distilbert-base-uncased-survey-category-0.0.2

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: 0.1386
• Accuracy: 0.9837

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	238	0.0975	0.9756
No log	2.0	476	0.1126	0.9715
0.3352	3.0	714	0.1133	0.9675
0.3352	4.0	952	0.0966	0.9797
0.0635	5.0	1190	0.1036	0.9756
0.0635	6.0	1428	0.1052	0.9797
0.0467	7.0	1666	0.1370	0.9797
0.0467	8.0	1904	0.1377	0.9756
0.0362	9.0	2142	0.1259	0.9837
0.0362	10.0	2380	0.1365	0.9837
0.0313	11.0	2618	0.1306	0.9837
0.0313	12.0	2856	0.1414	0.9797
0.0288	13.0	3094	0.1483	0.9837
0.0288	14.0	3332	0.1309	0.9797
0.0282	15.0	3570	0.1356	0.9837
0.0282	16.0	3808	0.1410	0.9837
0.028	17.0	4046	0.1322	0.9837
0.028	18.0	4284	0.1415	0.9837
0.026	19.0	4522	0.1397	0.9837
0.026	20.0	4760	0.1386	0.9837

Framework versions

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