add model

README.md

@@ -3,22 +3,22 @@ license: mit
 tags:
 - generated_from_keras_callback
 model-index:
-- name: jonaskoenig/topic_classification_03
+- name: topic_classification_03
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information Keras had access to. You should
 probably proofread and complete it, then remove this comment. -->
 
-# jonaskoenig/topic_classification_03
+# topic_classification_03
 
 This model is a fine-tuned version of [microsoft/xtremedistil-l6-h256-uncased](https://huggingface.co/microsoft/xtremedistil-l6-h256-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 1.0662
-- Train Sparse Categorical Accuracy: 0.6473
-- Validation Loss: 1.1182
-- Validation Sparse Categorical Accuracy: 0.6344
-- Epoch: 4
+- Train Loss: 1.0459
+- Train Sparse Categorical Accuracy: 0.6535
+- Validation Loss: 1.1181
+- Validation Sparse Categorical Accuracy: 0.6354
+- Epoch: 5
 
 ## Model description
 
@@ -49,6 +49,7 @@ The following hyperparameters were used during training:
 | 1.1163     | 0.6314                            | 1.1247          | 0.6292                                 | 2     |
 | 1.0888     | 0.6400                            | 1.1253          | 0.6323                                 | 3     |
 | 1.0662     | 0.6473                            | 1.1182          | 0.6344                                 | 4     |
+| 1.0459     | 0.6535                            | 1.1181          | 0.6354                                 | 5     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dbe8c6c5793e1d8fc5aff6ab638d74a24e198463b13b4a2764b8f916666e405
+oid sha256:fd6cf4d9fb2c38dccf4e8e17ee1e7ccedf37258eb0ff0b4eaf65e23055a56b80
 size 51159352