
+
"eval_pearson_dot": 0.7368072149645286,
|
| 4202 |
+
"eval_pearson_euclidean": 0.8002505346194582,
|
| 4203 |
+
"eval_pearson_manhattan": 0.8020724209892114,
|
| 4204 |
+
"eval_runtime": 3.2078,
|
| 4205 |
+
"eval_samples_per_second": 467.604,
|
| 4206 |
+
"eval_spearman_cosine": 0.8135314473340735,
|
| 4207 |
+
"eval_spearman_dot": 0.7336319115548467,
|
| 4208 |
+
"eval_spearman_euclidean": 0.8084064839841847,
|
| 4209 |
+
"eval_spearman_manhattan": 0.8100456053831014,
|
| 4210 |
+
"eval_steps_per_second": 29.303,
|
| 4211 |
+
"step": 5500
|
| 4212 |
+
},
|
| 4213 |
+
{
|
| 4214 |
+
"epoch": 2.5820056232427366,
|
| 4215 |
+
"grad_norm": 1.6468899250030518,
|
| 4216 |
+
"learning_rate": 1.838624648547329e-05,
|
| 4217 |
+
"loss": 0.1884,
|
| 4218 |
+
"step": 5510
|
| 4219 |
+
},
|
| 4220 |
+
{
|
| 4221 |
+
"epoch": 2.5866916588566076,
|
| 4222 |
+
"grad_norm": 1.9936749935150146,
|
| 4223 |
+
"learning_rate": 1.838331771321462e-05,
|
| 4224 |
+
"loss": 0.1692,
|
| 4225 |
+
"step": 5520
|
| 4226 |
+
},
|
| 4227 |
+
{
|
| 4228 |
+
"epoch": 2.591377694470478,
|
| 4229 |
+
"grad_norm": 2.251502513885498,
|
| 4230 |
+
"learning_rate": 1.8380388940955953e-05,
|
| 4231 |
+
"loss": 0.1657,
|
| 4232 |
+
"step": 5530
|
| 4233 |
+
},
|
| 4234 |
+
{
|
| 4235 |
+
"epoch": 2.5960637300843485,
|
| 4236 |
+
"grad_norm": 1.6334820985794067,
|
| 4237 |
+
"learning_rate": 1.8377460168697283e-05,
|
| 4238 |
+
"loss": 0.1692,
|
| 4239 |
+
"step": 5540
|
| 4240 |
+
},
|
| 4241 |
+
{
|
| 4242 |
+
"epoch": 2.600749765698219,
|
| 4243 |
+
"grad_norm": 1.9554181098937988,
|
| 4244 |
+
"learning_rate": 1.8374531396438616e-05,
|
| 4245 |
+
"loss": 0.167,
|
| 4246 |
+
"step": 5550
|
| 4247 |
+
},
|
| 4248 |
+
{
|
| 4249 |
+
"epoch": 2.60543580131209,
|
| 4250 |
+
"grad_norm": 1.866745114326477,
|
| 4251 |
+
"learning_rate": 1.8371602624179945e-05,
|
| 4252 |
+
"loss": 0.1508,
|
| 4253 |
+
"step": 5560
|
| 4254 |
+
},
|
| 4255 |
+
{
|
| 4256 |
+
"epoch": 2.610121836925961,
|
| 4257 |
+
"grad_norm": 1.533691644668579,
|
| 4258 |
+
"learning_rate": 1.8368673851921278e-05,
|
| 4259 |
+
"loss": 0.1726,
|
| 4260 |
+
"step": 5570
|
| 4261 |
+
},
|
| 4262 |
+
{
|
| 4263 |
+
"epoch": 2.6148078725398314,
|
| 4264 |
+
"grad_norm": 1.8526815176010132,
|
| 4265 |
+
"learning_rate": 1.8365745079662608e-05,
|
| 4266 |
+
"loss": 0.1714,
|
| 4267 |
+
"step": 5580
|
| 4268 |
+
},
|
| 4269 |
+
{
|
| 4270 |
+
"epoch": 2.619493908153702,
|
| 4271 |
+
"grad_norm": 1.5112234354019165,
|
| 4272 |
+
"learning_rate": 1.8362816307403937e-05,
|
| 4273 |
+
"loss": 0.1424,
|
| 4274 |
+
"step": 5590
|
| 4275 |
+
},
|
| 4276 |
+
{
|
| 4277 |
+
"epoch": 2.624179943767573,
|
| 4278 |
+
