metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- f1
- precision
- recall
model-index:
- name: mymodel
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: conll2003
type: conll2003
config: conll2003
split: validation
args: conll2003
metrics:
- name: F1
type: f1
value: 0.8445432910132625
- name: Precision
type: precision
value: 0.8428359044175097
- name: Recall
type: recall
value: 0.8473199717355161
mymodel
This model is a fine-tuned version of bert-base-uncased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0913
- F1: 0.8445
- Precision: 0.8428
- Recall: 0.8473
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: 32
- eval_batch_size: 32
- 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 | F1 | Precision | Recall |
---|---|---|---|---|---|---|
No log | 1.0 | 439 | 0.1035 | 0.8336 | 0.8340 | 0.8570 |
0.1502 | 2.0 | 878 | 0.0913 | 0.8445 | 0.8428 | 0.8473 |
Framework versions
- Transformers 4.37.0
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.1