Model card updated after epoch 20
Browse files
README.md
CHANGED
|
@@ -18,6 +18,6 @@ The model utilizes the HRM structure, consisting of a "Specialist" module for lo
|
|
| 18 |
- **Vocab Size**: 32100
|
| 19 |
- **Objective:** Causal Language Modeling
|
| 20 |
|
| 21 |
-
### Latest Performance (Epoch
|
| 22 |
-
- **Validation Loss**: `3.
|
| 23 |
-
- **Validation Perplexity**: `
|
|
|
|
| 18 |
- **Vocab Size**: 32100
|
| 19 |
- **Objective:** Causal Language Modeling
|
| 20 |
|
| 21 |
+
### Latest Performance (Epoch 20)
|
| 22 |
+
- **Validation Loss**: `3.6668`
|
| 23 |
+
- **Validation Perplexity**: `39.13`
|