metadata

library_name: transformers
license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
model-index:
  - name: bert-practice-classifier
    results: []

bert-practice-classifier

This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.5696
Accuracy: 0.69
Auc: 0.714
Precision: 0.722

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: 0.0002
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Auc	Precision
0.6689	1.0	21	0.6720	0.571	0.676	0.72
0.6684	2.0	42	0.5909	0.69	0.719	0.69
0.6279	3.0	63	0.6067	0.714	0.711	0.718
0.619	4.0	84	0.5969	0.714	0.711	0.73
0.6055	5.0	105	0.5809	0.714	0.708	0.718
0.5821	6.0	126	0.5729	0.714	0.714	0.718
0.5762	7.0	147	0.5921	0.667	0.708	0.727
0.5604	8.0	168	0.5659	0.714	0.716	0.73
0.5705	9.0	189	0.5659	0.69	0.714	0.722
0.571	10.0	210	0.5696	0.69	0.714	0.722

Framework versions

Transformers 4.48.3
Pytorch 2.5.1+cu124
Datasets 3.3.2
Tokenizers 0.21.0