metadata
library_name: transformers
license: mit
base_model: dslim/bert-base-NER
tags:
- generated_from_trainer
datasets:
- wnut_17
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-wnut17-optimized
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: wnut_17
type: wnut_17
config: wnut_17
split: test
args: wnut_17
metrics:
- name: Precision
type: precision
value: 0.5794655414908579
- name: Recall
type: recall
value: 0.3818350324374421
- name: F1
type: f1
value: 0.46033519553072627
- name: Accuracy
type: accuracy
value: 0.9485338120885697
bert-wnut17-optimized
This model is a fine-tuned version of dslim/bert-base-NER on the wnut_17 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2901
- Precision: 0.5795
- Recall: 0.3818
- F1: 0.4603
- Accuracy: 0.9485
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: 2.631245451057452e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- 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 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 213 | 0.2365 | 0.5265 | 0.4235 | 0.4694 | 0.9478 |
| No log | 2.0 | 426 | 0.2692 | 0.5710 | 0.3689 | 0.4482 | 0.9480 |
| 0.2086 | 3.0 | 639 | 0.2901 | 0.5795 | 0.3818 | 0.4603 | 0.9485 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0