Training in progress, step 325000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +62 -2
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 402588883
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e42d023231938ad3f3b3ffa7f1886bdb344fa022a5889a1607047813d6bfa258
|
3 |
size 402588883
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201355195
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aac97707c80cb6980df17a8587504825ea8b2da1acf91d4524face2c17eceb8c
|
3 |
size 201355195
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d72b8a5edaba92ed1e503bef5360ce95e62505684b7d27025362ea563de0c74
|
3 |
size 14503
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16a994e0d5d44eb2e35a146710940e8a11f807d98e99929f893720c878dcba12
|
3 |
size 14503
|
last-checkpoint/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17871c00816e6105ce41e861eceb66e926775f7afbd6cfaf2be614fa0f313e2c
|
3 |
size 14503
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ddbd058cbd4da43a3e73d6a900bda0f9af9c55fb7ed9d6153178aa2288da1004
|
3 |
size 14503
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a576f128ed2bbbc456ee1ec47c14c0a570de3e17ac9609b196afbbf6bf58c75
|
3 |
size 559
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3309cafff4258d3fdde3ff9b08ed2d2739aa8c5b405fa4ec1739c5bb261fd522
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 5.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -3846,6 +3846,66 @@
|
|
3846 |
"learning_rate": 5.024520424316668e-05,
|
3847 |
"loss": 0.3239,
|
3848 |
"step": 320000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3849 |
}
|
3850 |
],
|
3851 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.531910366720283,
|
5 |
+
"global_step": 325000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
3846 |
"learning_rate": 5.024520424316668e-05,
|
3847 |
"loss": 0.3239,
|
3848 |
"step": 320000
|
3849 |
+
},
|
3850 |
+
{
|
3851 |
+
"epoch": 5.46,
|
3852 |
+
"learning_rate": 5.004629606465258e-05,
|
3853 |
+
"loss": 0.3239,
|
3854 |
+
"step": 320500
|
3855 |
+
},
|
3856 |
+
{
|
3857 |
+
"epoch": 5.46,
|
3858 |
+
"learning_rate": 4.9847683517103505e-05,
|
3859 |
+
"loss": 0.324,
|
3860 |
+
"step": 321000
|
3861 |
+
},
|
3862 |
+
{
|
3863 |
+
"epoch": 5.47,
|
3864 |
+
"learning_rate": 4.9649368560745154e-05,
|
3865 |
+
"loss": 0.3238,
|
3866 |
+
"step": 321500
|
3867 |
+
},
|
3868 |
+
{
|
3869 |
+
"epoch": 5.48,
|
3870 |
+
"learning_rate": 4.945135315286604e-05,
|
3871 |
+
"loss": 0.3238,
|
3872 |
+
"step": 322000
|
3873 |
+
},
|
3874 |
+
{
|
3875 |
+
"epoch": 5.49,
|
3876 |
+
"learning_rate": 4.925363924779834e-05,
|
3877 |
+
"loss": 0.3239,
|
3878 |
+
"step": 322500
|
3879 |
+
},
|
3880 |
+
{
|
3881 |
+
"epoch": 5.5,
|
3882 |
+
"learning_rate": 4.905622879689845e-05,
|
3883 |
+
"loss": 0.3238,
|
3884 |
+
"step": 323000
|
3885 |
+
},
|
3886 |
+
{
|
3887 |
+
"epoch": 5.51,
|
3888 |
+
"learning_rate": 4.8859517652539344e-05,
|
3889 |
+
"loss": 0.3234,
|
3890 |
+
"step": 323500
|
3891 |
+
},
|
3892 |
+
{
|
3893 |
+
"epoch": 5.51,
|
3894 |
+
"learning_rate": 4.8663112624023495e-05,
|
3895 |
+
"loss": 0.3238,
|
3896 |
+
"step": 324000
|
3897 |
+
},
|
3898 |
+
{
|
3899 |
+
"epoch": 5.52,
|
3900 |
+
"learning_rate": 4.846662297269393e-05,
|
3901 |
+
"loss": 0.3235,
|
3902 |
+
"step": 324500
|
3903 |
+
},
|
3904 |
+
{
|
3905 |
+
"epoch": 5.53,
|
3906 |
+
"learning_rate": 4.827044454306512e-05,
|
3907 |
+
"loss": 0.3237,
|
3908 |
+
"step": 325000
|
3909 |
}
|
3910 |
],
|
3911 |
"max_steps": 500000,
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201355195
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aac97707c80cb6980df17a8587504825ea8b2da1acf91d4524face2c17eceb8c
|
3 |
size 201355195
|