End of training
Browse files- README.md +1 -1
- adapter_config.json +4 -4
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -34,7 +34,7 @@ More information needed
|
|
34 |
### Training hyperparameters
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
-
- learning_rate:
|
38 |
- train_batch_size: 3
|
39 |
- eval_batch_size: 8
|
40 |
- seed: 42
|
|
|
34 |
### Training hyperparameters
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 1e-05
|
38 |
- train_batch_size: 3
|
39 |
- eval_batch_size: 8
|
40 |
- seed: 42
|
adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"down_proj",
|
24 |
-
"up_proj",
|
25 |
"gate_proj",
|
|
|
26 |
"v_proj",
|
|
|
|
|
27 |
"o_proj",
|
28 |
-
"
|
29 |
-
"k_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
|
|
23 |
"gate_proj",
|
24 |
+
"q_proj",
|
25 |
"v_proj",
|
26 |
+
"k_proj",
|
27 |
+
"up_proj",
|
28 |
"o_proj",
|
29 |
+
"down_proj"
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 167832240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f5ceb47041ed813346d77dc3a8a1852c0f55dbbe330d4d8f31ee2f9e9b8f36e
|
3 |
size 167832240
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5368
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc25aaf41ea9e18ddbcf5b81fff23e35788f4fbd439297c39bbf898d91b12650
|
3 |
size 5368
|