<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
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: 0.1673
- Precision: 0.4622
- Recall: 0.5550
- F1: 0.5044
- Accuracy: 0.9518
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 |
---|---|---|---|---|---|---|---|
0.306 | 1.0 | 679 | 0.1701 | 0.3764 | 0.3938 | 0.3849 | 0.9442 |
0.1752 | 2.0 | 1358 | 0.1638 | 0.4538 | 0.5261 | 0.4873 | 0.9509 |
0.1072 | 3.0 | 2037 | 0.1673 | 0.4622 | 0.5550 | 0.5044 | 0.9518 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3