metadata
license: mit
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: roberta_large-unbalanced_simple-ner-conll2003_0908_v0
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: 0.9552732335537766
- name: Recall
type: recall
value: 0.9718484419263456
- name: F1
type: f1
value: 0.9634895559066174
- name: Accuracy
type: accuracy
value: 0.989226995491912
roberta_large-unbalanced_simple-ner-conll2003_0908_v0
This model is a fine-tuned version of roberta-large on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0881
- Precision: 0.9553
- Recall: 0.9718
- F1: 0.9635
- 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: 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 |
---|---|---|---|---|---|---|---|
0.07 | 1.0 | 878 | 0.0249 | 0.9616 | 0.9746 | 0.9681 | 0.9936 |
0.0176 | 2.0 | 1756 | 0.0241 | 0.9699 | 0.9818 | 0.9758 | 0.9948 |
Framework versions
- Transformers 4.21.3
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1