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
config: conll2003
split: validation
args: conll2003
metrics:
- name: Precision
type: precision
value: 0.9264624571491762
- name: Recall
type: recall
value: 0.9372413021590782
- name: F1
type: f1
value: 0.9318207095984874
- name: Accuracy
type: accuracy
value: 0.9840024147298521
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: 0.0621
- Precision: 0.9265
- Recall: 0.9372
- F1: 0.9318
- Accuracy: 0.9840
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: 32
- eval_batch_size: 32
- 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 | 439 | 0.0751 | 0.8976 | 0.9103 | 0.9039 | 0.9789 |
| 0.219 | 2.0 | 878 | 0.0626 | 0.9130 | 0.9284 | 0.9206 | 0.9817 |
| 0.0558 | 3.0 | 1317 | 0.0623 | 0.9195 | 0.9332 | 0.9263 | 0.9826 |
| 0.0321 | 4.0 | 1756 | 0.0610 | 0.9251 | 0.9359 | 0.9305 | 0.9835 |
| 0.0228 | 5.0 | 2195 | 0.0621 | 0.9265 | 0.9372 | 0.9318 | 0.9840 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3