Training in progress epoch 5

README.md

@@ -15,13 +15,13 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.7224
-- Validation Loss: 0.9349
-- Train Accuracy: 0.5550
-- Train Precision: 0.5512
-- Train Recall: 0.5550
-- Train F1: 0.5501
-- Epoch: 4
+- Train Loss: 0.6944
+- Validation Loss: 0.9348
+- Train Accuracy: 0.5568
+- Train Precision: 0.5590
+- Train Recall: 0.5568
+- Train F1: 0.5578
+- Epoch: 5
 
 ## Model description
 
@@ -52,6 +52,7 @@ The following hyperparameters were used during training:
 | 0.8071     | 0.9152          | 0.5567         | 0.5396          | 0.5567       | 0.5414   | 2     |
 | 0.7594     | 0.9245          | 0.5551         | 0.5581          | 0.5551       | 0.5553   | 3     |
 | 0.7224     | 0.9349          | 0.5550         | 0.5512          | 0.5550       | 0.5501   | 4     |
+| 0.6944     | 0.9348          | 0.5568         | 0.5590          | 0.5568       | 0.5578   | 5     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1716095701.6264913a9602.740.5.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3942241cb5c248570c1432eacb4d3884c6294dacf2fb3aba2e2c85292ee5f10d
-size 715723
+oid sha256:358a7f5e8288d8df8a2b9e117a37a32e22bb92f5ffd4c76fe22af406b98d3c7e
+size 716072

logs/validation/events.out.tfevents.1716095738.6264913a9602.740.6.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81043cf20088d2bf284894b9a778c3072bec4a53d36c282a345277674d5859dd
-size 856
+oid sha256:7e5d55d87736fdd2bbb6c45bf9e90e9c99dcc76f405f12d5161c4b799914b8e0
+size 1012

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4fc99b2f380f75d0d82fcab5489e452742df002b9542a7a3c6475811a69c2ab
+oid sha256:8c10a191dbcbccd48ac435ad94c9513b908be2a7c9ca49228d49a43c28f4c9b5
 size 17614080