857e2f748ab217fb3dc7d69df9da1bfa

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

• Loss: 2.6596
• Data Size: 0.125
• Epoch Runtime: 423.2466
• Accuracy: 0.0714
• F1 Macro: 0.0095
• Rouge1: 0.0714
• Rouge2: 0.0
• Rougel: 0.0715
• 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	2.7266	0	90.6602	0.0712	0.0150	0.0712	0.0	0.0711	0.0711
0.1664	1	17500	0.1060	0.0078	111.7174	0.9793	0.9792	0.9793	0.0	0.9793	0.9793
0.1765	2	35000	0.1435	0.0156	132.4780	0.9730	0.9731	0.9730	0.0	0.9730	0.9730
0.1234	3	52500	0.1585	0.0312	176.3683	0.9742	0.9742	0.9742	0.0	0.9741	0.9742
0.1596	4	70000	0.1384	0.0625	257.1087	0.9771	0.9771	0.9771	0.0	0.9771	0.9771
2.6658	5	87500	2.6596	0.125	423.2466	0.0714	0.0095	0.0714	0.0	0.0715	0.0715

Framework versions

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