metadata
license: apache-2.0
base_model: distilbert-base-uncased
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: 0.9089708310401761
- name: Recall
type: recall
value: 0.9238169817652981
- name: F1
type: f1
value: 0.9163337771859743
- name: Accuracy
type: accuracy
value: 0.980618615660794
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: 0.0690
- Precision: 0.9090
- Recall: 0.9238
- F1: 0.9163
- Accuracy: 0.9806
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 | 0.0951 | 0.8731 | 0.8890 | 0.8810 | 0.9740 |
| No log | 2.0 | 440 | 0.0718 | 0.9029 | 0.9169 | 0.9099 | 0.9796 |
| 0.1848 | 3.0 | 660 | 0.0690 | 0.9090 | 0.9238 | 0.9163 | 0.9806 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.2+cu118
- Datasets 2.20.0
- Tokenizers 0.15.1