bert-text-classification-final

This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0230
  • Accuracy: 0.9948
  • F1: 0.9929
  • Precision: 0.9935
  • Recall: 0.9924

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: 2e-05
  • train_batch_size: 16
  • eval_batch_size: 64
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 32
  • 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
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 5
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Precision Recall
0.5435 0.1166 100 0.4252 0.8876 0.8584 0.8010 0.9245
0.1382 0.2331 200 0.2558 0.9086 0.8891 0.8041 0.9940
0.0937 0.3497 300 0.1737 0.951 0.9372 0.8882 0.9919
0.0497 0.4662 400 0.1764 0.9546 0.9416 0.8945 0.9940
0.0712 0.5828 500 0.0430 0.9878 0.9835 0.9785 0.9886
0.0384 0.6993 600 0.0774 0.9822 0.9762 0.9606 0.9924
0.0433 0.8159 700 0.3870 0.9208 0.9028 0.8242 0.9978
0.0191 0.9324 800 0.0224 0.995 0.9932 0.9989 0.9875
0.0194 1.0490 900 0.0444 0.9914 0.9884 0.9833 0.9935
0.0142 1.1655 1000 0.1037 0.9818 0.9758 0.9577 0.9946
0.0216 1.2821 1100 0.0230 0.9948 0.9929 0.9935 0.9924

Framework versions

  • Transformers 4.51.3
  • Pytorch 2.7.0+cu126
  • Datasets 3.5.1
  • Tokenizers 0.21.1
Downloads last month
1
Safetensors
Model size
0.1B params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for bprhee01/bert-text-classification-final

Finetuned
(7,256)
this model