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: 0.0100
-- Train Accuracy: 0.4876
-- Validation Loss: 0.0147
-- Validation Accuracy: 0.3091
+- Train Loss: 0.0099
+- Train Accuracy: 0.4922
+- Validation Loss: 0.0150
+- Validation Accuracy: 0.3268
 - Epoch: 2
 
 ## Model description
@@ -44,9 +44,9 @@ The following hyperparameters were used during training:
 
 | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
 |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
-| 0.0124     | 0.4873         | 0.0155          | 0.5842              | 0     |
-| 0.0115     | 0.4832         | 0.0143          | 0.5168              | 1     |
-| 0.0100     | 0.4876         | 0.0147          | 0.3091              | 2     |
+| 0.0124     | 0.4999         | 0.0151          | 0.3214              | 0     |
+| 0.0114     | 0.4985         | 0.0148          | 0.6656              | 1     |
+| 0.0099     | 0.4922         | 0.0150          | 0.3268              | 2     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc1f6e41ea85da9a5420b74b3831e2a8c9f0da9fc6ecbe4f18a673237950bb70
+oid sha256:15c15abaef5c2fb756dbab29cbd942746cb0c9899e44014b2626dfb5441c3b63
 size 438223128