ys7yoo's picture
update model card README.md
1fe19c6
metadata
tags:
  - generated_from_trainer
datasets:
  - klue
metrics:
  - accuracy
  - f1
model-index:
  - name: nli_sts_roberta-large_lr1e-05_wd1e-03_ep3_lr1e-05_wd1e-03_ep3_ckpt
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: klue
          type: klue
          config: nli
          split: validation
          args: nli
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.894
          - name: F1
            type: f1
            value: 0.8938576137169963

nli_sts_roberta-large_lr1e-05_wd1e-03_ep3_lr1e-05_wd1e-03_ep3_ckpt

This model is a fine-tuned version of ys7yoo/sts_roberta-large_lr1e-05_wd1e-03_ep3 on the klue dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3529
  • Accuracy: 0.894
  • F1: 0.8939

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: 1e-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
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss Accuracy F1
0.5292 1.0 391 0.3853 0.857 0.8565
0.2468 2.0 782 0.3176 0.89 0.8899
0.1412 3.0 1173 0.3529 0.894 0.8939

Framework versions

  • Transformers 4.30.2
  • Pytorch 2.0.1+cu117
  • Datasets 2.13.0
  • Tokenizers 0.13.3