metadata
library_name: transformers
license: apache-2.0
base_model: google-bert/bert-base-cased
tags:
- generated_from_trainer
datasets:
- biobert_json
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-base-cased-finetuned-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: biobert_json
type: biobert_json
config: Biobert_json
split: validation
args: Biobert_json
metrics:
- name: Precision
type: precision
value: 0.941812865497076
- name: Recall
type: recall
value: 0.966852487135506
- name: F1
type: f1
value: 0.9541684299619129
- name: Accuracy
type: accuracy
value: 0.9754933560689555
bert-base-cased-finetuned-ner
This model is a fine-tuned version of google-bert/bert-base-cased on the biobert_json dataset. It achieves the following results on the evaluation set:
- Loss: 0.1119
- Precision: 0.9418
- Recall: 0.9669
- F1: 0.9542
- Accuracy: 0.9755
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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1824 | 1.0 | 1224 | 0.1170 | 0.9227 | 0.9563 | 0.9392 | 0.9686 |
| 0.1162 | 2.0 | 2448 | 0.1138 | 0.9277 | 0.9654 | 0.9462 | 0.9717 |
| 0.0756 | 3.0 | 3672 | 0.1025 | 0.9398 | 0.9685 | 0.9540 | 0.9751 |
| 0.051 | 4.0 | 4896 | 0.1076 | 0.9425 | 0.9691 | 0.9556 | 0.9759 |
| 0.0423 | 5.0 | 6120 | 0.1119 | 0.9418 | 0.9669 | 0.9542 | 0.9755 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1
- Datasets 3.1.0
- Tokenizers 0.20.3