metadata
base_model: medicalai/ClinicalBERT
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: ClinicalBERT-medical-text-classification
results: []
ClinicalBERT-medical-text-classification
This model is a fine-tuned version of medicalai/ClinicalBERT on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.8610
- Accuracy: 0.235
- Precision: 0.2005
- Recall: 0.235
- F1: 0.2115
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 2.6094 | 1.0 | 250 | 2.4951 | 0.353 | 0.1617 | 0.353 | 0.2001 |
| 2.2177 | 2.0 | 500 | 1.9842 | 0.359 | 0.2967 | 0.359 | 0.2843 |
| 1.8458 | 3.0 | 750 | 1.8258 | 0.345 | 0.2843 | 0.345 | 0.2893 |
| 1.6992 | 4.0 | 1000 | 1.8139 | 0.302 | 0.2616 | 0.302 | 0.2729 |
| 1.4773 | 5.0 | 1250 | 1.8341 | 0.265 | 0.2458 | 0.265 | 0.2482 |
| 1.3138 | 6.0 | 1500 | 1.8610 | 0.235 | 0.2005 | 0.235 | 0.2115 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2