AndrewR
/

distilbert-base-uncased-finetuned-imdb

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

AndrewR commited on Apr 12, 2022

Commit

0047231

•

1 Parent(s): c205584

update model card README.md

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.4719
 ## Model description
@@ -47,9 +47,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.699         | 1.0   | 157  | 2.4907          |
-| 2.5724        | 2.0   | 314  | 2.4237          |
-| 2.5377        | 3.0   | 471  | 2.4355          |
 ### Framework versions

 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset.
 It achieves the following results on the evaluation set:
+- Loss: 2.3919
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
+| 2.5273        | 1.0   | 157  | 2.4557          |
+| 2.4839        | 2.0   | 314  | 2.4263          |
+| 2.4696        | 3.0   | 471  | 2.3919          |
 ### Framework versions