Update README.md
Browse files
README.md
CHANGED
|
@@ -61,8 +61,9 @@ We tuned learning rate and training epochs for each model and task following [th
|
|
| 61 |
|
| 62 |
For tasks other than MARC-ja, the maximum length is short, so the attention_type was set to "original_full" and fine-tuning was performed for tasks other than MARC-ja. For MARC-ja, both "block_sparse" and "original_full" were used.
|
| 63 |
|
| 64 |
-
| Model |
|
| 65 |
-
|
| 66 |
-
| Waseda RoBERTa base |
|
| 67 |
-
| Waseda RoBERTa large (seq512) |
|
| 68 |
-
| BigBird base |
|
|
|
|
|
|
| 61 |
|
| 62 |
For tasks other than MARC-ja, the maximum length is short, so the attention_type was set to "original_full" and fine-tuning was performed for tasks other than MARC-ja. For MARC-ja, both "block_sparse" and "original_full" were used.
|
| 63 |
|
| 64 |
+
| Model | MARC-ja(original_full)/acc | JSTS/pearson | JSTS/spearman | JNLI/acc | JSQuAD/EM | JSQuAD/F1 | JComQA/acc |
|
| 65 |
+
|-------------------------------|--------------|---------------|----------|-----------|-----------|------------|------------|
|
| 66 |
+
| Waseda RoBERTa base | 0.965 | 0.913 | 0.876 | 0.905 | 0.853 | 0.916 | 0.853 |
|
| 67 |
+
| Waseda RoBERTa large (seq512) | 0.969 | 0.925 | 0.890 | 0.928 | 0.910 | 0.955 | 0.900 |
|
| 68 |
+
| BigBird base (original_full) |0.959 | 0.888 | 0.846 | 0.896 | 0.884 | 0.933 | 0.787 |
|
| 69 |
+
| BigBird base (block_sparse) |0.959 | - | - | - | - | - | - |
|