Training in progress epoch 2

README.md

@@ -14,10 +14,10 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [GCopoulos/deberta-base-finetuned-answer_pol](https://huggingface.co/GCopoulos/deberta-base-finetuned-answer_pol) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0433
-- Validation Loss: 0.5234
-- Train F1: 0.8822
-- Epoch: 1
+- Train Loss: 0.0197
+- Validation Loss: 0.6153
+- Train F1: 0.8799
+- Epoch: 2
 
 ## Model description
 
@@ -45,6 +45,7 @@ The following hyperparameters were used during training:
 |:----------:|:---------------:|:--------:|:-----:|
 | 0.1402     | 0.5322          | 0.8747   | 0     |
 | 0.0433     | 0.5234          | 0.8822   | 1     |
+| 0.0197     | 0.6153          | 0.8799   | 2     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1686257240.bf249ee763c5.1479.6.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac9f37327726690b1153ab4c6f8bf0747c365e030dae85f078647a0cbe7abe3d
-size 10580312
+oid sha256:70945570bc7737ed4a9a2e1222ae73affcb389341e347847a33c3feda69b39a0
+size 10580523

logs/validation/events.out.tfevents.1686257386.bf249ee763c5.1479.7.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:707db258292b04c42182404b495364121790b549cb5712085e2180f367020ac0
-size 388
+oid sha256:53b8f711282bbd918e4757951888d6407460aff2c717fc088b6757d8fb7071ed
+size 544

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa3b79db3d771313160a05e55512d53c5e0442d6b3a8b496557f5b1f7d6d2848
+oid sha256:225ea2ca557d7f2efe9598eb69cca3ffa2c944eb35dfe066549e046d84f4e0de
 size 557073416