Update README.md
Browse files
README.md
CHANGED
@@ -20,7 +20,7 @@ palmer is a series of ~1b parameters language models fine-tuned to be used as ba
|
|
20 |
|palmer-002|0.3242|**0.5956**|**0.7345**|0.5888|
|
21 |
|palmer-002-ultra|**0.3319**| 0.5877 |0.7252|**0.6038**|
|
22 |
|
23 |
-
This is a continuation on `palmer-x-002`.
|
24 |
|
25 |
### training
|
26 |
Training took ~7.5 P100 gpu hours. It was trained on 50,000 gpt-4 shuffled samples. palmer was fine-tuned using lower learning rates ensuring it keeps as much general knowledge as possible.
|
|
|
20 |
|palmer-002|0.3242|**0.5956**|**0.7345**|0.5888|
|
21 |
|palmer-002-ultra|**0.3319**| 0.5877 |0.7252|**0.6038**|
|
22 |
|
23 |
+
This is a continuation on `palmer-x-002`. As of now, this is the best overall model.
|
24 |
|
25 |
### training
|
26 |
Training took ~7.5 P100 gpu hours. It was trained on 50,000 gpt-4 shuffled samples. palmer was fine-tuned using lower learning rates ensuring it keeps as much general knowledge as possible.
|