Update README
Browse files
README.md
CHANGED
@@ -27,7 +27,7 @@ Tokenizer:
|
|
27 |
Training details:
|
28 |
|
29 |
* Training started on step 360K (bs 16) ppl 21 of earlier model trained with Adam optimizer.
|
30 |
-
* Training at step
|
31 |
* Block size: 512
|
32 |
* Optimizer: adafactor
|
33 |
* Learning rate: 3.3e-5
|
|
|
27 |
Training details:
|
28 |
|
29 |
* Training started on step 360K (bs 16) ppl 21 of earlier model trained with Adam optimizer.
|
30 |
+
* Training at step 1100K of 2082K (53%) pp 15,1
|
31 |
* Block size: 512
|
32 |
* Optimizer: adafactor
|
33 |
* Learning rate: 3.3e-5
|