metadata
license: mit
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: roberta-base-finetuned-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: conll2003
type: conll2003
config: conll2003
split: train
args: conll2003
metrics:
- name: Precision
type: precision
value: 0.9509868113366383
- name: Recall
type: recall
value: 0.9602380052890064
- name: F1
type: f1
value: 0.9555900183279289
- name: Accuracy
type: accuracy
value: 0.9892301555644196
roberta-base-finetuned-ner
This model is a fine-tuned version of roberta-base on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0497
- Precision: 0.9510
- Recall: 0.9602
- F1: 0.9556
- Accuracy: 0.9892
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: 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 |
|---|---|---|---|---|---|---|---|
| 0.2066 | 1.0 | 878 | 0.0699 | 0.9226 | 0.9294 | 0.9260 | 0.9828 |
| 0.0486 | 2.0 | 1756 | 0.0569 | 0.9465 | 0.9549 | 0.9507 | 0.9878 |
| 0.0254 | 3.0 | 2634 | 0.0497 | 0.9510 | 0.9602 | 0.9556 | 0.9892 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2