"grad_norm": 1.8528941869735718,
|
| 4279 |
+
"learning_rate": 1.835988753514527e-05,
|
| 4280 |
+
"loss": 0.1677,
|
| 4281 |
+
"step": 5600
|
| 4282 |
+
},
|
| 4283 |
+
{
|
| 4284 |
+
"epoch": 2.6288659793814433,
|
| 4285 |
+
"grad_norm": 1.9312357902526855,
|
| 4286 |
+
"learning_rate": 1.83569587628866e-05,
|
| 4287 |
+
"loss": 0.1505,
|
| 4288 |
+
"step": 5610
|
| 4289 |
+
},
|
| 4290 |
+
{
|
| 4291 |
+
"epoch": 2.633552014995314,
|
| 4292 |
+
"grad_norm": 1.429540753364563,
|
| 4293 |
+
"learning_rate": 1.8354029990627932e-05,
|
| 4294 |
+
"loss": 0.1559,
|
| 4295 |
+
"step": 5620
|
| 4296 |
+
},
|
| 4297 |
+
{
|
| 4298 |
+
"epoch": 2.6382380506091847,
|
| 4299 |
+
"grad_norm": 1.532606840133667,
|
| 4300 |
+
"learning_rate": 1.8351101218369262e-05,
|
| 4301 |
+
"loss": 0.1601,
|
| 4302 |
+
"step": 5630
|
| 4303 |
+
},
|
| 4304 |
+
{
|
| 4305 |
+
"epoch": 2.642924086223055,
|
| 4306 |
+
"grad_norm": 2.127380847930908,
|
| 4307 |
+
"learning_rate": 1.834817244611059e-05,
|
| 4308 |
+
"loss": 0.1992,
|
| 4309 |
+
"step": 5640
|
| 4310 |
+
},
|
| 4311 |
+
{
|
| 4312 |
+
"epoch": 2.647610121836926,
|
| 4313 |
+
"grad_norm": 1.3522067070007324,
|
| 4314 |
+
"learning_rate": 1.834524367385192e-05,
|
| 4315 |
+
"loss": 0.1629,
|
| 4316 |
+
"step": 5650
|
| 4317 |
+
},
|
| 4318 |
+
{
|
| 4319 |
+
"epoch": 2.6522961574507966,
|
| 4320 |
+
"grad_norm": 2.4547903537750244,
|
| 4321 |
+
"learning_rate": 1.8342314901593254e-05,
|
| 4322 |
+
"loss": 0.1817,
|
| 4323 |
+
"step": 5660
|
| 4324 |
+
},
|
| 4325 |
+
{
|
| 4326 |
+
"epoch": 2.6569821930646675,
|
| 4327 |
+
"grad_norm": 1.7367674112319946,
|
| 4328 |
+
"learning_rate": 1.8339386129334583e-05,
|
| 4329 |
+
"loss": 0.1764,
|
| 4330 |
+
"step": 5670
|
| 4331 |
+
},
|
| 4332 |
+
{
|
| 4333 |
+
"epoch": 2.661668228678538,
|
| 4334 |
+
"grad_norm": 1.256063461303711,
|
| 4335 |
+
"learning_rate": 1.8336457357075916e-05,
|
| 4336 |
+
"loss": 0.1532,
|
| 4337 |
+
"step": 5680
|
| 4338 |
+
},
|
| 4339 |
+
{
|
| 4340 |
+
"epoch": 2.6663542642924085,
|
| 4341 |
+
"grad_norm": 1.6752853393554688,
|
| 4342 |
+
"learning_rate": 1.8333528584817246e-05,
|
| 4343 |
+
"loss": 0.2087,
|
| 4344 |
+
"step": 5690
|
| 4345 |
+
},
|
| 4346 |
+
{
|
| 4347 |
+
"epoch": 2.6710402999062794,
|
| 4348 |
+
"grad_norm": 1.8749183416366577,
|
| 4349 |
+
"learning_rate": 1.8330599812558575e-05,
|
| 4350 |
+
"loss": 0.1722,
|
| 4351 |
+
"step": 5700
|
| 4352 |
+
},
|
| 4353 |
+
{
|
| 4354 |
+
"epoch": 2.67572633552015,
|
| 4355 |
+
"grad_norm": 1.9365167617797852,
|
| 4356 |
+
"learning_rate": 1.8327671040299908e-05,
|
| 4357 |
+
"loss": 0.1828,
|
| 4358 |
+
"step": 5710
|
| 4359 |
+
},
|
| 4360 |
+
{
|
| 4361 |
+
