Upload TFDistilBertForSequenceClassification

README.md

@@ -14,11 +14,11 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.7088
-- Train Sparse Categorical Accuracy: 0.3250
-- Validation Loss: 0.6958
-- Validation Sparse Categorical Accuracy: 0.3000
-- Epoch: 0
+- Train Loss: 0.0254
+- Train Sparse Categorical Accuracy: 0.9922
+- Validation Loss: 0.3001
+- Validation Sparse Categorical Accuracy: 0.9276
+- Epoch: 4
 
 ## Model description
 
@@ -44,7 +44,11 @@ The following hyperparameters were used during training:
 
 | Train Loss | Train Sparse Categorical Accuracy | Validation Loss | Validation Sparse Categorical Accuracy | Epoch |
 |:----------:|:---------------------------------:|:---------------:|:--------------------------------------:|:-----:|
-| 0.7088     | 0.3250                            | 0.6958          | 0.3000                                 | 0     |
+| 0.2755     | 0.8848                            | 0.1893          | 0.9269                                 | 0     |
+| 0.1537     | 0.9419                            | 0.1946          | 0.9244                                 | 1     |
+| 0.0822     | 0.9723                            | 0.2246          | 0.9211                                 | 2     |
+| 0.0437     | 0.9865                            | 0.2782          | 0.9240                                 | 3     |
+| 0.0254     | 0.9922                            | 0.3001          | 0.9276                                 | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a51a41a77638be79c67af63bbe42b4a951307123f0d6f6277b85da6cc6ae07e4
-size 267951808
+oid sha256:dcf57b64dec267d11fc7831c23faf024fe414b43dcc90c1a3506212044176b2e
+size 267955144