Training in progress epoch 9

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: 7.8599
-- Validation Loss: 7.8710
-- Epoch: 3
+- Train Loss: 7.3544
+- Validation Loss: 7.5526
+- Epoch: 9
 
 ## Model description
 
@@ -46,6 +46,12 @@ The following hyperparameters were used during training:
 | 7.9439     | 7.9478          | 1     |
 | 7.9228     | 7.9152          | 2     |
 | 7.8599     | 7.8710          | 3     |
+| 7.7957     | 7.8172          | 4     |
+| 7.7068     | 7.7585          | 5     |
+| 7.6083     | 7.6995          | 6     |
+| 7.5195     | 7.6441          | 7     |
+| 7.4214     | 7.5958          | 8     |
+| 7.3544     | 7.5526          | 9     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36664d924048eb04693134406f1f8b59d56df39dffc969da56a88bd939b49d2e
+oid sha256:dee96fd552a60be566ada0c31a36471d47b72a0b51e80e87dced63544ef7c24d
 size 351244368