metadata
license: mit
tags:
- generated_from_trainer
datasets:
- ncbi_disease
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bio_gpt_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: 0.826944757609921
- name: Recall
type: recall
value: 0.6462555066079295
- name: F1
type: f1
value: 0.7255192878338279
- name: Accuracy
type: accuracy
value: 0.9543616855854455
bio_gpt_ner
This model is a fine-tuned version of microsoft/biogpt on the ncbi_disease dataset. It achieves the following results on the evaluation set:
- Loss: 0.1558
- Precision: 0.8269
- Recall: 0.6463
- F1: 0.7255
- Accuracy: 0.9544
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: 1e-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 |
|---|---|---|---|---|---|---|---|
| 0.3027 | 1.0 | 680 | 0.1893 | 0.8417 | 0.4194 | 0.5598 | 0.9405 |
| 0.2037 | 2.0 | 1360 | 0.1562 | 0.8082 | 0.6388 | 0.7136 | 0.9517 |
| 0.1228 | 3.0 | 2040 | 0.1558 | 0.8269 | 0.6463 | 0.7255 | 0.9544 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3