Commit ·
8afd5dd
1
Parent(s): 32702df
Training in progress, step 180
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:f94f6600b9fcffce4258035ce042291e23c4579968b61a1277bb0e5f15c47b97
|
| 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:f94f6600b9fcffce4258035ce042291e23c4579968b61a1277bb0e5f15c47b97
|
| 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:dc45693ba4970551b76864817602c11f4ca8ba9235888c175fdf6a9bf4e31f61
|
| 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:e14d8247c9ae610692787b8915c107f0bf91789be26bc0740710193dd513ac6b
|
| 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 sha256:000fa190e62d83a5e8bdaab8d33f6975c549b9c8705916359f713129b2584290
|
| 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,
|
|
@@ -108,11 +108,17 @@
|
|
| 108 |
"learning_rate": 0.0002,
|
| 109 |
"loss": 0.0088,
|
| 110 |
"step": 170
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 111 |
}
|
| 112 |
],
|
| 113 |
"max_steps": 200,
|
| 114 |
"num_train_epochs": 50,
|
| 115 |
-
"total_flos": 5.
|
| 116 |
"trial_name": null,
|
| 117 |
"trial_params": null
|
| 118 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 45.0,
|
| 5 |
+
"global_step": 180,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 108 |
"learning_rate": 0.0002,
|
| 109 |
"loss": 0.0088,
|
| 110 |
"step": 170
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 45.0,
|
| 114 |
+
"learning_rate": 0.0002,
|
| 115 |
+
"loss": 0.0089,
|
| 116 |
+
"step": 180
|
| 117 |
}
|
| 118 |
],
|
| 119 |
"max_steps": 200,
|
| 120 |
"num_train_epochs": 50,
|
| 121 |
+
"total_flos": 5.88457764421632e+16,
|
| 122 |
"trial_name": null,
|
| 123 |
"trial_params": null
|
| 124 |
}
|