Training in progress epoch 0

README.md

@@ -13,11 +13,11 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base-sentiment-latest](https://huggingface.co/cardiffnlp/twitter-roberta-base-sentiment-latest) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.6622
-- Train Sparse Categorical Accuracy: 0.7344
-- Validation Loss: 0.1410
-- Validation Sparse Categorical Accuracy: 1.0
-- Epoch: 2
+- Train Loss: 1.1272
+- Train Sparse Categorical Accuracy: 0.3281
+- Validation Loss: 1.0190
+- Validation Sparse Categorical Accuracy: 0.3333
+- Epoch: 0
 
 ## Model description
 
@@ -43,9 +43,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Train Sparse Categorical Accuracy | Validation Loss | Validation Sparse Categorical Accuracy | Epoch |
 |:----------:|:---------------------------------:|:---------------:|:--------------------------------------:|:-----:|
-| 1.0655     | 0.4844                            | 0.6441          | 1.0                                    | 0     |
-| 0.8696     | 0.6719                            | 0.2738          | 1.0                                    | 1     |
-| 0.6622     | 0.7344                            | 0.1410          | 1.0                                    | 2     |
+| 1.1272     | 0.3281                            | 1.0190          | 0.3333                                 | 0     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4002bcc6cd53407cf2e5c8581f7d72a2d757faad6c6ddf23140c468f5fbac8bd
+oid sha256:64242399b6247d2a098be98c0849f1db9989263efe5c3207cfafa13f5e39896d
 size 498865280