thucnews / README.md
shed-e's picture
update model card README.md
bbc6910
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - load_train
metrics:
  - accuracy
model-index:
  - name: thucnews
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: load_train
          type: load_train
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9433

thucnews

This model is a fine-tuned version of hfl/rbt6 on the load_train dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3191
  • Accuracy: 0.9433

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: 0.0001
  • train_batch_size: 256
  • eval_batch_size: 256
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 8
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.2038 1.0 704 0.2018 0.9332
0.1403 2.0 1408 0.1829 0.9406
0.0894 3.0 2112 0.2073 0.9419
0.056 4.0 2816 0.2228 0.9408
0.0321 5.0 3520 0.2689 0.9417
0.0209 6.0 4224 0.2819 0.9431
0.0099 7.0 4928 0.3131 0.9421
0.0057 8.0 5632 0.3191 0.9433

Framework versions

  • Transformers 4.22.1
  • Pytorch 1.12.1+cu113
  • Datasets 2.5.1
  • Tokenizers 0.12.1