Upload TFRobertaForSequenceClassification

README.md

@@ -12,10 +12,11 @@ probably proofread and complete it, then remove this comment. -->
 
 # TextClassification-RoBERTa
 
-This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on GLUE(CoLA) dataset.
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.1953
-- Validation Loss: 0.5320
+- Train Loss: 0.1854
+- Validation Loss: 0.5199
+- Train Matthews Correlation: 0.5982
 - Epoch: 2
 
 ## Model description
@@ -40,16 +41,16 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Train Loss | Validation Loss | Epoch |
-|:----------:|:---------------:|:-----:|
-| 0.5069     | 0.4623          | 0     |
-| 0.3180     | 0.4570          | 1     |
-| 0.1953     | 0.5320          | 2     |
+| Train Loss | Validation Loss | Train Matthews Correlation | Epoch |
+|:----------:|:---------------:|:--------------------------:|:-----:|
+| 0.5037     | 0.4198          | 0.5498                     | 0     |
+| 0.3035     | 0.4965          | 0.5727                     | 1     |
+| 0.1854     | 0.5199          | 0.5982                     | 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

@@ -27,7 +27,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.28.1",
+  "transformers_version": "4.29.2",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 50265

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5146a2ecabb9ddea7fd8ae6c1ce41cdca274f4df9646da5b70535f69d3c36a7d
+oid sha256:ceda952c99d1d01cbf207995a5fd7a0b7b625898862006594588bec515a95941
 size 498878272