"epoch": 2.680412371134021,
|
| 4362 |
+
"grad_norm": 1.8167498111724854,
|
| 4363 |
+
"learning_rate": 1.8324742268041237e-05,
|
| 4364 |
+
"loss": 0.1566,
|
| 4365 |
+
"step": 5720
|
| 4366 |
+
},
|
| 4367 |
+
{
|
| 4368 |
+
"epoch": 2.6850984067478914,
|
| 4369 |
+
"grad_norm": 1.8729602098464966,
|
| 4370 |
+
"learning_rate": 1.832181349578257e-05,
|
| 4371 |
+
"loss": 0.159,
|
| 4372 |
+
"step": 5730
|
| 4373 |
+
},
|
| 4374 |
+
{
|
| 4375 |
+
"epoch": 2.689784442361762,
|
| 4376 |
+
"grad_norm": 1.565158724784851,
|
| 4377 |
+
"learning_rate": 1.83188847235239e-05,
|
| 4378 |
+
"loss": 0.1669,
|
| 4379 |
+
"step": 5740
|
| 4380 |
+
},
|
| 4381 |
+
{
|
| 4382 |
+
"epoch": 2.6944704779756328,
|
| 4383 |
+
"grad_norm": 2.2538883686065674,
|
| 4384 |
+
"learning_rate": 1.8315955951265233e-05,
|
| 4385 |
+
"loss": 0.1353,
|
| 4386 |
+
"step": 5750
|
| 4387 |
+
},
|
| 4388 |
+
{
|
| 4389 |
+
"epoch": 2.6944704779756328,
|
| 4390 |
+
"eval_loss": 0.03330089524388313,
|
| 4391 |
+
"eval_pearson_cosine": 0.8210346883559136,
|
| 4392 |
+
"eval_pearson_dot": 0.7463452164747508,
|
| 4393 |
+
"eval_pearson_euclidean": 0.8023729858931796,
|
| 4394 |
+
"eval_pearson_manhattan": 0.8045441158759452,
|
| 4395 |
+
"eval_runtime": 3.2103,
|
| 4396 |
+
"eval_samples_per_second": 467.241,
|
| 4397 |
+
"eval_spearman_cosine": 0.8210648613938134,
|
| 4398 |
+
"eval_spearman_dot": 0.7463044894785922,
|
| 4399 |
+
"eval_spearman_euclidean": 0.8102763562695625,
|
| 4400 |
+
"eval_spearman_manhattan": 0.8122826147618483,
|
| 4401 |
+
"eval_steps_per_second": 29.28,
|
| 4402 |
+
"step": 5750
|
| 4403 |
+
},
|
| 4404 |
+
{
|
| 4405 |
+
"epoch": 2.6991565135895033,
|
| 4406 |
+
"grad_norm": 1.5002834796905518,
|
| 4407 |
+
"learning_rate": 1.8313027179006562e-05,
|
| 4408 |
+
"loss": 0.1694,
|
| 4409 |
+
"step": 5760
|
| 4410 |
+
},
|
| 4411 |
+
{
|
| 4412 |
+
"epoch": 2.703842549203374,
|
| 4413 |
+
"grad_norm": 1.4530423879623413,
|
| 4414 |
+
"learning_rate": 1.8310098406747895e-05,
|
| 4415 |
+
"loss": 0.1625,
|
| 4416 |
+
"step": 5770
|
| 4417 |
+
},
|
| 4418 |
+
{
|
| 4419 |
+
"epoch": 2.7085285848172447,
|
| 4420 |
+
"grad_norm": 1.4987956285476685,
|
| 4421 |
+
"learning_rate": 1.8307169634489225e-05,
|
| 4422 |
+
"loss": 0.1881,
|
| 4423 |
+
"step": 5780
|
| 4424 |
+
},
|
| 4425 |
+
{
|
| 4426 |
+
"epoch": 2.713214620431115,
|
| 4427 |
+
"grad_norm": 1.6835180521011353,
|
| 4428 |
+
"learning_rate": 1.8304240862230554e-05,
|
| 4429 |
+
"loss": 0.1388,
|
| 4430 |
+
"step": 5790
|
| 4431 |
+
},
|
| 4432 |
+
{
|
| 4433 |
+
"epoch": 2.717900656044986,
|
| 4434 |
+
"grad_norm": 1.752693772315979,
|
| 4435 |
+
"learning_rate": 1.8301312089971887e-05,
|
| 4436 |
+
