Final push of DistilBERT fine-tuned on IMDb.

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: bert-base-cased
+base_model: distilbert-base-uncased
 tags:
 - generated_from_trainer
 model-index:
@@ -14,10 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # DistilBERT-MLM-IMDb
 
-This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.9568
-- Model Preparation Time: 0.0093
+- Loss: 2.2924
+- Model Preparation Time: 0.0018
 
 ## Model description
 
@@ -49,9 +49,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Model Preparation Time |
 |:-------------:|:-----:|:----:|:---------------:|:----------------------:|
-| 2.2075        | 1.0   | 985  | 2.0081          | 0.0093                 |
-| 2.0945        | 2.0   | 1970 | 1.9688          | 0.0093                 |
-| 2.0508        | 3.0   | 2955 | 1.9517          | 0.0093                 |
+| 2.5364        | 1.0   | 958  | 2.3577          | 0.0018                 |
+| 2.426         | 2.0   | 1916 | 2.3132          | 0.0018                 |
+| 2.3902        | 3.0   | 2874 | 2.2983          | 0.0018                 |
 
 
 ### Framework versions