potatomode
/

short_jokes_model

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions Metrics Training metrics Community

potatomode commited on Aug 1, 2023

Commit

8cd50e9

·

1 Parent(s): d895c83

update model card README.md

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -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 the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.6180
 ## Model description
@@ -46,9 +46,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 8    | 2.7887          |
-| No log        | 2.0   | 16   | 2.6354          |
-| No log        | 3.0   | 24   | 2.6180          |
 ### Framework versions

 This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 2.4125
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 16   | 2.6065          |
+| No log        | 2.0   | 32   | 2.4523          |
+| No log        | 3.0   | 48   | 2.4125          |
 ### Framework versions