singhshiva/excelB

README.md

@@ -16,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # my-bert-classifier3
 
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1884
-- Accuracy: 0.9555
+- Loss: 0.0814
+- Accuracy: 0.9826
 
 ## Model description
 
@@ -38,27 +38,25 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 1e-05
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 2
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.3273        | 1.0   | 73   | 0.2244          | 0.9247   |
-| 0.1971        | 2.0   | 146  | 0.1142          | 0.9658   |
-| 0.1245        | 3.0   | 219  | 0.1556          | 0.9623   |
-| 0.0031        | 4.0   | 292  | 0.1447          | 0.9692   |
-| 0.0357        | 5.0   | 365  | 0.1884          | 0.9555   |
+| 0.0409        | 1.0   | 689  | 0.1486          | 0.9666   |
+| 0.0055        | 2.0   | 1378 | 0.0814          | 0.9826   |
 
 
 ### Framework versions
 
 - Transformers 4.50.0
 - Pytorch 2.6.0+cu124
+- Datasets 3.4.1
 - Tokenizers 0.21.1