Model save
Browse files
README.md
CHANGED
|
@@ -19,6 +19,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 19 |
# granite-8b-code-instruct-spider
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [ibm-granite/granite-8b-code-instruct](https://huggingface.co/ibm-granite/granite-8b-code-instruct) on the generator dataset.
|
|
|
|
|
|
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -50,6 +52,17 @@ The following hyperparameters were used during training:
|
|
| 50 |
|
| 51 |
### Training results
|
| 52 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
|
| 54 |
|
| 55 |
### Framework versions
|
|
|
|
| 19 |
# granite-8b-code-instruct-spider
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [ibm-granite/granite-8b-code-instruct](https://huggingface.co/ibm-granite/granite-8b-code-instruct) on the generator dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.8823
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
|
|
| 52 |
|
| 53 |
### Training results
|
| 54 |
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 56 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 57 |
+
| 0.1877 | 0.1 | 100 | 0.6620 |
|
| 58 |
+
| 0.0784 | 0.2 | 200 | 0.6879 |
|
| 59 |
+
| 0.0552 | 0.3 | 300 | 0.7506 |
|
| 60 |
+
| 0.0607 | 0.4 | 400 | 0.8319 |
|
| 61 |
+
| 0.049 | 0.51 | 500 | 0.8430 |
|
| 62 |
+
| 0.0485 | 0.61 | 600 | 0.8774 |
|
| 63 |
+
| 0.0448 | 0.71 | 700 | 0.8839 |
|
| 64 |
+
| 0.0478 | 0.81 | 800 | 0.8807 |
|
| 65 |
+
| 0.0472 | 0.91 | 900 | 0.8823 |
|
| 66 |
|
| 67 |
|
| 68 |
### Framework versions
|