Update README.md
Browse files
README.md
CHANGED
|
@@ -45,8 +45,8 @@ Due to the sparse nature of the MoE layers, approximately **43% of the parameter
|
|
| 45 |
|
| 46 |
Training is currently in progress on a single NVIDIA RTX 5000.
|
| 47 |
|
| 48 |
-
* **Current Step:**
|
| 49 |
-
* **Current Loss:** ~
|
| 50 |
* **Dataset:** A subset of SlimPajama-627B
|
| 51 |
|
| 52 |
> **⚠️ Performance Notice:** Aetheris is currently in a "proof-of-concept" state. While it generates coherent English syntax, it does not yet possess strong reasoning capabilities. It is intended for architectural analysis rather than downstream tasks.
|
|
|
|
| 45 |
|
| 46 |
Training is currently in progress on a single NVIDIA RTX 5000.
|
| 47 |
|
| 48 |
+
* **Current Step:** 12,000
|
| 49 |
+
* **Current Loss:** ~2.64
|
| 50 |
* **Dataset:** A subset of SlimPajama-627B
|
| 51 |
|
| 52 |
> **⚠️ Performance Notice:** Aetheris is currently in a "proof-of-concept" state. While it generates coherent English syntax, it does not yet possess strong reasoning capabilities. It is intended for architectural analysis rather than downstream tasks.
|