Update README.md
Browse files
README.md
CHANGED
|
@@ -11,6 +11,13 @@ model-index:
|
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
| 15 |
<details><summary>See axolotl config</summary>
|
| 16 |
|
|
|
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
|
| 14 |
+
Catastrophic forgetting test results:
|
| 15 |
+
|
| 16 |
+
Initial evaluation loss on 1k subset of HuggingFaceTB/cosmopedia-100k dataset was 1.217. 100 steps of LISA training reduced this to 1.153.
|
| 17 |
+
|
| 18 |
+
Comparison to control:
|
| 19 |
+
cosmo-1b started out with 1.003 loss on (a different subset of) dataset, increasing to 1.024 at 100 steps.
|
| 20 |
+
|
| 21 |
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
| 22 |
<details><summary>See axolotl config</summary>
|
| 23 |
|