"loss": 0.1452,
|
| 4437 |
+
"step": 5800
|
| 4438 |
+
},
|
| 4439 |
+
{
|
| 4440 |
+
"epoch": 2.7225866916588566,
|
| 4441 |
+
"grad_norm": 1.5680220127105713,
|
| 4442 |
+
"learning_rate": 1.8298383317713217e-05,
|
| 4443 |
+
"loss": 0.1613,
|
| 4444 |
+
"step": 5810
|
| 4445 |
+
},
|
| 4446 |
+
{
|
| 4447 |
+
"epoch": 2.7272727272727275,
|
| 4448 |
+
"grad_norm": 2.067552328109741,
|
| 4449 |
+
"learning_rate": 1.8295454545454546e-05,
|
| 4450 |
+
"loss": 0.1458,
|
| 4451 |
+
"step": 5820
|
| 4452 |
+
},
|
| 4453 |
+
{
|
| 4454 |
+
"epoch": 2.731958762886598,
|
| 4455 |
+
"grad_norm": 2.0963711738586426,
|
| 4456 |
+
"learning_rate": 1.8292525773195876e-05,
|
| 4457 |
+
"loss": 0.1972,
|
| 4458 |
+
"step": 5830
|
| 4459 |
+
},
|
| 4460 |
+
{
|
| 4461 |
+
"epoch": 2.7366447985004685,
|
| 4462 |
+
"grad_norm": 1.5372573137283325,
|
| 4463 |
+
"learning_rate": 1.828959700093721e-05,
|
| 4464 |
+
"loss": 0.1657,
|
| 4465 |
+
"step": 5840
|
| 4466 |
+
},
|
| 4467 |
+
{
|
| 4468 |
+
"epoch": 2.7413308341143394,
|
| 4469 |
+
"grad_norm": 2.0116796493530273,
|
| 4470 |
+
"learning_rate": 1.8286668228678538e-05,
|
| 4471 |
+
"loss": 0.1576,
|
| 4472 |
+
"step": 5850
|
| 4473 |
+
},
|
| 4474 |
+
{
|
| 4475 |
+
"epoch": 2.74601686972821,
|
| 4476 |
+
"grad_norm": 1.3485506772994995,
|
| 4477 |
+
"learning_rate": 1.828373945641987e-05,
|
| 4478 |
+
"loss": 0.1503,
|
| 4479 |
+
"step": 5860
|
| 4480 |
+
},
|
| 4481 |
+
{
|
| 4482 |
+
"epoch": 2.750702905342081,
|
| 4483 |
+
"grad_norm": 1.7089899778366089,
|
| 4484 |
+
"learning_rate": 1.82808106841612e-05,
|
| 4485 |
+
"loss": 0.1787,
|
| 4486 |
+
"step": 5870
|
| 4487 |
+
},
|
| 4488 |
+
{
|
| 4489 |
+
"epoch": 2.7553889409559513,
|
| 4490 |
+
"grad_norm": 1.6269711256027222,
|
| 4491 |
+
"learning_rate": 1.8277881911902533e-05,
|
| 4492 |
+
"loss": 0.1879,
|
| 4493 |
+
"step": 5880
|
| 4494 |
+
},
|
| 4495 |
+
{
|
| 4496 |
+
"epoch": 2.760074976569822,
|
| 4497 |
+
"grad_norm": 1.6839511394500732,
|
| 4498 |
+
"learning_rate": 1.8274953139643863e-05,
|
| 4499 |
+
"loss": 0.1499,
|
| 4500 |
+
"step": 5890
|
| 4501 |
+
},
|
| 4502 |
+
{
|
| 4503 |
+
"epoch": 2.7647610121836927,
|
| 4504 |
+
"grad_norm": 1.829288363456726,
|
| 4505 |
+
"learning_rate": 1.8272024367385192e-05,
|
| 4506 |
+
"loss": 0.1776,
|
| 4507 |
+
"step": 5900
|
| 4508 |
+
},
|
| 4509 |
+
{
|
| 4510 |
+
"epoch": 2.7694470477975632,
|
| 4511 |
+
"grad_norm": 1.4138745069503784,
|
| 4512 |
+
"learning_rate": 1.8269095595126525e-05,
|
| 4513 |
+
"loss": 0.1612,
|
| 4514 |
+
"step": 5910
|
| 4515 |
+
},
|
| 4516 |
+
{
|
| 4517 |
+
"epoch": 2.774133083411434,
|
| 4518 |
+
"grad_norm": 1.4199497699737549,
|
| 4519 |
+
