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

Loss: 0.0098
Accuracy: 1.0
F1-weighted: 1.0
F1-micro: 1.0
F1-macro: 1.0
Precision-weighted: 1.0
Precision-micro: 1.0
Precision-macro: 1.0
Recall-weighted: 1.0
Recall-micro: 1.0
Recall-macro: 1.0
Ballanced-accuracy: 1.0

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: 3e-05
train_batch_size: 4
eval_batch_size: 4
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: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1-weighted	F1-micro	F1-macro	Precision-weighted	Precision-micro	Precision-macro	Recall-weighted	Recall-micro	Recall-macro	Ballanced-accuracy
4.4003	1.0	16	3.4838	0.4355	0.2642	0.4355	0.0758	0.1896	0.4355	0.0544	0.4355	0.4355	0.125	0.125
3.1502	2.0	32	2.5253	0.4355	0.2642	0.4355	0.0758	0.1896	0.4355	0.0544	0.4355	0.4355	0.125	0.125
2.3795	3.0	48	2.0500	0.4355	0.2642	0.4355	0.0758	0.1896	0.4355	0.0544	0.4355	0.4355	0.125	0.125
2.1547	4.0	64	1.7851	0.4355	0.2642	0.4355	0.0758	0.1896	0.4355	0.0544	0.4355	0.4355	0.125	0.125
1.8134	5.0	80	1.6321	0.7097	0.6172	0.7097	0.2054	0.5621	0.7097	0.1903	0.7097	0.7097	0.2313	0.2313
1.8482	6.0	96	1.4719	0.6290	0.5473	0.6290	0.1814	0.5577	0.6290	0.1925	0.6290	0.6290	0.2	0.2
1.3304	7.0	112	1.2452	0.7581	0.6605	0.7581	0.2212	0.5940	0.7581	0.2014	0.7581	0.7581	0.25	0.25
1.539	8.0	128	1.0717	0.7419	0.6452	0.7419	0.2161	0.5763	0.7419	0.1949	0.7419	0.7419	0.2454	0.2454
1.0643	9.0	144	0.9223	0.7581	0.6582	0.7581	0.2198	0.5872	0.7581	0.1980	0.7581	0.7581	0.25	0.25
1.1112	10.0	160	0.9477	0.7097	0.6260	0.7097	0.2037	0.5769	0.7097	0.1846	0.7097	0.7097	0.2361	0.2361
0.9397	11.0	176	0.6894	0.8387	0.7894	0.8387	0.3081	0.7518	0.8387	0.3023	0.8387	0.8387	0.3194	0.3194
0.6631	12.0	192	0.7062	0.8871	0.8452	0.8871	0.3424	0.8121	0.8871	0.3217	0.8871	0.8871	0.3704	0.3704
0.8743	13.0	208	0.5852	0.8548	0.8091	0.8548	0.3199	0.7724	0.8548	0.3101	0.8548	0.8548	0.3333	0.3333
0.4968	14.0	224	0.4154	0.9032	0.8591	0.9032	0.3496	0.8215	0.9032	0.3292	0.9032	0.9032	0.375	0.375
0.4657	15.0	240	0.4169	0.8871	0.8477	0.8871	0.3401	0.8199	0.8871	0.3198	0.8871	0.8871	0.3704	0.3704
0.347	16.0	256	0.3225	0.9355	0.9091	0.9355	0.4773	0.8908	0.9355	0.4615	0.9355	0.9355	0.5	0.5
0.4442	17.0	272	0.2796	0.9355	0.9069	0.9355	0.4791	0.8838	0.9355	0.4628	0.9355	0.9355	0.5	0.5
0.1852	18.0	288	0.2287	0.9355	0.9069	0.9355	0.4791	0.8838	0.9355	0.4628	0.9355	0.9355	0.5	0.5
0.3406	19.0	304	0.1952	0.9355	0.9091	0.9355	0.4773	0.8908	0.9355	0.4615	0.9355	0.9355	0.5	0.5
0.1838	20.0	320	0.1644	0.9677	0.9532	0.9677	0.7375	0.9413	0.9677	0.7273	0.9677	0.9677	0.75	0.75
0.1904	21.0	336	0.1426	0.9839	0.9762	0.9839	0.8684	0.9694	0.9839	0.8625	0.9839	0.9839	0.875	0.875
0.2215	22.0	352	0.1822	0.9355	0.9091	0.9355	0.4773	0.8908	0.9355	0.4615	0.9355	0.9355	0.5	0.5
0.0896	23.0	368	0.1058	0.9839	0.9762	0.9839	0.8684	0.9694	0.9839	0.8625	0.9839	0.9839	0.875	0.875
0.1403	24.0	384	0.1058	0.9839	0.9762	0.9839	0.8684	0.9694	0.9839	0.8625	0.9839	0.9839	0.875	0.875
0.0728	25.0	400	0.0855	0.9839	0.9762	0.9839	0.8684	0.9694	0.9839	0.8625	0.9839	0.9839	0.875	0.875
0.1104	26.0	416	0.0728	0.9839	0.9762	0.9839	0.8684	0.9694	0.9839	0.8625	0.9839	0.9839	0.875	0.875
0.1289	27.0	432	0.0663	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0579	28.0	448	0.0587	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0833	29.0	464	0.0505	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.069	30.0	480	0.0443	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0596	31.0	496	0.0366	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0457	32.0	512	0.0337	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0303	33.0	528	0.0283	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.035	34.0	544	0.0262	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0509	35.0	560	0.0260	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0267	36.0	576	0.0215	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0137	37.0	592	0.0200	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0375	38.0	608	0.0174	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.016	39.0	624	0.0162	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0257	40.0	640	0.0156	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0207	41.0	656	0.0135	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0205	42.0	672	0.0124	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0194	43.0	688	0.0118	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0202	44.0	704	0.0113	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0177	45.0	720	0.0110	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.013	46.0	736	0.0106	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0122	47.0	752	0.0103	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0136	48.0	768	0.0100	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0097	49.0	784	0.0098	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
0.0163	50.0	800	0.0098	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0

Framework versions

Transformers 4.56.1
Pytorch 2.8.0+cu126
Datasets 4.0.0
Tokenizers 0.22.0

Luggi/distilbert-base-german-cased-finetuned-grasc

distilbert-base-german-cased-finetuned-grasc

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Luggi/
distilbert-base-german-cased-finetuned-grasc