End of training
Browse files
README.md
CHANGED
|
@@ -14,7 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
# Llama-3-8B-wikihow
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
@@ -43,6 +45,17 @@ The following hyperparameters were used during training:
|
|
| 43 |
- lr_scheduler_type: linear
|
| 44 |
- training_steps: 100
|
| 45 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
### Framework versions
|
| 47 |
|
| 48 |
- PEFT 0.11.1
|
|
|
|
| 14 |
|
| 15 |
# Llama-3-8B-wikihow
|
| 16 |
|
| 17 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.9372
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
- training_steps: 100
|
| 47 |
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 52 |
+
| 2.1959 | 0.0323 | 20 | 2.0083 |
|
| 53 |
+
| 2.0718 | 0.0646 | 40 | 1.9825 |
|
| 54 |
+
| 2.0301 | 0.0970 | 60 | 1.9742 |
|
| 55 |
+
| 2.0023 | 0.1293 | 80 | 1.9466 |
|
| 56 |
+
| 1.9633 | 0.1616 | 100 | 1.9372 |
|
| 57 |
+
|
| 58 |
+
|
| 59 |
### Framework versions
|
| 60 |
|
| 61 |
- PEFT 0.11.1
|