metadata
license: mit
tags:
- generated_from_trainer
datasets:
- ncbi_disease
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: mlma_nchan19_biogpt_gpt2
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: 0.4473684210526316
- name: Recall
type: recall
value: 0.5400254129606099
- name: F1
type: f1
value: 0.48934945308002303
- name: Accuracy
type: accuracy
value: 0.9576801898167957
mlma_nchan19_biogpt_gpt2
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: 0.1551
- Precision: 0.4474
- Recall: 0.5400
- F1: 0.4893
- Accuracy: 0.9577
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 |
---|---|---|---|---|---|---|---|
0.2855 | 1.0 | 679 | 0.1675 | 0.3396 | 0.4130 | 0.3727 | 0.9456 |
0.1699 | 2.0 | 1358 | 0.1480 | 0.4084 | 0.5044 | 0.4514 | 0.9543 |
0.0965 | 3.0 | 2037 | 0.1551 | 0.4474 | 0.5400 | 0.4893 | 0.9577 |
Framework versions
- Transformers 4.29.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3