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: 2.4703
+- Loss: 2.6507
 
 ## Model description
 
@@ -49,8 +49,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.473         | 1.0   | 250  | 2.4041          |
-| 0.1526        | 2.0   | 500  | 2.4703          |
+| 0.4097        | 1.0   | 250  | 2.5146          |
+| 0.1179        | 2.0   | 500  | 2.6507          |
 
 
 ### Framework versions

runs/Dec26_13-57-19_4f87fa13cf4f/events.out.tfevents.1735221441.4f87fa13cf4f.42847.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8409c47ee6b30a5f903017dc23ec51ff2eb857e870643cd09bc5f097a0c817ae
-size 6022
+oid sha256:d0e019824bdeca61888ea7e2dc91a8cdb28f87e0bd6f2daefc4ec9a42295400a
+size 6647

runs/Dec26_13-57-19_4f87fa13cf4f/events.out.tfevents.1735221675.4f87fa13cf4f.42847.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc92e221c6f01a3e94840fd583c0d012ee41efc0eb16130a5da79b34420cf602
+size 359