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: 0.2808
-- Precision: 0.9608
-- Recall: 0.9612
-- F1: 0.9607
-- Accuracy: 0.9606
 ## 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: 16
 - eval_batch_size: 16
 - 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   | 450  | 0.2169          | 0.9437    | 0.9445 | 0.9432 | 0.9433   |
-| 0.4523        | 2.0   | 900  | 0.1979          | 0.9486    | 0.9486 | 0.9479 | 0.9478   |
-| 0.109         | 3.0   | 1350 | 0.2404          | 0.9545    | 0.9539 | 0.9533 | 0.9533   |
-| 0.0659        | 4.0   | 1800 | 0.2330          | 0.9559    | 0.9555 | 0.9550 | 0.955    |
-| 0.0301        | 5.0   | 2250 | 0.2434          | 0.9580    | 0.9583 | 0.9580 | 0.9578   |
-| 0.0201        | 6.0   | 2700 | 0.2462          | 0.9572    | 0.9569 | 0.9570 | 0.9567   |
-| 0.0089        | 7.0   | 3150 | 0.2618          | 0.9581    | 0.9585 | 0.9581 | 0.9578   |
-| 0.0074        | 8.0   | 3600 | 0.2717          | 0.9616    | 0.9618 | 0.9612 | 0.9611   |
-| 0.0025        | 9.0   | 4050 | 0.2805          | 0.9597    | 0.9601 | 0.9596 | 0.9594   |
-| 0.0014        | 10.0  | 4500 | 0.2808          | 0.9608    | 0.9612 | 0.9607 | 0.9606   |
 ### 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: 0.2754
+- Precision: 0.9537
+- Recall: 0.9539
+- F1: 0.9534
+- Accuracy: 0.9533
 ## Model description
 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 2e-05
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 450  | 0.2320          | 0.9410    | 0.9412 | 0.9399 | 0.94     |
+| 0.5426        | 2.0   | 900  | 0.2227          | 0.9465    | 0.9472 | 0.9460 | 0.9461   |
+| 0.1125        | 3.0   | 1350 | 0.2242          | 0.9456    | 0.9446 | 0.9444 | 0.9439   |
+| 0.0642        | 4.0   | 1800 | 0.2368          | 0.9557    | 0.9556 | 0.9550 | 0.955    |
+| 0.0368        | 5.0   | 2250 | 0.2539          | 0.9515    | 0.9512 | 0.9513 | 0.9506   |
+| 0.024         | 6.0   | 2700 | 0.2570          | 0.9543    | 0.9546 | 0.9539 | 0.9539   |
+| 0.0106        | 7.0   | 3150 | 0.2576          | 0.9554    | 0.9547 | 0.9549 | 0.9544   |
+| 0.0121        | 8.0   | 3600 | 0.2783          | 0.9538    | 0.9540 | 0.9534 | 0.9533   |
+| 0.0047        | 9.0   | 4050 | 0.2817          | 0.9538    | 0.9540 | 0.9534 | 0.9533   |
+| 0.003         | 10.0  | 4500 | 0.2754          | 0.9537    | 0.9539 | 0.9534 | 0.9533   |
 ### Framework versions