Training in progress epoch 8

README.md

@@ -16,9 +16,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 1.8832
-- Validation Loss: 1.8287
-- Epoch: 7
+- Train Loss: 1.8640
+- Validation Loss: 1.8091
+- Epoch: 8
 
 ## Model description
 
@@ -52,6 +52,7 @@ The following hyperparameters were used during training:
 | 1.9269     | 1.8583          | 5     |
 | 1.9049     | 1.8418          | 6     |
 | 1.8832     | 1.8287          | 7     |
+| 1.8640     | 1.8091          | 8     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81417ed8d6812b9a80b0ee763ed28970e296fd8796634a331f34e056091860c1
+oid sha256:228143dfb9d4fc7560ffc175cf8de916cb138ab7554603238d1468ee52562c71
 size 327745472