hw2942's picture
End of training
e865ae4
metadata
base_model: bert-base-chinese
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: bert-base-chinese-wallstreetcn-morning-news-market-overview-SSE50-v1
    results: []

bert-base-chinese-wallstreetcn-morning-news-market-overview-SSE50-v1

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

  • Loss: 0.7025
  • Accuracy: 0.7879

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: 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 34 0.7253 0.3939
No log 2.0 68 0.6520 0.6061
No log 3.0 102 0.6079 0.6970
No log 4.0 136 0.5872 0.6667
No log 5.0 170 0.4618 0.7879
No log 6.0 204 0.4237 0.7879
No log 7.0 238 0.6489 0.6667
No log 8.0 272 0.5943 0.8182
No log 9.0 306 0.7921 0.7879
No log 10.0 340 0.7025 0.7879

Framework versions

  • Transformers 4.33.2
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.13.3