metadata
library_name: transformers
license: apache-2.0
base_model: albert-base-v2
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: albert-finetuned-ner-gbgb
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: conll2003
type: conll2003
config: conll2003
split: validation
args: conll2003
metrics:
- name: Precision
type: precision
value: 0.5032151387102701
- name: Recall
type: recall
value: 0.46095590710198586
- name: F1
type: f1
value: 0.4811594202898551
- name: Accuracy
type: accuracy
value: 0.8898127980220168
albert-finetuned-ner-gbgb
This model is a fine-tuned version of albert-base-v2 on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3371
- Precision: 0.5032
- Recall: 0.4610
- F1: 0.4812
- Accuracy: 0.8898
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.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 |
---|---|---|---|---|---|---|---|
0.5379 | 1.0 | 1756 | 0.4843 | 0.4079 | 0.2740 | 0.3278 | 0.8502 |
0.3491 | 2.0 | 3512 | 0.3726 | 0.4903 | 0.3837 | 0.4305 | 0.8778 |
0.26 | 3.0 | 5268 | 0.3371 | 0.5032 | 0.4610 | 0.4812 | 0.8898 |
Framework versions
- Transformers 4.46.1
- Pytorch 2.5.1+cpu
- Datasets 3.1.0
- Tokenizers 0.20.2