|
--- |
|
license: mit |
|
base_model: microsoft/deberta-v3-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: deberta-v3-base-Whatsapp-ner |
|
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. --> |
|
|
|
# deberta-v3-base-Whatsapp-ner |
|
|
|
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: 0.0559 |
|
- Precision: 0.95 |
|
- Recall: 0.9661 |
|
- F1: 0.9580 |
|
- Accuracy: 0.9856 |
|
|
|
## 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: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 6 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 59 | 0.1342 | 0.8974 | 0.8898 | 0.8936 | 0.9633 | |
|
| No log | 2.0 | 118 | 0.0559 | 0.95 | 0.9661 | 0.9580 | 0.9856 | |
|
| No log | 3.0 | 177 | 0.0612 | 0.9417 | 0.9576 | 0.9496 | 0.9872 | |
|
| No log | 4.0 | 236 | 0.0605 | 0.9322 | 0.9322 | 0.9322 | 0.9840 | |
|
| No log | 5.0 | 295 | 0.0570 | 0.9496 | 0.9576 | 0.9536 | 0.9888 | |
|
| No log | 6.0 | 354 | 0.0579 | 0.9496 | 0.9576 | 0.9536 | 0.9888 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
