bea-german-3way-full – AI Model by khaled44 | AlphaNeural AI

You can deploy this model and start earning money today!

khaled44/
bea-german-3way-full

like

0

text-classification

generated_from_trainer

deepset/gbert-base

text-embeddings-inference

endpoints_compatible

Views

No views yet

bea-german-3way-full

This model is a fine-tuned version of deepset/gbert-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.7699
N Samples: 827.0
Accuracy: 0.7001
Precision Macro: 0.7079
Recall Macro: 0.7029
F1 Macro: 0.7035
Qwk: 0.6774

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: 8
eval_batch_size: 16
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	N Samples	Accuracy	Precision Macro	Recall Macro	F1 Macro	Qwk
0.9480	1.0	884	0.7906	827.0	0.6421	0.6411	0.6476	0.6425	0.5947
0.7067	2.0	1768	0.7200	827.0	0.6735	0.6949	0.6689	0.6751	0.6297
0.5056	3.0	2652	0.7699	827.0	0.7001	0.7079	0.7029	0.7035	0.6774

Framework versions

Transformers 5.1.0
Pytorch 2.10.0+cu128
Datasets 4.6.1
Tokenizers 0.22.2