Training in progress epoch 4

README.md

@@ -15,10 +15,10 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 95.7810
-- Validation Loss: 15.3191
-- Train Accuracy: 0.268
-- Epoch: 3
+- Train Loss: 62.5387
+- Validation Loss: 5.4845
+- Train Accuracy: 0.262
+- Epoch: 4
 
 ## Model description
 
@@ -48,6 +48,7 @@ The following hyperparameters were used during training:
 | 168.1700   | 10.9270         | 0.27           | 1     |
 | 103.5470   | 29.7673         | 0.243          | 2     |
 | 95.7810    | 15.3191         | 0.268          | 3     |
+| 62.5387    | 5.4845          | 0.262          | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cdcf5558a0a8d03248b56367344040ca5d6c98d812074199c80320f526a0821
+oid sha256:567cf34175fa2feeb116c684a9faa6fc24f502cd422d94d2d2196f7a38888089
 size 99819568