LovenOO
/

BERT_large_with_preprocessing_grid_search

Text Classification

Transformers

PyTorch

TensorBoard

bert

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

LovenOO commited on Aug 11, 2023

Commit

5824fb7

1 Parent(s): e7c2f36

update model card README.md

Browse files

Files changed (1) hide show

README.md +16 -16

README.md CHANGED Viewed

@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.0732
-- Precision: 0.0194
-- Recall: 0.125
-- F1: 0.0336
-- Accuracy: 0.1551
 ## 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 |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 2.1235        | 1.0   | 510  | 2.0738          | 0.0284    | 0.125  | 0.0462 | 0.2268   |
-| 2.1058        | 2.0   | 1020 | 2.0805          | 0.0194    | 0.125  | 0.0336 | 0.1551   |
-| 2.1039        | 3.0   | 1530 | 2.0780          | 0.0345    | 0.125  | 0.0541 | 0.2759   |
-| 2.1045        | 4.0   | 2040 | 2.0734          | 0.0284    | 0.125  | 0.0462 | 0.2268   |
-| 2.0963        | 5.0   | 2550 | 2.0779          | 0.0041    | 0.125  | 0.0080 | 0.0329   |
-| 2.0975        | 6.0   | 3060 | 2.0750          | 0.0284    | 0.125  | 0.0462 | 0.2268   |
-| 2.0944        | 7.0   | 3570 | 2.0734          | 0.0194    | 0.125  | 0.0336 | 0.1551   |
-| 2.1004        | 8.0   | 4080 | 2.0820          | 0.0029    | 0.125  | 0.0056 | 0.0231   |
-| 2.0974        | 9.0   | 4590 | 2.0724          | 0.0187    | 0.125  | 0.0326 | 0.1497   |
-| 2.0936        | 10.0  | 5100 | 2.0732          | 0.0194    | 0.125  | 0.0336 | 0.1551   |
 ### Framework versions

 This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.8575
+- Precision: 0.8355
+- Recall: 0.8484
+- F1: 0.8401
+- Accuracy: 0.8753
 ## 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 |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 1.0054        | 1.0   | 510  | 0.6756          | 0.7428    | 0.8093 | 0.7561 | 0.8095   |
+| 0.4708        | 2.0   | 1020 | 0.5588          | 0.7870    | 0.8473 | 0.8101 | 0.8419   |
+| 0.2992        | 3.0   | 1530 | 0.5928          | 0.8114    | 0.8595 | 0.8286 | 0.8660   |
+| 0.2202        | 4.0   | 2040 | 0.6855          | 0.8465    | 0.8468 | 0.8452 | 0.8729   |
+| 0.149         | 5.0   | 2550 | 0.6949          | 0.8136    | 0.8565 | 0.8324 | 0.8689   |
+| 0.1246        | 6.0   | 3060 | 0.7984          | 0.8290    | 0.8518 | 0.8393 | 0.8719   |
+| 0.0958        | 7.0   | 3570 | 0.7819          | 0.8326    | 0.8478 | 0.8391 | 0.8694   |
+| 0.0922        | 8.0   | 4080 | 0.8141          | 0.8263    | 0.8486 | 0.8358 | 0.8724   |
+| 0.0658        | 9.0   | 4590 | 0.8614          | 0.8472    | 0.8508 | 0.8476 | 0.8797   |
+| 0.0662        | 10.0  | 5100 | 0.8575          | 0.8355    | 0.8484 | 0.8401 | 0.8753   |
 ### Framework versions