End of training
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 [NickyNicky/Mistral-7B-OpenOrca-oasst_top1_2023-08-25-v2](https://huggingface.co/NickyNicky/Mistral-7B-OpenOrca-oasst_top1_2023-08-25-v2) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 0.
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -49,22 +49,22 @@ The following hyperparameters were used during training:
|
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|
|
52 |
-
| 1.
|
53 |
-
| 1.
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
|
69 |
|
70 |
### Framework versions
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [NickyNicky/Mistral-7B-OpenOrca-oasst_top1_2023-08-25-v2](https://huggingface.co/NickyNicky/Mistral-7B-OpenOrca-oasst_top1_2023-08-25-v2) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.1361
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|
|
52 |
+
| 1.6926 | 0.35 | 25 | 1.2134 |
|
53 |
+
| 1.0257 | 0.7 | 50 | 0.8432 |
|
54 |
+
| 0.7181 | 1.06 | 75 | 0.6250 |
|
55 |
+
| 0.5143 | 1.41 | 100 | 0.4992 |
|
56 |
+
| 0.3899 | 1.76 | 125 | 0.3987 |
|
57 |
+
| 0.3433 | 2.11 | 150 | 0.3065 |
|
58 |
+
| 0.1736 | 2.46 | 175 | 0.2739 |
|
59 |
+
| 0.26 | 2.82 | 200 | 0.2005 |
|
60 |
+
| 0.1403 | 3.17 | 225 | 0.2055 |
|
61 |
+
| 0.1211 | 3.52 | 250 | 0.1642 |
|
62 |
+
| 0.1243 | 3.87 | 275 | 0.1487 |
|
63 |
+
| 0.0737 | 4.23 | 300 | 0.1565 |
|
64 |
+
| 0.0867 | 4.58 | 325 | 0.1590 |
|
65 |
+
| 0.0863 | 4.93 | 350 | 0.1355 |
|
66 |
+
| 0.0627 | 5.28 | 375 | 0.1360 |
|
67 |
+
| 0.0609 | 5.63 | 400 | 0.1361 |
|
68 |
|
69 |
|
70 |
### Framework versions
|