metadata
license: mit
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: roberta_large-ner-conll2003_0818_v1
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: 0.8993300120254252
- name: Recall
type: recall
value: 0.9268767705382436
- name: F1
type: f1
value: 0.9128956317028512
- name: Accuracy
type: accuracy
value: 0.978371121718377
roberta_large-ner-conll2003_0818_v1
This model is a fine-tuned version of roberta-large on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1481
- Precision: 0.8993
- Recall: 0.9269
- F1: 0.9129
- Accuracy: 0.9784
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: 1e-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: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2033 | 1.0 | 878 | 0.0472 | 0.9277 | 0.9551 | 0.9412 | 0.9887 |
| 0.044 | 2.0 | 1756 | 0.0428 | 0.9365 | 0.9610 | 0.9486 | 0.9895 |
Framework versions
- Transformers 4.21.1
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1