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

Loss: 0.2129
Accuracy Evaluate: 0.95
Precision Evaluate: 0.9426
Recall Evaluate: 0.9573
F1 Evaluate: 0.9484
Accuracy Sklearn: 0.95
Precision Sklearn: 0.9524
Recall Sklearn: 0.95
F1 Sklearn: 0.9503
Acuracia Rotulo Objeto: 0.9711
Acuracia Rotulo Obrigacoes: 0.8956
Acuracia Rotulo Valor: 0.9513
Acuracia Rotulo Vigencia: 0.9843
Acuracia Rotulo Rescisao: 0.9086
Acuracia Rotulo Foro: 1.0
Acuracia Rotulo Reajuste: 0.9964
Acuracia Rotulo Fiscalizacao: 0.9180
Acuracia Rotulo Publicacao: 1.0
Acuracia Rotulo Pagamento: 0.9167
Acuracia Rotulo Casos Omissos: 0.9212
Acuracia Rotulo Sancoes: 0.9817
Acuracia Rotulo Dotacao Orcamentaria: 1.0

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
1.9189	1.0	1000	1.7267	0.668	0.7970	0.6344	0.6368	0.668	0.7560	0.668	0.6389	0.8967	0.8232	0.8023	0.6509	0.6842	0.8192	0.8149	0.1420	0.8670	0.0833	0.8916	0.4587	0.3132
0.9396	2.0	2000	0.8640	0.8688	0.8805	0.8778	0.8752	0.8688	0.8787	0.8688	0.8693	0.9773	0.7795	0.9427	0.7533	0.9003	0.9346	0.8932	0.8076	0.7635	0.8080	0.9163	0.9358	1.0
0.4896	3.0	3000	0.5016	0.917	0.9149	0.9287	0.9189	0.917	0.9244	0.917	0.9176	0.9793	0.7811	0.9370	0.9633	0.9086	0.9538	0.9466	0.8991	0.9704	0.8732	0.9163	0.9450	1.0
0.2993	4.0	4000	0.3596	0.9247	0.9222	0.9376	0.9271	0.9247	0.9312	0.9247	0.9252	0.9752	0.7879	0.9427	0.9790	0.9086	0.9615	0.9573	0.9148	0.9901	0.8877	0.9212	0.9633	1.0
0.2033	5.0	5000	0.2866	0.9363	0.9322	0.9479	0.9379	0.9363	0.9409	0.9363	0.9367	0.9711	0.8266	0.9513	0.9843	0.9086	0.9962	0.9715	0.9148	0.9901	0.9058	0.9212	0.9817	1.0
0.1484	6.0	6000	0.2518	0.9393	0.9343	0.9513	0.9406	0.9393	0.9437	0.9393	0.9397	0.9690	0.8300	0.9456	0.9843	0.9086	0.9962	0.9964	0.9180	1.0	0.9167	0.9212	0.9817	1.0
0.1321	7.0	7000	0.2310	0.9477	0.9410	0.9560	0.9469	0.9477	0.9503	0.9477	0.9481	0.9711	0.8822	0.9484	0.9843	0.9086	1.0	0.9964	0.9180	1.0	0.9167	0.9212	0.9817	1.0
0.1128	8.0	8000	0.2339	0.944	0.9379	0.9542	0.9442	0.944	0.9474	0.944	0.9443	0.9731	0.8535	0.9484	0.9843	0.9086	1.0	0.9964	0.9211	1.0	0.9167	0.9212	0.9817	1.0
0.1018	9.0	9000	0.2173	0.949	0.9417	0.9568	0.9476	0.949	0.9516	0.949	0.9493	0.9731	0.8872	0.9513	0.9843	0.9086	1.0	0.9964	0.9180	1.0	0.9167	0.9212	0.9817	1.0
0.1003	10.0	10000	0.2129	0.95	0.9426	0.9573	0.9484	0.95	0.9524	0.95	0.9503	0.9711	0.8956	0.9513	0.9843	0.9086	1.0	0.9964	0.9180	1.0	0.9167	0.9212	0.9817	1.0

Framework versions

Transformers 4.48.3
Pytorch 2.6.0+cu124
Datasets 3.3.0
Tokenizers 0.21.0

marcelovidigal/distilbert-base-multilingual-cased-2-contract-sections-classification-v4-10

distilbert-base-multilingual-cased-2-contract-sections-classification-v4-10

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

marcelovidigal/
distilbert-base-multilingual-cased-2-contract-sections-classification-v4-10