Training in progress epoch 4

README.md

@@ -15,9 +15,9 @@ 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: 1.9616
-- Validation Loss: 1.8620
-- Epoch: 3
+- Train Loss: 1.9643
+- Validation Loss: 1.8822
+- Epoch: 4
 
 ## Model description
 
@@ -47,6 +47,7 @@ The following hyperparameters were used during training:
 | 1.9656     | 1.8785          | 1     |
 | 1.9626     | 1.8783          | 2     |
 | 1.9616     | 1.8620          | 3     |
+| 1.9643     | 1.8822          | 4     |
 
 
 ### Framework versions

checkpoint/extra_data.pickle

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1cc1d7606916baaadc0bc664ee07ec008e09ed658e86ff1e968020373100074
+oid sha256:5602c44c0a97df7ada22032caeb169ced7dc5c9bbe96a4f83786bcfcc60bf552
 size 876130159