Training in progress epoch 23

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: 5.8569
-- Validation Loss: 7.0151
-- Epoch: 22
+- Train Loss: 5.7639
+- Validation Loss: 6.9941
+- Epoch: 23
 
 ## Model description
 
@@ -65,6 +65,7 @@ The following hyperparameters were used during training:
 | 5.9643     | 7.0540          | 20    |
 | 5.9225     | 7.0365          | 21    |
 | 5.8569     | 7.0151          | 22    |
+| 5.7639     | 6.9941          | 23    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0983b1b489db94d920366ab3cdb0e812464815a084e8372d6e17e8bb28f8bd8
+oid sha256:14dd28f07d63329cadb0a975f2fbab2e1f0c48b408cda154c6a14b2dad30110b
 size 351244368