morit commited on
Commit
286086d
1 Parent(s): 3abdf04

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -29,7 +29,7 @@ classifier = pipeline("zero-shot-classification",
29
 
30
 
31
  ## Training
32
- This model was pre-trained on a set of 100 languages and follwed further training on 198M multilingual tweets as described in the original [paper](https://arxiv.org/abs/2104.12250). Further it was trained on the training set of XNLI dataset in hindi which is a machine translated version of the MNLI dataset. It was trained on 5 epochs of the XNLI train set and evaluated on the XNLI eval dataset at the end of every to find the best performing model. The model which had the highest accuracy on the eval set was chosen at the end.
33
 
34
  ![Training Charts from wandb](screen_wandb.png)
35
  - learning rate: 2e-5
 
29
 
30
 
31
  ## Training
32
+ This model was pre-trained on a set of 100 languages and follwed further training on 198M multilingual tweets as described in the original [paper](https://arxiv.org/abs/2104.12250). Further it was trained on the training set of XNLI dataset in hindi which is a machine translated version of the MNLI dataset. It was trained on 5 epochs of the XNLI train set and evaluated on the XNLI eval dataset at the end of every epoch to find the best performing model. The model which had the highest accuracy on the eval set was chosen at the end.
33
 
34
  ![Training Charts from wandb](screen_wandb.png)
35
  - learning rate: 2e-5