LovenOO
/

BERT_without_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: 0.7387
-- Precision: 0.8354
-- Recall: 0.8466
-- F1: 0.8405
-- Accuracy: 0.8754
 ## Model description
@@ -43,7 +43,7 @@ More information needed
 ### Training hyperparameters
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
 - train_batch_size: 32
 - eval_batch_size: 32
 - seed: 42
@@ -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   | 257  | 0.5628          | 0.7527    | 0.8299 | 0.7774 | 0.8336   |
-| 0.6883        | 2.0   | 514  | 0.4727          | 0.8332    | 0.8530 | 0.8419 | 0.8740   |
-| 0.6883        | 3.0   | 771  | 0.4391          | 0.8188    | 0.8702 | 0.8411 | 0.8725   |
-| 0.2393        | 4.0   | 1028 | 0.5871          | 0.8243    | 0.8513 | 0.8327 | 0.8676   |
-| 0.2393        | 5.0   | 1285 | 0.6000          | 0.8211    | 0.8466 | 0.8323 | 0.8706   |
-| 0.1341        | 6.0   | 1542 | 0.6232          | 0.8244    | 0.8543 | 0.8376 | 0.8735   |
-| 0.1341        | 7.0   | 1799 | 0.6928          | 0.8334    | 0.8464 | 0.8390 | 0.8779   |
-| 0.0786        | 8.0   | 2056 | 0.7089          | 0.8337    | 0.8479 | 0.8400 | 0.8735   |
-| 0.0786        | 9.0   | 2313 | 0.7268          | 0.8363    | 0.8464 | 0.8404 | 0.8774   |
-| 0.0539        | 10.0  | 2570 | 0.7387          | 0.8354    | 0.8466 | 0.8405 | 0.8754   |
 ### 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: 0.6705
+- Precision: 0.8452
+- Recall: 0.8581
+- F1: 0.8510
+- Accuracy: 0.8818
 ## Model description
 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 3e-05
 - train_batch_size: 32
 - eval_batch_size: 32
 - seed: 42
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 257  | 0.5962          | 0.7414    | 0.8132 | 0.7626 | 0.8268   |
+| 0.7597        | 2.0   | 514  | 0.5120          | 0.8170    | 0.8507 | 0.8292 | 0.8652   |
+| 0.7597        | 3.0   | 771  | 0.4818          | 0.7975    | 0.8565 | 0.8202 | 0.8652   |
+| 0.2391        | 4.0   | 1028 | 0.5223          | 0.8220    | 0.8613 | 0.8377 | 0.8652   |
+| 0.2391        | 5.0   | 1285 | 0.5516          | 0.8172    | 0.8599 | 0.8347 | 0.8706   |
+| 0.1316        | 6.0   | 1542 | 0.5747          | 0.8139    | 0.8593 | 0.8333 | 0.8710   |
+| 0.1316        | 7.0   | 1799 | 0.6290          | 0.8332    | 0.8483 | 0.8386 | 0.8701   |
+| 0.0773        | 8.0   | 2056 | 0.6089          | 0.8312    | 0.8620 | 0.8450 | 0.8764   |
+| 0.0773        | 9.0   | 2313 | 0.6633          | 0.8384    | 0.8532 | 0.8448 | 0.8774   |
+| 0.0633        | 10.0  | 2570 | 0.6705          | 0.8452    | 0.8581 | 0.8510 | 0.8818   |
 ### Framework versions