Commit ·
891c910
1
Parent(s): 8afd5dd
Training in progress, step 190
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:f85de9073028143182eb832c8b922d808c07bd7b4c897b3d0792699604655561
|
| 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:f85de9073028143182eb832c8b922d808c07bd7b4c897b3d0792699604655561
|
| 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 sha256:401e949ad2644fac691202aa9ab4a60a9367ef62b9569cf3b1a212706149cb5a
|
| 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:a1229963b2882723559bc1f7e4fff8a6ded40d1a4656ab986b2c856e1991e43d
|
| 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 sha256:75f3970664cf1293b5433d45f23518e62ddd312294c8d30120d44b8a48b4c4b4
|
| 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,
|
|
@@ -114,11 +114,17 @@
|
|
| 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":
|
| 122 |
"trial_name": null,
|
| 123 |
"trial_params": null
|
| 124 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 47.5,
|
| 5 |
+
"global_step": 190,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 114 |
"learning_rate": 0.0002,
|
| 115 |
"loss": 0.0089,
|
| 116 |
"step": 180
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 47.5,
|
| 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": 6.212536468832256e+16,
|
| 128 |
"trial_name": null,
|
| 129 |
"trial_params": null
|
| 130 |
}
|