Farisya/qna
Browse files
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 [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss:
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -51,22 +51,22 @@ The following hyperparameters were used during training:
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|
|
54 |
-
|
|
55 |
-
|
|
56 |
-
|
|
57 |
-
|
|
58 |
-
|
|
59 |
-
|
|
60 |
-
|
|
61 |
-
|
|
62 |
-
|
|
63 |
-
|
|
64 |
|
65 |
|
66 |
### Framework versions
|
67 |
|
68 |
- PEFT 0.9.0
|
69 |
-
- Transformers 4.38.
|
70 |
-
- Pytorch 2.1.
|
71 |
-
- Datasets 2.
|
72 |
- Tokenizers 0.15.2
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.8247
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|
|
54 |
+
| 3.8587 | 0.94 | 4 | 3.3972 |
|
55 |
+
| 3.1119 | 1.88 | 8 | 2.7188 |
|
56 |
+
| 2.4626 | 2.82 | 12 | 2.1773 |
|
57 |
+
| 1.5464 | 4.0 | 17 | 1.6636 |
|
58 |
+
| 1.5121 | 4.94 | 21 | 1.3225 |
|
59 |
+
| 1.1923 | 5.88 | 25 | 1.0879 |
|
60 |
+
| 0.9689 | 6.82 | 29 | 0.9322 |
|
61 |
+
| 0.7061 | 8.0 | 34 | 0.8552 |
|
62 |
+
| 0.8246 | 8.94 | 38 | 0.8292 |
|
63 |
+
| 0.7081 | 9.41 | 40 | 0.8247 |
|
64 |
|
65 |
|
66 |
### Framework versions
|
67 |
|
68 |
- PEFT 0.9.0
|
69 |
+
- Transformers 4.38.2
|
70 |
+
- Pytorch 2.1.0+cu121
|
71 |
+
- Datasets 2.18.0
|
72 |
- Tokenizers 0.15.2
|
adapter_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
-
"base_model_name_or_path":
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "TheBloke/Mistral-7B-Instruct-v0.2-GPTQ",
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94d796195e3e5ebd95be7f4be1bef1079b18ea928b776b093625ee89e775f574
|
3 |
+
size 8397056
|
runs/Mar21_02-03-20_1d417d2608ed/events.out.tfevents.1710986605.1d417d2608ed.593.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10f164ce9cd6f52794f77d46bbe1dc34f594a7b1044687597bd6ad6413f0536c
|
3 |
+
size 10286
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4856
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1de3a9b8cdebc0fae2f228ebbc2fc90af170a57b6f9d2f24c20860d58e746a0e
|
3 |
size 4856
|