metadata
license: mit
base_model: microsoft/deberta-v3-large
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: deberta-v3-large-finetuned-ner
results: []
deberta-v3-large-finetuned-ner
This model is a fine-tuned version of microsoft/deberta-v3-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0364
- Precision: 0.9641
- Recall: 0.9716
- F1: 0.9678
- Accuracy: 0.9931
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: 16
- eval_batch_size: 16
- 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 |
|---|---|---|---|---|---|---|---|
| 0.1237 | 1.0 | 878 | 0.0406 | 0.9492 | 0.9589 | 0.9540 | 0.9906 |
| 0.0242 | 2.0 | 1756 | 0.0340 | 0.9550 | 0.9634 | 0.9592 | 0.9917 |
| 0.0123 | 3.0 | 2634 | 0.0383 | 0.9630 | 0.9679 | 0.9654 | 0.9923 |
| 0.0055 | 4.0 | 3512 | 0.0345 | 0.9633 | 0.9716 | 0.9674 | 0.9929 |
| 0.0034 | 5.0 | 4390 | 0.0364 | 0.9641 | 0.9716 | 0.9678 | 0.9931 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0
- Datasets 2.17.0
- Tokenizers 0.15.2