metadata

base_model: medicalai/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: 0.595
          - name: Precision
            type: precision
            value: 0.632109581421221
          - name: Recall
            type: recall
            value: 0.595
          - name: F1
            type: f1
            value: 0.5644107445349681

run1

This model is a fine-tuned version of medicalai/ClinicalBERT on the sem_eval_2024_task_2 dataset. It achieves the following results on the evaluation set:

Loss: 0.6989
Accuracy: 0.595
Precision: 0.6321
Recall: 0.595
F1: 0.5644

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: 20
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
No log	0.99	53	0.6932	0.5	0.5	0.5	0.4302
0.6952	2.0	107	0.6946	0.505	0.5059	0.505	0.4854
0.6952	2.99	160	0.6938	0.485	0.4127	0.485	0.3505
0.6953	4.0	214	0.6937	0.5	0.5	0.5	0.4389
0.6953	4.99	267	0.6961	0.5	0.25	0.5	0.3333
0.6937	6.0	321	0.6936	0.5	0.25	0.5	0.3333
0.6937	6.99	374	0.6908	0.495	0.4487	0.495	0.3479
0.6927	8.0	428	0.6804	0.545	0.5485	0.545	0.5366
0.6927	8.99	481	0.6888	0.525	0.5535	0.525	0.4520
0.6799	10.0	535	0.6657	0.615	0.6476	0.615	0.5925
0.6799	10.99	588	0.6600	0.625	0.6448	0.625	0.6117
0.6509	12.0	642	0.6598	0.595	0.6407	0.595	0.5592
0.6509	12.99	695	0.6598	0.605	0.6555	0.605	0.5701
0.6122	14.0	749	0.6643	0.59	0.6234	0.59	0.5603
0.6122	14.99	802	0.6754	0.605	0.6818	0.605	0.5584
0.5601	16.0	856	0.6788	0.605	0.6382	0.605	0.5798
0.5601	16.99	909	0.6864	0.59	0.6234	0.59	0.5603
0.5159	18.0	963	0.6967	0.6	0.6457	0.6	0.5660
0.5159	18.99	1016	0.7037	0.6	0.6507	0.6	0.5633
0.5117	19.81	1060	0.6989	0.595	0.6321	0.595	0.5644

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu121
Datasets 2.15.0
Tokenizers 0.15.0