hw2942's picture
End of training
e965223
metadata
license: apache-2.0
base_model: hfl/chinese-macbert-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: chinese-macbert-base-wallstreetcn-morning-news-market-overview-SSEC-v6
    results: []

chinese-macbert-base-wallstreetcn-morning-news-market-overview-SSEC-v6

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

  • Loss: 1.4847
  • Accuracy: 0.7188

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 0.6893 0.4375
No log 2.0 68 0.6156 0.6562
No log 3.0 102 0.8698 0.6562
No log 4.0 136 0.6379 0.6562
No log 5.0 170 0.8517 0.7188
No log 6.0 204 1.1949 0.6875
No log 7.0 238 1.2695 0.6875
No log 8.0 272 1.3954 0.7188
No log 9.0 306 1.5019 0.6875
No log 10.0 340 1.4847 0.7188

Framework versions

  • Transformers 4.33.1
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.13.3