yayima's picture
update model card README.md
c046a04
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - cmrc2018
model-index:
  - name: my_awesome_qa_cmrc2018_model
    results: []

my_awesome_qa_cmrc2018_model

This model is a fine-tuned version of hfl/chinese-pert-base-mrc on the cmrc2018 dataset. It achieves the following results on the evaluation set:

  • Loss: 1.5397

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: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss
0.8593 1.0 634 1.2136
0.6411 2.0 1268 1.3501
0.4974 3.0 1902 1.5397

Framework versions

  • Transformers 4.29.2
  • Pytorch 2.0.1+cu117
  • Datasets 2.15.0
  • Tokenizers 0.13.3