Training in progress epoch 4

README.md

@@ -14,10 +14,10 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [nlpaueb/bert-base-greek-uncased-v1](https://huggingface.co/nlpaueb/bert-base-greek-uncased-v1) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0976
-- Validation Loss: 0.4412
-- Train Matthews Correlation: 0.6738
-- Epoch: 3
+- Train Loss: 0.0647
+- Validation Loss: 0.4583
+- Train Matthews Correlation: 0.6642
+- Epoch: 4
 
 ## Model description
 
@@ -47,6 +47,7 @@ The following hyperparameters were used during training:
 | 0.2729     | 0.3549          | 0.6901                     | 1     |
 | 0.1718     | 0.3977          | 0.6504                     | 2     |
 | 0.0976     | 0.4412          | 0.6738                     | 3     |
+| 0.0647     | 0.4583          | 0.6642                     | 4     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1704316191.9e5a43f02215.207.8.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4579472da9146d6bd455bc382e098c94a26368a6bf9f3d14add7642ad7e32b46
-size 3569510
+oid sha256:9a7b0efddacbd351a818e3736b4416d674ca439217235ed1b44c8a2311ffd89d
+size 3569739

logs/validation/events.out.tfevents.1704316288.9e5a43f02215.207.9.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ba103ce7894117af91471e2232cd24c3899a49addfd5757a4ebd47b4682576d
-size 700
+oid sha256:ee7e4bc8b3e00056dbff724247b743d4d41acf563350dc0f002193c4ea5438f9
+size 856

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:241170392cd16894c9fdae33adbde4a9212ed826c0cb75677a4ac4901b50d5ee
+oid sha256:a635595156398fb6926139d2cfcfbc3f389ed39a133e7825bf586bb0916d3911
 size 451979544