mlxen's picture
Add evaluation results on the squad_v2 config and validation split of squad_v2 (#1)
b09f6b6
|
raw
history blame
2.34 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - squad
model-index:
  - name: electra-smallcase-squad
    results:
      - task:
          type: question-answering
          name: Question Answering
        dataset:
          name: squad_v2
          type: squad_v2
          config: squad_v2
          split: validation
        metrics:
          - type: f1
            value: 42.535
            name: F1
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNGYwZjExOTg1NGMwMTQxZGVhMjU4NzJiZTBlM2EzZDNmMzBlMGEzNjMwZjkzMTIxOTQzYWFhYjBiZDZhNTAxYSIsInZlcnNpb24iOjF9.PMOlW_iXGS5QjV0XCs4e5AK-ip9LUdXoDKRxFc7-VM_QMhGc0eq7GGLiY6OXCt-WUwRy6RkFhIg2nzid_qMgDw
          - type: exact
            value: 38.3889
            name: Exact Match
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMWIwNGVhYmIyNmUyNzkzMzA1Y2FkMDJmNzE3ZGNlOWNlNjk2Y2IwOTA5MjJkMmEwMmVhNjNkZWU1YTJhN2ViMiIsInZlcnNpb24iOjF9.S6L-PB3ZfllrXwHMfiSMDQm-tLANrBeWrNNekvfX1aZA79hbKdgP-OGPKatMatGJPirs-zPWDYXEIH4pSZeODw
          - type: loss
            value: 6.50607442855835
            name: loss
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZWFlOWNjOTUzMTBkMDc3MDRmYmUwNzk2NjY3MmJjOTNjMWM2NGZmMDY5MTY0MWIwOTIyNWM5ZDkzNmEwNTJkNiIsInZlcnNpb24iOjF9.wxm8AMY3iCdRD3_cZIJ8zLzUh5Cj7C3k4vCoy0raXOExLIYFs4qSRWxFaI21HCJ8NhZ0IirV5ziaTpSRsPlqAw

electra-smallcase-squad

This model is a fine-tuned version of google/electra-small-discriminator 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: 3
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • Transformers 4.24.0
  • Pytorch 1.12.1+cu113
  • Datasets 2.7.1
  • Tokenizers 0.13.2