Training in progress epoch 5

README.md

@@ -15,10 +15,10 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.7690
-- Validation Loss: 1.0625
-- Train Accuracy: 0.6756
-- Epoch: 4
+- Train Loss: 0.6847
+- Validation Loss: 1.0749
+- Train Accuracy: 0.6711
+- Epoch: 5
 
 ## Model description
 
@@ -49,6 +49,7 @@ The following hyperparameters were used during training:
 | 1.0302     | 1.1222          | 0.6667         | 2     |
 | 0.8825     | 1.0611          | 0.68           | 3     |
 | 0.7690     | 1.0625          | 0.6756         | 4     |
+| 0.6847     | 1.0749          | 0.6711         | 5     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e302c024015846bd69ddd9036f213ae954cd98b785096556d109d6078a97b8dd
+oid sha256:3db2c460ca30a87d41068a188eaf2f9d024760fdb17c200a69edf16bcaa268a5
 size 46793992