Upload TFBertForSequenceClassification

README.md

@@ -14,10 +14,10 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.5699
-- Train Accuracy: 0.7050
-- Validation Loss: 0.6535
-- Validation Accuracy: 0.5310
+- Train Loss: 0.5204
+- Train Accuracy: 0.7552
+- Validation Loss: 0.5316
+- Validation Accuracy: 0.7478
 - Epoch: 2
 
 ## Model description
@@ -44,9 +44,9 @@ The following hyperparameters were used during training:
 
 | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
 |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
-| 0.6465     | 0.6342         | 0.5810          | 0.6947              | 0     |
-| 0.6110     | 0.6711         | 0.5739          | 0.7478              | 1     |
-| 0.5699     | 0.7050         | 0.6535          | 0.5310              | 2     |
+| 0.6140     | 0.6549         | 0.5368          | 0.7699              | 0     |
+| 0.5649     | 0.7360         | 0.5733          | 0.6903              | 1     |
+| 0.5204     | 0.7552         | 0.5316          | 0.7478              | 2     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b56df855cf611ab86b77681cb60cbbece1d1ea8b92ccd4de921ce0127f6da4b4
+oid sha256:7732363dd243bb8ebf044ab5b29ecc43bd813f3f130bc8d843b081db8653c802
 size 438223128