|
--- |
|
license: mit |
|
base_model: microsoft/deberta-v3-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: cyner_deberta |
|
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. --> |
|
|
|
# cyner_deberta |
|
|
|
This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0685 |
|
- Precision: 0.7801 |
|
- Recall: 0.8110 |
|
- F1: 0.7952 |
|
- Accuracy: 0.9839 |
|
|
|
## 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: 10.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.1285 | 1.42 | 500 | 0.0762 | 0.7305 | 0.8033 | 0.7652 | 0.9823 | |
|
| 0.041 | 2.84 | 1000 | 0.0685 | 0.7801 | 0.8110 | 0.7952 | 0.9839 | |
|
| 0.024 | 4.26 | 1500 | 0.0796 | 0.7957 | 0.8008 | 0.7982 | 0.9855 | |
|
| 0.0156 | 5.68 | 2000 | 0.0747 | 0.7836 | 0.8276 | 0.8050 | 0.9858 | |
|
| 0.0106 | 7.1 | 2500 | 0.0817 | 0.7961 | 0.8327 | 0.8140 | 0.9859 | |
|
| 0.0064 | 8.52 | 3000 | 0.0828 | 0.7942 | 0.8429 | 0.8178 | 0.9865 | |
|
| 0.0049 | 9.94 | 3500 | 0.0858 | 0.7976 | 0.8352 | 0.8160 | 0.9865 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.0.dev0 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|
