| --- |
| license: mit |
| base_model: prajjwal1/bert-tiny |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| - f1 |
| model-index: |
| - name: TestForColab |
| 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. --> |
|
|
| # TestForColab |
|
|
| This model is a fine-tuned version of [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.2129 |
| - Accuracy: 0.94 |
| - F1: 0.9394 |
|
|
| ## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: linear |
| - num_epochs: 10 |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
| | No log | 0.01 | 50 | 0.6913 | 0.55 | 0.3903 | |
| | No log | 0.02 | 100 | 0.6909 | 0.59 | 0.5186 | |
| | No log | 0.03 | 150 | 0.6934 | 0.45 | 0.2793 | |
| | No log | 0.04 | 200 | 0.6889 | 0.57 | 0.5709 | |
| | No log | 0.05 | 250 | 0.6818 | 0.56 | 0.5607 | |
| | No log | 0.06 | 300 | 0.6854 | 0.56 | 0.5607 | |
| | No log | 0.07 | 350 | 0.6878 | 0.56 | 0.5607 | |
| | No log | 0.08 | 400 | 0.7014 | 0.56 | 0.5607 | |
| | No log | 0.09 | 450 | 0.6797 | 0.56 | 0.5607 | |
| | 0.6799 | 0.1 | 500 | 0.6731 | 0.56 | 0.5607 | |
| | 0.6799 | 0.11 | 550 | 0.6490 | 0.64 | 0.6203 | |
| | 0.6799 | 0.12 | 600 | 0.6456 | 0.71 | 0.7049 | |
| | 0.6799 | 0.13 | 650 | 0.6259 | 0.64 | 0.6203 | |
| | 0.6799 | 0.14 | 700 | 0.5264 | 0.83 | 0.8304 | |
| | 0.6799 | 0.15 | 750 | 0.4671 | 0.83 | 0.8304 | |
| | 0.6799 | 0.16 | 800 | 0.3387 | 0.94 | 0.9394 | |
| | 0.6799 | 0.17 | 850 | 0.2935 | 0.94 | 0.9394 | |
| | 0.6799 | 0.18 | 900 | 0.2604 | 0.94 | 0.9394 | |
| | 0.6799 | 0.19 | 950 | 0.2443 | 0.94 | 0.9394 | |
| | 0.4884 | 0.2 | 1000 | 0.2355 | 0.94 | 0.9394 | |
| | 0.4884 | 0.2 | 1050 | 0.2286 | 0.94 | 0.9394 | |
| | 0.4884 | 0.21 | 1100 | 0.2240 | 0.94 | 0.9394 | |
| | 0.4884 | 0.22 | 1150 | 0.2201 | 0.94 | 0.9394 | |
| | 0.4884 | 0.23 | 1200 | 0.2165 | 0.94 | 0.9394 | |
| | 0.4884 | 0.24 | 1250 | 0.2129 | 0.94 | 0.9394 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.35.2 |
| - Pytorch 2.1.0+cu118 |
| - Datasets 2.15.0 |
| - Tokenizers 0.15.0 |
|
|
