add model

README.md

@@ -3,20 +3,20 @@ license: mit
 tags:
 - generated_from_keras_callback
 model-index:
-- name: jonaskoenig/topic_classification_04
+- name: topic_classification_04
   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_04
+# topic_classification_04
 
 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: 0.8448
-- Train Sparse Categorical Accuracy: 0.7199
-- Epoch: 8
+- Train Loss: 0.8325
+- Train Sparse Categorical Accuracy: 0.7237
+- Epoch: 9
 
 ## Model description
 
@@ -51,6 +51,7 @@ The following hyperparameters were used during training:
 | 0.8707     | 0.7120                            | 6     |
 | 0.8578     | 0.7160                            | 7     |
 | 0.8448     | 0.7199                            | 8     |
+| 0.8325     | 0.7237                            | 9     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7039a7d20cec3949b1d13c9aa1599b1708a576661c1dbe91a278de33b34ef54a
+oid sha256:decfe12b70109af8215318fbc5150e8effb55949fa9897ce23981bbbaf6844ba
 size 51159352