Training in progress epoch 3

README.md

@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [deepset/gbert-base](https://huggingface.co/deepset/gbert-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.1234
-- Validation Loss: 0.1496
-- Epoch: 2
+- Train Loss: 0.1015
+- Validation Loss: 0.1404
+- Epoch: 3
 
 ## Model description
 
@@ -45,6 +45,7 @@ The following hyperparameters were used during training:
 | 0.2725     | 0.1879          | 0     |
 | 0.1604     | 0.1563          | 1     |
 | 0.1234     | 0.1496          | 2     |
+| 0.1015     | 0.1404          | 3     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1687454364.1c51bb8d902a.975.3.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9e826607fff8b76ec371c528aca11ec97f8785e6efdc67bf2d651a5cd6d0128
-size 3647482
+oid sha256:bb0017d262468b3bd5a22dc42288f1c928f3da041c3e91da8df6539bcc40518a
+size 3647627

logs/validation/events.out.tfevents.1687455216.1c51bb8d902a.975.4.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d84b2f53cd21f9640c3dd037dc35e0b9a637b0d4d67760d106b584a8210cd08a
-size 545
+oid sha256:a4e07f50ed75c376f50f5fc9a0a20ac18a40955f43889e46a2b013a23f943c57
+size 702

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85b9eb8f711e2e587e63af72a7a9e306a7ca64969a72dcbb4390ecc9e64023a7
+oid sha256:f0d980acc1f0e339d80487dc09d700b1aca0a0b1b71329320aaa1e222b5b6ec4
 size 437689360