Update README.md
Browse files
README.md
CHANGED
@@ -23,7 +23,7 @@ Training Configuration
|
|
23 |
- Training Dataset: samheym/ger-dpr-collection
|
24 |
- Dataset: 10% of randomly selected triples from the final dataset
|
25 |
- Vector Length: 128
|
26 |
-
- Maximum Document Length: 256
|
27 |
- Batch Size: 50
|
28 |
- Training Steps: 80,000
|
29 |
- Gradient Accumulation: 1 step
|
|
|
23 |
- Training Dataset: samheym/ger-dpr-collection
|
24 |
- Dataset: 10% of randomly selected triples from the final dataset
|
25 |
- Vector Length: 128
|
26 |
+
- Maximum Document Length: 256 Tokens
|
27 |
- Batch Size: 50
|
28 |
- Training Steps: 80,000
|
29 |
- Gradient Accumulation: 1 step
|