dccuchile_bert-base-spanish-wwm-cased_ep10_lr1e-05_batchpergpu16_gpu1_weighted

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

• Loss: 0.2989
• F1 Micro: 0.6953
• F1 Macro: 0.3893
• Exact Match: 0.6723

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: 1e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	F1 Micro	F1 Macro	Exact Match
0.3646	0.9924	131	0.4025	0.6082	0.1974	0.6307
0.3934	1.9848	262	0.3667	0.6261	0.2793	0.6420
0.3214	2.9773	393	0.3171	0.6577	0.3390	0.6572
0.2660	3.9697	524	0.2899	0.6656	0.3862	0.6686
0.1906	4.9621	655	0.2866	0.6783	0.3740	0.6705
0.1556	5.9545	786	0.2913	0.6907	0.3917	0.6345
0.1517	6.9470	917	0.2880	0.7009	0.4060	0.6913
0.1313	7.9394	1048	0.3007	0.6867	0.3850	0.6780
0.1124	8.9318	1179	0.2989	0.6953	0.3893	0.6723

Framework versions

• Transformers 5.6.2
• Pytorch 2.11.0+cu130
• Datasets 4.8.4
• Tokenizers 0.22.2