LovenOO
/

distilBERT_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 [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7065
-- Precision: 0.8418
-- Recall: 0.8521
-- F1: 0.8453
-- Accuracy: 0.8838
 ## 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   | 257  | 0.5948          | 0.7470    | 0.8351 | 0.7753 | 0.8375   |
-| 0.8584        | 2.0   | 514  | 0.5402          | 0.7946    | 0.8405 | 0.8048 | 0.8643   |
-| 0.8584        | 3.0   | 771  | 0.5362          | 0.8012    | 0.8425 | 0.8164 | 0.8682   |
-| 0.3181        | 4.0   | 1028 | 0.5224          | 0.8062    | 0.8622 | 0.8290 | 0.875    |
-| 0.3181        | 5.0   | 1285 | 0.5766          | 0.8234    | 0.8514 | 0.8353 | 0.8769   |
-| 0.1767        | 6.0   | 1542 | 0.6231          | 0.8229    | 0.8531 | 0.8363 | 0.8755   |
-| 0.1767        | 7.0   | 1799 | 0.6359          | 0.8370    | 0.8576 | 0.8456 | 0.8847   |
-| 0.1231        | 8.0   | 2056 | 0.6849          | 0.8391    | 0.8538 | 0.8452 | 0.8823   |
-| 0.1231        | 9.0   | 2313 | 0.6961          | 0.8453    | 0.8450 | 0.8431 | 0.8823   |
-| 0.0862        | 10.0  | 2570 | 0.7065          | 0.8418    | 0.8521 | 0.8453 | 0.8838   |
 ### 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: 0.8262
+- Precision: 0.8491
+- Recall: 0.8536
+- F1: 0.8511
+- Accuracy: 0.8837
 ## Model description
 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 5e-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 |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.8922        | 1.0   | 514  | 0.5350          | 0.7953    | 0.8363 | 0.8092 | 0.8628   |
+| 0.4521        | 2.0   | 1028 | 0.5359          | 0.8214    | 0.8385 | 0.8282 | 0.8652   |
+| 0.2928        | 3.0   | 1542 | 0.5876          | 0.8264    | 0.8504 | 0.8367 | 0.8798   |
+| 0.2099        | 4.0   | 2056 | 0.6974          | 0.8288    | 0.8435 | 0.8351 | 0.8764   |
+| 0.1531        | 5.0   | 2570 | 0.8245          | 0.8367    | 0.8125 | 0.8232 | 0.8710   |
+| 0.1124        | 6.0   | 3084 | 0.7553          | 0.8349    | 0.8543 | 0.8435 | 0.8764   |
+| 0.1045        | 7.0   | 3598 | 0.7912          | 0.8452    | 0.8538 | 0.8492 | 0.8822   |
+| 0.0716        | 8.0   | 4112 | 0.7909          | 0.8422    | 0.8529 | 0.8471 | 0.8788   |
+| 0.0746        | 9.0   | 4626 | 0.8364          | 0.8462    | 0.8458 | 0.8458 | 0.8779   |
+| 0.0533        | 10.0  | 5140 | 0.8262          | 0.8491    | 0.8536 | 0.8511 | 0.8837   |
 ### Framework versions