Update README.md
Browse files
README.md
CHANGED
@@ -27,7 +27,7 @@ We present the dev results on XNLI with zero-shot crosslingual transfer setting,
|
|
27 |
|
28 |
| Model |avg | en | fr| es | de | el | bg | ru |tr |ar |vi | th | zh | hi | sw | ur |
|
29 |
|--------------| ----|----|----|---- |-- |-- |-- | -- |-- |-- |-- | -- | -- | -- | -- | -- |
|
30 |
-
| XLM-R-base |
|
31 |
| mDeBERTa-base|**79.8**+/-0.2|**88.2**|**82.6**|**84.4** |**82.7** |**82.3** |**82.4** |**80.8** |**79.5** |**78.5** |**78.1** |**76.4** |**79.5**| **75.9**| **73.9**| **72.4**|
|
32 |
|
33 |
#### Fine-tuning with HF transformers
|
@@ -51,8 +51,8 @@ python -m torch.distributed.launch --nproc_per_node=${num_gpus} \
|
|
51 |
--task_name $TASK_NAME \
|
52 |
--do_train \
|
53 |
--do_eval \
|
54 |
-
|
55 |
-
|
56 |
--evaluation_strategy steps \
|
57 |
--max_seq_length 256 \
|
58 |
--warmup_steps 3000 \
|
|
|
27 |
|
28 |
| Model |avg | en | fr| es | de | el | bg | ru |tr |ar |vi | th | zh | hi | sw | ur |
|
29 |
|--------------| ----|----|----|---- |-- |-- |-- | -- |-- |-- |-- | -- | -- | -- | -- | -- |
|
30 |
+
| XLM-R-base |76.2 |85.8|79.7|80.7 |78.7 |77.5 |79.6 |78.1 |74.2 |73.8 |76.5 |74.6 |76.7| 72.4| 66.5| 68.3|
|
31 |
| mDeBERTa-base|**79.8**+/-0.2|**88.2**|**82.6**|**84.4** |**82.7** |**82.3** |**82.4** |**80.8** |**79.5** |**78.5** |**78.1** |**76.4** |**79.5**| **75.9**| **73.9**| **72.4**|
|
32 |
|
33 |
#### Fine-tuning with HF transformers
|
|
|
51 |
--task_name $TASK_NAME \
|
52 |
--do_train \
|
53 |
--do_eval \
|
54 |
+
--train_language en \
|
55 |
+
--language en \
|
56 |
--evaluation_strategy steps \
|
57 |
--max_seq_length 256 \
|
58 |
--warmup_steps 3000 \
|