Training in progress epoch 4

README.md

@@ -15,9 +15,9 @@ 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: 4.9123
-- Validation Loss: 5.5338
-- Epoch: 3
+- Train Loss: 4.6756
+- Validation Loss: 5.5673
+- Epoch: 4
 
 ## Model description
 
@@ -47,6 +47,7 @@ The following hyperparameters were used during training:
 | 5.5228     | 5.5932          | 1     |
 | 5.1845     | 5.5286          | 2     |
 | 4.9123     | 5.5338          | 3     |
+| 4.6756     | 5.5673          | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ac1f75fea71927b556a05720fb48a6bef20531c4a6191279bbaaa406053583d
+oid sha256:85c8a6ca8fe17b8fe9b455e822c6cf9865568940d93b8084a6a8601cedb76cb1
 size 327745472