Training in progress epoch 5

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: 0.0268
-- Train Binary Crossentropy: 0.4564
-- Validation Loss: 0.0250
-- Validation Binary Crossentropy: 0.4179
-- Epoch: 4
+- Train Loss: 0.0246
+- Train Binary Crossentropy: 0.4128
+- Validation Loss: 0.0231
+- Validation Binary Crossentropy: 0.3821
+- Epoch: 5
 
 ## Model description
 
@@ -49,6 +49,7 @@ The following hyperparameters were used during training:
 | 0.0336     | 0.5852                    | 0.0303          | 0.5096                         | 2     |
 | 0.0295     | 0.5047                    | 0.0275          | 0.4647                         | 3     |
 | 0.0268     | 0.4564                    | 0.0250          | 0.4179                         | 4     |
+| 0.0246     | 0.4128                    | 0.0231          | 0.3821                         | 5     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b968c1118f45a9a26cb81fb0b33d5bc89bcaa7dea33e39d038597dbf4ad84562
+oid sha256:b5b0dfd5a7a0fd5886a168384de27beb105f0a26acde41ec6e90a4d14ff69847
 size 51177784