README.md

metadata

tags:
  - generated_from_trainer
datasets:
  - squad
model-index:
  - name: >-
      bert-base-turkish-128k-cased-finetuned_lr-2e-05_epochs-3TQUAD2-finetuned_lr-2e-05_epochs-1
    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: 15.4073
            verified: true
          - name: F1
            type: f1
            value: 23.4093
            verified: true

bert-base-turkish-128k-cased-finetuned_lr-2e-05_epochs-3TQUAD2-finetuned_lr-2e-05_epochs-1

This model is a fine-tuned version of husnu/bert-base-turkish-128k-cased-finetuned_lr-2e-05_epochs-3 on the squad dataset. It achieves the following results on the evaluation set:

• Loss: 1.4196

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

Training results

Training Loss	Epoch	Step	Validation Loss
0.5885	1.0	2245	1.4196

Framework versions

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