nbtpj's picture
update model card README.md
a4bf674
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - squad
model-index:
  - name: mc-bart-base-mqa-fine-tune
    results: []

mc-bart-base-mqa-fine-tune

This model is a fine-tuned version of facebook/bart-base on the squad dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8651

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: 5e-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: 1.8

Training results

Training Loss Epoch Step Validation Loss
0.6673 0.59 10000 0.8870
0.6969 1.18 20000 0.8651
0.6298 1.77 30000 0.8651

Framework versions

  • Transformers 4.20.1
  • Pytorch 1.11.0
  • Datasets 2.1.0
  • Tokenizers 0.12.1