update model card README.md

README.md

@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-multilingual-uncased](https://huggingface.co/bert-base-multilingual-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3504
-- Precision: 0.7086
-- Recall: 0.6804
-- F1: 0.6942
-- Accuracy: 0.9171
+- Loss: 0.3736
+- Precision: 0.7185
+- Recall: 0.7180
+- F1: 0.7182
+- Accuracy: 0.9254
 
 ## Model description
 
@@ -43,8 +43,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- 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
@@ -54,11 +54,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 290  | 0.3937          | 0.6284    | 0.5766 | 0.6014 | 0.8895   |
-| 0.3266        | 2.0   | 580  | 0.3662          | 0.7089    | 0.6598 | 0.6834 | 0.9107   |
-| 0.3266        | 3.0   | 870  | 0.3504          | 0.7086    | 0.6804 | 0.6942 | 0.9171   |
-| 0.1231        | 4.0   | 1160 | 0.3523          | 0.7404    | 0.7099 | 0.7248 | 0.9274   |
-| 0.1231        | 5.0   | 1450 | 0.3636          | 0.7509    | 0.7305 | 0.7406 | 0.9293   |
+| No log        | 1.0   | 145  | 0.3877          | 0.7219    | 0.6767 | 0.6986 | 0.9218   |
+| No log        | 2.0   | 290  | 0.4076          | 0.72      | 0.6892 | 0.7043 | 0.9137   |
+| No log        | 3.0   | 435  | 0.3736          | 0.7185    | 0.7180 | 0.7182 | 0.9254   |
+| 0.0637        | 4.0   | 580  | 0.4199          | 0.7240    | 0.7128 | 0.7184 | 0.9216   |
+| 0.0637        | 5.0   | 725  | 0.4591          | 0.7206    | 0.7121 | 0.7163 | 0.9209   |
 
 
 ### Framework versions