c8a5ad3882c1a50da40f13374735261b

This model is a fine-tuned version of distilbert/distilbert-base-german-cased on the contemmcm/clickbait dataset. It achieves the following results on the evaluation set:

• Loss: 0.0073
• Data Size: 0.5
• Epoch Runtime: 10.9953
• Accuracy: 0.9988
• F1 Macro: 0.9988

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: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 32
• total_eval_batch_size: 32
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: constant
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Data Size	Epoch Runtime	Accuracy	F1 Macro
No log	0	0	0.6635	0	1.9498	0.8084	0.8077
No log	1	650	0.1981	0.0078	2.3967	0.9869	0.9861
No log	2	1300	0.0157	0.0156	2.2915	0.9958	0.9955
No log	3	1950	0.0058	0.0312	2.6622	0.9986	0.9986
No log	4	2600	0.0099	0.0625	3.2855	0.9973	0.9972
0.0016	5	3250	0.0094	0.125	4.4837	0.9975	0.9974
0.0053	6	3900	0.0062	0.25	6.7955	0.9990	0.9990
0.0016	7	4550	0.0073	0.5	10.9953	0.9988	0.9988

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 4.3.0
• Tokenizers 0.22.1