metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- nerd
metrics:
- precision
- recall
- f1
- accuracy
model_index:
- name: ner_nerd
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: nerd
type: nerd
args: nerd
metric:
name: Accuracy
type: accuracy
value: 0.9389165843185125
ner_nerd
This model is a fine-tuned version of bert-base-uncased on the nerd dataset. It achieves the following results on the evaluation set:
- Loss: 0.2553
- Precision: 0.7495
- Recall: 0.7859
- F1: 0.7672
- Accuracy: 0.9389
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 8
- 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2805 | 1.0 | 8235 | 0.1950 | 0.7355 | 0.7835 | 0.7587 | 0.9376 |
| 0.165 | 2.0 | 16470 | 0.1919 | 0.7528 | 0.7826 | 0.7674 | 0.9400 |
| 0.1214 | 3.0 | 24705 | 0.2124 | 0.7522 | 0.7859 | 0.7687 | 0.9395 |
| 0.0879 | 4.0 | 32940 | 0.2259 | 0.7483 | 0.7879 | 0.7675 | 0.9391 |
| 0.0652 | 5.0 | 41175 | 0.2550 | 0.7522 | 0.7874 | 0.7694 | 0.9390 |
Framework versions
- Transformers 4.9.1
- Pytorch 1.9.0+cu102
- Datasets 1.11.0
- Tokenizers 0.10.2