Hugging Face's logo

marcelovidigal
/
deepseek-llm-7b-base-2-contract-sections-classification-v4

PEFT
Safetensors
Generated from Trainer
Model card Files Community
deepseek-llm-7b-base-2-contract-sections-classification-v4 / README.md
marcelovidigal's picture
marcelovidigal
marcelovidigal/deepseek-llm-7b-base-2-contract-sections-classification-v4
0f8bb54 verified
preview code
|
raw
history blame contribute delete
6.46 kB
metadata
library_name: peft
license: other
base_model: deepseek-ai/deepseek-llm-7b-base
tags:
  - generated_from_trainer
model-index:
  - name: deepseek-llm-7b-base-2-contract-sections-classification-v4
    results: []

Visualize in Weights & Biases Visualize in Weights & Biases

deepseek-llm-7b-base-2-contract-sections-classification-v4

This model is a fine-tuned version of deepseek-ai/deepseek-llm-7b-base on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 2.6235
  • Accuracy Evaluate: 0.13
  • Precision Evaluate: 0.0501
  • Recall Evaluate: 0.0633
  • F1 Evaluate: 0.0303
  • Accuracy Sklearn: 0.13
  • Precision Sklearn: 0.0410
  • Recall Sklearn: 0.13
  • F1 Sklearn: 0.0475
  • Acuracia Rotulo Objeto: 0.0
  • Acuracia Rotulo Obrigacoes: 0.7391
  • Acuracia Rotulo Valor: 0.0
  • Acuracia Rotulo Vigencia: 0.0
  • Acuracia Rotulo Rescisao: 0.0
  • Acuracia Rotulo Foro: 0.0
  • Acuracia Rotulo Reajuste: 0.0
  • Acuracia Rotulo Fiscalizacao: 0.0
  • Acuracia Rotulo Publicacao: 0.0
  • Acuracia Rotulo Pagamento: 0.0
  • Acuracia Rotulo Casos Omissos: 0.0
  • Acuracia Rotulo Sancoes: 0.0833
  • Acuracia Rotulo Dotacao Orcamentaria: 0.0

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: 5
  • 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
No log 1.0 125 2.6317 0.13 0.0502 0.0633 0.0305 0.13 0.0413 0.13 0.0479 0.0 0.7391 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0833 0.0
No log 2.0 250 2.6288 0.13 0.0502 0.0633 0.0304 0.13 0.0413 0.13 0.0478 0.0 0.7391 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0833 0.0
No log 3.0 375 2.6261 0.13 0.0501 0.0633 0.0303 0.13 0.0411 0.13 0.0476 0.0 0.7391 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0833 0.0
2.6801 4.0 500 2.6242 0.13 0.0501 0.0633 0.0304 0.13 0.0412 0.13 0.0477 0.0 0.7391 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0833 0.0
2.6801 5.0 625 2.6235 0.13 0.0501 0.0633 0.0303 0.13 0.0410 0.13 0.0475 0.0 0.7391 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0833 0.0

Framework versions

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