Commit
•
683fb3c
1
Parent(s):
bd56622
Model save
Browse files
README.md
CHANGED
|
@@ -17,6 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
# spam-llama3.1-8B-teacher
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the None dataset.
|
|
|
|
|
|
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -47,6 +49,16 @@ The following hyperparameters were used during training:
|
|
| 47 |
- num_epochs: 1
|
| 48 |
- mixed_precision_training: Native AMP
|
| 49 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
### Framework versions
|
| 51 |
|
| 52 |
- PEFT 0.12.0
|
|
|
|
| 17 |
# spam-llama3.1-8B-teacher
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.7016
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 49 |
- num_epochs: 1
|
| 50 |
- mixed_precision_training: Native AMP
|
| 51 |
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 56 |
+
| 1.5284 | 0.2010 | 56 | 1.7909 |
|
| 57 |
+
| 1.7991 | 0.4020 | 112 | 1.7383 |
|
| 58 |
+
| 1.1971 | 0.6030 | 168 | 1.7155 |
|
| 59 |
+
| 1.2984 | 0.8039 | 224 | 1.7016 |
|
| 60 |
+
|
| 61 |
+
|
| 62 |
### Framework versions
|
| 63 |
|
| 64 |
- PEFT 0.12.0
|