Training in progress epoch 2

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: 3.9186
-- Validation Loss: 3.8146
-- Epoch: 1
+- Train Loss: 3.8062
+- Validation Loss: 3.7666
+- Epoch: 2
 
 ## Model description
 
@@ -45,6 +45,7 @@ The following hyperparameters were used during training:
 |:----------:|:---------------:|:-----:|
 | 4.2001     | 3.9108          | 0     |
 | 3.9186     | 3.8146          | 1     |
+| 3.8062     | 3.7666          | 2     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dcbedf2d703f27af9feb8557f79fc9f794f25978a6cd36ec76a397b6259013d
+oid sha256:61a2dfe01cdac26a6db6591ad5f777e3a3be531a4e6b2c0d30368ddae0bfa836
 size 327745472