metadata
library_name: transformers
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
datasets:
- biobert_json
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-base-uncased-biobert
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: 0.9400370317618573
- name: Recall
type: recall
value: 0.970873786407767
- name: F1
type: f1
value: 0.9552065996092336
- name: Accuracy
type: accuracy
value: 0.9768401312705111
bert-base-uncased-biobert
This model is a fine-tuned version of bert-base-uncased on the biobert_json dataset. It achieves the following results on the evaluation set:
- Loss: 0.0999
- Precision: 0.9400
- Recall: 0.9709
- F1: 0.9552
- Accuracy: 0.9768
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: 16
- eval_batch_size: 16
- 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 |
|---|---|---|---|---|---|---|---|
| 0.4627 | 1.0 | 612 | 0.1159 | 0.9268 | 0.9554 | 0.9409 | 0.9701 |
| 0.1413 | 2.0 | 1224 | 0.1089 | 0.9274 | 0.9722 | 0.9493 | 0.9734 |
| 0.0953 | 3.0 | 1836 | 0.0993 | 0.9400 | 0.9684 | 0.9540 | 0.9767 |
| 0.0746 | 4.0 | 2448 | 0.0983 | 0.9399 | 0.9714 | 0.9554 | 0.9768 |
| 0.054 | 5.0 | 3060 | 0.0999 | 0.9400 | 0.9709 | 0.9552 | 0.9768 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3