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: 4.5179
+- Loss: 4.3772
 
 ## Model description
 
@@ -50,8 +50,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 5.6774        | 1.0   | 256  | 4.5597          |
-| 4.9363        | 2.0   | 512  | 4.5179          |
+| 5.6591        | 1.0   | 256  | 4.4475          |
+| 4.9289        | 2.0   | 512  | 4.3772          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9f22c668cd93b3eb49bed26203c47994c23a250d296eb1528a430355a87113c
+oid sha256:f57508911116cdbe638440b6c6bc1ce923aa666eef9b3d5ab44f47ba873b70a7
 size 327657928

runs/Dec25_22-42-36_c4e2dfd104d2/events.out.tfevents.1735166557.c4e2dfd104d2.9517.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04a9e59ecbe258574b6940ea8350d0cc7f80015c0626390049c1417bb277af17
-size 5810
+oid sha256:222f905d7c792c73b616ddeb373d3dc82b93b7a7f54c3529f7a95686e67cbe82
+size 6646

runs/Dec25_22-42-36_c4e2dfd104d2/events.out.tfevents.1735166658.c4e2dfd104d2.9517.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eb841c574eba2c5d2f56791e64da6a2efb1d81b1e3277fa7b1e2df08f5b50c2
+size 359