Update README.md
Browse files
README.md
CHANGED
@@ -16,7 +16,7 @@ for testing purposes only. qlora trained using peft on codellama/CodeLlama-7b-hf
|
|
16 |
|
17 |
trained at 1000 steps with checkpoint every 50. training/validation loss below:
|
18 |
|
19 |
-
|
20 |
50 1.480500 0.935647
|
21 |
100 0.894800 0.867328
|
22 |
150 0.835700 0.841386
|
@@ -36,7 +36,7 @@ trained at 1000 steps with checkpoint every 50. training/validation loss below:
|
|
36 |
850 0.668700 0.669980
|
37 |
900 0.638100 0.669189
|
38 |
950 0.663200 0.668443
|
39 |
-
1000 0.668300 0.668069
|
40 |
|
41 |
training data transformed to the following structure for testing purposes:
|
42 |
```Example 1:
|
|
|
16 |
|
17 |
trained at 1000 steps with checkpoint every 50. training/validation loss below:
|
18 |
|
19 |
+
Step Training Loss Validation Loss
|
20 |
50 1.480500 0.935647
|
21 |
100 0.894800 0.867328
|
22 |
150 0.835700 0.841386
|
|
|
36 |
850 0.668700 0.669980
|
37 |
900 0.638100 0.669189
|
38 |
950 0.663200 0.668443
|
39 |
+
1000 0.668300 0.668069
|
40 |
|
41 |
training data transformed to the following structure for testing purposes:
|
42 |
```Example 1:
|