metadata
license: apache-2.0
base_model: google-bert/bert-large-uncased
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-large
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: 0.9432517889831918
- name: Recall
type: recall
value: 0.9538875799394143
- name: F1
type: f1
value: 0.9485398711404903
- name: Accuracy
type: accuracy
value: 0.9893561249940426
bert-finetuned-large
This model is a fine-tuned version of google-bert/bert-large-uncased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0517
- Precision: 0.9433
- Recall: 0.9539
- F1: 0.9485
- Accuracy: 0.9894
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 |
|---|---|---|---|---|---|---|---|
| 0.0639 | 1.0 | 1756 | 0.0610 | 0.9126 | 0.9349 | 0.9236 | 0.9851 |
| 0.0281 | 2.0 | 3512 | 0.0524 | 0.9420 | 0.9504 | 0.9461 | 0.9883 |
| 0.0148 | 3.0 | 5268 | 0.0517 | 0.9433 | 0.9539 | 0.9485 | 0.9894 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1