finetuned-die-verantwortung-fur-das-eigene-lernen-und-handeln-ubernehmen

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: 0.3849
• Accuracy: 0.8398
• F1: 0.8305

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.3945	1.0	1365	0.3718	0.8407	0.8255
0.2922	2.0	2730	0.3849	0.8398	0.8305

Framework versions

• Transformers 4.25.1
• Pytorch 1.12.1+cu113
• Datasets 2.3.2
• Tokenizers 0.13.2