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: 0.1030
-- Validation Loss: 0.4079
-- Train Matthews Correlation: 0.6920
-- Epoch: 3
+- Train Loss: 0.0644
+- Validation Loss: 0.4228
+- Train Matthews Correlation: 0.6855
+- Epoch: 4
 
 ## Model description
 
@@ -47,6 +47,7 @@ The following hyperparameters were used during training:
 | 0.2531     | 0.3534          | 0.6921                     | 1     |
 | 0.1756     | 0.3472          | 0.7141                     | 2     |
 | 0.1030     | 0.4079          | 0.6920                     | 3     |
+| 0.0644     | 0.4228          | 0.6855                     | 4     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1702925246.950a4a298924.2572.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fb2a865940f8a30d812808eb8ebd08e33b9c9f2ed04bd80d0030481a4f91ec8
-size 3530822
+oid sha256:32e93e857ab155833dbfffc07aad90c1bd6dd1108899af7480854239745af7de
+size 3531051

logs/validation/events.out.tfevents.1702925354.950a4a298924.2572.1.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a91884e637ffd4947acd48d79aa26b7abff071f8a386f0408a209cbda96ccdf
-size 700
+oid sha256:69fe2d26923523b9aa379f8e987bbbd61e1f2e5d56171352db64276f2cf88f69
+size 856

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d55298abd206a2801cebd5abaedb94e97aa3a6912a3f71190e5734e4844869f5
+oid sha256:9016b9bd086a8360acf40940d42af1d7057d669c3fb0c687fd23a51e6a3c2a78
 size 451979544