Model save
Browse files- README.md +1 -1
- adapter_config.json +5 -5
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -33,7 +33,7 @@ More information needed
|
|
| 33 |
### Training hyperparameters
|
| 34 |
|
| 35 |
The following hyperparameters were used during training:
|
| 36 |
-
- learning_rate:
|
| 37 |
- train_batch_size: 4
|
| 38 |
- eval_batch_size: 8
|
| 39 |
- seed: 42
|
|
|
|
| 33 |
### Training hyperparameters
|
| 34 |
|
| 35 |
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 6e-05
|
| 37 |
- train_batch_size: 4
|
| 38 |
- eval_batch_size: 8
|
| 39 |
- seed: 42
|
adapter_config.json
CHANGED
|
@@ -23,13 +23,13 @@
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
|
|
|
|
|
|
| 26 |
"up_proj",
|
| 27 |
-
"o_proj",
|
| 28 |
"down_proj",
|
| 29 |
-
"
|
| 30 |
-
"
|
| 31 |
-
"
|
| 32 |
-
"gate_proj"
|
| 33 |
],
|
| 34 |
"task_type": null,
|
| 35 |
"use_dora": true,
|
|
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
| 26 |
+
"k_proj",
|
| 27 |
+
"q_proj",
|
| 28 |
"up_proj",
|
|
|
|
| 29 |
"down_proj",
|
| 30 |
+
"gate_proj",
|
| 31 |
+
"o_proj",
|
| 32 |
+
"v_proj"
|
|
|
|
| 33 |
],
|
| 34 |
"task_type": null,
|
| 35 |
"use_dora": true,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 51802928
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1722f6dac1e1ed8540b99df2276c1da436921cdcec06d0ad26468427713b1cd6
|
| 3 |
size 51802928
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e961a0009640256e26a3c3a818d3b931622674907f303d90030377e62d78b2f4
|
| 3 |
size 5240
|