tylercross
commited on
Commit
•
51c0e23
1
Parent(s):
b68a1c0
Upload 7 files
Browse files- README.md +7 -7
- adapter_config.json +4 -4
- adapter_model.bin +1 -1
README.md
CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 2.
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -51,12 +51,12 @@ The following hyperparameters were used during training:
|
|
51 |
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|
|
53 |
| 2.4833 | 0.13 | 1 | 2.5152 |
|
54 |
-
| 2.5615 | 0.
|
55 |
-
| 2.
|
56 |
-
| 2.
|
57 |
-
| 2.
|
58 |
-
| 2.
|
59 |
-
| 2.
|
60 |
|
61 |
|
62 |
### Framework versions
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 2.3313
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
51 |
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|
|
53 |
| 2.4833 | 0.13 | 1 | 2.5152 |
|
54 |
+
| 2.5615 | 0.26 | 2 | 2.5078 |
|
55 |
+
| 2.4965 | 0.39 | 3 | 2.4691 |
|
56 |
+
| 2.3902 | 0.52 | 4 | 2.4249 |
|
57 |
+
| 2.3629 | 0.65 | 5 | 2.3824 |
|
58 |
+
| 2.2324 | 0.77 | 6 | 2.3441 |
|
59 |
+
| 2.1907 | 0.9 | 7 | 2.3313 |
|
60 |
|
61 |
|
62 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -16,13 +16,13 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
-
"
|
20 |
-
"down_proj",
|
21 |
"v_proj",
|
22 |
"up_proj",
|
23 |
"o_proj",
|
24 |
-
"
|
25 |
-
"k_proj"
|
|
|
26 |
],
|
27 |
"task_type": "CAUSAL_LM"
|
28 |
}
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
+
"gate_proj",
|
|
|
20 |
"v_proj",
|
21 |
"up_proj",
|
22 |
"o_proj",
|
23 |
+
"q_proj",
|
24 |
+
"k_proj",
|
25 |
+
"down_proj"
|
26 |
],
|
27 |
"task_type": "CAUSAL_LM"
|
28 |
}
|
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 335706186
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70c0859d3ab66e4c0ca38e9a1d5c4f55c26411dedc2ec00922ba89cc33b33535
|
3 |
size 335706186
|