Training in progress epoch 4

README.md

@@ -13,11 +13,11 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [cardiffnlp/twitter-xlm-roberta-base-sentiment](https://huggingface.co/cardiffnlp/twitter-xlm-roberta-base-sentiment) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.2873
-- Train Accuracy: 0.8908
-- Validation Loss: 0.6515
-- Validation Accuracy: 0.7858
-- Epoch: 3
+- Train Loss: 0.1965
+- Train Accuracy: 0.9293
+- Validation Loss: 0.7051
+- Validation Accuracy: 0.7813
+- Epoch: 4
 
 ## Model description
 
@@ -47,6 +47,7 @@ The following hyperparameters were used during training:
 | 0.4868     | 0.8044         | 0.5104          | 0.7807              | 1     |
 | 0.3846     | 0.8472         | 0.5949          | 0.7705              | 2     |
 | 0.2873     | 0.8908         | 0.6515          | 0.7858              | 3     |
+| 0.1965     | 0.9293         | 0.7051          | 0.7813              | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98cd83484463e1b23aa70cc9079f715c35f3e9edf7999af184b6594b7c858f03
+oid sha256:01dd3c045e8c4e8340ae23d711e12559d908f9be33e43052629a70c504f2b07f
 size 1112473408