xlm-roberta-base-2-contract-sections-classification-v4-10

This model is a fine-tuned version of FacebookAI/xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.2496
Accuracy Evaluate: 0.939
Precision Evaluate: 0.9389
Recall Evaluate: 0.9535
F1 Evaluate: 0.9432
Accuracy Sklearn: 0.939
Precision Sklearn: 0.9456
Recall Sklearn: 0.939
F1 Sklearn: 0.9398
Acuracia Rotulo Objeto: 0.9814
Acuracia Rotulo Obrigacoes: 0.7929
Acuracia Rotulo Valor: 0.9484
Acuracia Rotulo Vigencia: 0.9790
Acuracia Rotulo Rescisao: 0.9501
Acuracia Rotulo Foro: 0.9385
Acuracia Rotulo Reajuste: 0.9680
Acuracia Rotulo Fiscalizacao: 0.9243
Acuracia Rotulo Publicacao: 1.0
Acuracia Rotulo Pagamento: 0.9819
Acuracia Rotulo Casos Omissos: 0.9360
Acuracia Rotulo Sancoes: 1.0
Acuracia Rotulo Dotacao Orcamentaria: 0.9945

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-06
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	Accuracy Evaluate	Precision Evaluate	Recall Evaluate	F1 Evaluate	Accuracy Sklearn	Precision Sklearn	Recall Sklearn	F1 Sklearn	Acuracia Rotulo Objeto	Acuracia Rotulo Obrigacoes	Acuracia Rotulo Valor	Acuracia Rotulo Vigencia	Acuracia Rotulo Rescisao	Acuracia Rotulo Foro	Acuracia Rotulo Reajuste	Acuracia Rotulo Fiscalizacao	Acuracia Rotulo Publicacao	Acuracia Rotulo Pagamento	Acuracia Rotulo Casos Omissos	Acuracia Rotulo Sancoes	Acuracia Rotulo Dotacao Orcamentaria
1.8607	1.0	1000	1.4840	0.7468	0.8061	0.7434	0.7394	0.7468	0.7930	0.7468	0.7408	0.9628	0.7694	0.4699	0.5354	0.7618	0.9231	0.8754	0.7066	0.8424	0.8261	0.8571	0.9358	0.1978
0.9297	2.0	2000	0.6945	0.8858	0.9003	0.9002	0.8962	0.8858	0.8941	0.8858	0.8851	0.9587	0.7542	0.6762	0.9370	0.9418	0.9231	0.9609	0.9211	0.9261	0.9058	0.8768	0.9541	0.9670
0.5383	3.0	3000	0.3917	0.9225	0.9292	0.9356	0.9301	0.9225	0.9284	0.9225	0.9228	0.9711	0.7795	0.8625	0.9816	0.9612	0.9385	0.9715	0.9274	0.9951	0.9275	0.8966	0.9725	0.9780
0.343	4.0	4000	0.3102	0.9307	0.9375	0.9448	0.9389	0.9307	0.9370	0.9307	0.9311	0.9793	0.7744	0.9112	0.9764	0.9584	0.9385	0.9609	0.9306	0.9951	0.9819	0.9163	0.9817	0.9780
0.228	5.0	5000	0.2754	0.9333	0.9354	0.9472	0.9383	0.9333	0.9403	0.9333	0.9340	0.9793	0.7795	0.9484	0.9790	0.9612	0.9385	0.9680	0.9243	1.0	0.9312	0.9360	0.9908	0.9780
0.1585	6.0	6000	0.2710	0.9353	0.9361	0.9504	0.9400	0.9353	0.9428	0.9353	0.9360	0.9793	0.7778	0.9427	0.9790	0.9529	0.9385	0.9715	0.9306	1.0	0.9638	0.9360	1.0	0.9835
0.1407	7.0	7000	0.2619	0.9363	0.9375	0.9508	0.9411	0.9363	0.9432	0.9363	0.9370	0.9814	0.7828	0.9484	0.9790	0.9557	0.9385	0.9680	0.9274	1.0	0.9601	0.9360	1.0	0.9835
0.1155	8.0	8000	0.2612	0.937	0.9372	0.9524	0.9414	0.937	0.9447	0.937	0.9379	0.9814	0.7811	0.9484	0.9816	0.9418	0.9385	0.9680	0.9274	1.0	0.9819	0.9360	1.0	0.9945
0.1055	9.0	9000	0.2563	0.9385	0.9388	0.9533	0.9429	0.9385	0.9456	0.9385	0.9393	0.9814	0.7879	0.9513	0.9790	0.9474	0.9385	0.9680	0.9274	1.0	0.9819	0.9360	1.0	0.9945
0.1025	10.0	10000	0.2496	0.939	0.9389	0.9535	0.9432	0.939	0.9456	0.939	0.9398	0.9814	0.7929	0.9484	0.9790	0.9501	0.9385	0.9680	0.9243	1.0	0.9819	0.9360	1.0	0.9945

Framework versions

Transformers 4.48.3
Pytorch 2.6.0+cu124
Datasets 3.3.0
Tokenizers 0.21.0

marcelovidigal/xlm-roberta-base-2-contract-sections-classification-v4-10

xlm-roberta-base-2-contract-sections-classification-v4-10

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Seed this model