metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- caner
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-ner-v2.2
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: caner
type: caner
config: default
split: train[90%:91%]
args: default
metrics:
- name: Precision
type: precision
value: 0.8822751322751323
- name: Recall
type: recall
value: 0.8496815286624204
- name: F1
type: f1
value: 0.8656716417910448
- name: Accuracy
type: accuracy
value: 0.942741116751269
bert-finetuned-ner-v2.2
This model is a fine-tuned version of bert-base-multilingual-cased on the caner dataset. It achieves the following results on the evaluation set:
- Loss: 0.3595
- Precision: 0.8823
- Recall: 0.8497
- F1: 0.8657
- Accuracy: 0.9427
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2726 | 1.0 | 3228 | 0.4504 | 0.7390 | 0.7287 | 0.7338 | 0.9107 |
| 0.2057 | 2.0 | 6456 | 0.3679 | 0.8633 | 0.8446 | 0.8538 | 0.9385 |
| 0.1481 | 3.0 | 9684 | 0.3595 | 0.8823 | 0.8497 | 0.8657 | 0.9427 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2