RoBERTa-legal-de-cased_German_legal_SQuAD_17

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 4.9667

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: 160
• eval_batch_size: 40
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 17

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	2	6.2537
No log	2.0	4	6.3434
No log	3.0	6	6.2256
No log	4.0	8	6.0253
No log	5.0	10	5.8198
No log	6.0	12	5.5768
No log	7.0	14	5.4665
No log	8.0	16	5.4053
No log	9.0	18	5.3656
No log	10.0	20	5.3181
No log	11.0	22	5.2573
No log	12.0	24	5.1785
No log	13.0	26	5.1147
No log	14.0	28	5.0536
No log	15.0	30	5.0101
No log	16.0	32	4.9799
No log	17.0	34	4.9667

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.2+cu121
• Datasets 2.14.7
• Tokenizers 0.15.0