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: 4.2906
+- Loss: 4.4498
 
 ## Model description
 
@@ -50,8 +50,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 5.4763        | 1.0   | 256  | 4.3346          |
-| 4.7524        | 2.0   | 512  | 4.2906          |
+| 5.7279        | 1.0   | 256  | 4.4997          |
+| 4.9661        | 2.0   | 512  | 4.4498          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39d1fa2f49b79c7bcc633d17e7e573451594b3754b5a2d6437112aa9658c4b19
+oid sha256:499bf083c289dd094e15f2e9d987f34cb6ae494fb780e789ce2b8cc4fe5d7dde
 size 327657928

runs/Dec26_08-52-19_d061fc3f0ddb/events.out.tfevents.1735203143.d061fc3f0ddb.2509.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:360ea00674eda1c8e073b82b4c9551e4b685275b28140c6596eea01534b92342
-size 5810
+oid sha256:d0e8a411806f9bba52859a74f8741944a05d7d95daa2f6723b132e8f48371d5f
+size 6646

runs/Dec26_08-52-19_d061fc3f0ddb/events.out.tfevents.1735203268.d061fc3f0ddb.2509.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:225ed80ac26bb30d5f2e553394bc36f3d241bf45397b6a3655bfff81fe051cc3
+size 359