Model save

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: 3.7705
+- Loss: 3.5741
 
 ## Model description
 
@@ -46,9 +46,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 5    | 3.7920          |
-| No log        | 2.0   | 10   | 3.7762          |
-| No log        | 3.0   | 15   | 3.7705          |
+| No log        | 1.0   | 47   | 3.6236          |
+| No log        | 2.0   | 94   | 3.5828          |
+| No log        | 3.0   | 141  | 3.5741          |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c4cbd79baf74b6f36994715598c27852cf402e6ab64653a546d37d649ec8605
+oid sha256:7f640cd3b4a806a53bba27f9ee355dc0860c0edbbf734955cb199cbe49880dd5
 size 327675282

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:234d0c59a7862bea3aed94b1aca5fef5f4579c84f2710f2b5283e38e7557301f
+oid sha256:fa103d0116aef6bd63297b39dab813cb2e89f4f9e70fc0e852cce3a205a0998b
 size 4472