Training in progress epoch 3

README.md

@@ -15,13 +15,13 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/electra-small-discriminator](https://huggingface.co/google/electra-small-discriminator) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 2.1054
-- Train End Logits Accuracy: 0.5011
-- Train Start Logits Accuracy: 0.4714
-- Validation Loss: 1.6636
-- Validation End Logits Accuracy: 0.5884
-- Validation Start Logits Accuracy: 0.5755
-- Epoch: 2
+- Train Loss: 1.9002
+- Train End Logits Accuracy: 0.5421
+- Train Start Logits Accuracy: 0.5122
+- Validation Loss: 1.4655
+- Validation End Logits Accuracy: 0.6276
+- Validation Start Logits Accuracy: 0.6173
+- Epoch: 3
 
 ## Model description
 
@@ -50,6 +50,7 @@ The following hyperparameters were used during training:
 | 3.0718     | 0.3197                    | 0.2882                      | 2.3841          | 0.4358                         | 0.4158                           | 0     |
 | 2.4050     | 0.4412                    | 0.4100                      | 1.9607          | 0.5286                         | 0.5126                           | 1     |
 | 2.1054     | 0.5011                    | 0.4714                      | 1.6636          | 0.5884                         | 0.5755                           | 2     |
+| 1.9002     | 0.5421                    | 0.5122                      | 1.4655          | 0.6276                         | 0.6173                           | 3     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1868fb8310ba865a7b6d7895f3969e1a909e1634c9af0abf9786bb350c84d00
+oid sha256:35038faa7e28ac740a1912c2b2ffd77ea1d7edd306f9fccf8ad2ca58a30ff5da
 size 54221088