classifier-de

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

• Loss: 0.3460
• Accuracy: 0.8811
• Precision: 0.5353
• Recall: 0.2849
• F1: 0.3719

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: 1.5e-05
• train_batch_size: 256
• eval_batch_size: 256
• 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
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.2897	0.2569	500	0.3390	0.8773	0.5747	0.0282	0.0537
0.2437	0.5139	1000	0.3320	0.8789	0.5347	0.1568	0.2425
0.2292	0.7708	1500	0.3317	0.8826	0.5760	0.1901	0.2859
0.1915	1.0277	2000	0.3557	0.8820	0.5583	0.2164	0.3119
0.2146	1.2847	2500	0.3390	0.8837	0.5757	0.2250	0.3236
0.2222	1.5416	3000	0.3298	0.8811	0.5358	0.2819	0.3694
0.1861	1.7986	3500	0.3338	0.8823	0.5501	0.2620	0.3549
0.1789	2.0555	4000	0.3460	0.8811	0.5353	0.2849	0.3719
0.1739	2.3124	4500	0.3614	0.8850	0.5863	0.2368	0.3373
0.1899	2.5694	5000	0.3487	0.8844	0.5716	0.2578	0.3554
0.1692	2.8263	5500	0.3484	0.8847	0.5728	0.2653	0.3626

Framework versions

• Transformers 4.51.3
• Pytorch 2.7.0+cu126
• Datasets 3.5.0
• Tokenizers 0.21.1