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: 0.2467
-- Validation Loss: 0.3988
-- Train Accuracy: 0.8592
-- Epoch: 2
+- Train Loss: 0.1801
+- Validation Loss: 0.4358
+- Train Accuracy: 0.8620
+- Epoch: 3
 
 ## Model description
 
@@ -46,6 +46,7 @@ The following hyperparameters were used during training:
 | 0.4561     | 0.3859          | 0.8565         | 0     |
 | 0.3292     | 0.3796          | 0.8647         | 1     |
 | 0.2467     | 0.3988          | 0.8592         | 2     |
+| 0.1801     | 0.4358          | 0.8620         | 3     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1705456916.104-171-203-254.2049527.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fd28db34d29e1acebee5e3a60dd86ad1f62ca72ab04c7498af29178e2dabb2b
-size 2838049
+oid sha256:a9bba78252bcc19733e5881f264ba970daa33fdacdd47dc07a01cf907fca3bbf
+size 2838266

logs/validation/events.out.tfevents.1705459154.104-171-203-254.2049527.1.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed3f56841f1e34da8f2b624ffac62e5029226cf86ad2d497dd8fb0561e5ef825
-size 509
+oid sha256:29956f1033bfe2668f7a4b24c6481819175a387acf43ba44eecfd9d9df3c9716
+size 666

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:906e0fe7eb037b7d0664bf2e4e7f1095dc829ced03317fb7905571202b8169cb
+oid sha256:0afedc6e7277a4d5a6a243e3b5e2caccc0dc5cd418ca976fd221fe50d16852ce
 size 498865280