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 [distilgpt2](https://huggingface.co/distilgpt2) on the recipe_nlg dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1321
+- Loss: 2.4703
 
 ## Model description
 
@@ -49,8 +49,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.1047        | 1.0   | 250  | 1.1482          |
-| 0.858         | 2.0   | 500  | 1.1321          |
+| 0.473         | 1.0   | 250  | 2.4041          |
+| 0.1526        | 2.0   | 500  | 2.4703          |
 
 
 ### Framework versions

runs/Dec26_13-42-34_4f87fa13cf4f/events.out.tfevents.1735220556.4f87fa13cf4f.40074.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f05e5b0f94bcd7e56f7b6cbc6770ff7b96bc95413e5241f56a7eb214aec2babf
-size 6022
+oid sha256:da7f5b09c24b1654e201bdc4ece30db1f2104f47496bfc683ab2fb585525c4de
+size 6647

runs/Dec26_13-42-34_4f87fa13cf4f/events.out.tfevents.1735220789.4f87fa13cf4f.40074.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e088d7a2864f845f66ff2bc7bd6f97da8cd3b5d977703cbd32f3c92b5fc28fa
+size 359