BERT-SA-LORA / README.md
Intradiction's picture
End of training
6208e96 verified
|
raw
history blame
1.94 kB
metadata
license: apache-2.0
library_name: peft
tags:
  - generated_from_trainer
metrics:
  - accuracy
base_model: bert-base-uncased
model-index:
  - name: BERT-SA-LORA
    results: []

BERT-SA-LORA

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: 0.3776
  • Accuracy: 0.873

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: 0.0002
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 125 0.5379 0.74
No log 2.0 250 0.4962 0.78
No log 3.0 375 0.4127 0.827
0.4731 4.0 500 0.3871 0.849
0.4731 5.0 625 0.3720 0.861
0.4731 6.0 750 0.4096 0.858
0.4731 7.0 875 0.3971 0.869
0.2887 8.0 1000 0.3856 0.868
0.2887 9.0 1125 0.3751 0.872
0.2887 10.0 1250 0.3776 0.873

Framework versions

  • PEFT 0.9.0
  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2