results

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

• Loss: 0.1061
• Accuracy: 0.9758

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: 32
• eval_batch_size: 20
• 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
• lr_scheduler_warmup_steps: 10
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.1722	0.1990	500	0.1000	0.9667
0.1132	0.3979	1000	0.1039	0.9664
0.0945	0.5969	1500	0.0931	0.97
0.0939	0.7959	2000	0.0927	0.9719
0.0877	0.9948	2500	0.0878	0.9708
0.0528	1.1938	3000	0.1142	0.9720
0.0516	1.3928	3500	0.0925	0.9749
0.0534	1.5917	4000	0.0879	0.9749
0.054	1.7907	4500	0.1013	0.9744
0.0555	1.9897	5000	0.0984	0.9755
0.0296	2.1886	5500	0.1101	0.9748
0.0254	2.3876	6000	0.1129	0.9752
0.0241	2.5865	6500	0.1108	0.9758
0.0211	2.7855	7000	0.1156	0.9760
0.0251	2.9845	7500	0.1061	0.9758

Framework versions

• Transformers 4.48.2
• Pytorch 2.5.1+cu124
• Tokenizers 0.21.0