brian-todd
commited on
Commit
·
a45f5c9
1
Parent(s):
891c910
Training in progress, step 200
Browse files
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 522284877
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3c66a09f57b93d7f5598af9e1f117c7e35ff5e45b8c4e51b69f4613eb54064e
|
3 |
size 522284877
|
last-checkpoint/adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 522284877
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3c66a09f57b93d7f5598af9e1f117c7e35ff5e45b8c4e51b69f4613eb54064e
|
3 |
size 522284877
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1044539653
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34cb32cdf3e1d0e60ca23d5d23951b535a228e9e80ae877f63309eb8711cb6aa
|
3 |
size 1044539653
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b00c6815545fc0f34163fa32b4c2ed7d3c95b1506eb61adba243ce39b83b1e6
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -120,11 +120,17 @@
|
|
120 |
"learning_rate": 0.0002,
|
121 |
"loss": 0.0088,
|
122 |
"step": 190
|
|
|
|
|
|
|
|
|
|
|
|
|
123 |
}
|
124 |
],
|
125 |
"max_steps": 200,
|
126 |
"num_train_epochs": 50,
|
127 |
-
"total_flos": 6.
|
128 |
"trial_name": null,
|
129 |
"trial_params": null
|
130 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 50.0,
|
5 |
+
"global_step": 200,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
120 |
"learning_rate": 0.0002,
|
121 |
"loss": 0.0088,
|
122 |
"step": 190
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 50.0,
|
126 |
+
"learning_rate": 0.0002,
|
127 |
+
"loss": 0.009,
|
128 |
+
"step": 200
|
129 |
}
|
130 |
],
|
131 |
"max_steps": 200,
|
132 |
"num_train_epochs": 50,
|
133 |
+
"total_flos": 6.5384196046848e+16,
|
134 |
"trial_name": null,
|
135 |
"trial_params": null
|
136 |
}
|