metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: distilbert-base-uncased-finetuned-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: conll2003
type: conll2003
args: conll2003
metrics:
- name: Precision
type: precision
value: 0.8982049036777583
- name: Recall
type: recall
value: 0.9179997762613268
- name: F1
type: f1
value: 0.9079944674965422
- name: Accuracy
type: accuracy
value: 0.979427137115351
distilbert-base-uncased-finetuned-ner
This model is a fine-tuned version of distilbert-base-uncased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0729
- Precision: 0.8982
- Recall: 0.9180
- F1: 0.9080
- Accuracy: 0.9794
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 220 | 0.1036 | 0.8607 | 0.8797 | 0.8701 | 0.9727 |
| No log | 2.0 | 440 | 0.0762 | 0.8912 | 0.9131 | 0.9020 | 0.9783 |
| 0.2005 | 3.0 | 660 | 0.0729 | 0.8982 | 0.9180 | 0.9080 | 0.9794 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0a0+3fd9dcf
- Datasets 2.1.0
- Tokenizers 0.12.1