metadata
license: mit
base_model: microsoft/biogpt
tags:
- generated_from_trainer
model-index:
- name: results
results: []
results
This model is a fine-tuned version of microsoft/biogpt on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1870
- Overall Precision: 0.4821
- Overall Recall: 0.5760
- Overall F1: 0.5249
- Overall Accuracy: 0.9506
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2295 | 1.0 | 1358 | 0.1735 | 0.3341 | 0.3926 | 0.3610 | 0.9483 |
| 0.1401 | 2.0 | 2716 | 0.1512 | 0.3905 | 0.5413 | 0.4537 | 0.9509 |
| 0.0948 | 3.0 | 4074 | 0.1627 | 0.4667 | 0.5070 | 0.4860 | 0.9578 |
| 0.0778 | 4.0 | 5432 | 0.1672 | 0.4831 | 0.5642 | 0.5205 | 0.9587 |
| 0.0614 | 5.0 | 6790 | 0.1755 | 0.4967 | 0.5781 | 0.5344 | 0.9594 |
Framework versions
- Transformers 4.39.3
- Pytorch 1.12.1+cu113
- Datasets 2.18.0
- Tokenizers 0.15.2