FrederikKlinkby
commited on
Commit
•
4f44d35
1
Parent(s):
050a3ba
shawgpt-ft-lr2e-05-wd0.01
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: 3.
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -51,18 +51,18 @@ The following hyperparameters were used during training:
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
|:-------------:|:-------:|:----:|:---------------:|
|
54 |
-
| 4.
|
55 |
-
| 4.
|
56 |
-
| 4.
|
57 |
-
| 2.
|
58 |
-
| 3.
|
59 |
-
| 3.
|
60 |
-
| 3.
|
61 |
-
| 2.
|
62 |
-
| 3.
|
63 |
-
| 3.
|
64 |
-
| 3.
|
65 |
-
| 0.
|
66 |
|
67 |
|
68 |
### Framework versions
|
|
|
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: 3.3804
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
|:-------------:|:-------:|:----:|:---------------:|
|
54 |
+
| 4.1779 | 0.9231 | 3 | 3.8026 |
|
55 |
+
| 4.0882 | 1.8462 | 6 | 3.7331 |
|
56 |
+
| 4.0172 | 2.7692 | 9 | 3.6688 |
|
57 |
+
| 2.9507 | 4.0 | 13 | 3.5927 |
|
58 |
+
| 3.8869 | 4.9231 | 16 | 3.5431 |
|
59 |
+
| 3.8087 | 5.8462 | 19 | 3.4996 |
|
60 |
+
| 3.768 | 6.7692 | 22 | 3.4629 |
|
61 |
+
| 2.7826 | 8.0 | 26 | 3.4239 |
|
62 |
+
| 3.6824 | 8.9231 | 29 | 3.4026 |
|
63 |
+
| 3.6671 | 9.8462 | 32 | 3.3882 |
|
64 |
+
| 3.6579 | 10.7692 | 35 | 3.3812 |
|
65 |
+
| 0.8452 | 11.0769 | 36 | 3.3804 |
|
66 |
|
67 |
|
68 |
### Framework versions
|
runs/Oct22_09-52-11_99867d27916d/events.out.tfevents.1729590732.99867d27916d.882.27
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c3d96a4cccd99d3cd9b8b3b194571897b2b758b3827d9ecb91508995f10fbc8
|
3 |
+
size 11650
|
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 sha256:046196edb25c5e9bded3350424bc9083e2e49b364edae8bb35ab1217ab49f251
|
3 |
size 5240
|