kaelte

This model is a fine-tuned version of svalabs/gbert-large-zeroshot-nli on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1126
• F1: 0.9887

Label-Übersetzung

• 0 Freie_Kühlung
• 1 Kälteanlage_Allgemein
• 2 Kältemaschine
• 3 Kältespeicher
• 4 Rückkühlwerk

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: 5e-05
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• 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	F1
No log	0.98	46	0.3264	0.9074
No log	1.98	92	0.1266	0.9590
No log	2.98	138	0.0603	0.9887
No log	3.98	184	0.1000	0.9887
No log	4.98	230	0.1075	0.9887
No log	5.98	276	0.1091	0.9887
No log	6.98	322	0.1109	0.9887
No log	7.98	368	0.1119	0.9887
No log	8.98	414	0.1124	0.9887
No log	9.98	460	0.1126	0.9887

Framework versions

• Transformers 4.22.2
• Pytorch 1.12.1+cu113
• Datasets 2.5.1
• Tokenizers 0.12.1