DeepSeek-R1-Distill-Qwen-1.5B-2-contract-sections-classification-v4-10

marcelovidigal/DeepSeek-R1-Distill-Qwen-1.5B-2-contract-sections-classification-v4-10

DeepSeek-R1-Distill-Qwen-1.5B-2-contract-sections-classification-v4-10 is a machine learning model from marcelovidigal. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as mit.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

12% of all-time downloads

All-time downloads

119

Public

Repo size

55.2 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.json11.4 MB · 72%

At a glance

Library: peft
License: mit
Access: Public
Created: Feb 20, 2025
Updated: Feb 20, 2025
SHA: 6029b456

Base models

deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B

Model card

From the Hugging Face model README

DeepSeek-R1-Distill-Qwen-1.5B-2-contract-sections-classification-v4-10

This model is a fine-tuned version of deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 2.5912
Accuracy Evaluate: 0.2065
Precision Evaluate: 0.2225
Recall Evaluate: 0.2011
F1 Evaluate: 0.2053
Accuracy Sklearn: 0.2065
Precision Sklearn: 0.2227
Recall Sklearn: 0.2065
F1 Sklearn: 0.2079
Acuracia Rotulo Objeto: 0.2355
Acuracia Rotulo Obrigacoes: 0.2290
Acuracia Rotulo Valor: 0.2808
Acuracia Rotulo Vigencia: 0.1969
Acuracia Rotulo Rescisao: 0.1939
Acuracia Rotulo Foro: 0.1538
Acuracia Rotulo Reajuste: 0.1886
Acuracia Rotulo Fiscalizacao: 0.0662
Acuracia Rotulo Publicacao: 0.3892
Acuracia Rotulo Pagamento: 0.0616
Acuracia Rotulo Casos Omissos: 0.5616
Acuracia Rotulo Sancoes: 0.0183
Acuracia Rotulo Dotacao Orcamentaria: 0.0385

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
mixed_precision_training: Native AMP

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
3.7843	1.0	1000	3.6004	0.0655	0.0875	0.0674	0.0486	0.0655	0.1125	0.0655	0.0557	0.0744	0.0337	0.1203	0.0394	0.0388	0.2923	0.0890	0.0032	0.0	0.0	0.0	0.0092	0.1758
3.235	2.0	2000	3.2248	0.0762	0.0869	0.0680	0.0601	0.0762	0.1029	0.0762	0.0721	0.1178	0.0825	0.1662	0.0787	0.0499	0.1731	0.0854	0.0063	0.0148	0.0109	0.0049	0.0275	0.0659
2.8811	3.0	3000	3.0158	0.125	0.1463	0.1190	0.1212	0.125	0.1467	0.125	0.1250	0.1426	0.1650	0.2407	0.1601	0.0471	0.1308	0.0569	0.0063	0.0148	0.0145	0.5074	0.0275	0.0330
2.681	4.0	4000	2.8826	0.1635	0.1933	0.1554	0.1597	0.1635	0.1936	0.1635	0.1638	0.1446	0.2323	0.2951	0.1601	0.1330	0.1077	0.1210	0.0568	0.1527	0.0145	0.5419	0.0275	0.0330
2.495	5.0	5000	2.7849	0.1777	0.1958	0.1675	0.1711	0.1777	0.1985	0.1777	0.1774	0.1612	0.2525	0.2980	0.1654	0.1801	0.1038	0.1423	0.0631	0.2020	0.0217	0.5419	0.0183	0.0275
2.3573	6.0	6000	2.7106	0.197	0.2106	0.1877	0.1907	0.197	0.2128	0.197	0.1963	0.2211	0.2576	0.2865	0.1680	0.1967	0.1077	0.1708	0.0662	0.3202	0.0326	0.5616	0.0183	0.0330
2.2544	7.0	7000	2.6566	0.201	0.2131	0.1950	0.1969	0.201	0.2139	0.201	0.2001	0.2231	0.2441	0.2865	0.1601	0.1911	0.1308	0.1851	0.0662	0.3842	0.0507	0.5616	0.0183	0.0330
2.198	8.0	8000	2.6198	0.2015	0.2157	0.1961	0.1994	0.2015	0.2156	0.2015	0.2019	0.2335	0.2357	0.2865	0.1549	0.1884	0.1423	0.1851	0.0662	0.3842	0.0543	0.5616	0.0183	0.0385
2.1718	9.0	9000	2.5984	0.206	0.2216	0.2004	0.2046	0.206	0.2219	0.206	0.2073	0.2335	0.2290	0.2808	0.2021	0.1939	0.15	0.1886	0.0662	0.3842	0.0580	0.5616	0.0183	0.0385
2.1267	10.0	10000	2.5912	0.2065	0.2225	0.2011	0.2053	0.2065	0.2227	0.2065	0.2079	0.2355	0.2290	0.2808	0.1969	0.1939	0.1538	0.1886	0.0662	0.3892	0.0616	0.5616	0.0183	0.0385

Framework versions

PEFT 0.14.0
Transformers 4.48.3
Pytorch 2.6.0+cu124
Datasets 3.3.0
Tokenizers 0.21.0

Library: peft
License: mit
Created: Feb 20, 2025
Updated: Feb 20, 2025