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: 0.7803
-- Precision: 0.8448
-- Recall: 0.8438
-- F1: 0.8437
-- Accuracy: 0.8783
 ## 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: 16
-- eval_batch_size: 16
 - 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 |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 1.0001        | 1.0   | 514  | 0.6163          | 0.7620    | 0.8133 | 0.7790 | 0.8394   |
-| 0.4832        | 2.0   | 1028 | 0.5556          | 0.8131    | 0.8284 | 0.8166 | 0.8623   |
-| 0.3307        | 3.0   | 1542 | 0.5381          | 0.8168    | 0.8425 | 0.8254 | 0.8691   |
-| 0.2429        | 4.0   | 2056 | 0.6014          | 0.8289    | 0.8455 | 0.8353 | 0.8720   |
-| 0.1849        | 5.0   | 2570 | 0.6600          | 0.8367    | 0.8408 | 0.8375 | 0.8740   |
-| 0.1564        | 6.0   | 3084 | 0.6724          | 0.8219    | 0.8491 | 0.8333 | 0.8696   |
-| 0.1316        | 7.0   | 3598 | 0.7511          | 0.8536    | 0.8481 | 0.8501 | 0.8808   |
-| 0.1037        | 8.0   | 4112 | 0.7284          | 0.8438    | 0.8494 | 0.8461 | 0.8798   |
-| 0.0946        | 9.0   | 4626 | 0.7584          | 0.8452    | 0.8470 | 0.8457 | 0.8798   |
-| 0.0731        | 10.0  | 5140 | 0.7803          | 0.8448    | 0.8438 | 0.8437 | 0.8783   |
 ### 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: 0.7297
+- Precision: 0.8417
+- Recall: 0.8510
+- F1: 0.8460
+- Accuracy: 0.8793
 ## Model description
 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 5e-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
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 257  | 0.4958          | 0.7757    | 0.8526 | 0.8027 | 0.8526   |
+| 0.6647        | 2.0   | 514  | 0.4756          | 0.8336    | 0.8480 | 0.8386 | 0.8701   |
+| 0.6647        | 3.0   | 771  | 0.4823          | 0.8197    | 0.8588 | 0.8360 | 0.8730   |
+| 0.2305        | 4.0   | 1028 | 0.5479          | 0.8314    | 0.8618 | 0.8439 | 0.8735   |
+| 0.2305        | 5.0   | 1285 | 0.5832          | 0.8295    | 0.8542 | 0.8401 | 0.8779   |
+| 0.1282        | 6.0   | 1542 | 0.5929          | 0.8251    | 0.8627 | 0.8404 | 0.8745   |
+| 0.1282        | 7.0   | 1799 | 0.7066          | 0.8476    | 0.8496 | 0.8472 | 0.8774   |
+| 0.0828        | 8.0   | 2056 | 0.6873          | 0.8392    | 0.8510 | 0.8448 | 0.8764   |
+| 0.0828        | 9.0   | 2313 | 0.7189          | 0.8410    | 0.8524 | 0.8461 | 0.8788   |
+| 0.0566        | 10.0  | 2570 | 0.7297          | 0.8417    | 0.8510 | 0.8460 | 0.8793   |
 ### Framework versions