metadata
license: mit
base_model: microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: BiomedNLP-CIViC-evidence-level-finetuned
results: []
BiomedNLP-CIViC-evidence-level-finetuned
This model is a fine-tuned version of microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.5745
- F1: 0.8312
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: 16
- eval_batch_size: 16
- 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 | F1 |
|---|---|---|---|---|
| No log | 1.0 | 73 | 1.5464 | 0.8260 |
| No log | 2.0 | 146 | 1.7265 | 0.7844 |
| No log | 3.0 | 219 | 1.6166 | 0.8260 |
| No log | 4.0 | 292 | 1.5619 | 0.8260 |
| No log | 5.0 | 365 | 1.5745 | 0.8312 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2
- Datasets 2.21.0
- Tokenizers 0.15.0