Training in progress epoch 4

README.md

@@ -14,13 +14,13 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.4309
-- Train End Logits Accuracy: 0.8541
-- Train Start Logits Accuracy: 0.8465
-- Validation Loss: 1.0632
-- Validation End Logits Accuracy: 0.7417
-- Validation Start Logits Accuracy: 0.7320
-- Epoch: 3
+- Train Loss: 0.3087
+- Train End Logits Accuracy: 0.8935
+- Train Start Logits Accuracy: 0.8884
+- Validation Loss: 1.1857
+- Validation End Logits Accuracy: 0.7448
+- Validation Start Logits Accuracy: 0.7335
+- Epoch: 4
 
 ## Model description
 
@@ -50,6 +50,7 @@ The following hyperparameters were used during training:
 | 0.8373     | 0.7346                    | 0.7236                      | 0.9979          | 0.7117                         | 0.6974                           | 1     |
 | 0.5988     | 0.8012                    | 0.7931                      | 0.9518          | 0.7267                         | 0.7225                           | 2     |
 | 0.4309     | 0.8541                    | 0.8465                      | 1.0632          | 0.7417                         | 0.7320                           | 3     |
+| 0.3087     | 0.8935                    | 0.8884                      | 1.1857          | 0.7448                         | 0.7335                           | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c6cb52e7ec327456e9f1a4ff802bb96c1220f3190fcbdd66bbe0121e9d5746a
+oid sha256:bcd8fc79db8058de1e5151d4a6138bd12aa7084c16302671727c8b4b2b5b1d07
 size 265583592