Upload TFBertForSequenceClassification

README.md

@@ -16,10 +16,10 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0745
-- Train Accuracy: 0.9845
-- Validation Loss: 0.0733
-- Validation Accuracy: 0.9873
+- Train Loss: 0.0754
+- Train Accuracy: 0.9847
+- Validation Loss: 0.0764
+- Validation Accuracy: 0.9855
 - Epoch: 2
 
 ## Model description
@@ -46,9 +46,9 @@ The following hyperparameters were used during training:
 
 | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
 |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
-| 0.2354     | 0.9629         | 0.0875          | 0.9858              | 0     |
-| 0.0718     | 0.9864         | 0.0991          | 0.9821              | 1     |
-| 0.0745     | 0.9845         | 0.0733          | 0.9873              | 2     |
+| 0.2388     | 0.9651         | 0.0972          | 0.9870              | 0     |
+| 0.0842     | 0.9833         | 0.0702          | 0.9861              | 1     |
+| 0.0754     | 0.9847         | 0.0764          | 0.9855              | 2     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22ae5f496639cb47a2afb5eb57c4a3ba6bde442767b3fa49557d26208ec0a141
+oid sha256:ea415771c48978d000f5eb7b9109e17aeeb771df4e8c6a10fa6e9b3b4aba8b7a
 size 711769448