|
--- |
|
license: mit |
|
base_model: prajjwal1/bert-mini |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: bert_mini_cosmetic |
|
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. --> |
|
|
|
# bert_mini_cosmetic |
|
|
|
This model is a fine-tuned version of [prajjwal1/bert-mini](https://huggingface.co/prajjwal1/bert-mini) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3512 |
|
- Accuracy: 0.9083 |
|
|
|
## 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: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| No log | 1.0 | 120 | 0.7387 | 0.8848 | |
|
| No log | 2.0 | 240 | 0.4699 | 0.9047 | |
|
| No log | 3.0 | 360 | 0.3882 | 0.9041 | |
|
| No log | 4.0 | 480 | 0.3598 | 0.9078 | |
|
| 0.6339 | 5.0 | 600 | 0.3512 | 0.9083 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.1 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
|
|
