hilco's picture
Finished training.
2916aac verified
metadata
library_name: peft
tags:
  - parquet
  - text-classification
datasets:
  - ag_news
metrics:
  - accuracy
base_model: dhimskyy/wiki-bert
model-index:
  - name: dhimskyy_wiki-bert-finetuned-lora-ag_news
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: ag_news
          type: ag_news
          config: default
          split: test
          args: default
        metrics:
          - type: accuracy
            value: 0.8444736842105263
            name: accuracy

dhimskyy_wiki-bert-finetuned-lora-ag_news

This model is a fine-tuned version of dhimskyy/wiki-bert on the ag_news dataset. It achieves the following results on the evaluation set:

  • accuracy: 0.8445

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: 0.0004
  • train_batch_size: 24
  • eval_batch_size: 24
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 4

Training results

accuracy train_loss epoch
0.2471 None 0
0.8059 0.7762 0
0.8304 0.5563 1
0.8430 0.5109 2
0.8445 0.4907 3

Framework versions

  • PEFT 0.8.2
  • Transformers 4.37.2
  • Pytorch 2.2.0
  • Datasets 2.16.1
  • Tokenizers 0.15.2