README.md

metadata

tags:
  - generated_from_trainer
datasets:
  - Graphcore/gqa-lxmert
metrics:
  - accuracy
model-index:
  - name: gqa
    results:
      - task:
          name: Question Answering
          type: question-answering
        dataset:
          name: Graphcore/gqa-lxmert
          type: Graphcore/gqa-lxmert
          args: gqa
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.5933514030612245

gqa

This model is a fine-tuned version of unc-nlp/lxmert-base-uncased on the Graphcore/gqa-lxmert dataset. It achieves the following results on the evaluation set:

• Loss: 1.9326
• Accuracy: 0.5934

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: 1e-05
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• distributed_type: IPU
• total_train_batch_size: 64
• total_eval_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 4.0
• training precision: Mixed Precision

Training results

Framework versions

• Transformers 4.18.0.dev0
• Pytorch 1.10.0+cpu
• Datasets 2.0.0
• Tokenizers 0.11.6