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: 0.0345
-- Train Accuracy: 0.8923
-- Validation Loss: 0.0513
-- Validation Accuracy: 0.8414
+- Train Loss: 0.0297
+- Train Accuracy: 0.9041
+- Validation Loss: 0.0511
+- Validation Accuracy: 0.8462
 - Epoch: 2
 
 ## Model description
@@ -44,9 +44,9 @@ The following hyperparameters were used during training:
 
 | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
 |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
-| 0.0421     | 0.8796         | 0.0483          | 0.8364              | 0     |
-| 0.0393     | 0.8819         | 0.0478          | 0.8412              | 1     |
-| 0.0345     | 0.8923         | 0.0513          | 0.8414              | 2     |
+| 0.0417     | 0.8813         | 0.0471          | 0.8420              | 0     |
+| 0.0379     | 0.8833         | 0.0476          | 0.8399              | 1     |
+| 0.0297     | 0.9041         | 0.0511          | 0.8462              | 2     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c953a615ec0d5ec8041d4949d21a9382e3183e93eb67377afb55e3efe02b9f0d
+oid sha256:d05518ff30abc2add6aafbfef1abb31c64351790812585bde70b9d8c9ea1f4fb
 size 438223128