Training in progress epoch 3

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: 0.1756
-- Validation Loss: 0.3472
-- Train Matthews Correlation: 0.7141
-- Epoch: 2
+- Train Loss: 0.1030
+- Validation Loss: 0.4079
+- Train Matthews Correlation: 0.6920
+- Epoch: 3
 
 ## Model description
 
@@ -46,6 +46,7 @@ The following hyperparameters were used during training:
 | 0.4343     | 0.3521          | 0.6862                     | 0     |
 | 0.2531     | 0.3534          | 0.6921                     | 1     |
 | 0.1756     | 0.3472          | 0.7141                     | 2     |
+| 0.1030     | 0.4079          | 0.6920                     | 3     |
 
 
 ### 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 sha256:8475aaeec71eaf0b6aa135b9f465c276a7410ba292b3ea9379155a33ec40bfe8
-size 3530593
+oid sha256:3fb2a865940f8a30d812808eb8ebd08e33b9c9f2ed04bd80d0030481a4f91ec8
+size 3530822

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79eee602e827afa188793201980514ff7c918cc198c7d0566426c5bb2119b294
-size 544
+oid sha256:0a91884e637ffd4947acd48d79aa26b7abff071f8a386f0408a209cbda96ccdf
+size 700

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb48618860cb8e61a8a7a8efa0322bd2f5c51710a8448fba5dc35baad51268cf
+oid sha256:d55298abd206a2801cebd5abaedb94e97aa3a6912a3f71190e5734e4844869f5
 size 451979544