Upload TFBertForSequenceClassification

README.md

@@ -12,10 +12,11 @@ probably proofread and complete it, then remove this comment. -->
 
 # Textclassification-Bert
 
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on CoLA dataset.
+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: 0.1482
-- Validation Loss: 0.5542
+- Train Loss: 0.1439
+- Validation Loss: 0.5583
+- Train Matthews Correlation: 0.5803
 - Epoch: 2
 
 ## Model description
@@ -40,16 +41,16 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Train Loss | Validation Loss | Epoch |
-|:----------:|:---------------:|:-----:|
-| 0.4836     | 0.3981          | 0     |
-| 0.2721     | 0.4357          | 1     |
-| 0.1482     | 0.5542          | 2     |
+| Train Loss | Validation Loss | Train Matthews Correlation | Epoch |
+|:----------:|:---------------:|:--------------------------:|:-----:|
+| 0.4792     | 0.4276          | 0.5446                     | 0     |
+| 0.2664     | 0.4445          | 0.5602                     | 1     |
+| 0.1439     | 0.5583          | 0.5803                     | 2     |
 
 
 ### Framework versions
 
-- Transformers 4.28.1
+- Transformers 4.29.2
 - TensorFlow 2.12.0
 - Datasets 2.12.0
 - Tokenizers 0.13.3

config.json

@@ -26,7 +26,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.28.1",
+  "transformers_version": "4.29.2",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1d93d8bf4a3e56435ff7be40fa7499fcfe5dee41a69eaa42d9776a4e9c73d2a
+oid sha256:4895e0b15c6a6074e9538c3898c55ef70b923f0eb59981f8169d7d83975cba8c
 size 438223128