9af08bed8c59d6b91b2b478821930c23

This model is a fine-tuned version of FacebookAI/xlm-roberta-large-finetuned-conll03-german on the fancyzhx/dbpedia_14 dataset. It achieves the following results on the evaluation set:

• Loss: 2.7177
• Data Size: 0.25
• Epoch Runtime: 756.2599
• Accuracy: 0.0714
• F1 Macro: 0.0095
• Rouge1: 0.0715
• Rouge2: 0.0
• Rougel: 0.0714
• Rougelsum: 0.0715

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	Rouge2	Rougel	Rougelsum
No log	0	0	2.6238	0	92.3643	0.0784	0.0295	0.0784	0.0	0.0784	0.0784
0.2314	1	17500	0.1503	0.0078	113.7423	0.9688	0.9688	0.9688	0.0	0.9688	0.9687
0.1251	2	35000	0.0995	0.0156	133.8133	0.9831	0.9830	0.9831	0.0	0.9831	0.9831
0.1675	3	52500	0.1904	0.0312	175.6584	0.9669	0.9670	0.9669	0.0	0.9669	0.9668
0.2678	4	70000	0.1087	0.0625	257.7723	0.9804	0.9804	0.9805	0.0	0.9804	0.9804
2.6543	5	87500	2.6518	0.125	423.4285	0.0714	0.0095	0.0714	0.0	0.0715	0.0715
2.646	6	105000	2.7177	0.25	756.2599	0.0714	0.0095	0.0715	0.0	0.0714	0.0715

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 4.3.0
• Tokenizers 0.22.1