End of training

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert/distilgpt2](https://huggingface.co/distilbert/distilgpt2) on the recipe_nlg dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.3036
+- Loss: 1.9213
 
 ## Model description
 
@@ -50,8 +50,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.5638        | 1.0   | 112  | 2.3422          |
-| 2.3798        | 2.0   | 224  | 2.3036          |
+| 2.1178        | 1.0   | 1    | 2.0584          |
+| 1.9828        | 2.0   | 2    | 1.9213          |
 
 
 ### Framework versions

runs/Dec25_22-22-36_c4e2dfd104d2/events.out.tfevents.1735165373.c4e2dfd104d2.5268.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bae40e249173c4ffd48c67967c7b6f93d77fc5bc4b17923d85c6545a2713c9b
+size 354