Commit ·
ffa3a23
1
Parent(s): bb14c24
Training in progress, step 150
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:af04f516604e06958c79ad27fb8aaf8e7a3262ffc8299a5c6416a831f6a24eb1
|
| 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:af04f516604e06958c79ad27fb8aaf8e7a3262ffc8299a5c6416a831f6a24eb1
|
| 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 sha256:6148b1958e4a69a8b85a107e365104027fc249c7a22091cf38a9b292e19bb2c5
|
| 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:fe692295c91e854e9bdd4bad4f298114db98992d153f864e93bbb4a53a049eab
|
| 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 sha256:01422943191c18f4ce94fe70c7ffd85d7e6e08513a418ac2779ae0b3b3ba38a4
|
| 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,
|
|
@@ -90,11 +90,17 @@
|
|
| 90 |
"learning_rate": 0.0002,
|
| 91 |
"loss": 0.0094,
|
| 92 |
"step": 140
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 93 |
}
|
| 94 |
],
|
| 95 |
"max_steps": 200,
|
| 96 |
"num_train_epochs": 50,
|
| 97 |
-
"total_flos": 4.
|
| 98 |
"trial_name": null,
|
| 99 |
"trial_params": null
|
| 100 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 37.5,
|
| 5 |
+
"global_step": 150,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 90 |
"learning_rate": 0.0002,
|
| 91 |
"loss": 0.0094,
|
| 92 |
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 37.5,
|
| 96 |
+
"learning_rate": 0.0002,
|
| 97 |
+
"loss": 0.0091,
|
| 98 |
+
"step": 150
|
| 99 |
}
|
| 100 |
],
|
| 101 |
"max_steps": 200,
|
| 102 |
"num_train_epochs": 50,
|
| 103 |
+
"total_flos": 4.904852547895296e+16,
|
| 104 |
"trial_name": null,
|
| 105 |
"trial_params": null
|
| 106 |
}
|