|
|
--- |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: user_class_L |
|
|
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. --> |
|
|
|
|
|
# user_class_L |
|
|
|
|
|
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.5451 |
|
|
- Accuracy: 0.9237 |
|
|
|
|
|
## 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: 3.8e-05 |
|
|
- train_batch_size: 30 |
|
|
- eval_batch_size: 4 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 15 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
|
| 0.1572 | 1.0 | 24 | 0.2433 | 0.9025 | |
|
|
| 0.1649 | 2.0 | 48 | 0.2262 | 0.9237 | |
|
|
| 0.2498 | 3.0 | 72 | 0.2584 | 0.9237 | |
|
|
| 0.006 | 4.0 | 96 | 0.3393 | 0.9153 | |
|
|
| 0.0035 | 5.0 | 120 | 0.3967 | 0.9153 | |
|
|
| 0.0017 | 6.0 | 144 | 0.4777 | 0.9153 | |
|
|
| 0.0006 | 7.0 | 168 | 0.6257 | 0.8898 | |
|
|
| 0.0005 | 8.0 | 192 | 0.5752 | 0.9153 | |
|
|
| 0.0002 | 9.0 | 216 | 0.5182 | 0.9237 | |
|
|
| 0.0003 | 10.0 | 240 | 0.5041 | 0.9195 | |
|
|
| 0.0002 | 11.0 | 264 | 0.5051 | 0.9195 | |
|
|
| 0.0001 | 12.0 | 288 | 0.5292 | 0.9195 | |
|
|
| 0.0002 | 13.0 | 312 | 0.5391 | 0.9237 | |
|
|
| 0.0002 | 14.0 | 336 | 0.5437 | 0.9237 | |
|
|
| 0.0002 | 15.0 | 360 | 0.5451 | 0.9237 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.24.0 |
|
|
- Pytorch 1.13.0+cu117 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.2 |
|
|
|
