Model save
Browse files
README.md
CHANGED
|
@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the generator dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss: 0.
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
@@ -55,15 +55,15 @@ The following hyperparameters were used during training:
|
|
| 55 |
|
| 56 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 57 |
|:-------------:|:------:|:----:|:---------------:|
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
|
| 68 |
|
| 69 |
### Framework versions
|
|
|
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the generator dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.6452
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
|
|
| 55 |
|
| 56 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 57 |
|:-------------:|:------:|:----:|:---------------:|
|
| 58 |
+
| 0.7976 | 0.2146 | 50 | 0.8180 |
|
| 59 |
+
| 0.7427 | 0.4292 | 100 | 0.7618 |
|
| 60 |
+
| 0.7449 | 0.6438 | 150 | 0.7284 |
|
| 61 |
+
| 0.6912 | 0.8584 | 200 | 0.6968 |
|
| 62 |
+
| 0.5697 | 1.0730 | 250 | 0.6920 |
|
| 63 |
+
| 0.5641 | 1.2876 | 300 | 0.6837 |
|
| 64 |
+
| 0.5407 | 1.5021 | 350 | 0.6624 |
|
| 65 |
+
| 0.5387 | 1.7167 | 400 | 0.6548 |
|
| 66 |
+
| 0.5464 | 1.9313 | 450 | 0.6452 |
|
| 67 |
|
| 68 |
|
| 69 |
### Framework versions
|