LovenOO
/

distilBERT_gptdata_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 [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2381
-- Precision: 0.9596
-- Recall: 0.9599
-- F1: 0.9594
-- Accuracy: 0.9594
 ## Model description
@@ -43,7 +43,7 @@ More information needed
 ### Training hyperparameters
 The following hyperparameters were used during training:
-- learning_rate: 3e-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   | 225  | 0.2213          | 0.9434    | 0.9430 | 0.9419 | 0.9422   |
-| No log        | 2.0   | 450  | 0.1806          | 0.9512    | 0.9516 | 0.9508 | 0.9506   |
-| 0.3512        | 3.0   | 675  | 0.1927          | 0.9515    | 0.9518 | 0.9512 | 0.9511   |
-| 0.3512        | 4.0   | 900  | 0.2410          | 0.9490    | 0.9494 | 0.9490 | 0.9489   |
-| 0.044         | 5.0   | 1125 | 0.2280          | 0.9554    | 0.9556 | 0.9550 | 0.955    |
-| 0.044         | 6.0   | 1350 | 0.2199          | 0.9611    | 0.9609 | 0.9606 | 0.9606   |
-| 0.0176        | 7.0   | 1575 | 0.2272          | 0.9562    | 0.9565 | 0.9560 | 0.9561   |
-| 0.0176        | 8.0   | 1800 | 0.2321          | 0.9574    | 0.9576 | 0.9572 | 0.9572   |
-| 0.0067        | 9.0   | 2025 | 0.2397          | 0.9590    | 0.9593 | 0.9588 | 0.9589   |
-| 0.0067        | 10.0  | 2250 | 0.2381          | 0.9596    | 0.9599 | 0.9594 | 0.9594   |
 ### Framework versions

 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.2221
+- Precision: 0.9563
+- Recall: 0.9566
+- F1: 0.9562
+- Accuracy: 0.9561
 ## Model description
 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 2e-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   | 225  | 0.2531          | 0.9361    | 0.9359 | 0.9346 | 0.935    |
+| No log        | 2.0   | 450  | 0.1835          | 0.9514    | 0.9520 | 0.9512 | 0.9511   |
+| 0.4372        | 3.0   | 675  | 0.1798          | 0.9543    | 0.9546 | 0.9539 | 0.9539   |
+| 0.4372        | 4.0   | 900  | 0.2059          | 0.9499    | 0.9500 | 0.9497 | 0.9494   |
+| 0.0575        | 5.0   | 1125 | 0.2002          | 0.9563    | 0.9567 | 0.9561 | 0.9561   |
+| 0.0575        | 6.0   | 1350 | 0.2019          | 0.9557    | 0.9552 | 0.9553 | 0.955    |
+| 0.0231        | 7.0   | 1575 | 0.2152          | 0.9548    | 0.9550 | 0.9546 | 0.9544   |
+| 0.0231        | 8.0   | 1800 | 0.2156          | 0.9554    | 0.9556 | 0.9554 | 0.955    |
+| 0.0116        | 9.0   | 2025 | 0.2240          | 0.9559    | 0.9561 | 0.9557 | 0.9556   |
+| 0.0116        | 10.0  | 2250 | 0.2221          | 0.9563    | 0.9566 | 0.9562 | 0.9561   |
 ### Framework versions