You can deploy this model and start earning money today!

contemmcm/
520624318db90da6d6475b4419bf863a

Name: 520624318db90da6d6475b4419bf863a
Rating: 2.5 (5 reviews)

generated_from_trainer

google-bert/bert-base-german-dbmdz-uncased

finetune

mit

text-embeddings-inference

endpoints_compatible

Views

No views yet

520624318db90da6d6475b4419bf863a

This model is a fine-tuned version of google-bert/bert-base-german-dbmdz-uncased on the nyu-mll/glue [stsb] dataset. It achieves the following results on the evaluation set:

Loss: 0.6486
Data Size: 1.0
Epoch Runtime: 9.6808
Mse: 0.6491
Mae: 0.6157
R2: 0.7097

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: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 4
total_train_batch_size: 32
total_eval_batch_size: 32
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant
num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Data Size	Epoch Runtime	Mse	Mae	R2
No log	0	0	7.6353	0	1.2391	7.6366	2.3388	-2.4161
No log	1	179	2.5096	0.0078	1.6068	2.5105	1.3587	-0.1230
No log	2	358	3.3503	0.0156	1.5062	3.3509	1.4839	-0.4990
No log	3	537	2.2083	0.0312	1.7856	2.2090	1.2371	0.0118
No log	4	716	1.9341	0.0625	2.1140	1.9345	1.1504	0.1346
No log	5	895	1.0677	0.125	2.7296	1.0680	0.8512	0.5223
0.1019	6	1074	0.7717	0.25	3.6401	0.7720	0.6811	0.6547
0.7848	7	1253	0.6975	0.5	5.8578	0.6979	0.6590	0.6878
0.6653	8.0	1432	0.6445	1.0	10.1174	0.6448	0.6233	0.7116
0.471	9.0	1611	0.6505	1.0	10.0656	0.6508	0.6160	0.7089
0.3196	10.0	1790	0.7034	1.0	10.2678	0.7036	0.6336	0.6852
0.2395	11.0	1969	0.6751	1.0	10.4982	0.6755	0.6179	0.6978
0.2085	12.0	2148	0.6486	1.0	9.6808	0.6491	0.6157	0.7097

Framework versions

Transformers 4.57.0
Pytorch 2.8.0+cu128
Datasets 4.3.0
Tokenizers 0.22.1

contemmcm/520624318db90da6d6475b4419bf863a

520624318db90da6d6475b4419bf863a

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

contemmcm/
520624318db90da6d6475b4419bf863a