Training in progress epoch 29

README.md

@@ -15,10 +15,10 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.1321
-- Validation Loss: 0.6181
-- Train Accuracy: 0.9
-- Epoch: 20
+- Train Loss: 0.0645
+- Validation Loss: 0.5256
+- Train Accuracy: 0.89
+- Epoch: 29
 
 ## Model description
 
@@ -65,6 +65,15 @@ The following hyperparameters were used during training:
 | 0.1625     | 0.6388          | 0.8967         | 18    |
 | 0.1422     | 0.6158          | 0.9033         | 19    |
 | 0.1321     | 0.6181          | 0.9            | 20    |
+| 0.1187     | 0.5910          | 0.8933         | 21    |
+| 0.1072     | 0.5873          | 0.8967         | 22    |
+| 0.0988     | 0.5725          | 0.8967         | 23    |
+| 0.0902     | 0.5619          | 0.8967         | 24    |
+| 0.0844     | 0.5506          | 0.8967         | 25    |
+| 0.0776     | 0.5489          | 0.89           | 26    |
+| 0.0724     | 0.5411          | 0.8933         | 27    |
+| 0.0687     | 0.5280          | 0.8933         | 28    |
+| 0.0645     | 0.5256          | 0.89           | 29    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec7b08f883d2ec35c638dca6f8234830003d319a0291a61963828c07e671d2a4
+oid sha256:4355bca940c806ec4db38fce331c7a04def5a7f20c48b8e88b34d1f4b1e93246
 size 1341734528