metadata
license: mit
tags:
- generated_from_trainer
datasets:
- ncbi_disease
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: 2023MLMA_LAB9_task2
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: 0.48903878583473864
- name: Recall
type: recall
value: 0.5598455598455598
- name: F1
type: f1
value: 0.522052205220522
- name: Accuracy
type: accuracy
value: 0.9536349138434012
2023MLMA_LAB9_task2
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: 0.1611
- Precision: 0.4890
- Recall: 0.5598
- F1: 0.5221
- Accuracy: 0.9536
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 |
---|---|---|---|---|---|---|---|
0.3326 | 1.0 | 679 | 0.1749 | 0.4099 | 0.4546 | 0.4311 | 0.9449 |
0.175 | 2.0 | 1358 | 0.1616 | 0.4562 | 0.5125 | 0.4827 | 0.9511 |
0.1082 | 3.0 | 2037 | 0.1611 | 0.4890 | 0.5598 | 0.5221 | 0.9536 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3