Training in progress epoch 6

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: 3.2516
-- Validation Loss: 3.4550
-- Epoch: 4
+- Train Loss: 3.0721
+- Validation Loss: 3.4071
+- Epoch: 6
 
 ## Model description
 
@@ -48,6 +48,8 @@ The following hyperparameters were used during training:
 | 3.4972     | 3.5423          | 2     |
 | 3.3682     | 3.4870          | 3     |
 | 3.2516     | 3.4550          | 4     |
+| 3.1712     | 3.4239          | 5     |
+| 3.0721     | 3.4071          | 6     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:241fee73fee3280eaebcbb8d7a1d3c5bda9ff8bd522c4ec3b9c543029c210681
+oid sha256:a0aef61faed88708e6c393b170f300653723558db15c2b566c3f87f6c8514447
 size 327745472