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: 0.2471
-- Validation Loss: 0.4441
-- Train Accuracy: 0.8556
-- Epoch: 2
+- Train Loss: 0.1807
+- Validation Loss: 0.4561
+- Train Accuracy: 0.8596
+- Epoch: 3
 
 ## Model description
 
@@ -46,6 +46,7 @@ The following hyperparameters were used during training:
 | 0.4595     | 0.4097          | 0.8456         | 0     |
 | 0.3288     | 0.3983          | 0.8531         | 1     |
 | 0.2471     | 0.4441          | 0.8556         | 2     |
+| 0.1807     | 0.4561          | 0.8596         | 3     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1705551087.104-171-203-254.2445487.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f42dc22658c433f208e150ec5fad312d76fc614c389bec4f7689fbffe5bcfc01
-size 2838049
+oid sha256:0b35ec60dba9ee0a569c6ffdf3cc2d038cb773b44757cacde30b16514298934e
+size 2838266

logs/validation/events.out.tfevents.1705553327.104-171-203-254.2445487.1.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c917c8ff9950735025a60da257d532f6dfe80dd1bb10bd1a72510c0be8076c3c
-size 509
+oid sha256:7df4d5efa9d876034a5e4385769c59bd9901d12dc1534a9e245e3dda0faebeb0
+size 666

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e76c7b35da435431d23bebc43507958cd23e6736d3e6041eeb2f7f3284781ca
+oid sha256:17d3d741e93c5a1d06c841773ae68908fd824bd0cac3e66e597c2d6770434af7
 size 498865280