Training in progress epoch 4

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: 0.1169
-- Train Accuracy: 0.9624
-- Validation Loss: 0.4229
-- Validation Accuracy: 0.8808
-- Epoch: 3
+- Train Loss: 0.0616
+- Train Accuracy: 0.9800
+- Validation Loss: 0.4822
+- Validation Accuracy: 0.8788
+- Epoch: 4
 
 ## Model description
 
@@ -49,6 +49,7 @@ The following hyperparameters were used during training:
 | 0.3344     | 0.8761         | 0.3706          | 0.8626              | 1     |
 | 0.2097     | 0.9270         | 0.3300          | 0.8869              | 2     |
 | 0.1169     | 0.9624         | 0.4229          | 0.8808              | 3     |
+| 0.0616     | 0.9800         | 0.4822          | 0.8788              | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1cdb9c6e9fab6baa11d2369d86832e7f0ee6da4728a3b4299a18680e76df5c4
+oid sha256:d381675b0096d1b322b17cdbe22c4a500698515c5fb9939c48e07ae8513f6d24
 size 438226204