metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-base-cased_conll2003-sm-all-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: conll2003
type: conll2003
args: conll2003
metrics:
- name: Precision
type: precision
value: 0.9487479131886477
- name: Recall
type: recall
value: 0.9564119824974756
- name: F1
type: f1
value: 0.9525645323499833
- name: Accuracy
type: accuracy
value: 0.9916085822203186
bert-base-cased_conll2003-sm-all-ner
This model is a fine-tuned version of bert-base-cased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0489
- Precision: 0.9487
- Recall: 0.9564
- F1: 0.9526
- Accuracy: 0.9916
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.052 | 1.0 | 3511 | 0.0510 | 0.9374 | 0.9456 | 0.9415 | 0.9898 |
| 0.0213 | 2.0 | 7022 | 0.0497 | 0.9484 | 0.9519 | 0.9501 | 0.9911 |
| 0.0099 | 3.0 | 10533 | 0.0489 | 0.9487 | 0.9564 | 0.9526 | 0.9916 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.2+cu102
- Datasets 2.3.2
- Tokenizers 0.12.1