Training in progress epoch 1

README.md

@@ -15,13 +15,13 @@ 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: 4.3395
-- Train End Logits Accuracy: 0.0799
-- Train Start Logits Accuracy: 0.0714
-- Validation Loss: 3.5811
-- Validation End Logits Accuracy: 0.1680
-- Validation Start Logits Accuracy: 0.1473
-- Epoch: 0
+- Train Loss: 2.8629
+- Train End Logits Accuracy: 0.2996
+- Train Start Logits Accuracy: 0.2862
+- Validation Loss: 2.8396
+- Validation End Logits Accuracy: 0.3094
+- Validation Start Logits Accuracy: 0.3183
+- Epoch: 1
 
 ## Model description
 
@@ -48,6 +48,7 @@ The following hyperparameters were used during training:
 | Train Loss | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
 |:----------:|:-------------------------:|:---------------------------:|:---------------:|:------------------------------:|:--------------------------------:|:-----:|
 | 4.3395     | 0.0799                    | 0.0714                      | 3.5811          | 0.1680                         | 0.1473                           | 0     |
+| 2.8629     | 0.2996                    | 0.2862                      | 2.8396          | 0.3094                         | 0.3183                           | 1     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6e1b1358ca91dafef03b4b02d718d0775ab41fa0cf3fd44e1f25c2f99c2e134
+oid sha256:e20a272d8e1a6f19b3d40d61f5a3eae5b8b67e6404daa6288f87d642c2e183af
 size 265583592