metadata
library_name: transformers
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-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: 0.9298884840454896
- name: Recall
type: recall
value: 0.9421635529701309
- name: F1
type: f1
value: 0.9359857746165815
- name: Accuracy
type: accuracy
value: 0.985035029469236
bert-base-uncased-finetuned-ner
This model is a fine-tuned version of bert-base-uncased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0574
- Precision: 0.9299
- Recall: 0.9422
- F1: 0.9360
- Accuracy: 0.9850
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 439 | 0.0743 | 0.8911 | 0.9132 | 0.9020 | 0.9793 |
| 0.1936 | 2.0 | 878 | 0.0598 | 0.9231 | 0.9367 | 0.9298 | 0.9841 |
| 0.0507 | 3.0 | 1317 | 0.0574 | 0.9299 | 0.9422 | 0.9360 | 0.9850 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.2.0
- Tokenizers 0.19.1