Update README.md
Browse files
README.md
CHANGED
@@ -20,10 +20,11 @@ inference: False
|
|
20 |
|
21 |
## Updates
|
22 |
|
23 |
-
_As I
|
24 |
|
|
|
25 |
- July 8, 2022: add checkpoint with ~4 epochs of training on A100, equating to approx 350 steps of functional batch size 128
|
26 |
-
- July 4, 2022: add checkpoint with
|
27 |
|
28 |
## About
|
29 |
|
|
|
20 |
|
21 |
## Updates
|
22 |
|
23 |
+
_As I update this WIP checkpoint, I will post a note here._
|
24 |
|
25 |
+
- July 26, 2022: add two more epochs of training, metrics starting to be _almost_ as good as the more-tuned `base` variant
|
26 |
- July 8, 2022: add checkpoint with ~4 epochs of training on A100, equating to approx 350 steps of functional batch size 128
|
27 |
+
- July 4, 2022: add checkpoint with six additional epochs of training with the dataset summary outputs filtered to 1024 **tokens**, resolving the prior issue of short summaries.
|
28 |
|
29 |
## About
|
30 |
|