metadata
library_name: transformers
license: mit
base_model: microsoft/biogpt
tags:
- generated_from_trainer
datasets:
- ncbi_disease
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: biogpt-gpt2class-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: 0.42814070351758793
- name: Recall
type: recall
value: 0.5447570332480819
- name: F1
type: f1
value: 0.47945976364659537
- name: Accuracy
type: accuracy
value: 0.953528887448343
biogpt-gpt2class-finetuned-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: 0.1597
- Precision: 0.4281
- Recall: 0.5448
- F1: 0.4795
- Accuracy: 0.9535
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.3371 | 1.0 | 679 | 0.1850 | 0.3182 | 0.4399 | 0.3693 | 0.9424 |
| 0.1771 | 2.0 | 1358 | 0.1583 | 0.4254 | 0.4962 | 0.4581 | 0.9525 |
| 0.1085 | 3.0 | 2037 | 0.1597 | 0.4281 | 0.5448 | 0.4795 | 0.9535 |
Framework versions
- Transformers 4.51.2
- Pytorch 2.1.0+cu121
- Datasets 3.5.0
- Tokenizers 0.21.1