Update README.md

README.md

@@ -5,7 +5,7 @@ language:
 
 # Text Classification GoEmotions
 
-This model is a fined-tuned version of [nreimers/MiniLMv2-L6-H384-distilled-from-BERT-Large](https://huggingface.co/nreimers/MiniLMv2-L6-H384-distilled-from-BERT-Large) on the on the [Jigsaw 1st Kaggle competition](https://www.kaggle.com/competitions/jigsaw-toxic-comment-classification-challenge) dataset using [tasinho/text-classification-goemotions](https://huggingface.co/tasinhoque/text-classification-goemotions) as teacher model.
+This model is a fined-tuned version of [nreimers/MiniLMv2-L6-H384-distilled-from-BERT-Large](https://huggingface.co/nreimers/MiniLMv2-L6-H384-distilled-from-BERT-Large) on the on the [Jigsaw 1st Kaggle competition](https://www.kaggle.com/competitions/jigsaw-toxic-comment-classification-challenge) dataset using [unitary/toxic-bert](https://huggingface.co/unitary/toxic-bert) as teacher model.
 
 # Load the Model
 
@@ -26,14 +26,14 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 10
-- warmup-ratio: 0.1
+- warmup_ratio: 0.1
 
 
 # Metrics (comparison with teacher model)
 
 | Teacher (params)    |   Student (params)     | Set  (metric)     | Score (teacher)    |    Score (student)      |
 |--------------------|-------------|----------|--------| --------|
-| unitary/toxic-bert (110M) |      MiniLMv2-L6-H384-goemotions-v2 (33M)    | Test (ROC_AUC)  | 0.98636 |  0.98600 |
+| unitary/toxic-bert (110M) |  MiniLMv2-L6-H384-goemotions-v2 (33M)  | Test (ROC_AUC)  | 0.98636 |  0.98600 |
 
 # Training Code, Evaluation & Deployment