Training in progress epoch 8

README.md

@@ -15,13 +15,13 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.1054
-- Train End Logits Accuracy: 0.9666
-- Train Start Logits Accuracy: 0.9650
-- Validation Loss: 2.3507
-- Validation End Logits Accuracy: 0.6187
-- Validation Start Logits Accuracy: 0.6120
-- Epoch: 7
+- Train Loss: 0.0850
+- Train End Logits Accuracy: 0.9741
+- Train Start Logits Accuracy: 0.9728
+- Validation Loss: 2.5902
+- Validation End Logits Accuracy: 0.5977
+- Validation Start Logits Accuracy: 0.5977
+- Epoch: 8
 
 ## Model description
 
@@ -55,6 +55,7 @@ The following hyperparameters were used during training:
 | 0.2080     | 0.9388                    | 0.9279                      | 2.0004          | 0.6127                         | 0.5999                           | 5     |
 | 0.1521     | 0.9534                    | 0.9488                      | 2.0970          | 0.6157                         | 0.6067                           | 6     |
 | 0.1054     | 0.9666                    | 0.9650                      | 2.3507          | 0.6187                         | 0.6120                           | 7     |
+| 0.0850     | 0.9741                    | 0.9728                      | 2.5902          | 0.5977                         | 0.5977                           | 8     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4cf9edc702bbf0a49a07c10df2f2f6e0df8f181a99c9ab95e69c49462ce0b07
+oid sha256:593caa27de8f418bbbbe2b7b17cb65ae2846ea763601eef641aa496a47defd27
 size 435842000