NinaXiao's picture
update model card README.md
be72528
metadata
license: apache-2.0
tags:
  - generated_from_trainer
model-index:
  - name: distilroberta-base-wiki-mark
    results: []

distilroberta-base-wiki-mark

This model is a fine-tuned version of distilroberta-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 2.0062

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: 3

Training results

Training Loss Epoch Step Validation Loss
2.2841 1.0 1265 2.0553
2.1536 2.0 2530 1.9840
2.1067 3.0 3795 1.9731

Framework versions

  • Transformers 4.20.1
  • Pytorch 1.12.0+cu113
  • Datasets 2.3.2
  • Tokenizers 0.12.1