Training in progress epoch 8

README.md

@@ -15,8 +15,8 @@ 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: 3.8398
-- Epoch: 0
+- Train Loss: 3.2382
+- Epoch: 8
 
 ## Model description
 
@@ -43,6 +43,14 @@ The following hyperparameters were used during training:
 | Train Loss | Epoch |
 |:----------:|:-----:|
 | 3.8398     | 0     |
+| 3.6950     | 1     |
+| 3.6270     | 2     |
+| 3.5776     | 3     |
+| 3.4771     | 4     |
+| 3.4207     | 5     |
+| 3.3600     | 6     |
+| 3.2423     | 7     |
+| 3.2382     | 8     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e9f9ea834afb049dea0486c30c4e373c116bfa37b055929542d444a8e981201
+oid sha256:4c037f66573ad2a719d7e8ad62c953530c5696cd58c5318813f233694bb17614
 size 327745472