Training in progress epoch 3

README.md

@@ -14,10 +14,10 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.6784
-- Validation Loss: 0.8048
+- Train Loss: 0.6941
+- Validation Loss: 0.6740
 - Train Accuracy: 0.6119
-- Epoch: 2
+- Epoch: 3
 
 ## Model description
 
@@ -46,6 +46,7 @@ The following hyperparameters were used during training:
 | 0.7269     | 0.8209          | 0.6119         | 0     |
 | 0.6892     | 0.6686          | 0.6119         | 1     |
 | 0.6784     | 0.8048          | 0.6119         | 2     |
+| 0.6941     | 0.6740          | 0.6119         | 3     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02684698e0fbb64334067bd862d7ac58a2680cbeb567409caf38cf2b3c01c303
+oid sha256:552640b703daee3eaac741028ad5d578abe22fda5429236476865f0d1cff2ba7
 size 438223192