results

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

• Loss: 0.0114
• Accuracy: 1.0

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	5	0.6931	1.0
0.7541	2.0	10	0.5361	1.0
0.7541	3.0	15	0.3814	1.0
0.4427	4.0	20	0.2867	1.0
0.4427	5.0	25	0.2026	1.0
0.2459	6.0	30	0.1390	1.0
0.2459	7.0	35	0.0953	1.0
0.123	8.0	40	0.0653	1.0
0.123	9.0	45	0.0450	1.0
0.0595	10.0	50	0.0313	1.0
0.0595	11.0	55	0.0250	1.0
0.0331	12.0	60	0.0215	1.0
0.0331	13.0	65	0.0171	1.0
0.0242	14.0	70	0.0146	1.0
0.0242	15.0	75	0.0133	1.0
0.0191	16.0	80	0.0127	1.0
0.0191	17.0	85	0.0122	1.0
0.0162	18.0	90	0.0118	1.0
0.0162	19.0	95	0.0115	1.0
0.015	20.0	100	0.0114	1.0

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0