susooo's picture
update model card README.md
88649ad
metadata
tags:
  - generated_from_trainer
datasets:
  - custom_squad_v2
model-index:
  - name: kobigbird-base28-47999573
    results: []

kobigbird-base28-47999573

This model is a fine-tuned version of monologg/kobigbird-bert-base on the custom_squad_v2 dataset. It achieves the following results on the evaluation set:

  • Loss: 1.4225

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: 0.0005
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 28
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 256
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • num_epochs: 2
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
No log 0.99 42 1.4312
No log 1.99 84 1.4225

Framework versions

  • Transformers 4.25.1
  • Pytorch 1.13.0+cu116
  • Datasets 2.8.0
  • Tokenizers 0.13.2