metadata
library_name: transformers
license: mit
base_model: emilyalsentzer/Bio_ClinicalBERT
tags:
- generated_from_trainer
datasets:
- ncbi_disease
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: ncbi_disease
type: ncbi_disease
config: ncbi_disease
split: validation
args: ncbi_disease
metrics:
- name: Precision
type: precision
value: 0.8116805721096544
- name: Recall
type: recall
value: 0.8653113087674714
- name: F1
type: f1
value: 0.8376383763837638
- name: Accuracy
type: accuracy
value: 0.9840282291763395
bert-finetuned-ner
This model is a fine-tuned version of emilyalsentzer/Bio_ClinicalBERT on the ncbi_disease dataset. It achieves the following results on the evaluation set:
- Loss: 0.0621
- Precision: 0.8117
- Recall: 0.8653
- F1: 0.8376
- Accuracy: 0.9840
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 |
|---|---|---|---|---|---|---|---|
| 0.1181 | 1.0 | 680 | 0.0523 | 0.7339 | 0.8272 | 0.7778 | 0.9824 |
| 0.0386 | 2.0 | 1360 | 0.0554 | 0.8112 | 0.8463 | 0.8284 | 0.9838 |
| 0.0145 | 3.0 | 2040 | 0.0621 | 0.8117 | 0.8653 | 0.8376 | 0.9840 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1