End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.5367
+- Loss: 4.4820
 
 ## Model description
 
@@ -48,9 +48,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| No log        | 0.9981 | 331  | 4.5857          |
-| 4.7612        | 1.9992 | 663  | 4.5455          |
-| 4.7612        | 2.9943 | 993  | 4.5367          |
+| No log        | 0.9981 | 331  | 4.5034          |
+| 4.5695        | 1.9992 | 663  | 4.4857          |
+| 4.5695        | 2.9943 | 993  | 4.4820          |
 
 
 ### Framework versions

runs/Jul26_11-58-57_1a56f1dc4f04/events.out.tfevents.1721995669.1a56f1dc4f04.356.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36f8e56ec2715ffb91f2ef104a0352f9be7e1944d23a4680497d26356c3d9bce
-size 6283
+oid sha256:4e37f036a0eb60a5a09c7928f6b819524b229d430f2862e1e0e8b347b0928f0b
+size 6908

runs/Jul26_11-58-57_1a56f1dc4f04/events.out.tfevents.1721996638.1a56f1dc4f04.356.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e75a983f356b718abf22837950a2fba3a19eff34dda890077e565cfa82ad1db
+size 359