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: 0.1545
- Precision: 0.4435
- Recall: 0.5337
- F1: 0.4844
- Accuracy: 0.9563
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 |
---|---|---|---|---|---|---|---|
0.3269 | 1.0 | 679 | 0.1626 | 0.3330 | 0.3850 | 0.3571 | 0.9469 |
0.1703 | 2.0 | 1358 | 0.1466 | 0.3958 | 0.5070 | 0.4446 | 0.9544 |
0.0988 | 3.0 | 2037 | 0.1545 | 0.4435 | 0.5337 | 0.4844 | 0.9563 |
Framework versions
- Transformers 4.29.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 11
Dataset used to train nimeeshachan/mlma_nchan19_biogpt_gpt2
Evaluation results
- Precision on ncbi_diseasevalidation set self-reported0.444
- Recall on ncbi_diseasevalidation set self-reported0.534
- F1 on ncbi_diseasevalidation set self-reported0.484
- Accuracy on ncbi_diseasevalidation set self-reported0.956