README.md

metadata

tags:
  - generated_from_trainer
datasets:
  - klue
metrics:
  - f1
model_index:
  - name: bert-base-finetuned-ynat
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: klue
          type: klue
          args: ynat
        metric:
          name: F1
          type: f1
          value: 0.8691323654981199

bert-base-finetuned-ynat

This model is a fine-tuned version of klue/bert-base on the klue dataset. It achieves the following results on the evaluation set:

• Loss: 0.3636
• F1: 0.8691

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	F1
0.4713	1.0	714	0.3839	0.8670
0.3157	2.0	1428	0.3636	0.8691
0.2153	3.0	2142	0.3837	0.8657
0.1839	4.0	2856	0.4168	0.8629
0.132	5.0	3570	0.4334	0.8680

Framework versions

• Transformers 4.9.1
• Pytorch 1.9.0+cu102
• Datasets 1.11.0
• Tokenizers 0.10.3