Commit
•
3377fc8
1
Parent(s):
a522106
Update README.md
Browse files
README.md
CHANGED
|
@@ -225,9 +225,9 @@ The conversation indicates a model that may be based on an advanced language arc
|
|
| 225 |
As of **June 11, 2024**, I've finally **started training** the model! The training is progressing smoothly, although it will take some time. I used a combination of model merges and an abliterated model as base, followed by a comprehensive deep unalignment protocol to **unalign the model to its core**. A common issue with uncensoring and unaligning models is that it often **significantly** impacts their base intelligence. To mitigate these drawbacks, I've included a substantial corpus of common sense, theory of mind, and various other elements to counteract the effects of the deep uncensoring process. Given the extensive corpus involved, the training will require at least a week of continuous training. Expected early results: in about 3-4 days.
|
| 226 |
</details>
|
| 227 |
|
| 228 |
-
# Additional info:
|
| 229 |
<details>
|
| 230 |
-
<summary
|
|
|
|
| 231 |
|
| 232 |
These observations underscore the critical importance of fine-tuning for alignment. Given the current pace, training will likely extend beyond a week. However, the end result should be **interesting**. If the additional datasets focused on logic and common sense are effective, we should achieve a model that is **nearly completely unaligned**, while still retaining its core 'intelligence.'
|
| 233 |
<img src="https://i.imgur.com/b6unKyS.png" alt="LLAMA-3_Unaligned_Training" style="width: 60%; min-width: 600px; display: block; margin: auto;">
|
|
|
|
| 225 |
As of **June 11, 2024**, I've finally **started training** the model! The training is progressing smoothly, although it will take some time. I used a combination of model merges and an abliterated model as base, followed by a comprehensive deep unalignment protocol to **unalign the model to its core**. A common issue with uncensoring and unaligning models is that it often **significantly** impacts their base intelligence. To mitigate these drawbacks, I've included a substantial corpus of common sense, theory of mind, and various other elements to counteract the effects of the deep uncensoring process. Given the extensive corpus involved, the training will require at least a week of continuous training. Expected early results: in about 3-4 days.
|
| 226 |
</details>
|
| 227 |
|
|
|
|
| 228 |
<details>
|
| 229 |
+
<summary><b>June 13th, 2024</b></summary>
|
| 230 |
+
I've observed that even after two days of continuous training, the model is <b>still resistant to learning certain aspects</b>. For example, some of the validation data still shows a loss over <b>2.3</b>, whereas other parts have a loss of <<b>0.3</b> or lower. This is after the model was initially abliterated.
|
| 231 |
|
| 232 |
These observations underscore the critical importance of fine-tuning for alignment. Given the current pace, training will likely extend beyond a week. However, the end result should be **interesting**. If the additional datasets focused on logic and common sense are effective, we should achieve a model that is **nearly completely unaligned**, while still retaining its core 'intelligence.'
|
| 233 |
<img src="https://i.imgur.com/b6unKyS.png" alt="LLAMA-3_Unaligned_Training" style="width: 60%; min-width: 600px; display: block; margin: auto;">
|