Hugging Face's logo

hw2942
/
mengzi-bert-base-fin-SSE50

Text Classification
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
mengzi-bert-base-fin-SSE50 / README.md
hw2942's picture
hw2942
End of training
160b24d
preview code
|
raw
history blame contribute delete
2.06 kB
metadata
license: apache-2.0
base_model: Langboat/mengzi-bert-base-fin
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: mengzi-bert-base-fin-wallstreetcn-morning-news-market-overview-SSE50-12
    results: []

mengzi-bert-base-fin-wallstreetcn-morning-news-market-overview-SSE50-12

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

  • Loss: 1.9118
  • Accuracy: 0.7273

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 1.4376 0.6364
No log 2.0 68 2.2371 0.6364
No log 3.0 102 2.0078 0.6364
No log 4.0 136 2.2167 0.6970
No log 5.0 170 1.3631 0.7576
No log 6.0 204 1.6997 0.6970
No log 7.0 238 1.4750 0.7576
No log 8.0 272 1.8849 0.7273
No log 9.0 306 1.8603 0.7273
No log 10.0 340 1.9118 0.7273

Framework versions

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