hw2942's picture
Upload tokenizer
cba89e4 verified
metadata
base_model: hfl/chinese-macbert-base
license: apache-2.0
metrics:
  - accuracy
tags:
  - generated_from_trainer
model-index:
  - name: chinese-macbert-base-climate-related-prediction-v4
    results: []

chinese-macbert-base-climate-related-prediction-v4

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: 0.2409
  • Accuracy: 0.97

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 1.0 175 0.1739 0.98
No log 2.0 350 0.6559 0.93
0.0168 3.0 525 0.1504 0.98
0.0168 4.0 700 0.2066 0.97
0.0168 5.0 875 0.2227 0.97
0.0 6.0 1050 0.2335 0.97
0.0 7.0 1225 0.2404 0.97
0.0 8.0 1400 0.2420 0.97
0.0 9.0 1575 0.2398 0.97
0.0 10.0 1750 0.2409 0.97

Framework versions

  • Transformers 4.42.4
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1