update model card README.md

README.md

@@ -3,10 +3,10 @@ license: apache-2.0
 tags:
 - generated_from_trainer
 metrics:
+- accuracy
 - precision
 - recall
 - f1
-- accuracy
 model-index:
 - name: bert-finetuned-gesture-prediction-21-classes
   results: []
@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7728
-- Precision: 0.5873
-- Recall: 0.7150
-- F1: 0.6449
-- Accuracy: 0.7956
+- Loss: 0.9818
+- Accuracy: 0.8232
+- Precision: 0.8213
+- Recall: 0.8232
+- F1: 0.8181
 
 ## Model description
 
@@ -42,21 +42,28 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 9.076335861120684e-05
+- learning_rate: 2e-05
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 10
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 1.643         | 1.0   | 104  | 0.9867          | 0.4314    | 0.6039 | 0.5033 | 0.7449   |
-| 0.7256        | 2.0   | 208  | 0.7743          | 0.5393    | 0.6715 | 0.5982 | 0.7842   |
-| 0.3614        | 3.0   | 312  | 0.7728          | 0.5873    | 0.7150 | 0.6449 | 0.7956   |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 2.1826        | 1.0   | 104  | 1.2892          | 0.7193   | 0.6656    | 0.7193 | 0.6745 |
+| 1.0758        | 2.0   | 208  | 0.9593          | 0.7816   | 0.7519    | 0.7816 | 0.7621 |
+| 0.6947        | 3.0   | 312  | 0.9170          | 0.7885   | 0.7730    | 0.7885 | 0.7760 |
+| 0.4928        | 4.0   | 416  | 0.8967          | 0.8014   | 0.7931    | 0.8014 | 0.7913 |
+| 0.3413        | 5.0   | 520  | 0.9195          | 0.8034   | 0.8076    | 0.8034 | 0.7966 |
+| 0.2473        | 6.0   | 624  | 0.9123          | 0.8131   | 0.8134    | 0.8131 | 0.8078 |
+| 0.1799        | 7.0   | 728  | 0.9474          | 0.8191   | 0.8195    | 0.8191 | 0.8139 |
+| 0.1329        | 8.0   | 832  | 0.9611          | 0.8237   | 0.8222    | 0.8237 | 0.8182 |
+| 0.116         | 9.0   | 936  | 0.9849          | 0.8204   | 0.8190    | 0.8204 | 0.8148 |
+| 0.0972        | 10.0  | 1040 | 0.9818          | 0.8232   | 0.8213    | 0.8232 | 0.8181 |
 
 
 ### Framework versions