Hugging Face's logo

mrp
/
bert-finetuned-squad

Question Answering
Transformers
PyTorch
TensorBoard
bert
generated_from_trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
5
bert-finetuned-squad / README.md
mrp's picture
mrp
Add evaluation results on the plain_text config of squad (#2)
75831fb
preview code
|
raw history blame contribute delete
No virus
1.52 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - squad
model-index:
  - name: bert-finetuned-squad
    results:
      - task:
          type: question-answering
          name: Question Answering
        dataset:
          name: squad
          type: squad
          config: plain_text
          split: validation
        metrics:
          - name: Loss
            type: loss
            value: 1.073493242263794
            verified: true
          - name: Exact Match
            type: exact_match
            value: 80.0853
            verified: true
          - name: F1
            type: f1
            value: 87.606
            verified: true

bert-finetuned-squad

This model is a fine-tuned version of bert-base-cased on the squad dataset.

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: 1
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • Transformers 4.15.0
  • Pytorch 1.10.0+cu111
  • Datasets 1.17.0
  • Tokenizers 0.10.3