metadata
license: mit
base_model: microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: NHS-BiomedNLP-BiomedBERT-hypop
results: []
NHS-BiomedNLP-BiomedBERT-hypop
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: 0.4277
- Accuracy: 0.8293
- Precision: 0.8301
- Recall: 0.8375
- F1: 0.8285
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: 3e-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: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.0264 | 1.0 | 397 | 0.4689 | 0.7950 | 0.7974 | 0.8017 | 0.7946 |
| 0.5258 | 2.0 | 794 | 0.5543 | 0.7779 | 0.7745 | 0.7743 | 0.7744 |
| 3.0689 | 3.0 | 1191 | 0.6701 | 0.8050 | 0.8068 | 0.7957 | 0.7990 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.2+cpu
- Datasets 2.18.0
- Tokenizers 0.15.2