metadata
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_trainer
datasets:
- linnaeus
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: linnaeus
type: linnaeus
config: linnaeus
split: validation
args: linnaeus
metrics:
- name: Precision
type: precision
value: 0.9174008810572687
- name: Recall
type: recall
value: 0.9083969465648855
- name: F1
type: f1
value: 0.9128767123287672
- name: Accuracy
type: accuracy
value: 0.9982350038060345
bert-finetuned-ner
This model is a fine-tuned version of bert-base-cased on the linnaeus dataset. It achieves the following results on the evaluation set:
- Loss: 0.0095
- Precision: 0.9174
- Recall: 0.9084
- F1: 0.9129
- Accuracy: 0.9982
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 |
|---|---|---|---|---|---|---|---|
| 0.0094 | 1.0 | 1492 | 0.0129 | 0.8343 | 0.9280 | 0.8787 | 0.9968 |
| 0.002 | 2.0 | 2984 | 0.0090 | 0.8928 | 0.9084 | 0.9005 | 0.9979 |
| 0.0009 | 3.0 | 4476 | 0.0095 | 0.9174 | 0.9084 | 0.9129 | 0.9982 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.5
- Tokenizers 0.14.0