README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - squad
model-index:
  - name: distilbert-base-uncased-finetuned-squad-colab
    results:
      - task:
          type: question-answering
          name: Question Answering
        dataset:
          name: squad_v2
          type: squad_v2
          config: squad_v2
          split: validation
        metrics:
          - name: Exact Match
            type: exact_match
            value: 38.3909
            verified: true
          - name: F1
            type: f1
            value: 42.7051
            verified: true

distilbert-base-uncased-finetuned-squad-colab

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

• Loss: 1.1662

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: 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: 3

Training results

Training Loss	Epoch	Step	Validation Loss
1.2123	1.0	5533	1.1550
0.95	2.0	11066	1.1163
0.7539	3.0	16599	1.1662

Framework versions

• Transformers 4.18.0
• Pytorch 1.10.0+cu111
• Datasets 2.1.0
• Tokenizers 0.12.1