metadata
library_name: transformers
license: apache-2.0
base_model: distilbert/distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: ner_model_2
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: conll2003
type: conll2003
config: conll2003
split: test
args: conll2003
metrics:
- name: Precision
type: precision
value: 0.8894709271870089
- name: Recall
type: recall
value: 0.9019121813031161
- name: F1
type: f1
value: 0.8956483516483517
- name: Accuracy
type: accuracy
value: 0.9791105846882739
ner_model_2
This model is a fine-tuned version of distilbert/distilbert-base-uncased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1156
- Precision: 0.8895
- Recall: 0.9019
- F1: 0.8956
- Accuracy: 0.9791
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.207 | 1.0 | 878 | 0.1029 | 0.8715 | 0.8862 | 0.8788 | 0.9756 |
| 0.0398 | 2.0 | 1756 | 0.1129 | 0.8753 | 0.9019 | 0.8884 | 0.9777 |
| 0.0223 | 3.0 | 2634 | 0.1156 | 0.8895 | 0.9019 | 0.8956 | 0.9791 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3