Upload TFBertForSequenceClassification

README.md

@@ -16,11 +16,7 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google-bert/bert-base-multilingual-uncased](https://huggingface.co/google-bert/bert-base-multilingual-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.4675
-- Train Accuracy: 0.8051
-- Validation Loss: 0.7446
-- Validation Accuracy: 0.6894
-- Epoch: 2
+
 
 ## Model description
 
@@ -44,11 +40,6 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
-|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
-| 0.8694     | 0.5902         | 0.8641          | 0.6335              | 0     |
-| 0.5907     | 0.7526         | 0.7781          | 0.6832              | 1     |
-| 0.4675     | 0.8051         | 0.7446          | 0.6894              | 2     |
 
 
 ### Framework versions