End of training

README.md

@@ -17,7 +17,7 @@ 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 eli5_category dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.8221
+- Loss: 3.8365
 
 ## Model description
 
@@ -48,9 +48,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 3.9499        | 1.0   | 1318 | 3.8330          |
-| 3.8527        | 2.0   | 2636 | 3.8245          |
-| 3.815         | 3.0   | 3954 | 3.8221          |
+| 3.9504        | 1.0   | 1308 | 3.8461          |
+| 3.8509        | 2.0   | 2616 | 3.8372          |
+| 3.8114        | 3.0   | 3924 | 3.8365          |
 
 
 ### Framework versions

runs/Aug22_07-52-46_a4c9a4898b6f/events.out.tfevents.1724313167.a4c9a4898b6f.1596.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf83c20ddce930aa340eeebcf27e596128c6bd5bc2b3bac46412a6d9b790c81b
-size 7227
+oid sha256:8f752cbe797b35611309e6d04d94e6fe2cab2b1b7ac1ec71757011f133660114
+size 7852

runs/Aug22_07-52-46_a4c9a4898b6f/events.out.tfevents.1724314114.a4c9a4898b6f.1596.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:343d1f44db882d62ba26d34bd287652b96d43943c68b903114b8c51947842679
+size 630