metadata
license: mit
base_model: microsoft/biogpt
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: MLMA-Lab8-FinetunedBioGPT
results: []
MLMA-Lab8-FinetunedBioGPT
This model is a fine-tuned version of microsoft/biogpt on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1455
- Precision: 0.4466
- Recall: 0.5476
- F1: 0.4920
- Accuracy: 0.9579
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 |
|---|---|---|---|---|---|---|---|
| 0.3067 | 1.0 | 679 | 0.1668 | 0.3167 | 0.4358 | 0.3668 | 0.9470 |
| 0.1696 | 2.0 | 1358 | 0.1520 | 0.4094 | 0.5108 | 0.4545 | 0.9532 |
| 0.0952 | 3.0 | 2037 | 0.1455 | 0.4466 | 0.5476 | 0.4920 | 0.9579 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2