"learning_rate": 1.8266166822867855e-05,
|
| 4520 |
+
"loss": 0.1717,
|
| 4521 |
+
"step": 5920
|
| 4522 |
+
},
|
| 4523 |
+
{
|
| 4524 |
+
"epoch": 2.7788191190253047,
|
| 4525 |
+
"grad_norm": 1.8683243989944458,
|
| 4526 |
+
"learning_rate": 1.8263238050609187e-05,
|
| 4527 |
+
"loss": 0.1701,
|
| 4528 |
+
"step": 5930
|
| 4529 |
+
},
|
| 4530 |
+
{
|
| 4531 |
+
"epoch": 2.783505154639175,
|
| 4532 |
+
"grad_norm": 1.5344245433807373,
|
| 4533 |
+
"learning_rate": 1.8260309278350517e-05,
|
| 4534 |
+
"loss": 0.1704,
|
| 4535 |
+
"step": 5940
|
| 4536 |
+
},
|
| 4537 |
+
{
|
| 4538 |
+
"epoch": 2.788191190253046,
|
| 4539 |
+
"grad_norm": 1.8963440656661987,
|
| 4540 |
+
"learning_rate": 1.825738050609185e-05,
|
| 4541 |
+
"loss": 0.1876,
|
| 4542 |
+
"step": 5950
|
| 4543 |
+
},
|
| 4544 |
+
{
|
| 4545 |
+
"epoch": 2.7928772258669166,
|
| 4546 |
+
"grad_norm": 2.009709358215332,
|
| 4547 |
+
"learning_rate": 1.825445173383318e-05,
|
| 4548 |
+
"loss": 0.204,
|
| 4549 |
+
"step": 5960
|
| 4550 |
+
},
|
| 4551 |
+
{
|
| 4552 |
+
"epoch": 2.7975632614807875,
|
| 4553 |
+
"grad_norm": 1.5217466354370117,
|
| 4554 |
+
"learning_rate": 1.825152296157451e-05,
|
| 4555 |
+
"loss": 0.1582,
|
| 4556 |
+
"step": 5970
|
| 4557 |
+
},
|
| 4558 |
+
{
|
| 4559 |
+
"epoch": 2.802249297094658,
|
| 4560 |
+
"grad_norm": 1.7628065347671509,
|
| 4561 |
+
"learning_rate": 1.8248594189315842e-05,
|
| 4562 |
+
"loss": 0.1563,
|
| 4563 |
+
"step": 5980
|
| 4564 |
+
},
|
| 4565 |
+
{
|
| 4566 |
+
"epoch": 2.8069353327085285,
|
| 4567 |
+
"grad_norm": 1.8212190866470337,
|
| 4568 |
+
"learning_rate": 1.824566541705717e-05,
|
| 4569 |
+
"loss": 0.1662,
|
| 4570 |
+
"step": 5990
|
| 4571 |
+
},
|
| 4572 |
+
{
|
| 4573 |
+
"epoch": 2.8116213683223994,
|
| 4574 |
+
"grad_norm": 2.4741644859313965,
|
| 4575 |
+
"learning_rate": 1.82427366447985e-05,
|
| 4576 |
+
"loss": 0.1555,
|
| 4577 |
+
"step": 6000
|
| 4578 |
+
},
|
| 4579 |
+
{
|
| 4580 |
+
"epoch": 2.8116213683223994,
|
| 4581 |
+
"eval_loss": 0.03254643455147743,
|
| 4582 |
+
"eval_pearson_cosine": 0.818468145503374,
|
| 4583 |
+
"eval_pearson_dot": 0.7526356355108419,
|
| 4584 |
+
"eval_pearson_euclidean": 0.7938927456366471,
|
| 4585 |
+
"eval_pearson_manhattan": 0.7958636725988697,
|
| 4586 |
+
"eval_runtime": 3.1897,
|
| 4587 |
+
"eval_samples_per_second": 470.262,
|
| 4588 |
+
"eval_spearman_cosine": 0.8183439432602023,
|
| 4589 |
+
"eval_spearman_dot": 0.7537522979367676,
|
| 4590 |
+
"eval_spearman_euclidean": 0.8019040119245933,
|
| 4591 |
+
"eval_spearman_manhattan": 0.8036153637269691,
|
| 4592 |
+
"eval_steps_per_second": 29.47,
|
| 4593 |
+
"step": 6000
|
| 4594 |
}
|
| 4595 |
],
|
| 4596 |
"logging_steps": 10,
|