|
---
|
|
license: mit
|
|
base_model: FacebookAI/roberta-large
|
|
tags:
|
|
- generated_from_trainer
|
|
metrics:
|
|
- accuracy
|
|
model-index:
|
|
- name: super_clean_model
|
|
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. -->
|
|
|
|
# super_clean_model
|
|
|
|
This model is a fine-tuned version of [FacebookAI/roberta-large](https://huggingface.co/FacebookAI/roberta-large) on the None dataset.
|
|
It achieves the following results on the evaluation set:
|
|
- Loss: 0.2385
|
|
- Accuracy: 0.9485
|
|
|
|
## 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: 8
|
|
- eval_batch_size: 8
|
|
- seed: 42
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
|
- lr_scheduler_type: linear
|
|
- num_epochs: 3
|
|
|
|
### Training results
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
|
| 0.6712 | 0.04 | 100 | 0.7864 | 0.6115 |
|
|
| 0.4785 | 0.09 | 200 | 1.1828 | 0.7385 |
|
|
| 0.475 | 0.13 | 300 | 0.3719 | 0.888 |
|
|
| 0.3643 | 0.18 | 400 | 0.6170 | 0.887 |
|
|
| 0.3546 | 0.22 | 500 | 0.6397 | 0.9045 |
|
|
| 0.3796 | 0.27 | 600 | 0.2512 | 0.9435 |
|
|
| 0.3301 | 0.31 | 700 | 0.2626 | 0.9135 |
|
|
| 0.3343 | 0.36 | 800 | 0.4675 | 0.8745 |
|
|
| 0.3578 | 0.4 | 900 | 0.2701 | 0.903 |
|
|
| 0.2604 | 0.44 | 1000 | 0.2385 | 0.9485 |
|
|
| 0.3236 | 0.49 | 1100 | 1.9438 | 0.6565 |
|
|
| 0.3147 | 0.53 | 1200 | 1.2576 | 0.779 |
|
|
| 0.2758 | 0.58 | 1300 | 0.3486 | 0.9345 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.36.2
|
|
- Pytorch 2.1.1+cu118
|
|
- Datasets 2.16.0
|
|
- Tokenizers 0.15.0
|
|
|
