metadata

library_name: transformers
base_model: dmis-lab/biobert-v1.1
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
model-index:
  - name: biobert-v1.1-finetuned-medmcqa-100-2024-11-30-T09-48-50
    results: []

biobert-v1.1-finetuned-medmcqa-100-2024-11-30-T09-48-50

This model is a fine-tuned version of dmis-lab/biobert-v1.1 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.3905
Accuracy: 0.39
F1: 0.3970

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: 0.000159
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 32
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	0.96	3	1.3834	0.36	0.3619
No log	1.92	6	1.3872	0.36	0.3609
No log	2.88	9	1.3905	0.39	0.3970

Framework versions

Transformers 4.46.2
Pytorch 2.5.1+cu121
Datasets 3.1.0
Tokenizers 0.20.3