|
--- |
|
license: mit |
|
base_model: microsoft/deberta-v3-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: hr_techgroup |
|
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. --> |
|
|
|
# hr_techgroup |
|
|
|
This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0512 |
|
- Accuracy: 0.9773 |
|
- F1: 0.9784 |
|
- Precision: 0.9790 |
|
- Recall: 0.9779 |
|
|
|
## 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 | F1 | Precision | Recall | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| No log | 1.0 | 114 | 0.0839 | 0.9618 | 0.9624 | 0.9624 | 0.9624 | |
|
| No log | 2.0 | 228 | 0.0536 | 0.9740 | 0.9749 | 0.9746 | 0.9751 | |
|
| No log | 3.0 | 342 | 0.0523 | 0.9751 | 0.9757 | 0.9762 | 0.9751 | |
|
| No log | 4.0 | 456 | 0.0517 | 0.9768 | 0.9776 | 0.9773 | 0.9779 | |
|
| 0.1003 | 5.0 | 570 | 0.0512 | 0.9773 | 0.9784 | 0.9790 | 0.9779 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.4 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
