Training in progress epoch 4

README.md

@@ -15,11 +15,11 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 2.6160
-- Train Accuracy: 0.0831
-- Validation Loss: 2.2778
-- Validation Accuracy: 0.0909
-- Epoch: 3
+- Train Loss: 2.5523
+- Train Accuracy: 0.0844
+- Validation Loss: 2.2331
+- Validation Accuracy: 0.0916
+- Epoch: 4
 
 ## Model description
 
@@ -49,6 +49,7 @@ The following hyperparameters were used during training:
 | 2.8159     | 0.0795         | 2.4501          | 0.0871              | 1     |
 | 2.7022     | 0.0816         | 2.3638          | 0.0892              | 2     |
 | 2.6160     | 0.0831         | 2.2778          | 0.0909              | 3     |
+| 2.5523     | 0.0844         | 2.2331          | 0.0916              | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be103cc5c72f06baa6edb09496af82ffb7dcdb34e377802bf207e316d7fccfa4
+oid sha256:02c88c6f952ca2c0fd9a015e3687bc9941be30c84dfaaa1a05dc8873bee56668
 size 484838604