Training in progress epoch 3

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: 0.3527
-- Train End Logits Accuracy: 0.8856
-- Train Start Logits Accuracy: 0.8786
-- Validation Loss: 0.5971
-- Validation End Logits Accuracy: 0.8352
-- Validation Start Logits Accuracy: 0.8203
-- Epoch: 2
+- Train Loss: 0.2417
+- Train End Logits Accuracy: 0.9192
+- Train Start Logits Accuracy: 0.9158
+- Validation Loss: 0.6317
+- Validation End Logits Accuracy: 0.8375
+- Validation Start Logits Accuracy: 0.8303
+- Epoch: 3
 
 ## Model description
 
@@ -49,6 +49,7 @@ The following hyperparameters were used during training:
 | 1.1671     | 0.6791                    | 0.6668                      | 0.6925          | 0.7903                         | 0.7716                           | 0     |
 | 0.5541     | 0.8257                    | 0.8179                      | 0.5747          | 0.8230                         | 0.8090                           | 1     |
 | 0.3527     | 0.8856                    | 0.8786                      | 0.5971          | 0.8352                         | 0.8203                           | 2     |
+| 0.2417     | 0.9192                    | 0.9158                      | 0.6317          | 0.8375                         | 0.8303                           | 3     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79c1f3bce6da3b127f00c70cdb22de9943594c0f2abfead53f263f1b4607fd7d
+oid sha256:68ce45ffae7bb57c7c03f197aef0a552a3d0c97ae12b1cdd8ac2ba1f7907519b
 size 265583592