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: 2.4453
Accuracy: 0.284
Precision: 0.1812
Recall: 0.284
F1: 0.2132

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
2.9605	1.0	250	2.9477	0.221	0.0488	0.221	0.0800
2.5952	2.0	500	2.5658	0.341	0.1400	0.341	0.1958
2.5191	3.0	750	2.4897	0.355	0.1531	0.355	0.2046
2.414	4.0	1000	2.5463	0.323	0.1913	0.323	0.1902
2.2946	5.0	1250	2.4793	0.347	0.1461	0.347	0.2023
2.4065	6.0	1500	2.4471	0.349	0.1684	0.349	0.2198
2.3267	7.0	1750	2.4408	0.344	0.1672	0.344	0.2193
2.3173	8.0	2000	2.4214	0.358	0.1748	0.358	0.2286
2.1692	9.0	2250	2.4358	0.339	0.1638	0.339	0.2147
2.029	10.0	2500	2.4074	0.338	0.1658	0.338	0.2178
2.125	11.0	2750	2.3605	0.334	0.1756	0.334	0.2239
1.9541	12.0	3000	2.3997	0.326	0.1623	0.326	0.2123
2.1619	13.0	3250	2.4450	0.321	0.1765	0.321	0.2127
2.101	14.0	3500	2.4453	0.284	0.1812	0.284	0.2132

Framework versions

Transformers 4.39.3
Pytorch 2.1.2
Datasets 2.18.0
Tokenizers 0.15.2