Update README.md
Browse files
README.md
CHANGED
|
@@ -5,7 +5,6 @@ datasets:
|
|
| 5 |
---
|
| 6 |
## JGLUE Score
|
| 7 |
We evaluated our model using the following JGLUE tasks. Here are the scores:
|
| 8 |
-
|
| 9 |
| Task | Score |
|
| 10 |
|----------------|---------:|
|
| 11 |
| JSQUAD(exact_match) | 62.83 |
|
|
@@ -13,8 +12,8 @@ We evaluated our model using the following JGLUE tasks. Here are the scores:
|
|
| 13 |
| JNLI(acc) | 50.69 |
|
| 14 |
| MARC_JA(acc) | 79.64 |
|
| 15 |
| **Average** | **67.23** |
|
| 16 |
-
|
| 17 |
-
The JGLUE scores were measured using the following script:
|
| 18 |
[Stability-AI/lm-evaluation-harness](https://github.com/Stability-AI/lm-evaluation-harness/tree/jp-stable)
|
| 19 |
|
| 20 |
## Training procedure
|
|
|
|
| 5 |
---
|
| 6 |
## JGLUE Score
|
| 7 |
We evaluated our model using the following JGLUE tasks. Here are the scores:
|
|
|
|
| 8 |
| Task | Score |
|
| 9 |
|----------------|---------:|
|
| 10 |
| JSQUAD(exact_match) | 62.83 |
|
|
|
|
| 12 |
| JNLI(acc) | 50.69 |
|
| 13 |
| MARC_JA(acc) | 79.64 |
|
| 14 |
| **Average** | **67.23** |
|
| 15 |
+
- Note: Use v0.3 prompt template
|
| 16 |
+
- The JGLUE scores were measured using the following script:
|
| 17 |
[Stability-AI/lm-evaluation-harness](https://github.com/Stability-AI/lm-evaluation-harness/tree/jp-stable)
|
| 18 |
|
| 19 |
## Training procedure
|