BERT_Reciever_6

This model is a fine-tuned version of google-bert/bert-base-german-cased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1356
• Accuracy: 0.9561

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: 0.0001
• train_batch_size: 160
• eval_batch_size: 160
• seed: 2805
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	31	0.3889	0.9196
No log	2.0	62	0.2137	0.9342
No log	3.0	93	0.1763	0.9433
No log	4.0	124	0.1660	0.9433
No log	5.0	155	0.1592	0.9415
No log	6.0	186	0.1522	0.9470
No log	7.0	217	0.1454	0.9525
No log	8.0	248	0.1448	0.9506
No log	9.0	279	0.1388	0.9525
No log	10.0	310	0.1356	0.9561

Framework versions

• Transformers 4.44.0.dev0
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1