distilbert-base-uncased-survey-category-0.0.1

This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1004
• Accuracy: 0.9886

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: 16
• seed: 42
• 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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	232	0.1063	0.9773
No log	2.0	464	0.0811	0.9773
0.2551	3.0	696	0.0704	0.9830
0.2551	4.0	928	0.0903	0.9830
0.0423	5.0	1160	0.0949	0.9830
0.0423	6.0	1392	0.0890	0.9886
0.0268	7.0	1624	0.0916	0.9886
0.0268	8.0	1856	0.1001	0.9886
0.0246	9.0	2088	0.0965	0.9886
0.0246	10.0	2320	0.1002	0.9886
0.0156	11.0	2552	0.0785	0.9886
0.0156	12.0	2784	0.0904	0.9886
0.0157	13.0	3016	0.0825	0.9886
0.0157	14.0	3248	0.0999	0.9886
0.0157	15.0	3480	0.1004	0.9886
0.0137	16.0	3712	0.1020	0.9886
0.0137	17.0	3944	0.1010	0.9886
0.0152	18.0	4176	0.1002	0.9886
0.0152	19.0	4408	0.0999	0.9886
0.0114	20.0	4640	0.1004	0.9886

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0