Training in progress epoch 4

README.md

@@ -14,11 +14,11 @@ probably proofread and complete it, then remove this comment. -->
 
 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: 0.0299
-- Train Binary Crossentropy: 0.5146
-- Validation Loss: 0.0277
-- Validation Binary Crossentropy: 0.4839
-- Epoch: 3
+- Train Loss: 0.0272
+- Train Binary Crossentropy: 0.4642
+- Validation Loss: 0.0255
+- Validation Binary Crossentropy: 0.4240
+- Epoch: 4
 
 ## Model description
 
@@ -48,6 +48,7 @@ The following hyperparameters were used during training:
 | 0.0395     | 0.6218                    | 0.0356          | 0.6178                         | 1     |
 | 0.0337     | 0.5804                    | 0.0308          | 0.5594                         | 2     |
 | 0.0299     | 0.5146                    | 0.0277          | 0.4839                         | 3     |
+| 0.0272     | 0.4642                    | 0.0255          | 0.4240                         | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f3d70f6000fe94282caaf5a85133b63aeac53d4fb4e6da94ce3dfd46cdc829c
+oid sha256:fe58bd40391da8c94853b43fa48a7fb4522fd8c937064a32f8ceaf079a00db8f
 size 51177784