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 [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.2465
-- Validation Loss: 0.4150
-- Train Accuracy: 0.8627
-- Epoch: 2
+- Train Loss: 0.1784
+- Validation Loss: 0.4412
+- Train Accuracy: 0.8670
+- Epoch: 3
 
 ## Model description
 
@@ -46,6 +46,7 @@ The following hyperparameters were used during training:
 | 0.4558     | 0.3972          | 0.8495         | 0     |
 | 0.3309     | 0.3834          | 0.8520         | 1     |
 | 0.2465     | 0.4150          | 0.8627         | 2     |
+| 0.1784     | 0.4412          | 0.8670         | 3     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1705363114.104-171-203-254.1650350.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99138a980b53b4e3780f7199eef67047ef12db6c7089e34e921568fa37a0be3a
-size 2838049
+oid sha256:d795c2a970f810f59f8b24567baf2217d932ee7e6b569f93c5fd6e0dcf56d656
+size 2838266

logs/validation/events.out.tfevents.1705365347.104-171-203-254.1650350.1.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37ab682e9d5cc0fd7f38beb16146718a160a83aa0c6f8d033a70618e01155c0c
-size 509
+oid sha256:0dc79f8025a4ae0220d9f0d48a44387915a1ae67edd55a4608633bd4166d6667
+size 666

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d8cdb75b81b40d696883711c3328b08d2ecdd13ee7cf69f4bba4e9297f9dbea
+oid sha256:1530c1ca5187b5c0990c789acf558cee0f134adfe16fd61487a66c23c0b2282e
 size 498865280