68ea02186d872c15ce2c2d6139f79809

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

• Loss: 0.6668
• Data Size: 1.0
• Epoch Runtime: 110.4519
• Accuracy: 0.6130
• F1 Macro: 0.3801

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
No log	0	0	0.6634	0	7.8411	0.6130	0.3801
No log	1	650	0.0698	0.0078	8.9470	0.9913	0.9909
No log	2	1300	0.0174	0.0156	10.2748	0.9963	0.9961
No log	3	1950	0.0428	0.0312	14.1289	0.9954	0.9951
No log	4	2600	0.0317	0.0625	16.8512	0.9936	0.9933
0.0042	5	3250	0.0156	0.125	24.3123	0.9979	0.9978
0.0128	6	3900	0.0139	0.25	38.0073	0.9985	0.9984
0.0061	7	4550	0.0151	0.5	62.8121	0.9979	0.9978
0.6824	8.0	5200	0.6697	1.0	111.9600	0.6130	0.3801
0.6667	9.0	5850	0.6685	1.0	110.6394	0.6130	0.3801
0.6541	10.0	6500	0.6668	1.0	110.4519	0.6130	0.3801

Framework versions

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