finetuned_model

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: 0.0029
• Accuracy: 1.0
• F1: 1.0
• Precision: 1.0
• Recall: 1.0

Model description

It is a finetuned model for binary classification of description of city. It will result in either Pittsburgh or Shanghai.

Intended uses & limitations

This is for education and demonstration purposes.

Training and evaluation data

The data for finetuning the model comes from this HF dataset: cassieli226/cities-text-dataset

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.1213	1.0	80	0.0831	0.975	0.9750	0.9762	0.975
0.006	2.0	160	0.0034	1.0	1.0	1.0	1.0
0.002	3.0	240	0.0017	1.0	1.0	1.0	1.0
0.0016	4.0	320	0.0016	1.0	1.0	1.0	1.0
0.0014	5.0	400	0.0012	1.0	1.0	1.0	1.0

Framework versions

• Transformers 4.56.1
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.0