Training in progress epoch 21

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: 7.5339
-- Validation Loss: 7.8726
-- Epoch: 20
+- Train Loss: 7.4741
+- Validation Loss: 7.7917
+- Epoch: 21
 
 ## Model description
 
@@ -63,6 +63,7 @@ The following hyperparameters were used during training:
 | 7.8495     | 8.0607          | 18    |
 | 7.6980     | 7.9635          | 19    |
 | 7.5339     | 7.8726          | 20    |
+| 7.4741     | 7.7917          | 21    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62421067161c3b96600b70b35c31ce8502f5e4e4de81a6679ce5e98f56c3db89
+oid sha256:23b4b9d9d99d669b70c9b7fb4dbe8fb96348d1317fcc82a8ea410e2bbb586f73
 size 497935440