de-bert-base-german-cased-finetuned

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: 2.2858

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: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
3.3222	1.0	236	2.5917
2.7069	2.0	472	2.5008
2.5649	3.0	708	2.4164
2.4289	4.0	944	2.4542
2.3706	5.0	1180	2.3341
2.3106	6.0	1416	2.3479
2.2636	7.0	1652	2.2560
2.2039	8.0	1888	2.2804
2.1828	9.0	2124	2.2708
2.1414	10.0	2360	2.3298
2.1072	11.0	2596	2.2653
2.0809	12.0	2832	2.3277
2.0503	13.0	3068	2.2623
2.0231	14.0	3304	2.2312
2.039	15.0	3540	2.3196
1.9787	16.0	3776	2.2907
1.9726	17.0	4012	2.3083
1.9641	18.0	4248	2.3016
1.9501	19.0	4484	2.2497
1.948	20.0	4720	2.2211

Framework versions

• Transformers 4.29.2
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3