End of training

README.md

@@ -1,8 +1,8 @@
 ---
 license: apache-2.0
+base_model: distilgpt2
 tags:
 - generated_from_trainer
-base_model: distilgpt2
 model-index:
 - name: distilgpt2-finetuned-wikitext2
   results: []
@@ -15,7 +15,7 @@ should 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:
-- Loss: 4.0812
+- Loss: 3.9696
 
 ## Model description
 
@@ -46,9 +46,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 19   | 4.1523          |
-| No log        | 2.0   | 38   | 4.0968          |
-| No log        | 3.0   | 57   | 4.0812          |
+| No log        | 1.0   | 38   | 4.0603          |
+| No log        | 2.0   | 76   | 3.9883          |
+| No log        | 3.0   | 114  | 3.9696          |
 
 
 ### Framework versions

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03485aa6eafc764e5172a14c15e465e2cbe2758fb099c2f37b8981cd34570610
+oid sha256:8be379cb56589e737418dcef74d29a39b9352f31aaf9686344475968fb5da062
 size 4920