| --- |
| library_name: transformers |
| license: mit |
| base_model: prajjwal1/bert-tiny |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| - f1 |
| - precision |
| - recall |
| model-index: |
| - name: results |
| results: [] |
| --- |
| |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| should probably proofread and complete it, then remove this comment. --> |
|
|
| # results |
|
|
| This model is a fine-tuned version of [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) on the None dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.0081 |
| - Accuracy: 1.0 |
| - F1: 1.0 |
| - Precision: 1.0 |
| - Recall: 1.0 |
|
|
| ## Model description |
|
|
| More information needed |
|
|
| ## Intended uses & limitations |
|
|
| More information needed |
|
|
| ## Training and evaluation data |
|
|
| More information needed |
|
|
| ## Training procedure |
|
|
| ### Training hyperparameters |
|
|
| The following hyperparameters were used during training: |
| - learning_rate: 2e-05 |
| - train_batch_size: 16 |
| - eval_batch_size: 16 |
| - seed: 42 |
| - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
| - lr_scheduler_type: linear |
| - num_epochs: 50 |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| |
| | No log | 1.0 | 125 | 1.4595 | 0.666 | 0.5919 | 0.7955 | 0.6412 | |
| | No log | 2.0 | 250 | 1.2117 | 0.894 | 0.8814 | 0.8937 | 0.8839 | |
| | No log | 3.0 | 375 | 0.9703 | 0.924 | 0.9164 | 0.9352 | 0.9149 | |
| | 1.2705 | 4.0 | 500 | 0.7647 | 0.934 | 0.9284 | 0.9428 | 0.9262 | |
| | 1.2705 | 5.0 | 625 | 0.5898 | 0.97 | 0.9664 | 0.9722 | 0.9659 | |
| | 1.2705 | 6.0 | 750 | 0.4600 | 0.97 | 0.9664 | 0.9722 | 0.9659 | |
| | 1.2705 | 7.0 | 875 | 0.3596 | 0.97 | 0.9664 | 0.9722 | 0.9659 | |
| | 0.5486 | 8.0 | 1000 | 0.2753 | 0.97 | 0.9664 | 0.9722 | 0.9659 | |
| | 0.5486 | 9.0 | 1125 | 0.1988 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.5486 | 10.0 | 1250 | 0.1469 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.5486 | 11.0 | 1375 | 0.1139 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.1935 | 12.0 | 1500 | 0.0904 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.1935 | 13.0 | 1625 | 0.0743 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.1935 | 14.0 | 1750 | 0.0630 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.1935 | 15.0 | 1875 | 0.0542 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0781 | 16.0 | 2000 | 0.0473 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0781 | 17.0 | 2125 | 0.0418 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0781 | 18.0 | 2250 | 0.0374 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0781 | 19.0 | 2375 | 0.0337 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0449 | 20.0 | 2500 | 0.0305 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0449 | 21.0 | 2625 | 0.0279 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0449 | 22.0 | 2750 | 0.0256 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0449 | 23.0 | 2875 | 0.0236 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0305 | 24.0 | 3000 | 0.0219 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0305 | 25.0 | 3125 | 0.0204 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0305 | 26.0 | 3250 | 0.0190 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0305 | 27.0 | 3375 | 0.0178 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0224 | 28.0 | 3500 | 0.0167 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0224 | 29.0 | 3625 | 0.0157 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0224 | 30.0 | 3750 | 0.0149 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0224 | 31.0 | 3875 | 0.0141 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0181 | 32.0 | 4000 | 0.0134 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0181 | 33.0 | 4125 | 0.0127 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0181 | 34.0 | 4250 | 0.0121 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0181 | 35.0 | 4375 | 0.0116 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0141 | 36.0 | 4500 | 0.0111 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0141 | 37.0 | 4625 | 0.0107 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0141 | 38.0 | 4750 | 0.0103 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0141 | 39.0 | 4875 | 0.0099 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0120 | 40.0 | 5000 | 0.0096 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0120 | 41.0 | 5125 | 0.0093 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0120 | 42.0 | 5250 | 0.0091 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0120 | 43.0 | 5375 | 0.0088 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0108 | 44.0 | 5500 | 0.0087 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0108 | 45.0 | 5625 | 0.0085 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0108 | 46.0 | 5750 | 0.0083 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0108 | 47.0 | 5875 | 0.0082 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0096 | 48.0 | 6000 | 0.0082 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0096 | 49.0 | 6125 | 0.0081 | 1.0 | 1.0 | 1.0 | 1.0 | |
| | 0.0096 | 50.0 | 6250 | 0.0081 | 1.0 | 1.0 | 1.0 | 1.0 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 5.0.0 |
| - Pytorch 2.9.0+cu126 |
| - Datasets 4.0.0 |
| - Tokenizers 0.22.2 |
| |
