Update README.md
Browse files
README.md
CHANGED
@@ -65,8 +65,10 @@ Format: Instruction → Input (context) → Response (question)
|
|
65 |
|
66 |
|
67 |
## Training Performance:
|
68 |
-
|
69 |
-
|
|
|
|
|
70 |
|
71 |
- This exhibits a strong convergence for a fine-tuned instruction.
|
72 |
- The validation loss curve flattens under 2.0, which is a great sign for generative quality.
|
|
|
65 |
|
66 |
|
67 |
## Training Performance:
|
68 |
+
=======================================
|
69 |
+
Step | Train Loss | Validation Loss
|
70 |
+
=======================================
|
71 |
+
400 | 1.780 | 1.795
|
72 |
|
73 |
- This exhibits a strong convergence for a fine-tuned instruction.
|
74 |
- The validation loss curve flattens under 2.0, which is a great sign for generative quality.
|