You can deploy this model and start earning money today!

contemmcm/
0086e7e7fadf28b805c08c3dfb810a1b

generated_from_trainer

google-bert/bert-base-german-dbmdz-cased

finetune

mit

text-embeddings-inference

endpoints_compatible

Views

No views yet

0086e7e7fadf28b805c08c3dfb810a1b

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

Loss: 0.5520
Data Size: 1.0
Epoch Runtime: 151.7883
Accuracy: 0.8110
F1 Macro: 0.8110
Rouge1: 0.8110
Rouge2: 0.0
Rougel: 0.8107
Rougelsum: 0.8108

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	Accuracy	F1 Macro	Rouge1	Rougel	Rougelsum
No log	0	0	0.7120	0	3.0674	0.4259	0.4104	0.4257	0.4257	0.4261
No log	1	3273	0.5718	0.0078	4.3360	0.6947	0.6807	0.6947	0.6945	0.6945
0.0099	2	6546	0.5590	0.0156	5.4979	0.7263	0.7107	0.7263	0.7256	0.7257
0.5314	3	9819	0.4411	0.0312	7.9152	0.7994	0.7984	0.7993	0.7991	0.7993
0.497	4	13092	0.4584	0.0625	12.6144	0.7847	0.7829	0.7849	0.7847	0.7847
0.4511	5	16365	0.4161	0.125	21.8029	0.8131	0.8128	0.8131	0.8132	0.8129
0.486	6	19638	0.4321	0.25	40.8369	0.8121	0.8119	0.8118	0.8121	0.8119
0.4261	7	22911	0.4021	0.5	77.8398	0.8226	0.8225	0.8228	0.8226	0.8226
0.4026	8.0	26184	0.3990	1.0	152.2742	0.8329	0.8327	0.8329	0.8327	0.8329
0.3163	9.0	29457	0.4247	1.0	151.3264	0.8278	0.8277	0.8279	0.8278	0.8278
0.2364	10.0	32730	0.4484	1.0	149.9410	0.8263	0.8259	0.8261	0.8264	0.8261
0.2177	11.0	36003	0.5622	1.0	152.4354	0.8217	0.8217	0.8217	0.8219	0.8217
0.1881	12.0	39276	0.5520	1.0	151.7883	0.8110	0.8110	0.8110	0.8107	0.8108

Framework versions

Transformers 4.57.0
Pytorch 2.8.0+cu128
Datasets 4.3.0
Tokenizers 0.22.1

contemmcm/0086e7e7fadf28b805c08c3dfb810a1b

0086e7e7fadf28b805c08c3dfb810a1b

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

contemmcm/
0086e7e7fadf28b805c08c3dfb810a1b