Training in progress epoch 3

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: 0.1947
-- Train Accuracy: 0.9344
-- Validation Loss: 0.3971
-- Validation Accuracy: 0.8444
-- Epoch: 2
+- Train Loss: 0.0960
+- Train Accuracy: 0.9694
+- Validation Loss: 0.4772
+- Validation Accuracy: 0.8626
+- Epoch: 3
 
 ## Model description
 
@@ -48,6 +48,7 @@ The following hyperparameters were used during training:
 | 0.5305     | 0.7885         | 0.4253          | 0.8222              | 0     |
 | 0.3041     | 0.8887         | 0.3962          | 0.8404              | 1     |
 | 0.1947     | 0.9344         | 0.3971          | 0.8444              | 2     |
+| 0.0960     | 0.9694         | 0.4772          | 0.8626              | 3     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:591cf87d97566b2dd644ce252fb44f6a0e6112667015f848fe1f9f7e8f369eb1
+oid sha256:7afe4760be3f8a780b50b9a293524f2de89d099cfd0e37be940a71fa09f414b1
 size 438226204