ec6aae4a895aac715b6da775be1cc914

This model is a fine-tuned version of FacebookAI/xlm-roberta-large-finetuned-conll02-dutch on the fancyzhx/dbpedia_14 dataset. It achieves the following results on the evaluation set:

• Loss: 0.4303
• Data Size: 0.125
• Epoch Runtime: 424.2550
• Accuracy: 0.9308
• F1 Macro: 0.9311
• Rouge1: 0.9308
• Rouge2: 0.0
• Rougel: 0.9309
• Rougelsum: 0.9309

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	2.6526	0	92.1554	0.0715	0.0165	0.0714	0.0	0.0714	0.0715
0.2163	1	17500	0.1629	0.0078	114.4919	0.9716	0.9715	0.9716	0.0	0.9716	0.9716
0.2342	2	35000	0.2625	0.0156	133.9843	0.9525	0.9528	0.9526	0.0	0.9526	0.9526
0.1759	3	52500	0.2320	0.0312	176.1696	0.9634	0.9635	0.9634	0.0	0.9634	0.9634
0.1897	4	70000	0.1666	0.0625	258.6336	0.9723	0.9724	0.9724	0.0	0.9724	0.9724
0.1989	5	87500	0.4303	0.125	424.2550	0.9308	0.9311	0.9308	0.0	0.9309	0.9309

Framework versions

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