metadata
license: mit
base_model: emilyalsentzer/Bio_ClinicalBERT
tags:
- generated_from_trainer
datasets:
- sem_eval_2024_task_2
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: run1
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: sem_eval_2024_task_2
type: sem_eval_2024_task_2
config: sem_eval_2024_task_2_source
split: validation
args: sem_eval_2024_task_2_source
metrics:
- name: Accuracy
type: accuracy
value: 0.6
- name: Precision
type: precision
value: 0.6000400160064026
- name: Recall
type: recall
value: 0.6
- name: F1
type: f1
value: 0.5999599959995999
run1
This model is a fine-tuned version of emilyalsentzer/Bio_ClinicalBERT on the sem_eval_2024_task_2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.6634
- Accuracy: 0.6
- Precision: 0.6000
- Recall: 0.6
- F1: 0.6000
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: 64
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
---|---|---|---|---|---|---|---|
No log | 0.99 | 53 | 0.6935 | 0.515 | 0.5177 | 0.515 | 0.4958 |
0.7014 | 2.0 | 107 | 0.6895 | 0.535 | 0.5363 | 0.535 | 0.5308 |
0.7014 | 2.99 | 160 | 0.6894 | 0.52 | 0.5267 | 0.52 | 0.488 |
0.6961 | 4.0 | 214 | 0.6846 | 0.575 | 0.5842 | 0.575 | 0.5631 |
0.6961 | 4.99 | 267 | 0.6837 | 0.535 | 0.5931 | 0.535 | 0.4490 |
0.687 | 6.0 | 321 | 0.6762 | 0.585 | 0.5852 | 0.585 | 0.5847 |
0.687 | 6.99 | 374 | 0.6738 | 0.58 | 0.58 | 0.58 | 0.58 |
0.6707 | 8.0 | 428 | 0.6677 | 0.59 | 0.5900 | 0.59 | 0.5900 |
0.6707 | 8.99 | 481 | 0.6670 | 0.575 | 0.5767 | 0.575 | 0.5726 |
0.653 | 9.91 | 530 | 0.6634 | 0.6 | 0.6000 | 0.6 | 0.6000 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0