Training in progress epoch 3

README.md

@@ -15,11 +15,11 @@ 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: 10.1151
-- Train Accuracy: 0.0001
-- Validation Loss: 9.9763
-- Validation Accuracy: 0.0016
-- Epoch: 1
+- Train Loss: 9.5331
+- Train Accuracy: 0.0230
+- Validation Loss: 9.2992
+- Validation Accuracy: 0.0223
+- Epoch: 3
 
 ## Model description
 
@@ -47,6 +47,8 @@ The following hyperparameters were used during training:
 |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
 | 10.2437    | 0.0000         | 10.1909         | 0.0000              | 0     |
 | 10.1151    | 0.0001         | 9.9763          | 0.0016              | 1     |
+| 9.8665     | 0.0107         | 9.6535          | 0.0215              | 2     |
+| 9.5331     | 0.0230         | 9.2992          | 0.0223              | 3     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:895b2ddc83e04b7d1b137ffc1c96363f582c4eb8c969146511bce408b0577bb1
+oid sha256:32117800659fd2626a7904b43dd42a20de3bb3d71cefce91d0cbf46d52a125fb
 size 499741936