|
|
--- |
|
|
library_name: transformers |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
- f1 |
|
|
- precision |
|
|
model-index: |
|
|
- name: student_s3d_default_not_learning_RWF2000 |
|
|
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. --> |
|
|
|
|
|
# student_s3d_default_not_learning_RWF2000 |
|
|
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.3789 |
|
|
- Accuracy: 0.885 |
|
|
- F1: 0.8847 |
|
|
- Precision: 0.8893 |
|
|
|
|
|
## 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: 1e-05 |
|
|
- train_batch_size: 75 |
|
|
- eval_batch_size: 75 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_steps: 47 |
|
|
- training_steps: 475 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | |
|
|
|:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|:---------:| |
|
|
| 0.6345 | 2.0147 | 47 | 0.5707 | 0.7656 | 0.7621 | 0.7824 | |
|
|
| 0.4332 | 4.0295 | 94 | 0.3666 | 0.8219 | 0.8218 | 0.8222 | |
|
|
| 0.3306 | 7.0021 | 141 | 0.4903 | 0.825 | 0.8246 | 0.8283 | |
|
|
| 0.2447 | 9.0168 | 188 | 0.3415 | 0.8375 | 0.8361 | 0.8498 | |
|
|
| 0.1972 | 11.0316 | 235 | 0.4171 | 0.8375 | 0.8359 | 0.8516 | |
|
|
| 0.173 | 14.0042 | 282 | 0.3911 | 0.8656 | 0.8650 | 0.8720 | |
|
|
| 0.1481 | 16.0189 | 329 | 0.4326 | 0.8719 | 0.8714 | 0.8772 | |
|
|
| 0.1165 | 18.0337 | 376 | 0.2364 | 0.8812 | 0.8811 | 0.8834 | |
|
|
| 0.098 | 21.0063 | 423 | 0.5760 | 0.8844 | 0.8843 | 0.8856 | |
|
|
| 0.0857 | 23.0211 | 470 | 0.5217 | 0.8812 | 0.8811 | 0.8827 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.45.2 |
|
|
- Pytorch 2.0.1+cu118 |
|
|
- Datasets 3.0.1 |
|
|
- Tokenizers 0.20.0 |
|
|
|
