lora_training / README.md
desdesmond's picture
Update README.md
d845307 verified
metadata
library_name: peft
license: apache-2.0
base_model:
  - ykacer/bert-base-cased-imdb-sequence-classification
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: lora_training
    results: []
language:
  - en
pipeline_tag: token-classification

lora_training

This model is a fine-tuned version of ykacer/bert-base-cased-imdb-sequence-classification on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0969
  • Accuracy: 0.5975

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: 16
  • seed: 42
  • optimizer: Use 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

Training results

Training Loss Epoch Step Validation Loss Accuracy
1.6038 1.0 800 1.5082 0.4547
1.305 2.0 1600 1.2096 0.5466
1.1727 3.0 2400 1.1352 0.5775
1.1199 4.0 3200 1.1062 0.5947
1.0959 5.0 4000 1.0969 0.5975

Framework versions

  • PEFT 0.13.2
  • Transformers 4.46.2
  • Pytorch 2.5.0+cu121
  • Datasets 3.1.0
  • Tokenizers 0.20.3