LovenOO
/

BERT_with_preprocessing_grid_search

@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7918
-- Precision: 0.8374
-- Recall: 0.8246
-- F1: 0.8306
-- Accuracy: 0.8645
 ## Model description
@@ -43,9 +43,9 @@ More information needed
 ### Training hyperparameters
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 32
-- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -55,16 +55,16 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 255  | 0.7382          | 0.7058    | 0.7789 | 0.7260 | 0.7894   |
-| 0.907         | 2.0   | 510  | 0.5794          | 0.7838    | 0.8189 | 0.7976 | 0.8444   |
-| 0.907         | 3.0   | 765  | 0.5382          | 0.8084    | 0.8375 | 0.8200 | 0.8547   |
-| 0.2877        | 4.0   | 1020 | 0.5942          | 0.8301    | 0.8319 | 0.8301 | 0.8670   |
-| 0.2877        | 5.0   | 1275 | 0.6349          | 0.8198    | 0.8384 | 0.8280 | 0.8655   |
-| 0.1513        | 6.0   | 1530 | 0.7735          | 0.8384    | 0.8144 | 0.8250 | 0.8635   |
-| 0.1513        | 7.0   | 1785 | 0.7221          | 0.8456    | 0.8333 | 0.8385 | 0.8704   |
-| 0.1059        | 8.0   | 2040 | 0.7615          | 0.8390    | 0.8312 | 0.8349 | 0.8684   |
-| 0.1059        | 9.0   | 2295 | 0.7841          | 0.8362    | 0.8253 | 0.8306 | 0.8684   |
-| 0.0811        | 10.0  | 2550 | 0.7918          | 0.8374    | 0.8246 | 0.8306 | 0.8645   |
 ### Framework versions

 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.8836
+- Precision: 0.8262
+- Recall: 0.8258
+- F1: 0.8249
+- Accuracy: 0.8724
 ## Model description
 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 3e-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
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 1.047         | 1.0   | 510  | 0.6171          | 0.7493    | 0.8057 | 0.7716 | 0.8336   |
+| 0.4348        | 2.0   | 1020 | 0.4954          | 0.8056    | 0.8646 | 0.8296 | 0.8714   |
+| 0.2818        | 3.0   | 1530 | 0.6252          | 0.8181    | 0.8323 | 0.8212 | 0.8660   |
+| 0.1793        | 4.0   | 2040 | 0.7381          | 0.8216    | 0.8258 | 0.8227 | 0.8733   |
+| 0.1356        | 5.0   | 2550 | 0.8601          | 0.8161    | 0.8219 | 0.8165 | 0.8660   |
+| 0.1023        | 6.0   | 3060 | 0.8526          | 0.8363    | 0.8299 | 0.8307 | 0.8758   |
+| 0.0944        | 7.0   | 3570 | 0.8459          | 0.8234    | 0.8298 | 0.8251 | 0.8729   |
+| 0.0631        | 8.0   | 4080 | 0.8519          | 0.8212    | 0.8325 | 0.8252 | 0.8714   |
+| 0.0602        | 9.0   | 4590 | 0.8756          | 0.8200    | 0.8267 | 0.8226 | 0.8719   |
+| 0.0532        | 10.0  | 5100 | 0.8836          | 0.8262    | 0.8258 | 0.8249 | 0.8724   |
 ### Framework versions