metadata
license: mit
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
base_model: microsoft/deberta-base
model-index:
- name: deberta-base-finetuned-ner
results:
- task:
type: token-classification
name: Token Classification
dataset:
name: conll2003
type: conll2003
args: conll2003
metrics:
- type: precision
value: 0.9563020492186769
name: Precision
- type: recall
value: 0.9652436720816018
name: Recall
- type: f1
value: 0.9607520564042303
name: F1
- type: accuracy
value: 0.9899205302077261
name: Accuracy
deberta-base-finetuned-ner
This model is a fine-tuned version of microsoft/deberta-base on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0501
- Precision: 0.9563
- Recall: 0.9652
- F1: 0.9608
- Accuracy: 0.9899
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: 5e-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 |
|---|---|---|---|---|---|---|---|
| 0.1419 | 1.0 | 878 | 0.0628 | 0.9290 | 0.9288 | 0.9289 | 0.9835 |
| 0.0379 | 2.0 | 1756 | 0.0466 | 0.9456 | 0.9567 | 0.9511 | 0.9878 |
| 0.0176 | 3.0 | 2634 | 0.0473 | 0.9539 | 0.9575 | 0.9557 | 0.9890 |
| 0.0098 | 4.0 | 3512 | 0.0468 | 0.9570 | 0.9635 | 0.9603 | 0.9896 |
| 0.0043 | 5.0 | 4390 | 0.0501 | 0.9563 | 0.9652 | 0.9608 | 0.9899 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.9.0+cu111
- Datasets 1.12.1
- Tokenizers 0.10.3