shawgpt-ft-lr2e-05-wd0.001
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: 4.
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -52,15 +52,15 @@ The following hyperparameters were used during training:
|
|
52 |
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
|:-------------:|:------:|:----:|:---------------:|
|
54 |
| 25.5434 | 0.5714 | 1 | 4.2401 |
|
55 |
-
| 25.
|
56 |
-
| 25.
|
57 |
-
| 25.
|
58 |
-
| 25.
|
59 |
-
| 25.
|
60 |
-
| 25.
|
61 |
-
| 25.
|
62 |
-
| 25.
|
63 |
-
| 16.
|
64 |
|
65 |
|
66 |
### 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: 4.1499
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
52 |
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
|:-------------:|:------:|:----:|:---------------:|
|
54 |
| 25.5434 | 0.5714 | 1 | 4.2401 |
|
55 |
+
| 25.8658 | 1.5714 | 2 | 4.2350 |
|
56 |
+
| 25.5046 | 2.5714 | 3 | 4.2167 |
|
57 |
+
| 25.48 | 3.5714 | 4 | 4.2006 |
|
58 |
+
| 25.2746 | 4.5714 | 5 | 4.1864 |
|
59 |
+
| 25.2152 | 5.5714 | 6 | 4.1744 |
|
60 |
+
| 25.1326 | 6.5714 | 7 | 4.1646 |
|
61 |
+
| 25.2366 | 7.5714 | 8 | 4.1574 |
|
62 |
+
| 25.1957 | 8.5714 | 9 | 4.1522 |
|
63 |
+
| 16.3685 | 9.5714 | 10 | 4.1499 |
|
64 |
|
65 |
|
66 |
### Framework versions
|
runs/Feb18_20-08-13_9a3887f9873e/events.out.tfevents.1739909293.9a3887f9873e.3474.18
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be2ef5deeefb1009e707a9a5438d7ff7869a9eda05c7823ed2fbab79a37ef118
|
3 |
+
size 10847
|
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 sha256:7ad0b17c3549fa415bdc4e6560e9dd19624d3505aaeff66ce0827daeeafcee4a
|
3 |
size 5368
|