Briarur/outputs
Browse files- README.md +1 -1
- adapter_config.json +2 -2
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -46,7 +46,7 @@ The following hyperparameters were used during training:
|
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: linear
|
48 |
- lr_scheduler_warmup_ratio: 0.01
|
49 |
-
- num_epochs:
|
50 |
- mixed_precision_training: Native AMP
|
51 |
|
52 |
### Training results
|
|
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: linear
|
48 |
- lr_scheduler_warmup_ratio: 0.01
|
49 |
+
- num_epochs: 3
|
50 |
- mixed_precision_training: Native AMP
|
51 |
|
52 |
### Training results
|
adapter_config.json
CHANGED
@@ -21,9 +21,9 @@
|
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
"v_proj",
|
24 |
-
"
|
25 |
"dense",
|
26 |
-
"
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM",
|
29 |
"use_dora": false,
|
|
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
"v_proj",
|
24 |
+
"k_proj",
|
25 |
"dense",
|
26 |
+
"q_proj"
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM",
|
29 |
"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 1149331720
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94f5fdc204dc7137c53dc29ec004ddd91c33b138d1a9bc0a32d3885512eb344c
|
3 |
size 1149331720
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5496
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8c337a49042a2bb90f3b1858eff690376b0c0e66f7c95fbb57fc72db3cfdda9
|
3 |
size 5496
|