Training in progress epoch 2

README.md

@@ -15,11 +15,11 @@ 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: 0.2979
-- Train Accuracy: 0.8754
-- Validation Loss: 0.3127
-- Validation Accuracy: 0.8578
-- Epoch: 1
+- Train Loss: 0.0886
+- Train Accuracy: 0.9673
+- Validation Loss: 0.4091
+- Validation Accuracy: 0.875
+- Epoch: 2
 
 ## Model description
 
@@ -47,6 +47,7 @@ The following hyperparameters were used during training:
 |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
 | 0.5592     | 0.7268         | 0.3760          | 0.8554              | 0     |
 | 0.2979     | 0.8754         | 0.3127          | 0.8578              | 1     |
+| 0.0886     | 0.9673         | 0.4091          | 0.875               | 2     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf2c4a192a9c14a9009b6c2645242ed1ea39e1180eda525cbf98c996b328c56d
+oid sha256:be977be4ba7d604eac99d383682a06137b4110b5fa260b2044132d1d33ddf3b4
 size 438223128