Training in progress epoch 48

README.md

@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 5.1436
-- Validation Loss: 7.4110
-- Epoch: 47
+- Train Loss: 5.0199
+- Validation Loss: 7.5223
+- Epoch: 48
 
 ## Model description
 
@@ -90,6 +90,7 @@ The following hyperparameters were used during training:
 | 5.3243     | 7.4340          | 45    |
 | 5.2295     | 7.4170          | 46    |
 | 5.1436     | 7.4110          | 47    |
+| 5.0199     | 7.5223          | 48    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a79ef45e3deb68bea9d0c68c9d83b97594684ac6d494306ea0261beab8eb7293
+oid sha256:f99d1cf79e5f5e0dbe86e44e9841bddb7a4712ea69ab46553304e26f6c1d90c2
 size 497935440