metadata
license: mit
base_model: microsoft/biogpt
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: test-trainer
results: []
test-trainer
This model is a fine-tuned version of microsoft/biogpt on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1628
- Precision: 0.5127
- Recall: 0.5849
- F1: 0.5464
- Accuracy: 0.9564
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: 5e-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: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.3056 | 1.0 | 680 | 0.1724 | 0.4135 | 0.5029 | 0.4538 | 0.9478 |
| 0.1401 | 2.0 | 1360 | 0.1542 | 0.4719 | 0.5521 | 0.5089 | 0.9538 |
| 0.0738 | 3.0 | 2040 | 0.1628 | 0.5127 | 0.5849 | 0.5464 | 0.9564 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2