metadata
license: apache-2.0
base_model: dslim/distilbert-NER
tags:
- generated_from_trainer
datasets:
- conll2012_ontonotesv5
metrics:
- accuracy
- f1
model-index:
- name: distilbert-NER-finetuned
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: conll2012_ontonotesv5
type: conll2012_ontonotesv5
config: english_v4
split: validation
args: english_v4
metrics:
- name: Accuracy
type: accuracy
value: 0.8738244514106583
- name: F1
type: f1
value: 0.4990403071017275
distilbert-NER-finetuned
This model is a fine-tuned version of dslim/distilbert-NER on the conll2012_ontonotesv5 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4666
- Accuracy: 0.8738
- F1: 0.4990
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: 5e-05
- train_batch_size: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.8992 | 1.0 | 61 | 0.6227 | 0.8404 | 0.4295 |
| 0.5484 | 2.0 | 122 | 0.5143 | 0.8631 | 0.4784 |
| 0.4243 | 3.0 | 183 | 0.4757 | 0.8710 | 0.4985 |
| 0.3599 | 4.0 | 244 | 0.4666 | 0.8738 | 0.4990 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.4.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1