bert-base-german-cased-germeval2024

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

• Loss: 2.9423
• Accuracy: 0.4952
• F1: 0.5454

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.9231	0.9831	58	1.3925	0.4351	0.5393
0.4828	1.9661	116	1.9050	0.5	0.5349
0.1764	2.9492	174	2.3104	0.5481	0.5584
0.0737	3.9322	232	2.6077	0.5312	0.5683
0.0297	4.9153	290	2.9423	0.4952	0.5454

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1