Training in progress epoch 3

README.md

@@ -14,11 +14,11 @@ 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: 0.0958
-- Train Accuracy: 0.9688
-- Validation Loss: 0.2987
-- Validation Accuracy: 0.8888
-- Epoch: 2
+- Train Loss: 0.0990
+- Train Accuracy: 0.9662
+- Validation Loss: 0.4042
+- Validation Accuracy: 0.875
+- Epoch: 3
 
 ## Model description
 
@@ -47,6 +47,7 @@ The following hyperparameters were used during training:
 | 0.2304     | 0.9112         | 0.3037          | 0.8956              | 0     |
 | 0.1327     | 0.9544         | 0.3145          | 0.8911              | 1     |
 | 0.0958     | 0.9688         | 0.2987          | 0.8888              | 2     |
+| 0.0990     | 0.9662         | 0.4042          | 0.875               | 3     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5908a3b2760de5b40b4f5564a565909ac95e131198edadbbd4983ba321b6f789
+oid sha256:4a868f3fd406902b93336f08ab62e768be3371ffe921395a1e4abfa60a4e6e28
 size 438223192