update model card README.md

README.md

@@ -18,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.2354
-- Accuracy: 0.7269
-- Precision: 0.7269
-- Recall: 0.7269
-- F1 Score: 0.7277
+- Loss: 1.6569
+- Accuracy: 0.7419
+- Precision: 0.7419
+- Recall: 0.7419
+- F1 Score: 0.7426
 
 ## Model description
 
@@ -41,28 +41,23 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-06
-- train_batch_size: 16
-- eval_batch_size: 16
-- seed: 42
+- learning_rate: 3e-06
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 101
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 5
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 Score |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|
-| 0.0046        | 1.0   | 646  | 3.4709          | 0.7192   | 0.7192    | 0.7192 | 0.7212   |
-| 0.0078        | 2.0   | 1292 | 3.1741          | 0.7387   | 0.7387    | 0.7387 | 0.7395   |
-| 0.0112        | 3.0   | 1938 | 3.4579          | 0.7096   | 0.7096    | 0.7096 | 0.7093   |
-| 0.0084        | 4.0   | 2584 | 3.3145          | 0.7310   | 0.7310    | 0.7310 | 0.7321   |
-| 0.0172        | 5.0   | 3230 | 3.2485          | 0.7328   | 0.7328    | 0.7328 | 0.7336   |
-| 0.0178        | 6.0   | 3876 | 3.2365          | 0.7324   | 0.7324    | 0.7324 | 0.7329   |
-| 0.0129        | 7.0   | 4522 | 3.2885          | 0.7223   | 0.7223    | 0.7223 | 0.7230   |
-| 0.0213        | 8.0   | 5168 | 3.3215          | 0.7201   | 0.7201    | 0.7201 | 0.7209   |
-| 0.0397        | 9.0   | 5814 | 3.2563          | 0.7269   | 0.7269    | 0.7269 | 0.7274   |
-| 0.1601        | 10.0  | 6460 | 3.2354          | 0.7269   | 0.7269    | 0.7269 | 0.7277   |
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy | Precision | Recall | F1 Score |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:--------:|
+| 1.403         | 1.0   | 10330 | 1.3860          | 0.7128   | 0.7128    | 0.7128 | 0.7142   |
+| 1.3213        | 2.0   | 20660 | 1.3367          | 0.7365   | 0.7365    | 0.7365 | 0.7371   |
+| 1.1611        | 3.0   | 30990 | 1.4699          | 0.7396   | 0.7396    | 0.7396 | 0.7406   |
+| 1.0222        | 4.0   | 41320 | 1.6050          | 0.7374   | 0.7374    | 0.7374 | 0.7383   |
+| 0.9008        | 5.0   | 51650 | 1.6569          | 0.7419   | 0.7419    | 0.7419 | 0.7426   |
 
 
 ### Framework versions