Training in progress epoch 496

README.md

@@ -14,11 +14,11 @@ 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: 0.7078
-- Train Accuracy: 0.1220
-- Validation Loss: 0.7842
-- Validation Accuracy: 0.1216
-- Epoch: 495
+- Train Loss: 0.7079
+- Train Accuracy: 0.1221
+- Validation Loss: 0.7900
+- Validation Accuracy: 0.1211
+- Epoch: 496
 
 ## Model description
 
@@ -540,6 +540,7 @@ The following hyperparameters were used during training:
 | 0.7074     | 0.1221         | 0.7749          | 0.1215              | 493   |
 | 0.7075     | 0.1221         | 0.7764          | 0.1201              | 494   |
 | 0.7078     | 0.1220         | 0.7842          | 0.1216              | 495   |
+| 0.7079     | 0.1221         | 0.7900          | 0.1211              | 496   |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:595af7ea6f784afdffc8fcedf59b69aedf4cc766bebc410f5c3c57d3d98187a1
+oid sha256:d386f5a88403e20150762701fd4d89a5e0d536c748cf3cca3f8af75aff291810
 size 499741936