metadata
license: mit
base_model: microsoft/deberta-v3-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: DeBERTa-finetuned-ner-S800
results: []
DeBERTa-finetuned-ner-S800
This model is a fine-tuned version of microsoft/deberta-v3-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0681
- Precision: 0.6874
- Recall: 0.7731
- F1: 0.7278
- Accuracy: 0.9771
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 55 | 0.0748 | 0.5784 | 0.6457 | 0.6102 | 0.9699 |
| No log | 2.0 | 110 | 0.0709 | 0.6174 | 0.7773 | 0.6882 | 0.9750 |
| No log | 3.0 | 165 | 0.0670 | 0.6460 | 0.7899 | 0.7108 | 0.9758 |
| No log | 4.0 | 220 | 0.0628 | 0.6966 | 0.7717 | 0.7322 | 0.9775 |
| No log | 5.0 | 275 | 0.0681 | 0.6874 | 0.7731 | 0.7278 | 0.9771 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3