Training in progress, step 320000
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 sha256:47f7088cdadd3c77b8cd63cb7a6d3cb94faa3e4642cf15c204199eac55ac6cfc
|
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:d4b8cd1ed334d32a8a16cc2447e13a34a0e25dbe588a2d9839d8b9d9a7e15a34
|
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:a55ab3dfa9a28b268e14ce28eaa98d235fd369073de66d93bc17a07f35aa5f9b
|
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:a621023de1741c67e8dcc49b9b6f775cdb24e54bd96663859fd4443c9bffb0bd
|
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 sha256:9647d9392e479162b83c445ea6da04cbd65f13604d3ce7429aa57844e66e991c
|
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:c37e7dc304fc5c5c88dc58be0e26fa441d6837b1f130477fbf3cf19e4924da0b
|
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 sha256:0346b3edc14a746999e7f8263896677fe68097a2de3242e6ae02edb71987bcc6
|
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:c619812f7415edd1243c64c562d8026aff31b2ea251c532815a9faa9f3c05fdd
|
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,
|
@@ -3786,6 +3786,66 @@
|
|
3786 |
"learning_rate": 5.2249304849455853e-05,
|
3787 |
"loss": 0.3243,
|
3788 |
"step": 315000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3789 |
}
|
3790 |
],
|
3791 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.446804708045038,
|
5 |
+
"global_step": 320000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
3786 |
"learning_rate": 5.2249304849455853e-05,
|
3787 |
"loss": 0.3243,
|
3788 |
"step": 315000
|
3789 |
+
},
|
3790 |
+
{
|
3791 |
+
"epoch": 5.37,
|
3792 |
+
"learning_rate": 5.204754990551717e-05,
|
3793 |
+
"loss": 0.3244,
|
3794 |
+
"step": 315500
|
3795 |
+
},
|
3796 |
+
{
|
3797 |
+
"epoch": 5.38,
|
3798 |
+
"learning_rate": 5.184647352245537e-05,
|
3799 |
+
"loss": 0.3241,
|
3800 |
+
"step": 316000
|
3801 |
+
},
|
3802 |
+
{
|
3803 |
+
"epoch": 5.39,
|
3804 |
+
"learning_rate": 5.164527176811031e-05,
|
3805 |
+
"loss": 0.3245,
|
3806 |
+
"step": 316500
|
3807 |
+
},
|
3808 |
+
{
|
3809 |
+
"epoch": 5.4,
|
3810 |
+
"learning_rate": 5.144434986348564e-05,
|
3811 |
+
"loss": 0.3242,
|
3812 |
+
"step": 317000
|
3813 |
+
},
|
3814 |
+
{
|
3815 |
+
"epoch": 5.4,
|
3816 |
+
"learning_rate": 5.1243709791599435e-05,
|
3817 |
+
"loss": 0.3243,
|
3818 |
+
"step": 317500
|
3819 |
+
},
|
3820 |
+
{
|
3821 |
+
"epoch": 5.41,
|
3822 |
+
"learning_rate": 5.1043753960645855e-05,
|
3823 |
+
"loss": 0.324,
|
3824 |
+
"step": 318000
|
3825 |
+
},
|
3826 |
+
{
|
3827 |
+
"epoch": 5.42,
|
3828 |
+
"learning_rate": 5.0843682918592574e-05,
|
3829 |
+
"loss": 0.3241,
|
3830 |
+
"step": 318500
|
3831 |
+
},
|
3832 |
+
{
|
3833 |
+
"epoch": 5.43,
|
3834 |
+
"learning_rate": 5.064389963761796e-05,
|
3835 |
+
"loss": 0.3242,
|
3836 |
+
"step": 319000
|
3837 |
+
},
|
3838 |
+
{
|
3839 |
+
"epoch": 5.44,
|
3840 |
+
"learning_rate": 5.044440608950243e-05,
|
3841 |
+
"loss": 0.3239,
|
3842 |
+
"step": 319500
|
3843 |
+
},
|
3844 |
+
{
|
3845 |
+
"epoch": 5.45,
|
3846 |
+
"learning_rate": 5.024520424316668e-05,
|
3847 |
+
"loss": 0.3239,
|
3848 |
+
"step": 320000
|
3849 |
}
|
3850 |
],
|
3851 |
"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:d4b8cd1ed334d32a8a16cc2447e13a34a0e25dbe588a2d9839d8b9d9a7e15a34
|
3 |
size 201355195
|