gelectra-base-germanquad-finetuned-squad

This model is a fine-tuned version of deepset/gelectra-base-germanquad on the germanquad dataset. It achieves the following results on the evaluation set:

• Loss: 2.5011

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	180	1.7745
No log	2.0	360	1.8828
1.0639	3.0	540	1.9312
1.0639	4.0	720	2.1928
1.0639	5.0	900	2.2980
0.6008	6.0	1080	2.3243
0.6008	7.0	1260	2.3856
0.6008	8.0	1440	2.4762
0.4335	9.0	1620	2.4866
0.4335	10.0	1800	2.5011

Framework versions

• Transformers 4.27.2
• Pytorch 1.13.1+cu116
• Datasets 2.10.1
• Tokenizers 0.13.2