End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.93164
+      value: 0.93344
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ 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: 0.2819
-- Accuracy: 0.9316
+- Loss: 0.5739
+- Accuracy: 0.9334
 
 ## Model description
 
@@ -58,14 +58,22 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 10
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.1549        | 1.0   | 1563 | 0.3020          | 0.9198   |
-| 0.0778        | 2.0   | 3126 | 0.2819          | 0.9316   |
+| Training Loss | Epoch | Step  | Accuracy | Validation Loss |
+|:-------------:|:-----:|:-----:|:--------:|:---------------:|
+| 0.1549        | 1.0   | 1563  | 0.9198   | 0.3020          |
+| 0.0778        | 2.0   | 3126  | 0.9316   | 0.2819          |
+| 0.0931        | 3.0   | 4689  | 0.9255   | 0.2931          |
+| 0.0538        | 4.0   | 6252  | 0.9307   | 0.3606          |
+| 0.0303        | 5.0   | 7815  | 0.9314   | 0.4229          |
+| 0.0106        | 6.0   | 9378  | 0.9304   | 0.5013          |
+| 0.0125        | 7.0   | 10941 | 0.9316   | 0.4994          |
+| 0.0112        | 8.0   | 12504 | 0.9329   | 0.5481          |
+| 0.0129        | 9.0   | 14067 | 0.5440   | 0.9327          |
+| 0.0           | 10.0  | 15630 | 0.5739   | 0.9334          |
 
 
 ### Framework versions