metadata
license: mit
tags:
- generated_from_trainer
datasets:
- ncbi_disease
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: finetuned
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: 0.8246402877697842
- name: Recall
type: recall
value: 0.8725023786869648
- name: F1
type: f1
value: 0.8478964401294499
- name: Accuracy
type: accuracy
value: 0.9838910991496996
finetuned
This model is a fine-tuned version of microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext on the ncbi_disease dataset. It achieves the following results on the evaluation set:
- Loss: 0.0568
- Precision: 0.8246
- Recall: 0.8725
- F1: 0.8479
- Accuracy: 0.9839
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: 32
- eval_batch_size: 32
- 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 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 170 | 0.0582 | 0.7621 | 0.8506 | 0.8040 | 0.9816 |
| No log | 2.0 | 340 | 0.0588 | 0.8074 | 0.8535 | 0.8298 | 0.9828 |
| 0.0712 | 3.0 | 510 | 0.0568 | 0.8246 | 0.8725 | 0.8479 | 0.9839 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.2